From 177b49dbf9c1d8f9f25a22ffafa416fc2c8aa6a3 Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Wed, 3 Jul 2024 17:40:49 +0300
Subject: wifi: ath11k: use work queue to process beacon tx event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 3a415daa3e8b ("wifi: ath11k: add P2P IE in beacon template")
from Feb 28, 2024 (linux-next), leads to the following Smatch static
checker warning:

drivers/net/wireless/ath/ath11k/wmi.c:1742 ath11k_wmi_p2p_go_bcn_ie()
warn: sleeping in atomic context

The reason is that ath11k_bcn_tx_status_event() will directly call might
sleep function ath11k_wmi_cmd_send() during RCU read-side critical
sections. The call trace is like:

ath11k_bcn_tx_status_event()
-> rcu_read_lock()
-> ath11k_mac_bcn_tx_event()
	-> ath11k_mac_setup_bcn_tmpl()
	……
		-> ath11k_wmi_bcn_tmpl()
			-> ath11k_wmi_cmd_send()
-> rcu_read_unlock()

Commit 886433a98425 ("ath11k: add support for BSS color change") added the
ath11k_mac_bcn_tx_event(), commit 01e782c89108 ("ath11k: fix warning
of RCU usage for ath11k_mac_get_arvif_by_vdev_id()") added the RCU lock
to avoid warning but also introduced this BUG.

Use work queue to avoid directly calling ath11k_mac_bcn_tx_event()
during RCU critical sections. No need to worry about the deletion of vif
because cancel_work_sync() will drop the work if it doesn't start or
block vif deletion until the running work is done.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30

Fixes: 3a415daa3e8b ("wifi: ath11k: add P2P IE in beacon template")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/2d277abd-5e7b-4da0-80e0-52bd96337f6e@moroto.mountain/
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240626053543.1946-1-quic_kangyang@quicinc.com
---
 drivers/net/wireless/ath/ath11k/core.h |  1 +
 drivers/net/wireless/ath/ath11k/mac.c  | 12 ++++++++++++
 drivers/net/wireless/ath/ath11k/wmi.c  |  4 +++-
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index df24f0e409af..7122176dd91e 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -399,6 +399,7 @@ struct ath11k_vif {
 	u8 bssid[ETH_ALEN];
 	struct cfg80211_bitrate_mask bitrate_mask;
 	struct delayed_work connection_loss_work;
+	struct work_struct bcn_tx_work;
 	int num_legacy_stations;
 	int rtscts_prot_mode;
 	int txpower;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index ba910ae2c676..71ef89be823b 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -6599,6 +6599,16 @@ static int ath11k_mac_vdev_delete(struct ath11k *ar, struct ath11k_vif *arvif)
 	return ret;
 }
 
+static void ath11k_mac_bcn_tx_work(struct work_struct *work)
+{
+	struct ath11k_vif *arvif = container_of(work, struct ath11k_vif,
+						bcn_tx_work);
+
+	mutex_lock(&arvif->ar->conf_mutex);
+	ath11k_mac_bcn_tx_event(arvif);
+	mutex_unlock(&arvif->ar->conf_mutex);
+}
+
 static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 				       struct ieee80211_vif *vif)
 {
@@ -6637,6 +6647,7 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
 	arvif->vif = vif;
 
 	INIT_LIST_HEAD(&arvif->list);
+	INIT_WORK(&arvif->bcn_tx_work, ath11k_mac_bcn_tx_work);
 	INIT_DELAYED_WORK(&arvif->connection_loss_work,
 			  ath11k_mac_vif_sta_connection_loss_work);
 
@@ -6879,6 +6890,7 @@ static void ath11k_mac_op_remove_interface(struct ieee80211_hw *hw,
 	int i;
 
 	cancel_delayed_work_sync(&arvif->connection_loss_work);
+	cancel_work_sync(&arvif->bcn_tx_work);
 
 	mutex_lock(&ar->conf_mutex);
 
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 38f175dd1557..2662092ee00a 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -7404,7 +7404,9 @@ static void ath11k_bcn_tx_status_event(struct ath11k_base *ab, struct sk_buff *s
 		rcu_read_unlock();
 		return;
 	}
-	ath11k_mac_bcn_tx_event(arvif);
+
+	queue_work(ab->workqueue, &arvif->bcn_tx_work);
+
 	rcu_read_unlock();
 }
 
-- 
cgit v1.3-3-g829e


From e106b7ad13c1d246adaa57df73edb8f8b8acb240 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 4 Jul 2024 12:38:10 +0530
Subject: wifi: ath12k: fix array out-of-bound access in SoC stats

Currently, the ath12k_soc_dp_stats::hal_reo_error array is defined with a
maximum size of DP_REO_DST_RING_MAX. However, the ath12k_dp_rx_process()
function access ath12k_soc_dp_stats::hal_reo_error using the REO
destination SRNG ring ID, which is incorrect. SRNG ring ID differ from
normal ring ID, and this usage leads to out-of-bounds array access. To
fix this issue, modify ath12k_dp_rx_process() to use the normal ring ID
directly instead of the SRNG ring ID to avoid out-of-bounds array access.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240704070811.4186543-2-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 14236d0a0c89..91e3393f7b5f 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2681,7 +2681,7 @@ try_again:
 		if (push_reason !=
 		    HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION) {
 			dev_kfree_skb_any(msdu);
-			ab->soc_stats.hal_reo_error[dp->reo_dst_ring[ring_id].ring_id]++;
+			ab->soc_stats.hal_reo_error[ring_id]++;
 			continue;
 		}
 
-- 
cgit v1.3-3-g829e


From 69f253e46af98af17e3efa3e5dfa72fcb7d1983d Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 4 Jul 2024 12:38:11 +0530
Subject: wifi: ath11k: fix array out-of-bound access in SoC stats

Currently, the ath11k_soc_dp_stats::hal_reo_error array is defined with a
maximum size of DP_REO_DST_RING_MAX. However, the ath11k_dp_process_rx()
function access ath11k_soc_dp_stats::hal_reo_error using the REO
destination SRNG ring ID, which is incorrect. SRNG ring ID differ from
normal ring ID, and this usage leads to out-of-bounds array access. To fix
this issue, modify ath11k_dp_process_rx() to use the normal ring ID
directly instead of the SRNG ring ID to avoid out-of-bounds array access.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240704070811.4186543-3-quic_periyasa@quicinc.com
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 86485580dd89..c087d8a0f5b2 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -2697,7 +2697,7 @@ try_again:
 		if (unlikely(push_reason !=
 			     HAL_REO_DEST_RING_PUSH_REASON_ROUTING_INSTRUCTION)) {
 			dev_kfree_skb_any(msdu);
-			ab->soc_stats.hal_reo_error[dp->reo_dst_ring[ring_id].ring_id]++;
+			ab->soc_stats.hal_reo_error[ring_id]++;
 			continue;
 		}
 
-- 
cgit v1.3-3-g829e


From 04aee7a847795ff64d4a5fab285dd2764ff22b85 Mon Sep 17 00:00:00 2001
From: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Date: Thu, 4 Jul 2024 14:35:35 +0530
Subject: wifi: ath12k: Support Transmit DE stats

Add support to request transmit DE stats from firmware through HTT stats
type 8. These stats give information about enqueued packets, discarded
packets, failed packets and other information such as power, bandwidth
information, number of retries, etc.

Sample output:
-------------
echo 8 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats
HTT_TX_DE_CMN_STATS_TLV:
mac_id = 0
tcl2fw_entry_count = 0
not_to_fw = 0
.....

HTT_TX_DE_EAPOL_PACKETS_STATS_TLV:
m1_packets = 0
m2_packets = 0
m3_packets = 0
.....

HTT_TX_DE_CLASSIFY_STATS_TLV:
arp_packets = 0
igmp_packets = 0
dhcp_packets = 0
.....

HTT_TX_DE_CLASSIFY_FAILED_STATS_TLV:
ap_bss_peer_not_found = 0
ap_bcast_mcast_no_peer = 0
sta_delete_in_progress = 0
.....

HTT_TX_DE_CLASSIFY_STATUS_STATS_TLV:
eok = 0
classify_done = 0
lookup_failed = 0
.....

HTT_TX_DE_ENQUEUE_PACKETS_STATS_TLV:
enqueued_pkts = 0
to_tqm = 0
to_tqm_bypass = 0

HTT_TX_DE_ENQUEUE_DISCARD_STATS_TLV:
discarded_pkts = 0
local_frames = 0
is_ext_msdu = 0

HTT_TX_DE_COMPL_STATS_TLV:
tcl_dummy_frame = 0
tqm_dummy_frame = 0
tqm_notify_frame = 0
.....

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240704090535.827680-1-quic_rdevanat@quicinc.com
---
 .../net/wireless/ath/ath12k/debugfs_htt_stats.c    | 354 +++++++++++++++++++++
 .../net/wireless/ath/ath12k/debugfs_htt_stats.h    | 126 ++++++++
 2 files changed, 480 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index ce80e7b5175b..f1b7e74aefe4 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -1117,6 +1117,336 @@ ath12k_htt_print_tx_tqm_pdev_stats_tlv(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static void
+ath12k_htt_print_tx_de_cmn_stats_tlv(const void *tag_buf, u16 tag_len,
+				     struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_cmn_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 mac_id_word;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	mac_id_word = __le32_to_cpu(htt_stats_buf->mac_id__word);
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_TX_DE_CMN_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n",
+			 u32_get_bits(mac_id_word, ATH12K_HTT_STATS_MAC_ID));
+	len += scnprintf(buf + len, buf_len - len, "tcl2fw_entry_count = %u\n",
+			 le32_to_cpu(htt_stats_buf->tcl2fw_entry_count));
+	len += scnprintf(buf + len, buf_len - len, "not_to_fw = %u\n",
+			 le32_to_cpu(htt_stats_buf->not_to_fw));
+	len += scnprintf(buf + len, buf_len - len, "invalid_pdev_vdev_peer = %u\n",
+			 le32_to_cpu(htt_stats_buf->invalid_pdev_vdev_peer));
+	len += scnprintf(buf + len, buf_len - len, "tcl_res_invalid_addrx = %u\n",
+			 le32_to_cpu(htt_stats_buf->tcl_res_invalid_addrx));
+	len += scnprintf(buf + len, buf_len - len, "wbm2fw_entry_count = %u\n",
+			 le32_to_cpu(htt_stats_buf->wbm2fw_entry_count));
+	len += scnprintf(buf + len, buf_len - len, "invalid_pdev = %u\n",
+			 le32_to_cpu(htt_stats_buf->invalid_pdev));
+	len += scnprintf(buf + len, buf_len - len, "tcl_res_addrx_timeout = %u\n",
+			 le32_to_cpu(htt_stats_buf->tcl_res_addrx_timeout));
+	len += scnprintf(buf + len, buf_len - len, "invalid_vdev = %u\n",
+			 le32_to_cpu(htt_stats_buf->invalid_vdev));
+	len += scnprintf(buf + len, buf_len - len, "invalid_tcl_exp_frame_desc = %u\n",
+			 le32_to_cpu(htt_stats_buf->invalid_tcl_exp_frame_desc));
+	len += scnprintf(buf + len, buf_len - len, "vdev_id_mismatch_count = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->vdev_id_mismatch_cnt));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_eapol_packets_stats_tlv(const void *tag_buf, u16 tag_len,
+					       struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_eapol_packets_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_TX_DE_EAPOL_PACKETS_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "m1_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->m1_packets));
+	len += scnprintf(buf + len, buf_len - len, "m2_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->m2_packets));
+	len += scnprintf(buf + len, buf_len - len, "m3_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->m3_packets));
+	len += scnprintf(buf + len, buf_len - len, "m4_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->m4_packets));
+	len += scnprintf(buf + len, buf_len - len, "g1_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->g1_packets));
+	len += scnprintf(buf + len, buf_len - len, "g2_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->g2_packets));
+	len += scnprintf(buf + len, buf_len - len, "rc4_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->rc4_packets));
+	len += scnprintf(buf + len, buf_len - len, "eap_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->eap_packets));
+	len += scnprintf(buf + len, buf_len - len, "eapol_start_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->eapol_start_packets));
+	len += scnprintf(buf + len, buf_len - len, "eapol_logoff_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->eapol_logoff_packets));
+	len += scnprintf(buf + len, buf_len - len, "eapol_encap_asf_packets = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->eapol_encap_asf_packets));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_classify_stats_tlv(const void *tag_buf, u16 tag_len,
+					  struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_classify_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_TX_DE_CLASSIFY_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "arp_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->arp_packets));
+	len += scnprintf(buf + len, buf_len - len, "igmp_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->igmp_packets));
+	len += scnprintf(buf + len, buf_len - len, "dhcp_packets = %u\n",
+			 le32_to_cpu(htt_stats_buf->dhcp_packets));
+	len += scnprintf(buf + len, buf_len - len, "host_inspected = %u\n",
+			 le32_to_cpu(htt_stats_buf->host_inspected));
+	len += scnprintf(buf + len, buf_len - len, "htt_included = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_included));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_mcs = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_mcs));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_nss = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_nss));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_preamble_type = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_preamble_type));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_chainmask = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_chainmask));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_guard_interval = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_guard_interval));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_retries = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_retries));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_bw_info = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_bw_info));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_power = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_power));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_key_flags = 0x%x\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_key_flags));
+	len += scnprintf(buf + len, buf_len - len, "htt_valid_no_encryption = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_valid_no_encryption));
+	len += scnprintf(buf + len, buf_len - len, "fse_entry_count = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_entry_count));
+	len += scnprintf(buf + len, buf_len - len, "fse_priority_be = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_priority_be));
+	len += scnprintf(buf + len, buf_len - len, "fse_priority_high = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_priority_high));
+	len += scnprintf(buf + len, buf_len - len, "fse_priority_low = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_priority_low));
+	len += scnprintf(buf + len, buf_len - len, "fse_traffic_ptrn_be = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_traffic_ptrn_be));
+	len += scnprintf(buf + len, buf_len - len, "fse_traffic_ptrn_over_sub = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_traffic_ptrn_over_sub));
+	len += scnprintf(buf + len, buf_len - len, "fse_traffic_ptrn_bursty = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_traffic_ptrn_bursty));
+	len += scnprintf(buf + len, buf_len - len, "fse_traffic_ptrn_interactive = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_traffic_ptrn_interactive));
+	len += scnprintf(buf + len, buf_len - len, "fse_traffic_ptrn_periodic = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_traffic_ptrn_periodic));
+	len += scnprintf(buf + len, buf_len - len, "fse_hwqueue_alloc = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_hwqueue_alloc));
+	len += scnprintf(buf + len, buf_len - len, "fse_hwqueue_created = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_hwqueue_created));
+	len += scnprintf(buf + len, buf_len - len, "fse_hwqueue_send_to_host = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_hwqueue_send_to_host));
+	len += scnprintf(buf + len, buf_len - len, "mcast_entry = %u\n",
+			 le32_to_cpu(htt_stats_buf->mcast_entry));
+	len += scnprintf(buf + len, buf_len - len, "bcast_entry = %u\n",
+			 le32_to_cpu(htt_stats_buf->bcast_entry));
+	len += scnprintf(buf + len, buf_len - len, "htt_update_peer_cache = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_update_peer_cache));
+	len += scnprintf(buf + len, buf_len - len, "htt_learning_frame = %u\n",
+			 le32_to_cpu(htt_stats_buf->htt_learning_frame));
+	len += scnprintf(buf + len, buf_len - len, "fse_invalid_peer = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_invalid_peer));
+	len += scnprintf(buf + len, buf_len - len, "mec_notify = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->mec_notify));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_classify_failed_stats_tlv(const void *tag_buf, u16 tag_len,
+						 struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_classify_failed_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_TX_DE_CLASSIFY_FAILED_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "ap_bss_peer_not_found = %u\n",
+			 le32_to_cpu(htt_stats_buf->ap_bss_peer_not_found));
+	len += scnprintf(buf + len, buf_len - len, "ap_bcast_mcast_no_peer = %u\n",
+			 le32_to_cpu(htt_stats_buf->ap_bcast_mcast_no_peer));
+	len += scnprintf(buf + len, buf_len - len, "sta_delete_in_progress = %u\n",
+			 le32_to_cpu(htt_stats_buf->sta_delete_in_progress));
+	len += scnprintf(buf + len, buf_len - len, "ibss_no_bss_peer = %u\n",
+			 le32_to_cpu(htt_stats_buf->ibss_no_bss_peer));
+	len += scnprintf(buf + len, buf_len - len, "invalid_vdev_type = %u\n",
+			 le32_to_cpu(htt_stats_buf->invalid_vdev_type));
+	len += scnprintf(buf + len, buf_len - len, "invalid_ast_peer_entry = %u\n",
+			 le32_to_cpu(htt_stats_buf->invalid_ast_peer_entry));
+	len += scnprintf(buf + len, buf_len - len, "peer_entry_invalid = %u\n",
+			 le32_to_cpu(htt_stats_buf->peer_entry_invalid));
+	len += scnprintf(buf + len, buf_len - len, "ethertype_not_ip = %u\n",
+			 le32_to_cpu(htt_stats_buf->ethertype_not_ip));
+	len += scnprintf(buf + len, buf_len - len, "eapol_lookup_failed = %u\n",
+			 le32_to_cpu(htt_stats_buf->eapol_lookup_failed));
+	len += scnprintf(buf + len, buf_len - len, "qpeer_not_allow_data = %u\n",
+			 le32_to_cpu(htt_stats_buf->qpeer_not_allow_data));
+	len += scnprintf(buf + len, buf_len - len, "fse_tid_override = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_tid_override));
+	len += scnprintf(buf + len, buf_len - len, "ipv6_jumbogram_zero_length = %u\n",
+			 le32_to_cpu(htt_stats_buf->ipv6_jumbogram_zero_length));
+	len += scnprintf(buf + len, buf_len - len, "qos_to_non_qos_in_prog = %u\n",
+			 le32_to_cpu(htt_stats_buf->qos_to_non_qos_in_prog));
+	len += scnprintf(buf + len, buf_len - len, "ap_bcast_mcast_eapol = %u\n",
+			 le32_to_cpu(htt_stats_buf->ap_bcast_mcast_eapol));
+	len += scnprintf(buf + len, buf_len - len, "unicast_on_ap_bss_peer = %u\n",
+			 le32_to_cpu(htt_stats_buf->unicast_on_ap_bss_peer));
+	len += scnprintf(buf + len, buf_len - len, "ap_vdev_invalid = %u\n",
+			 le32_to_cpu(htt_stats_buf->ap_vdev_invalid));
+	len += scnprintf(buf + len, buf_len - len, "incomplete_llc = %u\n",
+			 le32_to_cpu(htt_stats_buf->incomplete_llc));
+	len += scnprintf(buf + len, buf_len - len, "eapol_duplicate_m3 = %u\n",
+			 le32_to_cpu(htt_stats_buf->eapol_duplicate_m3));
+	len += scnprintf(buf + len, buf_len - len, "eapol_duplicate_m4 = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->eapol_duplicate_m4));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_classify_status_stats_tlv(const void *tag_buf, u16 tag_len,
+						 struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_classify_status_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_TX_DE_CLASSIFY_STATUS_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "eok = %u\n",
+			 le32_to_cpu(htt_stats_buf->eok));
+	len += scnprintf(buf + len, buf_len - len, "classify_done = %u\n",
+			 le32_to_cpu(htt_stats_buf->classify_done));
+	len += scnprintf(buf + len, buf_len - len, "lookup_failed = %u\n",
+			 le32_to_cpu(htt_stats_buf->lookup_failed));
+	len += scnprintf(buf + len, buf_len - len, "send_host_dhcp = %u\n",
+			 le32_to_cpu(htt_stats_buf->send_host_dhcp));
+	len += scnprintf(buf + len, buf_len - len, "send_host_mcast = %u\n",
+			 le32_to_cpu(htt_stats_buf->send_host_mcast));
+	len += scnprintf(buf + len, buf_len - len, "send_host_unknown_dest = %u\n",
+			 le32_to_cpu(htt_stats_buf->send_host_unknown_dest));
+	len += scnprintf(buf + len, buf_len - len, "send_host = %u\n",
+			 le32_to_cpu(htt_stats_buf->send_host));
+	len += scnprintf(buf + len, buf_len - len, "status_invalid = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->status_invalid));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_enqueue_packets_stats_tlv(const void *tag_buf, u16 tag_len,
+						 struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_enqueue_packets_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_TX_DE_ENQUEUE_PACKETS_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "enqueued_pkts = %u\n",
+			 le32_to_cpu(htt_stats_buf->enqueued_pkts));
+	len += scnprintf(buf + len, buf_len - len, "to_tqm = %u\n",
+			 le32_to_cpu(htt_stats_buf->to_tqm));
+	len += scnprintf(buf + len, buf_len - len, "to_tqm_bypass = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->to_tqm_bypass));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_enqueue_discard_stats_tlv(const void *tag_buf, u16 tag_len,
+						 struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_enqueue_discard_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_TX_DE_ENQUEUE_DISCARD_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "discarded_pkts = %u\n",
+			 le32_to_cpu(htt_stats_buf->discarded_pkts));
+	len += scnprintf(buf + len, buf_len - len, "local_frames = %u\n",
+			 le32_to_cpu(htt_stats_buf->local_frames));
+	len += scnprintf(buf + len, buf_len - len, "is_ext_msdu = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->is_ext_msdu));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_tx_de_compl_stats_tlv(const void *tag_buf, u16 tag_len,
+				       struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_de_compl_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_TX_DE_COMPL_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "tcl_dummy_frame = %u\n",
+			 le32_to_cpu(htt_stats_buf->tcl_dummy_frame));
+	len += scnprintf(buf + len, buf_len - len, "tqm_dummy_frame = %u\n",
+			 le32_to_cpu(htt_stats_buf->tqm_dummy_frame));
+	len += scnprintf(buf + len, buf_len - len, "tqm_notify_frame = %u\n",
+			 le32_to_cpu(htt_stats_buf->tqm_notify_frame));
+	len += scnprintf(buf + len, buf_len - len, "fw2wbm_enq = %u\n",
+			 le32_to_cpu(htt_stats_buf->fw2wbm_enq));
+	len += scnprintf(buf + len, buf_len - len, "tqm_bypass_frame = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->tqm_bypass_frame));
+
+	stats_req->buf_len = len;
+}
+
 static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 					  u16 tag, u16 len, const void *tag_buf,
 					  void *user_data)
@@ -1198,6 +1528,30 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_TX_TQM_PDEV_TAG:
 		ath12k_htt_print_tx_tqm_pdev_stats_tlv(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_TX_DE_CMN_TAG:
+		ath12k_htt_print_tx_de_cmn_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_EAPOL_PACKETS_TAG:
+		ath12k_htt_print_tx_de_eapol_packets_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_CLASSIFY_STATS_TAG:
+		ath12k_htt_print_tx_de_classify_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_CLASSIFY_FAILED_TAG:
+		ath12k_htt_print_tx_de_classify_failed_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_CLASSIFY_STATUS_TAG:
+		ath12k_htt_print_tx_de_classify_status_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_ENQUEUE_PACKETS_TAG:
+		ath12k_htt_print_tx_de_enqueue_packets_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_ENQUEUE_DISCARD_TAG:
+		ath12k_htt_print_tx_de_enqueue_discard_stats_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_TX_DE_COMPL_STATS_TAG:
+		ath12k_htt_print_tx_de_compl_stats_tlv(tag_buf, len, stats_req);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index 6294a082cf8a..d52b26b23e65 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -128,6 +128,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_SCHED	= 4,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_ERROR	= 5,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TQM	= 6,
+	ATH12K_DBG_HTT_EXT_STATS_TX_DE_INFO	= 8,
 
 	/* keep this last */
 	ATH12K_DBG_HTT_NUM_EXT_STATS,
@@ -143,6 +144,13 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_TX_TQM_LIST_MPDU_CNT_TAG		= 13,
 	HTT_STATS_TX_TQM_CMN_TAG			= 14,
 	HTT_STATS_TX_TQM_PDEV_TAG			= 15,
+	HTT_STATS_TX_DE_EAPOL_PACKETS_TAG		= 17,
+	HTT_STATS_TX_DE_CLASSIFY_FAILED_TAG		= 18,
+	HTT_STATS_TX_DE_CLASSIFY_STATS_TAG		= 19,
+	HTT_STATS_TX_DE_CLASSIFY_STATUS_TAG		= 20,
+	HTT_STATS_TX_DE_ENQUEUE_PACKETS_TAG		= 21,
+	HTT_STATS_TX_DE_ENQUEUE_DISCARD_TAG		= 22,
+	HTT_STATS_TX_DE_CMN_TAG				= 23,
 	HTT_STATS_TX_PDEV_SCHEDULER_TXQ_STATS_TAG	= 36,
 	HTT_STATS_TX_SCHED_CMN_TAG			= 37,
 	HTT_STATS_SCHED_TXQ_CMD_POSTED_TAG		= 39,
@@ -150,6 +158,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_SCHED_TXQ_CMD_REAPED_TAG		= 44,
 	HTT_STATS_HW_INTR_MISC_TAG			= 54,
 	HTT_STATS_HW_PDEV_ERRS_TAG			= 56,
+	HTT_STATS_TX_DE_COMPL_STATS_TAG			= 65,
 	HTT_STATS_WHAL_TX_TAG				= 66,
 	HTT_STATS_TX_PDEV_SIFS_HIST_TAG			= 67,
 	HTT_STATS_SCHED_TXQ_SCHED_ORDER_SU_TAG		= 86,
@@ -564,4 +573,121 @@ struct ath12k_htt_tx_tqm_pdev_stats_tlv {
 	__le32 sched_nonudp_notify2;
 } __packed;
 
+struct ath12k_htt_tx_de_cmn_stats_tlv {
+	__le32 mac_id__word;
+	__le32 tcl2fw_entry_count;
+	__le32 not_to_fw;
+	__le32 invalid_pdev_vdev_peer;
+	__le32 tcl_res_invalid_addrx;
+	__le32 wbm2fw_entry_count;
+	__le32 invalid_pdev;
+	__le32 tcl_res_addrx_timeout;
+	__le32 invalid_vdev;
+	__le32 invalid_tcl_exp_frame_desc;
+	__le32 vdev_id_mismatch_cnt;
+} __packed;
+
+struct ath12k_htt_tx_de_eapol_packets_stats_tlv {
+	__le32 m1_packets;
+	__le32 m2_packets;
+	__le32 m3_packets;
+	__le32 m4_packets;
+	__le32 g1_packets;
+	__le32 g2_packets;
+	__le32 rc4_packets;
+	__le32 eap_packets;
+	__le32 eapol_start_packets;
+	__le32 eapol_logoff_packets;
+	__le32 eapol_encap_asf_packets;
+} __packed;
+
+struct ath12k_htt_tx_de_classify_stats_tlv {
+	__le32 arp_packets;
+	__le32 igmp_packets;
+	__le32 dhcp_packets;
+	__le32 host_inspected;
+	__le32 htt_included;
+	__le32 htt_valid_mcs;
+	__le32 htt_valid_nss;
+	__le32 htt_valid_preamble_type;
+	__le32 htt_valid_chainmask;
+	__le32 htt_valid_guard_interval;
+	__le32 htt_valid_retries;
+	__le32 htt_valid_bw_info;
+	__le32 htt_valid_power;
+	__le32 htt_valid_key_flags;
+	__le32 htt_valid_no_encryption;
+	__le32 fse_entry_count;
+	__le32 fse_priority_be;
+	__le32 fse_priority_high;
+	__le32 fse_priority_low;
+	__le32 fse_traffic_ptrn_be;
+	__le32 fse_traffic_ptrn_over_sub;
+	__le32 fse_traffic_ptrn_bursty;
+	__le32 fse_traffic_ptrn_interactive;
+	__le32 fse_traffic_ptrn_periodic;
+	__le32 fse_hwqueue_alloc;
+	__le32 fse_hwqueue_created;
+	__le32 fse_hwqueue_send_to_host;
+	__le32 mcast_entry;
+	__le32 bcast_entry;
+	__le32 htt_update_peer_cache;
+	__le32 htt_learning_frame;
+	__le32 fse_invalid_peer;
+	__le32 mec_notify;
+} __packed;
+
+struct ath12k_htt_tx_de_classify_failed_stats_tlv {
+	__le32 ap_bss_peer_not_found;
+	__le32 ap_bcast_mcast_no_peer;
+	__le32 sta_delete_in_progress;
+	__le32 ibss_no_bss_peer;
+	__le32 invalid_vdev_type;
+	__le32 invalid_ast_peer_entry;
+	__le32 peer_entry_invalid;
+	__le32 ethertype_not_ip;
+	__le32 eapol_lookup_failed;
+	__le32 qpeer_not_allow_data;
+	__le32 fse_tid_override;
+	__le32 ipv6_jumbogram_zero_length;
+	__le32 qos_to_non_qos_in_prog;
+	__le32 ap_bcast_mcast_eapol;
+	__le32 unicast_on_ap_bss_peer;
+	__le32 ap_vdev_invalid;
+	__le32 incomplete_llc;
+	__le32 eapol_duplicate_m3;
+	__le32 eapol_duplicate_m4;
+} __packed;
+
+struct ath12k_htt_tx_de_classify_status_stats_tlv {
+	__le32 eok;
+	__le32 classify_done;
+	__le32 lookup_failed;
+	__le32 send_host_dhcp;
+	__le32 send_host_mcast;
+	__le32 send_host_unknown_dest;
+	__le32 send_host;
+	__le32 status_invalid;
+} __packed;
+
+struct ath12k_htt_tx_de_enqueue_packets_stats_tlv {
+	__le32 enqueued_pkts;
+	__le32 to_tqm;
+	__le32 to_tqm_bypass;
+} __packed;
+
+struct ath12k_htt_tx_de_enqueue_discard_stats_tlv {
+	__le32 discarded_pkts;
+	__le32 local_frames;
+	__le32 is_ext_msdu;
+} __packed;
+
+struct ath12k_htt_tx_de_compl_stats_tlv {
+	__le32 tcl_dummy_frame;
+	__le32 tqm_dummy_frame;
+	__le32 tqm_notify_frame;
+	__le32 fw2wbm_enq;
+	__le32 tqm_bypass_frame;
+} __packed;
+
 #endif
-- 
cgit v1.3-3-g829e


From 8fbcaa308591b91e9037ab6a8d733873b749a70d Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Sat, 6 Jul 2024 01:40:58 +0300
Subject: wifi: rtw88: Set efuse->ext_lna_5g - fix typo

efuse->ext_lna_2g is set twice and efuse->ext_lna_5g is not set at all.
Set each one once.

Nothing uses these members right now. They will be used by the RTL8821AU
and RTL8812AU drivers.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/8ccc9e13-0d45-417d-8f88-93a0ad294f77@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 7ab7a988b123..9d9d33a4a503 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -2005,7 +2005,7 @@ static int rtw_chip_efuse_info_setup(struct rtw_dev *rtwdev)
 	efuse->ext_pa_2g = efuse->pa_type_2g & BIT(4) ? 1 : 0;
 	efuse->ext_lna_2g = efuse->lna_type_2g & BIT(3) ? 1 : 0;
 	efuse->ext_pa_5g = efuse->pa_type_5g & BIT(0) ? 1 : 0;
-	efuse->ext_lna_2g = efuse->lna_type_5g & BIT(3) ? 1 : 0;
+	efuse->ext_lna_5g = efuse->lna_type_5g & BIT(3) ? 1 : 0;
 
 	if (!is_valid_ether_addr(efuse->addr)) {
 		eth_random_addr(efuse->addr);
-- 
cgit v1.3-3-g829e


From d64270128bf551d68f47122c8893ea78bfbad8be Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Wed, 10 Jul 2024 12:22:53 +0100
Subject: wifi: rtw89: 8852bt: rfk: Fix spelling mistake "KIP_RESOTRE" ->
 "KIP_RESTORE"

There is a spelling mistake in a literal string. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240710112253.228171-1-colin.i.king@gmail.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index fa0e49d58112..5bdabb45e968 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -1863,7 +1863,7 @@ static void _dpk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		    id == 0x14 ? "PWR_CAL" :
 		    id == 0x15 ? "DPK_RXAGC" :
 		    id == 0x16 ? "KIP_PRESET" :
-		    id == 0x17 ? "KIP_RESOTRE" :
+		    id == 0x17 ? "KIP_RESTORE" :
 		    "DPK_TXAGC", dpk_cmd);
 }
 
-- 
cgit v1.3-3-g829e


From 315c23a64e99552502dd4d18d6ddc073fad9a7c3 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 11 Jul 2024 01:11:33 +0300
Subject: wifi: rtw88: usb: Support USB 3 with RTL8822CU/RTL8822BU

The Realtek wifi 5 devices which support USB 3 are weird: when first
plugged in, they pretend to be USB 2. The driver needs to send some
commands to the device, which make it disappear and come back as a
USB 3 device.

Implement the required commands in rtw88.

When a USB 3 device is plugged into a USB 2 port, rtw88 will try to
switch it to USB 3 mode only once. The device will disappear and come
back still in USB 2 mode, of course.

Some people experience heavy interference in the 2.4 GHz band in
USB 3 mode, so add a module parameter switch_usb_mode with the
default value 1 to let people disable the switching.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/77906c62-5674-426f-bde1-1b2a12a0339d@gmail.com
---
 drivers/net/wireless/realtek/rtw88/debug.h    |  1 +
 drivers/net/wireless/realtek/rtw88/main.h     |  2 +
 drivers/net/wireless/realtek/rtw88/reg.h      | 11 ++++
 drivers/net/wireless/realtek/rtw88/rtw8822b.c |  1 +
 drivers/net/wireless/realtek/rtw88/rtw8822b.h |  4 +-
 drivers/net/wireless/realtek/rtw88/rtw8822c.c |  1 +
 drivers/net/wireless/realtek/rtw88/rtw8822c.h | 24 ++++----
 drivers/net/wireless/realtek/rtw88/usb.c      | 84 +++++++++++++++++++++++++++
 8 files changed, 116 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/debug.h b/drivers/net/wireless/realtek/rtw88/debug.h
index eb69006c463e..9a1e0e85a13c 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.h
+++ b/drivers/net/wireless/realtek/rtw88/debug.h
@@ -25,6 +25,7 @@ enum rtw_debug_mask {
 	RTW_DBG_HW_SCAN		= 0x00010000,
 	RTW_DBG_STATE		= 0x00020000,
 	RTW_DBG_SDIO		= 0x00040000,
+	RTW_DBG_USB		= 0x00080000,
 
 	RTW_DBG_UNEXP		= 0x80000000,
 	RTW_DBG_ALL		= 0xffffffff
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 49a3fd4fb7dc..9d21637cf5d5 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -1785,6 +1785,8 @@ struct rtw_efuse {
 	bool share_ant;
 	u8 bt_setting;
 
+	u8 usb_mode_switch;
+
 	struct {
 		u8 hci;
 		u8 bw;
diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
index 02ef9a77316b..e7b24465f549 100644
--- a/drivers/net/wireless/realtek/rtw88/reg.h
+++ b/drivers/net/wireless/realtek/rtw88/reg.h
@@ -15,6 +15,7 @@
 #define BIT_WLOCK_1C_B6		BIT(5)
 #define REG_SYS_PW_CTRL		0x0004
 #define BIT_PFM_WOWL		BIT(3)
+#define BIT_APFM_OFFMAC		BIT(9)
 #define REG_SYS_CLK_CTRL	0x0008
 #define BIT_CPU_CLK_EN		BIT(14)
 
@@ -133,6 +134,14 @@
 #define REG_PMC_DBG_CTRL1	0xa8
 #define BITS_PMC_BT_IQK_STS	GENMASK(22, 21)
 
+#define REG_PAD_CTRL2		0x00C4
+#define BIT_RSM_EN_V1		BIT(16)
+#define BIT_NO_PDN_CHIPOFF_V1	BIT(17)
+#define BIT_MASK_USB23_SW_MODE_V1	GENMASK(19, 18)
+#define BIT_USB3_USB2_TRANSITION	BIT(20)
+#define BIT_USB_MODE_U2		1
+#define BIT_USB_MODE_U3		2
+
 #define REG_EFUSE_ACCESS	0x00CF
 #define EFUSE_ACCESS_ON		0x69
 #define EFUSE_ACCESS_OFF	0x00
@@ -568,6 +577,8 @@
 #define BIT_WL_SECURITY_CLK	BIT(15)
 #define BIT_DDMA_EN		BIT(8)
 
+#define REG_SW_MDIO		0x10C0
+
 #define REG_H2C_PKT_READADDR	0x10D0
 #define REG_H2C_PKT_WRITEADDR	0x10D4
 #define REG_FW_DBG6		0x10F8
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index 2456ff242818..6edb17aea90e 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -46,6 +46,7 @@ static int rtw8822b_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
 
 	map = (struct rtw8822b_efuse *)log_map;
 
+	efuse->usb_mode_switch = u8_get_bits(map->usb_mode, BIT(7));
 	efuse->rfe_option = map->rfe_option;
 	efuse->rf_board_option = map->rf_board_option;
 	efuse->crystal_cap = map->xtal_k;
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.h b/drivers/net/wireless/realtek/rtw88/rtw8822b.h
index 2dc3a6660f06..cf85e63966a1 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.h
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.h
@@ -72,7 +72,9 @@ struct rtw8822bs_efuse {
 
 struct rtw8822b_efuse {
 	__le16 rtl_id;
-	u8 res0[0x0e];
+	u8 res0[4];
+	u8 usb_mode;
+	u8 res1[0x09];
 
 	/* power index for four RF paths */
 	struct rtw_txpwr_idx txpwr_idx_table[4];
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index 62376d1cca22..bc807b13e9ce 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -49,6 +49,7 @@ static int rtw8822c_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
 
 	map = (struct rtw8822c_efuse *)log_map;
 
+	efuse->usb_mode_switch = u8_get_bits(map->usb_mode, BIT(7));
 	efuse->rfe_option = map->rfe_option;
 	efuse->rf_board_option = map->rf_board_option;
 	efuse->crystal_cap = map->xtal_k & XCAP_MASK;
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.h b/drivers/net/wireless/realtek/rtw88/rtw8822c.h
index 1bc0e7f5d6bb..e2b383d633cd 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.h
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.h
@@ -59,16 +59,18 @@ struct rtw8822ce_efuse {
 
 struct rtw8822c_efuse {
 	__le16 rtl_id;
-	u8 res0[0x0e];
+	u8 res0[4];
+	u8 usb_mode;
+	u8 res1[0x09];
 
 	/* power index for four RF paths */
 	struct rtw_txpwr_idx txpwr_idx_table[4];
 
 	u8 channel_plan;		/* 0xb8 */
 	u8 xtal_k;
-	u8 res1;
+	u8 res2;
 	u8 iqk_lck;
-	u8 res2[5];			/* 0xbc */
+	u8 res3[5];			/* 0xbc */
 	u8 rf_board_option;
 	u8 rf_feature_option;
 	u8 rf_bt_setting;
@@ -80,21 +82,21 @@ struct rtw8822c_efuse {
 	u8 rf_antenna_option;		/* 0xc9 */
 	u8 rfe_option;
 	u8 country_code[2];
-	u8 res3[3];
+	u8 res4[3];
 	u8 path_a_thermal;		/* 0xd0 */
 	u8 path_b_thermal;
-	u8 res4[2];
+	u8 res5[2];
 	u8 rx_gain_gap_2g_ofdm;
-	u8 res5;
-	u8 rx_gain_gap_2g_cck;
 	u8 res6;
-	u8 rx_gain_gap_5gl;
+	u8 rx_gain_gap_2g_cck;
 	u8 res7;
-	u8 rx_gain_gap_5gm;
+	u8 rx_gain_gap_5gl;
 	u8 res8;
-	u8 rx_gain_gap_5gh;
+	u8 rx_gain_gap_5gm;
 	u8 res9;
-	u8 res10[0x42];
+	u8 rx_gain_gap_5gh;
+	u8 res10;
+	u8 res11[0x42];
 	union {
 		struct rtw8822ce_efuse e;
 		struct rtw8822cu_efuse u;
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index a55ca5a24227..251a5726f3ee 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -14,6 +14,11 @@
 #include "ps.h"
 #include "usb.h"
 
+static bool rtw_switch_usb_mode = true;
+module_param_named(switch_usb_mode, rtw_switch_usb_mode, bool, 0644);
+MODULE_PARM_DESC(switch_usb_mode,
+		 "Set to N to disable switching to USB 3 mode to avoid potential interference in the 2.4 GHz band (default: Y)");
+
 #define RTW_USB_MAX_RXQ_LEN	512
 
 struct rtw_usb_txcb {
@@ -841,6 +846,77 @@ static void rtw_usb_intf_deinit(struct rtw_dev *rtwdev,
 	usb_set_intfdata(intf, NULL);
 }
 
+static int rtw_usb_switch_mode_new(struct rtw_dev *rtwdev)
+{
+	enum usb_device_speed cur_speed;
+	u8 id = rtwdev->chip->id;
+	bool can_switch;
+	u32 pad_ctrl2;
+
+	if (rtw_read8(rtwdev, REG_SYS_CFG2 + 3) == 0x20)
+		cur_speed = USB_SPEED_SUPER;
+	else
+		cur_speed = USB_SPEED_HIGH;
+
+	if (cur_speed == USB_SPEED_SUPER)
+		return 0;
+
+	pad_ctrl2 = rtw_read32(rtwdev, REG_PAD_CTRL2);
+
+	can_switch = !!(pad_ctrl2 & (BIT_MASK_USB23_SW_MODE_V1 |
+				     BIT_USB3_USB2_TRANSITION));
+
+	if (!can_switch) {
+		rtw_dbg(rtwdev, RTW_DBG_USB,
+			"Switching to USB 3 mode unsupported by the chip\n");
+		return 0;
+	}
+
+	/* At this point cur_speed is USB_SPEED_HIGH. If we already tried
+	 * to switch don't try again - it's a USB 2 port.
+	 */
+	if (u32_get_bits(pad_ctrl2, BIT_MASK_USB23_SW_MODE_V1) == BIT_USB_MODE_U3)
+		return 0;
+
+	/* Enable IO wrapper timeout */
+	if (id == RTW_CHIP_TYPE_8822B || id == RTW_CHIP_TYPE_8821C)
+		rtw_write8_clr(rtwdev, REG_SW_MDIO + 3, BIT(0));
+
+	u32p_replace_bits(&pad_ctrl2, BIT_USB_MODE_U3, BIT_MASK_USB23_SW_MODE_V1);
+	pad_ctrl2 |= BIT_RSM_EN_V1;
+
+	rtw_write32(rtwdev, REG_PAD_CTRL2, pad_ctrl2);
+	rtw_write8(rtwdev, REG_PAD_CTRL2 + 1, 4);
+
+	rtw_write16_set(rtwdev, REG_SYS_PW_CTRL, BIT_APFM_OFFMAC);
+	usleep_range(1000, 1001);
+	rtw_write32_set(rtwdev, REG_PAD_CTRL2, BIT_NO_PDN_CHIPOFF_V1);
+
+	return 1;
+}
+
+static int rtw_usb_switch_mode(struct rtw_dev *rtwdev)
+{
+	u8 id = rtwdev->chip->id;
+
+	if (id != RTW_CHIP_TYPE_8822C && id != RTW_CHIP_TYPE_8822B)
+		return 0;
+
+	if (!rtwdev->efuse.usb_mode_switch) {
+		rtw_dbg(rtwdev, RTW_DBG_USB,
+			"Switching to USB 3 mode disabled by chip's efuse\n");
+		return 0;
+	}
+
+	if (!rtw_switch_usb_mode) {
+		rtw_dbg(rtwdev, RTW_DBG_USB,
+			"Switching to USB 3 mode disabled by module parameter\n");
+		return 0;
+	}
+
+	return rtw_usb_switch_mode_new(rtwdev);
+}
+
 int rtw_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 {
 	struct rtw_dev *rtwdev;
@@ -896,6 +972,14 @@ int rtw_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 		goto err_destroy_rxwq;
 	}
 
+	ret = rtw_usb_switch_mode(rtwdev);
+	if (ret) {
+		/* Not a fail, but we do need to skip rtw_register_hw. */
+		rtw_dbg(rtwdev, RTW_DBG_USB, "switching to USB 3 mode\n");
+		ret = 0;
+		goto err_destroy_rxwq;
+	}
+
 	ret = rtw_register_hw(rtwdev, rtwdev->hw);
 	if (ret) {
 		rtw_err(rtwdev, "failed to register hw\n");
-- 
cgit v1.3-3-g829e


From 0af8cd2822f31ed8363223329e5cff2a7ed01961 Mon Sep 17 00:00:00 2001
From: Nick Morrow <morrownr@gmail.com>
Date: Thu, 11 Jul 2024 01:14:23 +0300
Subject: wifi: rtw88: 8821cu: Remove VID/PID 0bda:c82c

Remove VID/PID 0bda:c82c as it was inadvertently added to the device
list in driver rtw8821cu. This VID/PID is for the rtw8822cu device
and it is already in the appropriate place for that device.

Cc: stable@vger.kernel.org
Signed-off-by: Nick Morrow <morrownr@gmail.com>
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/335d7fa1-0ba5-4b86-bba5-f98834ace1f8@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8821cu.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
index e2c7d9f87683..a019f4085e73 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
@@ -31,8 +31,6 @@ static const struct usb_device_id rtw_8821cu_id_table[] = {
 	  .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82b, 0xff, 0xff, 0xff),
 	  .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82c, 0xff, 0xff, 0xff),
-	  .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331d, 0xff, 0xff, 0xff),
 	  .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* D-Link */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xc811, 0xff, 0xff, 0xff),
-- 
cgit v1.3-3-g829e


From e832bc9e818ca49078350a89f1de9aceba1775e3 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Mon, 29 Jul 2024 15:26:47 +0000
Subject: net: wangxun: use net_prefetch to simplify logic

Use net_prefetch to remove #ifdef and simplify prefetch logic. This
follows the pattern introduced in a previous commit f468f21b7af0 ("net:
Take common prefetch code structure into a function"), which replaced
the same logic in all existing drivers at that time.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/20240729152651.258713-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 1eecba984f3b..2b3d6586f44a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -251,10 +251,7 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring,
 				  rx_buffer->page_offset;
 
 		/* prefetch first cache line of first page */
-		prefetch(page_addr);
-#if L1_CACHE_BYTES < 128
-		prefetch(page_addr + L1_CACHE_BYTES);
-#endif
+		net_prefetch(page_addr);
 
 		/* allocate a skb to store the frags */
 		skb = napi_alloc_skb(&rx_ring->q_vector->napi, WX_RXBUFFER_256);
-- 
cgit v1.3-3-g829e


From 0a658d088cc63745528cf0ec8a2c2df0f37742d9 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 29 Jul 2024 21:53:37 +0100
Subject: net/tcp: Expand goo.gl link

The goo.gl URL shortener is deprecated and is due to stop
expanding existing links in 2025.

Expand the link in Kconfig.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240729205337.48058-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 8e94ed7c56a0..6d2c97f8e9ef 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -661,7 +661,8 @@ config TCP_CONG_CDG
 
 	  For further details see:
 	    D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using
-	    delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg
+	    delay gradients." In Networking 2011. Preprint:
+	    http://caia.swin.edu.au/cv/dahayes/content/networking2011-cdg-preprint.pdf
 
 config TCP_CONG_BBR
 	tristate "BBR TCP"
-- 
cgit v1.3-3-g829e


From 8db6c1ca64664ef9b071e6eeb646023ac5b240a8 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Thu, 18 Jul 2024 14:41:55 +0800
Subject: wifi: rtw88: debugfs: support multiple adapters debugging

Originally in order to read partial registers from large area, we write
a range value stored into a static variable and read registers according
to the static variable.

However, if we install more than one adapters supported by this driver,
the static variables will be overwritten by latter adapters. To resolve
the problem, move the static variables to struct rtw_dev for each adapter.

With changes, smatch spends too much time to parse rtw_debugfs_init():
    debug.c:1289 rtw_debugfs_init() parse error: turning off implications
    after 60 seconds
Move stuffs of adding debugfs entries to three rtw_debugfs_add_xxx()
functions.

Reported-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Closes: https://lore.kernel.org/linux-wireless/cd6a2acf3c2c36d938b40140b52a779516f446a9.camel@realtek.com/T/#m27662022c70d9f893ba96f6c6a8dd8fce2434dfe
Tested-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240718064155.38955-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw88/debug.c | 303 +++++++++++++++++------------
 drivers/net/wireless/realtek/rtw88/debug.h |   2 +
 drivers/net/wireless/realtek/rtw88/main.c  |   1 +
 drivers/net/wireless/realtek/rtw88/main.h  |   3 +-
 4 files changed, 180 insertions(+), 129 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index 5b2036798159..c26a6905fd15 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -43,6 +43,62 @@ struct rtw_debugfs_priv {
 	};
 };
 
+struct rtw_debugfs {
+	struct rtw_debugfs_priv mac_0;
+	struct rtw_debugfs_priv mac_1;
+	struct rtw_debugfs_priv mac_2;
+	struct rtw_debugfs_priv mac_3;
+	struct rtw_debugfs_priv mac_4;
+	struct rtw_debugfs_priv mac_5;
+	struct rtw_debugfs_priv mac_6;
+	struct rtw_debugfs_priv mac_7;
+	struct rtw_debugfs_priv mac_10;
+	struct rtw_debugfs_priv mac_11;
+	struct rtw_debugfs_priv mac_12;
+	struct rtw_debugfs_priv mac_13;
+	struct rtw_debugfs_priv mac_14;
+	struct rtw_debugfs_priv mac_15;
+	struct rtw_debugfs_priv mac_16;
+	struct rtw_debugfs_priv mac_17;
+	struct rtw_debugfs_priv bb_8;
+	struct rtw_debugfs_priv bb_9;
+	struct rtw_debugfs_priv bb_a;
+	struct rtw_debugfs_priv bb_b;
+	struct rtw_debugfs_priv bb_c;
+	struct rtw_debugfs_priv bb_d;
+	struct rtw_debugfs_priv bb_e;
+	struct rtw_debugfs_priv bb_f;
+	struct rtw_debugfs_priv bb_18;
+	struct rtw_debugfs_priv bb_19;
+	struct rtw_debugfs_priv bb_1a;
+	struct rtw_debugfs_priv bb_1b;
+	struct rtw_debugfs_priv bb_1c;
+	struct rtw_debugfs_priv bb_1d;
+	struct rtw_debugfs_priv bb_1e;
+	struct rtw_debugfs_priv bb_1f;
+	struct rtw_debugfs_priv bb_2c;
+	struct rtw_debugfs_priv bb_2d;
+	struct rtw_debugfs_priv bb_40;
+	struct rtw_debugfs_priv bb_41;
+	struct rtw_debugfs_priv rf_dump;
+	struct rtw_debugfs_priv tx_pwr_tbl;
+	struct rtw_debugfs_priv write_reg;
+	struct rtw_debugfs_priv h2c;
+	struct rtw_debugfs_priv rf_write;
+	struct rtw_debugfs_priv rf_read;
+	struct rtw_debugfs_priv read_reg;
+	struct rtw_debugfs_priv fix_rate;
+	struct rtw_debugfs_priv dump_cam;
+	struct rtw_debugfs_priv rsvd_page;
+	struct rtw_debugfs_priv phy_info;
+	struct rtw_debugfs_priv coex_enable;
+	struct rtw_debugfs_priv coex_info;
+	struct rtw_debugfs_priv edcca_enable;
+	struct rtw_debugfs_priv fw_crash;
+	struct rtw_debugfs_priv force_lowest_basic_rate;
+	struct rtw_debugfs_priv dm_cap;
+};
+
 static const char * const rtw_dm_cap_strs[] = {
 	[RTW_DM_CAP_NA] = "NA",
 	[RTW_DM_CAP_TXGAPK] = "TXGAPK",
@@ -524,7 +580,7 @@ static int rtw_debug_get_bb_page(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int rtw_debug_get_rf_dump(struct seq_file *m, void *v)
+static int rtw_debugfs_get_rf_dump(struct seq_file *m, void *v)
 {
 	struct rtw_debugfs_priv *debugfs_priv = m->private;
 	struct rtw_dev *rtwdev = debugfs_priv->rtwdev;
@@ -1074,139 +1130,102 @@ static int rtw_debugfs_get_dm_cap(struct seq_file *m, void *v)
 	return 0;
 }
 
-#define rtw_debug_impl_mac(page, addr)				\
-static struct rtw_debugfs_priv rtw_debug_priv_mac_ ##page = {	\
+#define rtw_debug_priv_mac(addr)				\
+{								\
 	.cb_read = rtw_debug_get_mac_page,			\
 	.cb_data = addr,					\
 }
 
-rtw_debug_impl_mac(0, 0x0000);
-rtw_debug_impl_mac(1, 0x0100);
-rtw_debug_impl_mac(2, 0x0200);
-rtw_debug_impl_mac(3, 0x0300);
-rtw_debug_impl_mac(4, 0x0400);
-rtw_debug_impl_mac(5, 0x0500);
-rtw_debug_impl_mac(6, 0x0600);
-rtw_debug_impl_mac(7, 0x0700);
-rtw_debug_impl_mac(10, 0x1000);
-rtw_debug_impl_mac(11, 0x1100);
-rtw_debug_impl_mac(12, 0x1200);
-rtw_debug_impl_mac(13, 0x1300);
-rtw_debug_impl_mac(14, 0x1400);
-rtw_debug_impl_mac(15, 0x1500);
-rtw_debug_impl_mac(16, 0x1600);
-rtw_debug_impl_mac(17, 0x1700);
-
-#define rtw_debug_impl_bb(page, addr)			\
-static struct rtw_debugfs_priv rtw_debug_priv_bb_ ##page = {	\
+#define rtw_debug_priv_bb(addr)					\
+{								\
 	.cb_read = rtw_debug_get_bb_page,			\
 	.cb_data = addr,					\
 }
 
-rtw_debug_impl_bb(8, 0x0800);
-rtw_debug_impl_bb(9, 0x0900);
-rtw_debug_impl_bb(a, 0x0a00);
-rtw_debug_impl_bb(b, 0x0b00);
-rtw_debug_impl_bb(c, 0x0c00);
-rtw_debug_impl_bb(d, 0x0d00);
-rtw_debug_impl_bb(e, 0x0e00);
-rtw_debug_impl_bb(f, 0x0f00);
-rtw_debug_impl_bb(18, 0x1800);
-rtw_debug_impl_bb(19, 0x1900);
-rtw_debug_impl_bb(1a, 0x1a00);
-rtw_debug_impl_bb(1b, 0x1b00);
-rtw_debug_impl_bb(1c, 0x1c00);
-rtw_debug_impl_bb(1d, 0x1d00);
-rtw_debug_impl_bb(1e, 0x1e00);
-rtw_debug_impl_bb(1f, 0x1f00);
-rtw_debug_impl_bb(2c, 0x2c00);
-rtw_debug_impl_bb(2d, 0x2d00);
-rtw_debug_impl_bb(40, 0x4000);
-rtw_debug_impl_bb(41, 0x4100);
-
-static struct rtw_debugfs_priv rtw_debug_priv_rf_dump = {
-	.cb_read = rtw_debug_get_rf_dump,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_tx_pwr_tbl = {
-	.cb_read = rtw_debugfs_get_tx_pwr_tbl,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_write_reg = {
-	.cb_write = rtw_debugfs_set_write_reg,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_h2c = {
-	.cb_write = rtw_debugfs_set_h2c,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_rf_write = {
-	.cb_write = rtw_debugfs_set_rf_write,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_rf_read = {
-	.cb_write = rtw_debugfs_set_rf_read,
-	.cb_read = rtw_debugfs_get_rf_read,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_read_reg = {
-	.cb_write = rtw_debugfs_set_read_reg,
-	.cb_read = rtw_debugfs_get_read_reg,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_fix_rate = {
-	.cb_write = rtw_debugfs_set_fix_rate,
-	.cb_read = rtw_debugfs_get_fix_rate,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_dump_cam = {
-	.cb_write = rtw_debugfs_set_single_input,
-	.cb_read = rtw_debugfs_get_dump_cam,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_rsvd_page = {
-	.cb_write = rtw_debugfs_set_rsvd_page,
-	.cb_read = rtw_debugfs_get_rsvd_page,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_phy_info = {
-	.cb_read = rtw_debugfs_get_phy_info,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_coex_enable = {
-	.cb_write = rtw_debugfs_set_coex_enable,
-	.cb_read = rtw_debugfs_get_coex_enable,
-};
-
-static struct rtw_debugfs_priv rtw_debug_priv_coex_info = {
-	.cb_read = rtw_debugfs_get_coex_info,
-};
+#define rtw_debug_priv_get(name)				\
+{								\
+	.cb_read = rtw_debugfs_get_ ##name,			\
+}
 
-static struct rtw_debugfs_priv rtw_debug_priv_edcca_enable = {
-	.cb_write = rtw_debugfs_set_edcca_enable,
-	.cb_read = rtw_debugfs_get_edcca_enable,
-};
+#define rtw_debug_priv_set(name)				\
+{								\
+	.cb_write = rtw_debugfs_set_ ##name,			\
+}
 
-static struct rtw_debugfs_priv rtw_debug_priv_fw_crash = {
-	.cb_write = rtw_debugfs_set_fw_crash,
-	.cb_read = rtw_debugfs_get_fw_crash,
-};
+#define rtw_debug_priv_set_and_get(name)			\
+{								\
+	.cb_write = rtw_debugfs_set_ ##name,			\
+	.cb_read = rtw_debugfs_get_ ##name,			\
+}
 
-static struct rtw_debugfs_priv rtw_debug_priv_force_lowest_basic_rate = {
-	.cb_write = rtw_debugfs_set_force_lowest_basic_rate,
-	.cb_read = rtw_debugfs_get_force_lowest_basic_rate,
-};
+#define rtw_debug_priv_set_single_and_get(name)			\
+{								\
+	.cb_write = rtw_debugfs_set_single_input,		\
+	.cb_read = rtw_debugfs_get_ ##name,			\
+}
 
-static struct rtw_debugfs_priv rtw_debug_priv_dm_cap = {
-	.cb_write = rtw_debugfs_set_dm_cap,
-	.cb_read = rtw_debugfs_get_dm_cap,
+static const struct rtw_debugfs rtw_debugfs_templ = {
+	.mac_0 = rtw_debug_priv_mac(0x0000),
+	.mac_1 = rtw_debug_priv_mac(0x0100),
+	.mac_2 = rtw_debug_priv_mac(0x0200),
+	.mac_3 = rtw_debug_priv_mac(0x0300),
+	.mac_4 = rtw_debug_priv_mac(0x0400),
+	.mac_5 = rtw_debug_priv_mac(0x0500),
+	.mac_6 = rtw_debug_priv_mac(0x0600),
+	.mac_7 = rtw_debug_priv_mac(0x0700),
+	.mac_10 = rtw_debug_priv_mac(0x1000),
+	.mac_11 = rtw_debug_priv_mac(0x1100),
+	.mac_12 = rtw_debug_priv_mac(0x1200),
+	.mac_13 = rtw_debug_priv_mac(0x1300),
+	.mac_14 = rtw_debug_priv_mac(0x1400),
+	.mac_15 = rtw_debug_priv_mac(0x1500),
+	.mac_16 = rtw_debug_priv_mac(0x1600),
+	.mac_17 = rtw_debug_priv_mac(0x1700),
+	.bb_8 = rtw_debug_priv_bb(0x0800),
+	.bb_9 = rtw_debug_priv_bb(0x0900),
+	.bb_a = rtw_debug_priv_bb(0x0a00),
+	.bb_b = rtw_debug_priv_bb(0x0b00),
+	.bb_c = rtw_debug_priv_bb(0x0c00),
+	.bb_d = rtw_debug_priv_bb(0x0d00),
+	.bb_e = rtw_debug_priv_bb(0x0e00),
+	.bb_f = rtw_debug_priv_bb(0x0f00),
+	.bb_18 = rtw_debug_priv_bb(0x1800),
+	.bb_19 = rtw_debug_priv_bb(0x1900),
+	.bb_1a = rtw_debug_priv_bb(0x1a00),
+	.bb_1b = rtw_debug_priv_bb(0x1b00),
+	.bb_1c = rtw_debug_priv_bb(0x1c00),
+	.bb_1d = rtw_debug_priv_bb(0x1d00),
+	.bb_1e = rtw_debug_priv_bb(0x1e00),
+	.bb_1f = rtw_debug_priv_bb(0x1f00),
+	.bb_2c = rtw_debug_priv_bb(0x2c00),
+	.bb_2d = rtw_debug_priv_bb(0x2d00),
+	.bb_40 = rtw_debug_priv_bb(0x4000),
+	.bb_41 = rtw_debug_priv_bb(0x4100),
+	.rf_dump = rtw_debug_priv_get(rf_dump),
+	.tx_pwr_tbl = rtw_debug_priv_get(tx_pwr_tbl),
+	.write_reg = rtw_debug_priv_set(write_reg),
+	.h2c = rtw_debug_priv_set(h2c),
+	.rf_write = rtw_debug_priv_set(rf_write),
+	.rf_read = rtw_debug_priv_set_and_get(rf_read),
+	.read_reg = rtw_debug_priv_set_and_get(read_reg),
+	.fix_rate = rtw_debug_priv_set_and_get(fix_rate),
+	.dump_cam = rtw_debug_priv_set_single_and_get(dump_cam),
+	.rsvd_page = rtw_debug_priv_set_and_get(rsvd_page),
+	.phy_info = rtw_debug_priv_get(phy_info),
+	.coex_enable = rtw_debug_priv_set_and_get(coex_enable),
+	.coex_info = rtw_debug_priv_get(coex_info),
+	.edcca_enable = rtw_debug_priv_set_and_get(edcca_enable),
+	.fw_crash = rtw_debug_priv_set_and_get(fw_crash),
+	.force_lowest_basic_rate = rtw_debug_priv_set_and_get(force_lowest_basic_rate),
+	.dm_cap = rtw_debug_priv_set_and_get(dm_cap),
 };
 
 #define rtw_debugfs_add_core(name, mode, fopname, parent)		\
 	do {								\
-		rtw_debug_priv_ ##name.rtwdev = rtwdev;			\
+		struct rtw_debugfs_priv *priv = &rtwdev->debugfs->name;	\
+		priv->rtwdev = rtwdev;					\
 		if (IS_ERR(debugfs_create_file(#name, mode,		\
-					 parent, &rtw_debug_priv_ ##name,\
+					 parent, priv,			\
 					 &file_ops_ ##fopname)))	\
 			pr_debug("Unable to initialize debugfs:%s\n",	\
 			       #name);					\
@@ -1219,12 +1238,9 @@ static struct rtw_debugfs_priv rtw_debug_priv_dm_cap = {
 #define rtw_debugfs_add_r(name)						\
 	rtw_debugfs_add_core(name, S_IFREG | 0444, single_r, debugfs_topdir)
 
-void rtw_debugfs_init(struct rtw_dev *rtwdev)
+static
+void rtw_debugfs_add_basic(struct rtw_dev *rtwdev, struct dentry *debugfs_topdir)
 {
-	struct dentry *debugfs_topdir;
-
-	debugfs_topdir = debugfs_create_dir("rtw88",
-					    rtwdev->hw->wiphy->debugfsdir);
 	rtw_debugfs_add_w(write_reg);
 	rtw_debugfs_add_rw(read_reg);
 	rtw_debugfs_add_w(rf_write);
@@ -1236,6 +1252,17 @@ void rtw_debugfs_init(struct rtw_dev *rtwdev)
 	rtw_debugfs_add_r(coex_info);
 	rtw_debugfs_add_rw(coex_enable);
 	rtw_debugfs_add_w(h2c);
+	rtw_debugfs_add_r(rf_dump);
+	rtw_debugfs_add_r(tx_pwr_tbl);
+	rtw_debugfs_add_rw(edcca_enable);
+	rtw_debugfs_add_rw(fw_crash);
+	rtw_debugfs_add_rw(force_lowest_basic_rate);
+	rtw_debugfs_add_rw(dm_cap);
+}
+
+static
+void rtw_debugfs_add_sec0(struct rtw_dev *rtwdev, struct dentry *debugfs_topdir)
+{
 	rtw_debugfs_add_r(mac_0);
 	rtw_debugfs_add_r(mac_1);
 	rtw_debugfs_add_r(mac_2);
@@ -1252,6 +1279,11 @@ void rtw_debugfs_init(struct rtw_dev *rtwdev)
 	rtw_debugfs_add_r(bb_d);
 	rtw_debugfs_add_r(bb_e);
 	rtw_debugfs_add_r(bb_f);
+}
+
+static
+void rtw_debugfs_add_sec1(struct rtw_dev *rtwdev, struct dentry *debugfs_topdir)
+{
 	rtw_debugfs_add_r(mac_10);
 	rtw_debugfs_add_r(mac_11);
 	rtw_debugfs_add_r(mac_12);
@@ -1274,14 +1306,29 @@ void rtw_debugfs_init(struct rtw_dev *rtwdev)
 		rtw_debugfs_add_r(bb_40);
 		rtw_debugfs_add_r(bb_41);
 	}
-	rtw_debugfs_add_r(rf_dump);
-	rtw_debugfs_add_r(tx_pwr_tbl);
-	rtw_debugfs_add_rw(edcca_enable);
-	rtw_debugfs_add_rw(fw_crash);
-	rtw_debugfs_add_rw(force_lowest_basic_rate);
-	rtw_debugfs_add_rw(dm_cap);
 }
 
+void rtw_debugfs_init(struct rtw_dev *rtwdev)
+{
+	struct dentry *debugfs_topdir;
+
+	rtwdev->debugfs = kmemdup(&rtw_debugfs_templ, sizeof(rtw_debugfs_templ),
+				  GFP_KERNEL);
+	if (!rtwdev->debugfs)
+		return;
+
+	debugfs_topdir = debugfs_create_dir("rtw88",
+					    rtwdev->hw->wiphy->debugfsdir);
+
+	rtw_debugfs_add_basic(rtwdev, debugfs_topdir);
+	rtw_debugfs_add_sec0(rtwdev, debugfs_topdir);
+	rtw_debugfs_add_sec1(rtwdev, debugfs_topdir);
+}
+
+void rtw_debugfs_deinit(struct rtw_dev *rtwdev)
+{
+	kfree(rtwdev->debugfs);
+}
 #endif /* CONFIG_RTW88_DEBUGFS */
 
 #ifdef CONFIG_RTW88_DEBUG
diff --git a/drivers/net/wireless/realtek/rtw88/debug.h b/drivers/net/wireless/realtek/rtw88/debug.h
index 9a1e0e85a13c..6570e84d8d24 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.h
+++ b/drivers/net/wireless/realtek/rtw88/debug.h
@@ -34,11 +34,13 @@ enum rtw_debug_mask {
 #ifdef CONFIG_RTW88_DEBUGFS
 
 void rtw_debugfs_init(struct rtw_dev *rtwdev);
+void rtw_debugfs_deinit(struct rtw_dev *rtwdev);
 void rtw_debugfs_get_simple_phy_info(struct seq_file *m);
 
 #else
 
 static inline void rtw_debugfs_init(struct rtw_dev *rtwdev) {}
+static inline void rtw_debugfs_deinit(struct rtw_dev *rtwdev) {}
 
 #endif /* CONFIG_RTW88_DEBUGFS */
 
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 9d9d33a4a503..dd77adea15c7 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -2299,6 +2299,7 @@ void rtw_unregister_hw(struct rtw_dev *rtwdev, struct ieee80211_hw *hw)
 
 	ieee80211_unregister_hw(hw);
 	rtw_unset_supported_band(hw, chip);
+	rtw_debugfs_deinit(rtwdev);
 }
 EXPORT_SYMBOL(rtw_unregister_hw);
 
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 9d21637cf5d5..b60a0f840e13 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -50,6 +50,7 @@ extern const struct ieee80211_ops rtw_ops;
 #define RTW_MAX_CHANNEL_NUM_5G 49
 
 struct rtw_dev;
+struct rtw_debugfs;
 
 enum rtw_hci_type {
 	RTW_HCI_TYPE_PCIE,
@@ -2053,7 +2054,7 @@ struct rtw_dev {
 	bool beacon_loss;
 	struct completion lps_leave_check;
 
-	struct dentry *debugfs;
+	struct rtw_debugfs *debugfs;
 
 	u8 sta_cnt;
 	u32 rts_threshold;
-- 
cgit v1.3-3-g829e


From 7e989b0c1e33210c07340bf5228aa83ea52515b5 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Thu, 18 Jul 2024 15:06:15 +0800
Subject: wifi: rtw88: select WANT_DEV_COREDUMP

We have invoked device coredump when fw crash.
Should select WANT_DEV_COREDUMP by ourselves.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240718070616.42217-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw88/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtw88/Kconfig b/drivers/net/wireless/realtek/rtw88/Kconfig
index 22838ede03cd..02b0d698413b 100644
--- a/drivers/net/wireless/realtek/rtw88/Kconfig
+++ b/drivers/net/wireless/realtek/rtw88/Kconfig
@@ -12,6 +12,7 @@ if RTW88
 
 config RTW88_CORE
 	tristate
+	select WANT_DEV_COREDUMP
 
 config RTW88_PCI
 	tristate
-- 
cgit v1.3-3-g829e


From d523dc49d13e8853b30ac7c5056bb506bbef1bcc Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Thu, 18 Jul 2024 15:06:16 +0800
Subject: wifi: rtw89: select WANT_DEV_COREDUMP

We have invoked device coredump when fw crash.
Should select WANT_DEV_COREDUMP by ourselves.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240718070616.42217-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtw89/Kconfig b/drivers/net/wireless/realtek/rtw89/Kconfig
index 3c9f864805b1..6278fd74e98e 100644
--- a/drivers/net/wireless/realtek/rtw89/Kconfig
+++ b/drivers/net/wireless/realtek/rtw89/Kconfig
@@ -12,6 +12,7 @@ if RTW89
 
 config RTW89_CORE
 	tristate
+	select WANT_DEV_COREDUMP
 
 config RTW89_PCI
 	tristate
-- 
cgit v1.3-3-g829e


From 6bd63e44e98e06efebc89c5b606259bf2fd8f96c Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:34 +0800
Subject: wifi: rtw89: 8852bt: add set_channel_rf

Add RF part of set_channel() is to configure RF registers, and then
hardware can TX/RX on specified frequency and bandwidth.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c | 226 +++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h |   3 +
 2 files changed, 229 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index 5bdabb45e968..0f2a74269b98 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -4017,3 +4017,229 @@ void rtw8852bt_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
 	else
 		rtw8852bt_tssi_default_txagc(rtwdev, phy_idx, false);
 }
+
+static void _bw_setting(struct rtw89_dev *rtwdev, enum rtw89_rf_path path,
+			enum rtw89_bandwidth bw, bool dav)
+{
+	u32 rf_reg18;
+	u32 reg18_addr = dav ? RR_CFGCH : RR_CFGCH_V1;
+
+	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[RFK]===> %s\n", __func__);
+
+	rf_reg18 = rtw89_read_rf(rtwdev, path, reg18_addr, RFREG_MASK);
+	if (rf_reg18 == INV_RF_DATA) {
+		rtw89_debug(rtwdev, RTW89_DBG_RFK,
+			    "[RFK]Invalid RF_0x18 for Path-%d\n", path);
+		return;
+	}
+	rf_reg18 &= ~RR_CFGCH_BW;
+
+	switch (bw) {
+	case RTW89_CHANNEL_WIDTH_5:
+	case RTW89_CHANNEL_WIDTH_10:
+	case RTW89_CHANNEL_WIDTH_20:
+		rf_reg18 |= FIELD_PREP(RR_CFGCH_BW, CFGCH_BW_20M);
+		break;
+	case RTW89_CHANNEL_WIDTH_40:
+		rf_reg18 |= FIELD_PREP(RR_CFGCH_BW, CFGCH_BW_40M);
+		break;
+	case RTW89_CHANNEL_WIDTH_80:
+		rf_reg18 |= FIELD_PREP(RR_CFGCH_BW, CFGCH_BW_80M);
+		break;
+	default:
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[RFK]Fail to set CH\n");
+	}
+
+	rf_reg18 &= ~(RR_CFGCH_POW_LCK | RR_CFGCH_TRX_AH | RR_CFGCH_BCN |
+		      RR_CFGCH_BW2) & RFREG_MASK;
+	rf_reg18 |= RR_CFGCH_BW2;
+	rtw89_write_rf(rtwdev, path, reg18_addr, RFREG_MASK, rf_reg18);
+
+	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[RFK] set %x at path%d, %x =0x%x\n",
+		    bw, path, reg18_addr,
+		    rtw89_read_rf(rtwdev, path, reg18_addr, RFREG_MASK));
+}
+
+static void _ctrl_bw(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		     enum rtw89_bandwidth bw)
+{
+	_bw_setting(rtwdev, RF_PATH_A, bw, true);
+	_bw_setting(rtwdev, RF_PATH_B, bw, true);
+	_bw_setting(rtwdev, RF_PATH_A, bw, false);
+	_bw_setting(rtwdev, RF_PATH_B, bw, false);
+}
+
+static bool _set_s0_arfc18(struct rtw89_dev *rtwdev, u32 val)
+{
+	u32 tmp;
+	int ret;
+
+	rtw89_write_rf(rtwdev, RF_PATH_A, RR_LCK_TRG, RR_LCK_TRGSEL, 0x1);
+	rtw89_write_rf(rtwdev, RF_PATH_A, RR_CFGCH, RFREG_MASK, val);
+
+	ret = read_poll_timeout_atomic(rtw89_read_rf, tmp, tmp == 0, 1, 1000,
+				       false, rtwdev, RF_PATH_A, RR_LPF, RR_LPF_BUSY);
+	if (ret)
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[LCK]LCK timeout\n");
+
+	rtw89_write_rf(rtwdev, RF_PATH_A, RR_LCK_TRG, RR_LCK_TRGSEL, 0x0);
+	return !!ret;
+}
+
+static void _lck_check(struct rtw89_dev *rtwdev)
+{
+	u32 tmp;
+
+	if (rtw89_read_rf(rtwdev, RF_PATH_A, RR_SYNFB, RR_SYNFB_LK) == 0) {
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[LCK]SYN MMD reset\n");
+
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_MMD, RR_MMD_RST_EN, 0x1);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_MMD, RR_MMD_RST_SYN, 0x0);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_MMD, RR_MMD_RST_SYN, 0x1);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_MMD, RR_MMD_RST_EN, 0x0);
+	}
+
+	udelay(10);
+
+	if (rtw89_read_rf(rtwdev, RF_PATH_A, RR_SYNFB, RR_SYNFB_LK) == 0) {
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[LCK]re-set RF 0x18\n");
+
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_LCK_TRG, RR_LCK_TRGSEL, 0x1);
+		tmp = rtw89_read_rf(rtwdev, RF_PATH_A, RR_CFGCH, RFREG_MASK);
+		_set_s0_arfc18(rtwdev, tmp);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_LCK_TRG, RR_LCK_TRGSEL, 0x0);
+	}
+
+	if (rtw89_read_rf(rtwdev, RF_PATH_A, RR_SYNFB, RR_SYNFB_LK) == 0) {
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[LCK]SYN off/on\n");
+
+		tmp = rtw89_read_rf(rtwdev, RF_PATH_A, RR_POW, RFREG_MASK);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_POW, RFREG_MASK, tmp);
+		tmp = rtw89_read_rf(rtwdev, RF_PATH_A, RR_SX, RFREG_MASK);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_SX, RFREG_MASK, tmp);
+
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_SYNLUT, RR_SYNLUT_MOD, 0x1);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_POW, RR_POW_SYN, 0x0);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_POW, RR_POW_SYN, 0x3);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_SYNLUT, RR_SYNLUT_MOD, 0x0);
+
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_LCK_TRG, RR_LCK_TRGSEL, 0x1);
+		tmp = rtw89_read_rf(rtwdev, RF_PATH_A, RR_CFGCH, RFREG_MASK);
+		_set_s0_arfc18(rtwdev, tmp);
+		rtw89_write_rf(rtwdev, RF_PATH_A, RR_LCK_TRG, RR_LCK_TRGSEL, 0x0);
+
+		rtw89_debug(rtwdev, RTW89_DBG_RFK, "[LCK]0xb2=%x, 0xc5=%x\n",
+			    rtw89_read_rf(rtwdev, RF_PATH_A, RR_VCO, RFREG_MASK),
+			    rtw89_read_rf(rtwdev, RF_PATH_A, RR_SYNFB, RFREG_MASK));
+	}
+}
+
+static void _set_ch(struct rtw89_dev *rtwdev, u32 val)
+{
+	bool timeout;
+	u32 bak;
+
+	bak = rtw89_read_rf(rtwdev, RF_PATH_A, RR_LDO, RFREG_MASK);
+	rtw89_write_rf(rtwdev, RF_PATH_A, RR_LDO, RR_LDO_SEL, 0x1);
+	timeout = _set_s0_arfc18(rtwdev, val);
+	rtw89_write_rf(rtwdev, RF_PATH_A, RR_LDO, RFREG_MASK, bak);
+	if (!timeout)
+		_lck_check(rtwdev);
+}
+
+static void _ch_setting(struct rtw89_dev *rtwdev, enum rtw89_rf_path path,
+			u8 central_ch, bool dav)
+{
+	u32 reg18_addr = dav ? RR_CFGCH : RR_CFGCH_V1;
+	bool is_2g_ch = central_ch <= 14;
+	u32 rf_reg18;
+
+	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[RFK]===> %s\n", __func__);
+
+	rf_reg18 = rtw89_read_rf(rtwdev, path, reg18_addr, RFREG_MASK);
+	rf_reg18 &= ~(RR_CFGCH_BAND1 | RR_CFGCH_POW_LCK | RR_CFGCH_TRX_AH |
+		      RR_CFGCH_BCN | RR_CFGCH_BAND0 | RR_CFGCH_CH);
+	rf_reg18 |= FIELD_PREP(RR_CFGCH_CH, central_ch);
+
+	if (!is_2g_ch)
+		rf_reg18 |= FIELD_PREP(RR_CFGCH_BAND1, CFGCH_BAND1_5G) |
+			    FIELD_PREP(RR_CFGCH_BAND0, CFGCH_BAND0_5G);
+
+	rf_reg18 &= ~(RR_CFGCH_POW_LCK | RR_CFGCH_TRX_AH | RR_CFGCH_BCN |
+		      RR_CFGCH_BW2) & RFREG_MASK;
+	rf_reg18 |= RR_CFGCH_BW2;
+
+	if (path == RF_PATH_A && dav)
+		_set_ch(rtwdev, rf_reg18);
+	else
+		rtw89_write_rf(rtwdev, path, reg18_addr, RFREG_MASK, rf_reg18);
+
+	rtw89_write_rf(rtwdev, path, RR_LCKST, RR_LCKST_BIN, 0);
+	rtw89_write_rf(rtwdev, path, RR_LCKST, RR_LCKST_BIN, 1);
+
+	rtw89_debug(rtwdev, RTW89_DBG_RFK,
+		    "[RFK]CH: %d for Path-%d, reg0x%x = 0x%x\n",
+		    central_ch, path, reg18_addr,
+		    rtw89_read_rf(rtwdev, path, reg18_addr, RFREG_MASK));
+}
+
+static void _ctrl_ch(struct rtw89_dev *rtwdev, u8 central_ch)
+{
+	_ch_setting(rtwdev, RF_PATH_A, central_ch, true);
+	_ch_setting(rtwdev, RF_PATH_B, central_ch, true);
+	_ch_setting(rtwdev, RF_PATH_A, central_ch, false);
+	_ch_setting(rtwdev, RF_PATH_B, central_ch, false);
+}
+
+static void _set_rxbb_bw(struct rtw89_dev *rtwdev, enum rtw89_bandwidth bw,
+			 enum rtw89_rf_path path)
+{
+	rtw89_write_rf(rtwdev, path, RR_LUTWE2, RR_LUTWE2_RTXBW, 0x1);
+	rtw89_write_rf(rtwdev, path, RR_LUTWA, RR_LUTWA_M2, 0x12);
+
+	if (bw == RTW89_CHANNEL_WIDTH_20)
+		rtw89_write_rf(rtwdev, path, RR_LUTWD0, RR_LUTWD0_LB, 0x1b);
+	else if (bw == RTW89_CHANNEL_WIDTH_40)
+		rtw89_write_rf(rtwdev, path, RR_LUTWD0, RR_LUTWD0_LB, 0x13);
+	else if (bw == RTW89_CHANNEL_WIDTH_80)
+		rtw89_write_rf(rtwdev, path, RR_LUTWD0, RR_LUTWD0_LB, 0xb);
+	else
+		rtw89_write_rf(rtwdev, path, RR_LUTWD0, RR_LUTWD0_LB, 0x3);
+
+	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[RFK] set S%d RXBB BW 0x3F = 0x%x\n",
+		    path, rtw89_read_rf(rtwdev, path, RR_LUTWD0, RR_LUTWD0_LB));
+
+	rtw89_write_rf(rtwdev, path, RR_LUTWE2, RR_LUTWE2_RTXBW, 0x0);
+}
+
+static void _rxbb_bw(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		     enum rtw89_bandwidth bw)
+{
+	u8 kpath, path;
+
+	kpath = _kpath(rtwdev, phy);
+
+	for (path = 0; path < RF_PATH_NUM_8852BT; path++) {
+		if (!(kpath & BIT(path)))
+			continue;
+
+		_set_rxbb_bw(rtwdev, bw, path);
+	}
+}
+
+static void rtw8852bt_ctrl_bw_ch(struct rtw89_dev *rtwdev,
+				 enum rtw89_phy_idx phy, u8 central_ch,
+				 enum rtw89_band band, enum rtw89_bandwidth bw)
+{
+	_ctrl_ch(rtwdev, central_ch);
+	_ctrl_bw(rtwdev, phy, bw);
+	_rxbb_bw(rtwdev, phy, bw);
+}
+
+void rtw8852bt_set_channel_rf(struct rtw89_dev *rtwdev,
+			      const struct rtw89_chan *chan,
+			      enum rtw89_phy_idx phy_idx)
+{
+	rtw8852bt_ctrl_bw_ch(rtwdev, phy_idx, chan->channel, chan->band_type,
+			     chan->band_width);
+}
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h
index 09918835c6e8..ef3d98f80400 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h
@@ -18,5 +18,8 @@ void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_
 void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
 void rtw8852bt_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
 				enum rtw89_phy_idx phy_idx);
+void rtw8852bt_set_channel_rf(struct rtw89_dev *rtwdev,
+			      const struct rtw89_chan *chan,
+			      enum rtw89_phy_idx phy_idx);
 
 #endif
-- 
cgit v1.3-3-g829e


From be457fbacea9fdceb1dbeb8034eaee9713962c06 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:35 +0800
Subject: wifi: rtw89: 8852bt: rfk: use predefined string choice for DPK
 enable/disable

clang warns precedence of '?:' and '&'. Even though original logic is
correct, use str_enable_disable() to avoid clang confusing. Another way to
fix is to add parentheses around '&', but I choose former one.

  >> drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c:1827:46: warning:
     operator '?:' has lower precedence than '&'; '&' will be evaluated
     first [-Wbitwise-conditional-parentheses]
    1827 |                     kidx, dpk->is_dpk_enable & off_reverse ? "enable" : "disable");
         |                           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ^

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202407200741.dMG9uvHU-lkp@intel.com/
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index 0f2a74269b98..e90a036db667 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -1824,7 +1824,7 @@ static void _dpk_onoff(struct rtw89_dev *rtwdev, enum rtw89_rf_path path, bool o
 			       BIT(24), val);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DPK] S%d[%d] DPK %s !!!\n", path,
-		    kidx, dpk->is_dpk_enable & off_reverse ? "enable" : "disable");
+		    kidx, str_enable_disable(dpk->is_dpk_enable & off_reverse));
 }
 
 static void _dpk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-- 
cgit v1.3-3-g829e


From c4dea0481e23b1e711d5ea3c3b1fe83e7b8e6797 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:36 +0800
Subject: wifi: rtw89: 8852bt: add chip_info of RTL8852BT

Add chip_info of RTL8852BT accordingly, including firmware elements
support, MAC memory quota (WDE, PLE and etc), SER IMR used by firmware,
BTC registers, register based H2C/C2H, WoWLAN stub.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.h        |  17 +-
 drivers/net/wireless/realtek/rtw89/mac.c       |   7 +
 drivers/net/wireless/realtek/rtw89/mac.h       |   6 +
 drivers/net/wireless/realtek/rtw89/reg.h       |  58 +++-
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 369 +++++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/rtw8852bt.h |   2 +
 6 files changed, 455 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/wireless/realtek/rtw89/rtw8852bt.c

diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index c3b4324c621c..935f89c09054 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3741,17 +3741,28 @@ enum rtw89_fw_element_id {
 	RTW89_FW_ELEMENT_ID_NUM,
 };
 
-#define BITS_OF_RTW89_TXPWR_FW_ELEMENTS \
+#define BITS_OF_RTW89_TXPWR_FW_ELEMENTS_NO_6GHZ \
 	(BIT(RTW89_FW_ELEMENT_ID_TXPWR_BYRATE) | \
 	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_2GHZ) | \
 	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_5GHZ) | \
-	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_6GHZ) | \
 	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_RU_2GHZ) | \
 	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_RU_5GHZ) | \
-	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_RU_6GHZ) | \
 	 BIT(RTW89_FW_ELEMENT_ID_TX_SHAPE_LMT) | \
 	 BIT(RTW89_FW_ELEMENT_ID_TX_SHAPE_LMT_RU))
 
+#define BITS_OF_RTW89_TXPWR_FW_ELEMENTS \
+	(BITS_OF_RTW89_TXPWR_FW_ELEMENTS_NO_6GHZ | \
+	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_6GHZ) | \
+	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_LMT_RU_6GHZ))
+
+#define RTW89_AX_GEN_DEF_NEEDED_FW_ELEMENTS_NO_6GHZ \
+	(BIT(RTW89_FW_ELEMENT_ID_BB_REG) | \
+	 BIT(RTW89_FW_ELEMENT_ID_RADIO_A) | \
+	 BIT(RTW89_FW_ELEMENT_ID_RADIO_B) | \
+	 BIT(RTW89_FW_ELEMENT_ID_RF_NCTL) | \
+	 BIT(RTW89_FW_ELEMENT_ID_TXPWR_TRK) | \
+	 BITS_OF_RTW89_TXPWR_FW_ELEMENTS_NO_6GHZ)
+
 #define RTW89_BE_GEN_DEF_NEEDED_FW_ELEMENTS (BIT(RTW89_FW_ELEMENT_ID_BBMCU0) | \
 					     BIT(RTW89_FW_ELEMENT_ID_BB_REG) | \
 					     BIT(RTW89_FW_ELEMENT_ID_RADIO_A) | \
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index e2399796aeb1..b479434e6301 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -1625,6 +1625,7 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.wde_size18 = {RTW89_WDE_PG_64, 0, 2048,},
 	/* 8852C PCIE SCC */
 	.wde_size19 = {RTW89_WDE_PG_64, 3328, 0,},
+	.wde_size23 = {RTW89_WDE_PG_64, 1022, 2,},
 	/* PCIE */
 	.ple_size0 = {RTW89_PLE_PG_128, 1520, 16,},
 	.ple_size0_v1 = {RTW89_PLE_PG_128, 2688, 240, 212992,},
@@ -1635,6 +1636,7 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.ple_size6 = {RTW89_PLE_PG_128, 496, 16,},
 	/* DLFW */
 	.ple_size8 = {RTW89_PLE_PG_128, 64, 960,},
+	.ple_size9 = {RTW89_PLE_PG_128, 2288, 16,},
 	/* 8852C DLFW */
 	.ple_size18 = {RTW89_PLE_PG_128, 2544, 16,},
 	/* 8852C PCIE SCC */
@@ -1652,6 +1654,7 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.wde_qt17 = {0, 0, 0,  0,},
 	/* 8852C PCIE SCC */
 	.wde_qt18 = {3228, 60, 0, 40,},
+	.wde_qt23 = {958, 48, 0, 16,},
 	.ple_qt0 = {320, 320, 32, 16, 13, 13, 292, 292, 64, 18, 1, 4, 0,},
 	.ple_qt1 = {320, 320, 32, 16, 1316, 1316, 1595, 1595, 1367, 1321, 1, 1307, 0,},
 	/* PCIE SCC */
@@ -1671,12 +1674,16 @@ const struct rtw89_mac_size_set rtw89_mac_size = {
 	.ple_qt46 = {525, 0, 16, 20, 13, 13, 178, 0, 32, 62, 8, 16,},
 	/* 8852C PCIE SCC */
 	.ple_qt47 = {525, 0, 32, 20, 1034, 13, 1199, 0, 1053, 62, 160, 1037,},
+	.ple_qt57 = {147, 0, 16, 20, 13, 13, 178, 0, 32, 14, 8, 0,},
 	/* PCIE 64 */
 	.ple_qt58 = {147, 0, 16, 20, 157, 13, 229, 0, 172, 14, 24, 0,},
+	.ple_qt59 = {147, 0, 32, 20, 1860, 13, 2025, 0, 1879, 14, 24, 0,},
 	/* 8852A PCIE WOW */
 	.ple_qt_52a_wow = {264, 0, 32, 20, 64, 13, 1005, 0, 64, 128, 120,},
 	/* 8852B PCIE WOW */
 	.ple_qt_52b_wow = {147, 0, 16, 20, 157, 13, 133, 0, 172, 14, 24, 0,},
+	/* 8852BT PCIE WOW */
+	.ple_qt_52bt_wow = {147, 0, 32, 20, 1860, 13, 1929, 0, 1879, 14, 24, 0,},
 	/* 8851B PCIE WOW */
 	.ple_qt_51b_wow = {147, 0, 16, 20, 157, 13, 133, 0, 172, 14, 24, 0,},
 	.ple_rsvd_qt0 = {2, 107, 107, 6, 6, 6, 6, 0, 0, 0,},
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index d5895516b3ed..02052fbbec1a 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -885,12 +885,14 @@ struct rtw89_mac_size_set {
 	const struct rtw89_dle_size wde_size9;
 	const struct rtw89_dle_size wde_size18;
 	const struct rtw89_dle_size wde_size19;
+	const struct rtw89_dle_size wde_size23;
 	const struct rtw89_dle_size ple_size0;
 	const struct rtw89_dle_size ple_size0_v1;
 	const struct rtw89_dle_size ple_size3_v1;
 	const struct rtw89_dle_size ple_size4;
 	const struct rtw89_dle_size ple_size6;
 	const struct rtw89_dle_size ple_size8;
+	const struct rtw89_dle_size ple_size9;
 	const struct rtw89_dle_size ple_size18;
 	const struct rtw89_dle_size ple_size19;
 	const struct rtw89_wde_quota wde_qt0;
@@ -900,6 +902,7 @@ struct rtw89_mac_size_set {
 	const struct rtw89_wde_quota wde_qt7;
 	const struct rtw89_wde_quota wde_qt17;
 	const struct rtw89_wde_quota wde_qt18;
+	const struct rtw89_wde_quota wde_qt23;
 	const struct rtw89_ple_quota ple_qt0;
 	const struct rtw89_ple_quota ple_qt1;
 	const struct rtw89_ple_quota ple_qt4;
@@ -911,9 +914,12 @@ struct rtw89_mac_size_set {
 	const struct rtw89_ple_quota ple_qt45;
 	const struct rtw89_ple_quota ple_qt46;
 	const struct rtw89_ple_quota ple_qt47;
+	const struct rtw89_ple_quota ple_qt57;
 	const struct rtw89_ple_quota ple_qt58;
+	const struct rtw89_ple_quota ple_qt59;
 	const struct rtw89_ple_quota ple_qt_52a_wow;
 	const struct rtw89_ple_quota ple_qt_52b_wow;
+	const struct rtw89_ple_quota ple_qt_52bt_wow;
 	const struct rtw89_ple_quota ple_qt_51b_wow;
 	const struct rtw89_rsvd_quota ple_rsvd_qt0;
 	const struct rtw89_rsvd_quota ple_rsvd_qt1;
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 7df36f3bff0b..15b17e2cf99b 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -706,6 +706,14 @@
 				B_AX_HDT_CHANNEL_DMA_ERR_INT_EN | \
 				B_AX_HDT_TOTAL_LEN_ERR_INT_EN | \
 				B_AX_HDT_DMA_PROCESS_ERR_INT_EN)
+#define B_AX_HOST_DISP_IMR_SET_V01 (B_AX_HDT_CHANNEL_DIFF_ERR_INT_EN | \
+				    B_AX_HDT_PAYLOAD_OVERFLOW_INT_EN | \
+				    B_AX_HDT_PAYLOAD_UNDERFLOW_INT_EN | \
+				    B_AX_HDT_CHANNEL_DMA_ERR_INT_EN | \
+				    B_AX_HDT_TOTAL_LEN_ERR_INT_EN | \
+				    B_AX_HDT_DMA_PROCESS_ERR_INT_EN | \
+				    B_AX_HDT_RX_WRITE_OVERFLOW_INT_EN | \
+				    B_AX_HDT_RX_WRITE_UNDERFLOW_INT_EN)
 
 #define B_AX_HR_WRFF_UNDERFLOW_ERR_INT_EN BIT(31)
 #define B_AX_HR_WRFF_OVERFLOW_ERR_INT_EN BIT(30)
@@ -1096,6 +1104,7 @@
 #define B_AX_WDE_BUFMGN_FRZTMR_MODE BIT(0)
 
 #define R_AX_WDE_ERR_IMR 0x8C38
+#define B_AX_WDE_DATCHN_UAPG_ERR_INT_EN BIT(30)
 #define B_AX_WDE_DATCHN_RRDY_ERR_INT_EN BIT(27)
 #define B_AX_WDE_DATCHN_FRZTO_ERR_INT_EN BIT(26)
 #define B_AX_WDE_DATCHN_NULLPG_ERR_INT_EN BIT(25)
@@ -1135,6 +1144,29 @@
 			  B_AX_WDE_DATCHN_ARBT_ERR_INT_EN | \
 			  B_AX_WDE_DATCHN_NULLPG_ERR_INT_EN | \
 			  B_AX_WDE_DATCHN_FRZTO_ERR_INT_EN)
+#define B_AX_WDE_IMR_CLR_V01 (B_AX_WDE_BUFREQ_QTAID_ERR_INT_EN | \
+			      B_AX_WDE_BUFREQ_UNAVAL_ERR_INT_EN | \
+			      B_AX_WDE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
+			      B_AX_WDE_BUFRTN_SIZE_ERR_INT_EN | \
+			      B_AX_WDE_BUFREQ_SRCHTAILPG_ERR_INT_EN | \
+			      B_AX_WDE_GETNPG_STRPG_ERR_INT_EN | \
+			      B_AX_WDE_GETNPG_PGOFST_ERR_INT_EN | \
+			      B_AX_WDE_BUFMGN_FRZTO_ERR_INT_EN | \
+			      B_AX_WDE_QUE_CMDTYPE_ERR_INT_EN | \
+			      B_AX_WDE_QUE_DSTQUEID_ERR_INT_EN | \
+			      B_AX_WDE_QUE_SRCQUEID_ERR_INT_EN | \
+			      B_AX_WDE_ENQ_PKTCNT_OVRF_ERR_INT_EN | \
+			      B_AX_WDE_ENQ_PKTCNT_NVAL_ERR_INT_EN | \
+			      B_AX_WDE_PREPKTLLT_AD_ERR_INT_EN | \
+			      B_AX_WDE_NXTPKTLL_AD_ERR_INT_EN | \
+			      B_AX_WDE_QUEMGN_FRZTO_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_ARBT_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_NULLPG_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_FRZTO_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_RRDY_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_ADRERR_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_CAMREQ_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_UAPG_ERR_INT_EN)
 #define B_AX_WDE_IMR_SET (B_AX_WDE_BUFREQ_QTAID_ERR_INT_EN | \
 			  B_AX_WDE_BUFREQ_UNAVAL_ERR_INT_EN | \
 			  B_AX_WDE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
@@ -1154,6 +1186,28 @@
 			  B_AX_WDE_DATCHN_ARBT_ERR_INT_EN | \
 			  B_AX_WDE_DATCHN_NULLPG_ERR_INT_EN | \
 			  B_AX_WDE_DATCHN_FRZTO_ERR_INT_EN)
+#define B_AX_WDE_IMR_SET_V01 (B_AX_WDE_BUFREQ_QTAID_ERR_INT_EN | \
+			      B_AX_WDE_BUFREQ_UNAVAL_ERR_INT_EN | \
+			      B_AX_WDE_BUFRTN_INVLD_PKTID_ERR_INT_EN | \
+			      B_AX_WDE_BUFRTN_SIZE_ERR_INT_EN | \
+			      B_AX_WDE_BUFREQ_SRCHTAILPG_ERR_INT_EN | \
+			      B_AX_WDE_GETNPG_STRPG_ERR_INT_EN | \
+			      B_AX_WDE_GETNPG_PGOFST_ERR_INT_EN | \
+			      B_AX_WDE_BUFMGN_FRZTO_ERR_INT_EN | \
+			      B_AX_WDE_QUE_CMDTYPE_ERR_INT_EN | \
+			      B_AX_WDE_QUE_DSTQUEID_ERR_INT_EN | \
+			      B_AX_WDE_QUE_SRCQUEID_ERR_INT_EN | \
+			      B_AX_WDE_ENQ_PKTCNT_OVRF_ERR_INT_EN | \
+			      B_AX_WDE_ENQ_PKTCNT_NVAL_ERR_INT_EN | \
+			      B_AX_WDE_PREPKTLLT_AD_ERR_INT_EN | \
+			      B_AX_WDE_NXTPKTLL_AD_ERR_INT_EN | \
+			      B_AX_WDE_QUEMGN_FRZTO_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_ARBT_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_NULLPG_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_FRZTO_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_RRDY_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_ADRERR_ERR_INT_EN | \
+			      B_AX_WDE_DATCHN_CAMREQ_ERR_INT_EN)
 
 #define B_AX_WDE_DATCHN_CAMREQ_ERR_INT_EN BIT(29)
 #define B_AX_WDE_DATCHN_ADRERR_ERR_INT_EN BIT(28)
@@ -3098,7 +3152,9 @@
 				 B_AX_OFDM_CCA_TIMEOUT_INT_EN | \
 				 B_AX_DATA_ON_TIMEOUT_INT_EN | \
 				 B_AX_STS_ON_TIMEOUT_INT_EN | \
-				 B_AX_CSI_ON_TIMEOUT_INT_EN)
+				 B_AX_CSI_ON_TIMEOUT_INT_EN | \
+				 B_AX_PHYINTF_TIMEOUT_THR_MSAK)
+#define B_AX_PHYINFO_IMR_SET (B_AX_PHY_TXON_TIMEOUT_INT_EN | 0x7)
 
 #define R_AX_PHYINFO_ERR_ISR 0xCCFC
 #define R_AX_PHYINFO_ERR_ISR_C1 0xECFC
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
new file mode 100644
index 000000000000..0ecd9d41c2ad
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -0,0 +1,369 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2024 Realtek Corporation
+ */
+
+#include "coex.h"
+#include "fw.h"
+#include "mac.h"
+#include "phy.h"
+#include "reg.h"
+#include "rtw8852bt.h"
+
+#define RTW8852BT_FW_FORMAT_MAX 0
+#define RTW8852BT_FW_BASENAME "rtw89/rtw8852bt_fw"
+#define RTW8852BT_MODULE_FIRMWARE \
+	RTW8852BT_FW_BASENAME ".bin"
+
+static const struct rtw89_hfc_ch_cfg rtw8852bt_hfc_chcfg_pcie[] = {
+	{16, 742, grp_0}, /* ACH 0 */
+	{16, 742, grp_0}, /* ACH 1 */
+	{16, 742, grp_0}, /* ACH 2 */
+	{16, 742, grp_0}, /* ACH 3 */
+	{0, 0, grp_0}, /* ACH 4 */
+	{0, 0, grp_0}, /* ACH 5 */
+	{0, 0, grp_0}, /* ACH 6 */
+	{0, 0, grp_0}, /* ACH 7 */
+	{15, 743, grp_0}, /* B0MGQ */
+	{15, 743, grp_0}, /* B0HIQ */
+	{0, 0, grp_0}, /* B1MGQ */
+	{0, 0, grp_0}, /* B1HIQ */
+	{40, 0, 0} /* FWCMDQ */
+};
+
+static const struct rtw89_hfc_pub_cfg rtw8852bt_hfc_pubcfg_pcie = {
+	958, /* Group 0 */
+	0, /* Group 1 */
+	958, /* Public Max */
+	0 /* WP threshold */
+};
+
+static const struct rtw89_hfc_param_ini rtw8852bt_hfc_param_ini_pcie[] = {
+	[RTW89_QTA_SCC] = {rtw8852bt_hfc_chcfg_pcie, &rtw8852bt_hfc_pubcfg_pcie,
+			   &rtw89_mac_size.hfc_preccfg_pcie, RTW89_HCIFC_POH},
+	[RTW89_QTA_DLFW] = {NULL, NULL, &rtw89_mac_size.hfc_preccfg_pcie,
+			    RTW89_HCIFC_POH},
+	[RTW89_QTA_INVALID] = {NULL},
+};
+
+static const struct rtw89_dle_mem rtw8852bt_dle_mem_pcie[] = {
+	[RTW89_QTA_SCC] = {RTW89_QTA_SCC, &rtw89_mac_size.wde_size23,
+			   &rtw89_mac_size.ple_size9, &rtw89_mac_size.wde_qt23,
+			   &rtw89_mac_size.wde_qt23, &rtw89_mac_size.ple_qt57,
+			   &rtw89_mac_size.ple_qt59},
+	[RTW89_QTA_WOW] = {RTW89_QTA_WOW, &rtw89_mac_size.wde_size23,
+			   &rtw89_mac_size.ple_size9, &rtw89_mac_size.wde_qt23,
+			   &rtw89_mac_size.wde_qt23, &rtw89_mac_size.ple_qt57,
+			   &rtw89_mac_size.ple_qt_52bt_wow},
+	[RTW89_QTA_DLFW] = {RTW89_QTA_DLFW, &rtw89_mac_size.wde_size4,
+			    &rtw89_mac_size.ple_size4, &rtw89_mac_size.wde_qt4,
+			    &rtw89_mac_size.wde_qt4, &rtw89_mac_size.ple_qt13,
+			    &rtw89_mac_size.ple_qt13},
+	[RTW89_QTA_INVALID] = {RTW89_QTA_INVALID, NULL, NULL, NULL, NULL, NULL,
+			       NULL},
+};
+
+static const u32 rtw8852bt_h2c_regs[RTW89_H2CREG_MAX] = {
+	R_AX_H2CREG_DATA0, R_AX_H2CREG_DATA1,  R_AX_H2CREG_DATA2,
+	R_AX_H2CREG_DATA3
+};
+
+static const u32 rtw8852bt_c2h_regs[RTW89_C2HREG_MAX] = {
+	R_AX_C2HREG_DATA0, R_AX_C2HREG_DATA1, R_AX_C2HREG_DATA2,
+	R_AX_C2HREG_DATA3
+};
+
+static const u32 rtw8852bt_wow_wakeup_regs[RTW89_WOW_REASON_NUM] = {
+	R_AX_C2HREG_DATA3 + 3, R_AX_C2HREG_DATA3 + 3,
+};
+
+static const struct rtw89_page_regs rtw8852bt_page_regs = {
+	.hci_fc_ctrl	= R_AX_HCI_FC_CTRL,
+	.ch_page_ctrl	= R_AX_CH_PAGE_CTRL,
+	.ach_page_ctrl	= R_AX_ACH0_PAGE_CTRL,
+	.ach_page_info	= R_AX_ACH0_PAGE_INFO,
+	.pub_page_info3	= R_AX_PUB_PAGE_INFO3,
+	.pub_page_ctrl1	= R_AX_PUB_PAGE_CTRL1,
+	.pub_page_ctrl2	= R_AX_PUB_PAGE_CTRL2,
+	.pub_page_info1	= R_AX_PUB_PAGE_INFO1,
+	.pub_page_info2 = R_AX_PUB_PAGE_INFO2,
+	.wp_page_ctrl1	= R_AX_WP_PAGE_CTRL1,
+	.wp_page_ctrl2	= R_AX_WP_PAGE_CTRL2,
+	.wp_page_info1	= R_AX_WP_PAGE_INFO1,
+};
+
+static const struct rtw89_reg_def rtw8852bt_dcfo_comp = {
+	R_DCFO_COMP_S0, B_DCFO_COMP_S0_MSK
+};
+
+static const struct rtw89_imr_info rtw8852bt_imr_info = {
+	.wdrls_imr_set		= B_AX_WDRLS_IMR_SET,
+	.wsec_imr_reg		= R_AX_SEC_DEBUG,
+	.wsec_imr_set		= B_AX_IMR_ERROR,
+	.mpdu_tx_imr_set	= 0,
+	.mpdu_rx_imr_set	= 0,
+	.sta_sch_imr_set	= B_AX_STA_SCHEDULER_IMR_SET,
+	.txpktctl_imr_b0_reg	= R_AX_TXPKTCTL_ERR_IMR_ISR,
+	.txpktctl_imr_b0_clr	= B_AX_TXPKTCTL_IMR_B0_CLR,
+	.txpktctl_imr_b0_set	= B_AX_TXPKTCTL_IMR_B0_SET,
+	.txpktctl_imr_b1_reg	= R_AX_TXPKTCTL_ERR_IMR_ISR_B1,
+	.txpktctl_imr_b1_clr	= B_AX_TXPKTCTL_IMR_B1_CLR,
+	.txpktctl_imr_b1_set	= B_AX_TXPKTCTL_IMR_B1_SET,
+	.wde_imr_clr		= B_AX_WDE_IMR_CLR_V01,
+	.wde_imr_set		= B_AX_WDE_IMR_SET_V01,
+	.ple_imr_clr		= B_AX_PLE_IMR_CLR,
+	.ple_imr_set		= B_AX_PLE_IMR_SET,
+	.host_disp_imr_clr	= B_AX_HOST_DISP_IMR_CLR,
+	.host_disp_imr_set	= B_AX_HOST_DISP_IMR_SET_V01,
+	.cpu_disp_imr_clr	= B_AX_CPU_DISP_IMR_CLR,
+	.cpu_disp_imr_set	= B_AX_CPU_DISP_IMR_SET,
+	.other_disp_imr_clr	= B_AX_OTHER_DISP_IMR_CLR,
+	.other_disp_imr_set	= 0,
+	.bbrpt_com_err_imr_reg	= R_AX_BBRPT_COM_ERR_IMR_ISR,
+	.bbrpt_chinfo_err_imr_reg = R_AX_BBRPT_CHINFO_ERR_IMR_ISR,
+	.bbrpt_err_imr_set	= 0,
+	.bbrpt_dfs_err_imr_reg	= R_AX_BBRPT_DFS_ERR_IMR_ISR,
+	.ptcl_imr_clr		= B_AX_PTCL_IMR_CLR_ALL,
+	.ptcl_imr_set		= B_AX_PTCL_IMR_SET,
+	.cdma_imr_0_reg		= R_AX_DLE_CTRL,
+	.cdma_imr_0_clr		= B_AX_DLE_IMR_CLR,
+	.cdma_imr_0_set		= B_AX_DLE_IMR_SET,
+	.cdma_imr_1_reg		= 0,
+	.cdma_imr_1_clr		= 0,
+	.cdma_imr_1_set		= 0,
+	.phy_intf_imr_reg	= R_AX_PHYINFO_ERR_IMR,
+	.phy_intf_imr_clr	= B_AX_PHYINFO_IMR_EN_ALL,
+	.phy_intf_imr_set	= B_AX_PHYINFO_IMR_SET,
+	.rmac_imr_reg		= R_AX_RMAC_ERR_ISR,
+	.rmac_imr_clr		= B_AX_RMAC_IMR_CLR,
+	.rmac_imr_set		= B_AX_RMAC_IMR_SET,
+	.tmac_imr_reg		= R_AX_TMAC_ERR_IMR_ISR,
+	.tmac_imr_clr		= B_AX_TMAC_IMR_CLR,
+	.tmac_imr_set		= B_AX_TMAC_IMR_SET,
+};
+
+static const struct rtw89_rrsr_cfgs rtw8852bt_rrsr_cfgs = {
+	.ref_rate = {R_AX_TRXPTCL_RRSR_CTL_0, B_AX_WMAC_RESP_REF_RATE_SEL, 0},
+	.rsc = {R_AX_TRXPTCL_RRSR_CTL_0, B_AX_WMAC_RESP_RSC_MASK, 2},
+};
+
+static const struct rtw89_dig_regs rtw8852bt_dig_regs = {
+	.seg0_pd_reg = R_SEG0R_PD_V1,
+	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
+	.pd_spatial_reuse_en = B_SEG0R_PD_SPATIAL_REUSE_EN_MSK_V1,
+	.bmode_pd_reg = R_BMODE_PDTH_EN_V1,
+	.bmode_cca_rssi_limit_en = B_BMODE_PDTH_LIMIT_EN_MSK_V1,
+	.bmode_pd_lower_bound_reg = R_BMODE_PDTH_V1,
+	.bmode_rssi_nocca_low_th_mask = B_BMODE_PDTH_LOWER_BOUND_MSK_V1,
+	.p0_lna_init = {R_PATH0_LNA_INIT_V1, B_PATH0_LNA_INIT_IDX_MSK},
+	.p1_lna_init = {R_PATH1_LNA_INIT_V1, B_PATH1_LNA_INIT_IDX_MSK},
+	.p0_tia_init = {R_PATH0_TIA_INIT_V1, B_PATH0_TIA_INIT_IDX_MSK_V1},
+	.p1_tia_init = {R_PATH1_TIA_INIT_V1, B_PATH1_TIA_INIT_IDX_MSK_V1},
+	.p0_rxb_init = {R_PATH0_RXB_INIT_V1, B_PATH0_RXB_INIT_IDX_MSK_V1},
+	.p1_rxb_init = {R_PATH1_RXB_INIT_V1, B_PATH1_RXB_INIT_IDX_MSK_V1},
+	.p0_p20_pagcugc_en = {R_PATH0_P20_FOLLOW_BY_PAGCUGC_V2,
+			      B_PATH0_P20_FOLLOW_BY_PAGCUGC_EN_MSK},
+	.p0_s20_pagcugc_en = {R_PATH0_S20_FOLLOW_BY_PAGCUGC_V2,
+			      B_PATH0_S20_FOLLOW_BY_PAGCUGC_EN_MSK},
+	.p1_p20_pagcugc_en = {R_PATH1_P20_FOLLOW_BY_PAGCUGC_V2,
+			      B_PATH1_P20_FOLLOW_BY_PAGCUGC_EN_MSK},
+	.p1_s20_pagcugc_en = {R_PATH1_S20_FOLLOW_BY_PAGCUGC_V2,
+			      B_PATH1_S20_FOLLOW_BY_PAGCUGC_EN_MSK},
+};
+
+static const struct rtw89_edcca_regs rtw8852bt_edcca_regs = {
+	.edcca_level			= R_SEG0R_EDCCA_LVL_V1,
+	.edcca_mask			= B_EDCCA_LVL_MSK0,
+	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
+	.ppdu_level			= R_SEG0R_EDCCA_LVL_V1,
+	.ppdu_mask			= B_EDCCA_LVL_MSK3,
+	.rpt_a				= R_EDCCA_RPT_A,
+	.rpt_b				= R_EDCCA_RPT_B,
+	.rpt_sel			= R_EDCCA_RPT_SEL,
+	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
+	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
+};
+
+static const struct rtw89_btc_rf_trx_para rtw89_btc_8852bt_rf_ul[] = {
+	{255, 0, 0, 7}, /* 0 -> original */
+	{255, 2, 0, 7}, /* 1 -> for BT-connected ACI issue && BTG co-rx */
+	{255, 0, 0, 7}, /* 2 ->reserved for shared-antenna */
+	{255, 0, 0, 7}, /* 3- >reserved for shared-antenna */
+	{255, 0, 0, 7}, /* 4 ->reserved for shared-antenna */
+	{255, 1, 0, 7}, /* the below id is for non-shared-antenna free-run */
+	{6, 1, 0, 7},
+	{13, 1, 0, 7},
+	{13, 1, 0, 7}
+};
+
+static const struct rtw89_btc_rf_trx_para rtw89_btc_8852bt_rf_dl[] = {
+	{255, 0, 0, 7}, /* 0 -> original */
+	{255, 2, 0, 7}, /* 1 -> reserved for shared-antenna */
+	{255, 0, 0, 7}, /* 2 ->reserved for shared-antenna */
+	{255, 0, 0, 7}, /* 3- >reserved for shared-antenna */
+	{255, 0, 0, 7}, /* 4 ->reserved for shared-antenna */
+	{255, 1, 0, 7}, /* the below id is for non-shared-antenna free-run */
+	{255, 1, 0, 7},
+	{255, 1, 0, 7},
+	{255, 1, 0, 7}
+};
+
+static const struct rtw89_btc_fbtc_mreg rtw89_btc_8852bt_mon_reg[] = {
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda24),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda28),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda2c),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda30),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda4c),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda10),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda20),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xda34),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xcef4),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0x8424),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xd200),
+	RTW89_DEF_FBTC_MREG(REG_MAC, 4, 0xd220),
+	RTW89_DEF_FBTC_MREG(REG_BB, 4, 0x980),
+	RTW89_DEF_FBTC_MREG(REG_BB, 4, 0x4aa4),
+	RTW89_DEF_FBTC_MREG(REG_BB, 4, 0x4778),
+	RTW89_DEF_FBTC_MREG(REG_BB, 4, 0x476c),
+};
+
+static const u8 rtw89_btc_8852bt_wl_rssi_thres[BTC_WL_RSSI_THMAX] = {70, 60, 50, 40};
+static const u8 rtw89_btc_8852bt_bt_rssi_thres[BTC_BT_RSSI_THMAX] = {50, 40, 30, 20};
+
+static const struct rtw89_chip_ops rtw8852bt_chip_ops = {
+};
+
+#ifdef CONFIG_PM
+static const struct wiphy_wowlan_support rtw_wowlan_stub_8852bt = {
+	.flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT,
+	.n_patterns = RTW89_MAX_PATTERN_NUM,
+	.pattern_max_len = RTW89_MAX_PATTERN_SIZE,
+	.pattern_min_len = 1,
+};
+#endif
+
+const struct rtw89_chip_info rtw8852bt_chip_info = {
+	.chip_id		= RTL8852BT,
+	.chip_gen		= RTW89_CHIP_AX,
+	.ops			= &rtw8852bt_chip_ops,
+	.mac_def		= &rtw89_mac_gen_ax,
+	.phy_def		= &rtw89_phy_gen_ax,
+	.fw_basename		= RTW8852BT_FW_BASENAME,
+	.fw_format_max		= RTW8852BT_FW_FORMAT_MAX,
+	.try_ce_fw		= true,
+	.bbmcu_nr		= 0,
+	.needed_fw_elms		= RTW89_AX_GEN_DEF_NEEDED_FW_ELEMENTS_NO_6GHZ,
+	.fifo_size		= 458752,
+	.small_fifo_size	= true,
+	.dle_scc_rsvd_size	= 98304,
+	.max_amsdu_limit	= 5000,
+	.dis_2g_40m_ul_ofdma	= true,
+	.rsvd_ple_ofst		= 0x6f800,
+	.hfc_param_ini		= rtw8852bt_hfc_param_ini_pcie,
+	.dle_mem		= rtw8852bt_dle_mem_pcie,
+	.wde_qempty_acq_grpnum	= 4,
+	.wde_qempty_mgq_grpsel	= 4,
+	.rf_base_addr		= {0xe000, 0xf000},
+	.pwr_on_seq		= NULL,
+	.pwr_off_seq		= NULL,
+	.bb_table		= NULL,
+	.bb_gain_table		= NULL,
+	.rf_table		= {},
+	.nctl_table		= NULL,
+	.nctl_post_table	= NULL,
+	.dflt_parms		= NULL,
+	.rfe_parms_conf		= NULL,
+	.txpwr_factor_rf	= 2,
+	.txpwr_factor_mac	= 1,
+	.dig_table		= NULL,
+	.dig_regs		= &rtw8852bt_dig_regs,
+	.tssi_dbw_table		= NULL,
+	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
+	.support_chanctx_num	= 1,
+	.support_rnr		= false,
+	.support_bands		= BIT(NL80211_BAND_2GHZ) |
+				  BIT(NL80211_BAND_5GHZ),
+	.support_bandwidths	= BIT(NL80211_CHAN_WIDTH_20) |
+				  BIT(NL80211_CHAN_WIDTH_40) |
+				  BIT(NL80211_CHAN_WIDTH_80),
+	.support_unii4		= true,
+	.ul_tb_waveform_ctrl	= true,
+	.ul_tb_pwr_diff		= false,
+	.hw_sec_hdr		= false,
+	.rf_path_num		= 2,
+	.tx_nss			= 2,
+	.rx_nss			= 2,
+	.acam_num		= 128,
+	.bcam_num		= 10,
+	.scam_num		= 128,
+	.bacam_num		= 2,
+	.bacam_dynamic_num	= 4,
+	.bacam_ver		= RTW89_BACAM_V0,
+	.ppdu_max_usr		= 4,
+	.sec_ctrl_efuse_size	= 4,
+	.physical_efuse_size	= 1216,
+	.logical_efuse_size	= 2048,
+	.limit_efuse_size	= 1280,
+	.dav_phy_efuse_size	= 96,
+	.dav_log_efuse_size	= 16,
+	.efuse_blocks		= NULL,
+	.phycap_addr		= 0x580,
+	.phycap_size		= 128,
+	.para_ver		= 0,
+	.wlcx_desired		= 0x070e0000,
+	.btcx_desired		= 0x7,
+	.scbd			= 0x1,
+	.mailbox		= 0x1,
+
+	.afh_guard_ch		= 6,
+	.wl_rssi_thres		= rtw89_btc_8852bt_wl_rssi_thres,
+	.bt_rssi_thres		= rtw89_btc_8852bt_bt_rssi_thres,
+	.rssi_tol		= 2,
+	.mon_reg_num		= ARRAY_SIZE(rtw89_btc_8852bt_mon_reg),
+	.mon_reg		= rtw89_btc_8852bt_mon_reg,
+	.rf_para_ulink_num	= ARRAY_SIZE(rtw89_btc_8852bt_rf_ul),
+	.rf_para_ulink		= rtw89_btc_8852bt_rf_ul,
+	.rf_para_dlink_num	= ARRAY_SIZE(rtw89_btc_8852bt_rf_dl),
+	.rf_para_dlink		= rtw89_btc_8852bt_rf_dl,
+	.ps_mode_supported	= BIT(RTW89_PS_MODE_RFOFF) |
+				  BIT(RTW89_PS_MODE_CLK_GATED) |
+				  BIT(RTW89_PS_MODE_PWR_GATED),
+	.low_power_hci_modes	= 0,
+	.h2c_cctl_func_id	= H2C_FUNC_MAC_CCTLINFO_UD,
+	.hci_func_en_addr	= R_AX_HCI_FUNC_EN,
+	.h2c_desc_size		= sizeof(struct rtw89_txwd_body),
+	.txwd_body_size		= sizeof(struct rtw89_txwd_body),
+	.txwd_info_size		= sizeof(struct rtw89_txwd_info),
+	.h2c_ctrl_reg		= R_AX_H2CREG_CTRL,
+	.h2c_counter_reg	= {R_AX_UDM1 + 1, B_AX_UDM1_HALMAC_H2C_DEQ_CNT_MASK >> 8},
+	.h2c_regs		= rtw8852bt_h2c_regs,
+	.c2h_ctrl_reg		= R_AX_C2HREG_CTRL,
+	.c2h_counter_reg	= {R_AX_UDM1 + 1, B_AX_UDM1_HALMAC_C2H_ENQ_CNT_MASK >> 8},
+	.c2h_regs		= rtw8852bt_c2h_regs,
+	.page_regs		= &rtw8852bt_page_regs,
+	.wow_reason_reg		= rtw8852bt_wow_wakeup_regs,
+	.cfo_src_fd		= true,
+	.cfo_hw_comp		= true,
+	.dcfo_comp		= &rtw8852bt_dcfo_comp,
+	.dcfo_comp_sft		= 10,
+	.imr_info		= &rtw8852bt_imr_info,
+	.imr_dmac_table		= NULL,
+	.imr_cmac_table		= NULL,
+	.rrsr_cfgs		= &rtw8852bt_rrsr_cfgs,
+	.bss_clr_vld		= {R_BSS_CLR_MAP_V1, B_BSS_CLR_MAP_VLD0},
+	.bss_clr_map_reg	= R_BSS_CLR_MAP_V1,
+	.dma_ch_mask		= BIT(RTW89_DMA_ACH4) | BIT(RTW89_DMA_ACH5) |
+				  BIT(RTW89_DMA_ACH6) | BIT(RTW89_DMA_ACH7) |
+				  BIT(RTW89_DMA_B1MG) | BIT(RTW89_DMA_B1HI),
+	.edcca_regs		= &rtw8852bt_edcca_regs,
+#ifdef CONFIG_PM
+	.wowlan_stub		= &rtw_wowlan_stub_8852bt,
+#endif
+	.xtal_info		= NULL,
+};
+EXPORT_SYMBOL(rtw8852bt_chip_info);
+
+MODULE_FIRMWARE(RTW8852BT_MODULE_FIRMWARE);
+MODULE_AUTHOR("Realtek Corporation");
+MODULE_DESCRIPTION("Realtek 802.11ax wireless 8852BT driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.h b/drivers/net/wireless/realtek/rtw89/rtw8852bt.h
index 6177f36ad667..b76b36aaf025 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.h
@@ -10,4 +10,6 @@
 #define RF_PATH_NUM_8852BT 2
 #define BB_PATH_NUM_8852BT 2
 
+extern const struct rtw89_chip_info rtw8852bt_chip_info;
+
 #endif
-- 
cgit v1.3-3-g829e


From 62eddca4d2961c6b9512b675ac199068f7b47578 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:37 +0800
Subject: wifi: rtw89: 8852bt: add chip_ops of RTL8852BT

Add chip_info of RTL8852BT accordingly, including power on/off function,
BB reset, TSSI settings while setting channel, RF calibration, and
BT coexistence.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.h      |   2 +
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 461 +++++++++++++++++++++++++
 2 files changed, 463 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index 0e5f268616f7..7678fb8bcf7e 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -193,6 +193,8 @@ enum btc_wa_type {
 	BTC_WA_5G_HI_CH_RX = BIT(0),
 	BTC_WA_NULL_AP = BIT(1),
 	BTC_WA_HFP_ZB = BIT(2),  /* HFP PTA req bit4 define issue */
+	BTC_WA_HFP_LAG = BIT(3),  /* 52BT WL break BT Rx lag issue */
+	BTC_WA_INIT_SCAN = BIT(4)  /* 52A/C/D init scan move to wl slot WA */
 };
 
 enum btc_3cx_type {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 0ecd9d41c2ad..dd9fbddc411a 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -8,6 +8,8 @@
 #include "phy.h"
 #include "reg.h"
 #include "rtw8852bt.h"
+#include "rtw8852bt_rfk.h"
+#include "rtw8852b_common.h"
 
 #define RTW8852BT_FW_FORMAT_MAX 0
 #define RTW8852BT_FW_BASENAME "rtw89/rtw8852bt_fw"
@@ -230,7 +232,466 @@ static const struct rtw89_btc_fbtc_mreg rtw89_btc_8852bt_mon_reg[] = {
 static const u8 rtw89_btc_8852bt_wl_rssi_thres[BTC_WL_RSSI_THMAX] = {70, 60, 50, 40};
 static const u8 rtw89_btc_8852bt_bt_rssi_thres[BTC_BT_RSSI_THMAX] = {50, 40, 30, 20};
 
+static int rtw8852bt_pwr_on_func(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	u32 ret;
+
+	rtw89_write32_set(rtwdev, R_AX_LDO_AON_CTRL0, B_AX_PD_REGU_L);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_AFSM_WLSUS_EN |
+						    B_AX_AFSM_PCIE_SUS_EN);
+	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_DIS_WLBT_PDNSUSEN_SOPC);
+	rtw89_write32_set(rtwdev, R_AX_WLLPS_CTRL, B_AX_DIS_WLBT_LPSEN_LOPC);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APDM_HPDN);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFM_SWLPS);
+	rtw89_write32_mask(rtwdev, R_AX_SPS_DIG_ON_CTRL0, B_AX_OCP_L1_MASK, 7);
+
+	ret = read_poll_timeout(rtw89_read32, val32, val32 & B_AX_RDY_SYSPWR,
+				1000, 20000, false, rtwdev, R_AX_SYS_PW_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_EN_WLON);
+	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFN_ONMAC);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_AX_APFN_ONMAC),
+				1000, 20000, false, rtwdev, R_AX_SYS_PW_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write8_set(rtwdev, R_AX_PLATFORM_ENABLE, B_AX_PLATFORM_EN);
+	rtw89_write8_clr(rtwdev, R_AX_PLATFORM_ENABLE, B_AX_PLATFORM_EN);
+	rtw89_write8_set(rtwdev, R_AX_PLATFORM_ENABLE, B_AX_PLATFORM_EN);
+	rtw89_write8_clr(rtwdev, R_AX_PLATFORM_ENABLE, B_AX_PLATFORM_EN);
+	rtw89_write8_set(rtwdev, R_AX_PLATFORM_ENABLE, B_AX_PLATFORM_EN);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_SDIO_CTRL, B_AX_PCIE_CALIB_EN_V1);
+	rtw89_write32_set(rtwdev, R_AX_SYS_ADIE_PAD_PWR_CTRL, B_AX_SYM_PADPDN_WL_PTA_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL,
+				      XTAL_SI_GND_SHDN_WL, XTAL_SI_GND_SHDN_WL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_AX_SYS_ADIE_PAD_PWR_CTRL, B_AX_SYM_PADPDN_WL_RFC_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL,
+				      XTAL_SI_SHDN_WL, XTAL_SI_SHDN_WL);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_OFF_WEI,
+				      XTAL_SI_OFF_WEI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_OFF_EI,
+				      XTAL_SI_OFF_EI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_RFC2RF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_PON_WEI,
+				      XTAL_SI_PON_WEI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_PON_EI,
+				      XTAL_SI_PON_EI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_SRAM2RFC);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_SRAM_CTRL, 0, XTAL_SI_SRAM_DIS);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XTAL_XMD_2, 0, XTAL_SI_LDO_LPS);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_XTAL_XMD_4, 0, XTAL_SI_LPS_CAP);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_AX_PMC_DBG_CTRL2, B_AX_SYSON_DIS_PMCR_AX_WRMSK);
+	rtw89_write32_set(rtwdev, R_AX_SYS_ISO_CTRL, B_AX_ISO_EB2CORE);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_ISO_CTRL, B_AX_PWC_EV2EF_B15);
+
+	fsleep(1000);
+
+	rtw89_write32_clr(rtwdev, R_AX_SYS_ISO_CTRL, B_AX_PWC_EV2EF_B14);
+	rtw89_write32_clr(rtwdev, R_AX_PMC_DBG_CTRL2, B_AX_SYSON_DIS_PMCR_AX_WRMSK);
+
+	if (!rtwdev->efuse.valid || rtwdev->efuse.power_k_valid)
+		goto func_en;
+
+	rtw89_write32_mask(rtwdev, R_AX_SPS_DIG_ON_CTRL0, B_AX_VOL_L1_MASK, 0x9);
+	rtw89_write32_mask(rtwdev, R_AX_SPS_DIG_ON_CTRL0, B_AX_VREFPFM_L_MASK, 0xA);
+
+func_en:
+	rtw89_write32_set(rtwdev, R_AX_DMAC_FUNC_EN,
+			  B_AX_MAC_FUNC_EN | B_AX_DMAC_FUNC_EN | B_AX_MPDU_PROC_EN |
+			  B_AX_WD_RLS_EN | B_AX_DLE_WDE_EN | B_AX_TXPKT_CTRL_EN |
+			  B_AX_STA_SCH_EN | B_AX_DLE_PLE_EN | B_AX_PKT_BUF_EN |
+			  B_AX_DMAC_TBL_EN | B_AX_PKT_IN_EN | B_AX_DLE_CPUIO_EN |
+			  B_AX_DISPATCHER_EN | B_AX_BBRPT_EN | B_AX_MAC_SEC_EN |
+			  B_AX_DMACREG_GCKEN);
+	rtw89_write32_set(rtwdev, R_AX_CMAC_FUNC_EN,
+			  B_AX_CMAC_EN | B_AX_CMAC_TXEN | B_AX_CMAC_RXEN |
+			  B_AX_FORCE_CMACREG_GCKEN | B_AX_PHYINTF_EN | B_AX_CMAC_DMA_EN |
+			  B_AX_PTCLTOP_EN | B_AX_SCHEDULER_EN | B_AX_TMAC_EN |
+			  B_AX_RMAC_EN);
+
+	rtw89_write32_mask(rtwdev, R_AX_EECS_EESK_FUNC_SEL,
+			   B_AX_PINMUX_EESK_FUNC_SEL_MASK, 0x1);
+
+	return 0;
+}
+
+static int rtw8852bt_pwr_off_func(struct rtw89_dev *rtwdev)
+{
+	u32 val32;
+	u32 ret;
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_RFC2RF,
+				      XTAL_SI_RFC2RF);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_OFF_EI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_OFF_WEI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_WL_RFC_S0, 0, XTAL_SI_RF00);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_WL_RFC_S1, 0, XTAL_SI_RF10);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_SRAM2RFC,
+				      XTAL_SI_SRAM2RFC);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_PON_EI);
+	if (ret)
+		return ret;
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_PON_WEI);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_EN_WLON);
+	rtw89_write32_clr(rtwdev, R_AX_WLRF_CTRL, B_AX_AFC_AFEDIG);
+	rtw89_write8_clr(rtwdev, R_AX_SYS_FUNC_EN, B_AX_FEN_BB_GLB_RSTN | B_AX_FEN_BBRSTB);
+	rtw89_write32_clr(rtwdev, R_AX_SYS_ADIE_PAD_PWR_CTRL, B_AX_SYM_PADPDN_WL_RFC_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_SHDN_WL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_clr(rtwdev, R_AX_SYS_ADIE_PAD_PWR_CTRL, B_AX_SYM_PADPDN_WL_PTA_1P3);
+
+	ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, 0, XTAL_SI_GND_SHDN_WL);
+	if (ret)
+		return ret;
+
+	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFM_OFFMAC);
+
+	ret = read_poll_timeout(rtw89_read32, val32, !(val32 & B_AX_APFM_OFFMAC),
+				1000, 20000, false, rtwdev, R_AX_SYS_PW_CTRL);
+	if (ret)
+		return ret;
+
+	rtw89_write32(rtwdev, R_AX_WLLPS_CTRL, SW_LPS_OPTION);
+	rtw89_write32_set(rtwdev, R_AX_SYS_SWR_CTRL1, B_AX_SYM_CTRL_SPS_PWMFREQ);
+	rtw89_write32_mask(rtwdev, R_AX_SPS_DIG_ON_CTRL0, B_AX_REG_ZCDC_H_MASK, 0x3);
+	rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFM_SWLPS);
+
+	return 0;
+}
+
+static void rtw8852bt_bb_reset_en(struct rtw89_dev *rtwdev, enum rtw89_band band,
+				  enum rtw89_phy_idx phy_idx, bool en)
+{
+	if (en) {
+		rtw89_phy_write32_idx(rtwdev, R_S0_HW_SI_DIS,
+				      B_S0_HW_SI_DIS_W_R_TRIG, 0x0, phy_idx);
+		rtw89_phy_write32_idx(rtwdev, R_S1_HW_SI_DIS,
+				      B_S1_HW_SI_DIS_W_R_TRIG, 0x0, phy_idx);
+		rtw89_phy_write32_idx(rtwdev, R_RSTB_ASYNC, B_RSTB_ASYNC_ALL, 1, phy_idx);
+		if (band == RTW89_BAND_2G)
+			rtw89_phy_write32_mask(rtwdev, R_RXCCA, B_RXCCA_DIS, 0x0);
+		rtw89_phy_write32_mask(rtwdev, R_PD_CTRL, B_PD_HIT_DIS, 0x0);
+	} else {
+		rtw89_phy_write32_mask(rtwdev, R_RXCCA, B_RXCCA_DIS, 0x1);
+		rtw89_phy_write32_mask(rtwdev, R_PD_CTRL, B_PD_HIT_DIS, 0x1);
+		rtw89_phy_write32_idx(rtwdev, R_S0_HW_SI_DIS,
+				      B_S0_HW_SI_DIS_W_R_TRIG, 0x7, phy_idx);
+		rtw89_phy_write32_idx(rtwdev, R_S1_HW_SI_DIS,
+				      B_S1_HW_SI_DIS_W_R_TRIG, 0x7, phy_idx);
+		fsleep(1);
+		rtw89_phy_write32_idx(rtwdev, R_RSTB_ASYNC, B_RSTB_ASYNC_ALL, 0, phy_idx);
+	}
+}
+
+static void rtw8852bt_bb_reset(struct rtw89_dev *rtwdev,
+			       enum rtw89_phy_idx phy_idx)
+{
+	rtw89_phy_write32_mask(rtwdev, R_P0_TXPW_RSTB,
+			       B_P0_TXPW_RSTB_MANON | B_P0_TXPW_RSTB_TSSI, 0x1);
+	rtw89_phy_write32_set(rtwdev, R_P0_TSSI_TRK, B_P0_TSSI_TRK_EN);
+	rtw89_phy_write32_mask(rtwdev, R_P1_TXPW_RSTB,
+			       B_P1_TXPW_RSTB_MANON | B_P1_TXPW_RSTB_TSSI, 0x1);
+	rtw89_phy_write32_set(rtwdev, R_P1_TSSI_TRK, B_P1_TSSI_TRK_EN);
+	rtw8852bx_bb_reset_all(rtwdev, phy_idx);
+	rtw89_phy_write32_mask(rtwdev, R_P0_TXPW_RSTB,
+			       B_P0_TXPW_RSTB_MANON | B_P0_TXPW_RSTB_TSSI, 3);
+	rtw89_phy_write32_clr(rtwdev, R_P0_TSSI_TRK, B_P0_TSSI_TRK_EN);
+	rtw89_phy_write32_mask(rtwdev, R_P1_TXPW_RSTB,
+			       B_P1_TXPW_RSTB_MANON | B_P0_TXPW_RSTB_TSSI, 0x3);
+	rtw89_phy_write32_clr(rtwdev, R_P1_TSSI_TRK, B_P1_TSSI_TRK_EN);
+}
+
+static void rtw8852bt_set_channel(struct rtw89_dev *rtwdev,
+				  const struct rtw89_chan *chan,
+				  enum rtw89_mac_idx mac_idx,
+				  enum rtw89_phy_idx phy_idx)
+{
+	rtw8852bx_set_channel_mac(rtwdev, chan, mac_idx);
+	rtw8852bx_set_channel_bb(rtwdev, chan, phy_idx);
+	rtw8852bt_set_channel_rf(rtwdev, chan, phy_idx);
+}
+
+static void rtw8852bt_tssi_cont_en(struct rtw89_dev *rtwdev, bool en,
+				   enum rtw89_rf_path path)
+{
+	static const u32 tssi_trk[2] = {R_P0_TSSI_TRK, R_P1_TSSI_TRK};
+
+	if (en)
+		rtw89_phy_write32_mask(rtwdev, tssi_trk[path], B_P0_TSSI_TRK_EN, 0x0);
+	else
+		rtw89_phy_write32_mask(rtwdev, tssi_trk[path], B_P0_TSSI_TRK_EN, 0x1);
+}
+
+static void rtw8852bt_tssi_cont_en_phyidx(struct rtw89_dev *rtwdev, bool en,
+					  u8 phy_idx)
+{
+	if (!rtwdev->dbcc_en) {
+		rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_A);
+		rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_B);
+		rtw8852bt_tssi_scan(rtwdev, phy_idx);
+	} else {
+		if (phy_idx == RTW89_PHY_0)
+			rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_A);
+		else
+			rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_B);
+	}
+}
+
+static void rtw8852bt_adc_en(struct rtw89_dev *rtwdev, bool en)
+{
+	if (en)
+		rtw89_phy_write32_mask(rtwdev, R_ADC_FIFO, B_ADC_FIFO_RST, 0x0);
+	else
+		rtw89_phy_write32_mask(rtwdev, R_ADC_FIFO, B_ADC_FIFO_RST, 0xf);
+}
+
+static void rtw8852bt_set_channel_help(struct rtw89_dev *rtwdev, bool enter,
+				       struct rtw89_channel_help_params *p,
+				       const struct rtw89_chan *chan,
+				       enum rtw89_mac_idx mac_idx,
+				       enum rtw89_phy_idx phy_idx)
+{
+	if (enter) {
+		rtw89_chip_stop_sch_tx(rtwdev, RTW89_MAC_0, &p->tx_en, RTW89_SCH_TX_SEL_ALL);
+		rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, false);
+		rtw8852bt_tssi_cont_en_phyidx(rtwdev, false, RTW89_PHY_0);
+		rtw8852bt_adc_en(rtwdev, false);
+		fsleep(40);
+		rtw8852bt_bb_reset_en(rtwdev, chan->band_type, phy_idx, false);
+	} else {
+		rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, true);
+		rtw8852bt_adc_en(rtwdev, true);
+		rtw8852bt_tssi_cont_en_phyidx(rtwdev, true, RTW89_PHY_0);
+		rtw8852bt_bb_reset_en(rtwdev, chan->band_type, phy_idx, true);
+		rtw89_chip_resume_sch_tx(rtwdev, RTW89_MAC_0, p->tx_en);
+	}
+}
+
+static void rtw8852bt_rfk_init(struct rtw89_dev *rtwdev)
+{
+	rtwdev->is_tssi_mode[RF_PATH_A] = false;
+	rtwdev->is_tssi_mode[RF_PATH_B] = false;
+
+	rtw8852bt_dpk_init(rtwdev);
+	rtw8852bt_rck(rtwdev);
+	rtw8852bt_dack(rtwdev);
+	rtw8852bt_rx_dck(rtwdev, RTW89_PHY_0);
+}
+
+static void rtw8852bt_rfk_channel(struct rtw89_dev *rtwdev)
+{
+	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+
+	rtw8852bt_rx_dck(rtwdev, phy_idx);
+	rtw8852bt_iqk(rtwdev, phy_idx);
+	rtw8852bt_tssi(rtwdev, phy_idx, true);
+	rtw8852bt_dpk(rtwdev, phy_idx);
+}
+
+static void rtw8852bt_rfk_band_changed(struct rtw89_dev *rtwdev,
+				       enum rtw89_phy_idx phy_idx)
+{
+	rtw8852bt_tssi_scan(rtwdev, phy_idx);
+}
+
+static void rtw8852bt_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+{
+	rtw8852bt_wifi_scan_notify(rtwdev, start, RTW89_PHY_0);
+}
+
+static void rtw8852bt_rfk_track(struct rtw89_dev *rtwdev)
+{
+	rtw8852bt_dpk_track(rtwdev);
+}
+
+static void rtw8852bt_btc_set_rfe(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_btc_ver *ver = rtwdev->btc.ver;
+	union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo;
+
+	if (ver->fcxinit == 7) {
+		md->md_v7.rfe_type = rtwdev->efuse.rfe_type;
+		md->md_v7.kt_ver = rtwdev->hal.cv;
+		md->md_v7.kt_ver_adie = rtwdev->hal.acv;
+		md->md_v7.bt_solo = 0;
+		md->md_v7.bt_pos = BTC_BT_BTG;
+		md->md_v7.switch_type = BTC_SWITCH_INTERNAL;
+		md->md_v7.wa_type = 0;
+
+		md->md_v7.ant.type = BTC_ANT_SHARED;
+		md->md_v7.ant.num = 2;
+		md->md_v7.ant.isolation = 10;
+		md->md_v7.ant.diversity = 0;
+		/* WL 1-stream+1-Ant is located at 0:s0(path-A) or 1:s1(path-B) */
+		md->md_v7.ant.single_pos = RF_PATH_A;
+		md->md_v7.ant.btg_pos = RF_PATH_B;
+
+		if (md->md_v7.rfe_type == 0) {
+			rtwdev->btc.dm.error.map.rfe_type0 = true;
+			return;
+		}
+
+		md->md_v7.ant.num = (md->md_v7.rfe_type % 2) ? 2 : 3;
+		md->md_v7.ant.stream_cnt = 2;
+		md->md_v7.wa_type |= BTC_WA_INIT_SCAN;
+
+		if (md->md_v7.ant.num == 2) {
+			md->md_v7.ant.type = BTC_ANT_SHARED;
+			md->md_v7.bt_pos = BTC_BT_BTG;
+			md->md_v7.wa_type |= BTC_WA_HFP_LAG;
+		} else {
+			md->md_v7.ant.type = BTC_ANT_DEDICATED;
+			md->md_v7.bt_pos = BTC_BT_ALONE;
+		}
+	} else {
+		return;
+	}
+}
+
+static void
+rtw8852bt_btc_set_wl_txpwr_ctrl(struct rtw89_dev *rtwdev, u32 txpwr_val)
+{
+	u16 ctrl_all_time = u32_get_bits(txpwr_val, GENMASK(15, 0));
+	u16 ctrl_gnt_bt = u32_get_bits(txpwr_val, GENMASK(31, 16));
+
+	switch (ctrl_all_time) {
+	case 0xffff:
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_RATE_CTRL,
+					     B_AX_FORCE_PWR_BY_RATE_EN, 0x0);
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_RATE_CTRL,
+					     B_AX_FORCE_PWR_BY_RATE_VALUE_MASK, 0x0);
+		break;
+	default:
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_RATE_CTRL,
+					     B_AX_FORCE_PWR_BY_RATE_VALUE_MASK,
+					     ctrl_all_time);
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_RATE_CTRL,
+					     B_AX_FORCE_PWR_BY_RATE_EN, 0x1);
+		break;
+	}
+
+	switch (ctrl_gnt_bt) {
+	case 0xffff:
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_COEXT_CTRL,
+					     B_AX_TXAGC_BT_EN, 0x0);
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_COEXT_CTRL,
+					     B_AX_TXAGC_BT_MASK, 0x0);
+		break;
+	default:
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_COEXT_CTRL,
+					     B_AX_TXAGC_BT_MASK, ctrl_gnt_bt);
+		rtw89_mac_txpwr_write32_mask(rtwdev, RTW89_PHY_0, R_AX_PWR_COEXT_CTRL,
+					     B_AX_TXAGC_BT_EN, 0x1);
+		break;
+	}
+}
+
 static const struct rtw89_chip_ops rtw8852bt_chip_ops = {
+	.enable_bb_rf		= rtw8852bx_mac_enable_bb_rf,
+	.disable_bb_rf		= rtw8852bx_mac_disable_bb_rf,
+	.bb_preinit		= NULL,
+	.bb_postinit		= NULL,
+	.bb_reset		= rtw8852bt_bb_reset,
+	.bb_sethw		= rtw8852bx_bb_sethw,
+	.read_rf		= rtw89_phy_read_rf_v1,
+	.write_rf		= rtw89_phy_write_rf_v1,
+	.set_channel		= rtw8852bt_set_channel,
+	.set_channel_help	= rtw8852bt_set_channel_help,
+	.read_efuse		= rtw8852bx_read_efuse,
+	.read_phycap		= rtw8852bx_read_phycap,
+	.fem_setup		= NULL,
+	.rfe_gpio		= NULL,
+	.rfk_hw_init		= NULL,
+	.rfk_init		= rtw8852bt_rfk_init,
+	.rfk_init_late		= NULL,
+	.rfk_channel		= rtw8852bt_rfk_channel,
+	.rfk_band_changed	= rtw8852bt_rfk_band_changed,
+	.rfk_scan		= rtw8852bt_rfk_scan,
+	.rfk_track		= rtw8852bt_rfk_track,
+	.power_trim		= rtw8852bx_power_trim,
+	.set_txpwr		= rtw8852bx_set_txpwr,
+	.set_txpwr_ctrl		= rtw8852bx_set_txpwr_ctrl,
+	.init_txpwr_unit	= rtw8852bx_init_txpwr_unit,
+	.get_thermal		= rtw8852bx_get_thermal,
+	.ctrl_btg_bt_rx		= rtw8852bx_ctrl_btg_bt_rx,
+	.query_ppdu		= rtw8852bx_query_ppdu,
+	.ctrl_nbtg_bt_tx	= rtw8852bx_ctrl_nbtg_bt_tx,
+	.cfg_txrx_path		= rtw8852bx_bb_cfg_txrx_path,
+	.set_txpwr_ul_tb_offset	= rtw8852bx_set_txpwr_ul_tb_offset,
+	.pwr_on_func		= rtw8852bt_pwr_on_func,
+	.pwr_off_func		= rtw8852bt_pwr_off_func,
+	.query_rxdesc		= rtw89_core_query_rxdesc,
+	.fill_txdesc		= rtw89_core_fill_txdesc,
+	.fill_txdesc_fwcmd	= rtw89_core_fill_txdesc,
+	.cfg_ctrl_path		= rtw89_mac_cfg_ctrl_path,
+	.mac_cfg_gnt		= rtw89_mac_cfg_gnt,
+	.stop_sch_tx		= rtw89_mac_stop_sch_tx,
+	.resume_sch_tx		= rtw89_mac_resume_sch_tx,
+	.h2c_dctl_sec_cam	= NULL,
+	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl,
+	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl,
+	.h2c_ampdu_cmac_tbl	= NULL,
+	.h2c_default_dmac_tbl	= NULL,
+	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon,
+	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam,
+
+	.btc_set_rfe		= rtw8852bt_btc_set_rfe,
+	.btc_init_cfg		= rtw8852bx_btc_init_cfg,
+	.btc_set_wl_pri		= rtw8852bx_btc_set_wl_pri,
+	.btc_set_wl_txpwr_ctrl	= rtw8852bt_btc_set_wl_txpwr_ctrl,
+	.btc_get_bt_rssi	= rtw8852bx_btc_get_bt_rssi,
+	.btc_update_bt_cnt	= rtw8852bx_btc_update_bt_cnt,
+	.btc_wl_s1_standby	= rtw8852bx_btc_wl_s1_standby,
+	.btc_set_wl_rx_gain	= rtw8852bx_btc_set_wl_rx_gain,
+	.btc_set_policy		= rtw89_btc_set_policy_v1,
 };
 
 #ifdef CONFIG_PM
-- 
cgit v1.3-3-g829e


From e67e15cb867c801afa6f6628a5405f7f3a0d9cbe Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:38 +0800
Subject: wifi: rtw89: 8852bt: declare firmware features of RTL8852BT

Firmware features are enabled after being supported, including TX wake,
firmware crash simulation, hardware scan.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index fbe08c162b93..c83274950793 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -670,6 +670,10 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = {
 	__CFG_FW_FEAT(RTL8852B, ge, 0, 29, 26, 0, TX_WAKE),
 	__CFG_FW_FEAT(RTL8852B, ge, 0, 29, 29, 0, CRASH_TRIGGER),
 	__CFG_FW_FEAT(RTL8852B, ge, 0, 29, 29, 0, SCAN_OFFLOAD),
+	__CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 74, 0, NO_LPS_PG),
+	__CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 74, 0, TX_WAKE),
+	__CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 90, 0, CRASH_TRIGGER),
+	__CFG_FW_FEAT(RTL8852BT, ge, 0, 29, 91, 0, SCAN_OFFLOAD),
 	__CFG_FW_FEAT(RTL8852C, le, 0, 27, 33, 0, NO_DEEP_PS),
 	__CFG_FW_FEAT(RTL8852C, ge, 0, 27, 34, 0, TX_WAKE),
 	__CFG_FW_FEAT(RTL8852C, ge, 0, 27, 36, 0, SCAN_OFFLOAD),
-- 
cgit v1.3-3-g829e


From bbe48c328ff85d9ebe48d1fdac6f9ba771237ad1 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:39 +0800
Subject: wifi: rtw89: 8852bte: add PCI entry of 8852BE-VT

PCI device ID 10ec:b520 of RTL8852BE-VT is added as PCI entry, and define
chip capabilities for driver common routines.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852bte.c | 93 +++++++++++++++++++++++++
 1 file changed, 93 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtw89/rtw8852bte.c

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bte.c b/drivers/net/wireless/realtek/rtw89/rtw8852bte.c
new file mode 100644
index 000000000000..702948119646
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bte.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2024  Realtek Corporation
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "pci.h"
+#include "reg.h"
+#include "rtw8852bt.h"
+
+static const struct rtw89_pci_info rtw8852bt_pci_info = {
+	.gen_def		= &rtw89_pci_gen_ax,
+	.txbd_trunc_mode	= MAC_AX_BD_TRUNC,
+	.rxbd_trunc_mode	= MAC_AX_BD_TRUNC,
+	.rxbd_mode		= MAC_AX_RXBD_PKT,
+	.tag_mode		= MAC_AX_TAG_MULTI,
+	.tx_burst		= MAC_AX_TX_BURST_2048B,
+	.rx_burst		= MAC_AX_RX_BURST_128B,
+	.wd_dma_idle_intvl	= MAC_AX_WD_DMA_INTVL_256NS,
+	.wd_dma_act_intvl	= MAC_AX_WD_DMA_INTVL_256NS,
+	.multi_tag_num		= MAC_AX_TAG_NUM_8,
+	.lbc_en			= MAC_AX_PCIE_ENABLE,
+	.lbc_tmr		= MAC_AX_LBC_TMR_2MS,
+	.autok_en		= MAC_AX_PCIE_DISABLE,
+	.io_rcy_en		= MAC_AX_PCIE_DISABLE,
+	.io_rcy_tmr		= MAC_AX_IO_RCY_ANA_TMR_6MS,
+	.rx_ring_eq_is_full	= false,
+	.check_rx_tag		= false,
+
+	.init_cfg_reg		= R_AX_PCIE_INIT_CFG1,
+	.txhci_en_bit		= B_AX_TXHCI_EN,
+	.rxhci_en_bit		= B_AX_RXHCI_EN,
+	.rxbd_mode_bit		= B_AX_RXBD_MODE,
+	.exp_ctrl_reg		= R_AX_PCIE_EXP_CTRL,
+	.max_tag_num_mask	= B_AX_MAX_TAG_NUM,
+	.rxbd_rwptr_clr_reg	= R_AX_RXBD_RWPTR_CLR,
+	.txbd_rwptr_clr2_reg	= 0,
+	.dma_io_stop		= {R_AX_PCIE_DMA_STOP1, B_AX_STOP_PCIEIO},
+	.dma_stop1		= {R_AX_PCIE_DMA_STOP1, B_AX_TX_STOP1_MASK_V1},
+	.dma_stop2		= {0},
+	.dma_busy1		= {R_AX_PCIE_DMA_BUSY1, DMA_BUSY1_CHECK_V1},
+	.dma_busy2_reg		= 0,
+	.dma_busy3_reg		= R_AX_PCIE_DMA_BUSY1,
+
+	.rpwm_addr		= R_AX_PCIE_HRPWM,
+	.cpwm_addr		= R_AX_CPWM,
+	.mit_addr		= R_AX_INT_MIT_RX,
+	.wp_sel_addr		= 0,
+	.tx_dma_ch_mask		= BIT(RTW89_TXCH_ACH4) | BIT(RTW89_TXCH_ACH5) |
+				  BIT(RTW89_TXCH_ACH6) | BIT(RTW89_TXCH_ACH7) |
+				  BIT(RTW89_TXCH_CH10) | BIT(RTW89_TXCH_CH11),
+	.bd_idx_addr_low_power	= NULL,
+	.dma_addr_set		= &rtw89_pci_ch_dma_addr_set,
+	.bd_ram_table		= &rtw89_bd_ram_table_single,
+
+	.ltr_set		= rtw89_pci_ltr_set,
+	.fill_txaddr_info	= rtw89_pci_fill_txaddr_info,
+	.config_intr_mask	= rtw89_pci_config_intr_mask,
+	.enable_intr		= rtw89_pci_enable_intr,
+	.disable_intr		= rtw89_pci_disable_intr,
+	.recognize_intrs	= rtw89_pci_recognize_intrs,
+};
+
+static const struct rtw89_driver_info rtw89_8852bte_info = {
+	.chip = &rtw8852bt_chip_info,
+	.quirks = NULL,
+	.bus = {
+		.pci = &rtw8852bt_pci_info,
+	},
+};
+
+static const struct pci_device_id rtw89_8852bte_id_table[] = {
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0xb520),
+		.driver_data = (kernel_ulong_t)&rtw89_8852bte_info,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(pci, rtw89_8852bte_id_table);
+
+static struct pci_driver rtw89_8852bte_driver = {
+	.name		= "rtw89_8852bte",
+	.id_table	= rtw89_8852bte_id_table,
+	.probe		= rtw89_pci_probe,
+	.remove		= rtw89_pci_remove,
+	.driver.pm	= &rtw89_pm_ops,
+};
+module_pci_driver(rtw89_8852bte_driver);
+
+MODULE_AUTHOR("Realtek Corporation");
+MODULE_DESCRIPTION("Realtek 802.11ax wireless 8852BE-VT driver");
+MODULE_LICENSE("Dual BSD/GPL");
-- 
cgit v1.3-3-g829e


From b9cdbb06d4fc4665b3a8a557926bcb09edc92c5f Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Sat, 20 Jul 2024 10:13:40 +0800
Subject: wifi: rtw89: 8852bt: add 8852BE-VT to Makefile and Kconfig

RTL8852BE-VT is a WiFi 6 2x2 chip, which can operate on 2/5 GHz channels
and 80MHz bandwidth.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240720021340.12102-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/Kconfig  | 15 +++++++++++++++
 drivers/net/wireless/realtek/rtw89/Makefile |  8 ++++++++
 2 files changed, 23 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/Kconfig b/drivers/net/wireless/realtek/rtw89/Kconfig
index 6278fd74e98e..d2a3361669d7 100644
--- a/drivers/net/wireless/realtek/rtw89/Kconfig
+++ b/drivers/net/wireless/realtek/rtw89/Kconfig
@@ -29,6 +29,9 @@ config RTW89_8852B_COMMON
 config RTW89_8852B
 	tristate
 
+config RTW89_8852BT
+	tristate
+
 config RTW89_8852C
 	tristate
 
@@ -69,6 +72,18 @@ config RTW89_8852BE
 
 	  802.11ax PCIe wireless network (Wi-Fi 6) adapter
 
+config RTW89_8852BTE
+	tristate "Realtek 8852BE-VT PCI wireless network (Wi-Fi 6) adapter"
+	depends on PCI
+	select RTW89_CORE
+	select RTW89_PCI
+	select RTW89_8852BT
+	select RTW89_8852B_COMMON
+	help
+	  Select this option will enable support for 8852BE-VT chipset
+
+	  802.11ax PCIe wireless network (Wi-Fi 6) adapter
+
 config RTW89_8852CE
 	tristate "Realtek 8852CE PCI wireless network (Wi-Fi 6E) adapter"
 	depends on PCI
diff --git a/drivers/net/wireless/realtek/rtw89/Makefile b/drivers/net/wireless/realtek/rtw89/Makefile
index 1f1050a7a89d..c751013e811e 100644
--- a/drivers/net/wireless/realtek/rtw89/Makefile
+++ b/drivers/net/wireless/realtek/rtw89/Makefile
@@ -52,6 +52,14 @@ rtw89_8852b-objs := rtw8852b.o \
 obj-$(CONFIG_RTW89_8852BE) += rtw89_8852be.o
 rtw89_8852be-objs := rtw8852be.o
 
+obj-$(CONFIG_RTW89_8852BT) += rtw89_8852bt.o
+rtw89_8852bt-objs := rtw8852bt.o \
+		    rtw8852bt_rfk.o \
+		    rtw8852bt_rfk_table.o
+
+obj-$(CONFIG_RTW89_8852BTE) += rtw89_8852bte.o
+rtw89_8852bte-objs := rtw8852bte.o
+
 obj-$(CONFIG_RTW89_8852C) += rtw89_8852c.o
 rtw89_8852c-objs := rtw8852c.o \
 		    rtw8852c_table.o \
-- 
cgit v1.3-3-g829e


From a71ed5898dfae68262f79277915d1dfe34586bc6 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 23 Jul 2024 22:31:36 +0300
Subject: wifi: rtw88: 8822c: Fix reported RX band width

"iw dev wlp2s0 station dump" shows incorrect rx bitrate:

tx bitrate:     866.7 MBit/s VHT-MCS 9 80MHz short GI VHT-NSS 2
rx bitrate:     86.7 MBit/s VHT-MCS 9 VHT-NSS 1

This is because the RX band width is calculated incorrectly. Fix the
calculation according to the phydm_rxsc_2_bw() function from the
official drivers.

After:

tx bitrate:     866.7 MBit/s VHT-MCS 9 80MHz short GI VHT-NSS 2
rx bitrate:     390.0 MBit/s VHT-MCS 9 80MHz VHT-NSS 1

It also works correctly with the AP configured for 20 MHz and 40 MHz.

Tested with RTL8822CE.

Cc: stable@vger.kernel.org
Fixes: e3037485c68e ("rtw88: new Realtek 802.11ac driver")
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/bca8949b-e2bd-4515-98fd-70d3049a0097@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8822c.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index bc807b13e9ce..e265a35184ab 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -2612,12 +2612,14 @@ static void query_phy_status_page1(struct rtw_dev *rtwdev, u8 *phy_status,
 	else
 		rxsc = GET_PHY_STAT_P1_HT_RXSC(phy_status);
 
-	if (rxsc >= 9 && rxsc <= 12)
+	if (rxsc == 0)
+		bw = rtwdev->hal.current_band_width;
+	else if (rxsc >= 1 && rxsc <= 8)
+		bw = RTW_CHANNEL_WIDTH_20;
+	else if (rxsc >= 9 && rxsc <= 12)
 		bw = RTW_CHANNEL_WIDTH_40;
-	else if (rxsc >= 13)
-		bw = RTW_CHANNEL_WIDTH_80;
 	else
-		bw = RTW_CHANNEL_WIDTH_20;
+		bw = RTW_CHANNEL_WIDTH_80;
 
 	channel = GET_PHY_STAT_P1_CHANNEL(phy_status);
 	rtw_set_rx_freq_band(pkt_stat, channel);
-- 
cgit v1.3-3-g829e


From 0129e5ff2842450f1426e312b5e580c0814e0de3 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 23 Jul 2024 22:32:59 +0300
Subject: wifi: rtw88: 8703b: Fix reported RX band width

The definition of GET_RX_DESC_BW is incorrect. Fix it according to the
GET_RX_STATUS_DESC_BW_8703B macro from the official driver.

Tested only with RTL8812AU, which uses the same bits.

Cc: stable@vger.kernel.org
Fixes: 9bb762b3a957 ("wifi: rtw88: Add definitions for 8703b chip")
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Tested-by: Fiona Klute <fiona.klute@gmx.de>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/1cfed9d5-4304-4b96-84c5-c347f59fedb9@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rx.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rx.h b/drivers/net/wireless/realtek/rtw88/rx.h
index d3668c4efc24..8a072dd3d73c 100644
--- a/drivers/net/wireless/realtek/rtw88/rx.h
+++ b/drivers/net/wireless/realtek/rtw88/rx.h
@@ -41,7 +41,7 @@ enum rtw_rx_desc_enc {
 #define GET_RX_DESC_TSFL(rxdesc)                                               \
 	le32_get_bits(*((__le32 *)(rxdesc) + 0x05), GENMASK(31, 0))
 #define GET_RX_DESC_BW(rxdesc)                                                 \
-	(le32_get_bits(*((__le32 *)(rxdesc) + 0x04), GENMASK(31, 24)))
+	(le32_get_bits(*((__le32 *)(rxdesc) + 0x04), GENMASK(5, 4)))
 
 void rtw_rx_stats(struct rtw_dev *rtwdev, struct ieee80211_vif *vif,
 		  struct sk_buff *skb);
-- 
cgit v1.3-3-g829e


From 2e7a280692bf43940728b7f6ca6a52ebf641a6f5 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:00 +0100
Subject: l2tp: lookup tunnel from socket without using sk_user_data

l2tp_sk_to_tunnel derives the tunnel from sk_user_data. Instead,
lookup the tunnel by walking the tunnel IDR for a tunnel using the
indicated sock. This is slow but l2tp_sk_to_tunnel is not used in
the datapath so performance isn't critical.

l2tp_tunnel_destruct needs a variant of l2tp_sk_to_tunnel which does
not bump the tunnel refcount since the tunnel refcount is already 0.

Change l2tp_sk_to_tunnel sk arg to const since it does not modify sk.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 52 +++++++++++++++++++++++++++++++++++++++++++---------
 net/l2tp/l2tp_core.h |  5 +----
 net/l2tp/l2tp_ip.c   |  7 +++++--
 net/l2tp/l2tp_ip6.c  |  7 +++++--
 4 files changed, 54 insertions(+), 17 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c80ab3f26084..c97cd0fd8514 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -150,15 +150,43 @@ static void l2tp_session_free(struct l2tp_session *session)
 	kfree(session);
 }
 
-struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk)
+static struct l2tp_tunnel *__l2tp_sk_to_tunnel(const struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = sk->sk_user_data;
+	const struct net *net = sock_net(sk);
+	unsigned long tunnel_id, tmp;
+	struct l2tp_tunnel *tunnel;
+	struct l2tp_net *pn;
+
+	WARN_ON_ONCE(!rcu_read_lock_bh_held());
+	pn = l2tp_pernet(net);
+	idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+		if (tunnel && tunnel->sock == sk)
+			return tunnel;
+	}
+
+	return NULL;
+}
 
-	if (tunnel)
-		if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC))
-			return NULL;
+struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk)
+{
+	const struct net *net = sock_net(sk);
+	unsigned long tunnel_id, tmp;
+	struct l2tp_tunnel *tunnel;
+	struct l2tp_net *pn;
+
+	rcu_read_lock_bh();
+	pn = l2tp_pernet(net);
+	idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
+		if (tunnel &&
+		    tunnel->sock == sk &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
+			rcu_read_unlock_bh();
+			return tunnel;
+		}
+	}
+	rcu_read_unlock_bh();
 
-	return tunnel;
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel);
 
@@ -1213,8 +1241,10 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
  */
 static void l2tp_tunnel_destruct(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel;
 
+	rcu_read_lock_bh();
+	tunnel = __l2tp_sk_to_tunnel(sk);
 	if (!tunnel)
 		goto end;
 
@@ -1242,6 +1272,7 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 
 	kfree_rcu(tunnel, rcu);
 end:
+	rcu_read_unlock_bh();
 	return;
 }
 
@@ -1308,10 +1339,13 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
 /* Tunnel socket destroy hook for UDP encapsulation */
 static void l2tp_udp_encap_destroy(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel;
 
-	if (tunnel)
+	tunnel = l2tp_sk_to_tunnel(sk);
+	if (tunnel) {
 		l2tp_tunnel_delete(tunnel);
+		l2tp_tunnel_dec_refcount(tunnel);
+	}
 }
 
 static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel)
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 8ac81bc1bc6f..a41cf6795df0 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -273,10 +273,7 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
 /* IOCTL helper for IP encap modules. */
 int l2tp_ioctl(struct sock *sk, int cmd, int *karg);
 
-/* Extract the tunnel structure from a socket's sk_user_data pointer,
- * validating the tunnel magic feather.
- */
-struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk);
+struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk);
 
 static inline int l2tp_get_l2specific_len(struct l2tp_session *session)
 {
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index e48aa177d74c..78243f993cda 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -235,14 +235,17 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 
 static void l2tp_ip_destroy_sock(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel;
 	struct sk_buff *skb;
 
 	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
 		kfree_skb(skb);
 
-	if (tunnel)
+	tunnel = l2tp_sk_to_tunnel(sk);
+	if (tunnel) {
 		l2tp_tunnel_delete(tunnel);
+		l2tp_tunnel_dec_refcount(tunnel);
+	}
 }
 
 static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index d217ff1f229e..3b0465f2d60d 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -246,14 +246,17 @@ static void l2tp_ip6_close(struct sock *sk, long timeout)
 
 static void l2tp_ip6_destroy_sock(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
+	struct l2tp_tunnel *tunnel;
 
 	lock_sock(sk);
 	ip6_flush_pending_frames(sk);
 	release_sock(sk);
 
-	if (tunnel)
+	tunnel = l2tp_sk_to_tunnel(sk);
+	if (tunnel) {
 		l2tp_tunnel_delete(tunnel);
+		l2tp_tunnel_dec_refcount(tunnel);
+	}
 }
 
 static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
-- 
cgit v1.3-3-g829e


From 4ff8863419cdc40f2c6e1ad99436e375b9b86b68 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:01 +0100
Subject: ipv4: export ip_flush_pending_frames

To avoid protocol modules implementing their own, export
ip_flush_pending_frames.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b90d0f78ac80..8a10a7c67834 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1534,6 +1534,7 @@ void ip_flush_pending_frames(struct sock *sk)
 {
 	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
+EXPORT_SYMBOL_GPL(ip_flush_pending_frames);
 
 struct sk_buff *ip_make_skb(struct sock *sk,
 			    struct flowi4 *fl4,
-- 
cgit v1.3-3-g829e


From ed8ebee6def7b7b760bd4fd90c03b9e86622701c Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:02 +0100
Subject: l2tp: have l2tp_ip_destroy_sock use ip_flush_pending_frames

Use the recently exported ip_flush_pending_frames instead of a
free-coded version and lock the socket while we call it.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 78243f993cda..f21dcbf3efd5 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -236,10 +236,10 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 static void l2tp_ip_destroy_sock(struct sock *sk)
 {
 	struct l2tp_tunnel *tunnel;
-	struct sk_buff *skb;
 
-	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
-		kfree_skb(skb);
+	lock_sock(sk);
+	ip_flush_pending_frames(sk);
+	release_sock(sk);
 
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
-- 
cgit v1.3-3-g829e


From eeb11209e000797d555aefd642e24ed6f4e70140 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:03 +0100
Subject: l2tp: don't use tunnel socket sk_user_data in ppp procfs output

l2tp's ppp procfs output can be used to show internal state of
pppol2tp. It includes a 'user-data-ok' field, which is derived from
the tunnel socket's sk_user_data being non-NULL. Use tunnel->sock
being non-NULL to indicate this instead.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 3596290047b2..0844b86cd0a6 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1513,7 +1513,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "\nTUNNEL '%s', %c %d\n",
 		   tunnel->name,
-		   (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N',
+		   tunnel->sock ? 'Y' : 'N',
 		   refcount_read(&tunnel->ref_count) - 1);
 	seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n",
 		   0,
-- 
cgit v1.3-3-g829e


From 4a4cd70369f162f819b7855b0eabcb2db21f01f4 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:04 +0100
Subject: l2tp: don't set sk_user_data in tunnel socket

l2tp no longer uses the tunnel socket's sk_user_data so drop the code
which sets it.

In l2tp_validate_socket use l2tp_sk_to_tunnel to check whether a given
socket is already attached to an l2tp tunnel since we can no longer
use non-null sk_user_data to indicate this.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c97cd0fd8514..59a171fa1a39 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1263,7 +1263,6 @@ static void l2tp_tunnel_destruct(struct sock *sk)
 	/* Remove hooks into tunnel socket */
 	write_lock_bh(&sk->sk_callback_lock);
 	sk->sk_destruct = tunnel->old_sk_destruct;
-	sk->sk_user_data = NULL;
 	write_unlock_bh(&sk->sk_callback_lock);
 
 	/* Call the original destructor */
@@ -1554,6 +1553,8 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
 static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 				enum l2tp_encap_type encap)
 {
+	struct l2tp_tunnel *tunnel;
+
 	if (!net_eq(sock_net(sk), net))
 		return -EINVAL;
 
@@ -1567,8 +1568,11 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
 		return -EPROTONOSUPPORT;
 
-	if (sk->sk_user_data)
+	tunnel = l2tp_sk_to_tunnel(sk);
+	if (tunnel) {
+		l2tp_tunnel_dec_refcount(tunnel);
 		return -EBUSY;
+	}
 
 	return 0;
 }
@@ -1607,12 +1611,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	ret = l2tp_validate_socket(sk, net, tunnel->encap);
 	if (ret < 0)
 		goto err_inval_sock;
-	rcu_assign_sk_user_data(sk, tunnel);
 	write_unlock_bh(&sk->sk_callback_lock);
 
 	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
 		struct udp_tunnel_sock_cfg udp_cfg = {
-			.sk_user_data = tunnel,
 			.encap_type = UDP_ENCAP_L2TPINUDP,
 			.encap_rcv = l2tp_udp_encap_recv,
 			.encap_err_rcv = l2tp_udp_encap_err_recv,
-- 
cgit v1.3-3-g829e


From 0fa51a7c6f54f1c0c23bb256eb9b2d31a8b9c544 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:05 +0100
Subject: l2tp: remove unused tunnel magic field

Since l2tp no longer derives tunnel pointers directly via
sk_user_data, it is no longer useful for l2tp to check tunnel pointers
using a magic feather. Drop the tunnel's magic field.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 1 -
 net/l2tp/l2tp_core.h | 3 ---
 2 files changed, 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 59a171fa1a39..1ef14f99e78c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1527,7 +1527,6 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id,
 	tunnel->tunnel_id = tunnel_id;
 	tunnel->peer_tunnel_id = peer_tunnel_id;
 
-	tunnel->magic = L2TP_TUNNEL_MAGIC;
 	sprintf(&tunnel->name[0], "tunl %u", tunnel_id);
 	spin_lock_init(&tunnel->list_lock);
 	tunnel->acpt_newsess = true;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a41cf6795df0..50107531fe3b 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -16,7 +16,6 @@
 #endif
 
 /* Random numbers used for internal consistency checks of tunnel and session structures */
-#define L2TP_TUNNEL_MAGIC	0x42114DDA
 #define L2TP_SESSION_MAGIC	0x0C04EB7D
 
 struct sk_buff;
@@ -155,8 +154,6 @@ struct l2tp_tunnel_cfg {
  */
 #define L2TP_TUNNEL_NAME_MAX 20
 struct l2tp_tunnel {
-	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
-
 	unsigned long		dead;
 
 	struct rcu_head rcu;
-- 
cgit v1.3-3-g829e


From 29717a4fb7fcbbcfa5f0d5e8969b8ce0929276be Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:06 +0100
Subject: l2tp: simplify tunnel and socket cleanup

When the l2tp tunnel socket used sk_user_data to point to its
associated l2tp tunnel, socket and tunnel cleanup had to make use of
the socket's destructor to free the tunnel only when the socket could
no longer be accessed.

Now that sk_user_data is no longer used, we can simplify socket and
tunnel cleanup:

  * If the tunnel closes first, it cleans up and drops its socket ref
    when the tunnel refcount drops to zero. If its socket was provided
    by userspace, the socket is closed and freed asynchronously, when
    userspace closes it. If its socket is a kernel socket, the tunnel
    closes the socket itself during cleanup and drops its socket ref
    when the tunnel's refcount drops to zero.

  * If the socket closes first, we initiate the closing of its
    associated tunnel. For UDP sockets, this is via the socket's
    encap_destroy hook. For L2TPIP sockets, this is via the socket's
    destroy callback. The tunnel holds a socket ref while it
    references the sock. When the tunnel is freed, it drops its socket
    ref and the socket will be cleaned up when its own refcount drops
    to zero, asynchronous to the tunnel free.

  * The tunnel socket destructor is no longer needed since the tunnel
    is no longer freed through the socket destructor.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 82 ++++++++++++++--------------------------------------
 net/l2tp/l2tp_core.h |  1 -
 2 files changed, 21 insertions(+), 62 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1ef14f99e78c..a01dd891639b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -137,9 +137,28 @@ static inline struct l2tp_net *l2tp_pernet(const struct net *net)
 
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
 {
+	struct sock *sk = tunnel->sock;
+
 	trace_free_tunnel(tunnel);
-	sock_put(tunnel->sock);
-	/* the tunnel is freed in the socket destructor */
+
+	if (sk) {
+		/* Disable udp encapsulation */
+		switch (tunnel->encap) {
+		case L2TP_ENCAPTYPE_UDP:
+			/* No longer an encapsulation socket. See net/ipv4/udp.c */
+			WRITE_ONCE(udp_sk(sk)->encap_type, 0);
+			udp_sk(sk)->encap_rcv = NULL;
+			udp_sk(sk)->encap_destroy = NULL;
+			break;
+		case L2TP_ENCAPTYPE_IP:
+			break;
+		}
+
+		tunnel->sock = NULL;
+		sock_put(sk);
+	}
+
+	kfree_rcu(tunnel, rcu);
 }
 
 static void l2tp_session_free(struct l2tp_session *session)
@@ -150,23 +169,6 @@ static void l2tp_session_free(struct l2tp_session *session)
 	kfree(session);
 }
 
-static struct l2tp_tunnel *__l2tp_sk_to_tunnel(const struct sock *sk)
-{
-	const struct net *net = sock_net(sk);
-	unsigned long tunnel_id, tmp;
-	struct l2tp_tunnel *tunnel;
-	struct l2tp_net *pn;
-
-	WARN_ON_ONCE(!rcu_read_lock_bh_held());
-	pn = l2tp_pernet(net);
-	idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
-		if (tunnel && tunnel->sock == sk)
-			return tunnel;
-	}
-
-	return NULL;
-}
-
 struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk)
 {
 	const struct net *net = sock_net(sk);
@@ -1235,46 +1237,6 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
  * Tinnel and session create/destroy.
  *****************************************************************************/
 
-/* Tunnel socket destruct hook.
- * The tunnel context is deleted only when all session sockets have been
- * closed.
- */
-static void l2tp_tunnel_destruct(struct sock *sk)
-{
-	struct l2tp_tunnel *tunnel;
-
-	rcu_read_lock_bh();
-	tunnel = __l2tp_sk_to_tunnel(sk);
-	if (!tunnel)
-		goto end;
-
-	/* Disable udp encapsulation */
-	switch (tunnel->encap) {
-	case L2TP_ENCAPTYPE_UDP:
-		/* No longer an encapsulation socket. See net/ipv4/udp.c */
-		WRITE_ONCE(udp_sk(sk)->encap_type, 0);
-		udp_sk(sk)->encap_rcv = NULL;
-		udp_sk(sk)->encap_destroy = NULL;
-		break;
-	case L2TP_ENCAPTYPE_IP:
-		break;
-	}
-
-	/* Remove hooks into tunnel socket */
-	write_lock_bh(&sk->sk_callback_lock);
-	sk->sk_destruct = tunnel->old_sk_destruct;
-	write_unlock_bh(&sk->sk_callback_lock);
-
-	/* Call the original destructor */
-	if (sk->sk_destruct)
-		(*sk->sk_destruct)(sk);
-
-	kfree_rcu(tunnel, rcu);
-end:
-	rcu_read_unlock_bh();
-	return;
-}
-
 /* Remove an l2tp session from l2tp_core's lists. */
 static void l2tp_session_unhash(struct l2tp_session *session)
 {
@@ -1623,8 +1585,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 		setup_udp_tunnel_sock(net, sock, &udp_cfg);
 	}
 
-	tunnel->old_sk_destruct = sk->sk_destruct;
-	sk->sk_destruct = &l2tp_tunnel_destruct;
 	sk->sk_allocation = GFP_ATOMIC;
 	release_sock(sk);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 50107531fe3b..6c62d02a0ae6 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -173,7 +173,6 @@ struct l2tp_tunnel {
 	struct net		*l2tp_net;	/* the net we belong to */
 
 	refcount_t		ref_count;
-	void (*old_sk_destruct)(struct sock *sk);
 	struct sock		*sock;		/* parent socket */
 	int			fd;		/* parent fd, if tunnel socket was created
 						 * by userspace
-- 
cgit v1.3-3-g829e


From fc7ec7f554d7d0a27ba339fcf48df11d14413329 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:07 +0100
Subject: l2tp: delete sessions using work queue

When a tunnel is closed, l2tp_tunnel_closeall closes all sessions in
the tunnel. Move the work of deleting each session to the work queue
so that sessions are deleted using the same codepath whether they are
closed by user API request or their parent tunnel is closing. This
also avoids the locking dance in l2tp_tunnel_closeall where the
tunnel's session list lock was unlocked and relocked in the loop.

In l2tp_exit_net, use drain_workqueue instead of flush_workqueue
because the processing of tunnel_delete work may queue session_delete
work items which must also be processed.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 36 ++++++++++++++++++++----------------
 net/l2tp/l2tp_core.h |  1 +
 2 files changed, 21 insertions(+), 16 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a01dd891639b..f6ae18c180bf 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1282,18 +1282,8 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
 
 	spin_lock_bh(&tunnel->list_lock);
 	tunnel->acpt_newsess = false;
-	for (;;) {
-		session = list_first_entry_or_null(&tunnel->session_list,
-						   struct l2tp_session, list);
-		if (!session)
-			break;
-		l2tp_session_inc_refcount(session);
-		list_del_init(&session->list);
-		spin_unlock_bh(&tunnel->list_lock);
+	list_for_each_entry(session, &tunnel->session_list, list)
 		l2tp_session_delete(session);
-		spin_lock_bh(&tunnel->list_lock);
-		l2tp_session_dec_refcount(session);
-	}
 	spin_unlock_bh(&tunnel->list_lock);
 }
 
@@ -1631,18 +1621,31 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
 void l2tp_session_delete(struct l2tp_session *session)
 {
-	if (test_and_set_bit(0, &session->dead))
-		return;
+	if (!test_and_set_bit(0, &session->dead)) {
+		trace_delete_session(session);
+		l2tp_session_inc_refcount(session);
+		queue_work(l2tp_wq, &session->del_work);
+	}
+}
+EXPORT_SYMBOL_GPL(l2tp_session_delete);
+
+/* Workqueue session deletion function */
+static void l2tp_session_del_work(struct work_struct *work)
+{
+	struct l2tp_session *session = container_of(work, struct l2tp_session,
+						    del_work);
 
-	trace_delete_session(session);
 	l2tp_session_unhash(session);
 	l2tp_session_queue_purge(session);
 	if (session->session_close)
 		(*session->session_close)(session);
 
+	/* drop initial ref */
+	l2tp_session_dec_refcount(session);
+
+	/* drop workqueue ref */
 	l2tp_session_dec_refcount(session);
 }
-EXPORT_SYMBOL_GPL(l2tp_session_delete);
 
 /* We come here whenever a session's send_seq, cookie_len or
  * l2specific_type parameters are set.
@@ -1694,6 +1697,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 		INIT_HLIST_NODE(&session->hlist);
 		INIT_LIST_HEAD(&session->clist);
 		INIT_LIST_HEAD(&session->list);
+		INIT_WORK(&session->del_work, l2tp_session_del_work);
 
 		if (cfg) {
 			session->pwtype = cfg->pw_type;
@@ -1751,7 +1755,7 @@ static __net_exit void l2tp_exit_net(struct net *net)
 	rcu_read_unlock_bh();
 
 	if (l2tp_wq)
-		flush_workqueue(l2tp_wq);
+		drain_workqueue(l2tp_wq);
 	rcu_barrier();
 
 	idr_destroy(&pn->l2tp_v2_session_idr);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 6c62d02a0ae6..8d7a589ccd2a 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -102,6 +102,7 @@ struct l2tp_session {
 	int			reorder_skip;	/* set if skip to next nr */
 	enum l2tp_pwtype	pwtype;
 	struct l2tp_stats	stats;
+	struct work_struct	del_work;
 
 	/* Session receive handler for data packets.
 	 * Each pseudowire implementation should implement this callback in order to
-- 
cgit v1.3-3-g829e


From d17e89999574aca143dd4ede43e4382d32d98724 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:08 +0100
Subject: l2tp: free sessions using rcu

l2tp sessions may be accessed under an rcu read lock. Have them freed
via rcu and remove the now unneeded synchronize_rcu when a session is
removed.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 4 +---
 net/l2tp/l2tp_core.h | 1 +
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index f6ae18c180bf..4cf4aa271353 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -166,7 +166,7 @@ static void l2tp_session_free(struct l2tp_session *session)
 	trace_free_session(session);
 	if (session->tunnel)
 		l2tp_tunnel_dec_refcount(session->tunnel);
-	kfree(session);
+	kfree_rcu(session, rcu);
 }
 
 struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk)
@@ -1269,8 +1269,6 @@ static void l2tp_session_unhash(struct l2tp_session *session)
 
 		spin_unlock_bh(&pn->l2tp_session_idr_lock);
 		spin_unlock_bh(&tunnel->list_lock);
-
-		synchronize_rcu();
 	}
 }
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 8d7a589ccd2a..58d3977870de 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -66,6 +66,7 @@ struct l2tp_session_coll_list {
 struct l2tp_session {
 	int			magic;		/* should be L2TP_SESSION_MAGIC */
 	long			dead;
+	struct rcu_head		rcu;
 
 	struct l2tp_tunnel	*tunnel;	/* back pointer to tunnel context */
 	u32			session_id;
-- 
cgit v1.3-3-g829e


From c5cbaef992d6420d8bcebea1b1fcc23302a67c57 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:09 +0100
Subject: l2tp: refactor ppp socket/session relationship

Each l2tp ppp session has an associated pppox socket. l2tp_ppp uses
the session's pppox socket refcount to manage session lifetimes; the
pppox socket holds a ref on the session which is dropped by the socket
destructor. This complicates session cleanup.

Given l2tp sessions are refcounted, it makes more sense to reverse
this relationship such that the session keeps the socket alive, not
the other way around. So refactor l2tp_ppp to have the session hold a
ref on its socket while it references it. When the session is closed,
it drops its socket ref when it detaches from its socket. If the
socket is closed first, it initiates the closing of its session, if
one is attached. The socket/session can then be freed asynchronously
when their refcounts drop to 0.

Use the session's session_close callback to detach the pppox socket
since this will be done on the work queue together with the rest of
the session cleanup via l2tp_session_delete.

Also, since l2tp_ppp uses the pppox socket's sk_user_data, use the rcu
sk_user_data access helpers when accessing it and set the socket's
SOCK_RCU_FREE flag to have pppox sockets freed by rcu.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 94 ++++++++++++++++++++++-------------------------------
 1 file changed, 39 insertions(+), 55 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 0844b86cd0a6..12a0a7162870 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -119,7 +119,6 @@ struct pppol2tp_session {
 	struct mutex		sk_lock;	/* Protects .sk */
 	struct sock __rcu	*sk;		/* Pointer to the session PPPoX socket */
 	struct sock		*__sk;		/* Copy of .sk, for cleanup */
-	struct rcu_head		rcu;		/* For asynchronous release */
 };
 
 static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
@@ -157,20 +156,16 @@ static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
 	if (!sk)
 		return NULL;
 
-	sock_hold(sk);
-	session = (struct l2tp_session *)(sk->sk_user_data);
-	if (!session) {
-		sock_put(sk);
-		goto out;
-	}
-	if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) {
-		session = NULL;
-		sock_put(sk);
-		goto out;
+	rcu_read_lock();
+	session = rcu_dereference_sk_user_data(sk);
+	if (session && refcount_inc_not_zero(&session->ref_count)) {
+		rcu_read_unlock();
+		WARN_ON_ONCE(session->magic != L2TP_SESSION_MAGIC);
+		return session;
 	}
+	rcu_read_unlock();
 
-out:
-	return session;
+	return NULL;
 }
 
 /*****************************************************************************
@@ -318,12 +313,12 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m,
 	l2tp_xmit_skb(session, skb);
 	local_bh_enable();
 
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 
 	return total_len;
 
 error_put_sess:
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 error:
 	return error;
 }
@@ -377,12 +372,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	l2tp_xmit_skb(session, skb);
 	local_bh_enable();
 
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 
 	return 1;
 
 abort_put_sess:
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 abort:
 	/* Free the original skb */
 	kfree_skb(skb);
@@ -393,28 +388,31 @@ abort:
  * Session (and tunnel control) socket create/destroy.
  *****************************************************************************/
 
-static void pppol2tp_put_sk(struct rcu_head *head)
-{
-	struct pppol2tp_session *ps;
-
-	ps = container_of(head, typeof(*ps), rcu);
-	sock_put(ps->__sk);
-}
-
 /* Really kill the session socket. (Called from sock_put() if
  * refcnt == 0.)
  */
 static void pppol2tp_session_destruct(struct sock *sk)
 {
-	struct l2tp_session *session = sk->sk_user_data;
-
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+}
 
-	if (session) {
-		sk->sk_user_data = NULL;
-		if (WARN_ON(session->magic != L2TP_SESSION_MAGIC))
-			return;
+static void pppol2tp_session_close(struct l2tp_session *session)
+{
+	struct pppol2tp_session *ps;
+
+	ps = l2tp_session_priv(session);
+	mutex_lock(&ps->sk_lock);
+	ps->__sk = rcu_dereference_protected(ps->sk,
+					     lockdep_is_held(&ps->sk_lock));
+	RCU_INIT_POINTER(ps->sk, NULL);
+	mutex_unlock(&ps->sk_lock);
+	if (ps->__sk) {
+		/* detach socket */
+		rcu_assign_sk_user_data(ps->__sk, NULL);
+		sock_put(ps->__sk);
+
+		/* drop ref taken when we referenced socket via sk_user_data */
 		l2tp_session_dec_refcount(session);
 	}
 }
@@ -444,30 +442,13 @@ static int pppol2tp_release(struct socket *sock)
 
 	session = pppol2tp_sock_to_session(sk);
 	if (session) {
-		struct pppol2tp_session *ps;
-
 		l2tp_session_delete(session);
-
-		ps = l2tp_session_priv(session);
-		mutex_lock(&ps->sk_lock);
-		ps->__sk = rcu_dereference_protected(ps->sk,
-						     lockdep_is_held(&ps->sk_lock));
-		RCU_INIT_POINTER(ps->sk, NULL);
-		mutex_unlock(&ps->sk_lock);
-		call_rcu(&ps->rcu, pppol2tp_put_sk);
-
-		/* Rely on the sock_put() call at the end of the function for
-		 * dropping the reference held by pppol2tp_sock_to_session().
-		 * The last reference will be dropped by pppol2tp_put_sk().
-		 */
+		/* drop ref taken by pppol2tp_sock_to_session */
+		l2tp_session_dec_refcount(session);
 	}
 
 	release_sock(sk);
 
-	/* This will delete the session context via
-	 * pppol2tp_session_destruct() if the socket's refcnt drops to
-	 * zero.
-	 */
 	sock_put(sk);
 
 	return 0;
@@ -506,6 +487,7 @@ static int pppol2tp_create(struct net *net, struct socket *sock, int kern)
 		goto out;
 
 	sock_init_data(sock, sk);
+	sock_set_flag(sk, SOCK_RCU_FREE);
 
 	sock->state  = SS_UNCONNECTED;
 	sock->ops    = &pppol2tp_ops;
@@ -542,6 +524,7 @@ static void pppol2tp_session_init(struct l2tp_session *session)
 	struct pppol2tp_session *ps;
 
 	session->recv_skb = pppol2tp_recv;
+	session->session_close = pppol2tp_session_close;
 	if (IS_ENABLED(CONFIG_L2TP_DEBUGFS))
 		session->show = pppol2tp_show;
 
@@ -830,12 +813,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 out_no_ppp:
 	/* This is how we get the session context from the socket. */
-	sk->sk_user_data = session;
+	sock_hold(sk);
+	rcu_assign_sk_user_data(sk, session);
 	rcu_assign_pointer(ps->sk, sk);
 	mutex_unlock(&ps->sk_lock);
 
 	/* Keep the reference we've grabbed on the session: sk doesn't expect
-	 * the session to disappear. pppol2tp_session_destruct() is responsible
+	 * the session to disappear. pppol2tp_session_close() is responsible
 	 * for dropping it.
 	 */
 	drop_refcnt = false;
@@ -1002,7 +986,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 
 	error = len;
 
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 end:
 	return error;
 }
@@ -1274,7 +1258,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 		err = pppol2tp_session_setsockopt(sk, session, optname, val);
 	}
 
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 end:
 	return err;
 }
@@ -1395,7 +1379,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 	err = 0;
 
 end_put_sess:
-	sock_put(sk);
+	l2tp_session_dec_refcount(session);
 end:
 	return err;
 }
-- 
cgit v1.3-3-g829e


From 24256415d18695b46da06c93135f5b51c548b950 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:10 +0100
Subject: l2tp: prevent possible tunnel refcount underflow

When a session is created, it sets a backpointer to its tunnel. When
the session refcount drops to 0, l2tp_session_free drops the tunnel
refcount if session->tunnel is non-NULL. However, session->tunnel is
set in l2tp_session_create, before the tunnel refcount is incremented
by l2tp_session_register, which leaves a small window where
session->tunnel is non-NULL when the tunnel refcount hasn't been
bumped.

Moving the assignment to l2tp_session_register is trivial but
l2tp_session_create calls l2tp_session_set_header_len which uses
session->tunnel to get the tunnel's encap. Add an encap arg to
l2tp_session_set_header_len to avoid using session->tunnel.

If l2tpv3 sessions have colliding IDs, it is possible for
l2tp_v3_session_get to race with l2tp_session_register and fetch a
session which doesn't yet have session->tunnel set. Add a check for
this case.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 24 +++++++++++++++++-------
 net/l2tp/l2tp_core.h    |  3 ++-
 net/l2tp/l2tp_netlink.c |  4 +++-
 net/l2tp/l2tp_ppp.c     |  3 ++-
 4 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 4cf4aa271353..cbf117683fab 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -279,7 +279,14 @@ struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk,
 
 		hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session,
 					   hlist, key) {
-			if (session->tunnel->sock == sk &&
+			/* session->tunnel may be NULL if another thread is in
+			 * l2tp_session_register and has added an item to
+			 * l2tp_v3_session_htable but hasn't yet added the
+			 * session to its tunnel's session_list.
+			 */
+			struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel);
+
+			if (tunnel && tunnel->sock == sk &&
 			    refcount_inc_not_zero(&session->ref_count)) {
 				rcu_read_unlock_bh();
 				return session;
@@ -507,6 +514,7 @@ int l2tp_session_register(struct l2tp_session *session,
 	}
 
 	l2tp_tunnel_inc_refcount(tunnel);
+	WRITE_ONCE(session->tunnel, tunnel);
 	list_add(&session->list, &tunnel->session_list);
 
 	if (tunnel->version == L2TP_HDR_VER_3) {
@@ -822,7 +830,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		if (!session->lns_mode && !session->send_seq) {
 			trace_session_seqnum_lns_enable(session);
 			session->send_seq = 1;
-			l2tp_session_set_header_len(session, tunnel->version);
+			l2tp_session_set_header_len(session, tunnel->version,
+						    tunnel->encap);
 		}
 	} else {
 		/* No sequence numbers.
@@ -843,7 +852,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		if (!session->lns_mode && session->send_seq) {
 			trace_session_seqnum_lns_disable(session);
 			session->send_seq = 0;
-			l2tp_session_set_header_len(session, tunnel->version);
+			l2tp_session_set_header_len(session, tunnel->version,
+						    tunnel->encap);
 		} else if (session->send_seq) {
 			pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
 					     session->name);
@@ -1648,7 +1658,8 @@ static void l2tp_session_del_work(struct work_struct *work)
 /* We come here whenever a session's send_seq, cookie_len or
  * l2specific_type parameters are set.
  */
-void l2tp_session_set_header_len(struct l2tp_session *session, int version)
+void l2tp_session_set_header_len(struct l2tp_session *session, int version,
+				 enum l2tp_encap_type encap)
 {
 	if (version == L2TP_HDR_VER_2) {
 		session->hdr_len = 6;
@@ -1657,7 +1668,7 @@ void l2tp_session_set_header_len(struct l2tp_session *session, int version)
 	} else {
 		session->hdr_len = 4 + session->cookie_len;
 		session->hdr_len += l2tp_get_l2specific_len(session);
-		if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP)
+		if (encap == L2TP_ENCAPTYPE_UDP)
 			session->hdr_len += 4;
 	}
 }
@@ -1671,7 +1682,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 	session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL);
 	if (session) {
 		session->magic = L2TP_SESSION_MAGIC;
-		session->tunnel = tunnel;
 
 		session->session_id = session_id;
 		session->peer_session_id = peer_session_id;
@@ -1710,7 +1720,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 			memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len);
 		}
 
-		l2tp_session_set_header_len(session, tunnel->version);
+		l2tp_session_set_header_len(session, tunnel->version, tunnel->encap);
 
 		refcount_set(&session->ref_count, 1);
 
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 58d3977870de..c907687705b9 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -258,7 +258,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
 
 /* Transmit path helpers for sending packets over the tunnel socket. */
-void l2tp_session_set_header_len(struct l2tp_session *session, int version);
+void l2tp_session_set_header_len(struct l2tp_session *session, int version,
+				 enum l2tp_encap_type encap);
 int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb);
 
 /* Pseudowire management.
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index d105030520f9..fc43ecbd128c 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -692,8 +692,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
 	if (info->attrs[L2TP_ATTR_SEND_SEQ]) {
+		struct l2tp_tunnel *tunnel = session->tunnel;
+
 		session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]);
-		l2tp_session_set_header_len(session, session->tunnel->version);
+		l2tp_session_set_header_len(session, tunnel->version, tunnel->encap);
 	}
 
 	if (info->attrs[L2TP_ATTR_LNS_MODE])
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 12a0a7162870..1b79a36d5756 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1189,7 +1189,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 			po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
 				PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
 		}
-		l2tp_session_set_header_len(session, session->tunnel->version);
+		l2tp_session_set_header_len(session, session->tunnel->version,
+					    session->tunnel->encap);
 		break;
 
 	case PPPOL2TP_SO_LNSMODE:
-- 
cgit v1.3-3-g829e


From 89b768ec2dfefaeba5212de14fc71368e12d06ba Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:11 +0100
Subject: l2tp: use rcu list add/del when updating lists

l2tp_v3_session_htable and tunnel->session_list are read by lockless
getters using RCU. Use rcu list variants when adding or removing list
items.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index cbf117683fab..cd9b157e8b4d 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -419,12 +419,12 @@ static int l2tp_session_collision_add(struct l2tp_net *pn,
 
 	/* If existing session isn't already in the session hlist, add it. */
 	if (!hash_hashed(&session2->hlist))
-		hash_add(pn->l2tp_v3_session_htable, &session2->hlist,
-			 session2->hlist_key);
+		hash_add_rcu(pn->l2tp_v3_session_htable, &session2->hlist,
+			     session2->hlist_key);
 
 	/* Add new session to the hlist and collision list */
-	hash_add(pn->l2tp_v3_session_htable, &session1->hlist,
-		 session1->hlist_key);
+	hash_add_rcu(pn->l2tp_v3_session_htable, &session1->hlist,
+		     session1->hlist_key);
 	refcount_inc(&clist->ref_count);
 	l2tp_session_coll_list_add(clist, session1);
 
@@ -440,7 +440,7 @@ static void l2tp_session_collision_del(struct l2tp_net *pn,
 
 	lockdep_assert_held(&pn->l2tp_session_idr_lock);
 
-	hash_del(&session->hlist);
+	hash_del_rcu(&session->hlist);
 
 	if (clist) {
 		/* Remove session from its collision list. If there
@@ -515,7 +515,7 @@ int l2tp_session_register(struct l2tp_session *session,
 
 	l2tp_tunnel_inc_refcount(tunnel);
 	WRITE_ONCE(session->tunnel, tunnel);
-	list_add(&session->list, &tunnel->session_list);
+	list_add_rcu(&session->list, &tunnel->session_list);
 
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		if (!other_session)
-- 
cgit v1.3-3-g829e


From 0aa45570c3241e3bdba1a8b5b30d200c819b5b15 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:12 +0100
Subject: l2tp: add idr consistency check in session_register

l2tp_session_register uses an idr_alloc then idr_replace pattern to
insert sessions into the session IDR. To catch invalid locking, add a
WARN_ON_ONCE if the IDR entry is modified by another thread between
alloc and replace steps.

Also add comments to make expectations clear.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index cd9b157e8b4d..fd03c17dd20c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -474,6 +474,7 @@ int l2tp_session_register(struct l2tp_session *session,
 {
 	struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
 	struct l2tp_session *other_session = NULL;
+	void *old = NULL;
 	u32 session_key;
 	int err;
 
@@ -517,13 +518,19 @@ int l2tp_session_register(struct l2tp_session *session,
 	WRITE_ONCE(session->tunnel, tunnel);
 	list_add_rcu(&session->list, &tunnel->session_list);
 
+	/* this makes session available to lockless getters */
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		if (!other_session)
-			idr_replace(&pn->l2tp_v3_session_idr, session, session_key);
+			old = idr_replace(&pn->l2tp_v3_session_idr, session, session_key);
 	} else {
-		idr_replace(&pn->l2tp_v2_session_idr, session, session_key);
+		old = idr_replace(&pn->l2tp_v2_session_idr, session, session_key);
 	}
 
+	/* old should be NULL, unless something removed or modified
+	 * the IDR entry after our idr_alloc_32 above (which shouldn't
+	 * happen).
+	 */
+	WARN_ON_ONCE(old);
 out:
 	spin_unlock_bh(&pn->l2tp_session_idr_lock);
 	spin_unlock_bh(&tunnel->list_lock);
-- 
cgit v1.3-3-g829e


From d93b8a63f011f252dcfb101d5b90367bd8f42db3 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:13 +0100
Subject: l2tp: cleanup eth/ppp pseudowire setup code

l2tp eth/ppp pseudowire setup/cleanup uses kfree() in some error
paths. Drop the refcount instead such that the session object is
always freed when the refcount reaches 0.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_eth.c | 2 +-
 net/l2tp/l2tp_ppp.c | 8 +++++---
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 8ba00ad433c2..cc8a3ce716e9 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -322,7 +322,7 @@ err_sess_dev:
 	l2tp_session_dec_refcount(session);
 	free_netdev(dev);
 err_sess:
-	kfree(session);
+	l2tp_session_dec_refcount(session);
 err:
 	return rc;
 }
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1b79a36d5756..90bf3a8ccab6 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -770,6 +770,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			goto end;
 		}
 
+		drop_refcnt = true;
+
 		pppol2tp_session_init(session);
 		ps = l2tp_session_priv(session);
 		l2tp_session_inc_refcount(session);
@@ -778,10 +780,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		error = l2tp_session_register(session, tunnel);
 		if (error < 0) {
 			mutex_unlock(&ps->sk_lock);
-			kfree(session);
+			l2tp_session_dec_refcount(session);
 			goto end;
 		}
-		drop_refcnt = true;
+
 		new_session = true;
 	}
 
@@ -875,7 +877,7 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
 	return 0;
 
 err_sess:
-	kfree(session);
+	l2tp_session_dec_refcount(session);
 err:
 	return error;
 }
-- 
cgit v1.3-3-g829e


From 5dfa598b249c5bd8fa620843cf9ece1ad16929d9 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 29 Jul 2024 16:38:14 +0100
Subject: l2tp: use pre_exit pernet hook to avoid rcu_barrier

Move the work of closing all tunnels from the pernet exit hook to
pre_exit since the core does rcu synchronisation between these steps
and we can therefore remove rcu_barrier from l2tp code.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fd03c17dd20c..5d2068b6c778 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1756,7 +1756,7 @@ static __net_init int l2tp_init_net(struct net *net)
 	return 0;
 }
 
-static __net_exit void l2tp_exit_net(struct net *net)
+static __net_exit void l2tp_pre_exit_net(struct net *net)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 	struct l2tp_tunnel *tunnel = NULL;
@@ -1771,7 +1771,11 @@ static __net_exit void l2tp_exit_net(struct net *net)
 
 	if (l2tp_wq)
 		drain_workqueue(l2tp_wq);
-	rcu_barrier();
+}
+
+static __net_exit void l2tp_exit_net(struct net *net)
+{
+	struct l2tp_net *pn = l2tp_pernet(net);
 
 	idr_destroy(&pn->l2tp_v2_session_idr);
 	idr_destroy(&pn->l2tp_v3_session_idr);
@@ -1781,6 +1785,7 @@ static __net_exit void l2tp_exit_net(struct net *net)
 static struct pernet_operations l2tp_net_ops = {
 	.init = l2tp_init_net,
 	.exit = l2tp_exit_net,
+	.pre_exit = l2tp_pre_exit_net,
 	.id   = &l2tp_net_id,
 	.size = sizeof(struct l2tp_net),
 };
-- 
cgit v1.3-3-g829e


From 3b91b03271c5dbf156301ff5028b36925f00e102 Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Mon, 29 Jul 2024 23:01:59 +0200
Subject: net: dsa: vsc73xx: make RGMII delays configurable

This patch switches hardcoded RGMII transmit/receive delay to
a configurable value. Delay values are taken from the properties of
the CPU port: 'tx-internal-delay-ps' and 'rx-internal-delay-ps'.

The default value is configured to 2.0 ns to maintain backward
compatibility with existing code.

Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/vitesse-vsc73xx-core.c | 70 ++++++++++++++++++++++++++++++++--
 1 file changed, 66 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index d9d3e30fd47a..07b704a1557e 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -684,6 +684,67 @@ vsc73xx_update_vlan_table(struct vsc73xx *vsc, int port, u16 vid, bool set)
 	return vsc73xx_write_vlan_table_entry(vsc, vid, portmap);
 }
 
+static int vsc73xx_configure_rgmii_port_delay(struct dsa_switch *ds)
+{
+	/* Keep 2.0 ns delay for backward complatibility */
+	u32 tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS;
+	u32 rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS;
+	struct dsa_port *dp = dsa_to_port(ds, CPU_PORT);
+	struct device_node *port_dn = dp->dn;
+	struct vsc73xx *vsc = ds->priv;
+	u32 delay;
+
+	if (!of_property_read_u32(port_dn, "tx-internal-delay-ps", &delay)) {
+		switch (delay) {
+		case 0:
+			tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_NONE;
+			break;
+		case 1400:
+			tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_4_NS;
+			break;
+		case 1700:
+			tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_7_NS;
+			break;
+		case 2000:
+			break;
+		default:
+			dev_err(vsc->dev,
+				"Unsupported RGMII Transmit Clock Delay\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_dbg(vsc->dev,
+			"RGMII Transmit Clock Delay isn't configured, set to 2.0 ns\n");
+	}
+
+	if (!of_property_read_u32(port_dn, "rx-internal-delay-ps", &delay)) {
+		switch (delay) {
+		case 0:
+			rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_NONE;
+			break;
+		case 1400:
+			rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_4_NS;
+			break;
+		case 1700:
+			rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_7_NS;
+			break;
+		case 2000:
+			break;
+		default:
+			dev_err(vsc->dev,
+				"Unsupported RGMII Receive Clock Delay value\n");
+			return -EINVAL;
+		}
+	} else {
+		dev_dbg(vsc->dev,
+			"RGMII Receive Clock Delay isn't configured, set to 2.0 ns\n");
+	}
+
+	/* MII delay, set both GTX and RX delay */
+	return vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY,
+			     tx_delay | rx_delay);
+}
+
 static int vsc73xx_setup(struct dsa_switch *ds)
 {
 	struct vsc73xx *vsc = ds->priv;
@@ -746,10 +807,11 @@ static int vsc73xx_setup(struct dsa_switch *ds)
 			      VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
 	}
 
-	/* MII delay, set both GTX and RX delay to 2 ns */
-	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY,
-		      VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS |
-		      VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS);
+	/* Configure RGMII delay */
+	ret = vsc73xx_configure_rgmii_port_delay(ds);
+	if (ret)
+		return ret;
+
 	/* Ingess VLAN reception mask (table 145) */
 	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_VLANMASK,
 		      0xff);
-- 
cgit v1.3-3-g829e


From b735154aeb3366b249ab52bbfa0aa8a4c61c9a44 Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Mon, 29 Jul 2024 23:02:01 +0200
Subject: dt-bindings: net: dsa: vsc73xx: add {rx,tx}-internal-delay-ps

Add a schema validator to vitesse,vsc73xx.yaml for MAC-level RGMII delays
in the CPU port. Additionally, valid values for VSC73XX were defined,
and a common definition for the RX and TX valid range was created.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/dsa/vitesse,vsc73xx.yaml          | 32 ++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml
index b99d7a694b70..51cf574249be 100644
--- a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml
@@ -52,6 +52,25 @@ properties:
 allOf:
   - $ref: dsa.yaml#/$defs/ethernet-ports
 
+patternProperties:
+  "^(ethernet-)?ports$":
+    additionalProperties: true
+    patternProperties:
+      "^(ethernet-)?port@6$":
+        allOf:
+          - if:
+              properties:
+                phy-mode:
+                  contains:
+                    enum:
+                      - rgmii
+            then:
+              properties:
+                rx-internal-delay-ps:
+                  $ref: "#/$defs/internal-delay-ps"
+                tx-internal-delay-ps:
+                  $ref: "#/$defs/internal-delay-ps"
+
 # This checks if reg is a chipselect so the device is on an SPI
 # bus, the if-clause will fail if reg is a tuple such as for a
 # platform device.
@@ -67,6 +86,15 @@ required:
   - compatible
   - reg
 
+$defs:
+  internal-delay-ps:
+    description:
+      Disable tunable delay lines using 0 ps, or enable them and select
+      the phase between 1400 ps and 2000 ps in increments of 300 ps.
+    default: 2000
+    enum:
+      [0, 1400, 1700, 2000]
+
 unevaluatedProperties: false
 
 examples:
@@ -108,6 +136,8 @@ examples:
             reg = <6>;
             ethernet = <&gmac1>;
             phy-mode = "rgmii";
+            rx-internal-delay-ps = <0>;
+            tx-internal-delay-ps = <0>;
             fixed-link {
               speed = <1000>;
               full-duplex;
@@ -150,6 +180,8 @@ examples:
           ethernet-port@6 {
             reg = <6>;
             ethernet = <&enet0>;
+            rx-internal-delay-ps = <0>;
+            tx-internal-delay-ps = <0>;
             phy-mode = "rgmii";
             fixed-link {
               speed = <1000>;
-- 
cgit v1.3-3-g829e


From 1018825a9539a67aa381ff033a49355eb03bd84d Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Tue, 30 Jul 2024 09:25:03 +0800
Subject: net/smc: remove unreferenced header in smc_loopback.h file

Because linux/err.h is unreferenced in smc_loopback.h file, so
remove it.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: D. Wythe <alibuda@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_loopback.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h
index 6dd4292dae56..04dc6808d2e1 100644
--- a/net/smc/smc_loopback.h
+++ b/net/smc/smc_loopback.h
@@ -15,7 +15,6 @@
 #define _SMC_LOOPBACK_H
 
 #include <linux/device.h>
-#include <linux/err.h>
 #include <net/smc.h>
 
 #if IS_ENABLED(CONFIG_SMC_LO)
-- 
cgit v1.3-3-g829e


From 5a79575711264b98b435e08107c9e5bf129df210 Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Tue, 30 Jul 2024 09:25:04 +0800
Subject: net/smc: remove the fallback in __smc_connect

When the SMC client begins to connect to server, smcd_version is set
to SMC_V1 + SMC_V2. If fail to get VLAN ID, only SMC_V2 information
is left in smcd_version. And smcd_version will not be changed to 0.
Therefore, remove the fallback caused by the failure to get VLAN ID.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 73a875573e7a..83f5a1849971 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1523,10 +1523,6 @@ static int __smc_connect(struct smc_sock *smc)
 		ini->smcd_version &= ~SMC_V1;
 		ini->smcr_version = 0;
 		ini->smc_type_v1 = SMC_TYPE_N;
-		if (!ini->smcd_version) {
-			rc = SMC_CLC_DECL_GETVLANERR;
-			goto fallback;
-		}
 	}
 
 	rc = smc_find_proposal_devices(smc, ini);
-- 
cgit v1.3-3-g829e


From d37307eaac13f3c5fe912787b5f9facbc574f2cf Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Tue, 30 Jul 2024 09:25:05 +0800
Subject: net/smc: remove redundant code in smc_connect_check_aclc

When the SMC client perform CLC handshake, it will check whether
the clc header type is correct in receiving SMC_CLC_ACCEPT packet.
The specific invoking path is as follows:
__smc_connect
  smc_connect_clc
    smc_clc_wait_msg
      smc_clc_msg_hdr_valid
        smc_clc_msg_acc_conf_valid
Therefore, the smc_connect_check_aclc interface invoked by
__smc_connect does not need to check type again.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 83f5a1849971..6f82e4d8fda4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1466,10 +1466,6 @@ connect_abort:
 static int smc_connect_check_aclc(struct smc_init_info *ini,
 				  struct smc_clc_msg_accept_confirm *aclc)
 {
-	if (aclc->hdr.typev1 != SMC_TYPE_R &&
-	    aclc->hdr.typev1 != SMC_TYPE_D)
-		return SMC_CLC_DECL_MODEUNSUPP;
-
 	if (aclc->hdr.version >= SMC_V2) {
 		if ((aclc->hdr.typev1 == SMC_TYPE_R &&
 		     !smcr_indicated(ini->smc_type_v2)) ||
-- 
cgit v1.3-3-g829e


From 0908503ade5f5fecbdb16c5ce16b2b5ee6107e8d Mon Sep 17 00:00:00 2001
From: Zhengchao Shao <shaozhengchao@huawei.com>
Date: Tue, 30 Jul 2024 09:25:06 +0800
Subject: net/smc: remove unused input parameters in smcr_new_buf_create

The input parameter "is_rmb" of the smcr_new_buf_create function
has never been used, remove it.

Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 3b95828d9976..71fb334d8234 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -2250,7 +2250,7 @@ int smcr_buf_reg_lgr(struct smc_link *lnk)
 }
 
 static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr,
-						bool is_rmb, int bufsize)
+						int bufsize)
 {
 	struct smc_buf_desc *buf_desc;
 
@@ -2398,7 +2398,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		if (is_smcd)
 			buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize);
 		else
-			buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize);
+			buf_desc = smcr_new_buf_create(lgr, bufsize);
 
 		if (PTR_ERR(buf_desc) == -ENOMEM)
 			break;
-- 
cgit v1.3-3-g829e


From 990c304930138dcd7a49763417e6e5313b81293e Mon Sep 17 00:00:00 2001
From: Patrick Rohr <prohr@google.com>
Date: Mon, 29 Jul 2024 15:00:59 -0700
Subject: Add support for PIO p flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

draft-ietf-6man-pio-pflag is adding a new flag to the Prefix Information
Option to signal that the network can allocate a unique IPv6 prefix per
client via DHCPv6-PD (see draft-ietf-v6ops-dhcp-pd-per-device).

When ra_honor_pio_pflag is enabled, the presence of a P-flag causes
SLAAC autoconfiguration to be disabled for that particular PIO.

An automated test has been added in Android (r.android.com/3195335) to
go along with this change.

Cc: Maciej Żenczykowski <maze@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Cc: David Lamparter <equinox@opensourcerouting.org>
Cc: Simon Horman <horms@kernel.org>
Signed-off-by: Patrick Rohr <prohr@google.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.rst | 14 ++++++++++++++
 include/linux/ipv6.h                   |  1 +
 include/net/addrconf.h                 | 10 +++++++---
 net/ipv6/addrconf.c                    | 15 ++++++++++++++-
 4 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 3616389c8c2d..eacf8983e230 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2362,6 +2362,20 @@ ra_honor_pio_life - BOOLEAN
 
 	Default: 0 (disabled)
 
+ra_honor_pio_pflag - BOOLEAN
+	The Prefix Information Option P-flag indicates the network can
+	allocate a unique IPv6 prefix per client using DHCPv6-PD.
+	This sysctl can be enabled when a userspace DHCPv6-PD client
+	is running to cause the P-flag to take effect: i.e. the
+	P-flag suppresses any effects of the A-flag within the same
+	PIO. For a given PIO, P=1 and A=1 is treated as A=0.
+
+	- If disabled, the P-flag is ignored.
+	- If enabled, the P-flag will disable SLAAC autoconfiguration
+	  for the given Prefix Information Option.
+
+	Default: 0 (disabled)
+
 accept_ra_rt_info_min_plen - INTEGER
 	Minimum prefix length of Route Information in RA.
 
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 383a0ea2ab91..a6e2aadbb91b 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -89,6 +89,7 @@ struct ipv6_devconf {
 	__u8		ioam6_enabled;
 	__u8		ndisc_evict_nocarrier;
 	__u8		ra_honor_pio_life;
+	__u8		ra_honor_pio_pflag;
 
 	struct ctl_table_header *sysctl_header;
 };
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 62a407db1bf5..b18e81f0c9e1 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -37,10 +37,14 @@ struct prefix_info {
 		struct __packed {
 #if defined(__BIG_ENDIAN_BITFIELD)
 			__u8	onlink : 1,
-			 	autoconf : 1,
-				reserved : 6;
+				autoconf : 1,
+				routeraddr : 1,
+				preferpd : 1,
+				reserved : 4;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-			__u8	reserved : 6,
+			__u8	reserved : 4,
+				preferpd : 1,
+				routeraddr : 1,
 				autoconf : 1,
 				onlink : 1;
 #else
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f70d8757af1a..c87d008aefa4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -239,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.ioam6_id_wide		= IOAM6_DEFAULT_IF_ID_WIDE,
 	.ndisc_evict_nocarrier	= 1,
 	.ra_honor_pio_life	= 0,
+	.ra_honor_pio_pflag	= 0,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -302,6 +303,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.ioam6_id_wide		= IOAM6_DEFAULT_IF_ID_WIDE,
 	.ndisc_evict_nocarrier	= 1,
 	.ra_honor_pio_life	= 0,
+	.ra_honor_pio_pflag	= 0,
 };
 
 /* Check if link is ready: is it up and is a valid qdisc available */
@@ -2762,6 +2764,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 	u32 addr_flags = 0;
 	struct inet6_dev *in6_dev;
 	struct net *net = dev_net(dev);
+	bool ignore_autoconf = false;
 
 	pinfo = (struct prefix_info *) opt;
 
@@ -2864,7 +2867,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
 
 	/* Try to figure out our local address for this prefix */
 
-	if (pinfo->autoconf && in6_dev->cnf.autoconf) {
+	ignore_autoconf = READ_ONCE(in6_dev->cnf.ra_honor_pio_pflag) && pinfo->preferpd;
+	if (pinfo->autoconf && in6_dev->cnf.autoconf && !ignore_autoconf) {
 		struct in6_addr addr;
 		bool tokenized = false, dev_addr_generated = false;
 
@@ -6926,6 +6930,15 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
 	},
+	{
+		.procname	= "ra_honor_pio_pflag",
+		.data		= &ipv6_devconf.ra_honor_pio_pflag,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
 #ifdef CONFIG_IPV6_ROUTER_PREF
 	{
 		.procname	= "accept_ra_rtr_pref",
-- 
cgit v1.3-3-g829e


From 9c26a1d0a01c941706fd0be55915b4db87bbe7c3 Mon Sep 17 00:00:00 2001
From: Krzysztof Olędzki <ole@ans.pl>
Date: Tue, 30 Jul 2024 17:49:53 -0700
Subject: net/mlx4: Add support for EEPROM high pages query for
 QSFP/QSFP+/QSFP28

Enable reading additional EEPROM information from high pages such as
thresholds and alarms on QSFP/QSFP+/QSFP28 modules.

"This is similar to commit a708fb7b1f8d ("net/mlx5e: ethtool, Add
support for EEPROM high pages query") but given all the required logic
already exists in mlx4_qsfp_eeprom_params_set() only s/_LEN/MAX_LEN/ is
needed.

Tested-by: Dan Merillat <git@dan.merillat.org>
Signed-off-by: Krzysztof Piotr Oledzki <ole@ans.pl>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/b17c5336-6dc3-41f2-afa6-f9e79231f224@ans.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 943d6918c2ec..cd17a3f4faf8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -2036,20 +2036,20 @@ static int mlx4_en_get_module_info(struct net_device *dev,
 	switch (data[0] /* identifier */) {
 	case MLX4_MODULE_ID_QSFP:
 		modinfo->type = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		break;
 	case MLX4_MODULE_ID_QSFP_PLUS:
 		if (data[1] >= 0x3) { /* revision id */
 			modinfo->type = ETH_MODULE_SFF_8636;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
 		} else {
 			modinfo->type = ETH_MODULE_SFF_8436;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN;
 		}
 		break;
 	case MLX4_MODULE_ID_QSFP28:
 		modinfo->type = ETH_MODULE_SFF_8636;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN;
 		break;
 	case MLX4_MODULE_ID_SFP:
 		modinfo->type = ETH_MODULE_SFF_8472;
-- 
cgit v1.3-3-g829e


From a1bb54b1a066e30e4130205a7dba78db9df56fa8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:12 +0200
Subject: mlxsw: core_thermal: Call thermal_zone_device_unregister()
 unconditionally

The function returns immediately if the thermal zone pointer is NULL so
there is no need to check it before calling the function.

Remove the check.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/0bd251aa8ce03d3c951983aa6b4300d8205b88a7.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index d61478c0c632..0b38bab4eaa8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -821,10 +821,7 @@ err_linecards_event_ops_register:
 err_thermal_gearboxes_init:
 	mlxsw_thermal_modules_fini(thermal, &thermal->line_cards[0]);
 err_thermal_modules_init:
-	if (thermal->tzdev) {
-		thermal_zone_device_unregister(thermal->tzdev);
-		thermal->tzdev = NULL;
-	}
+	thermal_zone_device_unregister(thermal->tzdev);
 err_thermal_zone_device_register:
 err_thermal_cooling_device_register:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
@@ -845,10 +842,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 					     thermal);
 	mlxsw_thermal_gearboxes_fini(thermal, &thermal->line_cards[0]);
 	mlxsw_thermal_modules_fini(thermal, &thermal->line_cards[0]);
-	if (thermal->tzdev) {
-		thermal_zone_device_unregister(thermal->tzdev);
-		thermal->tzdev = NULL;
-	}
+	thermal_zone_device_unregister(thermal->tzdev);
 
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
 		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
-- 
cgit v1.3-3-g829e


From 4be011d76408bb7ecfd2f3e00ab89c9a54ce94ce Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:13 +0200
Subject: mlxsw: core_thermal: Remove unnecessary check

mlxsw_thermal_modules_init() allocates an array of modules and then
calls mlxsw_thermal_module_init() to initialize each entry in the array.
It is therefore impossible for mlxsw_thermal_module_init() to encounter
an entry that is already initialized and has its 'parent' pointer set.

Remove the unnecessary check.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 0b38bab4eaa8..394e4fd633ef 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -453,9 +453,6 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
 	struct mlxsw_thermal_module *module_tz;
 
 	module_tz = &area->tz_module_arr[module];
-	/* Skip if parent is already set (case of port split). */
-	if (module_tz->parent)
-		return;
 	module_tz->module = module;
 	module_tz->slot_index = area->slot_index;
 	module_tz->parent = thermal;
-- 
cgit v1.3-3-g829e


From 2a1c9dcb52ddc2916115e4a781f9f2a09c536d97 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:14 +0200
Subject: mlxsw: core_thermal: Remove another unnecessary check

mlxsw_thermal_modules_init() allocates an array of modules and then
initializes each entry by calling mlxsw_thermal_module_init() which
among other things initializes the 'parent' pointer of the entry.

mlxsw_thermal_modules_init() then traverses over the array again, but
skips over entries that do not have their 'parent' pointer set which is
impossible given the above.

Therefore, remove the unnecessary check.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/fb3e8ded422a441436431d5785b900f11ffc9621.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 394e4fd633ef..afd8fe85a94d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -505,8 +505,6 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 
 	for (i = 0; i < area->tz_module_num; i++) {
 		module_tz = &area->tz_module_arr[i];
-		if (!module_tz->parent)
-			continue;
 		err = mlxsw_thermal_module_tz_init(module_tz);
 		if (err)
 			goto err_thermal_module_tz_init;
-- 
cgit v1.3-3-g829e


From d81d71434036642882b55cf93432bf4a1720a481 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:15 +0200
Subject: mlxsw: core_thermal: Fold two loops into one

There is no need to traverse the same array twice. Do it once by folding
both loops into one.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/81756744ed532aaa9249a83fc08757accfe8b07c.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index afd8fe85a94d..b2a4eea859d1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -500,10 +500,8 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 	if (!area->tz_module_arr)
 		return -ENOMEM;
 
-	for (i = 0; i < area->tz_module_num; i++)
-		mlxsw_thermal_module_init(dev, core, thermal, area, i);
-
 	for (i = 0; i < area->tz_module_num; i++) {
+		mlxsw_thermal_module_init(dev, core, thermal, area, i);
 		module_tz = &area->tz_module_arr[i];
 		err = mlxsw_thermal_module_tz_init(module_tz);
 		if (err)
-- 
cgit v1.3-3-g829e


From 73c18f9998fd1f172baaea26d266b1efa4e7b0c5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:16 +0200
Subject: mlxsw: core_thermal: Remove unused arguments

'dev' and 'core' arguments are not used by mlxsw_thermal_module_init().
Remove them.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/563fc7383f61809a306b9954872219eaaf3c689b.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index b2a4eea859d1..95821e91da18 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -446,8 +446,7 @@ static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev)
 }
 
 static void
-mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
-			  struct mlxsw_thermal *thermal,
+mlxsw_thermal_module_init(struct mlxsw_thermal *thermal,
 			  struct mlxsw_thermal_area *area, u8 module)
 {
 	struct mlxsw_thermal_module *module_tz;
@@ -501,7 +500,7 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 		return -ENOMEM;
 
 	for (i = 0; i < area->tz_module_num; i++) {
-		mlxsw_thermal_module_init(dev, core, thermal, area, i);
+		mlxsw_thermal_module_init(thermal, area, i);
 		module_tz = &area->tz_module_arr[i];
 		err = mlxsw_thermal_module_tz_init(module_tz);
 		if (err)
-- 
cgit v1.3-3-g829e


From fb76ea1d4b12dab4ad1573f16b340e97174269b6 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:17 +0200
Subject: mlxsw: core_thermal: Make mlxsw_thermal_module_{init, fini} symmetric

mlxsw_thermal_module_fini() de-initializes the module's thermal zone,
but mlxsw_thermal_module_init() does not initialize it. Make both
functions symmetric by moving the initialization of the module's thermal
zone to mlxsw_thermal_module_init().

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/a661ad468f8ad0d7d533d8334e4abf61dfe34342.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 95821e91da18..36b883a7ee60 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -445,7 +445,7 @@ static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev)
 	thermal_zone_device_unregister(tzdev);
 }
 
-static void
+static int
 mlxsw_thermal_module_init(struct mlxsw_thermal *thermal,
 			  struct mlxsw_thermal_area *area, u8 module)
 {
@@ -461,6 +461,8 @@ mlxsw_thermal_module_init(struct mlxsw_thermal *thermal,
 	       sizeof(thermal->trips));
 	memcpy(module_tz->cooling_states, default_cooling_states,
 	       sizeof(thermal->cooling_states));
+
+	return mlxsw_thermal_module_tz_init(module_tz);
 }
 
 static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
@@ -477,7 +479,6 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 			   struct mlxsw_thermal *thermal,
 			   struct mlxsw_thermal_area *area)
 {
-	struct mlxsw_thermal_module *module_tz;
 	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
 	int i, err;
 
@@ -500,16 +501,14 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 		return -ENOMEM;
 
 	for (i = 0; i < area->tz_module_num; i++) {
-		mlxsw_thermal_module_init(thermal, area, i);
-		module_tz = &area->tz_module_arr[i];
-		err = mlxsw_thermal_module_tz_init(module_tz);
+		err = mlxsw_thermal_module_init(thermal, area, i);
 		if (err)
-			goto err_thermal_module_tz_init;
+			goto err_thermal_module_init;
 	}
 
 	return 0;
 
-err_thermal_module_tz_init:
+err_thermal_module_init:
 	for (i = area->tz_module_num - 1; i >= 0; i--)
 		mlxsw_thermal_module_fini(&area->tz_module_arr[i]);
 	kfree(area->tz_module_arr);
-- 
cgit v1.3-3-g829e


From e25f3040a61961c9f1bcb896b983a33b64d978e2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:18 +0200
Subject: mlxsw: core_thermal: Simplify rollback

During rollback, instead of calling mlxsw_thermal_module_fini() for all
the modules, only call it for modules that were successfully
initialized. This is not a bug fix since mlxsw_thermal_module_fini()
first checks that the module was initialized.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/905bebc45f6e246031f0c5c177bba8efe11e05f5.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 36b883a7ee60..e9bf11a38ae9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -509,7 +509,7 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
 	return 0;
 
 err_thermal_module_init:
-	for (i = area->tz_module_num - 1; i >= 0; i--)
+	for (i--; i >= 0; i--)
 		mlxsw_thermal_module_fini(&area->tz_module_arr[i]);
 	kfree(area->tz_module_arr);
 	return err;
-- 
cgit v1.3-3-g829e


From e7e3a450e5527f3321dc6d0146bf2b86cf44b508 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:19 +0200
Subject: mlxsw: core_thermal: Remove unnecessary checks

mlxsw_thermal_module_fini() cannot be invoked with a thermal module
which is NULL or which is not associated with a thermal zone, so remove
these checks.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/8db5fe0a3a28ba09a15d4102cc03f7e8ca7675be.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index e9bf11a38ae9..cfbfabec816e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -467,11 +467,9 @@ mlxsw_thermal_module_init(struct mlxsw_thermal *thermal,
 
 static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
 {
-	if (module_tz && module_tz->tzdev) {
-		mlxsw_thermal_module_tz_fini(module_tz->tzdev);
-		module_tz->tzdev = NULL;
-		module_tz->parent = NULL;
-	}
+	mlxsw_thermal_module_tz_fini(module_tz->tzdev);
+	module_tz->tzdev = NULL;
+	module_tz->parent = NULL;
 }
 
 static int
-- 
cgit v1.3-3-g829e


From ec672931d150910b5f886d70a5305eb89681b076 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:20 +0200
Subject: mlxsw: core_thermal: Remove unnecessary assignments

Setting both pointers to NULL is unnecessary since the code never checks
whether these pointers are NULL or not. Remove the assignments.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/ea646f5d7642fffd5393fa23650660ab8f77a511.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index cfbfabec816e..269c4986ea24 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -468,8 +468,6 @@ mlxsw_thermal_module_init(struct mlxsw_thermal *thermal,
 static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
 {
 	mlxsw_thermal_module_tz_fini(module_tz->tzdev);
-	module_tz->tzdev = NULL;
-	module_tz->parent = NULL;
 }
 
 static int
-- 
cgit v1.3-3-g829e


From b0d21321140ce9a3cbdf877a4902cce2b596f282 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 30 Jul 2024 15:58:21 +0200
Subject: mlxsw: core_thermal: Fix -Wformat-truncation warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The name of a thermal zone device cannot be longer than 19 characters
('THERMAL_NAME_LENGTH - 1'). The format string 'mlxsw-lc%d-module%d' can
exceed this limitation if the maximum number of line cards cannot be
represented using a single digit and the maximum number of transceiver
modules cannot be represented using two digits.

This is not the case with current systems nor future ones. Therefore,
increase the size of the result buffer beyond 'THERMAL_NAME_LENGTH' and
suppress the following build warning [1].

If this limitation is ever exceeded, we will know about it since the
thermal core validates the thermal device's name during registration.

[1]
drivers/net/ethernet/mellanox/mlxsw/core_thermal.c: In function ‘mlxsw_thermal_modules_init.part.0’:
drivers/net/ethernet/mellanox/mlxsw/core_thermal.c:418:70: error: ‘%d’ directive output may be truncated writing between 1 and 3 bytes into a region of size between 2 and 4 [-Werror=format-truncation=]
  418 |                 snprintf(tz_name, sizeof(tz_name), "mlxsw-lc%d-module%d",
      |                                                                      ^~
In function ‘mlxsw_thermal_module_tz_init’,
    inlined from ‘mlxsw_thermal_module_init’ at drivers/net/ethernet/mellanox/mlxsw/core_thermal.c:465:9,
    inlined from ‘mlxsw_thermal_modules_init.part.0’ at drivers/net/ethernet/mellanox/mlxsw/core_thermal.c:500:9:
drivers/net/ethernet/mellanox/mlxsw/core_thermal.c:418:52: note: directive argument in the range [1, 256]
  418 |                 snprintf(tz_name, sizeof(tz_name), "mlxsw-lc%d-module%d",
      |                                                    ^~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/mellanox/mlxsw/core_thermal.c:418:17: note: ‘snprintf’ output between 18 and 22 bytes into a destination of size 20
  418 |                 snprintf(tz_name, sizeof(tz_name), "mlxsw-lc%d-module%d",
      |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  419 |                          module_tz->slot_index, module_tz->module + 1);
      |                          ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/583a70c6dbe75e6bf0c2c58abbb3470a860d2dc3.1722345311.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 269c4986ea24..303d2ce4dc1e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -411,7 +411,7 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = {
 static int
 mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
 {
-	char tz_name[THERMAL_NAME_LENGTH];
+	char tz_name[40];
 	int err;
 
 	if (module_tz->slot_index)
-- 
cgit v1.3-3-g829e


From 20a3bcfe9327e0559a25a9ecd45967fd4f11ff24 Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.lkml@gmail.com>
Date: Tue, 30 Jul 2024 11:33:49 -0700
Subject: net: alteon: Convert tasklet API to new bottom half workqueue
 mechanism

Migrate tasklet APIs to the new bottom half workqueue mechanism. It
replaces all occurrences of tasklet usage with the appropriate workqueue
APIs throughout the alteon driver. This transition ensures compatibility
with the latest design and enhances performance.

Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Link: https://patch.msgid.link/20240730183403.4176544-2-allen.lkml@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/alteon/acenic.c | 26 +++++++++++++-------------
 drivers/net/ethernet/alteon/acenic.h |  8 ++++----
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 3d8ac63132fb..9e6f91df2ba0 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -1560,9 +1560,9 @@ static void ace_watchdog(struct net_device *data, unsigned int txqueue)
 }
 
 
-static void ace_tasklet(struct tasklet_struct *t)
+static void ace_bh_work(struct work_struct *work)
 {
-	struct ace_private *ap = from_tasklet(ap, t, ace_tasklet);
+	struct ace_private *ap = from_work(ap, work, ace_bh_work);
 	struct net_device *dev = ap->ndev;
 	int cur_size;
 
@@ -1595,7 +1595,7 @@ static void ace_tasklet(struct tasklet_struct *t)
 #endif
 		ace_load_jumbo_rx_ring(dev, RX_JUMBO_SIZE - cur_size);
 	}
-	ap->tasklet_pending = 0;
+	ap->bh_work_pending = 0;
 }
 
 
@@ -1617,7 +1617,7 @@ static void ace_dump_trace(struct ace_private *ap)
  *
  * Loading rings is safe without holding the spin lock since this is
  * done only before the device is enabled, thus no interrupts are
- * generated and by the interrupt handler/tasklet handler.
+ * generated and by the interrupt handler/bh handler.
  */
 static void ace_load_std_rx_ring(struct net_device *dev, int nr_bufs)
 {
@@ -2160,7 +2160,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id)
 	 */
 	if (netif_running(dev)) {
 		int cur_size;
-		int run_tasklet = 0;
+		int run_bh_work = 0;
 
 		cur_size = atomic_read(&ap->cur_rx_bufs);
 		if (cur_size < RX_LOW_STD_THRES) {
@@ -2172,7 +2172,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id)
 				ace_load_std_rx_ring(dev,
 						     RX_RING_SIZE - cur_size);
 			} else
-				run_tasklet = 1;
+				run_bh_work = 1;
 		}
 
 		if (!ACE_IS_TIGON_I(ap)) {
@@ -2188,7 +2188,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id)
 					ace_load_mini_rx_ring(dev,
 							      RX_MINI_SIZE - cur_size);
 				} else
-					run_tasklet = 1;
+					run_bh_work = 1;
 			}
 		}
 
@@ -2205,12 +2205,12 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id)
 					ace_load_jumbo_rx_ring(dev,
 							       RX_JUMBO_SIZE - cur_size);
 				} else
-					run_tasklet = 1;
+					run_bh_work = 1;
 			}
 		}
-		if (run_tasklet && !ap->tasklet_pending) {
-			ap->tasklet_pending = 1;
-			tasklet_schedule(&ap->ace_tasklet);
+		if (run_bh_work && !ap->bh_work_pending) {
+			ap->bh_work_pending = 1;
+			queue_work(system_bh_wq, &ap->ace_bh_work);
 		}
 	}
 
@@ -2267,7 +2267,7 @@ static int ace_open(struct net_device *dev)
 	/*
 	 * Setup the bottom half rx ring refill handler
 	 */
-	tasklet_setup(&ap->ace_tasklet, ace_tasklet);
+	INIT_WORK(&ap->ace_bh_work, ace_bh_work);
 	return 0;
 }
 
@@ -2301,7 +2301,7 @@ static int ace_close(struct net_device *dev)
 	cmd.idx = 0;
 	ace_issue_cmd(regs, &cmd);
 
-	tasklet_kill(&ap->ace_tasklet);
+	cancel_work_sync(&ap->ace_bh_work);
 
 	/*
 	 * Make sure one CPU is not processing packets while
diff --git a/drivers/net/ethernet/alteon/acenic.h b/drivers/net/ethernet/alteon/acenic.h
index ca5ce0cbbad1..0e45a97b9c9b 100644
--- a/drivers/net/ethernet/alteon/acenic.h
+++ b/drivers/net/ethernet/alteon/acenic.h
@@ -2,7 +2,7 @@
 #ifndef _ACENIC_H_
 #define _ACENIC_H_
 #include <linux/interrupt.h>
-
+#include <linux/workqueue.h>
 
 /*
  * Generate TX index update each time, when TX ring is closed.
@@ -667,8 +667,8 @@ struct ace_private
 	struct rx_desc		*rx_mini_ring;
 	struct rx_desc		*rx_return_ring;
 
-	int			tasklet_pending, jumbo;
-	struct tasklet_struct	ace_tasklet;
+	int			bh_work_pending, jumbo;
+	struct work_struct	ace_bh_work;
 
 	struct event		*evt_ring;
 
@@ -776,7 +776,7 @@ static int ace_open(struct net_device *dev);
 static netdev_tx_t ace_start_xmit(struct sk_buff *skb,
 				  struct net_device *dev);
 static int ace_close(struct net_device *dev);
-static void ace_tasklet(struct tasklet_struct *t);
+static void ace_bh_work(struct work_struct *work);
 static void ace_dump_trace(struct ace_private *ap);
 static void ace_set_multicast_list(struct net_device *dev);
 static int ace_change_mtu(struct net_device *dev, int new_mtu);
-- 
cgit v1.3-3-g829e


From 2d671dc6f069f46214d96e934e14f5952d76d92f Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.lkml@gmail.com>
Date: Tue, 30 Jul 2024 11:33:50 -0700
Subject: net: xgbe: Convert tasklet API to new bottom half workqueue mechanism

Migrate tasklet APIs to the new bottom half workqueue mechanism. It
replaces all occurrences of tasklet usage with the appropriate workqueue
APIs throughout the xgbe driver. This transition ensures compatibility
with the latest design and enhances performance.

Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Link: https://patch.msgid.link/20240730183403.4176544-3-allen.lkml@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c  | 30 +++++++++++++++---------------
 drivers/net/ethernet/amd/xgbe/xgbe-i2c.c  | 16 ++++++++--------
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 16 ++++++++--------
 drivers/net/ethernet/amd/xgbe/xgbe-pci.c  |  4 ++--
 drivers/net/ethernet/amd/xgbe/xgbe.h      | 10 +++++-----
 5 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index c4a4e316683f..5475867708f4 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -403,9 +403,9 @@ static bool xgbe_ecc_ded(struct xgbe_prv_data *pdata, unsigned long *period,
 	return false;
 }
 
-static void xgbe_ecc_isr_task(struct tasklet_struct *t)
+static void xgbe_ecc_isr_bh_work(struct work_struct *work)
 {
-	struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_ecc);
+	struct xgbe_prv_data *pdata = from_work(pdata, work, ecc_bh_work);
 	unsigned int ecc_isr;
 	bool stop = false;
 
@@ -465,17 +465,17 @@ static irqreturn_t xgbe_ecc_isr(int irq, void *data)
 {
 	struct xgbe_prv_data *pdata = data;
 
-	if (pdata->isr_as_tasklet)
-		tasklet_schedule(&pdata->tasklet_ecc);
+	if (pdata->isr_as_bh_work)
+		queue_work(system_bh_wq, &pdata->ecc_bh_work);
 	else
-		xgbe_ecc_isr_task(&pdata->tasklet_ecc);
+		xgbe_ecc_isr_bh_work(&pdata->ecc_bh_work);
 
 	return IRQ_HANDLED;
 }
 
-static void xgbe_isr_task(struct tasklet_struct *t)
+static void xgbe_isr_bh_work(struct work_struct *work)
 {
-	struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_dev);
+	struct xgbe_prv_data *pdata = from_work(pdata, work, dev_bh_work);
 	struct xgbe_hw_if *hw_if = &pdata->hw_if;
 	struct xgbe_channel *channel;
 	unsigned int dma_isr, dma_ch_isr;
@@ -582,7 +582,7 @@ isr_done:
 
 	/* If there is not a separate ECC irq, handle it here */
 	if (pdata->vdata->ecc_support && (pdata->dev_irq == pdata->ecc_irq))
-		xgbe_ecc_isr_task(&pdata->tasklet_ecc);
+		xgbe_ecc_isr_bh_work(&pdata->ecc_bh_work);
 
 	/* If there is not a separate I2C irq, handle it here */
 	if (pdata->vdata->i2c_support && (pdata->dev_irq == pdata->i2c_irq))
@@ -604,10 +604,10 @@ static irqreturn_t xgbe_isr(int irq, void *data)
 {
 	struct xgbe_prv_data *pdata = data;
 
-	if (pdata->isr_as_tasklet)
-		tasklet_schedule(&pdata->tasklet_dev);
+	if (pdata->isr_as_bh_work)
+		queue_work(system_bh_wq, &pdata->dev_bh_work);
 	else
-		xgbe_isr_task(&pdata->tasklet_dev);
+		xgbe_isr_bh_work(&pdata->dev_bh_work);
 
 	return IRQ_HANDLED;
 }
@@ -1007,8 +1007,8 @@ static int xgbe_request_irqs(struct xgbe_prv_data *pdata)
 	unsigned int i;
 	int ret;
 
-	tasklet_setup(&pdata->tasklet_dev, xgbe_isr_task);
-	tasklet_setup(&pdata->tasklet_ecc, xgbe_ecc_isr_task);
+	INIT_WORK(&pdata->dev_bh_work, xgbe_isr_bh_work);
+	INIT_WORK(&pdata->ecc_bh_work, xgbe_ecc_isr_bh_work);
 
 	ret = devm_request_irq(pdata->dev, pdata->dev_irq, xgbe_isr, 0,
 			       netdev_name(netdev), pdata);
@@ -1078,8 +1078,8 @@ static void xgbe_free_irqs(struct xgbe_prv_data *pdata)
 
 	devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
 
-	tasklet_kill(&pdata->tasklet_dev);
-	tasklet_kill(&pdata->tasklet_ecc);
+	cancel_work_sync(&pdata->dev_bh_work);
+	cancel_work_sync(&pdata->ecc_bh_work);
 
 	if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
 		devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
index a9ccc4258ee5..7a833894f52a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c
@@ -274,9 +274,9 @@ static void xgbe_i2c_clear_isr_interrupts(struct xgbe_prv_data *pdata,
 		XI2C_IOREAD(pdata, IC_CLR_STOP_DET);
 }
 
-static void xgbe_i2c_isr_task(struct tasklet_struct *t)
+static void xgbe_i2c_isr_bh_work(struct work_struct *work)
 {
-	struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_i2c);
+	struct xgbe_prv_data *pdata = from_work(pdata, work, i2c_bh_work);
 	struct xgbe_i2c_op_state *state = &pdata->i2c.op_state;
 	unsigned int isr;
 
@@ -321,10 +321,10 @@ static irqreturn_t xgbe_i2c_isr(int irq, void *data)
 {
 	struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
 
-	if (pdata->isr_as_tasklet)
-		tasklet_schedule(&pdata->tasklet_i2c);
+	if (pdata->isr_as_bh_work)
+		queue_work(system_bh_wq, &pdata->i2c_bh_work);
 	else
-		xgbe_i2c_isr_task(&pdata->tasklet_i2c);
+		xgbe_i2c_isr_bh_work(&pdata->i2c_bh_work);
 
 	return IRQ_HANDLED;
 }
@@ -369,7 +369,7 @@ static void xgbe_i2c_set_target(struct xgbe_prv_data *pdata, unsigned int addr)
 
 static irqreturn_t xgbe_i2c_combined_isr(struct xgbe_prv_data *pdata)
 {
-	xgbe_i2c_isr_task(&pdata->tasklet_i2c);
+	xgbe_i2c_isr_bh_work(&pdata->i2c_bh_work);
 
 	return IRQ_HANDLED;
 }
@@ -449,7 +449,7 @@ static void xgbe_i2c_stop(struct xgbe_prv_data *pdata)
 
 	if (pdata->dev_irq != pdata->i2c_irq) {
 		devm_free_irq(pdata->dev, pdata->i2c_irq, pdata);
-		tasklet_kill(&pdata->tasklet_i2c);
+		cancel_work_sync(&pdata->i2c_bh_work);
 	}
 }
 
@@ -464,7 +464,7 @@ static int xgbe_i2c_start(struct xgbe_prv_data *pdata)
 
 	/* If we have a separate I2C irq, enable it */
 	if (pdata->dev_irq != pdata->i2c_irq) {
-		tasklet_setup(&pdata->tasklet_i2c, xgbe_i2c_isr_task);
+		INIT_WORK(&pdata->i2c_bh_work, xgbe_i2c_isr_bh_work);
 
 		ret = devm_request_irq(pdata->dev, pdata->i2c_irq,
 				       xgbe_i2c_isr, 0, pdata->i2c_name,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 4a2dc705b528..07f4f3418d01 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -703,9 +703,9 @@ static void xgbe_an73_isr(struct xgbe_prv_data *pdata)
 	}
 }
 
-static void xgbe_an_isr_task(struct tasklet_struct *t)
+static void xgbe_an_isr_bh_work(struct work_struct *work)
 {
-	struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_an);
+	struct xgbe_prv_data *pdata = from_work(pdata, work, an_bh_work);
 
 	netif_dbg(pdata, intr, pdata->netdev, "AN interrupt received\n");
 
@@ -727,17 +727,17 @@ static irqreturn_t xgbe_an_isr(int irq, void *data)
 {
 	struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data;
 
-	if (pdata->isr_as_tasklet)
-		tasklet_schedule(&pdata->tasklet_an);
+	if (pdata->isr_as_bh_work)
+		queue_work(system_bh_wq, &pdata->an_bh_work);
 	else
-		xgbe_an_isr_task(&pdata->tasklet_an);
+		xgbe_an_isr_bh_work(&pdata->an_bh_work);
 
 	return IRQ_HANDLED;
 }
 
 static irqreturn_t xgbe_an_combined_isr(struct xgbe_prv_data *pdata)
 {
-	xgbe_an_isr_task(&pdata->tasklet_an);
+	xgbe_an_isr_bh_work(&pdata->an_bh_work);
 
 	return IRQ_HANDLED;
 }
@@ -1454,7 +1454,7 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata)
 
 	if (pdata->dev_irq != pdata->an_irq) {
 		devm_free_irq(pdata->dev, pdata->an_irq, pdata);
-		tasklet_kill(&pdata->tasklet_an);
+		cancel_work_sync(&pdata->an_bh_work);
 	}
 
 	pdata->phy_if.phy_impl.stop(pdata);
@@ -1477,7 +1477,7 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata)
 
 	/* If we have a separate AN irq, enable it */
 	if (pdata->dev_irq != pdata->an_irq) {
-		tasklet_setup(&pdata->tasklet_an, xgbe_an_isr_task);
+		INIT_WORK(&pdata->an_bh_work, xgbe_an_isr_bh_work);
 
 		ret = devm_request_irq(pdata->dev, pdata->an_irq,
 				       xgbe_an_isr, 0, pdata->an_name,
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index c5e5fac49779..c636999a6a84 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -139,7 +139,7 @@ static int xgbe_config_multi_msi(struct xgbe_prv_data *pdata)
 		return ret;
 	}
 
-	pdata->isr_as_tasklet = 1;
+	pdata->isr_as_bh_work = 1;
 	pdata->irq_count = ret;
 
 	pdata->dev_irq = pci_irq_vector(pdata->pcidev, 0);
@@ -176,7 +176,7 @@ static int xgbe_config_irqs(struct xgbe_prv_data *pdata)
 		return ret;
 	}
 
-	pdata->isr_as_tasklet = pdata->pcidev->msi_enabled ? 1 : 0;
+	pdata->isr_as_bh_work = pdata->pcidev->msi_enabled ? 1 : 0;
 	pdata->irq_count = 1;
 	pdata->channel_irq_count = 1;
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index f01a1e566da6..d85386cac8d1 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -1298,11 +1298,11 @@ struct xgbe_prv_data {
 
 	unsigned int lpm_ctrl;		/* CTRL1 for resume */
 
-	unsigned int isr_as_tasklet;
-	struct tasklet_struct tasklet_dev;
-	struct tasklet_struct tasklet_ecc;
-	struct tasklet_struct tasklet_i2c;
-	struct tasklet_struct tasklet_an;
+	unsigned int isr_as_bh_work;
+	struct work_struct dev_bh_work;
+	struct work_struct ecc_bh_work;
+	struct work_struct i2c_bh_work;
+	struct work_struct an_bh_work;
 
 	struct dentry *xgbe_debugfs;
 
-- 
cgit v1.3-3-g829e


From 8d3beb6bc765ccea794612066454da5bb72a0746 Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.lkml@gmail.com>
Date: Tue, 30 Jul 2024 11:33:51 -0700
Subject: net: cnic: Convert tasklet API to new bottom half workqueue mechanism

Migrate tasklet APIs to the new bottom half workqueue mechanism. It
replaces all occurrences of tasklet usage with the appropriate workqueue
APIs throughout the cnic driver. This transition ensures compatibility
with the latest design and enhances performance.

Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Link: https://patch.msgid.link/20240730183403.4176544-4-allen.lkml@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/cnic.c | 19 ++++++++++---------
 drivers/net/ethernet/broadcom/cnic.h |  2 +-
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index c2b4188a1ef1..a9040c42d2ff 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -31,6 +31,7 @@
 #include <linux/if_vlan.h>
 #include <linux/prefetch.h>
 #include <linux/random.h>
+#include <linux/workqueue.h>
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 #define BCM_VLAN 1
 #endif
@@ -3015,9 +3016,9 @@ static int cnic_service_bnx2(void *data, void *status_blk)
 	return cnic_service_bnx2_queues(dev);
 }
 
-static void cnic_service_bnx2_msix(struct tasklet_struct *t)
+static void cnic_service_bnx2_msix(struct work_struct *work)
 {
-	struct cnic_local *cp = from_tasklet(cp, t, cnic_irq_task);
+	struct cnic_local *cp = from_work(cp, work, cnic_irq_bh_work);
 	struct cnic_dev *dev = cp->dev;
 
 	cp->last_status_idx = cnic_service_bnx2_queues(dev);
@@ -3036,7 +3037,7 @@ static void cnic_doirq(struct cnic_dev *dev)
 		prefetch(cp->status_blk.gen);
 		prefetch(&cp->kcq1.kcq[KCQ_PG(prod)][KCQ_IDX(prod)]);
 
-		tasklet_schedule(&cp->cnic_irq_task);
+		queue_work(system_bh_wq, &cp->cnic_irq_bh_work);
 	}
 }
 
@@ -3140,9 +3141,9 @@ static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info)
 	return last_status;
 }
 
-static void cnic_service_bnx2x_bh(struct tasklet_struct *t)
+static void cnic_service_bnx2x_bh_work(struct work_struct *work)
 {
-	struct cnic_local *cp = from_tasklet(cp, t, cnic_irq_task);
+	struct cnic_local *cp = from_work(cp, work, cnic_irq_bh_work);
 	struct cnic_dev *dev = cp->dev;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
 	u32 status_idx, new_status_idx;
@@ -4428,7 +4429,7 @@ static void cnic_free_irq(struct cnic_dev *dev)
 
 	if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) {
 		cp->disable_int_sync(dev);
-		tasklet_kill(&cp->cnic_irq_task);
+		cancel_work_sync(&cp->cnic_irq_bh_work);
 		free_irq(ethdev->irq_arr[0].vector, dev);
 	}
 }
@@ -4441,7 +4442,7 @@ static int cnic_request_irq(struct cnic_dev *dev)
 
 	err = request_irq(ethdev->irq_arr[0].vector, cnic_irq, 0, "cnic", dev);
 	if (err)
-		tasklet_disable(&cp->cnic_irq_task);
+		disable_work_sync(&cp->cnic_irq_bh_work);
 
 	return err;
 }
@@ -4464,7 +4465,7 @@ static int cnic_init_bnx2_irq(struct cnic_dev *dev)
 		CNIC_WR(dev, base + BNX2_HC_CMD_TICKS_OFF, (64 << 16) | 220);
 
 		cp->last_status_idx = cp->status_blk.bnx2->status_idx;
-		tasklet_setup(&cp->cnic_irq_task, cnic_service_bnx2_msix);
+		INIT_WORK(&cp->cnic_irq_bh_work, cnic_service_bnx2_msix);
 		err = cnic_request_irq(dev);
 		if (err)
 			return err;
@@ -4873,7 +4874,7 @@ static int cnic_init_bnx2x_irq(struct cnic_dev *dev)
 	struct cnic_eth_dev *ethdev = cp->ethdev;
 	int err = 0;
 
-	tasklet_setup(&cp->cnic_irq_task, cnic_service_bnx2x_bh);
+	INIT_WORK(&cp->cnic_irq_bh_work, cnic_service_bnx2x_bh_work);
 	if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX)
 		err = cnic_request_irq(dev);
 
diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h
index fedc84ada937..1a314a75d2d2 100644
--- a/drivers/net/ethernet/broadcom/cnic.h
+++ b/drivers/net/ethernet/broadcom/cnic.h
@@ -268,7 +268,7 @@ struct cnic_local {
 	u32				bnx2x_igu_sb_id;
 	u32				int_num;
 	u32				last_status_idx;
-	struct tasklet_struct		cnic_irq_task;
+	struct work_struct		cnic_irq_bh_work;
 
 	struct kcqe		*completed_kcq[MAX_COMPLETED_KCQE];
 
-- 
cgit v1.3-3-g829e


From c5092ba3155e0696e922fc9f1c2909f48fde2102 Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.lkml@gmail.com>
Date: Tue, 30 Jul 2024 11:33:52 -0700
Subject: net: macb: Convert tasklet API to new bottom half workqueue mechanism

Migrate tasklet APIs to the new bottom half workqueue mechanism. It
replaces all occurrences of tasklet usage with the appropriate workqueue
APIs throughout the macb driver. This transition ensures compatibility
with the latest design and enhances performance.

Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Link: https://patch.msgid.link/20240730183403.4176544-5-allen.lkml@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb.h      |  3 ++-
 drivers/net/ethernet/cadence/macb_main.c | 10 +++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index ea71612f6b36..5740c98d8c9f 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -13,6 +13,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/interrupt.h>
 #include <linux/phy/phy.h>
+#include <linux/workqueue.h>
 
 #if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP)
 #define MACB_EXT_DESC
@@ -1330,7 +1331,7 @@ struct macb {
 	spinlock_t rx_fs_lock;
 	unsigned int max_tuples;
 
-	struct tasklet_struct	hresp_err_tasklet;
+	struct work_struct	hresp_err_bh_work;
 
 	int	rx_bd_rd_prefetch;
 	int	tx_bd_rd_prefetch;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 11665be3a22c..95e8742dce1d 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1792,9 +1792,9 @@ static int macb_tx_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-static void macb_hresp_error_task(struct tasklet_struct *t)
+static void macb_hresp_error_task(struct work_struct *work)
 {
-	struct macb *bp = from_tasklet(bp, t, hresp_err_tasklet);
+	struct macb *bp = from_work(bp, work, hresp_err_bh_work);
 	struct net_device *dev = bp->dev;
 	struct macb_queue *queue;
 	unsigned int q;
@@ -1994,7 +1994,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 		}
 
 		if (status & MACB_BIT(HRESP)) {
-			tasklet_schedule(&bp->hresp_err_tasklet);
+			queue_work(system_bh_wq, &bp->hresp_err_bh_work);
 			netdev_err(dev, "DMA bus error: HRESP not OK\n");
 
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
@@ -5172,7 +5172,7 @@ static int macb_probe(struct platform_device *pdev)
 		goto err_out_unregister_mdio;
 	}
 
-	tasklet_setup(&bp->hresp_err_tasklet, macb_hresp_error_task);
+	INIT_WORK(&bp->hresp_err_bh_work, macb_hresp_error_task);
 
 	netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n",
 		    macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
@@ -5216,7 +5216,7 @@ static void macb_remove(struct platform_device *pdev)
 		mdiobus_free(bp->mii_bus);
 
 		unregister_netdev(dev);
-		tasklet_kill(&bp->hresp_err_tasklet);
+		cancel_work_sync(&bp->hresp_err_bh_work);
 		pm_runtime_disable(&pdev->dev);
 		pm_runtime_dont_use_autosuspend(&pdev->dev);
 		if (!pm_runtime_suspended(&pdev->dev)) {
-- 
cgit v1.3-3-g829e


From c9c0ee5f20c593faf289fa8850c3ed84031dd12a Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 29 Jul 2024 03:47:40 -0700
Subject: net: skbuff: Skip early return in skb_unref when debugging

This patch modifies the skb_unref function to skip the early return
optimization when CONFIG_DEBUG_NET is enabled. The change ensures that
the reference count decrement always occurs in debug builds, allowing
for more thorough checking of SKB reference counting.

Previously, when the SKB's reference count was 1 and CONFIG_DEBUG_NET
was not set, the function would return early after a memory barrier
(smp_rmb()) without decrementing the reference count. This optimization
assumes it's safe to proceed with freeing the SKB without the overhead
of an atomic decrement from 1 to 0.

With this change:
- In non-debug builds (CONFIG_DEBUG_NET not set), behavior remains
  unchanged, preserving the performance optimization.
- In debug builds (CONFIG_DEBUG_NET set), the reference count is always
  decremented, even when it's 1, allowing for consistent behavior and
  potentially catching subtle SKB management bugs.

This modification enhances debugging capabilities for networking code
without impacting performance in production kernels. It helps kernel
developers identify and diagnose issues related to SKB management and
reference counting in the network stack.

Cc: Chris Mason <clm@fb.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240729104741.370327-1-leitao@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 29c3ea5b6e93..cf8f6ce06742 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1225,7 +1225,7 @@ static inline bool skb_unref(struct sk_buff *skb)
 {
 	if (unlikely(!skb))
 		return false;
-	if (likely(refcount_read(&skb->users) == 1))
+	if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1))
 		smp_rmb();
 	else if (likely(!refcount_dec_and_test(&skb->users)))
 		return false;
-- 
cgit v1.3-3-g829e


From aa0d7643c8dd1a0483189499ea2f9492d74f4970 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 9 Apr 2024 22:28:27 +0200
Subject: wifi: ath9k: use unmanaged PCI functions in ath9k_pci_owl_loader
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Only managed PCI resource in the driver is the iomapped bar. However the bar
is unmapped in the same function. Therefore using the device-managed
versions just causes overhead, w/o any benefit. Once this is switched to the
non-managed versions, there's nothing left to be managed for
pcim_enable_device(). Therefore we can reduce overhead here too and switch to
the non-managed version as well. This includes removing the no longer needed
call to pcim_pin_device().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/3b46f6c7-4372-4cc9-9a7c-2c1c06d29324@gmail.com
---
 drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c
index a5eb43f30320..004ca5f536be 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c
+++ b/drivers/net/wireless/ath/ath9k/ath9k_pci_owl_loader.c
@@ -65,7 +65,7 @@ static int ath9k_pci_fixup(struct pci_dev *pdev, const u16 *cal_data,
 
 	dev_info(&pdev->dev, "fixup device configuration\n");
 
-	mem = pcim_iomap(pdev, 0, 0);
+	mem = pci_iomap(pdev, 0, 0);
 	if (!mem) {
 		dev_err(&pdev->dev, "ioremap error\n");
 		return -EINVAL;
@@ -103,7 +103,7 @@ static int ath9k_pci_fixup(struct pci_dev *pdev, const u16 *cal_data,
 	pci_write_config_word(pdev, PCI_COMMAND, cmd);
 
 	pci_write_config_dword(pdev, PCI_BASE_ADDRESS_0, bar0);
-	pcim_iounmap(pdev, mem);
+	pci_iounmap(pdev, mem);
 
 	pci_disable_device(pdev);
 
@@ -200,11 +200,9 @@ static int owl_probe(struct pci_dev *pdev,
 	const char *eeprom_name;
 	int err = 0;
 
-	if (pcim_enable_device(pdev))
+	if (pci_enable_device(pdev))
 		return -EIO;
 
-	pcim_pin_device(pdev);
-
 	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
-- 
cgit v1.3-3-g829e


From 215a19631d1125a2834b2ffe62b8de9a9e73d6a8 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@toblux.com>
Date: Wed, 10 Jul 2024 20:57:44 +0200
Subject: wifi: ath9k: Use swap() to improve ath9k_hw_get_nf_hist_mid()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the swap() macro to simplify the ath9k_hw_get_nf_hist_mid() function
and improve its readability.

Fixes the following Coccinelle/coccicheck warning reported by
swap.cocci:

  WARNING opportunity for swap()

Compile-tested only.

Signed-off-by: Thorsten Blum <thorsten.blum@toblux.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240710185743.709742-2-thorsten.blum@toblux.com
---
 drivers/net/wireless/ath/ath9k/calib.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c
index fb270df75eb2..4b331c85509c 100644
--- a/drivers/net/wireless/ath/ath9k/calib.c
+++ b/drivers/net/wireless/ath/ath9k/calib.c
@@ -32,11 +32,8 @@ static int16_t ath9k_hw_get_nf_hist_mid(int16_t *nfCalBuffer)
 
 	for (i = 0; i < ATH9K_NF_CAL_HIST_MAX - 1; i++) {
 		for (j = 1; j < ATH9K_NF_CAL_HIST_MAX - i; j++) {
-			if (sort[j] > sort[j - 1]) {
-				nfval = sort[j];
-				sort[j] = sort[j - 1];
-				sort[j - 1] = nfval;
-			}
+			if (sort[j] > sort[j - 1])
+				swap(sort[j], sort[j - 1]);
 		}
 	}
 	nfval = sort[(ATH9K_NF_CAL_HIST_MAX - 1) >> 1];
-- 
cgit v1.3-3-g829e


From 3f66f26703093886db81f0610b97a6794511917c Mon Sep 17 00:00:00 2001
From: Dmitry Kandybka <d.kandybka@gmail.com>
Date: Thu, 25 Jul 2024 14:17:43 +0300
Subject: wifi: ath9k: fix possible integer overflow in ath9k_get_et_stats()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In 'ath9k_get_et_stats()', promote TX stats counters to 'u64'
to avoid possible integer overflow. Compile tested only.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Signed-off-by: Dmitry Kandybka <d.kandybka@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240725111743.14422-1-d.kandybka@gmail.com
---
 drivers/net/wireless/ath/ath9k/debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index d84e3ee7b5d9..886a102e5b02 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -1325,11 +1325,11 @@ void ath9k_get_et_stats(struct ieee80211_hw *hw,
 	struct ath_softc *sc = hw->priv;
 	int i = 0;
 
-	data[i++] = (sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_BE)].tx_pkts_all +
+	data[i++] = ((u64)sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_BE)].tx_pkts_all +
 		     sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_BK)].tx_pkts_all +
 		     sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_VI)].tx_pkts_all +
 		     sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_VO)].tx_pkts_all);
-	data[i++] = (sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_BE)].tx_bytes_all +
+	data[i++] = ((u64)sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_BE)].tx_bytes_all +
 		     sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_BK)].tx_bytes_all +
 		     sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_VI)].tx_bytes_all +
 		     sc->debug.stats.txstats[PR_QNUM(IEEE80211_AC_VO)].tx_bytes_all);
-- 
cgit v1.3-3-g829e


From 501c3005f0311a7810cc7e56546930638ae6b26f Mon Sep 17 00:00:00 2001
From: Anand Khoje <anand.a.khoje@oracle.com>
Date: Tue, 30 Jul 2024 13:06:33 +0530
Subject: net/mlx5: Reclaim max 50K pages at once
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In non FLR context, at times CX-5 requests release of ~8 million FW pages.
This needs humongous number of cmd mailboxes, which to be released once
the pages are reclaimed. Release of humongous number of cmd mailboxes is
consuming cpu time running into many seconds. Which with non preemptible
kernels is leading to critical process starving on that cpu’s RQ.
On top of it, the FW does not use all the mailbox messages as it has a
limit of releasing 50K pages at once per MLX5_CMD_OP_MANAGE_PAGES +
MLX5_PAGES_TAKE device command. Hence, the allocation of these many
mailboxes is extra and adds unnecessary overhead.
To alleviate this, this change restricts the total number of pages
a worker will try to reclaim to maximum 50K pages in one go.

Our tests have shown significant benefit of this change in terms of
time consumed by dma_pool_free().
During a test where an event was raised by HCA
to release 1.3 Million pages, following observations were made:

- Without this change:
Number of mailbox messages allocated was around 20K, to accommodate
the DMA addresses of 1.3 million pages.
The average time spent by dma_pool_free() to free the DMA pool is between
16 usec to 32 usec.
           value  ------------- Distribution ------------- count
             256 |                                         0
             512 |@                                        287
            1024 |@@@                                      1332
            2048 |@                                        656
            4096 |@@@@@                                    2599
            8192 |@@@@@@@@@@                               4755
           16384 |@@@@@@@@@@@@@@@                          7545
           32768 |@@@@@                                    2501
           65536 |                                         0

- With this change:
Number of mailbox messages allocated was around 800; this was to
accommodate DMA addresses of only 50K pages.
The average time spent by dma_pool_free() to free the DMA pool in this case
lies between 1 usec to 2 usec.
           value  ------------- Distribution ------------- count
             256 |                                         0
             512 |@@@@@@@@@@@@@@@@@@                       346
            1024 |@@@@@@@@@@@@@@@@@@@@@@                   435
            2048 |                                         0
            4096 |                                         0
            8192 |                                         1
           16384 |                                         0

Signed-off-by: Anand Khoje <anand.a.khoje@oracle.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Acked-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://patch.msgid.link/20240730073634.114407-1-anand.a.khoje@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index d894a88fa9f2..972e8e9df585 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -608,6 +608,11 @@ enum {
 	RELEASE_ALL_PAGES_MASK = 0x4000,
 };
 
+/* This limit is based on the capability of the firmware as it cannot release
+ * more than 50000 back to the host in one go.
+ */
+#define MAX_RECLAIM_NPAGES (-50000)
+
 static int req_pages_handler(struct notifier_block *nb,
 			     unsigned long type, void *data)
 {
@@ -639,7 +644,16 @@ static int req_pages_handler(struct notifier_block *nb,
 
 	req->dev = dev;
 	req->func_id = func_id;
-	req->npages = npages;
+
+	/* npages > 0 means HCA asking host to allocate/give pages,
+	 * npages < 0 means HCA asking host to reclaim back the pages allocated.
+	 * Here we are restricting the maximum number of pages that can be
+	 * reclaimed to be MAX_RECLAIM_NPAGES. Note that MAX_RECLAIM_NPAGES is
+	 * a negative value.
+	 * Since MAX_RECLAIM is negative, we are using max() to restrict
+	 * req->npages (and not min ()).
+	 */
+	req->npages = max_t(s32, npages, MAX_RECLAIM_NPAGES);
 	req->ec_function = ec_function;
 	req->release_all = release_all;
 	INIT_WORK(&req->work, pages_work_handler);
-- 
cgit v1.3-3-g829e


From 887b1d1adb2e9318b9233bef648bd2b1cc1e66ff Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Tue, 30 Jul 2024 11:36:42 +0100
Subject: net: ethernet: mtk_eth_soc: drop clocks unused by Ethernet driver

Clocks for SerDes and PHY are going to be handled by standalone drivers
for each of those hardware components. Drop them from the Ethernet driver.

The clocks which are being removed for this patch are responsible for
the for the SerDes PCS and PHYs used for the 2nd and 3rd MAC which are
anyway not yet supported. Hence backwards compatibility is not an issue.

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/b5faaf69b5c6e3e155c64af03706c3c423c6a1c9.1722335682.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index eb1708b43aa3..0d5225f1d3ee 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -724,12 +724,8 @@ enum mtk_clks_map {
 	MTK_CLK_ETHWARP_WOCPU2,
 	MTK_CLK_ETHWARP_WOCPU1,
 	MTK_CLK_ETHWARP_WOCPU0,
-	MTK_CLK_TOP_USXGMII_SBUS_0_SEL,
-	MTK_CLK_TOP_USXGMII_SBUS_1_SEL,
 	MTK_CLK_TOP_SGM_0_SEL,
 	MTK_CLK_TOP_SGM_1_SEL,
-	MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL,
-	MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL,
 	MTK_CLK_TOP_ETH_GMII_SEL,
 	MTK_CLK_TOP_ETH_REFCK_50M_SEL,
 	MTK_CLK_TOP_ETH_SYS_200M_SEL,
@@ -800,19 +796,9 @@ enum mtk_clks_map {
 				 BIT_ULL(MTK_CLK_GP3) | BIT_ULL(MTK_CLK_XGP1) | \
 				 BIT_ULL(MTK_CLK_XGP2) | BIT_ULL(MTK_CLK_XGP3) | \
 				 BIT_ULL(MTK_CLK_CRYPTO) | \
-				 BIT_ULL(MTK_CLK_SGMII_TX_250M) | \
-				 BIT_ULL(MTK_CLK_SGMII_RX_250M) | \
-				 BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \
-				 BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \
 				 BIT_ULL(MTK_CLK_ETHWARP_WOCPU2) | \
 				 BIT_ULL(MTK_CLK_ETHWARP_WOCPU1) | \
 				 BIT_ULL(MTK_CLK_ETHWARP_WOCPU0) | \
-				 BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_0_SEL) | \
-				 BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_1_SEL) | \
-				 BIT_ULL(MTK_CLK_TOP_SGM_0_SEL) | \
-				 BIT_ULL(MTK_CLK_TOP_SGM_1_SEL) | \
-				 BIT_ULL(MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL) | \
-				 BIT_ULL(MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL) | \
 				 BIT_ULL(MTK_CLK_TOP_ETH_GMII_SEL) | \
 				 BIT_ULL(MTK_CLK_TOP_ETH_REFCK_50M_SEL) | \
 				 BIT_ULL(MTK_CLK_TOP_ETH_SYS_200M_SEL) | \
-- 
cgit v1.3-3-g829e


From f9c141fc33393923451bdd190c67d9d4f5d2c67f Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 31 Jul 2024 14:36:30 +0800
Subject: RDS: IB: Remove unused declarations

Commit f4f943c958a2 ("RDS: IB: ack more receive completions to improve performance")
removed rds_ib_recv_tasklet_fn() implementation but not the declaration.
And commit ec16227e1414 ("RDS/IB: Infiniband transport") declared but never implemented
other functions.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
Link: https://patch.msgid.link/20240731063630.3592046-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rds/ib.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/rds/ib.h b/net/rds/ib.h
index 2ba71102b1f1..8ef3178ed4d6 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -369,9 +369,6 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp);
 void rds_ib_conn_free(void *arg);
 int rds_ib_conn_path_connect(struct rds_conn_path *cp);
 void rds_ib_conn_path_shutdown(struct rds_conn_path *cp);
-void rds_ib_state_change(struct sock *sk);
-int rds_ib_listen_init(void);
-void rds_ib_listen_stop(void);
 __printf(2, 3)
 void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...);
 int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
@@ -402,7 +399,6 @@ void rds_ib_inc_free(struct rds_incoming *inc);
 int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to);
 void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc,
 			     struct rds_ib_ack_state *state);
-void rds_ib_recv_tasklet_fn(unsigned long data);
 void rds_ib_recv_init_ring(struct rds_ib_connection *ic);
 void rds_ib_recv_clear_ring(struct rds_ib_connection *ic);
 void rds_ib_recv_init_ack(struct rds_ib_connection *ic);
-- 
cgit v1.3-3-g829e


From 743ff02152bc46bb4a2f2a49ec891c87eba6ab5b Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 31 Jul 2024 10:15:28 +0100
Subject: ethtool: Don't check for NULL info in prepare_data callbacks

Since commit f946270d05c2 ("ethtool: netlink: always pass genl_info to
.prepare_data") the info argument of prepare_data callbacks is never
NULL. Remove checks present in callback implementations.

Link: https://lore.kernel.org/netdev/20240703121237.3f8b9125@kernel.org/
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240731-prepare_data-null-check-v1-1-627f2320678f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/linkinfo.c  | 2 +-
 net/ethtool/linkmodes.c | 2 +-
 net/ethtool/strset.c    | 3 +--
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c
index 5c317d23787b..30b8ce275159 100644
--- a/net/ethtool/linkinfo.c
+++ b/net/ethtool/linkinfo.c
@@ -35,7 +35,7 @@ static int linkinfo_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 	ret = __ethtool_get_link_ksettings(dev, &data->ksettings);
-	if (ret < 0 && info)
+	if (ret < 0)
 		GENL_SET_ERR_MSG(info, "failed to retrieve link settings");
 	ethnl_ops_complete(dev);
 
diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c
index b2591db49f7d..259cd9ef1f2a 100644
--- a/net/ethtool/linkmodes.c
+++ b/net/ethtool/linkmodes.c
@@ -40,7 +40,7 @@ static int linkmodes_prepare_data(const struct ethnl_req_info *req_base,
 		return ret;
 
 	ret = __ethtool_get_link_ksettings(dev, &data->ksettings);
-	if (ret < 0 && info) {
+	if (ret < 0) {
 		GENL_SET_ERR_MSG(info, "failed to retrieve link settings");
 		goto out;
 	}
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index c678b484a079..56b99606f00b 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -289,8 +289,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 		for (i = 0; i < ETH_SS_COUNT; i++) {
 			if ((req_info->req_ids & (1U << i)) &&
 			    data->sets[i].per_dev) {
-				if (info)
-					GENL_SET_ERR_MSG(info, "requested per device strings without dev");
+				GENL_SET_ERR_MSG(info, "requested per device strings without dev");
 				return -EINVAL;
 			}
 		}
-- 
cgit v1.3-3-g829e


From 5fcf0801ef5c8adb785520f16b4a1faa8c4ac147 Mon Sep 17 00:00:00 2001
From: John Wang <wangzq.jn@gmail.com>
Date: Tue, 30 Jul 2024 16:46:35 +0800
Subject: net: mctp: Consistent peer address handling in ioctl tag allocation

When executing ioctl to allocate tags, if the peer address is 0,
mctp_alloc_local_tag now replaces it with 0xff. However, during tag
dropping, this replacement is not performed, potentially causing the key
not to be dropped as expected.

Signed-off-by: John Wang <wangzhiqiang02@ieisystem.com>
Reviewed-by: Jeremy Kerr <jk@codeconstruct.com.au>
Link: https://patch.msgid.link/20240730084636.184140-1-wangzhiqiang02@ieisystem.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mctp/af_mctp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c
index de52a9191da0..43288b408fde 100644
--- a/net/mctp/af_mctp.c
+++ b/net/mctp/af_mctp.c
@@ -486,6 +486,9 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2,
 	tag = ctl.tag & MCTP_TAG_MASK;
 	rc = -EINVAL;
 
+	if (ctl.peer_addr == MCTP_ADDR_NULL)
+		ctl.peer_addr = MCTP_ADDR_ANY;
+
 	spin_lock_irqsave(&net->mctp.keys_lock, flags);
 	hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) {
 		/* we do an irqsave here, even though we know the irq state,
-- 
cgit v1.3-3-g829e


From 53ed4b25a79aeec5991c2dc579e635b136ef7676 Mon Sep 17 00:00:00 2001
From: Po-Hao Huang <phhuang@realtek.com>
Date: Wed, 24 Jul 2024 13:05:01 +0800
Subject: wifi: rtw88: 8822c: Parse channel from IE to correct invalid hardware
 reports

For CCK packets we could get incorrect reports from hardware.
And this causes wrong frequencies being reported. Parse the channel
information from IE if provided by AP to fix this.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240724050501.7550-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw88/main.h     |  1 +
 drivers/net/wireless/realtek/rtw88/pci.c      |  1 +
 drivers/net/wireless/realtek/rtw88/rtw8822c.c |  7 +++--
 drivers/net/wireless/realtek/rtw88/rx.c       | 41 +++++++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw88/rx.h       | 13 +++++++++
 drivers/net/wireless/realtek/rtw88/sdio.c     |  1 +
 drivers/net/wireless/realtek/rtw88/usb.c      |  2 ++
 7 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index b60a0f840e13..12b564ad3a58 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -623,6 +623,7 @@ struct rtw_rx_pkt_stat {
 	bool crc_err;
 	bool decrypted;
 	bool is_c2h;
+	bool channel_invalid;
 
 	s32 signal_power;
 	u16 pkt_len;
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index a5b9d6c7be37..5d0580da13fb 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -1088,6 +1088,7 @@ static u32 rtw_pci_rx_napi(struct rtw_dev *rtwdev, struct rtw_pci *rtwpci,
 			/* remove rx_desc */
 			skb_pull(new, pkt_offset);
 
+			rtw_update_rx_freq_for_invalid(rtwdev, new, &rx_status, &pkt_stat);
 			rtw_rx_stats(rtwdev, pkt_stat.vif, new);
 			memcpy(new->cb, &rx_status, sizeof(rx_status));
 			ieee80211_rx_napi(rtwdev->hw, NULL, new, napi);
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index e265a35184ab..1dbe1cdbc3fd 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -2576,9 +2576,10 @@ static void query_phy_status_page0(struct rtw_dev *rtwdev, u8 *phy_status,
 	rx_power[RF_PATH_B] -= 110;
 
 	channel = GET_PHY_STAT_P0_CHANNEL(phy_status);
-	if (channel == 0)
-		channel = rtwdev->hal.current_channel;
-	rtw_set_rx_freq_band(pkt_stat, channel);
+	if (channel != 0)
+		rtw_set_rx_freq_band(pkt_stat, channel);
+	else
+		pkt_stat->channel_invalid = true;
 
 	pkt_stat->rx_power[RF_PATH_A] = rx_power[RF_PATH_A];
 	pkt_stat->rx_power[RF_PATH_B] = rx_power[RF_PATH_B];
diff --git a/drivers/net/wireless/realtek/rtw88/rx.c b/drivers/net/wireless/realtek/rtw88/rx.c
index 84aedabdf285..66f9419588cf 100644
--- a/drivers/net/wireless/realtek/rtw88/rx.c
+++ b/drivers/net/wireless/realtek/rtw88/rx.c
@@ -146,6 +146,47 @@ static void rtw_set_rx_freq_by_pktstat(struct rtw_rx_pkt_stat *pkt_stat,
 	rx_status->band = pkt_stat->band;
 }
 
+void rtw_update_rx_freq_from_ie(struct rtw_dev *rtwdev, struct sk_buff *skb,
+				struct ieee80211_rx_status *rx_status,
+				struct rtw_rx_pkt_stat *pkt_stat)
+{
+	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data;
+	int channel = rtwdev->hal.current_channel;
+	size_t hdr_len, ielen;
+	int channel_number;
+	u8 *variable;
+
+	if (!test_bit(RTW_FLAG_SCANNING, rtwdev->flags))
+		goto fill_rx_status;
+
+	if (ieee80211_is_beacon(mgmt->frame_control)) {
+		variable = mgmt->u.beacon.variable;
+		hdr_len = offsetof(struct ieee80211_mgmt,
+				   u.beacon.variable);
+	} else if (ieee80211_is_probe_resp(mgmt->frame_control)) {
+		variable = mgmt->u.probe_resp.variable;
+		hdr_len = offsetof(struct ieee80211_mgmt,
+				   u.probe_resp.variable);
+	} else {
+		goto fill_rx_status;
+	}
+
+	if (skb->len > hdr_len)
+		ielen = skb->len - hdr_len;
+	else
+		goto fill_rx_status;
+
+	channel_number = cfg80211_get_ies_channel_number(variable, ielen,
+							 NL80211_BAND_2GHZ);
+	if (channel_number != -1)
+		channel = channel_number;
+
+fill_rx_status:
+	rtw_set_rx_freq_band(pkt_stat, channel);
+	rtw_set_rx_freq_by_pktstat(pkt_stat, rx_status);
+}
+EXPORT_SYMBOL(rtw_update_rx_freq_from_ie);
+
 void rtw_rx_fill_rx_status(struct rtw_dev *rtwdev,
 			   struct rtw_rx_pkt_stat *pkt_stat,
 			   struct ieee80211_hdr *hdr,
diff --git a/drivers/net/wireless/realtek/rtw88/rx.h b/drivers/net/wireless/realtek/rtw88/rx.h
index 8a072dd3d73c..9f0019112987 100644
--- a/drivers/net/wireless/realtek/rtw88/rx.h
+++ b/drivers/net/wireless/realtek/rtw88/rx.h
@@ -50,5 +50,18 @@ void rtw_rx_fill_rx_status(struct rtw_dev *rtwdev,
 			   struct ieee80211_hdr *hdr,
 			   struct ieee80211_rx_status *rx_status,
 			   u8 *phy_status);
+void rtw_update_rx_freq_from_ie(struct rtw_dev *rtwdev, struct sk_buff *skb,
+				struct ieee80211_rx_status *rx_status,
+				struct rtw_rx_pkt_stat *pkt_stat);
+
+static inline
+void rtw_update_rx_freq_for_invalid(struct rtw_dev *rtwdev, struct sk_buff *skb,
+				    struct ieee80211_rx_status *rx_status,
+				    struct rtw_rx_pkt_stat *pkt_stat)
+{
+	if (pkt_stat->channel_invalid)
+		rtw_update_rx_freq_from_ie(rtwdev, skb, rx_status, pkt_stat);
+}
+
 
 #endif
diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c
index 0cae5746f540..763aa8212a4b 100644
--- a/drivers/net/wireless/realtek/rtw88/sdio.c
+++ b/drivers/net/wireless/realtek/rtw88/sdio.c
@@ -948,6 +948,7 @@ static void rtw_sdio_rx_skb(struct rtw_dev *rtwdev, struct sk_buff *skb,
 	skb_put(skb, pkt_stat->pkt_len);
 	skb_reserve(skb, pkt_offset);
 
+	rtw_update_rx_freq_for_invalid(rtwdev, skb, rx_status, pkt_stat);
 	rtw_rx_stats(rtwdev, pkt_stat->vif, skb);
 
 	ieee80211_rx_irqsafe(rtwdev->hw, skb);
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 251a5726f3ee..9145c11a063e 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -579,6 +579,8 @@ static void rtw_usb_rx_handler(struct work_struct *work)
 
 		skb_put(skb, pkt_stat.pkt_len);
 		skb_reserve(skb, pkt_offset);
+
+		rtw_update_rx_freq_for_invalid(rtwdev, skb, &rx_status, &pkt_stat);
 		memcpy(skb->cb, &rx_status, sizeof(rx_status));
 		ieee80211_rx_irqsafe(rtwdev->hw, skb);
 	}
-- 
cgit v1.3-3-g829e


From 46e6acfe3501fa938af9c5bd730f0020235b08a2 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 31 Jul 2024 14:17:03 -0600
Subject: net: phy: qca807x: Drop unnecessary and broken DT validation

The check for "leds" and "gpio-controller" both being present is never
true because "leds" is a node, not a property. This could be fixed
with a check for child node, but there's really no need for the kernel
to validate a DT. Just continue ignoring the LEDs if GPIOs are present.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240731201703.1842022-2-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca807x.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index 672c6929119a..ba558486c72f 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -733,16 +733,6 @@ static int qca807x_probe(struct phy_device *phydev)
 								     "qcom,dac-disable-bias-current-tweak");
 
 #if IS_ENABLED(CONFIG_GPIOLIB)
-	/* Make sure we don't have mixed leds node and gpio-controller
-	 * to prevent registering leds and having gpio-controller usage
-	 * conflicting with them.
-	 */
-	if (of_find_property(node, "leds", NULL) &&
-	    of_find_property(node, "gpio-controller", NULL)) {
-		phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive.");
-		return -EINVAL;
-	}
-
 	/* Do not register a GPIO controller unless flagged for it */
 	if (of_property_read_bool(node, "gpio-controller")) {
 		ret = qca807x_gpio(phydev);
-- 
cgit v1.3-3-g829e


From 0b0e9cdb3d1f8fda823b592b0667b4b0595e2ba7 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 31 Jul 2024 14:15:15 -0600
Subject: net: mdio: Use of_property_count_u32_elems() to get property length

Replace of_get_property() with the type specific
of_property_count_u32_elems() to get the property length.

This is part of a larger effort to remove callers of of_get_property()
and similar functions. of_get_property() leaks the DT property data
pointer which is a problem for dynamically allocated nodes which may
be freed.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240731201514.1839974-2-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/of_mdio.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c
index 08e607f62e10..2f4fc664d2e1 100644
--- a/drivers/net/mdio/of_mdio.c
+++ b/drivers/net/mdio/of_mdio.c
@@ -390,7 +390,7 @@ EXPORT_SYMBOL(of_phy_get_and_connect);
 bool of_phy_is_fixed_link(struct device_node *np)
 {
 	struct device_node *dn;
-	int len, err;
+	int err;
 	const char *managed;
 
 	/* New binding */
@@ -405,8 +405,7 @@ bool of_phy_is_fixed_link(struct device_node *np)
 		return true;
 
 	/* Old binding */
-	if (of_get_property(np, "fixed-link", &len) &&
-	    len == (5 * sizeof(__be32)))
+	if (of_property_count_u32_elems(np, "fixed-link") == 5)
 		return true;
 
 	return false;
-- 
cgit v1.3-3-g829e


From 5fe164fb0e6e31dbcbb4b706fd76bc578e5af4c6 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 31 Jul 2024 13:16:00 -0600
Subject: net: Use of_property_read_bool()

Use of_property_read_bool() to read boolean properties rather than
of_find_property(). This is part of a larger effort to remove callers
of of_find_property() and similar functions. of_find_property() leaks
the DT struct property and data pointers which is a problem for
dynamically allocated nodes which may be freed.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20240731191601.1714639-2-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fman/fman_port.c   | 6 +++---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c      | 8 ++++----
 drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c  | 8 ++++----
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 +-
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index 406e75e9e5ea..f17a4e511510 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1748,7 +1748,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	struct resource res;
 	struct resource *dev_res;
 	u32 val;
-	int err = 0, lenp;
+	int err = 0;
 	enum fman_port_type port_type;
 	u16 port_speed;
 	u8 port_id;
@@ -1795,7 +1795,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	if (of_device_is_compatible(port_node, "fsl,fman-v3-port-tx")) {
 		port_type = FMAN_PORT_TYPE_TX;
 		port_speed = 1000;
-		if (of_find_property(port_node, "fsl,fman-10g-port", &lenp))
+		if (of_property_read_bool(port_node, "fsl,fman-10g-port"))
 			port_speed = 10000;
 
 	} else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-tx")) {
@@ -1808,7 +1808,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	} else if (of_device_is_compatible(port_node, "fsl,fman-v3-port-rx")) {
 		port_type = FMAN_PORT_TYPE_RX;
 		port_speed = 1000;
-		if (of_find_property(port_node, "fsl,fman-10g-port", &lenp))
+		if (of_property_read_bool(port_node, "fsl,fman-10g-port"))
 			port_speed = 10000;
 
 	} else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-rx")) {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 3e51b3a9b0a5..9dc9de39bb8f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1271,8 +1271,8 @@ static int prueth_probe(struct platform_device *pdev)
 			goto exit_iep;
 		}
 
-		if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL))
-			prueth->emac[PRUETH_MAC0]->half_duplex = 1;
+		prueth->emac[PRUETH_MAC0]->half_duplex =
+			of_property_read_bool(eth0_node, "ti,half-duplex-capable");
 
 		prueth->emac[PRUETH_MAC0]->iep = prueth->iep0;
 	}
@@ -1285,8 +1285,8 @@ static int prueth_probe(struct platform_device *pdev)
 			goto netdev_exit;
 		}
 
-		if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL))
-			prueth->emac[PRUETH_MAC1]->half_duplex = 1;
+		prueth->emac[PRUETH_MAC1]->half_duplex =
+			of_property_read_bool(eth1_node, "ti,half-duplex-capable");
 
 		prueth->emac[PRUETH_MAC1]->iep = prueth->iep0;
 	}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
index e180c1166170..54b7e27608ce 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -1045,8 +1045,8 @@ static int prueth_probe(struct platform_device *pdev)
 			goto exit_iep;
 		}
 
-		if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL))
-			prueth->emac[PRUETH_MAC0]->half_duplex = 1;
+		prueth->emac[PRUETH_MAC0]->half_duplex =
+			of_property_read_bool(eth0_node, "ti,half-duplex-capable");
 
 		prueth->emac[PRUETH_MAC0]->iep = prueth->iep0;
 	}
@@ -1059,8 +1059,8 @@ static int prueth_probe(struct platform_device *pdev)
 			goto netdev_exit;
 		}
 
-		if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL))
-			prueth->emac[PRUETH_MAC1]->half_duplex = 1;
+		prueth->emac[PRUETH_MAC1]->half_duplex =
+			of_property_read_bool(eth1_node, "ti,half-duplex-capable");
 
 		prueth->emac[PRUETH_MAC1]->iep = prueth->iep1;
 	}
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 02fdf66e07fa..f051f0387214 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2396,7 +2396,7 @@ static int axienet_probe(struct platform_device *pdev)
 		goto cleanup_clk;
 	}
 
-	if (!of_find_property(pdev->dev.of_node, "dmas", NULL)) {
+	if (!of_property_present(pdev->dev.of_node, "dmas")) {
 		/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
 		np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0);
 
-- 
cgit v1.3-3-g829e


From bd4a3b10fa0eaa80519fc0f8bffeb8740fa2f61e Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Wed, 24 Jul 2024 13:26:23 +0800
Subject: wifi: rtw89: add EVM statistics for 1SS rate

To more accurately debug performance issues, EVM statistics will
differentiate between different space streams, and only beacon
and data frames will be included.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240724052626.12774-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c  | 49 ++++++++++++++++++++++++------
 drivers/net/wireless/realtek/rtw89/core.h  |  3 ++
 drivers/net/wireless/realtek/rtw89/debug.c |  5 +--
 drivers/net/wireless/realtek/rtw89/txrx.h  |  8 ++++-
 4 files changed, 52 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 7019f7d482a8..86b6febedc25 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1449,16 +1449,20 @@ static int rtw89_core_rx_process_mac_ppdu(struct rtw89_dev *rtwdev,
 		return -EINVAL;
 	}
 
-	/* For WiFi 7 chips, RXWD.mac_id of PPDU status is not set by hardware,
-	 * so update mac_id by rxinfo_user[].mac_id.
-	 */
-	for (i = 0; i < usr_num && chip_gen == RTW89_CHIP_BE; i++) {
+	for (i = 0; i < usr_num; i++) {
 		user = &rxinfo->user[i];
 		if (!le32_get_bits(user->w0, RTW89_RXINFO_USER_MAC_ID_VALID))
 			continue;
-
-		phy_ppdu->mac_id =
-			le32_get_bits(user->w0, RTW89_RXINFO_USER_MACID);
+		/* For WiFi 7 chips, RXWD.mac_id of PPDU status is not set
+		 * by hardware, so update mac_id by rxinfo_user[].mac_id.
+		 */
+		if (chip_gen == RTW89_CHIP_BE)
+			phy_ppdu->mac_id =
+				le32_get_bits(user->w0, RTW89_RXINFO_USER_MACID);
+		phy_ppdu->has_data =
+			le32_get_bits(user->w0, RTW89_RXINFO_USER_DATA);
+		phy_ppdu->has_bcn =
+			le32_get_bits(user->w0, RTW89_RXINFO_USER_BCN);
 		break;
 	}
 
@@ -1480,6 +1484,26 @@ static int rtw89_core_rx_process_mac_ppdu(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static u8 rtw89_get_data_rate_nss(struct rtw89_dev *rtwdev, u16 data_rate)
+{
+	u8 data_rate_mode;
+
+	data_rate_mode = rtw89_get_data_rate_mode(rtwdev, data_rate);
+	switch (data_rate_mode) {
+	case DATA_RATE_MODE_NON_HT:
+		return 1;
+	case DATA_RATE_MODE_HT:
+		return rtw89_get_data_ht_nss(rtwdev, data_rate) + 1;
+	case DATA_RATE_MODE_VHT:
+	case DATA_RATE_MODE_HE:
+	case DATA_RATE_MODE_EHT:
+		return rtw89_get_data_nss(rtwdev, data_rate) + 1;
+	default:
+		rtw89_warn(rtwdev, "invalid RX rate mode %d\n", data_rate_mode);
+		return 0;
+	}
+}
+
 static void rtw89_core_rx_process_phy_ppdu_iter(void *data,
 						struct ieee80211_sta *sta)
 {
@@ -1509,10 +1533,14 @@ static void rtw89_core_rx_process_phy_ppdu_iter(void *data,
 			ewma_rssi_add(&rtwsta->rssi[i], phy_ppdu->rssi[i]);
 	}
 
-	if (phy_ppdu->ofdm.has) {
+	if (phy_ppdu->ofdm.has && (phy_ppdu->has_data || phy_ppdu->has_bcn)) {
 		ewma_snr_add(&rtwsta->avg_snr, phy_ppdu->ofdm.avg_snr);
-		ewma_evm_add(&rtwsta->evm_min[evm_pos], phy_ppdu->ofdm.evm_min);
-		ewma_evm_add(&rtwsta->evm_max[evm_pos], phy_ppdu->ofdm.evm_max);
+		if (rtw89_get_data_rate_nss(rtwdev, phy_ppdu->rate) == 1) {
+			ewma_evm_add(&rtwsta->evm_1ss, phy_ppdu->ofdm.evm_min);
+		} else {
+			ewma_evm_add(&rtwsta->evm_min[evm_pos], phy_ppdu->ofdm.evm_min);
+			ewma_evm_add(&rtwsta->evm_max[evm_pos], phy_ppdu->ofdm.evm_max);
+		}
 	}
 }
 
@@ -3367,6 +3395,7 @@ int rtw89_core_sta_add(struct rtw89_dev *rtwdev,
 
 	ewma_rssi_init(&rtwsta->avg_rssi);
 	ewma_snr_init(&rtwsta->avg_snr);
+	ewma_evm_init(&rtwsta->evm_1ss);
 	for (i = 0; i < ant_num; i++) {
 		ewma_rssi_init(&rtwsta->rssi[i]);
 		ewma_evm_init(&rtwsta->evm_min[i]);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 11fa003a9788..0a09360515dc 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -802,6 +802,8 @@ struct rtw89_rx_phy_ppdu {
 		u8 evm_max;
 		u8 evm_min;
 	} ofdm;
+	bool has_data;
+	bool has_bcn;
 	bool ldpc;
 	bool stbc;
 	bool to_self;
@@ -3306,6 +3308,7 @@ struct rtw89_sta {
 	struct ewma_rssi avg_rssi;
 	struct ewma_rssi rssi[RF_PATH_MAX];
 	struct ewma_snr avg_snr;
+	struct ewma_evm evm_1ss;
 	struct ewma_evm evm_min[RF_PATH_MAX];
 	struct ewma_evm evm_max[RF_PATH_MAX];
 	struct rtw89_ampdu_params ampdu_params[IEEE80211_NUM_TIDS];
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 9e1353cce9cc..6fc30f137eaa 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -3505,7 +3505,7 @@ static void rtw89_sta_info_get_iter(void *data, struct ieee80211_sta *sta)
 	struct rtw89_hal *hal = &rtwdev->hal;
 	u8 ant_num = hal->ant_diversity ? 2 : rtwdev->chip->rf_path_num;
 	bool ant_asterisk = hal->tx_path_diversity || hal->ant_diversity;
-	u8 evm_min, evm_max;
+	u8 evm_min, evm_max, evm_1ss;
 	u8 rssi;
 	u8 snr;
 	int i;
@@ -3574,7 +3574,8 @@ static void rtw89_sta_info_get_iter(void *data, struct ieee80211_sta *sta)
 	}
 	seq_puts(m, "]\n");
 
-	seq_puts(m, "EVM: [");
+	evm_1ss = ewma_evm_read(&rtwsta->evm_1ss);
+	seq_printf(m, "EVM: [%2u.%02u, ", evm_1ss >> 2, (evm_1ss & 0x3) * 25);
 	for (i = 0; i < (hal->ant_diversity ? 2 : 1); i++) {
 		evm_min = ewma_evm_read(&rtwsta->evm_min[i]);
 		evm_max = ewma_evm_read(&rtwsta->evm_max[i]);
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index 3882938c0893..a33280ec2a25 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -14,6 +14,7 @@
 #define DATA_RATE_HT_IDX_MASK		GENMASK(4, 0)
 #define DATA_RATE_HT_IDX_MASK_V1	GENMASK(4, 0)
 #define DATA_RATE_MODE_HT		0x1
+#define DATA_RATE_HT_NSS_MASK		GENMASK(4, 3)
 #define DATA_RATE_VHT_HE_NSS_MASK	GENMASK(6, 4)
 #define DATA_RATE_VHT_HE_IDX_MASK	GENMASK(3, 0)
 #define DATA_RATE_NSS_MASK_V1		GENMASK(7, 5)
@@ -51,6 +52,11 @@ static inline u8 rtw89_get_data_mcs(struct rtw89_dev *rtwdev, u16 hw_rate)
 	return u16_get_bits(hw_rate, DATA_RATE_VHT_HE_IDX_MASK);
 }
 
+static inline u8 rtw89_get_data_ht_nss(struct rtw89_dev *rtwdev, u16 hw_rate)
+{
+	return u16_get_bits(hw_rate, DATA_RATE_HT_NSS_MASK);
+}
+
 static inline u8 rtw89_get_data_nss(struct rtw89_dev *rtwdev, u16 hw_rate)
 {
 	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
@@ -408,7 +414,7 @@ struct rtw89_rxinfo_user {
 #define RTW89_RXINFO_USER_DATA BIT(1)
 #define RTW89_RXINFO_USER_CTRL BIT(2)
 #define RTW89_RXINFO_USER_MGMT BIT(3)
-#define RTW89_RXINFO_USER_BCM BIT(4)
+#define RTW89_RXINFO_USER_BCN BIT(4)
 #define RTW89_RXINFO_USER_MACID GENMASK(15, 8)
 
 struct rtw89_rxinfo {
-- 
cgit v1.3-3-g829e


From 0b38e6277aed8a59ccb64fcc1172d962c1f11b4c Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Wed, 24 Jul 2024 13:26:24 +0800
Subject: wifi: rtw89: add support for hardware rfkill

Add support for ieee80211::rfkill_poll ops. This enables periodic
monitoring of the hardware rfkill state, triggering updates when the
status changes.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240724052626.12774-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c      | 68 ++++++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/core.h      |  9 ++++
 drivers/net/wireless/realtek/rtw89/mac80211.c  | 17 +++++++
 drivers/net/wireless/realtek/rtw89/reg.h       | 24 +++++++++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  | 11 +++++
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  | 11 +++++
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  | 11 +++++
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 11 +++++
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  | 11 +++++
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  | 11 +++++
 10 files changed, 184 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 86b6febedc25..45952994ffa6 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -3217,6 +3217,7 @@ static void rtw89_track_work(struct work_struct *work)
 	rtw89_phy_edcca_track(rtwdev);
 	rtw89_tas_track(rtwdev);
 	rtw89_chanctx_track(rtwdev);
+	rtw89_core_rfkill_poll(rtwdev, false);
 
 	if (rtwdev->lps_enabled && !rtwdev->btc.lps)
 		rtw89_enter_lps_track(rtwdev);
@@ -4499,6 +4500,70 @@ static int rtw89_chip_board_info_setup(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
+static bool rtw89_chip_has_rfkill(struct rtw89_dev *rtwdev)
+{
+	return !!rtwdev->chip->rfkill_init;
+}
+
+static void rtw89_core_rfkill_init(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_rfkill_regs *regs = rtwdev->chip->rfkill_init;
+
+	rtw89_write16_mask(rtwdev, regs->pinmux.addr,
+			   regs->pinmux.mask, regs->pinmux.data);
+	rtw89_write16_mask(rtwdev, regs->mode.addr,
+			   regs->mode.mask, regs->mode.data);
+}
+
+static bool rtw89_core_rfkill_get(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_reg_def *reg = &rtwdev->chip->rfkill_get;
+
+	return !rtw89_read8_mask(rtwdev, reg->addr, reg->mask);
+}
+
+static void rtw89_rfkill_polling_init(struct rtw89_dev *rtwdev)
+{
+	if (!rtw89_chip_has_rfkill(rtwdev))
+		return;
+
+	rtw89_core_rfkill_init(rtwdev);
+	rtw89_core_rfkill_poll(rtwdev, true);
+	wiphy_rfkill_start_polling(rtwdev->hw->wiphy);
+}
+
+static void rtw89_rfkill_polling_deinit(struct rtw89_dev *rtwdev)
+{
+	if (!rtw89_chip_has_rfkill(rtwdev))
+		return;
+
+	wiphy_rfkill_stop_polling(rtwdev->hw->wiphy);
+}
+
+void rtw89_core_rfkill_poll(struct rtw89_dev *rtwdev, bool force)
+{
+	bool prev, blocked;
+
+	if (!rtw89_chip_has_rfkill(rtwdev))
+		return;
+
+	prev = test_bit(RTW89_FLAG_HW_RFKILL_STATE, rtwdev->flags);
+	blocked = rtw89_core_rfkill_get(rtwdev);
+
+	if (!force && prev == blocked)
+		return;
+
+	rtw89_info(rtwdev, "rfkill hardware state changed to %s\n",
+		   blocked ? "disable" : "enable");
+
+	if (blocked)
+		set_bit(RTW89_FLAG_HW_RFKILL_STATE, rtwdev->flags);
+	else
+		clear_bit(RTW89_FLAG_HW_RFKILL_STATE, rtwdev->flags);
+
+	wiphy_rfkill_set_hw_state(rtwdev->hw->wiphy, blocked);
+}
+
 int rtw89_chip_info_setup(struct rtw89_dev *rtwdev)
 {
 	int ret;
@@ -4654,6 +4719,8 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 		goto err_unregister_hw;
 	}
 
+	rtw89_rfkill_polling_init(rtwdev);
+
 	return 0;
 
 err_unregister_hw:
@@ -4668,6 +4735,7 @@ static void rtw89_core_unregister_hw(struct rtw89_dev *rtwdev)
 {
 	struct ieee80211_hw *hw = rtwdev->hw;
 
+	rtw89_rfkill_polling_deinit(rtwdev);
 	ieee80211_unregister_hw(hw);
 	rtw89_core_clr_supported_band(rtwdev);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 0a09360515dc..a0d0bf53d961 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4069,6 +4069,11 @@ struct rtw89_rrsr_cfgs {
 	struct rtw89_reg3_def rsc;
 };
 
+struct rtw89_rfkill_regs {
+	struct rtw89_reg3_def pinmux;
+	struct rtw89_reg3_def mode;
+};
+
 struct rtw89_dig_regs {
 	u32 seg0_pd_reg;
 	u32 pd_lower_bound_mask;
@@ -4260,6 +4265,8 @@ struct rtw89_chip_info {
 	const struct rtw89_rrsr_cfgs *rrsr_cfgs;
 	struct rtw89_reg_def bss_clr_vld;
 	u32 bss_clr_map_reg;
+	const struct rtw89_rfkill_regs *rfkill_init;
+	struct rtw89_reg_def rfkill_get;
 	u32 dma_ch_mask;
 	const struct rtw89_edcca_regs *edcca_regs;
 	const struct wiphy_wowlan_support *wowlan_stub;
@@ -4618,6 +4625,7 @@ enum rtw89_flags {
 	RTW89_FLAG_WOWLAN,
 	RTW89_FLAG_FORBIDDEN_TRACK_WROK,
 	RTW89_FLAG_CHANGING_INTERFACE,
+	RTW89_FLAG_HW_RFKILL_STATE,
 
 	NUM_OF_RTW89_FLAGS,
 };
@@ -6506,6 +6514,7 @@ int rtw89_core_sta_remove(struct rtw89_dev *rtwdev,
 void rtw89_core_set_tid_config(struct rtw89_dev *rtwdev,
 			       struct ieee80211_sta *sta,
 			       struct cfg80211_tid_config *tid_config);
+void rtw89_core_rfkill_poll(struct rtw89_dev *rtwdev, bool force);
 void rtw89_check_quirks(struct rtw89_dev *rtwdev, const struct dmi_system_id *quirks);
 int rtw89_core_init(struct rtw89_dev *rtwdev);
 void rtw89_core_deinit(struct rtw89_dev *rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 1508693032cb..b95fa288c5f5 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -1147,6 +1147,22 @@ static void rtw89_set_rekey_data(struct ieee80211_hw *hw,
 }
 #endif
 
+static void rtw89_ops_rfkill_poll(struct ieee80211_hw *hw)
+{
+	struct rtw89_dev *rtwdev = hw->priv;
+
+	mutex_lock(&rtwdev->mutex);
+
+	/* wl_disable GPIO get floating when entering LPS */
+	if (test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
+		goto out;
+
+	rtw89_core_rfkill_poll(rtwdev, false);
+
+out:
+	mutex_unlock(&rtwdev->mutex);
+}
+
 const struct ieee80211_ops rtw89_ops = {
 	.tx			= rtw89_ops_tx,
 	.wake_tx_queue		= rtw89_ops_wake_tx_queue,
@@ -1193,5 +1209,6 @@ const struct ieee80211_ops rtw89_ops = {
 	.set_wakeup		= rtw89_ops_set_wakeup,
 	.set_rekey_data		= rtw89_set_rekey_data,
 #endif
+	.rfkill_poll		= rtw89_ops_rfkill_poll,
 };
 EXPORT_SYMBOL(rtw89_ops);
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 15b17e2cf99b..7afec48c4056 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -107,6 +107,15 @@
 #define B_AX_DBG_SEL0_16BIT BIT(11)
 #define B_AX_DBG_SEL0 GENMASK(7, 0)
 
+#define R_AX_GPIO_EXT_CTRL 0x0060
+#define B_AX_GPIO_MOD_15_TO_8_MASK GENMASK(31, 24)
+#define B_AX_GPIO_MOD_9 BIT(25)
+#define B_AX_GPIO_IO_SEL_15_TO_8_MASK GENMASK(23, 16)
+#define B_AX_GPIO_IO_SEL_9 BIT(17)
+#define B_AX_GPIO_OUT_15_TO_8_MASK GENMASK(15, 8)
+#define B_AX_GPIO_IN_15_TO_8_MASK GENMASK(7, 0)
+#define B_AX_GPIO_IN_9 BIT(1)
+
 #define R_AX_SYS_SDIO_CTRL 0x0070
 #define B_AX_PCIE_DIS_L2_CTRL_LDO_HCI BIT(15)
 #define B_AX_PCIE_DIS_WLSUS_AFT_PDN BIT(14)
@@ -267,6 +276,9 @@
 
 #define R_AX_GPIO0_7_FUNC_SEL 0x02D0
 
+#define R_AX_GPIO8_15_FUNC_SEL 0x02D4
+#define B_AX_PINMUX_GPIO9_FUNC_SEL_MASK GENMASK(7, 4)
+
 #define R_AX_EECS_EESK_FUNC_SEL 0x02D8
 #define B_AX_PINMUX_EESK_FUNC_SEL_MASK GENMASK(7, 4)
 
@@ -3910,6 +3922,15 @@
 #define R_BE_EFUSE_CTRL_1_V1 0x0034
 #define B_BE_EF_DATA_MASK GENMASK(31, 0)
 
+#define R_BE_GPIO_EXT_CTRL 0x0060
+#define B_BE_GPIO_MOD_15_TO_8_MASK GENMASK(31, 24)
+#define B_BE_GPIO_MOD_9 BIT(25)
+#define B_BE_GPIO_IO_SEL_15_TO_8_MASK GENMASK(23, 16)
+#define B_BE_GPIO_IO_SEL_9 BIT(17)
+#define B_BE_GPIO_OUT_15_TO_8_MASK GENMASK(15, 8)
+#define B_BE_GPIO_IN_15_TO_8_MASK GENMASK(7, 0)
+#define B_BE_GPIO_IN_9 BIT(1)
+
 #define R_BE_WL_BT_PWR_CTRL 0x0068
 #define B_BE_ISO_BD2PP BIT(31)
 #define B_BE_LDOV12B_EN BIT(30)
@@ -4355,6 +4376,9 @@
 #define B_BE_REG_CK40M_EN BIT(1)
 #define B_BE_REG_CK640M_EN BIT(0)
 
+#define R_BE_GPIO8_15_FUNC_SEL 0x02D4
+#define B_BE_PINMUX_GPIO9_FUNC_SEL_MASK GENMASK(7, 4)
+
 #define R_BE_WLAN_XTAL_SI_CTRL 0x0270
 #define B_BE_WL_XTAL_SI_CMD_POLL BIT(31)
 #define B_BE_WL_XTAL_SI_CHIPID_MASK GENMASK(30, 28)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 40cf84a79c46..b8f57a602dcf 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -185,6 +185,15 @@ static const struct rtw89_rrsr_cfgs rtw8851b_rrsr_cfgs = {
 	.rsc = {R_AX_TRXPTCL_RRSR_CTL_0, B_AX_WMAC_RESP_RSC_MASK, 2},
 };
 
+static const struct rtw89_rfkill_regs rtw8851b_rfkill_regs = {
+	.pinmux = {R_AX_GPIO8_15_FUNC_SEL,
+		   B_AX_PINMUX_GPIO9_FUNC_SEL_MASK,
+		   0xf},
+	.mode = {R_AX_GPIO_EXT_CTRL + 2,
+		 (B_AX_GPIO_MOD_9 | B_AX_GPIO_IO_SEL_9) >> 16,
+		 0x0},
+};
+
 static const struct rtw89_dig_regs rtw8851b_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD_V1,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
@@ -2524,6 +2533,8 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.rrsr_cfgs		= &rtw8851b_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP_V1, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP_V1,
+	.rfkill_init		= &rtw8851b_rfkill_regs,
+	.rfkill_get		= {R_AX_GPIO_EXT_CTRL, B_AX_GPIO_IN_9},
 	.dma_ch_mask		= BIT(RTW89_DMA_ACH4) | BIT(RTW89_DMA_ACH5) |
 				  BIT(RTW89_DMA_ACH6) | BIT(RTW89_DMA_ACH7) |
 				  BIT(RTW89_DMA_B1MG) | BIT(RTW89_DMA_B1HI),
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 08e148328c62..88f8f2f4c6e2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -478,6 +478,15 @@ static const struct rtw89_rrsr_cfgs rtw8852a_rrsr_cfgs = {
 	.rsc = {R_AX_TRXPTCL_RRSR_CTL_0, B_AX_WMAC_RESP_RSC_MASK, 2},
 };
 
+static const struct rtw89_rfkill_regs rtw8852a_rfkill_regs = {
+	.pinmux = {R_AX_GPIO8_15_FUNC_SEL,
+		   B_AX_PINMUX_GPIO9_FUNC_SEL_MASK,
+		   0xf},
+	.mode = {R_AX_GPIO_EXT_CTRL + 2,
+		 (B_AX_GPIO_MOD_9 | B_AX_GPIO_IO_SEL_9) >> 16,
+		 0x0},
+};
+
 static const struct rtw89_dig_regs rtw8852a_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
@@ -2240,6 +2249,8 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.rrsr_cfgs		= &rtw8852a_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP,
+	.rfkill_init		= &rtw8852a_rfkill_regs,
+	.rfkill_get		= {R_AX_GPIO_EXT_CTRL, B_AX_GPIO_IN_9},
 	.dma_ch_mask		= 0,
 	.edcca_regs		= &rtw8852a_edcca_regs,
 #ifdef CONFIG_PM
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index a22847a311ad..ef888545d988 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -150,6 +150,15 @@ static const struct rtw89_rrsr_cfgs rtw8852b_rrsr_cfgs = {
 	.rsc = {R_AX_TRXPTCL_RRSR_CTL_0, B_AX_WMAC_RESP_RSC_MASK, 2},
 };
 
+static const struct rtw89_rfkill_regs rtw8852b_rfkill_regs = {
+	.pinmux = {R_AX_GPIO8_15_FUNC_SEL,
+		   B_AX_PINMUX_GPIO9_FUNC_SEL_MASK,
+		   0xf},
+	.mode = {R_AX_GPIO_EXT_CTRL + 2,
+		 (B_AX_GPIO_MOD_9 | B_AX_GPIO_IO_SEL_9) >> 16,
+		 0x0},
+};
+
 static const struct rtw89_dig_regs rtw8852b_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD_V1,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
@@ -880,6 +889,8 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.rrsr_cfgs		= &rtw8852b_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP_V1, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP_V1,
+	.rfkill_init		= &rtw8852b_rfkill_regs,
+	.rfkill_get		= {R_AX_GPIO_EXT_CTRL, B_AX_GPIO_IN_9},
 	.dma_ch_mask		= BIT(RTW89_DMA_ACH4) | BIT(RTW89_DMA_ACH5) |
 				  BIT(RTW89_DMA_ACH6) | BIT(RTW89_DMA_ACH7) |
 				  BIT(RTW89_DMA_B1MG) | BIT(RTW89_DMA_B1HI),
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index dd9fbddc411a..8173063bcc8e 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -148,6 +148,15 @@ static const struct rtw89_rrsr_cfgs rtw8852bt_rrsr_cfgs = {
 	.rsc = {R_AX_TRXPTCL_RRSR_CTL_0, B_AX_WMAC_RESP_RSC_MASK, 2},
 };
 
+static const struct rtw89_rfkill_regs rtw8852bt_rfkill_regs = {
+	.pinmux = {R_AX_GPIO8_15_FUNC_SEL,
+		   B_AX_PINMUX_GPIO9_FUNC_SEL_MASK,
+		   0xf},
+	.mode = {R_AX_GPIO_EXT_CTRL + 2,
+		 (B_AX_GPIO_MOD_9 | B_AX_GPIO_IO_SEL_9) >> 16,
+		 0x0},
+};
+
 static const struct rtw89_dig_regs rtw8852bt_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD_V1,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
@@ -813,6 +822,8 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.rrsr_cfgs		= &rtw8852bt_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP_V1, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP_V1,
+	.rfkill_init		= &rtw8852bt_rfkill_regs,
+	.rfkill_get		= {R_AX_GPIO_EXT_CTRL, B_AX_GPIO_IN_9},
 	.dma_ch_mask		= BIT(RTW89_DMA_ACH4) | BIT(RTW89_DMA_ACH5) |
 				  BIT(RTW89_DMA_ACH6) | BIT(RTW89_DMA_ACH7) |
 				  BIT(RTW89_DMA_B1MG) | BIT(RTW89_DMA_B1HI),
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 193168dc7b6c..8e500d0eb70b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -147,6 +147,15 @@ static const struct rtw89_rrsr_cfgs rtw8852c_rrsr_cfgs = {
 	.rsc = {R_AX_PTCL_RRSR1, B_AX_RSC_MASK, 2},
 };
 
+static const struct rtw89_rfkill_regs rtw8852c_rfkill_regs = {
+	.pinmux = {R_AX_GPIO8_15_FUNC_SEL,
+		   B_AX_PINMUX_GPIO9_FUNC_SEL_MASK,
+		   0xf},
+	.mode = {R_AX_GPIO_EXT_CTRL + 2,
+		 (B_AX_GPIO_MOD_9 | B_AX_GPIO_IO_SEL_9) >> 16,
+		 0x0},
+};
+
 static const struct rtw89_dig_regs rtw8852c_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
@@ -3022,6 +3031,8 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.rrsr_cfgs		= &rtw8852c_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_MAP, B_BSS_CLR_MAP_VLD0},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP,
+	.rfkill_init		= &rtw8852c_rfkill_regs,
+	.rfkill_get		= {R_AX_GPIO_EXT_CTRL, B_AX_GPIO_IN_9},
 	.dma_ch_mask		= 0,
 	.edcca_regs		= &rtw8852c_edcca_regs,
 #ifdef CONFIG_PM
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 2af568a3264d..c763b14d43e9 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -165,6 +165,15 @@ static const struct rtw89_rrsr_cfgs rtw8922a_rrsr_cfgs = {
 	.rsc = {R_BE_PTCL_RRSR1, B_BE_RSC_MASK, 2},
 };
 
+static const struct rtw89_rfkill_regs rtw8922a_rfkill_regs = {
+	.pinmux = {R_BE_GPIO8_15_FUNC_SEL,
+		   B_BE_PINMUX_GPIO9_FUNC_SEL_MASK,
+		   0xf},
+	.mode = {R_BE_GPIO_EXT_CTRL + 2,
+		 (B_BE_GPIO_MOD_9 | B_BE_GPIO_IO_SEL_9) >> 16,
+		 0x0},
+};
+
 static const struct rtw89_dig_regs rtw8922a_dig_regs = {
 	.seg0_pd_reg = R_SEG0R_PD_V2,
 	.pd_lower_bound_mask = B_SEG0R_PD_LOWER_BOUND_MSK,
@@ -2624,6 +2633,8 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.rrsr_cfgs		= &rtw8922a_rrsr_cfgs,
 	.bss_clr_vld		= {R_BSS_CLR_VLD_V2, B_BSS_CLR_VLD0_V2},
 	.bss_clr_map_reg	= R_BSS_CLR_MAP_V2,
+	.rfkill_init		= &rtw8922a_rfkill_regs,
+	.rfkill_get		= {R_BE_GPIO_EXT_CTRL, B_BE_GPIO_IN_9},
 	.dma_ch_mask		= 0,
 	.edcca_regs		= &rtw8922a_edcca_regs,
 #ifdef CONFIG_PM
-- 
cgit v1.3-3-g829e


From 80fb81bb46a57daedd5decbcc253ea48428a254e Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 24 Jul 2024 13:26:25 +0800
Subject: wifi: rtw89: 885xb: reset IDMEM mode to prevent download firmware
 failure

For different firmware type, it could change IDMEM mode, so reset it to
default to avoid encountering error for RTL8851B/RTL8852B/RTL8852BT
if that kind of firmware was downloaded before.

    rtw89_8851be 0000:02:00.0: Firmware version 0.29.41.3, cmd version 0, type 5
    rtw89_8851be 0000:02:00.0: Firmware version 0.29.41.3, cmd version 0, type 3
    rtw89_8851be 0000:02:00.0: MAC has already powered on
    rtw89_8851be 0000:02:00.0: fw security fail
    rtw89_8851be 0000:02:00.0: download firmware fail
    rtw89_8851be 0000:02:00.0: [ERR]fwdl 0x1E0 = 0x62
    rtw89_8851be 0000:02:00.0: [ERR]fwdl 0x83F2 = 0x8
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f51c
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f524
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f51c
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f500
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f51c
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f53c
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f520
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f520
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f508
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f534
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f520
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f534
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f508
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f53c
    rtw89_8851be 0000:02:00.0: [ERR]fw PC = 0xb892f524
    rtw89_8851be 0000:02:00.0: failed to setup chip information
    rtw89_8851be: probe of 0000:02:00.0 failed with error -16

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240724052626.12774-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index b479434e6301..a61d3a885ff0 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -3788,7 +3788,7 @@ static int rtw89_mac_enable_cpu_ax(struct rtw89_dev *rtwdev, u8 boot_reason,
 
 	rtw89_write32(rtwdev, R_AX_WCPU_FW_CTRL, val);
 
-	if (rtwdev->chip->chip_id == RTL8852B)
+	if (rtw89_is_rtl885xb(rtwdev))
 		rtw89_write32_mask(rtwdev, R_AX_SEC_CTRL,
 				   B_AX_SEC_IDMEM_SIZE_CONFIG_MASK, 0x2);
 
-- 
cgit v1.3-3-g829e


From 27d90ad37771ab4af5ae2bf531321497984053b7 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Wed, 24 Jul 2024 13:26:26 +0800
Subject: wifi: rtw89: fix typo of rtw89_phy_ra_updata_XXX

`updata` should be `update`

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240724052626.12774-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac80211.c | 4 ++--
 drivers/net/wireless/realtek/rtw89/phy.c      | 8 ++++----
 drivers/net/wireless/realtek/rtw89/phy.h      | 2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index b95fa288c5f5..7d6a44eb8a99 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -783,7 +783,7 @@ static void rtw89_ra_mask_info_update_iter(void *data, struct ieee80211_sta *sta
 
 	rtwsta->use_cfg_mask = true;
 	rtwsta->mask = *br_data->mask;
-	rtw89_phy_ra_updata_sta(br_data->rtwdev, sta, IEEE80211_RC_SUPP_RATES_CHANGED);
+	rtw89_phy_ra_update_sta(br_data->rtwdev, sta, IEEE80211_RC_SUPP_RATES_CHANGED);
 }
 
 static void rtw89_ra_mask_info_update(struct rtw89_dev *rtwdev,
@@ -925,7 +925,7 @@ static void rtw89_ops_sta_rc_update(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	rtw89_phy_ra_updata_sta(rtwdev, sta, changed);
+	rtw89_phy_ra_update_sta(rtwdev, sta, changed);
 }
 
 static int rtw89_ops_add_chanctx(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index ad11d1414874..9579260b5a73 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -462,7 +462,7 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 	ra->csi_mode = csi_mode;
 }
 
-void rtw89_phy_ra_updata_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta,
+void rtw89_phy_ra_update_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta,
 			     u32 changed)
 {
 	struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
@@ -610,17 +610,17 @@ out:
 	rtw89_debug(rtwdev, RTW89_DBG_RA, "unset rate pattern\n");
 }
 
-static void rtw89_phy_ra_updata_sta_iter(void *data, struct ieee80211_sta *sta)
+static void rtw89_phy_ra_update_sta_iter(void *data, struct ieee80211_sta *sta)
 {
 	struct rtw89_dev *rtwdev = (struct rtw89_dev *)data;
 
-	rtw89_phy_ra_updata_sta(rtwdev, sta, IEEE80211_RC_SUPP_RATES_CHANGED);
+	rtw89_phy_ra_update_sta(rtwdev, sta, IEEE80211_RC_SUPP_RATES_CHANGED);
 }
 
 void rtw89_phy_ra_update(struct rtw89_dev *rtwdev)
 {
 	ieee80211_iterate_stations_atomic(rtwdev->hw,
-					  rtw89_phy_ra_updata_sta_iter,
+					  rtw89_phy_ra_update_sta_iter,
 					  rtwdev);
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index d8df553b9cb0..512f17d808fe 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -894,7 +894,7 @@ void rtw89_phy_set_txpwr_limit_ru(struct rtw89_dev *rtwdev,
 
 void rtw89_phy_ra_assoc(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta);
 void rtw89_phy_ra_update(struct rtw89_dev *rtwdev);
-void rtw89_phy_ra_updata_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta,
+void rtw89_phy_ra_update_sta(struct rtw89_dev *rtwdev, struct ieee80211_sta *sta,
 			     u32 changed);
 void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev,
 				struct ieee80211_vif *vif,
-- 
cgit v1.3-3-g829e


From 0e735a4c6137262bcefe45bb52fde7b1f5fc6c4d Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Fri, 26 Jul 2024 14:46:57 +0300
Subject: wifi: rtw88: always wait for both firmware loading attempts

In 'rtw_wait_firmware_completion()', always wait for both (regular and
wowlan) firmware loading attempts. Otherwise if 'rtw_usb_intf_init()'
has failed in 'rtw_usb_probe()', 'rtw_usb_disconnect()' may issue
'ieee80211_free_hw()' when one of 'rtw_load_firmware_cb()' (usually
the wowlan one) is still in progress, causing UAF detected by KASAN.

Fixes: c8e5695eae99 ("rtw88: load wowlan firmware if wowlan is supported")
Reported-by: syzbot+6c6c08700f9480c41fe3@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=6c6c08700f9480c41fe3
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240726114657.25396-1-dmantipov@yandex.ru
---
 drivers/net/wireless/realtek/rtw88/main.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index dd77adea15c7..9c58b7a41b95 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1313,20 +1313,21 @@ static int rtw_wait_firmware_completion(struct rtw_dev *rtwdev)
 {
 	const struct rtw_chip_info *chip = rtwdev->chip;
 	struct rtw_fw_state *fw;
+	int ret = 0;
 
 	fw = &rtwdev->fw;
 	wait_for_completion(&fw->completion);
 	if (!fw->firmware)
-		return -EINVAL;
+		ret = -EINVAL;
 
 	if (chip->wow_fw_name) {
 		fw = &rtwdev->wow_fw;
 		wait_for_completion(&fw->completion);
 		if (!fw->firmware)
-			return -EINVAL;
+			ret = -EINVAL;
 	}
 
-	return 0;
+	return ret;
 }
 
 static enum rtw_lps_deep_mode rtw_update_lps_deep_mode(struct rtw_dev *rtwdev,
-- 
cgit v1.3-3-g829e


From 62c5a91b25f0cf610d55ee0cc9637eb8b670423f Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:44 +0800
Subject: wifi: rtw89: chan: refine MCC re-plan flow when unassign chanctx

Originally during unassign-chanctx, MCC (multi-channel concurrency) is
re-planed before set-channel if need. But, we might calculate MCC stuffs
based on old channel info. And, the following set-channel might be racing
with FW MCC state mechanism. So, we refine this flow. Now, if MCC re-plan
is needed here, it will be done after set-channel.

Besides, to be more rigorous, we now ensure entity isn't paused before we
deal with MCC things here.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c | 37 +++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 7f90d93dcdc0..3789c98de36a 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -2443,9 +2443,10 @@ void rtw89_chanctx_ops_unassign_vif(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_chanctx_cfg *cfg = (struct rtw89_chanctx_cfg *)ctx->drv_priv;
 	struct rtw89_hal *hal = &rtwdev->hal;
-	struct rtw89_entity_weight w = {};
 	enum rtw89_sub_entity_idx roll;
 	enum rtw89_entity_mode cur;
+	enum rtw89_entity_mode new;
+	int ret;
 
 	rtwvif->sub_entity_idx = RTW89_SUB_ENTITY_0;
 	rtwvif->chanctx_assigned = false;
@@ -2469,21 +2470,33 @@ void rtw89_chanctx_ops_unassign_vif(struct rtw89_dev *rtwdev,
 	rtw89_swap_sub_entity(rtwdev, cfg->idx, roll);
 
 out:
-	rtw89_entity_calculate_weight(rtwdev, &w);
+	if (!hal->entity_pause) {
+		cur = rtw89_get_entity_mode(rtwdev);
+		switch (cur) {
+		case RTW89_ENTITY_MODE_MCC:
+			rtw89_mcc_stop(rtwdev);
+			break;
+		default:
+			break;
+		}
+	}
+
+	ret = rtw89_set_channel(rtwdev);
+	if (ret)
+		return;
 
-	cur = rtw89_get_entity_mode(rtwdev);
-	switch (cur) {
+	if (hal->entity_pause)
+		return;
+
+	new = rtw89_get_entity_mode(rtwdev);
+	switch (new) {
 	case RTW89_ENTITY_MODE_MCC:
-		/* If still multi-roles, re-plan MCC for chanctx changes.
-		 * Otherwise, just stop MCC.
-		 */
-		rtw89_mcc_stop(rtwdev);
-		if (w.active_roles == NUM_OF_RTW89_MCC_ROLES)
-			rtw89_mcc_start(rtwdev);
+		/* re-plan MCC for chanctx changes. */
+		ret = rtw89_mcc_start(rtwdev);
+		if (ret)
+			rtw89_warn(rtwdev, "failed to start MCC: %d\n", ret);
 		break;
 	default:
 		break;
 	}
-
-	rtw89_set_channel(rtwdev);
 }
-- 
cgit v1.3-3-g829e


From 39b9271095b28971fe25ac188203230505a6bf49 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:45 +0800
Subject: wifi: rtw89: mcc: stop at a role holding chanctx

In general, MCC (multi-channel concurrency) stops when some chanctx is
unassigned. Originally, we let FW to stop at a fixed role. However, it
might be the one to be unassigned.

So, iterate MCC roles and select one which is still holding chanctx.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c | 37 ++++++++++++++++++++++++++++---
 drivers/net/wireless/realtek/rtw89/fw.c   |  5 +++--
 drivers/net/wireless/realtek/rtw89/fw.h   |  2 +-
 3 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 3789c98de36a..0d848aef72b9 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -1934,22 +1934,53 @@ static int rtw89_mcc_start(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
+struct rtw89_mcc_stop_sel {
+	u8 mac_id;
+	u8 slot_idx;
+};
+
+static void rtw89_mcc_stop_sel_fill(struct rtw89_mcc_stop_sel *sel,
+				    const struct rtw89_mcc_role *mcc_role)
+{
+	sel->mac_id = mcc_role->rtwvif->mac_id;
+	sel->slot_idx = mcc_role->slot_idx;
+}
+
+static int rtw89_mcc_stop_sel_iterator(struct rtw89_dev *rtwdev,
+				       struct rtw89_mcc_role *mcc_role,
+				       unsigned int ordered_idx,
+				       void *data)
+{
+	struct rtw89_mcc_stop_sel *sel = data;
+
+	if (!mcc_role->rtwvif->chanctx_assigned)
+		return 0;
+
+	rtw89_mcc_stop_sel_fill(sel, mcc_role);
+	return 1; /* break iteration */
+}
+
 static void rtw89_mcc_stop(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_mcc_info *mcc = &rtwdev->mcc;
 	struct rtw89_mcc_role *ref = &mcc->role_ref;
+	struct rtw89_mcc_stop_sel sel;
 	int ret;
 
-	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "MCC stop\n");
+	/* by default, stop at ref */
+	rtw89_mcc_stop_sel_fill(&sel, ref);
+	rtw89_iterate_mcc_roles(rtwdev, rtw89_mcc_stop_sel_iterator, &sel);
+
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "MCC stop at <macid %d>\n", sel.mac_id);
 
 	if (rtw89_concurrent_via_mrc(rtwdev)) {
-		ret = rtw89_fw_h2c_mrc_del(rtwdev, mcc->group);
+		ret = rtw89_fw_h2c_mrc_del(rtwdev, mcc->group, sel.slot_idx);
 		if (ret)
 			rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 				    "MRC h2c failed to trigger del: %d\n", ret);
 	} else {
 		ret = rtw89_fw_h2c_stop_mcc(rtwdev, mcc->group,
-					    ref->rtwvif->mac_id, true);
+					    sel.mac_id, true);
 		if (ret)
 			rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 				    "MCC h2c failed to trigger stop: %d\n", ret);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index c83274950793..6ff7cd77a259 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -7345,7 +7345,7 @@ int rtw89_fw_h2c_mrc_start(struct rtw89_dev *rtwdev,
 	return rtw89_h2c_tx_and_wait(rtwdev, skb, wait, cond);
 }
 
-int rtw89_fw_h2c_mrc_del(struct rtw89_dev *rtwdev, u8 sch_idx)
+int rtw89_fw_h2c_mrc_del(struct rtw89_dev *rtwdev, u8 sch_idx, u8 slot_idx)
 {
 	struct rtw89_wait_info *wait = &rtwdev->mcc.wait;
 	struct rtw89_h2c_mrc_del *h2c;
@@ -7362,7 +7362,8 @@ int rtw89_fw_h2c_mrc_del(struct rtw89_dev *rtwdev, u8 sch_idx)
 	skb_put(skb, len);
 	h2c = (struct rtw89_h2c_mrc_del *)skb->data;
 
-	h2c->w0 = le32_encode_bits(sch_idx, RTW89_H2C_MRC_DEL_W0_SCH_IDX);
+	h2c->w0 = le32_encode_bits(sch_idx, RTW89_H2C_MRC_DEL_W0_SCH_IDX) |
+		  le32_encode_bits(slot_idx, RTW89_H2C_MRC_DEL_W0_STOP_SLOT_IDX);
 
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
 			      H2C_CAT_MAC,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 935f89c09054..7d48383c6244 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4499,7 +4499,7 @@ int rtw89_fw_h2c_mrc_add(struct rtw89_dev *rtwdev,
 			 const struct rtw89_fw_mrc_add_arg *arg);
 int rtw89_fw_h2c_mrc_start(struct rtw89_dev *rtwdev,
 			   const struct rtw89_fw_mrc_start_arg *arg);
-int rtw89_fw_h2c_mrc_del(struct rtw89_dev *rtwdev, u8 sch_idx);
+int rtw89_fw_h2c_mrc_del(struct rtw89_dev *rtwdev, u8 sch_idx, u8 slot_idx);
 int rtw89_fw_h2c_mrc_req_tsf(struct rtw89_dev *rtwdev,
 			     const struct rtw89_fw_mrc_req_tsf_arg *arg,
 			     struct rtw89_mac_mrc_tsf_rpt *rpt);
-- 
cgit v1.3-3-g829e


From 583e998e202451c7a139afd9e59d4bce9bc7f963 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:46 +0800
Subject: wifi: rtw89: rename sub_entity to chanctx

Originally, we planed to fill MAC_0/1 indicators with chanctx and
use sub_entity_xxx for these things. However, there are some reasons
listed below which make us give up this plan after we know our Wi-Fi 7
HW design.
	1. one link is bound to one HW band during its life time
	   but, one link might change chanctx dynamically
	2. in concurrent mode, assume 1st vif is MLD
	   1st vif's 2nd link might use the same chanctx as 2nd vif
	   but, they are not on the same HW band
So, we let sub_entity_xxx stuffs deal with only chanctx now. And, to be
more readable, we rename sub_entity related words to chanctx.

No logic is changed.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c          | 112 ++++++++++-----------
 drivers/net/wireless/realtek/rtw89/chan.h          |   6 +-
 drivers/net/wireless/realtek/rtw89/coex.c          |   2 +-
 drivers/net/wireless/realtek/rtw89/coex.h          |   2 +-
 drivers/net/wireless/realtek/rtw89/core.c          |  54 +++++-----
 drivers/net/wireless/realtek/rtw89/core.h          |  38 +++----
 drivers/net/wireless/realtek/rtw89/debug.c         |   2 +-
 drivers/net/wireless/realtek/rtw89/fw.c            |  18 ++--
 drivers/net/wireless/realtek/rtw89/mac.c           |   4 +-
 drivers/net/wireless/realtek/rtw89/mac80211.c      |   8 +-
 drivers/net/wireless/realtek/rtw89/phy.c           |  10 +-
 drivers/net/wireless/realtek/rtw89/regd.c          |   4 +-
 drivers/net/wireless/realtek/rtw89/rtw8851b.c      |   6 +-
 drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c  |  26 ++---
 drivers/net/wireless/realtek/rtw89/rtw8852a.c      |   2 +-
 drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c  |  30 +++---
 .../net/wireless/realtek/rtw89/rtw8852b_common.c   |   4 +-
 drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c  |  38 +++----
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c |  34 +++----
 drivers/net/wireless/realtek/rtw89/rtw8852c.c      |   2 +-
 drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c  |  30 +++---
 drivers/net/wireless/realtek/rtw89/rtw8922a.c      |   4 +-
 drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c  |   8 +-
 drivers/net/wireless/realtek/rtw89/sar.c           |   2 +-
 24 files changed, 223 insertions(+), 223 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 0d848aef72b9..a67e16ded91d 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -124,12 +124,12 @@ void rtw89_chan_create(struct rtw89_chan *chan, u8 center_chan, u8 primary_chan,
 }
 
 bool rtw89_assign_entity_chan(struct rtw89_dev *rtwdev,
-			      enum rtw89_sub_entity_idx idx,
+			      enum rtw89_chanctx_idx idx,
 			      const struct rtw89_chan *new)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
-	struct rtw89_chan *chan = &hal->sub[idx].chan;
-	struct rtw89_chan_rcd *rcd = &hal->sub[idx].rcd;
+	struct rtw89_chan *chan = &hal->chanctx[idx].chan;
+	struct rtw89_chan_rcd *rcd = &hal->chanctx[idx].rcd;
 	bool band_changed;
 
 	rcd->prev_primary_channel = chan->primary_channel;
@@ -153,7 +153,7 @@ int rtw89_iterate_entity_chan(struct rtw89_dev *rtwdev,
 
 	lockdep_assert_held(&rtwdev->mutex);
 
-	for_each_set_bit(idx,  hal->entity_map, NUM_OF_RTW89_SUB_ENTITY) {
+	for_each_set_bit(idx,  hal->entity_map, NUM_OF_RTW89_CHANCTX) {
 		chan = rtw89_chan_get(rtwdev, idx);
 		ret = iterator(chan, data);
 		if (ret)
@@ -164,36 +164,36 @@ int rtw89_iterate_entity_chan(struct rtw89_dev *rtwdev,
 }
 
 static void __rtw89_config_entity_chandef(struct rtw89_dev *rtwdev,
-					  enum rtw89_sub_entity_idx idx,
+					  enum rtw89_chanctx_idx idx,
 					  const struct cfg80211_chan_def *chandef,
 					  bool from_stack)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 
-	hal->sub[idx].chandef = *chandef;
+	hal->chanctx[idx].chandef = *chandef;
 
 	if (from_stack)
 		set_bit(idx, hal->entity_map);
 }
 
 void rtw89_config_entity_chandef(struct rtw89_dev *rtwdev,
-				 enum rtw89_sub_entity_idx idx,
+				 enum rtw89_chanctx_idx idx,
 				 const struct cfg80211_chan_def *chandef)
 {
 	__rtw89_config_entity_chandef(rtwdev, idx, chandef, true);
 }
 
 void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
-			      enum rtw89_sub_entity_idx idx,
+			      enum rtw89_chanctx_idx idx,
 			      const struct cfg80211_chan_def *chandef)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
-	enum rtw89_sub_entity_idx cur;
+	enum rtw89_chanctx_idx cur;
 
 	if (chandef) {
 		cur = atomic_cmpxchg(&hal->roc_entity_idx,
-				     RTW89_SUB_ENTITY_IDLE, idx);
-		if (cur != RTW89_SUB_ENTITY_IDLE) {
+				     RTW89_CHANCTX_IDLE, idx);
+		if (cur != RTW89_CHANCTX_IDLE) {
 			rtw89_debug(rtwdev, RTW89_DBG_TXRX,
 				    "ROC still processing on entity %d\n", idx);
 			return;
@@ -202,11 +202,11 @@ void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
 		hal->roc_chandef = *chandef;
 	} else {
 		cur = atomic_cmpxchg(&hal->roc_entity_idx, idx,
-				     RTW89_SUB_ENTITY_IDLE);
+				     RTW89_CHANCTX_IDLE);
 		if (cur == idx)
 			return;
 
-		if (cur == RTW89_SUB_ENTITY_IDLE)
+		if (cur == RTW89_CHANCTX_IDLE)
 			rtw89_debug(rtwdev, RTW89_DBG_TXRX,
 				    "ROC already finished on entity %d\n", idx);
 		else
@@ -220,7 +220,7 @@ static void rtw89_config_default_chandef(struct rtw89_dev *rtwdev)
 	struct cfg80211_chan_def chandef = {0};
 
 	rtw89_get_default_chandef(&chandef);
-	__rtw89_config_entity_chandef(rtwdev, RTW89_SUB_ENTITY_0, &chandef, false);
+	__rtw89_config_entity_chandef(rtwdev, RTW89_CHANCTX_0, &chandef, false);
 }
 
 void rtw89_entity_init(struct rtw89_dev *rtwdev)
@@ -228,9 +228,9 @@ void rtw89_entity_init(struct rtw89_dev *rtwdev)
 	struct rtw89_hal *hal = &rtwdev->hal;
 
 	hal->entity_pause = false;
-	bitmap_zero(hal->entity_map, NUM_OF_RTW89_SUB_ENTITY);
+	bitmap_zero(hal->entity_map, NUM_OF_RTW89_CHANCTX);
 	bitmap_zero(hal->changes, NUM_OF_RTW89_CHANCTX_CHANGES);
-	atomic_set(&hal->roc_entity_idx, RTW89_SUB_ENTITY_IDLE);
+	atomic_set(&hal->roc_entity_idx, RTW89_CHANCTX_IDLE);
 	rtw89_config_default_chandef(rtwdev);
 }
 
@@ -242,8 +242,8 @@ static void rtw89_entity_calculate_weight(struct rtw89_dev *rtwdev,
 	struct rtw89_vif *rtwvif;
 	int idx;
 
-	for_each_set_bit(idx, hal->entity_map, NUM_OF_RTW89_SUB_ENTITY) {
-		cfg = hal->sub[idx].cfg;
+	for_each_set_bit(idx, hal->entity_map, NUM_OF_RTW89_CHANCTX) {
+		cfg = hal->chanctx[idx].cfg;
 		if (!cfg) {
 			/* doesn't run with chanctx ops; one channel at most */
 			w->active_chanctxs = 1;
@@ -262,7 +262,7 @@ static void rtw89_entity_calculate_weight(struct rtw89_dev *rtwdev,
 
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 {
-	DECLARE_BITMAP(recalc_map, NUM_OF_RTW89_SUB_ENTITY) = {};
+	DECLARE_BITMAP(recalc_map, NUM_OF_RTW89_CHANCTX) = {};
 	struct rtw89_hal *hal = &rtwdev->hal;
 	const struct cfg80211_chan_def *chandef;
 	struct rtw89_entity_weight w = {};
@@ -272,23 +272,23 @@ enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 
 	lockdep_assert_held(&rtwdev->mutex);
 
-	bitmap_copy(recalc_map, hal->entity_map, NUM_OF_RTW89_SUB_ENTITY);
+	bitmap_copy(recalc_map, hal->entity_map, NUM_OF_RTW89_CHANCTX);
 
 	rtw89_entity_calculate_weight(rtwdev, &w);
 	switch (w.active_chanctxs) {
 	default:
 		rtw89_warn(rtwdev, "unknown ent chanctxs weight: %d\n",
 			   w.active_chanctxs);
-		bitmap_zero(recalc_map, NUM_OF_RTW89_SUB_ENTITY);
+		bitmap_zero(recalc_map, NUM_OF_RTW89_CHANCTX);
 		fallthrough;
 	case 0:
 		rtw89_config_default_chandef(rtwdev);
-		set_bit(RTW89_SUB_ENTITY_0, recalc_map);
+		set_bit(RTW89_CHANCTX_0, recalc_map);
 		fallthrough;
 	case 1:
 		mode = RTW89_ENTITY_MODE_SCC;
 		break;
-	case 2 ... NUM_OF_RTW89_SUB_ENTITY:
+	case 2 ... NUM_OF_RTW89_CHANCTX:
 		if (w.active_roles != NUM_OF_RTW89_MCC_ROLES) {
 			rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 				    "unhandled ent: %d chanctxs %d roles\n",
@@ -304,7 +304,7 @@ enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 		break;
 	}
 
-	for_each_set_bit(idx, recalc_map, NUM_OF_RTW89_SUB_ENTITY) {
+	for_each_set_bit(idx, recalc_map, NUM_OF_RTW89_CHANCTX) {
 		chandef = rtw89_chandef_get(rtwdev, idx);
 		rtw89_get_channel_params(chandef, &chan);
 		if (chan.channel == 0) {
@@ -650,7 +650,7 @@ static int rtw89_mcc_fill_role(struct rtw89_dev *rtwdev,
 
 	role->duration = role->beacon_interval / 2;
 
-	chan = rtw89_chan_get(rtwdev, rtwvif->sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 	role->is_2ghz = chan->band_type == RTW89_BAND_2G;
 	role->is_go = rtwvif->wifi_role == RTW89_WIFI_ROLE_P2P_GO;
 	role->is_gc = rtwvif->wifi_role == RTW89_WIFI_ROLE_P2P_CLIENT;
@@ -678,10 +678,10 @@ static void rtw89_mcc_fill_bt_role(struct rtw89_dev *rtwdev)
 }
 
 struct rtw89_mcc_fill_role_selector {
-	struct rtw89_vif *bind_vif[NUM_OF_RTW89_SUB_ENTITY];
+	struct rtw89_vif *bind_vif[NUM_OF_RTW89_CHANCTX];
 };
 
-static_assert((u8)NUM_OF_RTW89_SUB_ENTITY >= NUM_OF_RTW89_MCC_ROLES);
+static_assert((u8)NUM_OF_RTW89_CHANCTX >= NUM_OF_RTW89_MCC_ROLES);
 
 static int rtw89_mcc_fill_role_iterator(struct rtw89_dev *rtwdev,
 					struct rtw89_mcc_role *mcc_role,
@@ -719,14 +719,14 @@ static int rtw89_mcc_fill_all_roles(struct rtw89_dev *rtwdev)
 		if (!rtwvif->chanctx_assigned)
 			continue;
 
-		if (sel.bind_vif[rtwvif->sub_entity_idx]) {
+		if (sel.bind_vif[rtwvif->chanctx_idx]) {
 			rtw89_warn(rtwdev,
 				   "MCC skip extra vif <macid %d> on chanctx[%d]\n",
-				   rtwvif->mac_id, rtwvif->sub_entity_idx);
+				   rtwvif->mac_id, rtwvif->chanctx_idx);
 			continue;
 		}
 
-		sel.bind_vif[rtwvif->sub_entity_idx] = rtwvif;
+		sel.bind_vif[rtwvif->chanctx_idx] = rtwvif;
 	}
 
 	ret = rtw89_iterate_mcc_roles(rtwdev, rtw89_mcc_fill_role_iterator, &sel);
@@ -1390,7 +1390,7 @@ static int __mcc_fw_add_role(struct rtw89_dev *rtwdev, struct rtw89_mcc_role *ro
 	const struct rtw89_chan *chan;
 	int ret;
 
-	chan = rtw89_chan_get(rtwdev, role->rtwvif->sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, role->rtwvif->chanctx_idx);
 	req.central_ch_seg0 = chan->channel;
 	req.primary_ch = chan->primary_channel;
 	req.bandwidth = chan->band_width;
@@ -1448,7 +1448,7 @@ void __mrc_fw_add_role(struct rtw89_dev *rtwdev, struct rtw89_mcc_role *role,
 	slot_arg->duration = role->duration;
 	slot_arg->role_num = 1;
 
-	chan = rtw89_chan_get(rtwdev, role->rtwvif->sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, role->rtwvif->chanctx_idx);
 
 	slot_arg->roles[0].role_type = RTW89_H2C_MRC_ROLE_WIFI;
 	slot_arg->roles[0].is_master = role == ref;
@@ -2370,9 +2370,9 @@ void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev)
 	rtw89_queue_chanctx_work(rtwdev);
 }
 
-static void rtw89_swap_sub_entity(struct rtw89_dev *rtwdev,
-				  enum rtw89_sub_entity_idx idx1,
-				  enum rtw89_sub_entity_idx idx2)
+static void rtw89_swap_chanctx(struct rtw89_dev *rtwdev,
+			       enum rtw89_chanctx_idx idx1,
+			       enum rtw89_chanctx_idx idx2)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_vif *rtwvif;
@@ -2381,18 +2381,18 @@ static void rtw89_swap_sub_entity(struct rtw89_dev *rtwdev,
 	if (idx1 == idx2)
 		return;
 
-	hal->sub[idx1].cfg->idx = idx2;
-	hal->sub[idx2].cfg->idx = idx1;
+	hal->chanctx[idx1].cfg->idx = idx2;
+	hal->chanctx[idx2].cfg->idx = idx1;
 
-	swap(hal->sub[idx1], hal->sub[idx2]);
+	swap(hal->chanctx[idx1], hal->chanctx[idx2]);
 
 	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
 		if (!rtwvif->chanctx_assigned)
 			continue;
-		if (rtwvif->sub_entity_idx == idx1)
-			rtwvif->sub_entity_idx = idx2;
-		else if (rtwvif->sub_entity_idx == idx2)
-			rtwvif->sub_entity_idx = idx1;
+		if (rtwvif->chanctx_idx == idx1)
+			rtwvif->chanctx_idx = idx2;
+		else if (rtwvif->chanctx_idx == idx2)
+			rtwvif->chanctx_idx = idx1;
 	}
 
 	cur = atomic_read(&hal->roc_entity_idx);
@@ -2410,14 +2410,14 @@ int rtw89_chanctx_ops_add(struct rtw89_dev *rtwdev,
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u8 idx;
 
-	idx = find_first_zero_bit(hal->entity_map, NUM_OF_RTW89_SUB_ENTITY);
+	idx = find_first_zero_bit(hal->entity_map, NUM_OF_RTW89_CHANCTX);
 	if (idx >= chip->support_chanctx_num)
 		return -ENOENT;
 
 	rtw89_config_entity_chandef(rtwdev, idx, &ctx->def);
 	cfg->idx = idx;
 	cfg->ref_count = 0;
-	hal->sub[idx].cfg = cfg;
+	hal->chanctx[idx].cfg = cfg;
 	return 0;
 }
 
@@ -2450,19 +2450,19 @@ int rtw89_chanctx_ops_assign_vif(struct rtw89_dev *rtwdev,
 	struct rtw89_chanctx_cfg *cfg = (struct rtw89_chanctx_cfg *)ctx->drv_priv;
 	struct rtw89_entity_weight w = {};
 
-	rtwvif->sub_entity_idx = cfg->idx;
+	rtwvif->chanctx_idx = cfg->idx;
 	rtwvif->chanctx_assigned = true;
 	cfg->ref_count++;
 
-	if (cfg->idx == RTW89_SUB_ENTITY_0)
+	if (cfg->idx == RTW89_CHANCTX_0)
 		goto out;
 
 	rtw89_entity_calculate_weight(rtwdev, &w);
 	if (w.active_chanctxs != 1)
 		goto out;
 
-	/* put the first active chanctx at RTW89_SUB_ENTITY_0 */
-	rtw89_swap_sub_entity(rtwdev, cfg->idx, RTW89_SUB_ENTITY_0);
+	/* put the first active chanctx at RTW89_CHANCTX_0 */
+	rtw89_swap_chanctx(rtwdev, cfg->idx, RTW89_CHANCTX_0);
 
 out:
 	return rtw89_set_channel(rtwdev);
@@ -2474,31 +2474,31 @@ void rtw89_chanctx_ops_unassign_vif(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_chanctx_cfg *cfg = (struct rtw89_chanctx_cfg *)ctx->drv_priv;
 	struct rtw89_hal *hal = &rtwdev->hal;
-	enum rtw89_sub_entity_idx roll;
+	enum rtw89_chanctx_idx roll;
 	enum rtw89_entity_mode cur;
 	enum rtw89_entity_mode new;
 	int ret;
 
-	rtwvif->sub_entity_idx = RTW89_SUB_ENTITY_0;
+	rtwvif->chanctx_idx = RTW89_CHANCTX_0;
 	rtwvif->chanctx_assigned = false;
 	cfg->ref_count--;
 
 	if (cfg->ref_count != 0)
 		goto out;
 
-	if (cfg->idx != RTW89_SUB_ENTITY_0)
+	if (cfg->idx != RTW89_CHANCTX_0)
 		goto out;
 
-	roll = find_next_bit(hal->entity_map, NUM_OF_RTW89_SUB_ENTITY,
+	roll = find_next_bit(hal->entity_map, NUM_OF_RTW89_CHANCTX,
 			     cfg->idx + 1);
 	/* Follow rtw89_config_default_chandef() when rtw89_entity_recalc(). */
-	if (roll == NUM_OF_RTW89_SUB_ENTITY)
+	if (roll == NUM_OF_RTW89_CHANCTX)
 		goto out;
 
-	/* RTW89_SUB_ENTITY_0 is going to release, and another exists.
-	 * Make another roll down to RTW89_SUB_ENTITY_0 to replace.
+	/* RTW89_CHANCTX_0 is going to release, and another exists.
+	 * Make another roll down to RTW89_CHANCTX_0 to replace.
 	 */
-	rtw89_swap_sub_entity(rtwdev, cfg->idx, roll);
+	rtw89_swap_chanctx(rtwdev, cfg->idx, roll);
 
 out:
 	if (!hal->entity_pause) {
diff --git a/drivers/net/wireless/realtek/rtw89/chan.h b/drivers/net/wireless/realtek/rtw89/chan.h
index 5278ff8c513b..c6d31984e575 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.h
+++ b/drivers/net/wireless/realtek/rtw89/chan.h
@@ -76,17 +76,17 @@ static inline void rtw89_set_entity_mode(struct rtw89_dev *rtwdev,
 void rtw89_chan_create(struct rtw89_chan *chan, u8 center_chan, u8 primary_chan,
 		       enum rtw89_band band, enum rtw89_bandwidth bandwidth);
 bool rtw89_assign_entity_chan(struct rtw89_dev *rtwdev,
-			      enum rtw89_sub_entity_idx idx,
+			      enum rtw89_chanctx_idx idx,
 			      const struct rtw89_chan *new);
 int rtw89_iterate_entity_chan(struct rtw89_dev *rtwdev,
 			      int (*iterator)(const struct rtw89_chan *chan,
 					      void *data),
 			      void *data);
 void rtw89_config_entity_chandef(struct rtw89_dev *rtwdev,
-				 enum rtw89_sub_entity_idx idx,
+				 enum rtw89_chanctx_idx idx,
 				 const struct cfg80211_chan_def *chandef);
 void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
-			      enum rtw89_sub_entity_idx idx,
+			      enum rtw89_chanctx_idx idx,
 			      const struct cfg80211_chan_def *chandef);
 void rtw89_entity_init(struct rtw89_dev *rtwdev);
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 24929ef534e0..c1f6fcef904b 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -7169,7 +7169,7 @@ void rtw89_btc_ntfy_role_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif
 			      struct rtw89_sta *rtwsta, enum btc_role_state state)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 	struct ieee80211_sta *sta = rtwsta_to_sta(rtwsta);
 	struct rtw89_btc *btc = &rtwdev->btc;
diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index 7678fb8bcf7e..72e3c77d2a3a 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -293,7 +293,7 @@ static inline u8 rtw89_btc_phymap(struct rtw89_dev *rtwdev,
 				  enum rtw89_phy_idx phy_idx,
 				  enum rtw89_rf_path_bit paths)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 phy_map;
 
 	phy_map = FIELD_PREP(BTC_RFK_PATH_MAP, paths) |
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 45952994ffa6..fbe94c68b171 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -346,8 +346,8 @@ void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 	struct rtw89_hal *hal = &rtwdev->hal;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_chan *chan;
-	enum rtw89_sub_entity_idx sub_entity_idx;
-	enum rtw89_sub_entity_idx roc_idx;
+	enum rtw89_chanctx_idx chanctx_idx;
+	enum rtw89_chanctx_idx roc_idx;
 	enum rtw89_phy_idx phy_idx;
 	enum rtw89_entity_mode mode;
 	bool entity_active;
@@ -360,10 +360,10 @@ void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 	switch (mode) {
 	case RTW89_ENTITY_MODE_SCC:
 	case RTW89_ENTITY_MODE_MCC:
-		sub_entity_idx = RTW89_SUB_ENTITY_0;
+		chanctx_idx = RTW89_CHANCTX_0;
 		break;
 	case RTW89_ENTITY_MODE_MCC_PREPARE:
-		sub_entity_idx = RTW89_SUB_ENTITY_1;
+		chanctx_idx = RTW89_CHANCTX_1;
 		break;
 	default:
 		WARN(1, "Invalid ent mode: %d\n", mode);
@@ -371,11 +371,11 @@ void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 	}
 
 	roc_idx = atomic_read(&hal->roc_entity_idx);
-	if (roc_idx != RTW89_SUB_ENTITY_IDLE)
-		sub_entity_idx = roc_idx;
+	if (roc_idx != RTW89_CHANCTX_IDLE)
+		chanctx_idx = roc_idx;
 
 	phy_idx = RTW89_PHY_0;
-	chan = rtw89_chan_get(rtwdev, sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	chip->ops->set_txpwr(rtwdev, chan, phy_idx);
 }
 
@@ -385,8 +385,8 @@ int rtw89_set_channel(struct rtw89_dev *rtwdev)
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_chan_rcd *chan_rcd;
 	const struct rtw89_chan *chan;
-	enum rtw89_sub_entity_idx sub_entity_idx;
-	enum rtw89_sub_entity_idx roc_idx;
+	enum rtw89_chanctx_idx chanctx_idx;
+	enum rtw89_chanctx_idx roc_idx;
 	enum rtw89_mac_idx mac_idx;
 	enum rtw89_phy_idx phy_idx;
 	struct rtw89_channel_help_params bak;
@@ -399,10 +399,10 @@ int rtw89_set_channel(struct rtw89_dev *rtwdev)
 	switch (mode) {
 	case RTW89_ENTITY_MODE_SCC:
 	case RTW89_ENTITY_MODE_MCC:
-		sub_entity_idx = RTW89_SUB_ENTITY_0;
+		chanctx_idx = RTW89_CHANCTX_0;
 		break;
 	case RTW89_ENTITY_MODE_MCC_PREPARE:
-		sub_entity_idx = RTW89_SUB_ENTITY_1;
+		chanctx_idx = RTW89_CHANCTX_1;
 		break;
 	default:
 		WARN(1, "Invalid ent mode: %d\n", mode);
@@ -410,14 +410,14 @@ int rtw89_set_channel(struct rtw89_dev *rtwdev)
 	}
 
 	roc_idx = atomic_read(&hal->roc_entity_idx);
-	if (roc_idx != RTW89_SUB_ENTITY_IDLE)
-		sub_entity_idx = roc_idx;
+	if (roc_idx != RTW89_CHANCTX_IDLE)
+		chanctx_idx = roc_idx;
 
 	mac_idx = RTW89_MAC_0;
 	phy_idx = RTW89_PHY_0;
 
-	chan = rtw89_chan_get(rtwdev, sub_entity_idx);
-	chan_rcd = rtw89_chan_rcd_get(rtwdev, sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, chanctx_idx);
+	chan_rcd = rtw89_chan_rcd_get(rtwdev, chanctx_idx);
 
 	rtw89_chip_set_channel_prepare(rtwdev, &bak, chan, mac_idx, phy_idx);
 
@@ -441,7 +441,7 @@ void rtw89_get_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 {
 	const struct cfg80211_chan_def *chandef;
 
-	chandef = rtw89_chandef_get(rtwdev, rtwvif->sub_entity_idx);
+	chandef = rtw89_chandef_get(rtwdev, rtwvif->chanctx_idx);
 	rtw89_get_channel_params(chandef, chan);
 }
 
@@ -610,7 +610,7 @@ rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev,
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	u8 qsel, ch_dma;
 
 	qsel = desc_info->hiq ? RTW89_TX_QSEL_B0_HI : RTW89_TX_QSEL_B0_MGMT;
@@ -769,7 +769,7 @@ static u16 rtw89_core_get_data_rate(struct rtw89_dev *rtwdev,
 	struct ieee80211_sta *sta = tx_req->sta;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_phy_rate_pattern *rate_pattern = &rtwvif->rate_pattern;
-	enum rtw89_sub_entity_idx idx = rtwvif->sub_entity_idx;
+	enum rtw89_chanctx_idx idx = rtwvif->chanctx_idx;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, idx);
 	u16 lowest_rate;
 
@@ -1987,7 +1987,7 @@ static void rtw89_correct_cck_chan(struct rtw89_dev *rtwdev,
 				   struct ieee80211_rx_status *status)
 {
 	const struct rtw89_chan_rcd *rcd =
-		rtw89_chan_rcd_get(rtwdev, RTW89_SUB_ENTITY_0);
+		rtw89_chan_rcd_get(rtwdev, RTW89_CHANCTX_0);
 	u16 chan = rcd->prev_primary_channel;
 	u8 band = rtw89_hw_to_nl80211_band(rcd->prev_band_type);
 
@@ -2391,7 +2391,7 @@ static void rtw89_core_update_rx_status(struct rtw89_dev *rtwdev,
 					struct ieee80211_rx_status *rx_status)
 {
 	const struct cfg80211_chan_def *chandef =
-		rtw89_chandef_get(rtwdev, RTW89_SUB_ENTITY_0);
+		rtw89_chandef_get(rtwdev, RTW89_CHANCTX_0);
 	u16 data_rate;
 	u8 data_rate_mode;
 	bool eht = false;
@@ -2884,7 +2884,7 @@ static void rtw89_core_sta_pending_tx_iter(void *data,
 	struct sk_buff *skb, *tmp;
 	int qsel, ret;
 
-	if (rtwvif->sub_entity_idx != rtwvif_target->sub_entity_idx)
+	if (rtwvif->chanctx_idx != rtwvif_target->chanctx_idx)
 		return;
 
 	if (skb_queue_len(&rtwsta->roc_queue) == 0)
@@ -2978,11 +2978,11 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 			    "roc send null-1 failed: %d\n", ret);
 
 	rtw89_for_each_rtwvif(rtwdev, tmp)
-		if (tmp->sub_entity_idx == rtwvif->sub_entity_idx)
+		if (tmp->chanctx_idx == rtwvif->chanctx_idx)
 			tmp->offchan = true;
 
 	cfg80211_chandef_create(&roc_chan, &roc->chan, NL80211_CHAN_NO_HT);
-	rtw89_config_roc_chandef(rtwdev, rtwvif->sub_entity_idx, &roc_chan);
+	rtw89_config_roc_chandef(rtwdev, rtwvif->chanctx_idx, &roc_chan);
 	rtw89_set_channel(rtwdev);
 	rtw89_write32_clr(rtwdev,
 			  rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_0),
@@ -3015,7 +3015,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 			   rtwdev->hal.rx_fltr);
 
 	roc->state = RTW89_ROC_IDLE;
-	rtw89_config_roc_chandef(rtwdev, rtwvif->sub_entity_idx, NULL);
+	rtw89_config_roc_chandef(rtwdev, rtwvif->chanctx_idx, NULL);
 	rtw89_chanctx_proceed(rtwdev);
 	ret = rtw89_core_send_nullfunc(rtwdev, rtwvif, true, false);
 	if (ret)
@@ -3023,7 +3023,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 			    "roc send null-0 failed: %d\n", ret);
 
 	rtw89_for_each_rtwvif(rtwdev, tmp)
-		if (tmp->sub_entity_idx == rtwvif->sub_entity_idx)
+		if (tmp->chanctx_idx == rtwvif->chanctx_idx)
 			tmp->offchan = false;
 
 	rtw89_core_handle_sta_pending_tx(rtwdev, rtwvif);
@@ -3521,7 +3521,7 @@ int rtw89_core_sta_assoc(struct rtw89_dev *rtwdev,
 	struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
 	struct rtw89_bssid_cam_entry *bssid_cam = rtw89_get_bssid_cam_of(rtwvif, rtwsta);
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	int ret;
 
 	if (vif->type == NL80211_IFTYPE_AP || sta->tdls) {
@@ -4363,7 +4363,7 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			   const u8 *mac_addr, bool hw_scan)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 
 	rtwdev->scanning = true;
 	rtw89_leave_lps(rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index a0d0bf53d961..d43a30ae3181 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -822,12 +822,12 @@ enum rtw89_phy_idx {
 	RTW89_PHY_MAX
 };
 
-enum rtw89_sub_entity_idx {
-	RTW89_SUB_ENTITY_0 = 0,
-	RTW89_SUB_ENTITY_1 = 1,
+enum rtw89_chanctx_idx {
+	RTW89_CHANCTX_0 = 0,
+	RTW89_CHANCTX_1 = 1,
 
-	NUM_OF_RTW89_SUB_ENTITY,
-	RTW89_SUB_ENTITY_IDLE = NUM_OF_RTW89_SUB_ENTITY,
+	NUM_OF_RTW89_CHANCTX,
+	RTW89_CHANCTX_IDLE = NUM_OF_RTW89_CHANCTX,
 };
 
 enum rtw89_rf_path {
@@ -3406,7 +3406,7 @@ struct rtw89_vif {
 	struct rtw89_dev *rtwdev;
 	struct rtw89_roc roc;
 	bool chanctx_assigned; /* only valid when running with chanctx_ops */
-	enum rtw89_sub_entity_idx sub_entity_idx;
+	enum rtw89_chanctx_idx chanctx_idx;
 	enum rtw89_reg_6ghz_power reg_6ghz_power;
 	struct rtw89_reg_6ghz_tpe reg_6ghz_tpe;
 
@@ -4529,7 +4529,7 @@ struct rtw89_tas_info {
 };
 
 struct rtw89_chanctx_cfg {
-	enum rtw89_sub_entity_idx idx;
+	enum rtw89_chanctx_idx idx;
 	int ref_count;
 };
 
@@ -4554,7 +4554,7 @@ enum rtw89_entity_mode {
 	RTW89_ENTITY_MODE_UNHANDLED = -ESRCH,
 };
 
-struct rtw89_sub_entity {
+struct rtw89_chanctx {
 	struct cfg80211_chan_def chandef;
 	struct rtw89_chan chan;
 	struct rtw89_chan_rcd rcd;
@@ -4590,8 +4590,8 @@ struct rtw89_hal {
 	atomic_t roc_entity_idx;
 
 	DECLARE_BITMAP(changes, NUM_OF_RTW89_CHANCTX_CHANGES);
-	DECLARE_BITMAP(entity_map, NUM_OF_RTW89_SUB_ENTITY);
-	struct rtw89_sub_entity sub[NUM_OF_RTW89_SUB_ENTITY];
+	DECLARE_BITMAP(entity_map, NUM_OF_RTW89_CHANCTX);
+	struct rtw89_chanctx chanctx[NUM_OF_RTW89_CHANCTX];
 	struct cfg80211_chan_def roc_chandef;
 
 	bool entity_active;
@@ -6039,33 +6039,33 @@ void rtw89_chip_set_channel_done(struct rtw89_dev *rtwdev,
 
 static inline
 const struct cfg80211_chan_def *rtw89_chandef_get(struct rtw89_dev *rtwdev,
-						  enum rtw89_sub_entity_idx idx)
+						  enum rtw89_chanctx_idx idx)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
-	enum rtw89_sub_entity_idx roc_idx = atomic_read(&hal->roc_entity_idx);
+	enum rtw89_chanctx_idx roc_idx = atomic_read(&hal->roc_entity_idx);
 
 	if (roc_idx == idx)
 		return &hal->roc_chandef;
 
-	return &hal->sub[idx].chandef;
+	return &hal->chanctx[idx].chandef;
 }
 
 static inline
 const struct rtw89_chan *rtw89_chan_get(struct rtw89_dev *rtwdev,
-					enum rtw89_sub_entity_idx idx)
+					enum rtw89_chanctx_idx idx)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 
-	return &hal->sub[idx].chan;
+	return &hal->chanctx[idx].chan;
 }
 
 static inline
 const struct rtw89_chan_rcd *rtw89_chan_rcd_get(struct rtw89_dev *rtwdev,
-						enum rtw89_sub_entity_idx idx)
+						enum rtw89_chanctx_idx idx)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
 
-	return &hal->sub[idx].rcd;
+	return &hal->chanctx[idx].rcd;
 }
 
 static inline
@@ -6075,9 +6075,9 @@ const struct rtw89_chan *rtw89_scan_chan_get(struct rtw89_dev *rtwdev)
 	struct rtw89_vif *rtwvif = vif_to_rtwvif_safe(vif);
 
 	if (rtwvif)
-		return rtw89_chan_get(rtwdev, rtwvif->sub_entity_idx);
+		return rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 	else
-		return rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+		return rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 }
 
 static inline void rtw89_chip_fem_setup(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 6fc30f137eaa..bb65b814585a 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -851,7 +851,7 @@ static int rtw89_debug_priv_txpwr_table_get(struct seq_file *m, void *v)
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
-	chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	rtw89_debug_priv_txpwr_table_get_regd(m, rtwdev, chan);
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 6ff7cd77a259..1db32418e912 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -2495,7 +2495,7 @@ fail:
 int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_h2c_lps_ch_info *h2c;
 	u32 len = sizeof(*h2c);
@@ -2814,7 +2814,7 @@ int rtw89_fw_h2c_assoc_cmac_tbl(struct rtw89_dev *rtwdev,
 	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	struct sk_buff *skb;
 	u8 pads[RTW89_PPE_BW_NUM];
 	u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id;
@@ -2947,7 +2947,7 @@ int rtw89_fw_h2c_assoc_cmac_tbl_g7(struct rtw89_dev *rtwdev,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
 	u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id;
@@ -3210,7 +3210,7 @@ int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev,
 			       struct rtw89_vif *rtwvif)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 	struct rtw89_h2c_bcn_upd *h2c;
 	struct sk_buff *skb_beacon;
@@ -3289,7 +3289,7 @@ EXPORT_SYMBOL(rtw89_fw_h2c_update_beacon);
 int rtw89_fw_h2c_update_beacon_be(struct rtw89_dev *rtwdev,
 				  struct rtw89_vif *rtwvif)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 	struct rtw89_h2c_bcn_upd_be *h2c;
 	struct sk_buff *skb_beacon;
@@ -5209,7 +5209,7 @@ int rtw89_fw_h2c_rf_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
 			 enum rtw89_tssi_mode tssi_mode)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_SUB_ENTITY_0);
+						       RTW89_CHANCTX_0);
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_h2c_rf_tssi *h2c;
 	u32 len = sizeof(*h2c);
@@ -5291,7 +5291,7 @@ fail:
 int rtw89_fw_h2c_rf_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_SUB_ENTITY_0);
+						       RTW89_CHANCTX_0);
 	struct rtw89_h2c_rf_dpk *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
@@ -5334,7 +5334,7 @@ fail:
 int rtw89_fw_h2c_rf_txgapk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_SUB_ENTITY_0);
+						       RTW89_CHANCTX_0);
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_h2c_rf_txgapk *h2c;
 	u32 len = sizeof(*h2c);
@@ -5414,7 +5414,7 @@ fail:
 int rtw89_fw_h2c_rf_rxdck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_SUB_ENTITY_0);
+						       RTW89_CHANCTX_0);
 	struct rtw89_h2c_rf_rxdck *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index a61d3a885ff0..6c2cef134d9b 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4781,14 +4781,14 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 	case RTW89_SCAN_ENTER_OP_NOTIFY:
 	case RTW89_SCAN_ENTER_CH_NOTIFY:
 		if (rtw89_is_op_chan(rtwdev, band, chan)) {
-			rtw89_assign_entity_chan(rtwdev, rtwvif->sub_entity_idx,
+			rtw89_assign_entity_chan(rtwdev, rtwvif->chanctx_idx,
 						 &rtwdev->scan_info.op_chan);
 			rtw89_mac_enable_beacon_for_ap_vifs(rtwdev, true);
 			ieee80211_wake_queues(rtwdev->hw);
 		} else {
 			rtw89_chan_create(&new, chan, chan, band,
 					  RTW89_CHANNEL_WIDTH_20);
-			rtw89_assign_entity_chan(rtwdev, rtwvif->sub_entity_idx,
+			rtw89_assign_entity_chan(rtwdev, rtwvif->chanctx_idx,
 						 &new);
 		}
 		break;
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 7d6a44eb8a99..95cff2a8a337 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -90,7 +90,7 @@ static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed)
 		rtw89_leave_ips(rtwdev);
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
-		rtw89_config_entity_chandef(rtwdev, RTW89_SUB_ENTITY_0,
+		rtw89_config_entity_chandef(rtwdev, RTW89_CHANCTX_0,
 					    &hw->conf.chandef);
 		rtw89_set_channel(rtwdev);
 	}
@@ -144,7 +144,7 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 	rtwvif->bcn_hit_cond = 0;
 	rtwvif->mac_idx = RTW89_MAC_0;
 	rtwvif->phy_idx = RTW89_PHY_0;
-	rtwvif->sub_entity_idx = RTW89_SUB_ENTITY_0;
+	rtwvif->chanctx_idx = RTW89_CHANCTX_0;
 	rtwvif->chanctx_assigned = false;
 	rtwvif->hit_rule = 0;
 	rtwvif->reg_6ghz_power = RTW89_REG_6GHZ_POWER_DFLT;
@@ -313,7 +313,7 @@ static u8 rtw89_aifsn_to_aifs(struct rtw89_dev *rtwdev,
 {
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	u8 slot_time;
 	u8 sifs;
 
@@ -503,7 +503,7 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 
 	mutex_lock(&rtwdev->mutex);
 
-	chan = rtw89_chan_get(rtwdev, rtwvif->sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 	if (chan->band_type == RTW89_BAND_6G) {
 		mutex_unlock(&rtwdev->mutex);
 		return -EOPNOTSUPP;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 9579260b5a73..118d09b3eadd 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -302,7 +302,7 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 	struct rtw89_phy_rate_pattern *rate_pattern = &rtwvif->rate_pattern;
 	struct rtw89_ra_info *ra = &rtwsta->ra;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwsta->rtwvif);
 	const u64 *high_rate_masks = rtw89_ra_mask_ht_rates;
 	u8 rssi = ewma_rssi_read(&rtwsta->avg_rssi);
@@ -528,7 +528,7 @@ void rtw89_phy_rate_pattern_vif(struct rtw89_dev *rtwdev,
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_phy_rate_pattern next_pattern = {0};
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	static const u16 hw_rate_he[][RTW89_CHIP_GEN_NUM] = {
 		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS1_MCS0),
 		RTW89_HW_RATE_BY_CHIP_GEN(HE_NSS2_MCS0),
@@ -4285,7 +4285,7 @@ void rtw89_phy_ul_tb_assoc(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       rtwvif->sub_entity_idx);
+						       rtwvif->chanctx_idx);
 	struct rtw89_phy_ul_tb_info *ul_tb_info = &rtwdev->ul_tb_info;
 
 	if (!chip->ul_tb_waveform_ctrl)
@@ -5367,7 +5367,7 @@ static void rtw89_phy_dig_update_rssi_info(struct rtw89_dev *rtwdev)
 static void rtw89_phy_dig_update_para(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_dig_info *dig = &rtwdev->dig;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	bool is_linked = rtwdev->total_sta_assoc > 0;
 	const u16 *fa_th_src = NULL;
 
@@ -5611,7 +5611,7 @@ static void rtw89_phy_dig_config_igi(struct rtw89_dev *rtwdev)
 static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi,
 				    bool enable)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	const struct rtw89_dig_regs *dig_regs = rtwdev->chip->dig_regs;
 	enum rtw89_bandwidth cbw = chan->band_width;
 	struct rtw89_dig_info *dig = &rtwdev->dig;
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index a251b0e3b16e..a7720a1f17a7 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -800,7 +800,7 @@ static bool __rtw89_reg_6ghz_tpe_recalc(struct rtw89_dev *rtwdev)
 		const struct rtw89_reg_6ghz_tpe *tmp;
 		const struct rtw89_chan *chan;
 
-		chan = rtw89_chan_get(rtwdev, rtwvif->sub_entity_idx);
+		chan = rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 		if (chan->band_type != RTW89_BAND_6G)
 			continue;
 
@@ -872,7 +872,7 @@ static bool __rtw89_reg_6ghz_power_recalc(struct rtw89_dev *rtwdev)
 	u8 index;
 
 	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
-		chan = rtw89_chan_get(rtwdev, rtwvif->sub_entity_idx);
+		chan = rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 		if (chan->band_type != RTW89_BAND_6G)
 			continue;
 
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index b8f57a602dcf..1cbf6f8ad817 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -1810,7 +1810,7 @@ rtw8851b_init_txpwr_unit(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 static void rtw8851b_ctrl_nbtg_bt_tx(struct rtw89_dev *rtwdev, bool en,
 				     enum rtw89_phy_idx phy_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	rtw89_phy_write_reg3_tbl(rtwdev, en ? &rtw8851b_btc_preagc_en_defs_tbl :
 						 &rtw8851b_btc_preagc_dis_defs_tbl);
@@ -1833,7 +1833,7 @@ static void rtw8851b_ctrl_nbtg_bt_tx(struct rtw89_dev *rtwdev, bool en,
 static void rtw8851b_ctrl_btg_bt_rx(struct rtw89_dev *rtwdev, bool en,
 				    enum rtw89_phy_idx phy_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	if (en) {
 		rtw89_phy_write32_mask(rtwdev, R_PATH0_BT_SHARE_V1,
@@ -1878,7 +1878,7 @@ static void rtw8851b_ctrl_btg_bt_rx(struct rtw89_dev *rtwdev, bool en,
 static void rtw8851b_bb_ctrl_rx_path(struct rtw89_dev *rtwdev,
 				     enum rtw89_rf_path_bit rx_path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 rst_mask0;
 
 	if (rx_path == RF_A) {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
index a221f94627f5..1312e299e1aa 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
@@ -523,7 +523,7 @@ static void _dac_cal(struct rtw89_dev *rtwdev, bool force)
 static void _rx_dck_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			 enum rtw89_rf_path path, bool is_afe)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[RX_DCK] ==== S%d RX DCK (%s / CH%d / %s / by %s)====\n", path,
@@ -1483,7 +1483,7 @@ static void _rfk_restore_rf_reg(struct rtw89_dev *rtwdev,
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     u8 path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 idx = 0;
 
@@ -1748,7 +1748,7 @@ static void _dpk_init(struct rtw89_dev *rtwdev, enum rtw89_rf_path path)
 static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -2619,7 +2619,7 @@ static void _rck(struct rtw89_dev *rtwdev, enum rtw89_rf_path path)
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			  enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8851b_tssi_sys_defs_tbl);
@@ -2664,7 +2664,7 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -2757,7 +2757,7 @@ static void _tssi_set_dac_gain_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser_by_cond(rtwdev, band == RTW89_BAND_2G,
@@ -2768,7 +2768,7 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 static void _tssi_alignment_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				    enum rtw89_rf_path path, bool all)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser_by_cond(rtwdev, band == RTW89_BAND_2G,
@@ -2947,7 +2947,7 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			    enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 gidx, gidx_1st, gidx_2nd;
 	u8 ch = chan->channel;
 	s8 de_1st;
@@ -2983,7 +2983,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 				 enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	u8 ch = chan->channel;
 	s8 tde_1st;
@@ -3020,7 +3020,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3099,7 +3099,7 @@ static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy, enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u8 band;
 
@@ -3338,7 +3338,7 @@ void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_e
 
 void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u32 i;
 
@@ -3361,7 +3361,7 @@ void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 static void rtw8851b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 					enum rtw89_phy_idx phy, bool enable)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "======> %s   ch=%d\n",
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 88f8f2f4c6e2..e77500045327 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -1545,7 +1545,7 @@ void rtw8852a_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 			     struct rtw8852a_bb_pmac_info *tx_info,
 			     enum rtw89_phy_idx idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	if (!tx_info->en_pmac_tx) {
 		rtw8852a_stop_pmac_tx(rtwdev, tx_info, idx);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
index d86429e4a35f..b059f6ff6e8f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
@@ -1356,7 +1356,7 @@ static void _iqk_get_ch_info(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy, u8 path)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 reg_rf18 = 0x0, reg_35c = 0x0;
 	u8 idx = 0;
 	u8 get_empty_table = false;
@@ -1852,7 +1852,7 @@ static void _dpk_information(struct rtw89_dev *rtwdev,
 			     enum rtw89_rf_path path)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 kidx = dpk->cur_idx[path];
 
 	dpk->bp[path][kidx].band = chan->band_type;
@@ -2330,7 +2330,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 #define DPK_RXBB_UPPER 0x1f
 #define DPK_RXBB_LOWER 0
 #define DPK_GL_CRIT 7
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 tmp_txagc, tmp_rxbb = 0, tmp_gl_idx = 0;
 	u8 agc_cnt = 0;
 	bool limited_rxbb = false;
@@ -2521,7 +2521,7 @@ static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			      enum rtw89_rf_path path)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	bool is_reload = false;
 	u8 idx, cur_band, cur_ch;
 
@@ -2655,7 +2655,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_fem_info *fem = &rtwdev->fem;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	if (fem->epa_2g && chan->band_type == RTW89_BAND_2G) {
 		rtw89_debug(rtwdev, RTW89_DBG_RFK,
@@ -2817,7 +2817,7 @@ static void _dpk_track(struct rtw89_dev *rtwdev)
 static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (band == RTW89_BAND_2G)
@@ -2828,7 +2828,7 @@ static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8852a_tssi_sys_defs_tbl);
@@ -2840,7 +2840,7 @@ static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 static void _tssi_ini_txpwr_ctrl_bb(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				    enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser_by_cond(rtwdev, path == RF_PATH_A,
@@ -2883,7 +2883,7 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -3078,7 +3078,7 @@ static void _tssi_set_txagc_offset_mv_avg(struct rtw89_dev *rtwdev,
 static void _tssi_pak(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		      enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 subband = chan->subband_type;
 
 	switch (subband) {
@@ -3255,7 +3255,7 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			    enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
 	s8 de_1st = 0;
@@ -3293,7 +3293,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev,
 				 enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	s8 tde_1st = 0;
@@ -3332,7 +3332,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 {
 #define __DE_MASK 0x003ff000
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	static const u32 r_cck_long[RF_PATH_NUM_8852A] = {0x5858, 0x7858};
 	static const u32 r_cck_short[RF_PATH_NUM_8852A] = {0x5860, 0x7860};
 	static const u32 r_mcs_20m[RF_PATH_NUM_8852A] = {0x5838, 0x7838};
@@ -3461,7 +3461,7 @@ static void _tssi_track(struct rtw89_dev *rtwdev)
 static void _tssi_high_power(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel, ch_tmp;
 	u8 bw = chan->band_width;
 	u8 band = chan->band_type;
@@ -3508,7 +3508,7 @@ static void _tssi_hw_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static void _tssi_pre_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	const struct rtw89_chip_info *mac_reg = rtwdev->chip;
 	u8 ch = chan->channel, ch_tmp;
 	u8 bw = chan->band_width;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
index 1745c2882acf..f364e76e2b34 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
@@ -1447,7 +1447,7 @@ void rtw8852bx_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 			      struct rtw8852bx_bb_pmac_info *tx_info,
 			      enum rtw89_phy_idx idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	if (!tx_info->en_pmac_tx) {
 		rtw8852bx_stop_pmac_tx(rtwdev, tx_info, idx);
@@ -1625,7 +1625,7 @@ static
 void __rtw8852bx_bb_ctrl_rx_path(struct rtw89_dev *rtwdev,
 				 enum rtw89_rf_path_bit rx_path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 rst_mask0;
 	u32 rst_mask1;
 
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
index 12354612441c..72072042aca6 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
@@ -1384,7 +1384,7 @@ static void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u
 
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, u8 path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 reg_rf18;
 	u32 reg_35c;
@@ -1763,7 +1763,7 @@ static void _dpk_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -1788,7 +1788,7 @@ static void _dpk_bb_afe_setting(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path, u8 kpath)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	rtw89_rfk_parser(rtwdev, &rtw8852b_dpk_afe_defs_tbl);
 
@@ -1805,7 +1805,7 @@ static void _dpk_bb_afe_restore(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path, u8 kpath)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	rtw89_rfk_parser(rtwdev, &rtw8852b_dpk_afe_restore_defs_tbl);
 
@@ -2219,7 +2219,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		   enum rtw89_rf_path path, u8 kidx, u8 init_txagc,
 		   bool loss_only)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 step = DPK_AGC_STEP_SYNC_DGAIN;
 	u8 tmp_txagc, tmp_rxbb = 0, tmp_gl_idx = 0;
 	u8 goout = 0, agc_cnt = 0, limited_rxbb = 0;
@@ -2418,7 +2418,7 @@ static void _dpk_fill_result(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			      enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	bool is_reload = false;
 	u8 idx, cur_band, cur_ch;
@@ -2545,7 +2545,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 
 static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_fem_info *fem = &rtwdev->fem;
 
 	if (fem->epa_2g && chan->band_type == RTW89_BAND_2G) {
@@ -2724,7 +2724,7 @@ static void _set_dpd_backoff(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (band == RTW89_BAND_2G)
@@ -2736,7 +2736,7 @@ static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			  enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8852b_tssi_sys_defs_tbl);
@@ -2792,7 +2792,7 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -2946,7 +2946,7 @@ static void _tssi_set_dac_gain_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A)
@@ -2962,7 +2962,7 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 static void _tssi_alignment_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				    enum rtw89_rf_path path, bool all)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	const struct rtw89_rfk_tbl *tbl = NULL;
 	u8 ch = chan->channel;
@@ -3234,7 +3234,7 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			    enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
 	s8 de_1st;
@@ -3270,7 +3270,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 				 enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	s8 tde_1st;
@@ -3307,7 +3307,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3386,7 +3386,7 @@ static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy, enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u8 band;
 
@@ -3574,7 +3574,7 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	static const s16 power_2g[4] = {48, 20, 4, 4};
 	static const s16 power_5g[4] = {48, 20, 4, 4};
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	s32 tssi_alim_offset_1, tssi_alim_offset_2, tssi_alim_offset_3;
 	u32 tssi_cw_rpt[RTW8852B_TSSI_PATH_NR] = {0};
 	u8 channel = chan->channel;
@@ -3856,7 +3856,7 @@ void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_e
 
 void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	u8 channel = chan->channel;
 	u8 band;
@@ -3896,7 +3896,7 @@ void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 static void rtw8852b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 					enum rtw89_phy_idx phy, bool enable)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "======> %s   ch=%d\n",
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index e90a036db667..56ca3fea8459 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -1527,7 +1527,7 @@ static void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u
 
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, u8 path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 get_empty_table = false;
 	u32 reg_rf18;
@@ -1881,7 +1881,7 @@ static void _dpk_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -2279,7 +2279,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		   enum rtw89_rf_path path, u8 kidx, u8 init_txagc,
 		   bool loss_only)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 goout = 0, agc_cnt = 0, limited_rxbb = 0, gl_cnt = 0;
 	u8 tmp_txagc, tmp_rxbb, tmp_gl_idx = 0;
@@ -2506,7 +2506,7 @@ static void _dpk_fill_result(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			      enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 idx, cur_band, cur_ch;
 	bool is_reload = false;
@@ -2648,7 +2648,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev,
 
 static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_fem_info *fem = &rtwdev->fem;
 
 	if (fem->epa_2g && chan->band_type == RTW89_BAND_2G) {
@@ -2819,7 +2819,7 @@ static void _tssi_dpk_off(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (band == RTW89_BAND_2G)
@@ -2831,7 +2831,7 @@ static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			  enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8852bt_tssi_sys_defs_tbl);
@@ -2893,7 +2893,7 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 })
 	struct rtw89_fw_txpwr_track_cfg *trk = rtwdev->fw.elm_info.txpwr_trk;
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -3049,7 +3049,7 @@ static void _tssi_set_dac_gain_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A)
@@ -3065,7 +3065,7 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 static void _tssi_alignment_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				    enum rtw89_rf_path path, bool all)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	const struct rtw89_rfk_tbl *tbl = NULL;
 	u8 ch = chan->channel;
@@ -3313,7 +3313,7 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			    enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
 	s8 de_1st;
@@ -3349,7 +3349,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 				 enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	s8 tde_1st;
@@ -3386,7 +3386,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3466,7 +3466,7 @@ static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy, enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u8 band;
 
@@ -3655,7 +3655,7 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	static const s16 power_2g[4] = {48, 20, 4, -8};
 	static const s16 power_5g[4] = {48, 20, 4, 4};
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	s32 tssi_alim_offset_1, tssi_alim_offset_2, tssi_alim_offset_3;
 	u32 tssi_cw_rpt[RTW8852BT_TSSI_PATH_NR] = {};
 	u8 channel = chan->channel;
@@ -3934,7 +3934,7 @@ void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_
 
 void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	u8 channel = chan->channel;
 	u8 band;
@@ -3974,7 +3974,7 @@ void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 static void rtw8852bt_tssi_default_txagc(struct rtw89_dev *rtwdev,
 					 enum rtw89_phy_idx phy, bool enable)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "======> %s   ch=%d\n",
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 8e500d0eb70b..2b3921f1297e 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2117,7 +2117,7 @@ rtw8852c_init_txpwr_unit(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 static void rtw8852c_bb_cfg_rx_path(struct rtw89_dev *rtwdev, u8 rx_path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 band = chan->band_type;
 	u32 rst_mask0 = B_P0_TXPW_RSTB_MANON | B_P0_TXPW_RSTB_TSSI;
 	u32 rst_mask1 = B_P1_TXPW_RSTB_MANON | B_P1_TXPW_RSTB_TSSI;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
index 743f7014bf3e..7c529304c5b8 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
@@ -1323,7 +1323,7 @@ static void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy, u8 path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]===>%s\n", __func__);
@@ -1903,7 +1903,7 @@ static void _dpk_information(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy,
 			     enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -2497,7 +2497,7 @@ static void _dpk_idl_mpa(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			      enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	bool is_reload = false;
 	u8 idx, cur_band, cur_ch;
@@ -2758,7 +2758,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 {
 	struct rtw89_fem_info *fem = &rtwdev->fem;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 band = chan->band_type;
 
 	if (rtwdev->hal.cv == CHIP_CAV && band != RTW89_BAND_2G) {
@@ -2893,7 +2893,7 @@ static void _dpk_track(struct rtw89_dev *rtwdev)
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			  enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_bandwidth bw = chan->band_width;
 	enum rtw89_band band = chan->band_type;
 	u32 clk = 0x0;
@@ -2947,7 +2947,7 @@ static void _tssi_ini_txpwr_ctrl_bb_he_tb(struct rtw89_dev *rtwdev,
 static void _tssi_set_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			  enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A) {
@@ -2986,7 +2986,7 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -3160,7 +3160,7 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A) {
@@ -3177,7 +3177,7 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 static void _tssi_set_aligk_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				    enum rtw89_rf_path path)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	const struct rtw89_rfk_tbl *tbl;
 
@@ -3589,7 +3589,7 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			    enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
@@ -3653,7 +3653,7 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev,
 				 enum rtw89_rf_path path)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
@@ -3718,7 +3718,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 				  enum rtw89_phy_idx phy)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -4079,10 +4079,10 @@ void rtw8852c_mcc_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_i
 	mode = rtw89_get_entity_mode(rtwdev);
 	switch (mode) {
 	case RTW89_ENTITY_MODE_MCC_PREPARE:
-		chan_idx = RTW89_SUB_ENTITY_1;
+		chan_idx = RTW89_CHANCTX_1;
 		break;
 	default:
-		chan_idx = RTW89_SUB_ENTITY_0;
+		chan_idx = RTW89_CHANCTX_0;
 		break;
 	}
 
@@ -4202,7 +4202,7 @@ void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_a
 
 void rtw8852c_rx_dck_track(struct rtw89_dev *rtwdev)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_rx_dck_info *rx_dck = &rtwdev->rx_dck;
 	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
 	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index c763b14d43e9..807cc88543ce 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -1691,7 +1691,7 @@ static int rtw8922a_ctrl_rx_path_tmac(struct rtw89_dev *rtwdev,
 
 static int rtw8922a_ctrl_mlo(struct rtw89_dev *rtwdev, enum rtw89_mlo_dbcc_mode mode)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
 	if (mode == MLO_1_PLUS_1_1RF || mode == DBCC_LEGACY) {
 		rtw89_phy_write32_mask(rtwdev, R_DBCC, B_DBCC_EN, 0x1);
@@ -2118,7 +2118,7 @@ static void rtw8922a_ctrl_nbtg_bt_tx(struct rtw89_dev *rtwdev, bool en,
 
 static void rtw8922a_bb_cfg_txrx_path(struct rtw89_dev *rtwdev)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	struct rtw89_hal *hal = &rtwdev->hal;
 	u8 ntx_path = RF_PATH_AB;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
index 0ebcb06ae848..28907df7407d 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a_rfk.c
@@ -256,7 +256,7 @@ static void rtw8922a_chlk_reload(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_rfk_mcc_info *rfk_mcc = &rtwdev->rfk_mcc;
 	struct rtw89_rfk_chan_desc desc[__RTW89_RFK_CHS_NR_V1] = {};
-	enum rtw89_sub_entity_idx sub_entity_idx;
+	enum rtw89_chanctx_idx chanctx_idx;
 	const struct rtw89_chan *chan;
 	enum rtw89_entity_mode mode;
 	u8 s0_tbl, s1_tbl;
@@ -265,14 +265,14 @@ static void rtw8922a_chlk_reload(struct rtw89_dev *rtwdev)
 	mode = rtw89_get_entity_mode(rtwdev);
 	switch (mode) {
 	case RTW89_ENTITY_MODE_MCC_PREPARE:
-		sub_entity_idx = RTW89_SUB_ENTITY_1;
+		chanctx_idx = RTW89_CHANCTX_1;
 		break;
 	default:
-		sub_entity_idx = RTW89_SUB_ENTITY_0;
+		chanctx_idx = RTW89_CHANCTX_0;
 		break;
 	}
 
-	chan = rtw89_chan_get(rtwdev, sub_entity_idx);
+	chan = rtw89_chan_get(rtwdev, chanctx_idx);
 
 	for (tbl_sel = 0; tbl_sel < ARRAY_SIZE(desc); tbl_sel++) {
 		struct rtw89_rfk_chan_desc *p = &desc[tbl_sel];
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 1b2a400406ae..27826d909785 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -366,7 +366,7 @@ static void rtw89_tas_state_update(struct rtw89_dev *rtwdev)
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return;
 
-	chan = rtw89_chan_get(rtwdev, RTW89_SUB_ENTITY_0);
+	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	ret = sar_hdl->query_sar_config(rtwdev, chan->freq, &cfg);
 	if (ret)
 		return;
-- 
cgit v1.3-3-g829e


From 75d853d4ae45ee1d4af31d6ced003aab8da5db70 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:47 +0800
Subject: wifi: rtw89: pass rtwvif to RFK channel

For chips supporting multiple channels, they need to get target info
from rtwvif, e.g. PHY index and Chanctx index.

So, change rfk_channel prototype and pass rtwvif ahead.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c      | 2 +-
 drivers/net/wireless/realtek/rtw89/core.h      | 7 ++++---
 drivers/net/wireless/realtek/rtw89/mac80211.c  | 2 +-
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  | 4 ++--
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  | 4 ++--
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  | 4 ++--
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 4 ++--
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  | 4 ++--
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  | 4 ++--
 9 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index fbe94c68b171..b502bacd429b 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -3414,7 +3414,7 @@ int rtw89_core_sta_add(struct rtw89_dev *rtwdev,
 
 		rtw89_btc_ntfy_role_info(rtwdev, rtwvif, rtwsta,
 					 BTC_ROLE_MSTS_STA_CONN_START);
-		rtw89_chip_rfk_channel(rtwdev);
+		rtw89_chip_rfk_channel(rtwdev, rtwvif);
 	} else if (vif->type == NL80211_IFTYPE_AP || sta->tdls) {
 		rtwsta->mac_id = rtw89_acquire_mac_id(rtwdev);
 		if (rtwsta->mac_id == RTW89_MAX_MAC_ID_NUM)
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index d43a30ae3181..9fe3762951a8 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3540,7 +3540,7 @@ struct rtw89_chip_ops {
 	void (*rfk_hw_init)(struct rtw89_dev *rtwdev);
 	void (*rfk_init)(struct rtw89_dev *rtwdev);
 	void (*rfk_init_late)(struct rtw89_dev *rtwdev);
-	void (*rfk_channel)(struct rtw89_dev *rtwdev);
+	void (*rfk_channel)(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
 	void (*rfk_band_changed)(struct rtw89_dev *rtwdev,
 				 enum rtw89_phy_idx phy_idx);
 	void (*rfk_scan)(struct rtw89_dev *rtwdev, bool start);
@@ -6151,12 +6151,13 @@ static inline void rtw89_chip_rfk_init_late(struct rtw89_dev *rtwdev)
 		chip->ops->rfk_init_late(rtwdev);
 }
 
-static inline void rtw89_chip_rfk_channel(struct rtw89_dev *rtwdev)
+static inline void rtw89_chip_rfk_channel(struct rtw89_dev *rtwdev,
+					  struct rtw89_vif *rtwvif)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 
 	if (chip->ops->rfk_channel)
-		chip->ops->rfk_channel(rtwdev);
+		chip->ops->rfk_channel(rtwdev, rtwvif);
 }
 
 static inline void rtw89_chip_rfk_band_changed(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 95cff2a8a337..ed7990a2827b 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -519,7 +519,7 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 	rtw89_fw_h2c_role_maintain(rtwdev, rtwvif, NULL, RTW89_ROLE_TYPE_CHANGE);
 	rtw89_fw_h2c_join_info(rtwdev, rtwvif, NULL, true);
 	rtw89_fw_h2c_cam(rtwdev, rtwvif, NULL, NULL);
-	rtw89_chip_rfk_channel(rtwdev);
+	rtw89_chip_rfk_channel(rtwdev, rtwvif);
 
 	rtw89_queue_chanctx_work(rtwdev);
 	mutex_unlock(&rtwdev->mutex);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 1cbf6f8ad817..8cbbe10cb095 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -1590,9 +1590,9 @@ static void rtw8851b_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8851b_rx_dck(rtwdev, RTW89_PHY_0);
 }
 
-static void rtw8851b_rfk_channel(struct rtw89_dev *rtwdev)
+static void rtw8851b_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
 	rtw8851b_rx_dck(rtwdev, phy_idx);
 	rtw8851b_iqk(rtwdev, phy_idx);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index e77500045327..5405a883d74a 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -1345,9 +1345,9 @@ static void rtw8852a_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8852a_rx_dck(rtwdev, RTW89_PHY_0, true);
 }
 
-static void rtw8852a_rfk_channel(struct rtw89_dev *rtwdev)
+static void rtw8852a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
 	rtw8852a_rx_dck(rtwdev, phy_idx, true);
 	rtw8852a_iqk(rtwdev, phy_idx);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index ef888545d988..ec74afad32da 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -562,9 +562,9 @@ static void rtw8852b_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8852b_rx_dck(rtwdev, RTW89_PHY_0);
 }
 
-static void rtw8852b_rfk_channel(struct rtw89_dev *rtwdev)
+static void rtw8852b_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
 	rtw8852b_rx_dck(rtwdev, phy_idx);
 	rtw8852b_iqk(rtwdev, phy_idx);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 8173063bcc8e..733876d4bb59 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -535,9 +535,9 @@ static void rtw8852bt_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8852bt_rx_dck(rtwdev, RTW89_PHY_0);
 }
 
-static void rtw8852bt_rfk_channel(struct rtw89_dev *rtwdev)
+static void rtw8852bt_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
 	rtw8852bt_rx_dck(rtwdev, phy_idx);
 	rtw8852bt_iqk(rtwdev, phy_idx);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 2b3921f1297e..f14e320feac0 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -1846,9 +1846,9 @@ static void rtw8852c_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8852c_rx_dck(rtwdev, RTW89_PHY_0, false);
 }
 
-static void rtw8852c_rfk_channel(struct rtw89_dev *rtwdev)
+static void rtw8852c_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
 	rtw8852c_mcc_get_ch_info(rtwdev, phy_idx);
 	rtw8852c_rx_dck(rtwdev, phy_idx, false);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 807cc88543ce..9b9a1dd11d4f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -1962,9 +1962,9 @@ static void _wait_rx_mode(struct rtw89_dev *rtwdev, u8 kpath)
 	}
 }
 
-static void rtw8922a_rfk_channel(struct rtw89_dev *rtwdev)
+static void rtw8922a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
-	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
+	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
 	u32 tx_en;
 
-- 
cgit v1.3-3-g829e


From ed5f66a2812025a6818e12f07686735d0fe8580f Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:48 +0800
Subject: wifi: rtw89: pass rtwvif to RFK scan

For chips supporting multiple channels, they need to get target info
from rtwvif, e.g. PHY index and Chanctx index.

So, change rfk_scan prototype and pass rtwvif ahead.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c      | 4 ++--
 drivers/net/wireless/realtek/rtw89/core.h      | 8 +++++---
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  | 5 +++--
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  | 5 +++--
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  | 5 +++--
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 5 +++--
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  | 5 +++--
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  | 3 ++-
 8 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index b502bacd429b..894b03d77a05 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4372,7 +4372,7 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 
 	ether_addr_copy(rtwvif->mac_addr, mac_addr);
 	rtw89_btc_ntfy_scan_start(rtwdev, RTW89_PHY_0, chan->band_type);
-	rtw89_chip_rfk_scan(rtwdev, true);
+	rtw89_chip_rfk_scan(rtwdev, rtwvif, true);
 	rtw89_hci_recalc_int_mit(rtwdev);
 	rtw89_phy_config_edcca(rtwdev, true);
 
@@ -4390,7 +4390,7 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 	ether_addr_copy(rtwvif->mac_addr, vif->addr);
 	rtw89_fw_h2c_cam(rtwdev, rtwvif, NULL, NULL);
 
-	rtw89_chip_rfk_scan(rtwdev, false);
+	rtw89_chip_rfk_scan(rtwdev, rtwvif, false);
 	rtw89_btc_ntfy_scan_finish(rtwdev, RTW89_PHY_0);
 	rtw89_phy_config_edcca(rtwdev, false);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 9fe3762951a8..fc31655d9e7c 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3543,7 +3543,8 @@ struct rtw89_chip_ops {
 	void (*rfk_channel)(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
 	void (*rfk_band_changed)(struct rtw89_dev *rtwdev,
 				 enum rtw89_phy_idx phy_idx);
-	void (*rfk_scan)(struct rtw89_dev *rtwdev, bool start);
+	void (*rfk_scan)(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			 bool start);
 	void (*rfk_track)(struct rtw89_dev *rtwdev);
 	void (*power_trim)(struct rtw89_dev *rtwdev);
 	void (*set_txpwr)(struct rtw89_dev *rtwdev,
@@ -6169,12 +6170,13 @@ static inline void rtw89_chip_rfk_band_changed(struct rtw89_dev *rtwdev,
 		chip->ops->rfk_band_changed(rtwdev, phy_idx);
 }
 
-static inline void rtw89_chip_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static inline void rtw89_chip_rfk_scan(struct rtw89_dev *rtwdev,
+				       struct rtw89_vif *rtwvif, bool start)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 
 	if (chip->ops->rfk_scan)
-		chip->ops->rfk_scan(rtwdev, start);
+		chip->ops->rfk_scan(rtwdev, rtwvif, start);
 }
 
 static inline void rtw89_chip_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 8cbbe10cb095..cfaea0193d35 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -1606,9 +1606,10 @@ static void rtw8851b_rfk_band_changed(struct rtw89_dev *rtwdev,
 	rtw8851b_tssi_scan(rtwdev, phy_idx);
 }
 
-static void rtw8851b_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static void rtw8851b_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			      bool start)
 {
-	rtw8851b_wifi_scan_notify(rtwdev, start, RTW89_PHY_0);
+	rtw8851b_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
 }
 
 static void rtw8851b_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 5405a883d74a..ec9f7bc5c6d2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -1361,9 +1361,10 @@ static void rtw8852a_rfk_band_changed(struct rtw89_dev *rtwdev,
 	rtw8852a_tssi_scan(rtwdev, phy_idx);
 }
 
-static void rtw8852a_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static void rtw8852a_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			      bool start)
 {
-	rtw8852a_wifi_scan_notify(rtwdev, start, RTW89_PHY_0);
+	rtw8852a_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
 }
 
 static void rtw8852a_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index ec74afad32da..71c166202560 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -578,9 +578,10 @@ static void rtw8852b_rfk_band_changed(struct rtw89_dev *rtwdev,
 	rtw8852b_tssi_scan(rtwdev, phy_idx);
 }
 
-static void rtw8852b_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static void rtw8852b_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			      bool start)
 {
-	rtw8852b_wifi_scan_notify(rtwdev, start, RTW89_PHY_0);
+	rtw8852b_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
 }
 
 static void rtw8852b_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 733876d4bb59..9aa2106a64b7 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -551,9 +551,10 @@ static void rtw8852bt_rfk_band_changed(struct rtw89_dev *rtwdev,
 	rtw8852bt_tssi_scan(rtwdev, phy_idx);
 }
 
-static void rtw8852bt_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static void rtw8852bt_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			       bool start)
 {
-	rtw8852bt_wifi_scan_notify(rtwdev, start, RTW89_PHY_0);
+	rtw8852bt_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
 }
 
 static void rtw8852bt_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index f14e320feac0..e0c1cf8811a2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -1864,9 +1864,10 @@ static void rtw8852c_rfk_band_changed(struct rtw89_dev *rtwdev,
 	rtw8852c_tssi_scan(rtwdev, phy_idx);
 }
 
-static void rtw8852c_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static void rtw8852c_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			      bool start)
 {
-	rtw8852c_wifi_scan_notify(rtwdev, start, RTW89_PHY_0);
+	rtw8852c_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
 }
 
 static void rtw8852c_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 9b9a1dd11d4f..6aa706d8a420 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -1989,7 +1989,8 @@ static void rtw8922a_rfk_band_changed(struct rtw89_dev *rtwdev,
 	rtw89_phy_rfk_tssi_and_wait(rtwdev, phy_idx, RTW89_TSSI_SCAN, 6);
 }
 
-static void rtw8922a_rfk_scan(struct rtw89_dev *rtwdev, bool start)
+static void rtw8922a_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			      bool start)
 {
 }
 
-- 
cgit v1.3-3-g829e


From db0dbe26f48a4cf3a46967fb8a75ee1abd1d59ab Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:49 +0800
Subject: wifi: rtw89: fw: correct chan access in assoc_cmac_tbl_g7 and
 update_beacon_be

Originally, these H2C commands access chan with hard-code RTW89_CHANCTX_0.
They are problematic when the chip supports multiple channels. So, correct
them by accessing right chan under rtwvif.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 1db32418e912..b9bf9ae3a512 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -2947,9 +2947,9 @@ int rtw89_fw_h2c_assoc_cmac_tbl_g7(struct rtw89_dev *rtwdev,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta_safe(sta);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 	u8 mac_id = rtwsta ? rtwsta->mac_id : rtwvif->mac_id;
 	struct rtw89_h2c_cctlinfo_ud_g7 *h2c;
 	u8 pads[RTW89_PPE_BW_NUM];
@@ -3289,7 +3289,7 @@ EXPORT_SYMBOL(rtw89_fw_h2c_update_beacon);
 int rtw89_fw_h2c_update_beacon_be(struct rtw89_dev *rtwdev,
 				  struct rtw89_vif *rtwvif)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, rtwvif->chanctx_idx);
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 	struct rtw89_h2c_bcn_upd_be *h2c;
 	struct sk_buff *skb_beacon;
-- 
cgit v1.3-3-g829e


From 11b227901ffaf9f6b4eebd3ed708d03ec91e764c Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Sat, 27 Jul 2024 16:06:50 +0800
Subject: wifi: rtw89: pass chanctx_idx to rtw89_btc_{path_}phymap()

Originally, rtw89_btc_phymap() and rtw89_btc_path_phymap() access chan
with hard-code RTW89_CHANCTX_0. But, they are problematic when the chip
supports multiple channels.

So, change their prototype and pass chanctx_idx ahead. Let callers still
pass RTW89_CHANCTX_0 for now, but we will refine callers in the following.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240727080650.12195-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.h          | 10 ++++++----
 drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c  | 10 +++++-----
 drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c  | 20 ++++++++++----------
 drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c  | 12 ++++++------
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c | 10 +++++-----
 drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c  | 12 ++++++------
 drivers/net/wireless/realtek/rtw89/rtw8922a.c      |  2 +-
 7 files changed, 39 insertions(+), 37 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index 72e3c77d2a3a..de53b56632f7 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -291,9 +291,10 @@ void rtw89_coex_recognize_ver(struct rtw89_dev *rtwdev);
 
 static inline u8 rtw89_btc_phymap(struct rtw89_dev *rtwdev,
 				  enum rtw89_phy_idx phy_idx,
-				  enum rtw89_rf_path_bit paths)
+				  enum rtw89_rf_path_bit paths,
+				  enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 phy_map;
 
 	phy_map = FIELD_PREP(BTC_RFK_PATH_MAP, paths) |
@@ -305,9 +306,10 @@ static inline u8 rtw89_btc_phymap(struct rtw89_dev *rtwdev,
 
 static inline u8 rtw89_btc_path_phymap(struct rtw89_dev *rtwdev,
 				       enum rtw89_phy_idx phy_idx,
-				       enum rtw89_rf_path path)
+				       enum rtw89_rf_path path,
+				       enum rtw89_chanctx_idx chanctx_idx)
 {
-	return rtw89_btc_phymap(rtwdev, phy_idx, BIT(path));
+	return rtw89_btc_phymap(rtwdev, phy_idx, BIT(path), chanctx_idx);
 }
 
 /* return bt req len in TU */
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
index 1312e299e1aa..7942f334066c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
@@ -1589,7 +1589,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 		   enum rtw89_phy_idx phy_idx, u8 path)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
 	u32 backup_rf_val[RTW8851B_IQK_SS][BACKUP_RF_REGS_NR];
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 
@@ -3257,7 +3257,7 @@ void rtw8851b_dack(struct rtw89_dev *rtwdev)
 
 void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
@@ -3273,7 +3273,7 @@ void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 void rtw8851b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
@@ -3288,7 +3288,7 @@ void rtw8851b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 void rtw8851b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
@@ -3310,7 +3310,7 @@ void rtw8851b_dpk_track(struct rtw89_dev *rtwdev)
 
 void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_A);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_A, RTW89_CHANCTX_0);
 	u8 i;
 
 	rtw89_debug(rtwdev, RTW89_DBG_TSSI, "[TSSI] %s: phy=%d\n", __func__, phy);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
index b059f6ff6e8f..6bae8bc07e93 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
@@ -497,7 +497,7 @@ static void _dac_cal(struct rtw89_dev *rtwdev, bool force)
 {
 	struct rtw89_dack_info *dack = &rtwdev->dack;
 	u32 rf0_0, rf1_0;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB, RTW89_CHANCTX_0);
 
 	dack->dack_done = false;
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]DACK b\n");
@@ -804,7 +804,7 @@ static bool _iqk_one_shot(struct rtw89_dev *rtwdev,
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	bool fail = false;
 	u32 iqk_cmd = 0x0;
-	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy_idx, path);
+	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy_idx, path, RTW89_CHANCTX_0);
 	u32 addr_rfc_ctl = 0x0;
 
 	if (path == RF_PATH_A)
@@ -1612,7 +1612,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852A_IQK_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -1658,7 +1658,7 @@ static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool forc
 static void _set_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			enum rtw89_rf_path path, bool is_afe)
 {
-	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy, path);
+	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy, path, RTW89_CHANCTX_0);
 	u32 ori_val;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
@@ -1802,7 +1802,7 @@ static void _dpk_reload_kip(struct rtw89_dev *rtwdev, u32 *reg,
 static u8 _dpk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			enum rtw89_rf_path path, enum rtw8852a_dpk_id id)
 {
-	u8 phy_map  = rtw89_btc_path_phymap(rtwdev, phy, path);
+	u8 phy_map  = rtw89_btc_path_phymap(rtwdev, phy, path, RTW89_CHANCTX_0);
 	u16 dpk_cmd = 0x0;
 	u32 val;
 	int ret;
@@ -3514,7 +3514,7 @@ static void _tssi_pre_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	u8 bw = chan->band_width;
 	u8 band = chan->band_type;
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, 0, RTW89_CHANCTX_0);
 	s8 power;
 	s16 xdbm;
 	u32 i, tx_counter = 0;
@@ -3602,7 +3602,7 @@ void rtw8852a_rck(struct rtw89_dev *rtwdev)
 
 void rtw8852a_dack(struct rtw89_dev *rtwdev)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
 	_dac_cal(rtwdev, false);
@@ -3612,7 +3612,7 @@ void rtw8852a_dack(struct rtw89_dev *rtwdev)
 void rtw8852a_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
@@ -3632,7 +3632,7 @@ void rtw8852a_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
 		     bool is_afe)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
@@ -3647,7 +3647,7 @@ void rtw8852a_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
 void rtw8852a_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
index 72072042aca6..776a45d1fe33 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
@@ -1613,7 +1613,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852B_IQK_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -3757,7 +3757,7 @@ void rtw8852b_rck(struct rtw89_dev *rtwdev)
 
 void rtw8852b_dack(struct rtw89_dev *rtwdev)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
 	_dac_cal(rtwdev, false);
@@ -3766,7 +3766,7 @@ void rtw8852b_dack(struct rtw89_dev *rtwdev)
 
 void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
@@ -3782,7 +3782,7 @@ void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
@@ -3797,7 +3797,7 @@ void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 void rtw8852b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
@@ -3819,7 +3819,7 @@ void rtw8852b_dpk_track(struct rtw89_dev *rtwdev)
 
 void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB, RTW89_CHANCTX_0);
 	u32 tx_en;
 	u8 i;
 
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index 56ca3fea8459..278f907fd895 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -1760,7 +1760,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852BT_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -3835,7 +3835,7 @@ void rtw8852bt_rck(struct rtw89_dev *rtwdev)
 
 void rtw8852bt_dack(struct rtw89_dev *rtwdev)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
 	_dac_cal(rtwdev, false);
@@ -3844,7 +3844,7 @@ void rtw8852bt_dack(struct rtw89_dev *rtwdev)
 
 void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
@@ -3860,7 +3860,7 @@ void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 void rtw8852bt_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
@@ -3892,7 +3892,7 @@ void rtw8852bt_dpk_track(struct rtw89_dev *rtwdev)
 void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en)
 {
 	static const u32 reg[2] = {R_DPD_CH0A, R_DPD_CH0B};
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB, RTW89_CHANCTX_0);
 	u32 reg_backup[2] = {};
 	u32 tx_en;
 	u8 i;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
index 7c529304c5b8..6e199e82690b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
@@ -588,7 +588,7 @@ static void _dac_cal(struct rtw89_dev *rtwdev, bool force)
 {
 	struct rtw89_dack_info *dack = &rtwdev->dack;
 	u32 rf0_0, rf1_0;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB, RTW89_CHANCTX_0);
 
 	dack->dack_done = false;
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]DACK b\n");
@@ -1521,7 +1521,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852C_IQK_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -4114,7 +4114,7 @@ void rtw8852c_rck(struct rtw89_dev *rtwdev)
 
 void rtw8852c_dack(struct rtw89_dev *rtwdev)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
 	_dac_cal(rtwdev, false);
@@ -4124,7 +4124,7 @@ void rtw8852c_dack(struct rtw89_dev *rtwdev)
 void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
@@ -4205,7 +4205,7 @@ void rtw8852c_rx_dck_track(struct rtw89_dev *rtwdev)
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_rx_dck_info *rx_dck = &rtwdev->rx_dck;
 	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 	u8 dck_channel;
 	u8 cur_thermal;
 	u32 tx_en;
@@ -4262,7 +4262,7 @@ void rtw8852c_dpk_init(struct rtw89_dev *rtwdev)
 void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 6aa706d8a420..8921a1b9e791 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -1965,7 +1965,7 @@ static void _wait_rx_mode(struct rtw89_dev *rtwdev, u8 kpath)
 static void rtw8922a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_CHLK, BTC_WRFK_START);
-- 
cgit v1.3-3-g829e


From 744500d81f81346b4d442809c0511684bb28c829 Mon Sep 17 00:00:00 2001
From: Luigi Leonardi <luigi.leonardi@outlook.com>
Date: Tue, 30 Jul 2024 21:43:06 +0200
Subject: vsock: add support for SIOCOUTQ ioctl

Add support for ioctl(s) in AF_VSOCK.
The only ioctl available is SIOCOUTQ/TIOCOUTQ, which returns the number
of unsent bytes in the socket. This information is transport-specific
and is delegated to them using a callback.

Suggested-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Signed-off-by: Luigi Leonardi <luigi.leonardi@outlook.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/af_vsock.h   |  3 +++
 net/vmw_vsock/af_vsock.c | 58 +++++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 58 insertions(+), 3 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 535701efc1e5..fc504d2da3d0 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -169,6 +169,9 @@ struct vsock_transport {
 	void (*notify_buffer_size)(struct vsock_sock *, u64 *);
 	int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
 
+	/* SIOCOUTQ ioctl */
+	ssize_t (*unsent_bytes)(struct vsock_sock *vsk);
+
 	/* Shutdown. */
 	int (*shutdown)(struct vsock_sock *, int);
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 4b040285aa78..58e639e82942 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -112,6 +112,7 @@
 #include <net/sock.h>
 #include <net/af_vsock.h>
 #include <uapi/linux/vm_sockets.h>
+#include <uapi/asm-generic/ioctls.h>
 
 static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
 static void vsock_sk_destruct(struct sock *sk);
@@ -1292,6 +1293,57 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 }
 EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
 
+static int vsock_do_ioctl(struct socket *sock, unsigned int cmd,
+			  int __user *arg)
+{
+	struct sock *sk = sock->sk;
+	struct vsock_sock *vsk;
+	int ret;
+
+	vsk = vsock_sk(sk);
+
+	switch (cmd) {
+	case SIOCOUTQ: {
+		ssize_t n_bytes;
+
+		if (!vsk->transport || !vsk->transport->unsent_bytes) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) {
+			ret = -EINVAL;
+			break;
+		}
+
+		n_bytes = vsk->transport->unsent_bytes(vsk);
+		if (n_bytes < 0) {
+			ret = n_bytes;
+			break;
+		}
+
+		ret = put_user(n_bytes, arg);
+		break;
+	}
+	default:
+		ret = -ENOIOCTLCMD;
+	}
+
+	return ret;
+}
+
+static int vsock_ioctl(struct socket *sock, unsigned int cmd,
+		       unsigned long arg)
+{
+	int ret;
+
+	lock_sock(sock->sk);
+	ret = vsock_do_ioctl(sock, cmd, (int __user *)arg);
+	release_sock(sock->sk);
+
+	return ret;
+}
+
 static const struct proto_ops vsock_dgram_ops = {
 	.family = PF_VSOCK,
 	.owner = THIS_MODULE,
@@ -1302,7 +1354,7 @@ static const struct proto_ops vsock_dgram_ops = {
 	.accept = sock_no_accept,
 	.getname = vsock_getname,
 	.poll = vsock_poll,
-	.ioctl = sock_no_ioctl,
+	.ioctl = vsock_ioctl,
 	.listen = sock_no_listen,
 	.shutdown = vsock_shutdown,
 	.sendmsg = vsock_dgram_sendmsg,
@@ -2286,7 +2338,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.accept = vsock_accept,
 	.getname = vsock_getname,
 	.poll = vsock_poll,
-	.ioctl = sock_no_ioctl,
+	.ioctl = vsock_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
 	.setsockopt = vsock_connectible_setsockopt,
@@ -2308,7 +2360,7 @@ static const struct proto_ops vsock_seqpacket_ops = {
 	.accept = vsock_accept,
 	.getname = vsock_getname,
 	.poll = vsock_poll,
-	.ioctl = sock_no_ioctl,
+	.ioctl = vsock_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
 	.setsockopt = vsock_connectible_setsockopt,
-- 
cgit v1.3-3-g829e


From e6ab45005772014ce49a693a63f928203c0cbbb0 Mon Sep 17 00:00:00 2001
From: Luigi Leonardi <luigi.leonardi@outlook.com>
Date: Tue, 30 Jul 2024 21:43:07 +0200
Subject: vsock/virtio: add SIOCOUTQ support for all virtio based transports

Introduce support for virtio_transport_unsent_bytes
ioctl for virtio_transport, vhost_vsock and vsock_loopback.

For all transports the unsent bytes counter is incremented
in virtio_transport_get_credit.

In virtio_transport (G2H) and in vhost-vsock (H2G) the counter
is decremented when the skbuff is consumed. In vsock_loopback the
same skbuff is passed from the transmitter to the receiver, so
the counter is decremented before queuing the skbuff to the
receiver.

Signed-off-by: Luigi Leonardi <luigi.leonardi@outlook.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vsock.c                   |  4 +++-
 include/linux/virtio_vsock.h            |  6 ++++++
 net/vmw_vsock/virtio_transport.c        |  4 +++-
 net/vmw_vsock/virtio_transport_common.c | 35 +++++++++++++++++++++++++++++++++
 net/vmw_vsock/vsock_loopback.c          |  6 ++++++
 5 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index bf664ec9341b..802153e23073 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -244,7 +244,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 					restart_tx = true;
 			}
 
-			consume_skb(skb);
+			virtio_transport_consume_skb_sent(skb, true);
 		}
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
@@ -451,6 +451,8 @@ static struct virtio_transport vhost_transport = {
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
 		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
+		.unsent_bytes             = virtio_transport_unsent_bytes,
+
 		.read_skb = virtio_transport_read_skb,
 	},
 
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index c82089dee0c8..0387d64e2c66 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -133,6 +133,7 @@ struct virtio_vsock_sock {
 	u32 tx_cnt;
 	u32 peer_fwd_cnt;
 	u32 peer_buf_alloc;
+	size_t bytes_unsent;
 
 	/* Protected by rx_lock */
 	u32 fwd_cnt;
@@ -193,6 +194,11 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
 u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk);
 
+ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk);
+
+void virtio_transport_consume_skb_sent(struct sk_buff *skb,
+				       bool consume);
+
 int virtio_transport_do_socket_init(struct vsock_sock *vsk,
 				 struct vsock_sock *psk);
 int
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 64a07acfef12..e0160da4ef43 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -311,7 +311,7 @@ static void virtio_transport_tx_work(struct work_struct *work)
 
 		virtqueue_disable_cb(vq);
 		while ((skb = virtqueue_get_buf(vq, &len)) != NULL) {
-			consume_skb(skb);
+			virtio_transport_consume_skb_sent(skb, true);
 			added = true;
 		}
 	} while (!virtqueue_enable_cb(vq));
@@ -540,6 +540,8 @@ static struct virtio_transport virtio_transport = {
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
 		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
+		.unsent_bytes             = virtio_transport_unsent_bytes,
+
 		.read_skb = virtio_transport_read_skb,
 	},
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 16ff976a86e3..884ee128851e 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -463,6 +463,26 @@ void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *
 }
 EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt);
 
+void virtio_transport_consume_skb_sent(struct sk_buff *skb, bool consume)
+{
+	struct sock *s = skb->sk;
+
+	if (s && skb->len) {
+		struct vsock_sock *vs = vsock_sk(s);
+		struct virtio_vsock_sock *vvs;
+
+		vvs = vs->trans;
+
+		spin_lock_bh(&vvs->tx_lock);
+		vvs->bytes_unsent -= skb->len;
+		spin_unlock_bh(&vvs->tx_lock);
+	}
+
+	if (consume)
+		consume_skb(skb);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_consume_skb_sent);
+
 u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit)
 {
 	u32 ret;
@@ -475,6 +495,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit)
 	if (ret > credit)
 		ret = credit;
 	vvs->tx_cnt += ret;
+	vvs->bytes_unsent += ret;
 	spin_unlock_bh(&vvs->tx_lock);
 
 	return ret;
@@ -488,6 +509,7 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit)
 
 	spin_lock_bh(&vvs->tx_lock);
 	vvs->tx_cnt -= credit;
+	vvs->bytes_unsent -= credit;
 	spin_unlock_bh(&vvs->tx_lock);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_put_credit);
@@ -1090,6 +1112,19 @@ void virtio_transport_destruct(struct vsock_sock *vsk)
 }
 EXPORT_SYMBOL_GPL(virtio_transport_destruct);
 
+ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	size_t ret;
+
+	spin_lock_bh(&vvs->tx_lock);
+	ret = vvs->bytes_unsent;
+	spin_unlock_bh(&vvs->tx_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_unsent_bytes);
+
 static int virtio_transport_reset(struct vsock_sock *vsk,
 				  struct sk_buff *skb)
 {
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 6dea6119f5b2..6e78927a598e 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -98,6 +98,8 @@ static struct virtio_transport loopback_transport = {
 		.notify_buffer_size       = virtio_transport_notify_buffer_size,
 		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
 
+		.unsent_bytes             = virtio_transport_unsent_bytes,
+
 		.read_skb = virtio_transport_read_skb,
 	},
 
@@ -123,6 +125,10 @@ static void vsock_loopback_work(struct work_struct *work)
 	spin_unlock_bh(&vsock->pkt_queue.lock);
 
 	while ((skb = __skb_dequeue(&pkts))) {
+		/* Decrement the bytes_unsent counter without deallocating skb
+		 * It is freed by the receiver.
+		 */
+		virtio_transport_consume_skb_sent(skb, false);
 		virtio_transport_deliver_tap_pkt(skb);
 		virtio_transport_recv_pkt(&loopback_transport, skb);
 	}
-- 
cgit v1.3-3-g829e


From 18ee44ce97c18ee72f5807140d07ff8cebe3cab5 Mon Sep 17 00:00:00 2001
From: Luigi Leonardi <luigi.leonardi@outlook.com>
Date: Tue, 30 Jul 2024 21:43:08 +0200
Subject: test/vsock: add ioctl unsent bytes test

Introduce two tests, one for SOCK_STREAM and one for SOCK_SEQPACKET,
which use SIOCOUTQ ioctl to check that the number of unsent bytes is
zero after delivering a packet.

vsock_connect and vsock_accept are no longer static: this is to
create more generic tests, allowing code to be reused for SEQPACKET
and STREAM.

Signed-off-by: Luigi Leonardi <luigi.leonardi@outlook.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/vsock/util.c       |  6 +--
 tools/testing/vsock/util.h       |  3 ++
 tools/testing/vsock/vsock_test.c | 85 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 91 insertions(+), 3 deletions(-)

diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 554b290fefdc..a3d448a075e3 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -139,7 +139,7 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po
 }
 
 /* Connect to <cid, port> and return the file descriptor. */
-static int vsock_connect(unsigned int cid, unsigned int port, int type)
+int vsock_connect(unsigned int cid, unsigned int port, int type)
 {
 	union {
 		struct sockaddr sa;
@@ -226,8 +226,8 @@ static int vsock_listen(unsigned int cid, unsigned int port, int type)
 /* Listen on <cid, port> and return the first incoming connection.  The remote
  * address is stored to clientaddrp.  clientaddrp may be NULL.
  */
-static int vsock_accept(unsigned int cid, unsigned int port,
-			struct sockaddr_vm *clientaddrp, int type)
+int vsock_accept(unsigned int cid, unsigned int port,
+		 struct sockaddr_vm *clientaddrp, int type)
 {
 	union {
 		struct sockaddr sa;
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index e95e62485959..fff22d4a14c0 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -39,6 +39,9 @@ struct test_case {
 void init_signals(void);
 unsigned int parse_cid(const char *str);
 unsigned int parse_port(const char *str);
+int vsock_connect(unsigned int cid, unsigned int port, int type);
+int vsock_accept(unsigned int cid, unsigned int port,
+		 struct sockaddr_vm *clientaddrp, int type);
 int vsock_stream_connect(unsigned int cid, unsigned int port);
 int vsock_bind_connect(unsigned int cid, unsigned int port,
 		       unsigned int bind_port, int type);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index f851f8961247..8d38dbf8f41f 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -20,6 +20,8 @@
 #include <sys/mman.h>
 #include <poll.h>
 #include <signal.h>
+#include <sys/ioctl.h>
+#include <linux/sockios.h>
 
 #include "vsock_test_zerocopy.h"
 #include "timeout.h"
@@ -1238,6 +1240,79 @@ static void test_double_bind_connect_client(const struct test_opts *opts)
 	}
 }
 
+#define MSG_BUF_IOCTL_LEN 64
+static void test_unsent_bytes_server(const struct test_opts *opts, int type)
+{
+	unsigned char buf[MSG_BUF_IOCTL_LEN];
+	int client_fd;
+
+	client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type);
+	if (client_fd < 0) {
+		perror("accept");
+		exit(EXIT_FAILURE);
+	}
+
+	recv_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf));
+	control_writeln("RECEIVED");
+
+	close(client_fd);
+}
+
+static void test_unsent_bytes_client(const struct test_opts *opts, int type)
+{
+	unsigned char buf[MSG_BUF_IOCTL_LEN];
+	int ret, fd, sock_bytes_unsent;
+
+	fd = vsock_connect(opts->peer_cid, opts->peer_port, type);
+	if (fd < 0) {
+		perror("connect");
+		exit(EXIT_FAILURE);
+	}
+
+	for (int i = 0; i < sizeof(buf); i++)
+		buf[i] = rand() & 0xFF;
+
+	send_buf(fd, buf, sizeof(buf), 0, sizeof(buf));
+	control_expectln("RECEIVED");
+
+	ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent);
+	if (ret < 0) {
+		if (errno == EOPNOTSUPP) {
+			fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n");
+		} else {
+			perror("ioctl");
+			exit(EXIT_FAILURE);
+		}
+	} else if (ret == 0 && sock_bytes_unsent != 0) {
+		fprintf(stderr,
+			"Unexpected 'SIOCOUTQ' value, expected 0, got %i\n",
+			sock_bytes_unsent);
+		exit(EXIT_FAILURE);
+	}
+
+	close(fd);
+}
+
+static void test_stream_unsent_bytes_client(const struct test_opts *opts)
+{
+	test_unsent_bytes_client(opts, SOCK_STREAM);
+}
+
+static void test_stream_unsent_bytes_server(const struct test_opts *opts)
+{
+	test_unsent_bytes_server(opts, SOCK_STREAM);
+}
+
+static void test_seqpacket_unsent_bytes_client(const struct test_opts *opts)
+{
+	test_unsent_bytes_client(opts, SOCK_SEQPACKET);
+}
+
+static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts)
+{
+	test_unsent_bytes_server(opts, SOCK_SEQPACKET);
+}
+
 #define RCVLOWAT_CREDIT_UPD_BUF_SIZE	(1024 * 128)
 /* This define is the same as in 'include/linux/virtio_vsock.h':
  * it is used to decide when to send credit update message during
@@ -1523,6 +1598,16 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_rcvlowat_def_cred_upd_client,
 		.run_server = test_stream_cred_upd_on_low_rx_bytes,
 	},
+	{
+		.name = "SOCK_STREAM ioctl(SIOCOUTQ) 0 unsent bytes",
+		.run_client = test_stream_unsent_bytes_client,
+		.run_server = test_stream_unsent_bytes_server,
+	},
+	{
+		.name = "SOCK_SEQPACKET ioctl(SIOCOUTQ) 0 unsent bytes",
+		.run_client = test_seqpacket_unsent_bytes_client,
+		.run_server = test_seqpacket_unsent_bytes_server,
+	},
 	{},
 };
 
-- 
cgit v1.3-3-g829e


From 3ff578c91cd86461b58561e19cce087e8899d0ce Mon Sep 17 00:00:00 2001
From: Appana Durga Kedareswara Rao <appana.durga.rao@xilinx.com>
Date: Wed, 31 Jul 2024 14:46:04 +0530
Subject: net: axienet: Replace the occurrences of (1<<x) by BIT(x)

Replace all occurences of (1<<x) by BIT(x) to get rid of checkpatch.pl
"CHECK" output "Prefer using the BIT macro".

Signed-off-by: Appana Durga Kedareswara Rao <appana.durga.rao@xilinx.com>
Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index fa5500decc96..0d5b300107e0 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -29,26 +29,26 @@
 /* Configuration options */
 
 /* Accept all incoming packets. Default: disabled (cleared) */
-#define XAE_OPTION_PROMISC			(1 << 0)
+#define XAE_OPTION_PROMISC			BIT(0)
 
 /* Jumbo frame support for Tx & Rx. Default: disabled (cleared) */
-#define XAE_OPTION_JUMBO			(1 << 1)
+#define XAE_OPTION_JUMBO			BIT(1)
 
 /* VLAN Rx & Tx frame support. Default: disabled (cleared) */
-#define XAE_OPTION_VLAN				(1 << 2)
+#define XAE_OPTION_VLAN				BIT(2)
 
 /* Enable recognition of flow control frames on Rx. Default: enabled (set) */
-#define XAE_OPTION_FLOW_CONTROL			(1 << 4)
+#define XAE_OPTION_FLOW_CONTROL			BIT(4)
 
 /* Strip FCS and PAD from incoming frames. Note: PAD from VLAN frames is not
  * stripped. Default: disabled (set)
  */
-#define XAE_OPTION_FCS_STRIP			(1 << 5)
+#define XAE_OPTION_FCS_STRIP			BIT(5)
 
 /* Generate FCS field and add PAD automatically for outgoing frames.
  * Default: enabled (set)
  */
-#define XAE_OPTION_FCS_INSERT			(1 << 6)
+#define XAE_OPTION_FCS_INSERT			BIT(6)
 
 /* Enable Length/Type error checking for incoming frames. When this option is
  * set, the MAC will filter frames that have a mismatched type/length field
@@ -56,13 +56,13 @@
  * types of frames are encountered. When this option is cleared, the MAC will
  * allow these types of frames to be received. Default: enabled (set)
  */
-#define XAE_OPTION_LENTYPE_ERR			(1 << 7)
+#define XAE_OPTION_LENTYPE_ERR			BIT(7)
 
 /* Enable the transmitter. Default: enabled (set) */
-#define XAE_OPTION_TXEN				(1 << 11)
+#define XAE_OPTION_TXEN				BIT(11)
 
 /*  Enable the receiver. Default: enabled (set) */
-#define XAE_OPTION_RXEN				(1 << 12)
+#define XAE_OPTION_RXEN				BIT(12)
 
 /*  Default options set when device is initialized or reset */
 #define XAE_OPTION_DEFAULTS				   \
@@ -326,11 +326,11 @@
 #define XAE_MULTICAST_CAM_TABLE_NUM	4
 
 /* Axi Ethernet Synthesis features */
-#define XAE_FEATURE_PARTIAL_RX_CSUM	(1 << 0)
-#define XAE_FEATURE_PARTIAL_TX_CSUM	(1 << 1)
-#define XAE_FEATURE_FULL_RX_CSUM	(1 << 2)
-#define XAE_FEATURE_FULL_TX_CSUM	(1 << 3)
-#define XAE_FEATURE_DMA_64BIT		(1 << 4)
+#define XAE_FEATURE_PARTIAL_RX_CSUM	BIT(0)
+#define XAE_FEATURE_PARTIAL_TX_CSUM	BIT(1)
+#define XAE_FEATURE_FULL_RX_CSUM	BIT(2)
+#define XAE_FEATURE_FULL_TX_CSUM	BIT(3)
+#define XAE_FEATURE_DMA_64BIT		BIT(4)
 
 #define XAE_NO_CSUM_OFFLOAD		0
 
-- 
cgit v1.3-3-g829e


From f7061a3e04cf17162a2d96f4f746f7904c26158e Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Date: Wed, 31 Jul 2024 14:46:05 +0530
Subject: net: axienet: add missing blank line after declaration

Add missing blank line after declaration. Fixes below
checkpatch warnings.

WARNING: Missing a blank line after declarations
+       struct sockaddr *addr = p;
+       axienet_set_mac_address(ndev, addr->sa_data);

WARNING: Missing a blank line after declarations
+       struct axienet_local *lp = netdev_priv(ndev);
+       disable_irq(lp->tx_irq);

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index f051f0387214..32b49270e8d6 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -415,6 +415,7 @@ static void axienet_set_mac_address(struct net_device *ndev,
 static int netdev_set_mac_address(struct net_device *ndev, void *p)
 {
 	struct sockaddr *addr = p;
+
 	axienet_set_mac_address(ndev, addr->sa_data);
 	return 0;
 }
@@ -1657,6 +1658,7 @@ static int axienet_change_mtu(struct net_device *ndev, int new_mtu)
 static void axienet_poll_controller(struct net_device *ndev)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
+
 	disable_irq(lp->tx_irq);
 	disable_irq(lp->rx_irq);
 	axienet_rx_irq(lp->tx_irq, ndev);
-- 
cgit v1.3-3-g829e


From f83828a0522fc57b244629844fc413e38cde95f3 Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Date: Wed, 31 Jul 2024 14:46:06 +0530
Subject: net: axienet: remove unnecessary ftrace-like logging

remove unnecessary ftrace-like logging. Also fixes below
checkpatch WARNING.

WARNING: Unnecessary ftrace-like logging - prefer using ftrace
+       dev_dbg(&ndev->dev, "%s\n", __func__);

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 32b49270e8d6..490d647a9069 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1515,8 +1515,6 @@ static int axienet_open(struct net_device *ndev)
 	int ret;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	dev_dbg(&ndev->dev, "%s\n", __func__);
-
 	/* When we do an Axi Ethernet reset, it resets the complete core
 	 * including the MDIO. MDIO must be disabled before resetting.
 	 * Hold MDIO bus lock to avoid MDIO accesses during the reset.
@@ -1577,8 +1575,6 @@ static int axienet_stop(struct net_device *ndev)
 	struct axienet_local *lp = netdev_priv(ndev);
 	int i;
 
-	dev_dbg(&ndev->dev, "axienet_close()\n");
-
 	if (!lp->use_dmaengine) {
 		napi_disable(&lp->napi_tx);
 		napi_disable(&lp->napi_rx);
-- 
cgit v1.3-3-g829e


From 48ba8a1d0424347e375f5deccdd2eda461fa9a94 Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Date: Wed, 31 Jul 2024 14:46:07 +0530
Subject: net: axienet: remove unnecessary parentheses

Remove unnecessary parentheses around 'ndev->mtu
<= XAE_JUMBO_MTU' and 'ndev->mtu > XAE_MTU'. Reported
by checkpatch.

CHECK: Unnecessary parentheses around 'ndev->mtu > XAE_MTU'
+       if ((ndev->mtu > XAE_MTU) &&
+           (ndev->mtu <= XAE_JUMBO_MTU)) {

CHECK: Unnecessary parentheses around 'ndev->mtu <= XAE_JUMBO_MTU'
+       if ((ndev->mtu > XAE_MTU) &&
+           (ndev->mtu <= XAE_JUMBO_MTU)) {

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 490d647a9069..ca04c298daa2 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -614,8 +614,7 @@ static int axienet_device_reset(struct net_device *ndev)
 	lp->options |= XAE_OPTION_VLAN;
 	lp->options &= (~XAE_OPTION_JUMBO);
 
-	if ((ndev->mtu > XAE_MTU) &&
-	    (ndev->mtu <= XAE_JUMBO_MTU)) {
+	if (ndev->mtu > XAE_MTU && ndev->mtu <= XAE_JUMBO_MTU) {
 		lp->max_frm_size = ndev->mtu + VLAN_ETH_HLEN +
 					XAE_TRL_SIZE;
 
-- 
cgit v1.3-3-g829e


From 49675f5bdf9ae2624b430dafda4cb29024521625 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 1 Aug 2024 09:34:01 -0700
Subject: net: remove IFF_* re-definition

We re-define values of enum netdev_priv_flags as preprocessor
macros with the same name. I guess this was done to avoid breaking
out of tree modules which may use #ifdef X for kernel compatibility?
Commit 7aa98047df95 ("net: move net_device priv_flags out from UAPI")
which added the enum doesn't say. In any case, the flags with defines
are quite old now, and defines for new flags don't get added.
OOT drivers have to resort to code greps for compat detection, anyway.
Let's delete these defines, save LoC, help LXR link to the right place.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20240801163401.378723-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 32 --------------------------------
 1 file changed, 32 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 607009150b5f..0ef3eaa23f4b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1689,38 +1689,6 @@ enum netdev_priv_flags {
 	IFF_SEE_ALL_HWTSTAMP_REQUESTS	= BIT_ULL(33),
 };
 
-#define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
-#define IFF_EBRIDGE			IFF_EBRIDGE
-#define IFF_BONDING			IFF_BONDING
-#define IFF_ISATAP			IFF_ISATAP
-#define IFF_WAN_HDLC			IFF_WAN_HDLC
-#define IFF_XMIT_DST_RELEASE		IFF_XMIT_DST_RELEASE
-#define IFF_DONT_BRIDGE			IFF_DONT_BRIDGE
-#define IFF_DISABLE_NETPOLL		IFF_DISABLE_NETPOLL
-#define IFF_MACVLAN_PORT		IFF_MACVLAN_PORT
-#define IFF_BRIDGE_PORT			IFF_BRIDGE_PORT
-#define IFF_OVS_DATAPATH		IFF_OVS_DATAPATH
-#define IFF_TX_SKB_SHARING		IFF_TX_SKB_SHARING
-#define IFF_UNICAST_FLT			IFF_UNICAST_FLT
-#define IFF_TEAM_PORT			IFF_TEAM_PORT
-#define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
-#define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
-#define IFF_MACVLAN			IFF_MACVLAN
-#define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
-#define IFF_L3MDEV_MASTER		IFF_L3MDEV_MASTER
-#define IFF_NO_QUEUE			IFF_NO_QUEUE
-#define IFF_OPENVSWITCH			IFF_OPENVSWITCH
-#define IFF_L3MDEV_SLAVE		IFF_L3MDEV_SLAVE
-#define IFF_TEAM			IFF_TEAM
-#define IFF_RXFH_CONFIGURED		IFF_RXFH_CONFIGURED
-#define IFF_PHONY_HEADROOM		IFF_PHONY_HEADROOM
-#define IFF_MACSEC			IFF_MACSEC
-#define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
-#define IFF_FAILOVER			IFF_FAILOVER
-#define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
-#define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
-#define IFF_TX_SKB_NO_LINEAR		IFF_TX_SKB_NO_LINEAR
-
 /* Specifies the type of the struct net_device::ml_priv pointer */
 enum netdev_ml_priv_type {
 	ML_PRIV_NONE,
-- 
cgit v1.3-3-g829e


From ab1000976cc7de8e57bdef811dfcfcb6c17a929f Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 1 Aug 2024 17:03:07 -0700
Subject: selftests: net-drv: exercise queue stats when the device is down

Verify that total device stats don't decrease after it has been turned down.
Also make sure the device doesn't crash when we access per-queue stats
when it's down (in case it tries to access some pointers that are NULL).

  KTAP version 1
  1..5
  ok 1 stats.check_pause
  ok 2 stats.check_fec
  ok 3 stats.pkt_byte_sum
  ok 4 stats.qstat_by_ifindex
  ok 5 stats.check_down
  # Totals: pass:5 fail:0 xfail:0 xpass:0 skip:0 error:0

v3:
- use errno.EOPNOTSUPP (Petr)
- move qstat[0] under try (Petr)

v2:
- KTAP output formatting (Jakub)
- defer instead of try/finally (Jakub)
- disappearing stats is an error (Jakub)
- ksft_ge instead of open coding (Jakub)

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20240802000309.2368-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/stats.py | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index 820b8e0a22c6..2fdde8cf0307 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -1,10 +1,12 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
+import errno
 from lib.py import ksft_run, ksft_exit, ksft_pr
 from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx
 from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError
 from lib.py import NetDrvEnv
+from lib.py import ip, defer
 
 ethnl = EthtoolFamily()
 netfam = NetdevFamily()
@@ -133,9 +135,30 @@ def qstat_by_ifindex(cfg) -> None:
     ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
 
 
+def check_down(cfg) -> None:
+    try:
+        qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("qstats not supported by the device")
+        raise
+
+    ip(f"link set dev {cfg.dev['ifname']} down")
+    defer(ip, f"link set dev {cfg.dev['ifname']} up")
+
+    qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+    for k, v in qstat.items():
+        ksft_ge(qstat2[k], qstat[k], comment=f"{k} went backwards on device down")
+
+    # exercise per-queue API to make sure that "device down" state
+    # is handled correctly and doesn't crash
+    netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True)
+
+
 def main() -> None:
     with NetDrvEnv(__file__) as cfg:
-        ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex],
+        ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
+                  check_down],
                  args=(cfg, ))
     ksft_exit()
 
-- 
cgit v1.3-3-g829e


From f879306834818ebd1722a4372079610cdd466fec Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 1 Aug 2024 17:03:08 -0700
Subject: selftests: net: ksft: support marking tests as disruptive

Add new @ksft_disruptive decorator to mark the tests that might
be disruptive to the system. Depending on how well the previous
test works in the CI we might want to disable disruptive tests
by default and only let the developers run them manually.

KSFT framework runs disruptive tests by default. DISRUPTIVE=False
environment (or config file) can be used to disable these tests.
ksft_setup should be called by the test cases that want to use
new decorator (ksft_setup is only called via NetDrvEnv/NetDrvEpEnv for now).

In the future we can add similar decorators to, for example, avoid
running slow tests all the time. And/or have some option to run
only 'fast' tests for some sort of smoke test scenario.

  $ DISRUPTIVE=False ./stats.py
  KTAP version 1
  1..5
  ok 1 stats.check_pause
  ok 2 stats.check_fec
  ok 3 stats.pkt_byte_sum
  ok 4 stats.qstat_by_ifindex
  ok 5 stats.check_down # SKIP marked as disruptive
  # Totals: pass:4 fail:0 xfail:0 xpass:0 skip:1 error:0

v3:
- parse yes and properly treat non-zero nums as true (Petr)

v2:
- convert from cli argument to env variable (Jakub)

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20240802000309.2368-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/lib/py/env.py |  5 +--
 tools/testing/selftests/drivers/net/stats.py      |  2 ++
 tools/testing/selftests/net/lib/py/ksft.py        | 40 +++++++++++++++++++++++
 3 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index a5e800b8f103..1ea9bb695e94 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -4,6 +4,7 @@ import os
 import time
 from pathlib import Path
 from lib.py import KsftSkipEx, KsftXfailEx
+from lib.py import ksft_setup
 from lib.py import cmd, ethtool, ip
 from lib.py import NetNS, NetdevSimDev
 from .remote import Remote
@@ -14,7 +15,7 @@ def _load_env_file(src_path):
 
     src_dir = Path(src_path).parent.resolve()
     if not (src_dir / "net.config").exists():
-        return env
+        return ksft_setup(env)
 
     with open((src_dir / "net.config").as_posix(), 'r') as fp:
         for line in fp.readlines():
@@ -30,7 +31,7 @@ def _load_env_file(src_path):
             if len(pair) != 2:
                 raise Exception("Can't parse configuration line:", full_file)
             env[pair[0]] = pair[1]
-    return env
+    return ksft_setup(env)
 
 
 class NetDrvEnv:
diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index 2fdde8cf0307..d17dfed2788f 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -4,6 +4,7 @@
 import errno
 from lib.py import ksft_run, ksft_exit, ksft_pr
 from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx
+from lib.py import ksft_disruptive
 from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError
 from lib.py import NetDrvEnv
 from lib.py import ip, defer
@@ -135,6 +136,7 @@ def qstat_by_ifindex(cfg) -> None:
     ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
 
 
+@ksft_disruptive
 def check_down(cfg) -> None:
     try:
         qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index f26c20df9db4..353860fe6223 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 import builtins
+import functools
 import inspect
 import sys
 import time
@@ -10,6 +11,7 @@ from .utils import global_defer_queue
 
 KSFT_RESULT = None
 KSFT_RESULT_ALL = True
+KSFT_DISRUPTIVE = True
 
 
 class KsftFailEx(Exception):
@@ -127,6 +129,44 @@ def ksft_flush_defer():
             KSFT_RESULT = False
 
 
+def ksft_disruptive(func):
+    """
+    Decorator that marks the test as disruptive (e.g. the test
+    that can down the interface). Disruptive tests can be skipped
+    by passing DISRUPTIVE=False environment variable.
+    """
+
+    @functools.wraps(func)
+    def wrapper(*args, **kwargs):
+        if not KSFT_DISRUPTIVE:
+            raise KsftSkipEx(f"marked as disruptive")
+        return func(*args, **kwargs)
+    return wrapper
+
+
+def ksft_setup(env):
+    """
+    Setup test framework global state from the environment.
+    """
+
+    def get_bool(env, name):
+        value = env.get(name, "").lower()
+        if value in ["yes", "true"]:
+            return True
+        if value in ["no", "false"]:
+            return False
+        try:
+            return bool(int(value))
+        except:
+            raise Exception(f"failed to parse {name}")
+
+    if "DISRUPTIVE" in env:
+        global KSFT_DISRUPTIVE
+        KSFT_DISRUPTIVE = get_bool(env, "DISRUPTIVE")
+
+    return env
+
+
 def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
     cases = cases or []
 
-- 
cgit v1.3-3-g829e


From a48395f22b8c8687ceb77ae3014a0eabcd4bf688 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 1 Aug 2024 17:03:09 -0700
Subject: selftests: net: ksft: replace 95 with errno.EOPNOTSUPP

Petr suggested to use errno.EOPNOTSUPP instead of hard-coded 95
in the new test case. Adjust existing ones to match this style.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20240802000309.2368-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py | 3 ++-
 tools/testing/selftests/drivers/net/stats.py            | 6 +++---
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py
index 026d98976c35..05b6fbb3fcdd 100755
--- a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py
+++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
+import errno
 import time
 import os
 from lib.py import ksft_run, ksft_exit, ksft_pr
@@ -61,7 +62,7 @@ def test_pp_alloc(cfg, netdevnl):
     try:
         stats = get_stats()
     except NlError as e:
-        if e.nl_msg.error == -95:
+        if e.nl_msg.error == -errno.EOPNOTSUPP:
             stats = {}
         else:
             raise
diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index d17dfed2788f..63e3c045a3b2 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -20,7 +20,7 @@ def check_pause(cfg) -> None:
     try:
         ethnl.pause_get({"header": {"dev-index": cfg.ifindex}})
     except NlError as e:
-        if e.error == 95:
+        if e.error == errno.EOPNOTSUPP:
             raise KsftXfailEx("pause not supported by the device")
         raise
 
@@ -35,7 +35,7 @@ def check_fec(cfg) -> None:
     try:
         ethnl.fec_get({"header": {"dev-index": cfg.ifindex}})
     except NlError as e:
-        if e.error == 95:
+        if e.error == errno.EOPNOTSUPP:
             raise KsftXfailEx("FEC not supported by the device")
         raise
 
@@ -120,7 +120,7 @@ def qstat_by_ifindex(cfg) -> None:
     # loopback has no stats
     with ksft_raises(NlError) as cm:
         netfam.qstats_get({"ifindex": 1}, dump=True)
-    ksft_eq(cm.exception.nl_msg.error, -95)
+    ksft_eq(cm.exception.nl_msg.error, -errno.EOPNOTSUPP)
     ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
 
     # Try to get stats for lowest unused ifindex but not 0
-- 
cgit v1.3-3-g829e


From 46619175f1b7e4f7fc5dc98547f5eca27193f8dc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 1 Aug 2024 16:23:17 -0700
Subject: selftests: net: ksft: print more of the stack for checks

Print more stack frames and the failing line when check fails.
This helps when tests use helpers to do the checks.

Before:

  # At ./ksft/drivers/net/hw/rss_ctx.py line 92:
  # Check failed 1037698 >= 396893.0 traffic on other queues:[344612, 462380, 233020, 449174, 342298]
  not ok 8 rss_ctx.test_rss_context_queue_reconfigure

After:

  # Check| At ./ksft/drivers/net/hw/rss_ctx.py, line 387, in test_rss_context_queue_reconfigure:
  # Check|     test_rss_queue_reconfigure(cfg, main_ctx=False)
  # Check| At ./ksft/drivers/net/hw/rss_ctx.py, line 230, in test_rss_queue_reconfigure:
  # Check|     _send_traffic_check(cfg, port, ctx_ref, { 'target': (0, 3),
  # Check| At ./ksft/drivers/net/hw/rss_ctx.py, line 92, in _send_traffic_check:
  # Check|     ksft_lt(sum(cnts[i] for i in params['noise']), directed / 2,
  # Check failed 1045235 >= 405823.5 traffic on other queues (context 1)':[460068, 351995, 565970, 351579, 127270]
  not ok 8 rss_ctx.test_rss_context_queue_reconfigure

Link: https://patch.msgid.link/20240801232317.545577-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib/py/ksft.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 353860fe6223..f663e0daec0d 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -34,8 +34,18 @@ def _fail(*args):
     global KSFT_RESULT
     KSFT_RESULT = False
 
-    frame = inspect.stack()[2]
-    ksft_pr("At " + frame.filename + " line " + str(frame.lineno) + ":")
+    stack = inspect.stack()
+    started = False
+    for frame in reversed(stack[2:]):
+        # Start printing from the test case function
+        if not started:
+            if frame.function == 'ksft_run':
+                started = True
+            continue
+
+        ksft_pr("Check| At " + frame.filename + ", line " + str(frame.lineno) +
+                ", in " + frame.function + ":")
+        ksft_pr("Check|     " + frame.code_context[0].strip())
     ksft_pr(*args)
 
 
-- 
cgit v1.3-3-g829e


From 9a95b7a89dffae5f1e99dd73748f144fec820292 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Fri, 2 Aug 2024 16:43:17 +0100
Subject: eth: fbnic: select DEVLINK and PAGE_POOL

Build bot reports undefined references to devlink functions.
And local testing revealed undefined references to page_pool functions.

Based on a patch by Jakub Kicinski <kuba@kernel.org>

Fixes: 1a9d48892ea5 ("eth: fbnic: Allocate core device specific structures and devlink interface")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202408011219.hiPmwwAs-lkp@intel.com/
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240802-fbnic-select-v2-1-41f82a3e0178@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig
index c002ede36402..85519690b837 100644
--- a/drivers/net/ethernet/meta/Kconfig
+++ b/drivers/net/ethernet/meta/Kconfig
@@ -23,6 +23,8 @@ config FBNIC
 	depends on !S390
 	depends on MAX_SKB_FRAGS < 22
 	depends on PCI_MSI
+	select NET_DEVLINK
+	select PAGE_POOL
 	select PHYLINK
 	help
 	  This driver supports Meta Platforms Host Network Interface.
-- 
cgit v1.3-3-g829e


From 16874d1cf3818a5804cded8eaff634122b1d6c7c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:03 +0200
Subject: net: airoha: Introduce airoha_qdma struct

Introduce airoha_qdma struct and move qdma IO register mapping in
airoha_qdma. This is a preliminary patch to enable both QDMA controllers
available on EN7581 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/7df163bdc72ee29c3d27a0cbf54522ffeeafe53c.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 197 ++++++++++++++++-------------
 1 file changed, 112 insertions(+), 85 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 1c5b85a86df1..7add08bac8cf 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -18,6 +18,7 @@
 #include <uapi/linux/ppp_defs.h>
 
 #define AIROHA_MAX_NUM_GDM_PORTS	1
+#define AIROHA_MAX_NUM_QDMA		1
 #define AIROHA_MAX_NUM_RSTS		3
 #define AIROHA_MAX_NUM_XSI_RSTS		5
 #define AIROHA_MAX_MTU			2000
@@ -782,6 +783,10 @@ struct airoha_hw_stats {
 	u64 rx_len[7];
 };
 
+struct airoha_qdma {
+	void __iomem *regs;
+};
+
 struct airoha_gdm_port {
 	struct net_device *dev;
 	struct airoha_eth *eth;
@@ -794,8 +799,6 @@ struct airoha_eth {
 	struct device *dev;
 
 	unsigned long state;
-
-	void __iomem *qdma_regs;
 	void __iomem *fe_regs;
 
 	/* protect concurrent irqmask accesses */
@@ -806,6 +809,7 @@ struct airoha_eth {
 	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
 	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
 
+	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
 	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
 
 	struct net_device *napi_dev;
@@ -850,16 +854,16 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 #define airoha_fe_clear(eth, offset, val)			\
 	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
 
-#define airoha_qdma_rr(eth, offset)				\
-	airoha_rr((eth)->qdma_regs, (offset))
-#define airoha_qdma_wr(eth, offset, val)			\
-	airoha_wr((eth)->qdma_regs, (offset), (val))
-#define airoha_qdma_rmw(eth, offset, mask, val)			\
-	airoha_rmw((eth)->qdma_regs, (offset), (mask), (val))
-#define airoha_qdma_set(eth, offset, val)			\
-	airoha_rmw((eth)->qdma_regs, (offset), 0, (val))
-#define airoha_qdma_clear(eth, offset, val)			\
-	airoha_rmw((eth)->qdma_regs, (offset), (val), 0)
+#define airoha_qdma_rr(qdma, offset)				\
+	airoha_rr((qdma)->regs, (offset))
+#define airoha_qdma_wr(qdma, offset, val)			\
+	airoha_wr((qdma)->regs, (offset), (val))
+#define airoha_qdma_rmw(qdma, offset, mask, val)		\
+	airoha_rmw((qdma)->regs, (offset), (mask), (val))
+#define airoha_qdma_set(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), 0, (val))
+#define airoha_qdma_clear(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), (val), 0)
 
 static void airoha_qdma_set_irqmask(struct airoha_eth *eth, int index,
 				    u32 clear, u32 set)
@@ -873,11 +877,12 @@ static void airoha_qdma_set_irqmask(struct airoha_eth *eth, int index,
 
 	eth->irqmask[index] &= ~clear;
 	eth->irqmask[index] |= set;
-	airoha_qdma_wr(eth, REG_INT_ENABLE(index), eth->irqmask[index]);
+	airoha_qdma_wr(&eth->qdma[0], REG_INT_ENABLE(index),
+		       eth->irqmask[index]);
 	/* Read irq_enable register in order to guarantee the update above
 	 * completes in the spinlock critical section.
 	 */
-	airoha_qdma_rr(eth, REG_INT_ENABLE(index));
+	airoha_qdma_rr(&eth->qdma[0], REG_INT_ENABLE(index));
 
 	spin_unlock_irqrestore(&eth->irq_lock, flags);
 }
@@ -1383,6 +1388,7 @@ static int airoha_fe_init(struct airoha_eth *eth)
 static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
 {
 	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
+	struct airoha_qdma *qdma = &q->eth->qdma[0];
 	struct airoha_eth *eth = q->eth;
 	int qid = q - &eth->q_rx[0];
 	int nframes = 0;
@@ -1420,7 +1426,8 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
 		WRITE_ONCE(desc->msg2, 0);
 		WRITE_ONCE(desc->msg3, 0);
 
-		airoha_qdma_rmw(eth, REG_RX_CPU_IDX(qid), RX_RING_CPU_IDX_MASK,
+		airoha_qdma_rmw(qdma, REG_RX_CPU_IDX(qid),
+				RX_RING_CPU_IDX_MASK,
 				FIELD_PREP(RX_RING_CPU_IDX_MASK, q->head));
 	}
 
@@ -1529,7 +1536,8 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 }
 
 static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
-				     struct airoha_queue *q, int ndesc)
+				     struct airoha_queue *q,
+				     struct airoha_qdma *qdma, int ndesc)
 {
 	const struct page_pool_params pp_params = {
 		.order = 0,
@@ -1568,14 +1576,15 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
 
 	netif_napi_add(eth->napi_dev, &q->napi, airoha_qdma_rx_napi_poll);
 
-	airoha_qdma_wr(eth, REG_RX_RING_BASE(qid), dma_addr);
-	airoha_qdma_rmw(eth, REG_RX_RING_SIZE(qid), RX_RING_SIZE_MASK,
+	airoha_qdma_wr(qdma, REG_RX_RING_BASE(qid), dma_addr);
+	airoha_qdma_rmw(qdma, REG_RX_RING_SIZE(qid),
+			RX_RING_SIZE_MASK,
 			FIELD_PREP(RX_RING_SIZE_MASK, ndesc));
 
 	thr = clamp(ndesc >> 3, 1, 32);
-	airoha_qdma_rmw(eth, REG_RX_RING_SIZE(qid), RX_RING_THR_MASK,
+	airoha_qdma_rmw(qdma, REG_RX_RING_SIZE(qid), RX_RING_THR_MASK,
 			FIELD_PREP(RX_RING_THR_MASK, thr));
-	airoha_qdma_rmw(eth, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
+	airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
 			FIELD_PREP(RX_RING_DMA_IDX_MASK, q->head));
 
 	airoha_qdma_fill_rx_queue(q);
@@ -1599,7 +1608,8 @@ static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 	}
 }
 
-static int airoha_qdma_init_rx(struct airoha_eth *eth)
+static int airoha_qdma_init_rx(struct airoha_eth *eth,
+			       struct airoha_qdma *qdma)
 {
 	int i;
 
@@ -1612,7 +1622,7 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth)
 		}
 
 		err = airoha_qdma_init_rx_queue(eth, &eth->q_rx[i],
-						RX_DSCP_NUM(i));
+						qdma, RX_DSCP_NUM(i));
 		if (err)
 			return err;
 	}
@@ -1623,11 +1633,13 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth)
 static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct airoha_tx_irq_queue *irq_q;
+	struct airoha_qdma *qdma;
 	struct airoha_eth *eth;
 	int id, done = 0;
 
 	irq_q = container_of(napi, struct airoha_tx_irq_queue, napi);
 	eth = irq_q->eth;
+	qdma = &eth->qdma[0];
 	id = irq_q - &eth->q_tx_irq[0];
 
 	while (irq_q->queued > 0 && done < budget) {
@@ -1697,9 +1709,9 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 		int i, len = done >> 7;
 
 		for (i = 0; i < len; i++)
-			airoha_qdma_rmw(eth, REG_IRQ_CLEAR_LEN(id),
+			airoha_qdma_rmw(qdma, REG_IRQ_CLEAR_LEN(id),
 					IRQ_CLEAR_LEN_MASK, 0x80);
-		airoha_qdma_rmw(eth, REG_IRQ_CLEAR_LEN(id),
+		airoha_qdma_rmw(qdma, REG_IRQ_CLEAR_LEN(id),
 				IRQ_CLEAR_LEN_MASK, (done & 0x7f));
 	}
 
@@ -1711,7 +1723,8 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 }
 
 static int airoha_qdma_init_tx_queue(struct airoha_eth *eth,
-				     struct airoha_queue *q, int size)
+				     struct airoha_queue *q,
+				     struct airoha_qdma *qdma, int size)
 {
 	int i, qid = q - &eth->q_tx[0];
 	dma_addr_t dma_addr;
@@ -1738,10 +1751,10 @@ static int airoha_qdma_init_tx_queue(struct airoha_eth *eth,
 		WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val));
 	}
 
-	airoha_qdma_wr(eth, REG_TX_RING_BASE(qid), dma_addr);
-	airoha_qdma_rmw(eth, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK,
+	airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr);
+	airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK,
 			FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head));
-	airoha_qdma_rmw(eth, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK,
+	airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK,
 			FIELD_PREP(TX_RING_DMA_IDX_MASK, q->head));
 
 	return 0;
@@ -1749,7 +1762,7 @@ static int airoha_qdma_init_tx_queue(struct airoha_eth *eth,
 
 static int airoha_qdma_tx_irq_init(struct airoha_eth *eth,
 				   struct airoha_tx_irq_queue *irq_q,
-				   int size)
+				   struct airoha_qdma *qdma, int size)
 {
 	int id = irq_q - &eth->q_tx_irq[0];
 	dma_addr_t dma_addr;
@@ -1765,29 +1778,30 @@ static int airoha_qdma_tx_irq_init(struct airoha_eth *eth,
 	irq_q->size = size;
 	irq_q->eth = eth;
 
-	airoha_qdma_wr(eth, REG_TX_IRQ_BASE(id), dma_addr);
-	airoha_qdma_rmw(eth, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK,
+	airoha_qdma_wr(qdma, REG_TX_IRQ_BASE(id), dma_addr);
+	airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK,
 			FIELD_PREP(TX_IRQ_DEPTH_MASK, size));
-	airoha_qdma_rmw(eth, REG_TX_IRQ_CFG(id), TX_IRQ_THR_MASK,
+	airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_THR_MASK,
 			FIELD_PREP(TX_IRQ_THR_MASK, 1));
 
 	return 0;
 }
 
-static int airoha_qdma_init_tx(struct airoha_eth *eth)
+static int airoha_qdma_init_tx(struct airoha_eth *eth,
+			       struct airoha_qdma *qdma)
 {
 	int i, err;
 
 	for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) {
 		err = airoha_qdma_tx_irq_init(eth, &eth->q_tx_irq[i],
-					      IRQ_QUEUE_LEN(i));
+					      qdma, IRQ_QUEUE_LEN(i));
 		if (err)
 			return err;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) {
 		err = airoha_qdma_init_tx_queue(eth, &eth->q_tx[i],
-						TX_DSCP_NUM);
+						qdma, TX_DSCP_NUM);
 		if (err)
 			return err;
 	}
@@ -1814,7 +1828,8 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 	spin_unlock_bh(&q->lock);
 }
 
-static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth)
+static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth,
+					struct airoha_qdma *qdma)
 {
 	dma_addr_t dma_addr;
 	u32 status;
@@ -1826,7 +1841,7 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth)
 	if (!eth->hfwd.desc)
 		return -ENOMEM;
 
-	airoha_qdma_wr(eth, REG_FWD_DSCP_BASE, dma_addr);
+	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
 
 	size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
 	eth->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr,
@@ -1834,14 +1849,14 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth)
 	if (!eth->hfwd.q)
 		return -ENOMEM;
 
-	airoha_qdma_wr(eth, REG_FWD_BUF_BASE, dma_addr);
+	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
 
-	airoha_qdma_rmw(eth, REG_HW_FWD_DSCP_CFG,
+	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
 			HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
 			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
-	airoha_qdma_rmw(eth, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
+	airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
 			FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128));
-	airoha_qdma_rmw(eth, REG_LMGR_INIT_CFG,
+	airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
 			HW_FWD_DESC_NUM_MASK,
 			FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
@@ -1849,67 +1864,69 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth)
 
 	return read_poll_timeout(airoha_qdma_rr, status,
 				 !(status & LMGR_INIT_START), USEC_PER_MSEC,
-				 30 * USEC_PER_MSEC, true, eth,
+				 30 * USEC_PER_MSEC, true, qdma,
 				 REG_LMGR_INIT_CFG);
 }
 
-static void airoha_qdma_init_qos(struct airoha_eth *eth)
+static void airoha_qdma_init_qos(struct airoha_eth *eth,
+				 struct airoha_qdma *qdma)
 {
-	airoha_qdma_clear(eth, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK);
-	airoha_qdma_set(eth, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK);
+	airoha_qdma_clear(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK);
+	airoha_qdma_set(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK);
 
-	airoha_qdma_clear(eth, REG_PSE_BUF_USAGE_CFG,
+	airoha_qdma_clear(qdma, REG_PSE_BUF_USAGE_CFG,
 			  PSE_BUF_ESTIMATE_EN_MASK);
 
-	airoha_qdma_set(eth, REG_EGRESS_RATE_METER_CFG,
+	airoha_qdma_set(qdma, REG_EGRESS_RATE_METER_CFG,
 			EGRESS_RATE_METER_EN_MASK |
 			EGRESS_RATE_METER_EQ_RATE_EN_MASK);
 	/* 2047us x 31 = 63.457ms */
-	airoha_qdma_rmw(eth, REG_EGRESS_RATE_METER_CFG,
+	airoha_qdma_rmw(qdma, REG_EGRESS_RATE_METER_CFG,
 			EGRESS_RATE_METER_WINDOW_SZ_MASK,
 			FIELD_PREP(EGRESS_RATE_METER_WINDOW_SZ_MASK, 0x1f));
-	airoha_qdma_rmw(eth, REG_EGRESS_RATE_METER_CFG,
+	airoha_qdma_rmw(qdma, REG_EGRESS_RATE_METER_CFG,
 			EGRESS_RATE_METER_TIMESLICE_MASK,
 			FIELD_PREP(EGRESS_RATE_METER_TIMESLICE_MASK, 0x7ff));
 
 	/* ratelimit init */
-	airoha_qdma_set(eth, REG_GLB_TRTCM_CFG, GLB_TRTCM_EN_MASK);
+	airoha_qdma_set(qdma, REG_GLB_TRTCM_CFG, GLB_TRTCM_EN_MASK);
 	/* fast-tick 25us */
-	airoha_qdma_rmw(eth, REG_GLB_TRTCM_CFG, GLB_FAST_TICK_MASK,
+	airoha_qdma_rmw(qdma, REG_GLB_TRTCM_CFG, GLB_FAST_TICK_MASK,
 			FIELD_PREP(GLB_FAST_TICK_MASK, 25));
-	airoha_qdma_rmw(eth, REG_GLB_TRTCM_CFG, GLB_SLOW_TICK_RATIO_MASK,
+	airoha_qdma_rmw(qdma, REG_GLB_TRTCM_CFG, GLB_SLOW_TICK_RATIO_MASK,
 			FIELD_PREP(GLB_SLOW_TICK_RATIO_MASK, 40));
 
-	airoha_qdma_set(eth, REG_EGRESS_TRTCM_CFG, EGRESS_TRTCM_EN_MASK);
-	airoha_qdma_rmw(eth, REG_EGRESS_TRTCM_CFG, EGRESS_FAST_TICK_MASK,
+	airoha_qdma_set(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_TRTCM_EN_MASK);
+	airoha_qdma_rmw(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_FAST_TICK_MASK,
 			FIELD_PREP(EGRESS_FAST_TICK_MASK, 25));
-	airoha_qdma_rmw(eth, REG_EGRESS_TRTCM_CFG,
+	airoha_qdma_rmw(qdma, REG_EGRESS_TRTCM_CFG,
 			EGRESS_SLOW_TICK_RATIO_MASK,
 			FIELD_PREP(EGRESS_SLOW_TICK_RATIO_MASK, 40));
 
-	airoha_qdma_set(eth, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_EN_MASK);
-	airoha_qdma_clear(eth, REG_INGRESS_TRTCM_CFG,
+	airoha_qdma_set(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_EN_MASK);
+	airoha_qdma_clear(qdma, REG_INGRESS_TRTCM_CFG,
 			  INGRESS_TRTCM_MODE_MASK);
-	airoha_qdma_rmw(eth, REG_INGRESS_TRTCM_CFG, INGRESS_FAST_TICK_MASK,
+	airoha_qdma_rmw(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_FAST_TICK_MASK,
 			FIELD_PREP(INGRESS_FAST_TICK_MASK, 125));
-	airoha_qdma_rmw(eth, REG_INGRESS_TRTCM_CFG,
+	airoha_qdma_rmw(qdma, REG_INGRESS_TRTCM_CFG,
 			INGRESS_SLOW_TICK_RATIO_MASK,
 			FIELD_PREP(INGRESS_SLOW_TICK_RATIO_MASK, 8));
 
-	airoha_qdma_set(eth, REG_SLA_TRTCM_CFG, SLA_TRTCM_EN_MASK);
-	airoha_qdma_rmw(eth, REG_SLA_TRTCM_CFG, SLA_FAST_TICK_MASK,
+	airoha_qdma_set(qdma, REG_SLA_TRTCM_CFG, SLA_TRTCM_EN_MASK);
+	airoha_qdma_rmw(qdma, REG_SLA_TRTCM_CFG, SLA_FAST_TICK_MASK,
 			FIELD_PREP(SLA_FAST_TICK_MASK, 25));
-	airoha_qdma_rmw(eth, REG_SLA_TRTCM_CFG, SLA_SLOW_TICK_RATIO_MASK,
+	airoha_qdma_rmw(qdma, REG_SLA_TRTCM_CFG, SLA_SLOW_TICK_RATIO_MASK,
 			FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40));
 }
 
-static int airoha_qdma_hw_init(struct airoha_eth *eth)
+static int airoha_qdma_hw_init(struct airoha_eth *eth,
+			       struct airoha_qdma *qdma)
 {
 	int i;
 
 	/* clear pending irqs */
 	for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++)
-		airoha_qdma_wr(eth, REG_INT_STATUS(i), 0xffffffff);
+		airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff);
 
 	/* setup irqs */
 	airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0, INT_IDX0_MASK);
@@ -1922,14 +1939,14 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth)
 			continue;
 
 		if (TX_RING_IRQ_BLOCKING_MAP_MASK & BIT(i))
-			airoha_qdma_set(eth, REG_TX_RING_BLOCKING(i),
+			airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(i),
 					TX_RING_IRQ_BLOCKING_CFG_MASK);
 		else
-			airoha_qdma_clear(eth, REG_TX_RING_BLOCKING(i),
+			airoha_qdma_clear(qdma, REG_TX_RING_BLOCKING(i),
 					  TX_RING_IRQ_BLOCKING_CFG_MASK);
 	}
 
-	airoha_qdma_wr(eth, REG_QDMA_GLOBAL_CFG,
+	airoha_qdma_wr(qdma, REG_QDMA_GLOBAL_CFG,
 		       GLOBAL_CFG_RX_2B_OFFSET_MASK |
 		       FIELD_PREP(GLOBAL_CFG_DMA_PREFERENCE_MASK, 3) |
 		       GLOBAL_CFG_CPU_TXR_RR_MASK |
@@ -1940,18 +1957,18 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth)
 		       GLOBAL_CFG_TX_WB_DONE_MASK |
 		       FIELD_PREP(GLOBAL_CFG_MAX_ISSUE_NUM_MASK, 2));
 
-	airoha_qdma_init_qos(eth);
+	airoha_qdma_init_qos(eth, qdma);
 
 	/* disable qdma rx delay interrupt */
 	for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) {
 		if (!eth->q_rx[i].ndesc)
 			continue;
 
-		airoha_qdma_clear(eth, REG_RX_DELAY_INT_IDX(i),
+		airoha_qdma_clear(qdma, REG_RX_DELAY_INT_IDX(i),
 				  RX_DELAY_INT_MASK);
 	}
 
-	airoha_qdma_set(eth, REG_TXQ_CNGST_CFG,
+	airoha_qdma_set(qdma, REG_TXQ_CNGST_CFG,
 			TXQ_CNGST_DROP_EN | TXQ_CNGST_DEI_DROP_EN);
 
 	return 0;
@@ -1961,12 +1978,14 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 {
 	struct airoha_eth *eth = dev_instance;
 	u32 intr[ARRAY_SIZE(eth->irqmask)];
+	struct airoha_qdma *qdma;
 	int i;
 
+	qdma = &eth->qdma[0];
 	for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++) {
-		intr[i] = airoha_qdma_rr(eth, REG_INT_STATUS(i));
+		intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i));
 		intr[i] &= eth->irqmask[i];
-		airoha_qdma_wr(eth, REG_INT_STATUS(i), intr[i]);
+		airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]);
 	}
 
 	if (!test_bit(DEV_STATE_INITIALIZED, &eth->state))
@@ -1996,7 +2015,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 			airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX0,
 						TX_DONE_INT_MASK(i));
 
-			status = airoha_qdma_rr(eth, REG_IRQ_STATUS(i));
+			status = airoha_qdma_rr(qdma, REG_IRQ_STATUS(i));
 			head = FIELD_GET(IRQ_HEAD_IDX_MASK, status);
 			irq_q->head = head % irq_q->size;
 			irq_q->queued = FIELD_GET(IRQ_ENTRY_LEN_MASK, status);
@@ -2010,6 +2029,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 
 static int airoha_qdma_init(struct airoha_eth *eth)
 {
+	struct airoha_qdma *qdma = &eth->qdma[0];
 	int err;
 
 	err = devm_request_irq(eth->dev, eth->irq, airoha_irq_handler,
@@ -2017,19 +2037,19 @@ static int airoha_qdma_init(struct airoha_eth *eth)
 	if (err)
 		return err;
 
-	err = airoha_qdma_init_rx(eth);
+	err = airoha_qdma_init_rx(eth, qdma);
 	if (err)
 		return err;
 
-	err = airoha_qdma_init_tx(eth);
+	err = airoha_qdma_init_tx(eth, qdma);
 	if (err)
 		return err;
 
-	err = airoha_qdma_init_hfwd_queues(eth);
+	err = airoha_qdma_init_hfwd_queues(eth, qdma);
 	if (err)
 		return err;
 
-	err = airoha_qdma_hw_init(eth);
+	err = airoha_qdma_hw_init(eth, qdma);
 	if (err)
 		return err;
 
@@ -2262,8 +2282,9 @@ static int airoha_dev_open(struct net_device *dev)
 		airoha_fe_clear(eth, REG_GDM_INGRESS_CFG(port->id),
 				GDM_STAG_EN_MASK);
 
-	airoha_qdma_set(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_TX_DMA_EN_MASK);
-	airoha_qdma_set(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_DMA_EN_MASK);
+	airoha_qdma_set(&eth->qdma[0], REG_QDMA_GLOBAL_CFG,
+			GLOBAL_CFG_TX_DMA_EN_MASK |
+			GLOBAL_CFG_RX_DMA_EN_MASK);
 
 	return 0;
 }
@@ -2279,8 +2300,9 @@ static int airoha_dev_stop(struct net_device *dev)
 	if (err)
 		return err;
 
-	airoha_qdma_clear(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_TX_DMA_EN_MASK);
-	airoha_qdma_clear(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_DMA_EN_MASK);
+	airoha_qdma_clear(&eth->qdma[0], REG_QDMA_GLOBAL_CFG,
+			  GLOBAL_CFG_TX_DMA_EN_MASK |
+			  GLOBAL_CFG_RX_DMA_EN_MASK);
 
 	return 0;
 }
@@ -2340,6 +2362,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	struct airoha_eth *eth = port->eth;
 	u32 nr_frags = 1 + sinfo->nr_frags;
 	struct netdev_queue *txq;
+	struct airoha_qdma *qdma;
 	struct airoha_queue *q;
 	void *data = skb->data;
 	u16 index;
@@ -2367,6 +2390,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) |
 	       FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f);
 
+	qdma = &eth->qdma[0];
 	q = &eth->q_tx[qid];
 	if (WARN_ON_ONCE(!q->ndesc))
 		goto error;
@@ -2411,7 +2435,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		e->dma_addr = addr;
 		e->dma_len = len;
 
-		airoha_qdma_rmw(eth, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK,
+		airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid),
+				TX_RING_CPU_IDX_MASK,
 				FIELD_PREP(TX_RING_CPU_IDX_MASK, index));
 
 		data = skb_frag_address(frag);
@@ -2613,9 +2638,11 @@ static int airoha_probe(struct platform_device *pdev)
 		return dev_err_probe(eth->dev, PTR_ERR(eth->fe_regs),
 				     "failed to iomap fe regs\n");
 
-	eth->qdma_regs = devm_platform_ioremap_resource_byname(pdev, "qdma0");
-	if (IS_ERR(eth->qdma_regs))
-		return dev_err_probe(eth->dev, PTR_ERR(eth->qdma_regs),
+	eth->qdma[0].regs = devm_platform_ioremap_resource_byname(pdev,
+								  "qdma0");
+	if (IS_ERR(eth->qdma[0].regs))
+		return dev_err_probe(eth->dev,
+				     PTR_ERR(eth->qdma[0].regs),
 				     "failed to iomap qdma regs\n");
 
 	eth->rsts[0].id = "fe";
-- 
cgit v1.3-3-g829e


From 245c7bc86b198e5ec227eba6b582da73cb0721c8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:04 +0200
Subject: net: airoha: Move airoha_queues in airoha_qdma

QDMA controllers available in EN7581 SoC have independent tx/rx hw queues
so move them in airoha_queues structure.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/795fc4797bffbf7f0a1351308aa9bf0e65b5126e.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 126 +++++++++++++++--------------
 1 file changed, 65 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 7add08bac8cf..fc6712216c47 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -785,6 +785,17 @@ struct airoha_hw_stats {
 
 struct airoha_qdma {
 	void __iomem *regs;
+
+	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
+
+	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
+	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
+
+	/* descriptor and packet buffers for qdma hw forward */
+	struct {
+		void *desc;
+		void *q;
+	} hfwd;
 };
 
 struct airoha_gdm_port {
@@ -809,20 +820,10 @@ struct airoha_eth {
 	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
 	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
 
-	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
-	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
-
 	struct net_device *napi_dev;
-	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
-	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
-
-	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
 
-	/* descriptor and packet buffers for qdma hw forward */
-	struct {
-		void *desc;
-		void *q;
-	} hfwd;
+	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
+	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
 };
 
 static u32 airoha_rr(void __iomem *base, u32 offset)
@@ -1390,7 +1391,7 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
 	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
 	struct airoha_qdma *qdma = &q->eth->qdma[0];
 	struct airoha_eth *eth = q->eth;
-	int qid = q - &eth->q_rx[0];
+	int qid = q - &qdma->q_rx[0];
 	int nframes = 0;
 
 	while (q->queued < q->ndesc - 1) {
@@ -1457,8 +1458,9 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
 static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 {
 	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
+	struct airoha_qdma *qdma = &q->eth->qdma[0];
 	struct airoha_eth *eth = q->eth;
-	int qid = q - &eth->q_rx[0];
+	int qid = q - &qdma->q_rx[0];
 	int done = 0;
 
 	while (done < budget) {
@@ -1549,7 +1551,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
 		.dev = eth->dev,
 		.napi = &q->napi,
 	};
-	int qid = q - &eth->q_rx[0], thr;
+	int qid = q - &qdma->q_rx[0], thr;
 	dma_addr_t dma_addr;
 
 	q->buf_size = PAGE_SIZE / 2;
@@ -1613,7 +1615,7 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth,
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) {
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
 		int err;
 
 		if (!(RX_DONE_INT_MASK & BIT(i))) {
@@ -1621,7 +1623,7 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth,
 			continue;
 		}
 
-		err = airoha_qdma_init_rx_queue(eth, &eth->q_rx[i],
+		err = airoha_qdma_init_rx_queue(eth, &qdma->q_rx[i],
 						qdma, RX_DSCP_NUM(i));
 		if (err)
 			return err;
@@ -1640,7 +1642,7 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 	irq_q = container_of(napi, struct airoha_tx_irq_queue, napi);
 	eth = irq_q->eth;
 	qdma = &eth->qdma[0];
-	id = irq_q - &eth->q_tx_irq[0];
+	id = irq_q - &qdma->q_tx_irq[0];
 
 	while (irq_q->queued > 0 && done < budget) {
 		u32 qid, last, val = irq_q->q[irq_q->head];
@@ -1657,10 +1659,10 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 		last = FIELD_GET(IRQ_DESC_IDX_MASK, val);
 		qid = FIELD_GET(IRQ_RING_IDX_MASK, val);
 
-		if (qid >= ARRAY_SIZE(eth->q_tx))
+		if (qid >= ARRAY_SIZE(qdma->q_tx))
 			continue;
 
-		q = &eth->q_tx[qid];
+		q = &qdma->q_tx[qid];
 		if (!q->ndesc)
 			continue;
 
@@ -1726,7 +1728,7 @@ static int airoha_qdma_init_tx_queue(struct airoha_eth *eth,
 				     struct airoha_queue *q,
 				     struct airoha_qdma *qdma, int size)
 {
-	int i, qid = q - &eth->q_tx[0];
+	int i, qid = q - &qdma->q_tx[0];
 	dma_addr_t dma_addr;
 
 	spin_lock_init(&q->lock);
@@ -1764,7 +1766,7 @@ static int airoha_qdma_tx_irq_init(struct airoha_eth *eth,
 				   struct airoha_tx_irq_queue *irq_q,
 				   struct airoha_qdma *qdma, int size)
 {
-	int id = irq_q - &eth->q_tx_irq[0];
+	int id = irq_q - &qdma->q_tx_irq[0];
 	dma_addr_t dma_addr;
 
 	netif_napi_add_tx(eth->napi_dev, &irq_q->napi,
@@ -1792,15 +1794,15 @@ static int airoha_qdma_init_tx(struct airoha_eth *eth,
 {
 	int i, err;
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) {
-		err = airoha_qdma_tx_irq_init(eth, &eth->q_tx_irq[i],
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) {
+		err = airoha_qdma_tx_irq_init(eth, &qdma->q_tx_irq[i],
 					      qdma, IRQ_QUEUE_LEN(i));
 		if (err)
 			return err;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) {
-		err = airoha_qdma_init_tx_queue(eth, &eth->q_tx[i],
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
+		err = airoha_qdma_init_tx_queue(eth, &qdma->q_tx[i],
 						qdma, TX_DSCP_NUM);
 		if (err)
 			return err;
@@ -1836,17 +1838,17 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth,
 	int size;
 
 	size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
-	eth->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					     GFP_KERNEL);
-	if (!eth->hfwd.desc)
+	qdma->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr,
+					      GFP_KERNEL);
+	if (!qdma->hfwd.desc)
 		return -ENOMEM;
 
 	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
 
 	size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
-	eth->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr,
-					  GFP_KERNEL);
-	if (!eth->hfwd.q)
+	qdma->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr,
+					   GFP_KERNEL);
+	if (!qdma->hfwd.q)
 		return -ENOMEM;
 
 	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
@@ -1934,8 +1936,8 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth,
 	airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX4, INT_IDX4_MASK);
 
 	/* setup irq binding */
-	for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) {
-		if (!eth->q_tx[i].ndesc)
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
+		if (!qdma->q_tx[i].ndesc)
 			continue;
 
 		if (TX_RING_IRQ_BLOCKING_MAP_MASK & BIT(i))
@@ -1960,8 +1962,8 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth,
 	airoha_qdma_init_qos(eth, qdma);
 
 	/* disable qdma rx delay interrupt */
-	for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) {
-		if (!eth->q_rx[i].ndesc)
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
 			continue;
 
 		airoha_qdma_clear(qdma, REG_RX_DELAY_INT_IDX(i),
@@ -1995,18 +1997,18 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 		airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX1,
 					RX_DONE_INT_MASK);
 
-		for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) {
-			if (!eth->q_rx[i].ndesc)
+		for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+			if (!qdma->q_rx[i].ndesc)
 				continue;
 
 			if (intr[1] & BIT(i))
-				napi_schedule(&eth->q_rx[i].napi);
+				napi_schedule(&qdma->q_rx[i].napi);
 		}
 	}
 
 	if (intr[0] & INT_TX_MASK) {
-		for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) {
-			struct airoha_tx_irq_queue *irq_q = &eth->q_tx_irq[i];
+		for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) {
+			struct airoha_tx_irq_queue *irq_q = &qdma->q_tx_irq[i];
 			u32 status, head;
 
 			if (!(intr[0] & TX_DONE_INT_MASK(i)))
@@ -2020,7 +2022,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 			irq_q->head = head % irq_q->size;
 			irq_q->queued = FIELD_GET(IRQ_ENTRY_LEN_MASK, status);
 
-			napi_schedule(&eth->q_tx_irq[i].napi);
+			napi_schedule(&qdma->q_tx_irq[i].napi);
 		}
 	}
 
@@ -2079,44 +2081,46 @@ static int airoha_hw_init(struct airoha_eth *eth)
 
 static void airoha_hw_cleanup(struct airoha_eth *eth)
 {
+	struct airoha_qdma *qdma = &eth->qdma[0];
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) {
-		if (!eth->q_rx[i].ndesc)
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
 			continue;
 
-		napi_disable(&eth->q_rx[i].napi);
-		netif_napi_del(&eth->q_rx[i].napi);
-		airoha_qdma_cleanup_rx_queue(&eth->q_rx[i]);
-		if (eth->q_rx[i].page_pool)
-			page_pool_destroy(eth->q_rx[i].page_pool);
+		napi_disable(&qdma->q_rx[i].napi);
+		netif_napi_del(&qdma->q_rx[i].napi);
+		airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]);
+		if (qdma->q_rx[i].page_pool)
+			page_pool_destroy(qdma->q_rx[i].page_pool);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) {
-		napi_disable(&eth->q_tx_irq[i].napi);
-		netif_napi_del(&eth->q_tx_irq[i].napi);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) {
+		napi_disable(&qdma->q_tx_irq[i].napi);
+		netif_napi_del(&qdma->q_tx_irq[i].napi);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) {
-		if (!eth->q_tx[i].ndesc)
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
+		if (!qdma->q_tx[i].ndesc)
 			continue;
 
-		airoha_qdma_cleanup_tx_queue(&eth->q_tx[i]);
+		airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
 	}
 }
 
 static void airoha_qdma_start_napi(struct airoha_eth *eth)
 {
+	struct airoha_qdma *qdma = &eth->qdma[0];
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++)
-		napi_enable(&eth->q_tx_irq[i].napi);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++)
+		napi_enable(&qdma->q_tx_irq[i].napi);
 
-	for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) {
-		if (!eth->q_rx[i].ndesc)
+	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
+		if (!qdma->q_rx[i].ndesc)
 			continue;
 
-		napi_enable(&eth->q_rx[i].napi);
+		napi_enable(&qdma->q_rx[i].napi);
 	}
 }
 
@@ -2391,7 +2395,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	       FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f);
 
 	qdma = &eth->qdma[0];
-	q = &eth->q_tx[qid];
+	q = &qdma->q_tx[qid];
 	if (WARN_ON_ONCE(!q->ndesc))
 		goto error;
 
-- 
cgit v1.3-3-g829e


From 19e47fc2aeda3a657c4f64144ffd6e65f7a66601 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:05 +0200
Subject: net: airoha: Move irq_mask in airoha_qdma structure

QDMA controllers have independent irq lines, so move irqmask in
airoha_qdma structure. This is a preliminary patch to support multiple
QDMA controllers.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/1c8a06e8be605278a7b2f3cd8ac06e74bf5ebf2b.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 84 +++++++++++++++---------------
 1 file changed, 42 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index fc6712216c47..48d0b44e6d92 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -786,6 +786,11 @@ struct airoha_hw_stats {
 struct airoha_qdma {
 	void __iomem *regs;
 
+	/* protect concurrent irqmask accesses */
+	spinlock_t irq_lock;
+	u32 irqmask[QDMA_INT_REG_MAX];
+	int irq;
+
 	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
 
 	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
@@ -812,11 +817,6 @@ struct airoha_eth {
 	unsigned long state;
 	void __iomem *fe_regs;
 
-	/* protect concurrent irqmask accesses */
-	spinlock_t irq_lock;
-	u32 irqmask[QDMA_INT_REG_MAX];
-	int irq;
-
 	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
 	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
 
@@ -866,38 +866,37 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 #define airoha_qdma_clear(qdma, offset, val)			\
 	airoha_rmw((qdma)->regs, (offset), (val), 0)
 
-static void airoha_qdma_set_irqmask(struct airoha_eth *eth, int index,
+static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index,
 				    u32 clear, u32 set)
 {
 	unsigned long flags;
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(eth->irqmask)))
+	if (WARN_ON_ONCE(index >= ARRAY_SIZE(qdma->irqmask)))
 		return;
 
-	spin_lock_irqsave(&eth->irq_lock, flags);
+	spin_lock_irqsave(&qdma->irq_lock, flags);
 
-	eth->irqmask[index] &= ~clear;
-	eth->irqmask[index] |= set;
-	airoha_qdma_wr(&eth->qdma[0], REG_INT_ENABLE(index),
-		       eth->irqmask[index]);
+	qdma->irqmask[index] &= ~clear;
+	qdma->irqmask[index] |= set;
+	airoha_qdma_wr(qdma, REG_INT_ENABLE(index), qdma->irqmask[index]);
 	/* Read irq_enable register in order to guarantee the update above
 	 * completes in the spinlock critical section.
 	 */
-	airoha_qdma_rr(&eth->qdma[0], REG_INT_ENABLE(index));
+	airoha_qdma_rr(qdma, REG_INT_ENABLE(index));
 
-	spin_unlock_irqrestore(&eth->irq_lock, flags);
+	spin_unlock_irqrestore(&qdma->irq_lock, flags);
 }
 
-static void airoha_qdma_irq_enable(struct airoha_eth *eth, int index,
+static void airoha_qdma_irq_enable(struct airoha_qdma *qdma, int index,
 				   u32 mask)
 {
-	airoha_qdma_set_irqmask(eth, index, 0, mask);
+	airoha_qdma_set_irqmask(qdma, index, 0, mask);
 }
 
-static void airoha_qdma_irq_disable(struct airoha_eth *eth, int index,
+static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index,
 				    u32 mask)
 {
-	airoha_qdma_set_irqmask(eth, index, mask, 0);
+	airoha_qdma_set_irqmask(qdma, index, mask, 0);
 }
 
 static void airoha_set_macaddr(struct airoha_eth *eth, const u8 *addr)
@@ -1522,7 +1521,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct airoha_queue *q = container_of(napi, struct airoha_queue, napi);
-	struct airoha_eth *eth = q->eth;
+	struct airoha_qdma *qdma = &q->eth->qdma[0];
 	int cur, done = 0;
 
 	do {
@@ -1531,7 +1530,7 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 	} while (cur && done < budget);
 
 	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX1,
+		airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1,
 				       RX_DONE_INT_MASK);
 
 	return done;
@@ -1718,7 +1717,7 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 	}
 
 	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0,
+		airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0,
 				       TX_DONE_INT_MASK(id));
 
 	return done;
@@ -1927,13 +1926,13 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth,
 	int i;
 
 	/* clear pending irqs */
-	for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++)
+	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++)
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff);
 
 	/* setup irqs */
-	airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0, INT_IDX0_MASK);
-	airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX1, INT_IDX1_MASK);
-	airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX4, INT_IDX4_MASK);
+	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, INT_IDX0_MASK);
+	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1, INT_IDX1_MASK);
+	airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX4, INT_IDX4_MASK);
 
 	/* setup irq binding */
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
@@ -1979,14 +1978,13 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth,
 static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 {
 	struct airoha_eth *eth = dev_instance;
-	u32 intr[ARRAY_SIZE(eth->irqmask)];
-	struct airoha_qdma *qdma;
+	struct airoha_qdma *qdma = &eth->qdma[0];
+	u32 intr[ARRAY_SIZE(qdma->irqmask)];
 	int i;
 
-	qdma = &eth->qdma[0];
-	for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++) {
+	for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) {
 		intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i));
-		intr[i] &= eth->irqmask[i];
+		intr[i] &= qdma->irqmask[i];
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]);
 	}
 
@@ -1994,7 +1992,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 		return IRQ_NONE;
 
 	if (intr[1] & RX_DONE_INT_MASK) {
-		airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX1,
+		airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX1,
 					RX_DONE_INT_MASK);
 
 		for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
@@ -2014,7 +2012,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 			if (!(intr[0] & TX_DONE_INT_MASK(i)))
 				continue;
 
-			airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX0,
+			airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0,
 						TX_DONE_INT_MASK(i));
 
 			status = airoha_qdma_rr(qdma, REG_IRQ_STATUS(i));
@@ -2029,12 +2027,18 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 	return IRQ_HANDLED;
 }
 
-static int airoha_qdma_init(struct airoha_eth *eth)
+static int airoha_qdma_init(struct platform_device *pdev,
+			    struct airoha_eth *eth)
 {
 	struct airoha_qdma *qdma = &eth->qdma[0];
 	int err;
 
-	err = devm_request_irq(eth->dev, eth->irq, airoha_irq_handler,
+	spin_lock_init(&qdma->irq_lock);
+	qdma->irq = platform_get_irq(pdev, 0);
+	if (qdma->irq < 0)
+		return qdma->irq;
+
+	err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler,
 			       IRQF_SHARED, KBUILD_MODNAME, eth);
 	if (err)
 		return err;
@@ -2060,7 +2064,8 @@ static int airoha_qdma_init(struct airoha_eth *eth)
 	return 0;
 }
 
-static int airoha_hw_init(struct airoha_eth *eth)
+static int airoha_hw_init(struct platform_device *pdev,
+			  struct airoha_eth *eth)
 {
 	int err;
 
@@ -2076,7 +2081,7 @@ static int airoha_hw_init(struct airoha_eth *eth)
 	if (err)
 		return err;
 
-	return airoha_qdma_init(eth);
+	return airoha_qdma_init(pdev, eth);
 }
 
 static void airoha_hw_cleanup(struct airoha_eth *eth)
@@ -2673,11 +2678,6 @@ static int airoha_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	spin_lock_init(&eth->irq_lock);
-	eth->irq = platform_get_irq(pdev, 0);
-	if (eth->irq < 0)
-		return eth->irq;
-
 	eth->napi_dev = alloc_netdev_dummy(0);
 	if (!eth->napi_dev)
 		return -ENOMEM;
@@ -2687,7 +2687,7 @@ static int airoha_probe(struct platform_device *pdev)
 	strscpy(eth->napi_dev->name, "qdma_eth", sizeof(eth->napi_dev->name));
 	platform_set_drvdata(pdev, eth);
 
-	err = airoha_hw_init(eth);
+	err = airoha_hw_init(pdev, eth);
 	if (err)
 		goto error;
 
-- 
cgit v1.3-3-g829e


From 9a2500ab22f059e596942172a8e4a60ae8243ce4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:06 +0200
Subject: net: airoha: Add airoha_qdma pointer in
 airoha_tx_irq_queue/airoha_queue structures

Move airoha_eth pointer in airoha_qdma structure from
airoha_tx_irq_queue/airoha_queue ones. This is a preliminary patch to
introduce support for multi-QDMA controllers available on EN7581.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/074565b82fd0ceefe66e186f21133d825dbd48eb.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 84 +++++++++++++++---------------
 1 file changed, 41 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 48d0b44e6d92..54515c8a8b03 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -728,7 +728,7 @@ struct airoha_queue_entry {
 };
 
 struct airoha_queue {
-	struct airoha_eth *eth;
+	struct airoha_qdma *qdma;
 
 	/* protect concurrent queue accesses */
 	spinlock_t lock;
@@ -747,7 +747,7 @@ struct airoha_queue {
 };
 
 struct airoha_tx_irq_queue {
-	struct airoha_eth *eth;
+	struct airoha_qdma *qdma;
 
 	struct napi_struct napi;
 	u32 *q;
@@ -784,6 +784,7 @@ struct airoha_hw_stats {
 };
 
 struct airoha_qdma {
+	struct airoha_eth *eth;
 	void __iomem *regs;
 
 	/* protect concurrent irqmask accesses */
@@ -1388,8 +1389,8 @@ static int airoha_fe_init(struct airoha_eth *eth)
 static int airoha_qdma_fill_rx_queue(struct airoha_queue *q)
 {
 	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
-	struct airoha_qdma *qdma = &q->eth->qdma[0];
-	struct airoha_eth *eth = q->eth;
+	struct airoha_qdma *qdma = q->qdma;
+	struct airoha_eth *eth = qdma->eth;
 	int qid = q - &qdma->q_rx[0];
 	int nframes = 0;
 
@@ -1457,8 +1458,8 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
 static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 {
 	enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool);
-	struct airoha_qdma *qdma = &q->eth->qdma[0];
-	struct airoha_eth *eth = q->eth;
+	struct airoha_qdma *qdma = q->qdma;
+	struct airoha_eth *eth = qdma->eth;
 	int qid = q - &qdma->q_rx[0];
 	int done = 0;
 
@@ -1521,7 +1522,6 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct airoha_queue *q = container_of(napi, struct airoha_queue, napi);
-	struct airoha_qdma *qdma = &q->eth->qdma[0];
 	int cur, done = 0;
 
 	do {
@@ -1530,14 +1530,13 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget)
 	} while (cur && done < budget);
 
 	if (done < budget && napi_complete(napi))
-		airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1,
+		airoha_qdma_irq_enable(q->qdma, QDMA_INT_REG_IDX1,
 				       RX_DONE_INT_MASK);
 
 	return done;
 }
 
-static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
-				     struct airoha_queue *q,
+static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
 				     struct airoha_qdma *qdma, int ndesc)
 {
 	const struct page_pool_params pp_params = {
@@ -1547,15 +1546,16 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
 		.dma_dir = DMA_FROM_DEVICE,
 		.max_len = PAGE_SIZE,
 		.nid = NUMA_NO_NODE,
-		.dev = eth->dev,
+		.dev = qdma->eth->dev,
 		.napi = &q->napi,
 	};
+	struct airoha_eth *eth = qdma->eth;
 	int qid = q - &qdma->q_rx[0], thr;
 	dma_addr_t dma_addr;
 
 	q->buf_size = PAGE_SIZE / 2;
 	q->ndesc = ndesc;
-	q->eth = eth;
+	q->qdma = qdma;
 
 	q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry),
 				GFP_KERNEL);
@@ -1595,7 +1595,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth,
 
 static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 {
-	struct airoha_eth *eth = q->eth;
+	struct airoha_eth *eth = q->qdma->eth;
 
 	while (q->queued) {
 		struct airoha_queue_entry *e = &q->entry[q->tail];
@@ -1609,8 +1609,7 @@ static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q)
 	}
 }
 
-static int airoha_qdma_init_rx(struct airoha_eth *eth,
-			       struct airoha_qdma *qdma)
+static int airoha_qdma_init_rx(struct airoha_qdma *qdma)
 {
 	int i;
 
@@ -1622,8 +1621,8 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth,
 			continue;
 		}
 
-		err = airoha_qdma_init_rx_queue(eth, &qdma->q_rx[i],
-						qdma, RX_DSCP_NUM(i));
+		err = airoha_qdma_init_rx_queue(&qdma->q_rx[i], qdma,
+						RX_DSCP_NUM(i));
 		if (err)
 			return err;
 	}
@@ -1639,9 +1638,9 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 	int id, done = 0;
 
 	irq_q = container_of(napi, struct airoha_tx_irq_queue, napi);
-	eth = irq_q->eth;
-	qdma = &eth->qdma[0];
+	qdma = irq_q->qdma;
 	id = irq_q - &qdma->q_tx_irq[0];
+	eth = qdma->eth;
 
 	while (irq_q->queued > 0 && done < budget) {
 		u32 qid, last, val = irq_q->q[irq_q->head];
@@ -1723,16 +1722,16 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget)
 	return done;
 }
 
-static int airoha_qdma_init_tx_queue(struct airoha_eth *eth,
-				     struct airoha_queue *q,
+static int airoha_qdma_init_tx_queue(struct airoha_queue *q,
 				     struct airoha_qdma *qdma, int size)
 {
+	struct airoha_eth *eth = qdma->eth;
 	int i, qid = q - &qdma->q_tx[0];
 	dma_addr_t dma_addr;
 
 	spin_lock_init(&q->lock);
 	q->ndesc = size;
-	q->eth = eth;
+	q->qdma = qdma;
 	q->free_thr = 1 + MAX_SKB_FRAGS;
 
 	q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry),
@@ -1761,11 +1760,11 @@ static int airoha_qdma_init_tx_queue(struct airoha_eth *eth,
 	return 0;
 }
 
-static int airoha_qdma_tx_irq_init(struct airoha_eth *eth,
-				   struct airoha_tx_irq_queue *irq_q,
+static int airoha_qdma_tx_irq_init(struct airoha_tx_irq_queue *irq_q,
 				   struct airoha_qdma *qdma, int size)
 {
 	int id = irq_q - &qdma->q_tx_irq[0];
+	struct airoha_eth *eth = qdma->eth;
 	dma_addr_t dma_addr;
 
 	netif_napi_add_tx(eth->napi_dev, &irq_q->napi,
@@ -1777,7 +1776,7 @@ static int airoha_qdma_tx_irq_init(struct airoha_eth *eth,
 
 	memset(irq_q->q, 0xff, size * sizeof(u32));
 	irq_q->size = size;
-	irq_q->eth = eth;
+	irq_q->qdma = qdma;
 
 	airoha_qdma_wr(qdma, REG_TX_IRQ_BASE(id), dma_addr);
 	airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK,
@@ -1788,21 +1787,20 @@ static int airoha_qdma_tx_irq_init(struct airoha_eth *eth,
 	return 0;
 }
 
-static int airoha_qdma_init_tx(struct airoha_eth *eth,
-			       struct airoha_qdma *qdma)
+static int airoha_qdma_init_tx(struct airoha_qdma *qdma)
 {
 	int i, err;
 
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) {
-		err = airoha_qdma_tx_irq_init(eth, &qdma->q_tx_irq[i],
-					      qdma, IRQ_QUEUE_LEN(i));
+		err = airoha_qdma_tx_irq_init(&qdma->q_tx_irq[i], qdma,
+					      IRQ_QUEUE_LEN(i));
 		if (err)
 			return err;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
-		err = airoha_qdma_init_tx_queue(eth, &qdma->q_tx[i],
-						qdma, TX_DSCP_NUM);
+		err = airoha_qdma_init_tx_queue(&qdma->q_tx[i], qdma,
+						TX_DSCP_NUM);
 		if (err)
 			return err;
 	}
@@ -1812,7 +1810,7 @@ static int airoha_qdma_init_tx(struct airoha_eth *eth,
 
 static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 {
-	struct airoha_eth *eth = q->eth;
+	struct airoha_eth *eth = q->qdma->eth;
 
 	spin_lock_bh(&q->lock);
 	while (q->queued) {
@@ -1829,9 +1827,9 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 	spin_unlock_bh(&q->lock);
 }
 
-static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth,
-					struct airoha_qdma *qdma)
+static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 {
+	struct airoha_eth *eth = qdma->eth;
 	dma_addr_t dma_addr;
 	u32 status;
 	int size;
@@ -1869,8 +1867,7 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth,
 				 REG_LMGR_INIT_CFG);
 }
 
-static void airoha_qdma_init_qos(struct airoha_eth *eth,
-				 struct airoha_qdma *qdma)
+static void airoha_qdma_init_qos(struct airoha_qdma *qdma)
 {
 	airoha_qdma_clear(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK);
 	airoha_qdma_set(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK);
@@ -1920,8 +1917,7 @@ static void airoha_qdma_init_qos(struct airoha_eth *eth,
 			FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40));
 }
 
-static int airoha_qdma_hw_init(struct airoha_eth *eth,
-			       struct airoha_qdma *qdma)
+static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 {
 	int i;
 
@@ -1958,7 +1954,7 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth,
 		       GLOBAL_CFG_TX_WB_DONE_MASK |
 		       FIELD_PREP(GLOBAL_CFG_MAX_ISSUE_NUM_MASK, 2));
 
-	airoha_qdma_init_qos(eth, qdma);
+	airoha_qdma_init_qos(qdma);
 
 	/* disable qdma rx delay interrupt */
 	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
@@ -2034,6 +2030,8 @@ static int airoha_qdma_init(struct platform_device *pdev,
 	int err;
 
 	spin_lock_init(&qdma->irq_lock);
+	qdma->eth = eth;
+
 	qdma->irq = platform_get_irq(pdev, 0);
 	if (qdma->irq < 0)
 		return qdma->irq;
@@ -2043,19 +2041,19 @@ static int airoha_qdma_init(struct platform_device *pdev,
 	if (err)
 		return err;
 
-	err = airoha_qdma_init_rx(eth, qdma);
+	err = airoha_qdma_init_rx(qdma);
 	if (err)
 		return err;
 
-	err = airoha_qdma_init_tx(eth, qdma);
+	err = airoha_qdma_init_tx(qdma);
 	if (err)
 		return err;
 
-	err = airoha_qdma_init_hfwd_queues(eth, qdma);
+	err = airoha_qdma_init_hfwd_queues(qdma);
 	if (err)
 		return err;
 
-	err = airoha_qdma_hw_init(eth, qdma);
+	err = airoha_qdma_hw_init(qdma);
 	if (err)
 		return err;
 
-- 
cgit v1.3-3-g829e


From e3d6bfdfc0aeb8c1d7965413b1050ec07f9761e5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:07 +0200
Subject: net: airoha: Use qdma pointer as private structure in
 airoha_irq_handler routine

This is a preliminary patch to support multi-QDMA controllers.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/1e40c3cb973881c0eb3c3c247c78550da62054ab.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 54515c8a8b03..2ded99434a17 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -1973,8 +1973,7 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 
 static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 {
-	struct airoha_eth *eth = dev_instance;
-	struct airoha_qdma *qdma = &eth->qdma[0];
+	struct airoha_qdma *qdma = dev_instance;
 	u32 intr[ARRAY_SIZE(qdma->irqmask)];
 	int i;
 
@@ -1984,7 +1983,7 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 		airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]);
 	}
 
-	if (!test_bit(DEV_STATE_INITIALIZED, &eth->state))
+	if (!test_bit(DEV_STATE_INITIALIZED, &qdma->eth->state))
 		return IRQ_NONE;
 
 	if (intr[1] & RX_DONE_INT_MASK) {
@@ -2037,7 +2036,7 @@ static int airoha_qdma_init(struct platform_device *pdev,
 		return qdma->irq;
 
 	err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler,
-			       IRQF_SHARED, KBUILD_MODNAME, eth);
+			       IRQF_SHARED, KBUILD_MODNAME, qdma);
 	if (err)
 		return err;
 
-- 
cgit v1.3-3-g829e


From e618447cf492d04415007336eec025fae6e9a2ea Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:08 +0200
Subject: net: airoha: Allow mapping IO region for multiple qdma controllers

Map MMIO regions of both qdma controllers available on EN7581 SoC.
Run airoha_hw_cleanup routine for both QDMA controllers available on
EN7581 SoC removing airoha_eth module or in airoha_probe error path.
This is a preliminary patch to support multi-QDMA controllers.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/a734ae608da14b67ae749b375d880dbbc70868ea.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 56 +++++++++++++++++-------------
 1 file changed, 32 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 2ded99434a17..5286afbc6f3f 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -2023,15 +2023,25 @@ static irqreturn_t airoha_irq_handler(int irq, void *dev_instance)
 }
 
 static int airoha_qdma_init(struct platform_device *pdev,
-			    struct airoha_eth *eth)
+			    struct airoha_eth *eth,
+			    struct airoha_qdma *qdma)
 {
-	struct airoha_qdma *qdma = &eth->qdma[0];
-	int err;
+	int err, id = qdma - &eth->qdma[0];
+	const char *res;
 
 	spin_lock_init(&qdma->irq_lock);
 	qdma->eth = eth;
 
-	qdma->irq = platform_get_irq(pdev, 0);
+	res = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d", id);
+	if (!res)
+		return -ENOMEM;
+
+	qdma->regs = devm_platform_ioremap_resource_byname(pdev, res);
+	if (IS_ERR(qdma->regs))
+		return dev_err_probe(eth->dev, PTR_ERR(qdma->regs),
+				     "failed to iomap qdma%d regs\n", id);
+
+	qdma->irq = platform_get_irq(pdev, 4 * id);
 	if (qdma->irq < 0)
 		return qdma->irq;
 
@@ -2052,19 +2062,13 @@ static int airoha_qdma_init(struct platform_device *pdev,
 	if (err)
 		return err;
 
-	err = airoha_qdma_hw_init(qdma);
-	if (err)
-		return err;
-
-	set_bit(DEV_STATE_INITIALIZED, &eth->state);
-
-	return 0;
+	return airoha_qdma_hw_init(qdma);
 }
 
 static int airoha_hw_init(struct platform_device *pdev,
 			  struct airoha_eth *eth)
 {
-	int err;
+	int err, i;
 
 	/* disable xsi */
 	reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), eth->xsi_rsts);
@@ -2078,12 +2082,19 @@ static int airoha_hw_init(struct platform_device *pdev,
 	if (err)
 		return err;
 
-	return airoha_qdma_init(pdev, eth);
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) {
+		err = airoha_qdma_init(pdev, eth, &eth->qdma[i]);
+		if (err)
+			return err;
+	}
+
+	set_bit(DEV_STATE_INITIALIZED, &eth->state);
+
+	return 0;
 }
 
-static void airoha_hw_cleanup(struct airoha_eth *eth)
+static void airoha_hw_cleanup(struct airoha_qdma *qdma)
 {
-	struct airoha_qdma *qdma = &eth->qdma[0];
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) {
@@ -2644,13 +2655,6 @@ static int airoha_probe(struct platform_device *pdev)
 		return dev_err_probe(eth->dev, PTR_ERR(eth->fe_regs),
 				     "failed to iomap fe regs\n");
 
-	eth->qdma[0].regs = devm_platform_ioremap_resource_byname(pdev,
-								  "qdma0");
-	if (IS_ERR(eth->qdma[0].regs))
-		return dev_err_probe(eth->dev,
-				     PTR_ERR(eth->qdma[0].regs),
-				     "failed to iomap qdma regs\n");
-
 	eth->rsts[0].id = "fe";
 	eth->rsts[1].id = "pdma";
 	eth->rsts[2].id = "qdma";
@@ -2706,7 +2710,9 @@ static int airoha_probe(struct platform_device *pdev)
 	return 0;
 
 error:
-	airoha_hw_cleanup(eth);
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+		airoha_hw_cleanup(&eth->qdma[i]);
+
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
 
@@ -2724,7 +2730,9 @@ static void airoha_remove(struct platform_device *pdev)
 	struct airoha_eth *eth = platform_get_drvdata(pdev);
 	int i;
 
-	airoha_hw_cleanup(eth);
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+		airoha_hw_cleanup(&eth->qdma[i]);
+
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
 
-- 
cgit v1.3-3-g829e


From 160231e34b8e9512ba20530f3e68fb0ac499af87 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:09 +0200
Subject: net: airoha: Start all qdma NAPIs in airoha_probe()

This is a preliminary patch to support multi-QDMA controllers.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/b51cf69c94d8cbc81e0a0b35587f024d01e6d9c0.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 5286afbc6f3f..13c72ab6d87a 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -2121,9 +2121,8 @@ static void airoha_hw_cleanup(struct airoha_qdma *qdma)
 	}
 }
 
-static void airoha_qdma_start_napi(struct airoha_eth *eth)
+static void airoha_qdma_start_napi(struct airoha_qdma *qdma)
 {
-	struct airoha_qdma *qdma = &eth->qdma[0];
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++)
@@ -2692,7 +2691,9 @@ static int airoha_probe(struct platform_device *pdev)
 	if (err)
 		goto error;
 
-	airoha_qdma_start_napi(eth);
+	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
+		airoha_qdma_start_napi(&eth->qdma[i]);
+
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_device_is_compatible(np, "airoha,eth-mac"))
 			continue;
-- 
cgit v1.3-3-g829e


From 9304640f2f78147dddf97a5ea01502ae175e41d9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 16:35:10 +0200
Subject: net: airoha: Link the gdm port to the selected qdma controller

Link the running gdm port to the qdma controller used to connect with
the CPU. Moreover, load all QDMA controllers available on EN7581 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/95b515df34ba4727f7ae5b14a1d0462cceec84ff.1722522582.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 37 +++++++++++++++---------------
 1 file changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 13c72ab6d87a..db4267225fa4 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -18,7 +18,7 @@
 #include <uapi/linux/ppp_defs.h>
 
 #define AIROHA_MAX_NUM_GDM_PORTS	1
-#define AIROHA_MAX_NUM_QDMA		1
+#define AIROHA_MAX_NUM_QDMA		2
 #define AIROHA_MAX_NUM_RSTS		3
 #define AIROHA_MAX_NUM_XSI_RSTS		5
 #define AIROHA_MAX_MTU			2000
@@ -805,8 +805,8 @@ struct airoha_qdma {
 };
 
 struct airoha_gdm_port {
+	struct airoha_qdma *qdma;
 	struct net_device *dev;
-	struct airoha_eth *eth;
 	int id;
 
 	struct airoha_hw_stats stats;
@@ -2138,7 +2138,7 @@ static void airoha_qdma_start_napi(struct airoha_qdma *qdma)
 
 static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 {
-	struct airoha_eth *eth = port->eth;
+	struct airoha_eth *eth = port->qdma->eth;
 	u32 val, i = 0;
 
 	spin_lock(&port->stats.lock);
@@ -2283,22 +2283,22 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 static int airoha_dev_open(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
-	struct airoha_eth *eth = port->eth;
+	struct airoha_qdma *qdma = port->qdma;
 	int err;
 
 	netif_tx_start_all_queues(dev);
-	err = airoha_set_gdm_ports(eth, true);
+	err = airoha_set_gdm_ports(qdma->eth, true);
 	if (err)
 		return err;
 
 	if (netdev_uses_dsa(dev))
-		airoha_fe_set(eth, REG_GDM_INGRESS_CFG(port->id),
+		airoha_fe_set(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
 			      GDM_STAG_EN_MASK);
 	else
-		airoha_fe_clear(eth, REG_GDM_INGRESS_CFG(port->id),
+		airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
 				GDM_STAG_EN_MASK);
 
-	airoha_qdma_set(&eth->qdma[0], REG_QDMA_GLOBAL_CFG,
+	airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG,
 			GLOBAL_CFG_TX_DMA_EN_MASK |
 			GLOBAL_CFG_RX_DMA_EN_MASK);
 
@@ -2308,15 +2308,15 @@ static int airoha_dev_open(struct net_device *dev)
 static int airoha_dev_stop(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
-	struct airoha_eth *eth = port->eth;
+	struct airoha_qdma *qdma = port->qdma;
 	int err;
 
 	netif_tx_disable(dev);
-	err = airoha_set_gdm_ports(eth, false);
+	err = airoha_set_gdm_ports(qdma->eth, false);
 	if (err)
 		return err;
 
-	airoha_qdma_clear(&eth->qdma[0], REG_QDMA_GLOBAL_CFG,
+	airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
 			  GLOBAL_CFG_TX_DMA_EN_MASK |
 			  GLOBAL_CFG_RX_DMA_EN_MASK);
 
@@ -2332,7 +2332,7 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
 	if (err)
 		return err;
 
-	airoha_set_macaddr(port->eth, dev->dev_addr);
+	airoha_set_macaddr(port->qdma->eth, dev->dev_addr);
 
 	return 0;
 }
@@ -2341,7 +2341,7 @@ static int airoha_dev_init(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
 
-	airoha_set_macaddr(port->eth, dev->dev_addr);
+	airoha_set_macaddr(port->qdma->eth, dev->dev_addr);
 
 	return 0;
 }
@@ -2375,10 +2375,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	struct airoha_gdm_port *port = netdev_priv(dev);
 	u32 msg0 = 0, msg1, len = skb_headlen(skb);
 	int i, qid = skb_get_queue_mapping(skb);
-	struct airoha_eth *eth = port->eth;
+	struct airoha_qdma *qdma = port->qdma;
 	u32 nr_frags = 1 + sinfo->nr_frags;
 	struct netdev_queue *txq;
-	struct airoha_qdma *qdma;
 	struct airoha_queue *q;
 	void *data = skb->data;
 	u16 index;
@@ -2406,7 +2405,6 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) |
 	       FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f);
 
-	qdma = &eth->qdma[0];
 	q = &qdma->q_tx[qid];
 	if (WARN_ON_ONCE(!q->ndesc))
 		goto error;
@@ -2489,7 +2487,7 @@ static void airoha_ethtool_get_drvinfo(struct net_device *dev,
 				       struct ethtool_drvinfo *info)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
-	struct airoha_eth *eth = port->eth;
+	struct airoha_eth *eth = port->qdma->eth;
 
 	strscpy(info->driver, eth->dev->driver->name, sizeof(info->driver));
 	strscpy(info->bus_info, dev_name(eth->dev), sizeof(info->bus_info));
@@ -2570,6 +2568,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 {
 	const __be32 *id_ptr = of_get_property(np, "reg", NULL);
 	struct airoha_gdm_port *port;
+	struct airoha_qdma *qdma;
 	struct net_device *dev;
 	int err, index;
 	u32 id;
@@ -2599,6 +2598,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 		return -ENOMEM;
 	}
 
+	qdma = &eth->qdma[index % AIROHA_MAX_NUM_QDMA];
 	dev->netdev_ops = &airoha_netdev_ops;
 	dev->ethtool_ops = &airoha_ethtool_ops;
 	dev->max_mtu = AIROHA_MAX_MTU;
@@ -2608,6 +2608,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 			   NETIF_F_SG | NETIF_F_TSO;
 	dev->features |= dev->hw_features;
 	dev->dev.of_node = np;
+	dev->irq = qdma->irq;
 	SET_NETDEV_DEV(dev, eth->dev);
 
 	err = of_get_ethdev_address(np, dev);
@@ -2623,8 +2624,8 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	port = netdev_priv(dev);
 	u64_stats_init(&port->stats.syncp);
 	spin_lock_init(&port->stats.lock);
+	port->qdma = qdma;
 	port->dev = dev;
-	port->eth = eth;
 	port->id = id;
 	eth->ports[index] = port;
 
-- 
cgit v1.3-3-g829e


From 7e1d512dab5042aa1c2224ed362be79e3f22a15e Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 1 Aug 2024 21:00:03 +0100
Subject: linkmode: Change return type of linkmode_andnot to bool

linkmode_andnot() simply returns the result of bitmap_andnot().
And the return type of bitmap_andnot() is bool.
So it makes sense for the return type of linkmode_andnot()
to also be bool.

I checked all call-sites and they either ignore the return
value or treat it as a bool.

Compile tested only.

Link: https://lore.kernel.org/netdev/68088998-4486-4930-90a4-96a32f08c490@lunn.ch/
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240801-linkfield-bowl-v1-1-d58f68967802@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/linkmode.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index d94bfd9ac8cc..3b9de09871f6 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -37,8 +37,9 @@ static inline bool linkmode_empty(const unsigned long *src)
 	return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1,
-				  const unsigned long *src2)
+static inline bool linkmode_andnot(unsigned long *dst,
+				   const unsigned long *src1,
+				   const unsigned long *src2)
 {
 	return bitmap_andnot(dst, src1, src2,  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
-- 
cgit v1.3-3-g829e


From f128c7cf0530cd104d1370648c29eff0b582700f Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Thu, 1 Aug 2024 16:12:14 -0500
Subject: ibmveth: Optimize poll rescheduling process

When the ibmveth driver processes less than the budget, it must call
napi_complete_done() to release the instance. This function will
return false if the driver should avoid rearming interrupts.
Previously, the driver was ignoring the return code of
napi_complete_done(). As a result, there were unnecessary calls to
enable the veth irq.
Therefore, use the return code napi_complete_done() to determine if
irq rearm is necessary.

Additionally, in the event that new data is received immediately after
rearming interrupts, rather than just rescheduling napi, also jump
back to the poll processing loop since we are already in the poll
function (and know that we did not expense all of budget).

This slight tweak results in a 15% increase in TCP_RR transaction rate
(320k to 370k txns). We can see the ftrace data supports this:
PREV: ibmveth_poll = 8818014.0 us / 182802.0 hits = AVG 48.24
NEW:  ibmveth_poll = 8082398.0 us / 191413.0 hits = AVG 42.22

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20240801211215.128101-2-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmveth.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 4c9d9badd698..e6eb594f0751 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1337,6 +1337,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	unsigned long lpar_rc;
 	u16 mss = 0;
 
+restart_poll:
 	while (frames_processed < budget) {
 		if (!ibmveth_rxq_pending_buffer(adapter))
 			break;
@@ -1420,24 +1421,25 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 
 	ibmveth_replenish_task(adapter);
 
-	if (frames_processed < budget) {
-		napi_complete_done(napi, frames_processed);
+	if (frames_processed == budget)
+		goto out;
 
-		/* We think we are done - reenable interrupts,
-		 * then check once more to make sure we are done.
-		 */
-		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
-				       VIO_IRQ_ENABLE);
+	if (!napi_complete_done(napi, frames_processed))
+		goto out;
 
-		BUG_ON(lpar_rc != H_SUCCESS);
+	/* We think we are done - reenable interrupts,
+	 * then check once more to make sure we are done.
+	 */
+	lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE);
+	BUG_ON(lpar_rc != H_SUCCESS);
 
-		if (ibmveth_rxq_pending_buffer(adapter) &&
-		    napi_schedule(napi)) {
-			lpar_rc = h_vio_signal(adapter->vdev->unit_address,
-					       VIO_IRQ_DISABLE);
-		}
+	if (ibmveth_rxq_pending_buffer(adapter) && napi_schedule(napi)) {
+		lpar_rc = h_vio_signal(adapter->vdev->unit_address,
+				       VIO_IRQ_DISABLE);
+		goto restart_poll;
 	}
 
+out:
 	return frames_processed;
 }
 
-- 
cgit v1.3-3-g829e


From b5381a5540cbb7c18642a3280cb3906160bd6546 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Thu, 1 Aug 2024 16:12:15 -0500
Subject: ibmveth: Recycle buffers during replenish phase

When the length of a packet is under the rx_copybreak threshold, the
buffer is copied into a new skb and sent up the stack. This allows the
dma mapped memory to be recycled back to FW.

Previously, the reuse of the DMA space was handled immediately.
This means that further packet processing has to wait until
h_add_logical_lan finishes for this packet.

Therefore, when reusing a packet, offload the hcall to the replenish
function. As a result, much of the shared logic between the recycle and
replenish functions can be removed.

This change increases TCP_RR packet rate by another 15% (370k to 430k
txns). We can see the ftrace data supports this:
PREV: ibmveth_poll = 8078553.0 us / 190999.0 hits = AVG 42.3 us
NEW:  ibmveth_poll = 7632787.0 us / 224060.0 hits = AVG 34.07 us

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20240801211215.128101-3-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmveth.c | 144 ++++++++++++++++---------------------
 1 file changed, 60 insertions(+), 84 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index e6eb594f0751..b619a3ec245b 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -39,7 +39,8 @@
 #include "ibmveth.h"
 
 static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter);
+static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
+				       bool reuse);
 static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev);
 
 static struct kobj_type ktype_veth_pool;
@@ -226,6 +227,16 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
 	for (i = 0; i < count; ++i) {
 		union ibmveth_buf_desc desc;
 
+		free_index = pool->consumer_index;
+		index = pool->free_map[free_index];
+		skb = NULL;
+
+		BUG_ON(index == IBM_VETH_INVALID_MAP);
+
+		/* are we allocating a new buffer or recycling an old one */
+		if (pool->skbuff[index])
+			goto reuse;
+
 		skb = netdev_alloc_skb(adapter->netdev, pool->buff_size);
 
 		if (!skb) {
@@ -235,46 +246,46 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
 			break;
 		}
 
-		free_index = pool->consumer_index;
-		pool->consumer_index++;
-		if (pool->consumer_index >= pool->size)
-			pool->consumer_index = 0;
-		index = pool->free_map[free_index];
-
-		BUG_ON(index == IBM_VETH_INVALID_MAP);
-		BUG_ON(pool->skbuff[index] != NULL);
-
 		dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
 				pool->buff_size, DMA_FROM_DEVICE);
 
 		if (dma_mapping_error(&adapter->vdev->dev, dma_addr))
 			goto failure;
 
-		pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
 		pool->dma_addr[index] = dma_addr;
 		pool->skbuff[index] = skb;
 
-		correlator = ((u64)pool->index << 32) | index;
-		*(u64 *)skb->data = correlator;
-
-		desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size;
-		desc.fields.address = dma_addr;
-
 		if (rx_flush) {
 			unsigned int len = min(pool->buff_size,
-						adapter->netdev->mtu +
-						IBMVETH_BUFF_OH);
+					       adapter->netdev->mtu +
+					       IBMVETH_BUFF_OH);
 			ibmveth_flush_buffer(skb->data, len);
 		}
+reuse:
+		dma_addr = pool->dma_addr[index];
+		desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size;
+		desc.fields.address = dma_addr;
+
+		correlator = ((u64)pool->index << 32) | index;
+		*(u64 *)pool->skbuff[index]->data = correlator;
+
 		lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address,
 						   desc.desc);
 
 		if (lpar_rc != H_SUCCESS) {
+			netdev_warn(adapter->netdev,
+				    "%sadd_logical_lan failed %lu\n",
+				    skb ? "" : "When recycling: ", lpar_rc);
 			goto failure;
-		} else {
-			buffers_added++;
-			adapter->replenish_add_buff_success++;
 		}
+
+		pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
+		pool->consumer_index++;
+		if (pool->consumer_index >= pool->size)
+			pool->consumer_index = 0;
+
+		buffers_added++;
+		adapter->replenish_add_buff_success++;
 	}
 
 	mb();
@@ -282,17 +293,13 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter,
 	return;
 
 failure:
-	pool->free_map[free_index] = index;
-	pool->skbuff[index] = NULL;
-	if (pool->consumer_index == 0)
-		pool->consumer_index = pool->size - 1;
-	else
-		pool->consumer_index--;
-	if (!dma_mapping_error(&adapter->vdev->dev, dma_addr))
+
+	if (dma_addr && !dma_mapping_error(&adapter->vdev->dev, dma_addr))
 		dma_unmap_single(&adapter->vdev->dev,
 		                 pool->dma_addr[index], pool->buff_size,
 		                 DMA_FROM_DEVICE);
-	dev_kfree_skb_any(skb);
+	dev_kfree_skb_any(pool->skbuff[index]);
+	pool->skbuff[index] = NULL;
 	adapter->replenish_add_buff_failure++;
 
 	mb();
@@ -365,7 +372,7 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter,
 
 /* remove a buffer from a pool */
 static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
-					    u64 correlator)
+					    u64 correlator, bool reuse)
 {
 	unsigned int pool  = correlator >> 32;
 	unsigned int index = correlator & 0xffffffffUL;
@@ -376,15 +383,23 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter,
 	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
 
 	skb = adapter->rx_buff_pool[pool].skbuff[index];
-
 	BUG_ON(skb == NULL);
 
-	adapter->rx_buff_pool[pool].skbuff[index] = NULL;
+	/* if we are going to reuse the buffer then keep the pointers around
+	 * but mark index as available. replenish will see the skb pointer and
+	 * assume it is to be recycled.
+	 */
+	if (!reuse) {
+		/* remove the skb pointer to mark free. actual freeing is done
+		 * by upper level networking after gro_recieve
+		 */
+		adapter->rx_buff_pool[pool].skbuff[index] = NULL;
 
-	dma_unmap_single(&adapter->vdev->dev,
-			 adapter->rx_buff_pool[pool].dma_addr[index],
-			 adapter->rx_buff_pool[pool].buff_size,
-			 DMA_FROM_DEVICE);
+		dma_unmap_single(&adapter->vdev->dev,
+				 adapter->rx_buff_pool[pool].dma_addr[index],
+				 adapter->rx_buff_pool[pool].buff_size,
+				 DMA_FROM_DEVICE);
+	}
 
 	free_index = adapter->rx_buff_pool[pool].producer_index;
 	adapter->rx_buff_pool[pool].producer_index++;
@@ -411,51 +426,13 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada
 	return adapter->rx_buff_pool[pool].skbuff[index];
 }
 
-/* recycle the current buffer on the rx queue */
-static int ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter)
+static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter,
+				       bool reuse)
 {
-	u32 q_index = adapter->rx_queue.index;
-	u64 correlator = adapter->rx_queue.queue_addr[q_index].correlator;
-	unsigned int pool = correlator >> 32;
-	unsigned int index = correlator & 0xffffffffUL;
-	union ibmveth_buf_desc desc;
-	unsigned long lpar_rc;
-	int ret = 1;
-
-	BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS);
-	BUG_ON(index >= adapter->rx_buff_pool[pool].size);
+	u64 cor;
 
-	if (!adapter->rx_buff_pool[pool].active) {
-		ibmveth_rxq_harvest_buffer(adapter);
-		ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]);
-		goto out;
-	}
-
-	desc.fields.flags_len = IBMVETH_BUF_VALID |
-		adapter->rx_buff_pool[pool].buff_size;
-	desc.fields.address = adapter->rx_buff_pool[pool].dma_addr[index];
-
-	lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);
-
-	if (lpar_rc != H_SUCCESS) {
-		netdev_dbg(adapter->netdev, "h_add_logical_lan_buffer failed "
-			   "during recycle rc=%ld", lpar_rc);
-		ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);
-		ret = 0;
-	}
-
-	if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
-		adapter->rx_queue.index = 0;
-		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
-	}
-
-out:
-	return ret;
-}
-
-static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter)
-{
-	ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);
+	cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
+	ibmveth_remove_buffer_from_pool(adapter, cor, reuse);
 
 	if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
 		adapter->rx_queue.index = 0;
@@ -1347,7 +1324,7 @@ restart_poll:
 			wmb(); /* suggested by larson1 */
 			adapter->rx_invalid_buffer++;
 			netdev_dbg(netdev, "recycling invalid buffer\n");
-			ibmveth_rxq_recycle_buffer(adapter);
+			ibmveth_rxq_harvest_buffer(adapter, true);
 		} else {
 			struct sk_buff *skb, *new_skb;
 			int length = ibmveth_rxq_frame_length(adapter);
@@ -1380,11 +1357,10 @@ restart_poll:
 				if (rx_flush)
 					ibmveth_flush_buffer(skb->data,
 						length + offset);
-				if (!ibmveth_rxq_recycle_buffer(adapter))
-					kfree_skb(skb);
+				ibmveth_rxq_harvest_buffer(adapter, true);
 				skb = new_skb;
 			} else {
-				ibmveth_rxq_harvest_buffer(adapter);
+				ibmveth_rxq_harvest_buffer(adapter, false);
 				skb_reserve(skb, offset);
 			}
 
-- 
cgit v1.3-3-g829e


From 6555a2a9212be6983d2319d65276484f7c5f431a Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 1 Aug 2024 19:35:37 +0100
Subject: tipc: guard against string buffer overrun

Smatch reports that copying media_name and if_name to name_parts may
overwrite the destination.

 .../bearer.c:166 bearer_name_validate() error: strcpy() 'media_name' too large for 'name_parts->media_name' (32 vs 16)
 .../bearer.c:167 bearer_name_validate() error: strcpy() 'if_name' too large for 'name_parts->if_name' (1010102 vs 16)

This does seem to be the case so guard against this possibility by using
strscpy() and failing if truncation occurs.

Introduced by commit b97bf3fd8f6a ("[TIPC] Initial merge")

Compile tested only.

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240801-tipic-overrun-v2-1-c5b869d1f074@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/bearer.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 5a526ebafeb4..3c9e25f6a1d2 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -163,8 +163,12 @@ static int bearer_name_validate(const char *name,
 
 	/* return bearer name components, if necessary */
 	if (name_parts) {
-		strcpy(name_parts->media_name, media_name);
-		strcpy(name_parts->if_name, if_name);
+		if (strscpy(name_parts->media_name, media_name,
+			    TIPC_MAX_MEDIA_NAME) < 0)
+			return 0;
+		if (strscpy(name_parts->if_name, if_name,
+			    TIPC_MAX_IF_NAME) < 0)
+			return 0;
 	}
 	return 1;
 }
-- 
cgit v1.3-3-g829e


From f94074687d05aea10b50c4f4055a19d9d0c3bd27 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 1 Aug 2024 17:23:11 +0300
Subject: net: core: annotate socks of struct sock_reuseport with __counted_by

According to '__reuseport_alloc()', annotate flexible array member
'sock' of 'struct sock_reuseport' with '__counted_by()' and use
convenient 'struct_size()' to simplify the math used in 'kzalloc()'.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240801142311.42837-1-dmantipov@yandex.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock_reuseport.h | 2 +-
 net/core/sock_reuseport.c    | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 6ec140b0a61b..6e4faf3ee76f 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -26,7 +26,7 @@ struct sock_reuseport {
 	unsigned int		bind_inany:1;
 	unsigned int		has_conns:1;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
-	struct sock		*socks[];	/* array of sock pointers */
+	struct sock		*socks[] __counted_by(max_socks);
 };
 
 extern int reuseport_alloc(struct sock *sk, bool bind_inany);
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 5a165286e4d8..4211710393a8 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -173,10 +173,9 @@ static bool __reuseport_detach_closed_sock(struct sock *sk,
 
 static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
-	unsigned int size = sizeof(struct sock_reuseport) +
-		      sizeof(struct sock *) * max_socks;
-	struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC);
+	struct sock_reuseport *reuse;
 
+	reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC);
 	if (!reuse)
 		return NULL;
 
-- 
cgit v1.3-3-g829e


From 7e51d21ee01077c538d87c22fc9a164bd9b60a53 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 31 Jul 2024 18:08:15 +0800
Subject: rxrpc: Remove unused function declarations

commit 3cec055c5695 ("rxrpc: Don't hold a ref for connection workqueue")
left behind rxrpc_put_client_conn().
And commit 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
removed rxrpc_accept_incoming_calls() but left declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240731100815.1277894-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/ar-internal.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 08de24658f4f..80d682f89b23 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -856,7 +856,6 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local,
 			     struct rxrpc_connection *conn,
 			     struct sockaddr_rxrpc *peer_srx,
 			     struct sk_buff *skb);
-void rxrpc_accept_incoming_calls(struct rxrpc_local *);
 int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long);
 
 /*
@@ -969,7 +968,6 @@ void rxrpc_connect_client_calls(struct rxrpc_local *local);
 void rxrpc_expose_client_call(struct rxrpc_call *);
 void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
 void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle);
-void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace);
 void rxrpc_discard_expired_client_conns(struct rxrpc_local *local);
 void rxrpc_clean_up_local_conns(struct rxrpc_local *);
 
-- 
cgit v1.3-3-g829e


From 8d5be2c4f4477915fee079572665198e70246b69 Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Wed, 31 Jul 2024 22:34:55 +0200
Subject: net: dsa: vsc73xx: speed up MDIO bus to max allowed value

According to the datasheet, the VSC73xx family's maximum internal MDIO bus
speed is 20 MHz. It also allows disabling the preamble.

This commit sets the MDIO clock prescaler to the minimum value and
disables the preamble to speed up MDIO operations.

It doesn't affect the external bus because it's configured in a different
subblock.

Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240731203455.580262-1-paweldembicki@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/vitesse-vsc73xx-core.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index 07b704a1557e..1711e780e65b 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -40,6 +40,9 @@
 #define VSC73XX_BLOCK_ARBITER	0x5 /* Only subblock 0 */
 #define VSC73XX_BLOCK_SYSTEM	0x7 /* Only subblock 0 */
 
+/* MII Block subblock */
+#define VSC73XX_BLOCK_MII_INTERNAL     0x0 /* Internal MDIO subblock */
+
 #define CPU_PORT	6 /* CPU port */
 
 /* MAC Block registers */
@@ -224,6 +227,11 @@
 #define VSC73XX_MII_STAT	0x0
 #define VSC73XX_MII_CMD		0x1
 #define VSC73XX_MII_DATA	0x2
+#define VSC73XX_MII_MPRES	0x3
+
+#define VSC73XX_MII_MPRES_NOPREAMBLE	BIT(6)
+#define VSC73XX_MII_MPRES_PRESCALEVAL	GENMASK(5, 0)
+#define VSC73XX_MII_PRESCALEVAL_MIN	3 /* min allowed mdio clock prescaler */
 
 /* Arbiter block 5 registers */
 #define VSC73XX_ARBEMPTY		0x0c
@@ -748,7 +756,7 @@ static int vsc73xx_configure_rgmii_port_delay(struct dsa_switch *ds)
 static int vsc73xx_setup(struct dsa_switch *ds)
 {
 	struct vsc73xx *vsc = ds->priv;
-	int i, ret;
+	int i, ret, val;
 
 	dev_info(vsc->dev, "set up the switch\n");
 
@@ -821,6 +829,15 @@ static int vsc73xx_setup(struct dsa_switch *ds)
 
 	mdelay(50);
 
+	/* Disable preamble and use maximum allowed clock for the internal
+	 * mdio bus, used for communication with internal PHYs only.
+	 */
+	val = VSC73XX_MII_MPRES_NOPREAMBLE |
+	      FIELD_PREP(VSC73XX_MII_MPRES_PRESCALEVAL,
+			 VSC73XX_MII_PRESCALEVAL_MIN);
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL,
+		      VSC73XX_MII_MPRES, val);
+
 	/* Release reset from the internal PHYs */
 	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
 		      VSC73XX_GLORESET_PHY_RESET);
-- 
cgit v1.3-3-g829e


From c4b28e5699d2a789fc9464e7ce89f2a1e9d5085d Mon Sep 17 00:00:00 2001
From: Kyle Swenson <kyle.swenson@est.tech>
Date: Wed, 31 Jul 2024 15:42:14 +0000
Subject: net: pse-pd: tps23881: Fix the device ID check

The DEVID register contains two pieces of information: the device ID in
the upper nibble, and the silicon revision number in the lower nibble.
The driver should work fine with any silicon revision, so let's mask
that out in the device ID check.

Fixes: 20e6d190ffe1 ("net: pse-pd: Add TI TPS23881 PSE controller driver")
Signed-off-by: Kyle Swenson <kyle.swenson@est.tech>
Reviewed-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/pse-pd/tps23881.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c
index 61f6ad9c1934..f90db758554b 100644
--- a/drivers/net/pse-pd/tps23881.c
+++ b/drivers/net/pse-pd/tps23881.c
@@ -29,6 +29,8 @@
 #define TPS23881_REG_TPON	BIT(0)
 #define TPS23881_REG_FWREV	0x41
 #define TPS23881_REG_DEVID	0x43
+#define TPS23881_REG_DEVID_MASK	0xF0
+#define TPS23881_DEVICE_ID	0x02
 #define TPS23881_REG_SRAM_CTRL	0x60
 #define TPS23881_REG_SRAM_DATA	0x61
 
@@ -750,7 +752,7 @@ static int tps23881_i2c_probe(struct i2c_client *client)
 	if (ret < 0)
 		return ret;
 
-	if (ret != 0x22) {
+	if (FIELD_GET(TPS23881_REG_DEVID_MASK, ret) != TPS23881_DEVICE_ID) {
 		dev_err(dev, "Wrong device ID\n");
 		return -ENXIO;
 	}
-- 
cgit v1.3-3-g829e


From 1ad001347fb1ca1f036144b42a6f1df6615e4104 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 31 Jul 2024 13:07:16 -0700
Subject: l2tp: Don't assign net->gen->ptr[] for pppol2tp_net_ops.

Commit fd558d186df2 ("l2tp: Split pppol2tp patch into separate l2tp and
ppp parts") converted net->gen->ptr[pppol2tp_net_id] in l2tp_ppp.c to
net->gen->ptr[l2tp_net_id] in l2tp_core.c.

Now the leftover wastes one entry of net->gen->ptr[] in each netns.

Let's avoid the unwanted allocation.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 90bf3a8ccab6..9b4273fd518a 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1393,8 +1393,6 @@ end:
  * L2TPv2, we dump only L2TPv2 tunnels and sessions here.
  *****************************************************************************/
 
-static unsigned int pppol2tp_net_id;
-
 #ifdef CONFIG_PROC_FS
 
 struct pppol2tp_seq_data {
@@ -1628,7 +1626,6 @@ static __net_exit void pppol2tp_exit_net(struct net *net)
 static struct pernet_operations pppol2tp_net_ops = {
 	.init = pppol2tp_init_net,
 	.exit = pppol2tp_exit_net,
-	.id   = &pppol2tp_net_id,
 };
 
 /*****************************************************************************
-- 
cgit v1.3-3-g829e


From 768e4bb6a75e3c6a034df7c67edac20bd222857e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 31 Jul 2024 13:07:17 -0700
Subject: net: Don't register pernet_operations if only one of id or size is
 specified.

We can allocate per-netns memory for struct pernet_operations by specifying
id and size.

register_pernet_operations() assigns an id to pernet_operations and later
ops_init() allocates the specified size of memory as net->gen->ptr[id].

If id is missing, no memory is allocated.  If size is not specified,
pernet_operations just wastes an entry of net->gen->ptr[] for every netns.

net_generic is available only when both id and size are specified, so let's
ensure that.

While we are at it, we add const to both fields.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h |  4 ++--
 net/core/net_namespace.c    | 12 ++++++++----
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 20c34bd7a077..e67b483cc8bb 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -451,8 +451,8 @@ struct pernet_operations {
 	/* Following method is called with RTNL held. */
 	void (*exit_batch_rtnl)(struct list_head *net_exit_list,
 				struct list_head *dev_kill_list);
-	unsigned int *id;
-	size_t size;
+	unsigned int * const id;
+	const size_t size;
 };
 
 /*
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6a823ba906c6..1cd87df13f39 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -125,7 +125,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
 	int err = -ENOMEM;
 	void *data = NULL;
 
-	if (ops->id && ops->size) {
+	if (ops->id) {
 		data = kzalloc(ops->size, GFP_KERNEL);
 		if (!data)
 			goto out;
@@ -140,7 +140,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
 	if (!err)
 		return 0;
 
-	if (ops->id && ops->size) {
+	if (ops->id) {
 		ng = rcu_dereference_protected(net->gen,
 					       lockdep_is_held(&pernet_ops_rwsem));
 		ng->ptr[*ops->id] = NULL;
@@ -182,7 +182,8 @@ static void ops_free_list(const struct pernet_operations *ops,
 			  struct list_head *net_exit_list)
 {
 	struct net *net;
-	if (ops->size && ops->id) {
+
+	if (ops->id) {
 		list_for_each_entry(net, net_exit_list, exit_list)
 			kfree(net_generic(net, *ops->id));
 	}
@@ -1244,7 +1245,7 @@ static int __register_pernet_operations(struct list_head *list,
 	LIST_HEAD(net_exit_list);
 
 	list_add_tail(&ops->list, list);
-	if (ops->init || (ops->id && ops->size)) {
+	if (ops->init || ops->id) {
 		/* We held write locked pernet_ops_rwsem, and parallel
 		 * setup_net() and cleanup_net() are not possible.
 		 */
@@ -1310,6 +1311,9 @@ static int register_pernet_operations(struct list_head *list,
 {
 	int error;
 
+	if (WARN_ON(!!ops->id ^ !!ops->size))
+		return -EINVAL;
+
 	if (ops->id) {
 		error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID,
 				GFP_KERNEL);
-- 
cgit v1.3-3-g829e


From 2b5afc1d5d5a33060034f0f275bc0e9c243394bb Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 31 Jul 2024 13:07:18 -0700
Subject: net: Initialise net->passive once in preinit_net().

When initialising the root netns, we set net->passive in setup_net().

However, we do it twice for non-root netns in copy_net_ns() and
setup_net().

This is because we could bypass setup_net() in copy_net_ns() if
down_read_killable() fails.

preinit_net() is a better place to put such an operation.

Let's initialise net->passive in preinit_net().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 1cd87df13f39..6c9acb086852 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -312,6 +312,7 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_id);
 /* init code that must occur even if setup_net() is not called. */
 static __net_init void preinit_net(struct net *net)
 {
+	refcount_set(&net->passive, 1);
 	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt");
 }
 
@@ -329,7 +330,6 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	refcount_set(&net->ns.count, 1);
 	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
 
-	refcount_set(&net->passive, 1);
 	get_random_bytes(&net->hash_mix, sizeof(u32));
 	preempt_disable();
 	net->net_cookie = gen_cookie_next(&net_cookie);
@@ -498,7 +498,6 @@ struct net *copy_net_ns(unsigned long flags,
 	}
 
 	preinit_net(net);
-	refcount_set(&net->passive, 1);
 	net->ucounts = ucounts;
 	get_user_ns(user_ns);
 
-- 
cgit v1.3-3-g829e


From 930299491825575503ec411ff28473aaa6b8c9ca Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 31 Jul 2024 13:07:19 -0700
Subject: net: Call preinit_net() without pernet_ops_rwsem.

When initialising the root netns, we call preinit_net() under
pernet_ops_rwsem.

However, the operations in preinit_net() do not require pernet_ops_rwsem.

Also, we don't hold it for preinit_net() when initialising non-root netns.

To be consistent, let's call preinit_net() without pernet_ops_rwsem in
net_ns_init().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6c9acb086852..b91c15b27fb2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -1199,8 +1199,9 @@ void __init net_ns_init(void)
 #ifdef CONFIG_KEYS
 	init_net.key_domain = &init_net_key_domain;
 #endif
-	down_write(&pernet_ops_rwsem);
 	preinit_net(&init_net);
+
+	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
 		panic("Could not setup the initial network namespace");
 
-- 
cgit v1.3-3-g829e


From 05be8012594451fbeb7e6319107440eef27bd17b Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 31 Jul 2024 13:07:20 -0700
Subject: net: Slim down setup_net().

Most initialisations in setup_net() do not require pernet_ops_rwsem
and can be moved to preinit_net().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b91c15b27fb2..eed5a28e8ee3 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -310,16 +310,26 @@ struct net *get_net_ns_by_id(const struct net *net, int id)
 EXPORT_SYMBOL_GPL(get_net_ns_by_id);
 
 /* init code that must occur even if setup_net() is not called. */
-static __net_init void preinit_net(struct net *net)
+static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns)
 {
 	refcount_set(&net->passive, 1);
+	refcount_set(&net->ns.count, 1);
+	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
 	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt");
+
+	get_random_bytes(&net->hash_mix, sizeof(u32));
+	net->dev_base_seq = 1;
+	net->user_ns = user_ns;
+
+	idr_init(&net->netns_ids);
+	spin_lock_init(&net->nsid_lock);
+	mutex_init(&net->ipv4.ra_mutex);
 }
 
 /*
  * setup_net runs the initializers for the network namespace object.
  */
-static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
+static __net_init int setup_net(struct net *net)
 {
 	/* Must be called with pernet_ops_rwsem held */
 	const struct pernet_operations *ops, *saved_ops;
@@ -327,18 +337,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	LIST_HEAD(dev_kill_list);
 	int error = 0;
 
-	refcount_set(&net->ns.count, 1);
-	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
-
-	get_random_bytes(&net->hash_mix, sizeof(u32));
 	preempt_disable();
 	net->net_cookie = gen_cookie_next(&net_cookie);
 	preempt_enable();
-	net->dev_base_seq = 1;
-	net->user_ns = user_ns;
-	idr_init(&net->netns_ids);
-	spin_lock_init(&net->nsid_lock);
-	mutex_init(&net->ipv4.ra_mutex);
 
 	list_for_each_entry(ops, &pernet_list, list) {
 		error = ops_init(ops, net);
@@ -497,7 +498,7 @@ struct net *copy_net_ns(unsigned long flags,
 		goto dec_ucounts;
 	}
 
-	preinit_net(net);
+	preinit_net(net, user_ns);
 	net->ucounts = ucounts;
 	get_user_ns(user_ns);
 
@@ -505,7 +506,7 @@ struct net *copy_net_ns(unsigned long flags,
 	if (rv < 0)
 		goto put_userns;
 
-	rv = setup_net(net, user_ns);
+	rv = setup_net(net);
 
 	up_read(&pernet_ops_rwsem);
 
@@ -1199,10 +1200,10 @@ void __init net_ns_init(void)
 #ifdef CONFIG_KEYS
 	init_net.key_domain = &init_net_key_domain;
 #endif
-	preinit_net(&init_net);
+	preinit_net(&init_net, &init_user_ns);
 
 	down_write(&pernet_ops_rwsem);
-	if (setup_net(&init_net, &init_user_ns))
+	if (setup_net(&init_net))
 		panic("Could not setup the initial network namespace");
 
 	init_net_initialized = true;
-- 
cgit v1.3-3-g829e


From 8eaf71f77c923f13e41a146703b93fa7988d101f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 31 Jul 2024 13:07:21 -0700
Subject: net: Initialise net.core sysctl defaults in preinit_net().

Commit 7c3f1875c66f ("net: move somaxconn init from sysctl code")
introduced net_defaults_ops to make sure that net.core sysctl knobs
are always initialised even if CONFIG_SYSCTL is disabled.

Such operations better fit preinit_net() added for a similar purpose
by commit 6e77a5a4af05 ("net: initialize net->notrefcnt_tracker earlier").

Let's initialise the sysctl defaults in preinit_net().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net_namespace.c | 37 +++++++++++--------------------------
 1 file changed, 11 insertions(+), 26 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index eed5a28e8ee3..11e4dd4f09ed 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -309,6 +309,16 @@ struct net *get_net_ns_by_id(const struct net *net, int id)
 }
 EXPORT_SYMBOL_GPL(get_net_ns_by_id);
 
+static __net_init void preinit_net_sysctl(struct net *net)
+{
+	net->core.sysctl_somaxconn = SOMAXCONN;
+	/* Limits per socket sk_omem_alloc usage.
+	 * TCP zerocopy regular usage needs 128 KB.
+	 */
+	net->core.sysctl_optmem_max = 128 * 1024;
+	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
+}
+
 /* init code that must occur even if setup_net() is not called. */
 static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns)
 {
@@ -324,6 +334,7 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
 	idr_init(&net->netns_ids);
 	spin_lock_init(&net->nsid_lock);
 	mutex_init(&net->ipv4.ra_mutex);
+	preinit_net_sysctl(net);
 }
 
 /*
@@ -384,32 +395,6 @@ out_undo:
 	goto out;
 }
 
-static int __net_init net_defaults_init_net(struct net *net)
-{
-	net->core.sysctl_somaxconn = SOMAXCONN;
-	/* Limits per socket sk_omem_alloc usage.
-	 * TCP zerocopy regular usage needs 128 KB.
-	 */
-	net->core.sysctl_optmem_max = 128 * 1024;
-	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
-
-	return 0;
-}
-
-static struct pernet_operations net_defaults_ops = {
-	.init = net_defaults_init_net,
-};
-
-static __init int net_defaults_init(void)
-{
-	if (register_pernet_subsys(&net_defaults_ops))
-		panic("Cannot initialize net default settings");
-
-	return 0;
-}
-
-core_initcall(net_defaults_init);
-
 #ifdef CONFIG_NET_NS
 static struct ucounts *inc_net_namespaces(struct user_namespace *ns)
 {
-- 
cgit v1.3-3-g829e


From e8b7d0c66a4ddbae909534cda515fbb56771d4bf Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Thu, 30 May 2024 15:01:56 +0200
Subject: wifi: mwifiex: increase max_num_akm_suites

The maximum number of AKM suites will be set to two if not specified by
the driver. Set it to CFG80211_MAX_NUM_AKM_SUITES to let userspace
specify up to ten AKM suites in the akm_suites array.

Without only the first two AKM suites will be used, further ones are
ignored.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240530130156.1651174-1-s.hauer@pengutronix.de
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 155eb0fab12a..6de4bdd3c8ae 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4360,6 +4360,8 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 				 BIT(NL80211_IFTYPE_P2P_GO) |
 				 BIT(NL80211_IFTYPE_AP);
 
+	wiphy->max_num_akm_suites = CFG80211_MAX_NUM_AKM_SUITES;
+
 	if (ISSUPP_ADHOC_ENABLED(adapter->fw_cap_info))
 		wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
 
-- 
cgit v1.3-3-g829e


From 36995892c271cce5e2230bc165a06f109b117222 Mon Sep 17 00:00:00 2001
From: David Lin <yu-hao.lin@nxp.com>
Date: Thu, 4 Jul 2024 11:30:00 +0800
Subject: wifi: mwifiex: add host mlme for client mode

Add host based MLME to enable WPA3 functionalities in client mode.
This feature required a firmware with the corresponding V2 Key API
support. The feature (WPA3) is currently enabled and verified only
on IW416. Also, verified no regression with change when host MLME
is disabled.

Signed-off-by: David Lin <yu-hao.lin@nxp.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240704033001.603419-2-yu-hao.lin@nxp.com
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c  | 318 +++++++++++++++++++++++
 drivers/net/wireless/marvell/mwifiex/cmdevt.c    |  25 ++
 drivers/net/wireless/marvell/mwifiex/decl.h      |  23 ++
 drivers/net/wireless/marvell/mwifiex/fw.h        |  33 +++
 drivers/net/wireless/marvell/mwifiex/init.c      |   6 +
 drivers/net/wireless/marvell/mwifiex/join.c      |  66 ++++-
 drivers/net/wireless/marvell/mwifiex/main.c      |  62 +++++
 drivers/net/wireless/marvell/mwifiex/main.h      |  16 ++
 drivers/net/wireless/marvell/mwifiex/scan.c      |   6 +
 drivers/net/wireless/marvell/mwifiex/sdio.c      |  13 +
 drivers/net/wireless/marvell/mwifiex/sdio.h      |   2 +
 drivers/net/wireless/marvell/mwifiex/sta_event.c |  36 ++-
 drivers/net/wireless/marvell/mwifiex/sta_ioctl.c |   2 +-
 drivers/net/wireless/marvell/mwifiex/sta_tx.c    |   9 +-
 drivers/net/wireless/marvell/mwifiex/util.c      |  80 ++++++
 15 files changed, 683 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 6de4bdd3c8ae..c1aaa91c5574 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -268,6 +268,8 @@ mwifiex_cfg80211_update_mgmt_frame_registrations(struct wiphy *wiphy,
 
 	if (mask != priv->mgmt_frame_mask) {
 		priv->mgmt_frame_mask = mask;
+		if (priv->host_mlme_reg)
+			priv->mgmt_frame_mask |= HOST_MLME_MGMT_MASK;
 		mwifiex_send_cmd(priv, HostCmd_CMD_MGMT_FRAME_REG,
 				 HostCmd_ACT_GEN_SET, 0,
 				 &priv->mgmt_frame_mask, false);
@@ -848,6 +850,7 @@ static int mwifiex_deinit_priv_params(struct mwifiex_private *priv)
 	struct mwifiex_adapter *adapter = priv->adapter;
 	unsigned long flags;
 
+	priv->host_mlme_reg = false;
 	priv->mgmt_frame_mask = 0;
 	if (mwifiex_send_cmd(priv, HostCmd_CMD_MGMT_FRAME_REG,
 			     HostCmd_ACT_GEN_SET, 0,
@@ -3633,6 +3636,9 @@ static int mwifiex_set_rekey_data(struct wiphy *wiphy, struct net_device *dev,
 	if (!ISSUPP_FIRMWARE_SUPPLICANT(priv->adapter->fw_cap_info))
 		return -EOPNOTSUPP;
 
+	if (priv->adapter->host_mlme_enabled)
+		return 0;
+
 	return mwifiex_send_cmd(priv, HostCmd_CMD_GTK_REKEY_OFFLOAD_CFG,
 				HostCmd_ACT_GEN_SET, 0, data, true);
 }
@@ -4206,6 +4212,305 @@ mwifiex_cfg80211_change_station(struct wiphy *wiphy, struct net_device *dev,
 	return ret;
 }
 
+static int
+mwifiex_cfg80211_authenticate(struct wiphy *wiphy,
+			      struct net_device *dev,
+			      struct cfg80211_auth_request *req)
+{
+	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
+	struct mwifiex_adapter *adapter = priv->adapter;
+	struct sk_buff *skb;
+	u16 pkt_len, auth_alg;
+	int ret;
+	struct mwifiex_ieee80211_mgmt *mgmt;
+	struct mwifiex_txinfo *tx_info;
+	u32 tx_control = 0, pkt_type = PKT_TYPE_MGMT;
+	u8 trans = 1, status_code = 0;
+	u8 *varptr;
+
+	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
+		mwifiex_dbg(priv->adapter, ERROR, "Interface role is AP\n");
+		return -EFAULT;
+	}
+
+	if (priv->wdev.iftype != NL80211_IFTYPE_STATION) {
+		mwifiex_dbg(priv->adapter, ERROR,
+			    "Interface type is not correct (type %d)\n",
+			    priv->wdev.iftype);
+		return -EINVAL;
+	}
+
+	if (priv->auth_alg != WLAN_AUTH_SAE &&
+	    (priv->auth_flag & HOST_MLME_AUTH_PENDING)) {
+		mwifiex_dbg(priv->adapter, ERROR, "Pending auth on going\n");
+		return -EBUSY;
+	}
+
+	if (!priv->host_mlme_reg) {
+		priv->host_mlme_reg = true;
+		priv->mgmt_frame_mask |= HOST_MLME_MGMT_MASK;
+		mwifiex_send_cmd(priv, HostCmd_CMD_MGMT_FRAME_REG,
+				 HostCmd_ACT_GEN_SET, 0,
+				 &priv->mgmt_frame_mask, false);
+	}
+
+	switch (req->auth_type) {
+	case NL80211_AUTHTYPE_OPEN_SYSTEM:
+		auth_alg = WLAN_AUTH_OPEN;
+		break;
+	case NL80211_AUTHTYPE_SHARED_KEY:
+		auth_alg = WLAN_AUTH_SHARED_KEY;
+		break;
+	case NL80211_AUTHTYPE_FT:
+		auth_alg = WLAN_AUTH_FT;
+		break;
+	case NL80211_AUTHTYPE_NETWORK_EAP:
+		auth_alg = WLAN_AUTH_LEAP;
+		break;
+	case NL80211_AUTHTYPE_SAE:
+		auth_alg = WLAN_AUTH_SAE;
+		break;
+	default:
+		mwifiex_dbg(priv->adapter, ERROR,
+			    "unsupported auth type=%d\n", req->auth_type);
+		return -EOPNOTSUPP;
+	}
+
+	if (!priv->auth_flag) {
+		ret = mwifiex_remain_on_chan_cfg(priv, HostCmd_ACT_GEN_SET,
+						 req->bss->channel,
+						 AUTH_TX_DEFAULT_WAIT_TIME);
+
+		if (!ret) {
+			priv->roc_cfg.cookie = get_random_u32() | 1;
+			priv->roc_cfg.chan = *req->bss->channel;
+		} else {
+			return -EFAULT;
+		}
+	}
+
+	priv->sec_info.authentication_mode = auth_alg;
+
+	mwifiex_cancel_scan(adapter);
+
+	pkt_len = (u16)req->ie_len + req->auth_data_len +
+		MWIFIEX_MGMT_HEADER_LEN + MWIFIEX_AUTH_BODY_LEN;
+	if (req->auth_data_len >= 4)
+		pkt_len -= 4;
+
+	skb = dev_alloc_skb(MWIFIEX_MIN_DATA_HEADER_LEN +
+			    MWIFIEX_MGMT_FRAME_HEADER_SIZE +
+			    pkt_len + sizeof(pkt_len));
+	if (!skb) {
+		mwifiex_dbg(priv->adapter, ERROR,
+			    "allocate skb failed for management frame\n");
+		return -ENOMEM;
+	}
+
+	tx_info = MWIFIEX_SKB_TXCB(skb);
+	memset(tx_info, 0, sizeof(*tx_info));
+	tx_info->bss_num = priv->bss_num;
+	tx_info->bss_type = priv->bss_type;
+	tx_info->pkt_len = pkt_len;
+
+	skb_reserve(skb, MWIFIEX_MIN_DATA_HEADER_LEN +
+		    MWIFIEX_MGMT_FRAME_HEADER_SIZE + sizeof(pkt_len));
+	memcpy(skb_push(skb, sizeof(pkt_len)), &pkt_len, sizeof(pkt_len));
+	memcpy(skb_push(skb, sizeof(tx_control)),
+	       &tx_control, sizeof(tx_control));
+	memcpy(skb_push(skb, sizeof(pkt_type)), &pkt_type, sizeof(pkt_type));
+
+	mgmt = (struct mwifiex_ieee80211_mgmt *)skb_put(skb, pkt_len);
+	memset(mgmt, 0, pkt_len);
+	mgmt->frame_control =
+		cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_AUTH);
+	memcpy(mgmt->da, req->bss->bssid, ETH_ALEN);
+	memcpy(mgmt->sa, priv->curr_addr, ETH_ALEN);
+	memcpy(mgmt->bssid, req->bss->bssid, ETH_ALEN);
+	eth_broadcast_addr(mgmt->addr4);
+
+	if (req->auth_data_len >= 4) {
+		if (req->auth_type == NL80211_AUTHTYPE_SAE) {
+			__le16 *pos = (__le16 *)req->auth_data;
+
+			trans = le16_to_cpu(pos[0]);
+			status_code = le16_to_cpu(pos[1]);
+		}
+		memcpy((u8 *)(&mgmt->auth.variable), req->auth_data + 4,
+		       req->auth_data_len - 4);
+		varptr = (u8 *)&mgmt->auth.variable +
+			 (req->auth_data_len - 4);
+	}
+
+	mgmt->auth.auth_alg = cpu_to_le16(auth_alg);
+	mgmt->auth.auth_transaction = cpu_to_le16(trans);
+	mgmt->auth.status_code = cpu_to_le16(status_code);
+
+	if (req->ie && req->ie_len) {
+		if (!varptr)
+			varptr = (u8 *)&mgmt->auth.variable;
+		memcpy((u8 *)varptr, req->ie, req->ie_len);
+	}
+
+	priv->auth_flag = HOST_MLME_AUTH_PENDING;
+	priv->auth_alg = auth_alg;
+
+	skb->priority = WMM_HIGHEST_PRIORITY;
+	__net_timestamp(skb);
+
+	mwifiex_dbg(priv->adapter, MSG,
+		    "auth: send authentication to %pM\n", req->bss->bssid);
+
+	mwifiex_queue_tx_pkt(priv, skb);
+
+	return 0;
+}
+
+static int
+mwifiex_cfg80211_associate(struct wiphy *wiphy, struct net_device *dev,
+			   struct cfg80211_assoc_request *req)
+{
+	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
+	struct mwifiex_adapter *adapter = priv->adapter;
+	int ret;
+	struct cfg80211_ssid req_ssid;
+	const u8 *ssid_ie;
+
+	if (GET_BSS_ROLE(priv) != MWIFIEX_BSS_ROLE_STA) {
+		mwifiex_dbg(adapter, ERROR,
+			    "%s: reject infra assoc request in non-STA role\n",
+			    dev->name);
+		return -EINVAL;
+	}
+
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags) ||
+	    test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
+		mwifiex_dbg(adapter, ERROR,
+			    "%s: Ignore association.\t"
+			    "Card removed or FW in bad state\n",
+			    dev->name);
+		return -EFAULT;
+	}
+
+	if (priv->auth_alg == WLAN_AUTH_SAE)
+		priv->auth_flag = HOST_MLME_AUTH_DONE;
+
+	if (priv->auth_flag && !(priv->auth_flag & HOST_MLME_AUTH_DONE))
+		return -EBUSY;
+
+	if (priv->roc_cfg.cookie) {
+		ret = mwifiex_remain_on_chan_cfg(priv, HostCmd_ACT_GEN_REMOVE,
+						 &priv->roc_cfg.chan, 0);
+		if (!ret)
+			memset(&priv->roc_cfg, 0,
+			       sizeof(struct mwifiex_roc_cfg));
+		else
+			return -EFAULT;
+	}
+
+	if (!mwifiex_stop_bg_scan(priv))
+		cfg80211_sched_scan_stopped_locked(priv->wdev.wiphy, 0);
+
+	memset(&req_ssid, 0, sizeof(struct cfg80211_ssid));
+	rcu_read_lock();
+	ssid_ie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID);
+
+	if (!ssid_ie)
+		goto ssid_err;
+
+	req_ssid.ssid_len = ssid_ie[1];
+	if (req_ssid.ssid_len > IEEE80211_MAX_SSID_LEN) {
+		mwifiex_dbg(adapter, ERROR, "invalid SSID - aborting\n");
+		goto ssid_err;
+	}
+
+	memcpy(req_ssid.ssid, ssid_ie + 2, req_ssid.ssid_len);
+	if (!req_ssid.ssid_len || req_ssid.ssid[0] < 0x20) {
+		mwifiex_dbg(adapter, ERROR, "invalid SSID - aborting\n");
+		goto ssid_err;
+	}
+	rcu_read_unlock();
+
+	/* As this is new association, clear locally stored
+	 * keys and security related flags
+	 */
+	priv->sec_info.wpa_enabled = false;
+	priv->sec_info.wpa2_enabled = false;
+	priv->wep_key_curr_index = 0;
+	priv->sec_info.encryption_mode = 0;
+	priv->sec_info.is_authtype_auto = 0;
+	if (mwifiex_set_encode(priv, NULL, NULL, 0, 0, NULL, 1)) {
+		mwifiex_dbg(priv->adapter, ERROR, "deleting the crypto keys\n");
+		return -EFAULT;
+	}
+
+	if (req->crypto.n_ciphers_pairwise)
+		priv->sec_info.encryption_mode =
+			req->crypto.ciphers_pairwise[0];
+
+	if (req->crypto.cipher_group)
+		priv->sec_info.encryption_mode = req->crypto.cipher_group;
+
+	if (req->ie)
+		mwifiex_set_gen_ie(priv, req->ie, req->ie_len);
+
+	memcpy(priv->cfg_bssid, req->bss->bssid, ETH_ALEN);
+
+	mwifiex_dbg(adapter, MSG,
+		    "assoc: send association to %pM\n", req->bss->bssid);
+
+	cfg80211_ref_bss(adapter->wiphy, req->bss);
+	ret = mwifiex_bss_start(priv, req->bss, &req_ssid);
+	if (ret) {
+		priv->auth_flag = 0;
+		priv->auth_alg = WLAN_AUTH_NONE;
+		eth_zero_addr(priv->cfg_bssid);
+	}
+
+	if (priv->assoc_rsp_size) {
+		priv->req_bss = req->bss;
+		adapter->assoc_resp_received = true;
+		queue_work(adapter->host_mlme_workqueue,
+			   &adapter->host_mlme_work);
+	}
+
+	cfg80211_put_bss(priv->adapter->wiphy, req->bss);
+
+	return 0;
+
+ssid_err:
+	rcu_read_unlock();
+	return -EFAULT;
+}
+
+static int
+mwifiex_cfg80211_deauthenticate(struct wiphy *wiphy,
+				struct net_device *dev,
+				struct cfg80211_deauth_request *req)
+{
+	return mwifiex_cfg80211_disconnect(wiphy, dev, req->reason_code);
+}
+
+static int
+mwifiex_cfg80211_disassociate(struct wiphy *wiphy,
+			      struct net_device *dev,
+			      struct cfg80211_disassoc_request *req)
+{
+	return mwifiex_cfg80211_disconnect(wiphy, dev, req->reason_code);
+}
+
+static int
+mwifiex_cfg80211_probe_client(struct wiphy *wiphy,
+			      struct net_device *dev, const u8 *peer,
+			      u64 *cookie)
+{
+	/* hostapd looks for NL80211_CMD_PROBE_CLIENT support; otherwise,
+	 * it requires monitor-mode support (which mwifiex doesn't support).
+	 * Provide fake probe_client support to work around this.
+	 */
+	return -EOPNOTSUPP;
+}
+
 /* station cfg80211 operations */
 static struct cfg80211_ops mwifiex_cfg80211_ops = {
 	.add_virtual_intf = mwifiex_add_virtual_intf,
@@ -4351,6 +4656,16 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 			    "%s: creating new wiphy\n", __func__);
 		return -ENOMEM;
 	}
+	if (adapter->host_mlme_enabled) {
+		mwifiex_cfg80211_ops.auth = mwifiex_cfg80211_authenticate;
+		mwifiex_cfg80211_ops.assoc = mwifiex_cfg80211_associate;
+		mwifiex_cfg80211_ops.deauth = mwifiex_cfg80211_deauthenticate;
+		mwifiex_cfg80211_ops.disassoc = mwifiex_cfg80211_disassociate;
+		mwifiex_cfg80211_ops.disconnect = NULL;
+		mwifiex_cfg80211_ops.connect = NULL;
+		mwifiex_cfg80211_ops.probe_client =
+			mwifiex_cfg80211_probe_client;
+	}
 	wiphy->max_scan_ssids = MWIFIEX_MAX_SSID_LIST_LENGTH;
 	wiphy->max_scan_ie_len = MWIFIEX_MAX_VSIE_LEN;
 	wiphy->mgmt_stypes = mwifiex_mgmt_stypes;
@@ -4434,6 +4749,9 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 			   NL80211_FEATURE_LOW_PRIORITY_SCAN |
 			   NL80211_FEATURE_NEED_OBSS_SCAN;
 
+	if (adapter->host_mlme_enabled)
+		wiphy->features |= NL80211_FEATURE_SAE;
+
 	if (ISSUPP_ADHOC_ENABLED(adapter->fw_cap_info))
 		wiphy->features |= NL80211_FEATURE_HT_IBSS;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 9eff29a25544..da983e27023c 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -924,6 +924,24 @@ int mwifiex_process_cmdresp(struct mwifiex_adapter *adapter)
 	return ret;
 }
 
+void mwifiex_process_assoc_resp(struct mwifiex_adapter *adapter)
+{
+	struct cfg80211_rx_assoc_resp_data assoc_resp = {
+		.uapsd_queues = -1,
+	};
+	struct mwifiex_private *priv =
+		mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA);
+
+	if (priv->assoc_rsp_size) {
+		assoc_resp.links[0].bss = priv->req_bss;
+		assoc_resp.buf = priv->assoc_rsp_buf;
+		assoc_resp.len = priv->assoc_rsp_size;
+		cfg80211_rx_assoc_resp(priv->netdev,
+				       &assoc_resp);
+		priv->assoc_rsp_size = 0;
+	}
+}
+
 /*
  * This function handles the timeout of command sending.
  *
@@ -1672,6 +1690,13 @@ int mwifiex_ret_get_hw_spec(struct mwifiex_private *priv,
 	if (adapter->fw_api_ver == MWIFIEX_FW_V15)
 		adapter->scan_chan_gap_enabled = true;
 
+	if (adapter->key_api_major_ver != KEY_API_VER_MAJOR_V2)
+		adapter->host_mlme_enabled = false;
+
+	mwifiex_dbg(adapter, MSG, "host_mlme: %s, key_api: %d\n",
+		    adapter->host_mlme_enabled ? "enable" : "disable",
+		    adapter->key_api_major_ver);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/decl.h b/drivers/net/wireless/marvell/mwifiex/decl.h
index 326ffb05d791..84603f1e7f6e 100644
--- a/drivers/net/wireless/marvell/mwifiex/decl.h
+++ b/drivers/net/wireless/marvell/mwifiex/decl.h
@@ -31,6 +31,29 @@
 						 *   + sizeof(tx_control)
 						 */
 
+#define FRMCTL_LEN                2
+#define DURATION_LEN              2
+#define SEQCTL_LEN                2
+/* special FW 4 address management header */
+#define MWIFIEX_MGMT_HEADER_LEN   (FRMCTL_LEN + DURATION_LEN + ETH_ALEN + \
+				   ETH_ALEN + ETH_ALEN + SEQCTL_LEN + ETH_ALEN)
+
+#define AUTH_ALG_LEN              2
+#define AUTH_TRANSACTION_LEN      2
+#define AUTH_STATUS_LEN           2
+#define MWIFIEX_AUTH_BODY_LEN     (AUTH_ALG_LEN + AUTH_TRANSACTION_LEN + \
+				   AUTH_STATUS_LEN)
+
+#define HOST_MLME_AUTH_PENDING    BIT(0)
+#define HOST_MLME_AUTH_DONE       BIT(1)
+
+#define HOST_MLME_MGMT_MASK       (BIT(IEEE80211_STYPE_AUTH >> 4) | \
+				   BIT(IEEE80211_STYPE_DEAUTH >> 4) | \
+				   BIT(IEEE80211_STYPE_DISASSOC >> 4))
+#define AUTH_TX_DEFAULT_WAIT_TIME 2400
+
+#define WLAN_AUTH_NONE            0xFFFF
+
 #define MWIFIEX_MAX_TX_BASTREAM_SUPPORTED	2
 #define MWIFIEX_MAX_RX_BASTREAM_SUPPORTED	16
 #define MWIFIEX_MAX_TDLS_PEER_SUPPORTED 8
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 3adc447b715f..0f89b86aa527 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -210,6 +210,8 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define TLV_TYPE_RANDOM_MAC         (PROPRIETARY_TLV_BASE_ID + 236)
 #define TLV_TYPE_CHAN_ATTR_CFG      (PROPRIETARY_TLV_BASE_ID + 237)
 #define TLV_TYPE_MAX_CONN           (PROPRIETARY_TLV_BASE_ID + 279)
+#define TLV_TYPE_HOST_MLME          (PROPRIETARY_TLV_BASE_ID + 307)
+#define TLV_TYPE_SAE_PWE_MODE       (PROPRIETARY_TLV_BASE_ID + 339)
 
 #define MWIFIEX_TX_DATA_BUF_SIZE_2K        2048
 
@@ -744,6 +746,25 @@ struct uap_rxpd {
 	u8 flags;
 } __packed;
 
+struct mwifiex_auth {
+	__le16 auth_alg;
+	__le16 auth_transaction;
+	__le16 status_code;
+	/* possibly followed by Challenge text */
+	u8 variable[];
+} __packed;
+
+struct mwifiex_ieee80211_mgmt {
+	__le16 frame_control;
+	__le16 duration;
+	u8 da[ETH_ALEN];
+	u8 sa[ETH_ALEN];
+	u8 bssid[ETH_ALEN];
+	__le16 seq_ctrl;
+	u8 addr4[ETH_ALEN];
+	struct mwifiex_auth auth;
+} __packed;
+
 struct mwifiex_fw_chan_stats {
 	u8 chan_num;
 	u8 bandcfg;
@@ -803,6 +824,11 @@ struct mwifiex_ie_types_ssid_param_set {
 	u8 ssid[];
 } __packed;
 
+struct mwifiex_ie_types_host_mlme {
+	struct mwifiex_ie_types_header header;
+	u8 host_mlme;
+} __packed;
+
 struct mwifiex_ie_types_num_probes {
 	struct mwifiex_ie_types_header header;
 	__le16 num_probes;
@@ -906,6 +932,13 @@ struct mwifiex_ie_types_tdls_idle_timeout {
 	__le16 value;
 } __packed;
 
+#define MWIFIEX_AUTHTYPE_SAE 6
+
+struct mwifiex_ie_types_sae_pwe_mode {
+	struct mwifiex_ie_types_header header;
+	u8 pwe[];
+} __packed;
+
 struct mwifiex_ie_types_rsn_param_set {
 	struct mwifiex_ie_types_header header;
 	u8 rsn_ie[];
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index c9c58419c37b..a336d45b9677 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -81,6 +81,9 @@ int mwifiex_init_priv(struct mwifiex_private *priv)
 	priv->bcn_avg_factor = DEFAULT_BCN_AVG_FACTOR;
 	priv->data_avg_factor = DEFAULT_DATA_AVG_FACTOR;
 
+	priv->auth_flag = 0;
+	priv->auth_alg = WLAN_AUTH_NONE;
+
 	priv->sec_info.wep_enabled = 0;
 	priv->sec_info.authentication_mode = NL80211_AUTHTYPE_OPEN_SYSTEM;
 	priv->sec_info.encryption_mode = 0;
@@ -220,6 +223,9 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 	adapter->cmd_resp_received = false;
 	adapter->event_received = false;
 	adapter->data_received = false;
+	adapter->assoc_resp_received = false;
+	adapter->priv_link_lost = NULL;
+	adapter->host_mlme_link_lost = false;
 
 	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 
diff --git a/drivers/net/wireless/marvell/mwifiex/join.c b/drivers/net/wireless/marvell/mwifiex/join.c
index 9d98a1908dd6..249210fb2e75 100644
--- a/drivers/net/wireless/marvell/mwifiex/join.c
+++ b/drivers/net/wireless/marvell/mwifiex/join.c
@@ -382,7 +382,9 @@ int mwifiex_cmd_802_11_associate(struct mwifiex_private *priv,
 	struct mwifiex_ie_types_ss_param_set *ss_tlv;
 	struct mwifiex_ie_types_rates_param_set *rates_tlv;
 	struct mwifiex_ie_types_auth_type *auth_tlv;
+	struct mwifiex_ie_types_sae_pwe_mode *sae_pwe_tlv;
 	struct mwifiex_ie_types_chan_list_param_set *chan_tlv;
+	struct mwifiex_ie_types_host_mlme *host_mlme_tlv;
 	u8 rates[MWIFIEX_SUPPORTED_RATES];
 	u32 rates_size;
 	u16 tmp_cap;
@@ -460,6 +462,24 @@ int mwifiex_cmd_802_11_associate(struct mwifiex_private *priv,
 
 	pos += sizeof(auth_tlv->header) + le16_to_cpu(auth_tlv->header.len);
 
+	if (priv->sec_info.authentication_mode == WLAN_AUTH_SAE) {
+		auth_tlv->auth_type = cpu_to_le16(MWIFIEX_AUTHTYPE_SAE);
+		if (bss_desc->bcn_rsnx_ie &&
+		    bss_desc->bcn_rsnx_ie->ieee_hdr.len &&
+		    (bss_desc->bcn_rsnx_ie->data[0] &
+		    WLAN_RSNX_CAPA_SAE_H2E)) {
+			sae_pwe_tlv =
+				(struct mwifiex_ie_types_sae_pwe_mode *)pos;
+			sae_pwe_tlv->header.type =
+				cpu_to_le16(TLV_TYPE_SAE_PWE_MODE);
+			sae_pwe_tlv->header.len =
+				cpu_to_le16(sizeof(sae_pwe_tlv->pwe[0]));
+			sae_pwe_tlv->pwe[0] = bss_desc->bcn_rsnx_ie->data[0];
+			pos += sizeof(sae_pwe_tlv->header) +
+				sizeof(sae_pwe_tlv->pwe[0]);
+		}
+	}
+
 	if (IS_SUPPORT_MULTI_BANDS(priv->adapter) &&
 	    !(ISSUPP_11NENABLED(priv->adapter->fw_cap_info) &&
 	    (!bss_desc->disable_11n) &&
@@ -491,6 +511,16 @@ int mwifiex_cmd_802_11_associate(struct mwifiex_private *priv,
 			sizeof(struct mwifiex_chan_scan_param_set);
 	}
 
+	if (priv->adapter->host_mlme_enabled) {
+		host_mlme_tlv = (struct mwifiex_ie_types_host_mlme *)pos;
+		host_mlme_tlv->header.type = cpu_to_le16(TLV_TYPE_HOST_MLME);
+		host_mlme_tlv->header.len =
+			cpu_to_le16(sizeof(host_mlme_tlv->host_mlme));
+		host_mlme_tlv->host_mlme = 1;
+		pos += sizeof(host_mlme_tlv->header) +
+			sizeof(host_mlme_tlv->host_mlme);
+	}
+
 	if (!priv->wps.session_enable) {
 		if (priv->sec_info.wpa_enabled || priv->sec_info.wpa2_enabled)
 			rsn_ie_len = mwifiex_append_rsn_ie_wpa_wpa2(priv, &pos);
@@ -641,7 +671,21 @@ int mwifiex_ret_802_11_associate(struct mwifiex_private *priv,
 		goto done;
 	}
 
-	assoc_rsp = (struct ieee_types_assoc_rsp *) &resp->params;
+	if (adapter->host_mlme_enabled) {
+		struct ieee80211_mgmt *hdr;
+
+		hdr = (struct ieee80211_mgmt *)&resp->params;
+		if (!memcmp(hdr->bssid,
+			    priv->attempted_bss_desc->mac_address,
+			    ETH_ALEN))
+			assoc_rsp = (struct ieee_types_assoc_rsp *)
+				&hdr->u.assoc_resp;
+		else
+			assoc_rsp =
+				(struct ieee_types_assoc_rsp *)&resp->params;
+	} else {
+		assoc_rsp = (struct ieee_types_assoc_rsp *)&resp->params;
+	}
 
 	cap_info = le16_to_cpu(assoc_rsp->cap_info_bitmap);
 	status_code = le16_to_cpu(assoc_rsp->status_code);
@@ -680,6 +724,9 @@ int mwifiex_ret_802_11_associate(struct mwifiex_private *priv,
 				mwifiex_dbg(priv->adapter, ERROR,
 					    "ASSOC_RESP: UNSPECIFIED failure\n");
 			}
+
+			if (priv->adapter->host_mlme_enabled)
+				priv->assoc_rsp_size = 0;
 		} else {
 			ret = status_code;
 		}
@@ -778,7 +825,8 @@ int mwifiex_ret_802_11_associate(struct mwifiex_private *priv,
 
 	priv->adapter->dbg.num_cmd_assoc_success++;
 
-	mwifiex_dbg(priv->adapter, INFO, "info: ASSOC_RESP: associated\n");
+	mwifiex_dbg(priv->adapter, MSG, "assoc: associated with %pM\n",
+		    priv->attempted_bss_desc->mac_address);
 
 	/* Add the ra_list here for infra mode as there will be only 1 ra
 	   always */
@@ -1491,6 +1539,20 @@ int mwifiex_deauthenticate(struct mwifiex_private *priv, u8 *mac)
 	if (!priv->media_connected)
 		return 0;
 
+	if (priv->adapter->host_mlme_enabled) {
+		priv->auth_flag = 0;
+		priv->auth_alg = WLAN_AUTH_NONE;
+		priv->host_mlme_reg = false;
+		priv->mgmt_frame_mask = 0;
+		if (mwifiex_send_cmd(priv, HostCmd_CMD_MGMT_FRAME_REG,
+				     HostCmd_ACT_GEN_SET, 0,
+				     &priv->mgmt_frame_mask, false)) {
+			mwifiex_dbg(priv->adapter, ERROR,
+				    "could not unregister mgmt frame rx\n");
+			return -1;
+		}
+	}
+
 	switch (priv->bss_mode) {
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index d99127dc466e..88cd2d6a1dcb 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -530,6 +530,11 @@ static void mwifiex_terminate_workqueue(struct mwifiex_adapter *adapter)
 		destroy_workqueue(adapter->rx_workqueue);
 		adapter->rx_workqueue = NULL;
 	}
+
+	if (adapter->host_mlme_workqueue) {
+		destroy_workqueue(adapter->host_mlme_workqueue);
+		adapter->host_mlme_workqueue = NULL;
+	}
 }
 
 /*
@@ -802,6 +807,10 @@ mwifiex_bypass_tx_queue(struct mwifiex_private *priv,
 			    "bypass txqueue; eth type %#x, mgmt %d\n",
 			     ntohs(eth_hdr->h_proto),
 			     mwifiex_is_skb_mgmt_frame(skb));
+		if (eth_hdr->h_proto == htons(ETH_P_PAE))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "key: send EAPOL to %pM\n",
+				    eth_hdr->h_dest);
 		return true;
 	}
 
@@ -1384,6 +1393,35 @@ int is_command_pending(struct mwifiex_adapter *adapter)
 	return !is_cmd_pend_q_empty;
 }
 
+/* This is the host mlme work queue function.
+ * It handles the host mlme operations.
+ */
+static void mwifiex_host_mlme_work_queue(struct work_struct *work)
+{
+	struct mwifiex_adapter *adapter =
+		container_of(work, struct mwifiex_adapter, host_mlme_work);
+
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
+		return;
+
+	/* Check for host mlme disconnection */
+	if (adapter->host_mlme_link_lost) {
+		if (adapter->priv_link_lost) {
+			mwifiex_reset_connect_state(adapter->priv_link_lost,
+						    WLAN_REASON_DEAUTH_LEAVING,
+						    true);
+			adapter->priv_link_lost = NULL;
+		}
+		adapter->host_mlme_link_lost = false;
+	}
+
+	/* Check for host mlme Assoc Resp */
+	if (adapter->assoc_resp_received) {
+		mwifiex_process_assoc_resp(adapter);
+		adapter->assoc_resp_received = false;
+	}
+}
+
 /*
  * This is the RX work queue function.
  *
@@ -1558,6 +1596,18 @@ mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 		INIT_WORK(&adapter->rx_work, mwifiex_rx_work_queue);
 	}
 
+	if (adapter->host_mlme_enabled) {
+		adapter->host_mlme_workqueue =
+			alloc_workqueue("MWIFIEX_HOST_MLME_WORK_QUEUE",
+					WQ_HIGHPRI |
+					WQ_MEM_RECLAIM |
+					WQ_UNBOUND, 0);
+		if (!adapter->host_mlme_workqueue)
+			goto err_kmalloc;
+		INIT_WORK(&adapter->host_mlme_work,
+			  mwifiex_host_mlme_work_queue);
+	}
+
 	/* Register the device. Fill up the private data structure with
 	 * relevant information from the card. Some code extracted from
 	 * mwifiex_register_dev()
@@ -1721,6 +1771,18 @@ mwifiex_add_card(void *card, struct completion *fw_done,
 		goto err_registerdev;
 	}
 
+	if (adapter->host_mlme_enabled) {
+		adapter->host_mlme_workqueue =
+			alloc_workqueue("MWIFIEX_HOST_MLME_WORK_QUEUE",
+					WQ_HIGHPRI |
+					WQ_MEM_RECLAIM |
+					WQ_UNBOUND, 0);
+		if (!adapter->host_mlme_workqueue)
+			goto err_kmalloc;
+		INIT_WORK(&adapter->host_mlme_work,
+			  mwifiex_host_mlme_work_queue);
+	}
+
 	if (mwifiex_init_hw_fw(adapter, true)) {
 		pr_err("%s: firmware init failed\n", __func__);
 		goto err_init_fw;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index c5164ae41b54..d4c56c3d4cf1 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -424,6 +424,8 @@ struct mwifiex_bssdescriptor {
 	u16 wpa_offset;
 	struct ieee_types_generic *bcn_rsn_ie;
 	u16 rsn_offset;
+	struct ieee_types_generic *bcn_rsnx_ie;
+	u16 rsnx_offset;
 	struct ieee_types_generic *bcn_wapi_ie;
 	u16 wapi_offset;
 	u8 *beacon_buf;
@@ -525,6 +527,8 @@ struct mwifiex_private {
 	u8 bss_priority;
 	u8 bss_num;
 	u8 bss_started;
+	u8 auth_flag;
+	u16 auth_alg;
 	u8 frame_type;
 	u8 curr_addr[ETH_ALEN];
 	u8 media_connected;
@@ -608,6 +612,7 @@ struct mwifiex_private {
 #define MWIFIEX_ASSOC_RSP_BUF_SIZE  500
 	u8 assoc_rsp_buf[MWIFIEX_ASSOC_RSP_BUF_SIZE];
 	u32 assoc_rsp_size;
+	struct cfg80211_bss *req_bss;
 
 #define MWIFIEX_GENIE_BUF_SIZE      256
 	u8 gen_ie_buf[MWIFIEX_GENIE_BUF_SIZE];
@@ -647,6 +652,7 @@ struct mwifiex_private {
 	u16 gen_idx;
 	u8 ap_11n_enabled;
 	u8 ap_11ac_enabled;
+	bool host_mlme_reg;
 	u32 mgmt_frame_mask;
 	struct mwifiex_roc_cfg roc_cfg;
 	bool scan_aborting;
@@ -876,6 +882,8 @@ struct mwifiex_adapter {
 	struct work_struct main_work;
 	struct workqueue_struct *rx_workqueue;
 	struct work_struct rx_work;
+	struct workqueue_struct *host_mlme_workqueue;
+	struct work_struct host_mlme_work;
 	bool rx_work_enabled;
 	bool rx_processing;
 	bool delay_main_work;
@@ -907,6 +915,9 @@ struct mwifiex_adapter {
 	u8 cmd_resp_received;
 	u8 event_received;
 	u8 data_received;
+	u8 assoc_resp_received;
+	struct mwifiex_private *priv_link_lost;
+	u8 host_mlme_link_lost;
 	u16 seq_num;
 	struct cmd_ctrl_node *cmd_pool;
 	struct cmd_ctrl_node *curr_cmd;
@@ -996,6 +1007,7 @@ struct mwifiex_adapter {
 	bool is_up;
 
 	bool ext_scan;
+	bool host_mlme_enabled;
 	u8 fw_api_ver;
 	u8 key_api_major_ver, key_api_minor_ver;
 	u8 max_p2p_conn, max_sta_conn;
@@ -1061,6 +1073,9 @@ int mwifiex_recv_packet(struct mwifiex_private *priv, struct sk_buff *skb);
 int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 			    struct sk_buff *skb);
 
+void mwifiex_host_mlme_disconnect(struct mwifiex_private *priv,
+				  u16 reason_code, u8 *sa);
+
 int mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 				struct sk_buff *skb);
 
@@ -1092,6 +1107,7 @@ void mwifiex_insert_cmd_to_pending_q(struct mwifiex_adapter *adapter,
 
 int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter);
 int mwifiex_process_cmdresp(struct mwifiex_adapter *adapter);
+void mwifiex_process_assoc_resp(struct mwifiex_adapter *adapter);
 int mwifiex_handle_rx_packet(struct mwifiex_adapter *adapter,
 			     struct sk_buff *skb);
 int mwifiex_process_tx(struct mwifiex_private *priv, struct sk_buff *skb,
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 0326b121747c..e782d652cb93 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1371,6 +1371,12 @@ int mwifiex_update_bss_desc_with_ie(struct mwifiex_adapter *adapter,
 			bss_entry->rsn_offset = (u16) (current_ptr -
 							bss_entry->beacon_buf);
 			break;
+		case WLAN_EID_RSNX:
+			bss_entry->bcn_rsnx_ie =
+				(struct ieee_types_generic *)current_ptr;
+			bss_entry->rsnx_offset =
+				(u16)(current_ptr - bss_entry->beacon_buf);
+			break;
 		case WLAN_EID_BSS_AC_ACCESS_DELAY:
 			bss_entry->bcn_wapi_ie =
 				(struct ieee_types_generic *) current_ptr;
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index bda9b2b8a1f3..490ffd981164 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -332,6 +332,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8786 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = false,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = {
@@ -348,6 +349,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8787 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = {
@@ -364,6 +366,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8797 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = {
@@ -380,6 +383,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = {
@@ -397,6 +401,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8978 = {
@@ -414,6 +419,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8978 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = true,
+	.host_mlme = true,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = {
@@ -432,6 +438,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8887 = {
@@ -448,6 +455,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8887 = {
 	.can_auto_tdls = true,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8987 = {
@@ -465,6 +473,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8987 = {
 	.can_auto_tdls = true,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static const struct mwifiex_sdio_device mwifiex_sdio_sd8801 = {
@@ -481,6 +490,7 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8801 = {
 	.can_auto_tdls = false,
 	.can_ext_scan = true,
 	.fw_ready_extra_delay = false,
+	.host_mlme = false,
 };
 
 static struct memory_type_mapping generic_mem_type_map[] = {
@@ -574,6 +584,7 @@ mwifiex_sdio_probe(struct sdio_func *func, const struct sdio_device_id *id)
 		card->can_auto_tdls = data->can_auto_tdls;
 		card->can_ext_scan = data->can_ext_scan;
 		card->fw_ready_extra_delay = data->fw_ready_extra_delay;
+		card->host_mlme = data->host_mlme;
 		INIT_WORK(&card->work, mwifiex_sdio_work);
 	}
 
@@ -2511,6 +2522,8 @@ static int mwifiex_register_dev(struct mwifiex_adapter *adapter)
 		adapter->num_mem_types = ARRAY_SIZE(mem_type_mapping_tbl);
 	}
 
+	adapter->host_mlme_enabled = card->host_mlme;
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h
index cb63ad55d675..65d142286c46 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.h
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.h
@@ -256,6 +256,7 @@ struct sdio_mmc_card {
 	bool can_auto_tdls;
 	bool can_ext_scan;
 	bool fw_ready_extra_delay;
+	bool host_mlme;
 
 	struct mwifiex_sdio_mpa_tx mpa_tx;
 	struct mwifiex_sdio_mpa_rx mpa_rx;
@@ -280,6 +281,7 @@ struct mwifiex_sdio_device {
 	bool can_auto_tdls;
 	bool can_ext_scan;
 	bool fw_ready_extra_delay;
+	bool host_mlme;
 };
 
 /*
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index df9cdd10a494..b5f3821a6a8f 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -135,6 +135,9 @@ void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code,
 
 	priv->media_connected = false;
 
+	priv->auth_flag = 0;
+	priv->auth_alg = WLAN_AUTH_NONE;
+
 	priv->scan_block = false;
 	priv->port_open = false;
 
@@ -222,8 +225,12 @@ void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code,
 		    priv->cfg_bssid, reason_code);
 	if (priv->bss_mode == NL80211_IFTYPE_STATION ||
 	    priv->bss_mode == NL80211_IFTYPE_P2P_CLIENT) {
-		cfg80211_disconnected(priv->netdev, reason_code, NULL, 0,
-				      !from_ap, GFP_KERNEL);
+		if (adapter->host_mlme_enabled && adapter->host_mlme_link_lost)
+			mwifiex_host_mlme_disconnect(adapter->priv_link_lost,
+						     reason_code, NULL);
+		else
+			cfg80211_disconnected(priv->netdev, reason_code, NULL,
+					      0, !from_ap, GFP_KERNEL);
 	}
 	eth_zero_addr(priv->cfg_bssid);
 
@@ -746,7 +753,15 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 		if (priv->media_connected) {
 			reason_code =
 				get_unaligned_le16(adapter->event_body);
-			mwifiex_reset_connect_state(priv, reason_code, true);
+			if (adapter->host_mlme_enabled) {
+				adapter->priv_link_lost = priv;
+				adapter->host_mlme_link_lost = true;
+				queue_work(adapter->host_mlme_workqueue,
+					   &adapter->host_mlme_work);
+			} else {
+				mwifiex_reset_connect_state(priv, reason_code,
+							    true);
+			}
 		}
 		break;
 
@@ -999,10 +1014,17 @@ int mwifiex_process_sta_event(struct mwifiex_private *priv)
 	case EVENT_REMAIN_ON_CHAN_EXPIRED:
 		mwifiex_dbg(adapter, EVENT,
 			    "event: Remain on channel expired\n");
-		cfg80211_remain_on_channel_expired(&priv->wdev,
-						   priv->roc_cfg.cookie,
-						   &priv->roc_cfg.chan,
-						   GFP_ATOMIC);
+
+		if (adapter->host_mlme_enabled &&
+		    (priv->auth_flag & HOST_MLME_AUTH_PENDING)) {
+			priv->auth_flag = 0;
+			priv->auth_alg = WLAN_AUTH_NONE;
+		} else {
+			cfg80211_remain_on_channel_expired(&priv->wdev,
+							   priv->roc_cfg.cookie,
+							   &priv->roc_cfg.chan,
+							   GFP_ATOMIC);
+		}
 
 		memset(&priv->roc_cfg, 0x00, sizeof(struct mwifiex_roc_cfg));
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 32a27fad7b79..a94659988a4c 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -339,7 +339,7 @@ int mwifiex_bss_start(struct mwifiex_private *priv, struct cfg80211_bss *bss,
 			ret = mwifiex_associate(priv, bss_desc);
 		}
 
-		if (bss)
+		if (bss && !priv->adapter->host_mlme_enabled)
 			cfg80211_put_bss(priv->adapter->wiphy, bss);
 	} else {
 		/* Adhoc mode */
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_tx.c b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
index 70c2790b8e35..9d0ef04ebe02 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_tx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
@@ -36,7 +36,7 @@ void mwifiex_process_sta_txpd(struct mwifiex_private *priv,
 	struct txpd *local_tx_pd;
 	struct mwifiex_txinfo *tx_info = MWIFIEX_SKB_TXCB(skb);
 	unsigned int pad;
-	u16 pkt_type, pkt_offset;
+	u16 pkt_type, pkt_length, pkt_offset;
 	int hroom = adapter->intf_hdr_len;
 
 	pkt_type = mwifiex_is_skb_mgmt_frame(skb) ? PKT_TYPE_MGMT : 0;
@@ -49,9 +49,10 @@ void mwifiex_process_sta_txpd(struct mwifiex_private *priv,
 	memset(local_tx_pd, 0, sizeof(struct txpd));
 	local_tx_pd->bss_num = priv->bss_num;
 	local_tx_pd->bss_type = priv->bss_type;
-	local_tx_pd->tx_pkt_length = cpu_to_le16((u16)(skb->len -
-						       (sizeof(struct txpd) +
-							pad)));
+	pkt_length = (u16)(skb->len - (sizeof(struct txpd) + pad));
+	if (pkt_type == PKT_TYPE_MGMT)
+		pkt_length -= MWIFIEX_MGMT_FRAME_HEADER_SIZE;
+	local_tx_pd->tx_pkt_length = cpu_to_le16(pkt_length);
 
 	local_tx_pd->priority = (u8) skb->priority;
 	local_tx_pd->pkt_delay_2ms =
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 745b1d925b21..3817c08a1507 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -370,6 +370,45 @@ mwifiex_parse_mgmt_packet(struct mwifiex_private *priv, u8 *payload, u16 len,
 
 	return 0;
 }
+
+/* This function sends deauth packet to the kernel. */
+void mwifiex_host_mlme_disconnect(struct mwifiex_private *priv,
+				  u16 reason_code, u8 *sa)
+{
+	u8 frame_buf[100];
+	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)frame_buf;
+
+	memset(frame_buf, 0, sizeof(frame_buf));
+	mgmt->frame_control = cpu_to_le16(IEEE80211_STYPE_DEAUTH);
+	mgmt->duration = 0;
+	mgmt->seq_ctrl = 0;
+	mgmt->u.deauth.reason_code = cpu_to_le16(reason_code);
+
+	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) {
+		eth_broadcast_addr(mgmt->da);
+		memcpy(mgmt->sa,
+		       priv->curr_bss_params.bss_descriptor.mac_address,
+		       ETH_ALEN);
+		memcpy(mgmt->bssid, priv->cfg_bssid, ETH_ALEN);
+		priv->auth_flag = 0;
+		priv->auth_alg = WLAN_AUTH_NONE;
+	} else {
+		memcpy(mgmt->da, priv->curr_addr, ETH_ALEN);
+		memcpy(mgmt->sa, sa, ETH_ALEN);
+		memcpy(mgmt->bssid, priv->curr_addr, ETH_ALEN);
+	}
+
+	if (GET_BSS_ROLE(priv) != MWIFIEX_BSS_ROLE_UAP) {
+		wiphy_lock(priv->wdev.wiphy);
+		cfg80211_rx_mlme_mgmt(priv->netdev, frame_buf, 26);
+		wiphy_unlock(priv->wdev.wiphy);
+	} else {
+		cfg80211_rx_mgmt(&priv->wdev,
+				 priv->bss_chandef.chan->center_freq,
+				 0, frame_buf, 26, 0);
+	}
+}
+
 /*
  * This function processes the received management packet and send it
  * to the kernel.
@@ -417,6 +456,47 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 	pkt_len -= ETH_ALEN;
 	rx_pd->rx_pkt_length = cpu_to_le16(pkt_len);
 
+	if (priv->host_mlme_reg &&
+	    (GET_BSS_ROLE(priv) != MWIFIEX_BSS_ROLE_UAP) &&
+	    (ieee80211_is_auth(ieee_hdr->frame_control) ||
+	     ieee80211_is_deauth(ieee_hdr->frame_control) ||
+	     ieee80211_is_disassoc(ieee_hdr->frame_control))) {
+		if (ieee80211_is_auth(ieee_hdr->frame_control)) {
+			if (priv->auth_flag & HOST_MLME_AUTH_PENDING) {
+				if (priv->auth_alg != WLAN_AUTH_SAE) {
+					priv->auth_flag &=
+						~HOST_MLME_AUTH_PENDING;
+					priv->auth_flag |=
+						HOST_MLME_AUTH_DONE;
+				}
+			} else {
+				return 0;
+			}
+
+			mwifiex_dbg(priv->adapter, MSG,
+				    "auth: receive authentication from %pM\n",
+				    ieee_hdr->addr3);
+		} else {
+			if (!priv->wdev.connected)
+				return 0;
+
+			if (ieee80211_is_deauth(ieee_hdr->frame_control)) {
+				mwifiex_dbg(priv->adapter, MSG,
+					    "auth: receive deauth from %pM\n",
+					    ieee_hdr->addr3);
+				priv->auth_flag = 0;
+				priv->auth_alg = WLAN_AUTH_NONE;
+			} else {
+				mwifiex_dbg
+				(priv->adapter, MSG,
+				 "assoc: receive disassoc from %pM\n",
+				 ieee_hdr->addr3);
+			}
+		}
+
+		cfg80211_rx_mlme_mgmt(priv->netdev, skb->data, pkt_len);
+	}
+
 	cfg80211_rx_mgmt(&priv->wdev, priv->roc_cfg.chan.center_freq,
 			 CAL_RSSI(rx_pd->snr, rx_pd->nf), skb->data, pkt_len,
 			 0);
-- 
cgit v1.3-3-g829e


From 9588469d06977bc8ff2c131c4eb589c6477c3b7c Mon Sep 17 00:00:00 2001
From: David Lin <yu-hao.lin@nxp.com>
Date: Thu, 4 Jul 2024 11:30:01 +0800
Subject: wifi: mwifiex: add host mlme for AP mode

Add host based MLME to enable WPA3 functionalities in AP mode.
This feature required a firmware with the corresponding V2 Key API
support. The feature (WPA3) is currently enabled and verified only
on IW416. Also, verified no regression with change when host MLME
is disabled.

Signed-off-by: David Lin <yu-hao.lin@nxp.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240704033001.603419-3-yu-hao.lin@nxp.com
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c    |  86 ++++++++++-
 drivers/net/wireless/marvell/mwifiex/cmdevt.c      |   2 +
 drivers/net/wireless/marvell/mwifiex/fw.h          |  21 +++
 drivers/net/wireless/marvell/mwifiex/ioctl.h       |   5 +
 drivers/net/wireless/marvell/mwifiex/main.h        |   1 +
 drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c |   2 +
 drivers/net/wireless/marvell/mwifiex/uap_cmd.c     | 171 +++++++++++++++++++++
 drivers/net/wireless/marvell/mwifiex/util.c        |  24 +++
 8 files changed, 309 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index c1aaa91c5574..722ead51e912 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -221,6 +221,26 @@ mwifiex_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		return 0;
 	}
 
+	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
+		if (ieee80211_is_auth(mgmt->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "auth: send auth to %pM\n", mgmt->da);
+		if (ieee80211_is_deauth(mgmt->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "auth: send deauth to %pM\n", mgmt->da);
+		if (ieee80211_is_disassoc(mgmt->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "assoc: send disassoc to %pM\n", mgmt->da);
+		if (ieee80211_is_assoc_resp(mgmt->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "assoc: send assoc resp to %pM\n",
+				    mgmt->da);
+		if (ieee80211_is_reassoc_resp(mgmt->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "assoc: send reassoc resp to %pM\n",
+				    mgmt->da);
+	}
+
 	pkt_len = len + ETH_ALEN;
 	skb = dev_alloc_skb(MWIFIEX_MIN_DATA_HEADER_LEN +
 			    MWIFIEX_MGMT_FRAME_HEADER_SIZE +
@@ -505,6 +525,9 @@ mwifiex_cfg80211_set_default_mgmt_key(struct wiphy *wiphy,
 
 	wiphy_dbg(wiphy, "set default mgmt key, key index=%d\n", key_index);
 
+	if (priv->adapter->host_mlme_enabled)
+		return 0;
+
 	memset(&encrypt_key, 0, sizeof(struct mwifiex_ds_encrypt_key));
 	encrypt_key.key_len = WLAN_KEY_LEN_CCMP;
 	encrypt_key.key_index = key_index;
@@ -3953,12 +3976,43 @@ mwifiex_cfg80211_tdls_cancel_chan_switch(struct wiphy *wiphy,
 	}
 }
 
+static int
+mwifiex_cfg80211_uap_add_station(struct mwifiex_private *priv, const u8 *mac,
+				 struct station_parameters *params)
+{
+	struct mwifiex_sta_info add_sta;
+	int ret;
+
+	memcpy(add_sta.peer_mac, mac, ETH_ALEN);
+	add_sta.params = params;
+
+	ret = mwifiex_send_cmd(priv, HostCmd_CMD_ADD_NEW_STATION,
+			       HostCmd_ACT_ADD_STA, 0, (void *)&add_sta, true);
+
+	if (!ret) {
+		struct station_info *sinfo;
+
+		sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL);
+		if (!sinfo)
+			return -ENOMEM;
+
+		cfg80211_new_sta(priv->netdev, mac, sinfo, GFP_KERNEL);
+		kfree(sinfo);
+	}
+
+	return ret;
+}
+
 static int
 mwifiex_cfg80211_add_station(struct wiphy *wiphy, struct net_device *dev,
 			     const u8 *mac, struct station_parameters *params)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
+	if (priv->adapter->host_mlme_enabled &&
+	    (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP))
+		return mwifiex_cfg80211_uap_add_station(priv, mac, params);
+
 	if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)))
 		return -EOPNOTSUPP;
 
@@ -4196,6 +4250,10 @@ mwifiex_cfg80211_change_station(struct wiphy *wiphy, struct net_device *dev,
 	int ret;
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 
+	if (priv->adapter->host_mlme_enabled &&
+	    (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP))
+		return 0;
+
 	/* we support change_station handler only for TDLS peers*/
 	if (!(params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)))
 		return -EOPNOTSUPP;
@@ -4668,7 +4726,25 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 	}
 	wiphy->max_scan_ssids = MWIFIEX_MAX_SSID_LIST_LENGTH;
 	wiphy->max_scan_ie_len = MWIFIEX_MAX_VSIE_LEN;
-	wiphy->mgmt_stypes = mwifiex_mgmt_stypes;
+	if (adapter->host_mlme_enabled) {
+		memcpy(adapter->mwifiex_mgmt_stypes,
+		       mwifiex_mgmt_stypes,
+		       NUM_NL80211_IFTYPES *
+		       sizeof(struct ieee80211_txrx_stypes));
+
+		adapter->mwifiex_mgmt_stypes[NL80211_IFTYPE_AP].tx = 0xffff;
+		adapter->mwifiex_mgmt_stypes[NL80211_IFTYPE_AP].rx =
+			BIT(IEEE80211_STYPE_ASSOC_REQ >> 4) |
+			BIT(IEEE80211_STYPE_REASSOC_REQ >> 4) |
+			BIT(IEEE80211_STYPE_PROBE_REQ >> 4) |
+			BIT(IEEE80211_STYPE_DISASSOC >> 4) |
+			BIT(IEEE80211_STYPE_AUTH >> 4) |
+			BIT(IEEE80211_STYPE_DEAUTH >> 4) |
+			BIT(IEEE80211_STYPE_ACTION >> 4);
+		wiphy->mgmt_stypes = adapter->mwifiex_mgmt_stypes;
+	} else {
+		wiphy->mgmt_stypes = mwifiex_mgmt_stypes;
+	}
 	wiphy->max_remain_on_channel_duration = 5000;
 	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
 				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
@@ -4712,14 +4788,18 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 
 	ether_addr_copy(wiphy->perm_addr, adapter->perm_addr);
 	wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM;
-	wiphy->flags |= WIPHY_FLAG_HAVE_AP_SME |
-			WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD |
+	wiphy->flags |= WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD |
 			WIPHY_FLAG_AP_UAPSD |
 			WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL |
 			WIPHY_FLAG_HAS_CHANNEL_SWITCH |
 			WIPHY_FLAG_NETNS_OK |
 			WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
+	if (adapter->host_mlme_enabled)
+		wiphy->flags |= WIPHY_FLAG_REPORTS_OBSS;
+	else
+		wiphy->flags |= WIPHY_FLAG_HAVE_AP_SME;
+
 	if (ISSUPP_TDLS_ENABLED(adapter->fw_cap_info))
 		wiphy->flags |= WIPHY_FLAG_SUPPORTS_TDLS |
 				WIPHY_FLAG_TDLS_EXTERNAL_SETUP;
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index da983e27023c..ea6ebc9c23ef 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -635,6 +635,8 @@ int mwifiex_send_cmd(struct mwifiex_private *priv, u16 cmd_no,
 		case HostCmd_CMD_UAP_STA_DEAUTH:
 		case HOST_CMD_APCMD_SYS_RESET:
 		case HOST_CMD_APCMD_STA_LIST:
+		case HostCmd_CMD_CHAN_REPORT_REQUEST:
+		case HostCmd_CMD_ADD_NEW_STATION:
 			ret = mwifiex_uap_prepare_cmd(priv, cmd_no, cmd_action,
 						      cmd_oid, data_buf,
 						      cmd_ptr);
diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 0f89b86aa527..65799ae3bc72 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -211,6 +211,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define TLV_TYPE_CHAN_ATTR_CFG      (PROPRIETARY_TLV_BASE_ID + 237)
 #define TLV_TYPE_MAX_CONN           (PROPRIETARY_TLV_BASE_ID + 279)
 #define TLV_TYPE_HOST_MLME          (PROPRIETARY_TLV_BASE_ID + 307)
+#define TLV_TYPE_UAP_STA_FLAGS      (PROPRIETARY_TLV_BASE_ID + 313)
 #define TLV_TYPE_SAE_PWE_MODE       (PROPRIETARY_TLV_BASE_ID + 339)
 
 #define MWIFIEX_TX_DATA_BUF_SIZE_2K        2048
@@ -407,6 +408,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define HostCmd_CMD_STA_CONFIGURE		      0x023f
 #define HostCmd_CMD_CHAN_REGION_CFG		      0x0242
 #define HostCmd_CMD_PACKET_AGGR_CTRL		      0x0251
+#define HostCmd_CMD_ADD_NEW_STATION		      0x025f
 
 #define PROTOCOL_NO_SECURITY        0x01
 #define PROTOCOL_STATIC_WEP         0x02
@@ -417,6 +419,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define KEY_MGMT_NONE               0x04
 #define KEY_MGMT_PSK                0x02
 #define KEY_MGMT_EAP                0x01
+#define KEY_MGMT_SAE                0x400
 #define CIPHER_TKIP                 0x04
 #define CIPHER_AES_CCMP             0x08
 #define VALID_CIPHER_BITMAP         0x0c
@@ -502,6 +505,9 @@ enum mwifiex_channel_flags {
 #define HostCmd_ACT_GET_TX              0x0008
 #define HostCmd_ACT_GET_BOTH            0x000c
 
+#define HostCmd_ACT_REMOVE_STA          0x0
+#define HostCmd_ACT_ADD_STA             0x1
+
 #define RF_ANTENNA_AUTO                 0xFFFF
 
 #define HostCmd_SET_SEQ_NO_BSS_INFO(seq, num, type) \
@@ -2331,6 +2337,20 @@ struct host_cmd_ds_sta_configure {
 	u8 tlv_buffer[];
 } __packed;
 
+struct mwifiex_ie_types_sta_flag {
+	struct mwifiex_ie_types_header header;
+	__le32 sta_flags;
+} __packed;
+
+struct host_cmd_ds_add_station {
+	__le16 action;
+	__le16 aid;
+	u8 peer_mac[ETH_ALEN];
+	__le32 listen_interval;
+	__le16 cap_info;
+	u8 tlv[];
+} __packed;
+
 struct host_cmd_ds_command {
 	__le16 command;
 	__le16 size;
@@ -2409,6 +2429,7 @@ struct host_cmd_ds_command {
 		struct host_cmd_ds_chan_region_cfg reg_cfg;
 		struct host_cmd_ds_pkt_aggr_ctrl pkt_aggr_ctrl;
 		struct host_cmd_ds_sta_configure sta_cfg;
+		struct host_cmd_ds_add_station sta_info;
 	} params;
 } __packed;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/ioctl.h b/drivers/net/wireless/marvell/mwifiex/ioctl.h
index e8825f302de8..516159b721d3 100644
--- a/drivers/net/wireless/marvell/mwifiex/ioctl.h
+++ b/drivers/net/wireless/marvell/mwifiex/ioctl.h
@@ -158,6 +158,11 @@ struct mwifiex_bss_info {
 	u8 bssid[ETH_ALEN];
 };
 
+struct mwifiex_sta_info {
+	u8 peer_mac[ETH_ALEN];
+	struct station_parameters *params;
+};
+
 #define MAX_NUM_TID     8
 
 #define MAX_RX_WINSIZE  64
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index d4c56c3d4cf1..9024bb944e6a 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1008,6 +1008,7 @@ struct mwifiex_adapter {
 
 	bool ext_scan;
 	bool host_mlme_enabled;
+	struct ieee80211_txrx_stypes mwifiex_mgmt_stypes[NUM_NL80211_IFTYPES];
 	u8 fw_api_ver;
 	u8 key_api_major_ver, key_api_minor_ver;
 	u8 max_p2p_conn, max_sta_conn;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
index 7b69d27e0c0e..9c53825f222d 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c
@@ -1398,6 +1398,8 @@ int mwifiex_process_sta_cmdresp(struct mwifiex_private *priv, u16 cmdresp_no,
 		break;
 	case HostCmd_CMD_UAP_STA_DEAUTH:
 		break;
+	case HostCmd_CMD_ADD_NEW_STATION:
+		break;
 	case HOST_CMD_APCMD_SYS_RESET:
 		break;
 	case HostCmd_CMD_MEF_CFG:
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
index 491e36611909..073c665183b3 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
@@ -72,6 +72,10 @@ int mwifiex_set_secure_params(struct mwifiex_private *priv,
 				bss_config->key_mgmt = KEY_MGMT_PSK;
 			}
 			break;
+		case WLAN_AKM_SUITE_SAE:
+			bss_config->protocol = PROTOCOL_WPA2;
+			bss_config->key_mgmt = KEY_MGMT_SAE;
+			break;
 		default:
 			break;
 		}
@@ -751,6 +755,28 @@ mwifiex_cmd_uap_sys_config(struct host_cmd_ds_command *cmd, u16 cmd_action,
 	return 0;
 }
 
+/* This function prepares AP start up command with or without host MLME
+ */
+static void mwifiex_cmd_uap_bss_start(struct mwifiex_private *priv,
+				     struct host_cmd_ds_command *cmd)
+{
+	struct mwifiex_ie_types_host_mlme *tlv;
+	int size;
+
+	cmd->command = cpu_to_le16(HostCmd_CMD_UAP_BSS_START);
+	size = S_DS_GEN;
+
+	if (priv->adapter->host_mlme_enabled) {
+		tlv = (struct mwifiex_ie_types_host_mlme *)((u8 *)cmd + size);
+		tlv->header.type = cpu_to_le16(TLV_TYPE_HOST_MLME);
+		tlv->header.len = cpu_to_le16(sizeof(tlv->host_mlme));
+		tlv->host_mlme = 1;
+		size += sizeof(struct mwifiex_ie_types_host_mlme);
+	}
+
+	cmd->size = cpu_to_le16(size);
+}
+
 /* This function prepares AP specific deauth command with mac supplied in
  * function parameter.
  */
@@ -768,6 +794,144 @@ static int mwifiex_cmd_uap_sta_deauth(struct mwifiex_private *priv,
 	return 0;
 }
 
+/* This function prepares AP specific add station command.
+ */
+static int mwifiex_cmd_uap_add_station(struct mwifiex_private *priv,
+				       struct host_cmd_ds_command *cmd,
+				       u16 cmd_action, void *data_buf)
+{
+	struct host_cmd_ds_add_station *new_sta = &cmd->params.sta_info;
+	struct mwifiex_sta_info *add_sta = (struct mwifiex_sta_info *)data_buf;
+	struct station_parameters *params = add_sta->params;
+	struct mwifiex_sta_node *sta_ptr;
+	u8 *pos;
+	u8 qos_capa;
+	u16 header_len = sizeof(struct mwifiex_ie_types_header);
+	u16 tlv_len;
+	int size;
+	struct mwifiex_ie_types_data *tlv;
+	struct mwifiex_ie_types_sta_flag *sta_flag;
+	int i;
+
+	cmd->command = cpu_to_le16(HostCmd_CMD_ADD_NEW_STATION);
+	new_sta->action = cpu_to_le16(cmd_action);
+	size = sizeof(struct host_cmd_ds_add_station) + S_DS_GEN;
+
+	if (cmd_action == HostCmd_ACT_ADD_STA)
+		sta_ptr = mwifiex_add_sta_entry(priv, add_sta->peer_mac);
+	else
+		sta_ptr = mwifiex_get_sta_entry(priv, add_sta->peer_mac);
+
+	if (!sta_ptr)
+		return -1;
+
+	memcpy(new_sta->peer_mac, add_sta->peer_mac, ETH_ALEN);
+
+	if (cmd_action == HostCmd_ACT_REMOVE_STA) {
+		cmd->size = cpu_to_le16(size);
+		return 0;
+	}
+
+	new_sta->aid = cpu_to_le16(params->aid);
+	new_sta->listen_interval = cpu_to_le32(params->listen_interval);
+	new_sta->cap_info = cpu_to_le16(params->capability);
+
+	pos = new_sta->tlv;
+
+	if (params->sta_flags_set & NL80211_STA_FLAG_WME)
+		sta_ptr->is_wmm_enabled = 1;
+	sta_flag = (struct mwifiex_ie_types_sta_flag *)pos;
+	sta_flag->header.type = cpu_to_le16(TLV_TYPE_UAP_STA_FLAGS);
+	sta_flag->header.len = cpu_to_le16(sizeof(__le32));
+	sta_flag->sta_flags = cpu_to_le32(params->sta_flags_set);
+	pos += sizeof(struct mwifiex_ie_types_sta_flag);
+	size += sizeof(struct mwifiex_ie_types_sta_flag);
+
+	if (params->ext_capab_len) {
+		tlv = (struct mwifiex_ie_types_data *)pos;
+		tlv->header.type = cpu_to_le16(WLAN_EID_EXT_CAPABILITY);
+		tlv_len = params->ext_capab_len;
+		tlv->header.len = cpu_to_le16(tlv_len);
+		memcpy(tlv->data, params->ext_capab, tlv_len);
+		pos += (header_len + tlv_len);
+		size += (header_len + tlv_len);
+	}
+
+	if (params->link_sta_params.supported_rates_len) {
+		tlv = (struct mwifiex_ie_types_data *)pos;
+		tlv->header.type = cpu_to_le16(WLAN_EID_SUPP_RATES);
+		tlv_len = params->link_sta_params.supported_rates_len;
+		tlv->header.len = cpu_to_le16(tlv_len);
+		memcpy(tlv->data,
+		       params->link_sta_params.supported_rates, tlv_len);
+		pos += (header_len + tlv_len);
+		size += (header_len + tlv_len);
+	}
+
+	if (params->uapsd_queues || params->max_sp) {
+		tlv = (struct mwifiex_ie_types_data *)pos;
+		tlv->header.type = cpu_to_le16(WLAN_EID_QOS_CAPA);
+		tlv_len = sizeof(qos_capa);
+		tlv->header.len = cpu_to_le16(tlv_len);
+		qos_capa = params->uapsd_queues | (params->max_sp << 5);
+		memcpy(tlv->data, &qos_capa, tlv_len);
+		pos += (header_len + tlv_len);
+		size += (header_len + tlv_len);
+		sta_ptr->is_wmm_enabled = 1;
+	}
+
+	if (params->link_sta_params.ht_capa) {
+		tlv = (struct mwifiex_ie_types_data *)pos;
+		tlv->header.type = cpu_to_le16(WLAN_EID_HT_CAPABILITY);
+		tlv_len = sizeof(struct ieee80211_ht_cap);
+		tlv->header.len = cpu_to_le16(tlv_len);
+		memcpy(tlv->data, params->link_sta_params.ht_capa, tlv_len);
+		pos += (header_len + tlv_len);
+		size += (header_len + tlv_len);
+		sta_ptr->is_11n_enabled = 1;
+		sta_ptr->max_amsdu =
+			le16_to_cpu(params->link_sta_params.ht_capa->cap_info) &
+			IEEE80211_HT_CAP_MAX_AMSDU ?
+			MWIFIEX_TX_DATA_BUF_SIZE_8K :
+			MWIFIEX_TX_DATA_BUF_SIZE_4K;
+	}
+
+	if (params->link_sta_params.vht_capa) {
+		tlv = (struct mwifiex_ie_types_data *)pos;
+		tlv->header.type = cpu_to_le16(WLAN_EID_VHT_CAPABILITY);
+		tlv_len = sizeof(struct ieee80211_vht_cap);
+		tlv->header.len = cpu_to_le16(tlv_len);
+		memcpy(tlv->data, params->link_sta_params.vht_capa, tlv_len);
+		pos += (header_len + tlv_len);
+		size += (header_len + tlv_len);
+		sta_ptr->is_11ac_enabled = 1;
+	}
+
+	if (params->link_sta_params.opmode_notif_used) {
+		tlv = (struct mwifiex_ie_types_data *)pos;
+		tlv->header.type = cpu_to_le16(WLAN_EID_OPMODE_NOTIF);
+		tlv_len = sizeof(u8);
+		tlv->header.len = cpu_to_le16(tlv_len);
+		memcpy(tlv->data, &params->link_sta_params.opmode_notif,
+		       tlv_len);
+		pos += (header_len + tlv_len);
+		size += (header_len + tlv_len);
+	}
+
+	for (i = 0; i < MAX_NUM_TID; i++) {
+		if (sta_ptr->is_11n_enabled)
+			sta_ptr->ampdu_sta[i] =
+				      priv->aggr_prio_tbl[i].ampdu_user;
+		else
+			sta_ptr->ampdu_sta[i] = BA_STREAM_NOT_ALLOWED;
+	}
+
+	memset(sta_ptr->rx_seq, 0xff, sizeof(sta_ptr->rx_seq));
+	cmd->size = cpu_to_le16(size);
+
+	return 0;
+}
+
 /* This function prepares the AP specific commands before sending them
  * to the firmware.
  * This is a generic function which calls specific command preparation
@@ -785,6 +949,8 @@ int mwifiex_uap_prepare_cmd(struct mwifiex_private *priv, u16 cmd_no,
 			return -1;
 		break;
 	case HostCmd_CMD_UAP_BSS_START:
+		mwifiex_cmd_uap_bss_start(priv, cmd);
+		break;
 	case HostCmd_CMD_UAP_BSS_STOP:
 	case HOST_CMD_APCMD_SYS_RESET:
 	case HOST_CMD_APCMD_STA_LIST:
@@ -800,6 +966,11 @@ int mwifiex_uap_prepare_cmd(struct mwifiex_private *priv, u16 cmd_no,
 							  data_buf))
 			return -1;
 		break;
+	case HostCmd_CMD_ADD_NEW_STATION:
+		if (mwifiex_cmd_uap_add_station(priv, cmd, cmd_action,
+						data_buf))
+			return -1;
+		break;
 	default:
 		mwifiex_dbg(priv->adapter, ERROR,
 			    "PREP_CMD: unknown cmd %#x\n", cmd_no);
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 3817c08a1507..42c04bf858da 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -497,6 +497,30 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 		cfg80211_rx_mlme_mgmt(priv->netdev, skb->data, pkt_len);
 	}
 
+	if (priv->adapter->host_mlme_enabled &&
+	    (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP)) {
+		if (ieee80211_is_auth(ieee_hdr->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "auth: receive auth from %pM\n",
+				    ieee_hdr->addr2);
+		if (ieee80211_is_deauth(ieee_hdr->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "auth: receive deauth from %pM\n",
+				    ieee_hdr->addr2);
+		if (ieee80211_is_disassoc(ieee_hdr->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "assoc: receive disassoc from %pM\n",
+				    ieee_hdr->addr2);
+		if (ieee80211_is_assoc_req(ieee_hdr->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "assoc: receive assoc req from %pM\n",
+				    ieee_hdr->addr2);
+		if (ieee80211_is_reassoc_req(ieee_hdr->frame_control))
+			mwifiex_dbg(priv->adapter, MSG,
+				    "assoc: receive reassoc req from %pM\n",
+				    ieee_hdr->addr2);
+	}
+
 	cfg80211_rx_mgmt(&priv->wdev, priv->roc_cfg.chan.center_freq,
 			 CAL_RSSI(rx_pd->snr, rx_pd->nf), skb->data, pkt_len,
 			 0);
-- 
cgit v1.3-3-g829e


From 16b31ecb802946f1855259a2006c32c8d340ea5c Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 21 Jul 2024 09:40:19 +0200
Subject: wifi: brcmfmac: fwsignal: Use struct_size() to simplify
 brcmf_fws_rxreorder()

In the "struct brcmf_ampdu_rx_reorder", change the 'pktslots' field into
flexible array.

It saves the size of a pointer when the memory is allocated and avoids
an indirection when the array is used.
It also removes the usage of a pointer arithmetic and saves a few lines of
code.

Finally, struct_size() can be used. It is not a must have here, because
it is easy to see that buf_size can not overflow, but still, it is a good
practice.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/f4ca6b887ca1290c71e76247218adea4d1c42442.1721547559.git.christophe.jaillet@wanadoo.fr
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h     | 4 ++--
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c | 8 ++------
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
index ea76b8d33401..39226b9c0fa8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
@@ -48,20 +48,20 @@
 /**
  * struct brcmf_ampdu_rx_reorder - AMPDU receive reorder info
  *
- * @pktslots: dynamic allocated array for ordering AMPDU packets.
  * @flow_id: AMPDU flow identifier.
  * @cur_idx: last AMPDU index from firmware.
  * @exp_idx: expected next AMPDU index.
  * @max_idx: maximum amount of packets per AMPDU.
  * @pend_pkts: number of packets currently in @pktslots.
+ * @pktslots: array for ordering AMPDU packets.
  */
 struct brcmf_ampdu_rx_reorder {
-	struct sk_buff **pktslots;
 	u8 flow_id;
 	u8 cur_idx;
 	u8 exp_idx;
 	u8 max_idx;
 	u8 pend_pkts;
+	struct sk_buff *pktslots[];
 };
 
 /* Forward decls for struct brcmf_pub (see below) */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
index 36af81975855..0949e7975ff1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwsignal.c
@@ -1673,7 +1673,6 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 	struct sk_buff_head reorder_list;
 	struct sk_buff *pnext;
 	u8 flags;
-	u32 buf_size;
 
 	reorder_data = ((struct brcmf_skb_reorder_data *)pkt->cb)->reorder;
 	flow_id = reorder_data[BRCMF_RXREORDER_FLOWID_OFFSET];
@@ -1708,15 +1707,13 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 	}
 	/* from here on we need a flow reorder instance */
 	if (rfi == NULL) {
-		buf_size = sizeof(*rfi);
 		max_idx = reorder_data[BRCMF_RXREORDER_MAXIDX_OFFSET];
 
-		buf_size += (max_idx + 1) * sizeof(pkt);
-
 		/* allocate space for flow reorder info */
 		brcmf_dbg(INFO, "flow-%d: start, maxidx %d\n",
 			  flow_id, max_idx);
-		rfi = kzalloc(buf_size, GFP_ATOMIC);
+		rfi = kzalloc(struct_size(rfi, pktslots, max_idx + 1),
+			      GFP_ATOMIC);
 		if (rfi == NULL) {
 			bphy_err(drvr, "failed to alloc buffer\n");
 			brcmf_netif_rx(ifp, pkt);
@@ -1724,7 +1721,6 @@ void brcmf_fws_rxreorder(struct brcmf_if *ifp, struct sk_buff *pkt)
 		}
 
 		ifp->drvr->reorder_flows[flow_id] = rfi;
-		rfi->pktslots = (struct sk_buff **)(rfi + 1);
 		rfi->max_idx = max_idx;
 	}
 	if (flags & BRCMF_RXREORDER_NEW_HOLE)  {
-- 
cgit v1.3-3-g829e


From c6002b6c05f3edfa12fd25990cc637281f200442 Mon Sep 17 00:00:00 2001
From: Arend van Spriel <arend.vanspriel@broadcom.com>
Date: Sat, 27 Jul 2024 20:56:17 +0200
Subject: wifi: brcmfmac: introducing fwil query functions

When the firmware interface layer was refactored it provided various
"get" and "set" functions. For the "get" in some cases a parameter
needed to be passed down to firmware as a key indicating what to
"get" turning the output parameter of the "get" function into an
input parameter as well. To accommodate this the "get" function blindly
copies the parameter which in some places resulted in an uninitialized
warnings from the compiler. These have been fixed by initializing the
input parameter in the past. Recently another batch of similar fixes
were submitted to address clang static checker warnings [1].

Proposing another solution by introducing a "query" variant which is used
when the (input) parameter is needed by firmware. The "get" variant will
only fill the (output) parameter with the result received from firmware
taking care of proper endianess conversion.

[1] https://lore.kernel.org/all/20240702122450.2213833-1-suhui@nfschina.com/

Fixes: 81f5dcb80830 ("brcmfmac: refactor firmware interface layer.")
Reported-by: Su Hui <suhui@nfschina.com>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240727185617.253210-1-arend.vanspriel@broadcom.com
---
 .../wireless/broadcom/brcm80211/brcmfmac/btcoex.c  |  2 +-
 .../broadcom/brcm80211/brcmfmac/cfg80211.c         | 30 ++++++++--------
 .../wireless/broadcom/brcm80211/brcmfmac/core.c    |  2 +-
 .../wireless/broadcom/brcm80211/brcmfmac/feature.c |  2 +-
 .../wireless/broadcom/brcm80211/brcmfmac/fwil.h    | 40 ++++++++++++++++------
 5 files changed, 48 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
index 0c3d119d1219..1e8495f50c16 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
@@ -123,7 +123,7 @@ static s32 brcmf_btcoex_params_read(struct brcmf_if *ifp, u32 addr, u32 *data)
 {
 	*data = addr;
 
-	return brcmf_fil_iovar_int_get(ifp, "btc_params", data);
+	return brcmf_fil_iovar_int_query(ifp, "btc_params", data);
 }
 
 /**
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 1585a5653ee4..2379f46e2326 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -663,8 +663,8 @@ static int brcmf_cfg80211_request_sta_if(struct brcmf_if *ifp, u8 *macaddr)
 	/* interface_create version 3+ */
 	/* get supported version from firmware side */
 	iface_create_ver = 0;
-	err = brcmf_fil_bsscfg_int_get(ifp, "interface_create",
-				       &iface_create_ver);
+	err = brcmf_fil_bsscfg_int_query(ifp, "interface_create",
+					 &iface_create_ver);
 	if (err) {
 		brcmf_err("fail to get supported version, err=%d\n", err);
 		return -EOPNOTSUPP;
@@ -756,8 +756,8 @@ static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp)
 	/* interface_create version 3+ */
 	/* get supported version from firmware side */
 	iface_create_ver = 0;
-	err = brcmf_fil_bsscfg_int_get(ifp, "interface_create",
-				       &iface_create_ver);
+	err = brcmf_fil_bsscfg_int_query(ifp, "interface_create",
+					 &iface_create_ver);
 	if (err) {
 		brcmf_err("fail to get supported version, err=%d\n", err);
 		return -EOPNOTSUPP;
@@ -2101,7 +2101,8 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme)
 	if (!sme->crypto.n_akm_suites)
 		return 0;
 
-	err = brcmf_fil_bsscfg_int_get(netdev_priv(ndev), "wpa_auth", &val);
+	err = brcmf_fil_bsscfg_int_get(netdev_priv(ndev),
+				       "wpa_auth", &val);
 	if (err) {
 		bphy_err(drvr, "could not get wpa_auth (%d)\n", err);
 		return err;
@@ -2680,7 +2681,7 @@ brcmf_cfg80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev,
 	struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
 	struct brcmf_cfg80211_vif *vif = wdev_to_vif(wdev);
 	struct brcmf_pub *drvr = cfg->pub;
-	s32 qdbm = 0;
+	s32 qdbm;
 	s32 err;
 
 	brcmf_dbg(TRACE, "Enter\n");
@@ -3067,7 +3068,7 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 	struct brcmf_scb_val_le scbval;
 	struct brcmf_pktcnt_le pktcnt;
 	s32 err;
-	u32 rate = 0;
+	u32 rate;
 	u32 rssi;
 
 	/* Get the current tx rate */
@@ -7039,8 +7040,8 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg,
 			ch.bw = BRCMU_CHAN_BW_20;
 			cfg->d11inf.encchspec(&ch);
 			chaninfo = ch.chspec;
-			err = brcmf_fil_bsscfg_int_get(ifp, "per_chan_info",
-						       &chaninfo);
+			err = brcmf_fil_bsscfg_int_query(ifp, "per_chan_info",
+							 &chaninfo);
 			if (!err) {
 				if (chaninfo & WL_CHAN_RADAR)
 					channel->flags |=
@@ -7074,7 +7075,7 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg)
 
 	/* verify support for bw_cap command */
 	val = WLC_BAND_5G;
-	err = brcmf_fil_iovar_int_get(ifp, "bw_cap", &val);
+	err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &val);
 
 	if (!err) {
 		/* only set 2G bandwidth using bw_cap command */
@@ -7150,11 +7151,11 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[])
 	int err;
 
 	band = WLC_BAND_2G;
-	err = brcmf_fil_iovar_int_get(ifp, "bw_cap", &band);
+	err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &band);
 	if (!err) {
 		bw_cap[NL80211_BAND_2GHZ] = band;
 		band = WLC_BAND_5G;
-		err = brcmf_fil_iovar_int_get(ifp, "bw_cap", &band);
+		err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &band);
 		if (!err) {
 			bw_cap[NL80211_BAND_5GHZ] = band;
 			return;
@@ -7163,7 +7164,6 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[])
 		return;
 	}
 	brcmf_dbg(INFO, "fallback to mimo_bw_cap info\n");
-	mimo_bwcap = 0;
 	err = brcmf_fil_iovar_int_get(ifp, "mimo_bw_cap", &mimo_bwcap);
 	if (err)
 		/* assume 20MHz if firmware does not give a clue */
@@ -7259,10 +7259,10 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg)
 	struct brcmf_pub *drvr = cfg->pub;
 	struct brcmf_if *ifp = brcmf_get_ifp(drvr, 0);
 	struct wiphy *wiphy = cfg_to_wiphy(cfg);
-	u32 nmode = 0;
+	u32 nmode;
 	u32 vhtmode = 0;
 	u32 bw_cap[2] = { WLC_BW_20MHZ_BIT, WLC_BW_20MHZ_BIT };
-	u32 rxchain = 0;
+	u32 rxchain;
 	u32 nchain;
 	int err;
 	s32 i;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index bf91b1e1368f..df53dd1d7e74 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -691,7 +691,7 @@ static int brcmf_net_mon_open(struct net_device *ndev)
 {
 	struct brcmf_if *ifp = netdev_priv(ndev);
 	struct brcmf_pub *drvr = ifp->drvr;
-	u32 monitor = 0;
+	u32 monitor;
 	int err;
 
 	brcmf_dbg(TRACE, "Enter\n");
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index f23310a77a5d..0d9ae197fa1e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -184,7 +184,7 @@ static void brcmf_feat_wlc_version_overrides(struct brcmf_pub *drv)
 static void brcmf_feat_iovar_int_get(struct brcmf_if *ifp,
 				     enum brcmf_feat_id id, char *name)
 {
-	u32 data = 0;
+	u32 data;
 	int err;
 
 	/* we need to know firmware error */
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
index a315a7fac6a0..31e080e4da66 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
@@ -96,15 +96,22 @@ static inline
 s32 brcmf_fil_cmd_int_get(struct brcmf_if *ifp, u32 cmd, u32 *data)
 {
 	s32 err;
-	__le32 data_le = cpu_to_le32(*data);
 
-	err = brcmf_fil_cmd_data_get(ifp, cmd, &data_le, sizeof(data_le));
+	err = brcmf_fil_cmd_data_get(ifp, cmd, data, sizeof(*data));
 	if (err == 0)
-		*data = le32_to_cpu(data_le);
+		*data = le32_to_cpu(*(__le32 *)data);
 	brcmf_dbg(FIL, "ifidx=%d, cmd=%d, value=%d\n", ifp->ifidx, cmd, *data);
 
 	return err;
 }
+static inline
+s32 brcmf_fil_cmd_int_query(struct brcmf_if *ifp, u32 cmd, u32 *data)
+{
+	__le32 *data_le = (__le32 *)data;
+
+	*data_le = cpu_to_le32(*data);
+	return brcmf_fil_cmd_int_get(ifp, cmd, data);
+}
 
 s32 brcmf_fil_iovar_data_set(struct brcmf_if *ifp, const char *name,
 			     const void *data, u32 len);
@@ -120,14 +127,21 @@ s32 brcmf_fil_iovar_int_set(struct brcmf_if *ifp, const char *name, u32 data)
 static inline
 s32 brcmf_fil_iovar_int_get(struct brcmf_if *ifp, const char *name, u32 *data)
 {
-	__le32 data_le = cpu_to_le32(*data);
 	s32 err;
 
-	err = brcmf_fil_iovar_data_get(ifp, name, &data_le, sizeof(data_le));
+	err = brcmf_fil_iovar_data_get(ifp, name, data, sizeof(*data));
 	if (err == 0)
-		*data = le32_to_cpu(data_le);
+		*data = le32_to_cpu(*(__le32 *)data);
 	return err;
 }
+static inline
+s32 brcmf_fil_iovar_int_query(struct brcmf_if *ifp, const char *name, u32 *data)
+{
+	__le32 *data_le = (__le32 *)data;
+
+	*data_le = cpu_to_le32(*data);
+	return brcmf_fil_iovar_int_get(ifp, name, data);
+}
 
 
 s32 brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, const char *name,
@@ -145,15 +159,21 @@ s32 brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, const char *name, u32 data)
 static inline
 s32 brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, const char *name, u32 *data)
 {
-	__le32 data_le = cpu_to_le32(*data);
 	s32 err;
 
-	err = brcmf_fil_bsscfg_data_get(ifp, name, &data_le,
-					sizeof(data_le));
+	err = brcmf_fil_bsscfg_data_get(ifp, name, data, sizeof(*data));
 	if (err == 0)
-		*data = le32_to_cpu(data_le);
+		*data = le32_to_cpu(*(__le32 *)data);
 	return err;
 }
+static inline
+s32 brcmf_fil_bsscfg_int_query(struct brcmf_if *ifp, const char *name, u32 *data)
+{
+	__le32 *data_le = (__le32 *)data;
+
+	*data_le = cpu_to_le32(*data);
+	return brcmf_fil_bsscfg_int_get(ifp, name, data);
+}
 
 s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, const char *name, u16 id,
 			    void *data, u32 len);
-- 
cgit v1.3-3-g829e


From 420a549395c24bf9e4755f9fb220ce72b2f4f8bd Mon Sep 17 00:00:00 2001
From: Dmitry Kandybka <d.kandybka@gmail.com>
Date: Thu, 1 Aug 2024 13:15:31 +0300
Subject: wifi: brcmsmac: clean up unnecessary current_ampdu_cnt and related
 checks

In 'brcms_c_ffpld_check_txfunfl()', 'current_ampdu_cnt' is hardcoded to
zero, so 'txunfl_ratio' is always zero as well and some dead code can be
removed. Compile tested only.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Signed-off-by: Dmitry Kandybka <d.kandybka@gmail.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240801101531.6626-1-d.kandybka@gmail.com
---
 .../wireless/broadcom/brcm80211/brcmsmac/ampdu.c   | 22 +---------------------
 1 file changed, 1 insertion(+), 21 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
index 33d17b779201..a767cbb79185 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/ampdu.c
@@ -351,9 +351,7 @@ static int brcms_c_ffpld_check_txfunfl(struct brcms_c_info *wlc, int fid)
 {
 	struct ampdu_info *ampdu = wlc->ampdu;
 	u32 phy_rate = mcs_2_rate(FFPLD_MAX_MCS, true, false);
-	u32 txunfl_ratio;
 	u8 max_mpdu;
-	u32 current_ampdu_cnt = 0;
 	u16 max_pld_size;
 	u32 new_txunfl;
 	struct brcms_fifo_info *fifo = (ampdu->fifo_tb + fid);
@@ -389,26 +387,8 @@ static int brcms_c_ffpld_check_txfunfl(struct brcms_c_info *wlc, int fid)
 	if (fifo->accum_txfunfl < 10)
 		return 0;
 
-	brcms_dbg_ht(wlc->hw->d11core, "ampdu_count %d  tx_underflows %d\n",
-		     current_ampdu_cnt, fifo->accum_txfunfl);
+	brcms_dbg_ht(wlc->hw->d11core, "tx_underflows %d\n", fifo->accum_txfunfl);
 
-	/*
-	   compute the current ratio of tx unfl per ampdu.
-	   When the current ampdu count becomes too
-	   big while the ratio remains small, we reset
-	   the current count in order to not
-	   introduce too big of a latency in detecting a
-	   large amount of tx underflows later.
-	 */
-
-	txunfl_ratio = current_ampdu_cnt / fifo->accum_txfunfl;
-
-	if (txunfl_ratio > ampdu->tx_max_funl) {
-		if (current_ampdu_cnt >= FFPLD_MAX_AMPDU_CNT)
-			fifo->accum_txfunfl = 0;
-
-		return 0;
-	}
 	max_mpdu = min_t(u8, fifo->mcs2ampdu_table[FFPLD_MAX_MCS],
 			 AMPDU_NUM_MPDU_LEGACY);
 
-- 
cgit v1.3-3-g829e


From 101a002af005a21619463372f45ffb444a203438 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 09:35:11 +0200
Subject: dt-bindings: net: dsa: mediatek,mt7530: Add airoha,en7581-switch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add documentation for the built-in switch which can be found in the
Airoha EN7581 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Arınç ÜNAL <arinc.unal@arinc9.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml
index 7e405ad96eb2..ea979bcae1d6 100644
--- a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml
@@ -92,6 +92,10 @@ properties:
           Built-in switch of the MT7988 SoC
         const: mediatek,mt7988-switch
 
+      - description:
+          Built-in switch of the Airoha EN7581 SoC
+        const: airoha,en7581-switch
+
   reg:
     maxItems: 1
 
@@ -284,7 +288,9 @@ allOf:
   - if:
       properties:
         compatible:
-          const: mediatek,mt7988-switch
+          enum:
+            - mediatek,mt7988-switch
+            - airoha,en7581-switch
     then:
       $ref: "#/$defs/mt7530-dsa-port"
       properties:
-- 
cgit v1.3-3-g829e


From 2b0229f67932e4b9e2f458bf286903582bd30740 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 1 Aug 2024 09:35:12 +0200
Subject: net: dsa: mt7530: Add EN7581 support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce support for the DSA built-in switch available on the EN7581
development board. EN7581 support is similar to MT7988 one except
it requires to set MT7530_FORCE_MODE bit in MT753X_PMCR_P register
for on cpu port.

Tested-by: Benjamin Larsson <benjamin.larsson@genexis.eu>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Arınç ÜNAL <arinc.unal@arinc9.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mt7530-mmio.c |  1 +
 drivers/net/dsa/mt7530.c      | 49 +++++++++++++++++++++++++++++++++++++------
 drivers/net/dsa/mt7530.h      | 20 +++++++++++++-----
 3 files changed, 59 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c
index b74a230a3f13..10dc49961f15 100644
--- a/drivers/net/dsa/mt7530-mmio.c
+++ b/drivers/net/dsa/mt7530-mmio.c
@@ -11,6 +11,7 @@
 #include "mt7530.h"
 
 static const struct of_device_id mt7988_of_match[] = {
+	{ .compatible = "airoha,en7581-switch", .data = &mt753x_table[ID_EN7581], },
 	{ .compatible = "mediatek,mt7988-switch", .data = &mt753x_table[ID_MT7988], },
 	{ /* sentinel */ },
 };
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index ec18e68bf3a8..d84ee1b419a6 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1152,7 +1152,8 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port)
 	 * the MT7988 SoC. Trapped frames will be forwarded to the CPU port that
 	 * is affine to the inbound user port.
 	 */
-	if (priv->id == ID_MT7531 || priv->id == ID_MT7988)
+	if (priv->id == ID_MT7531 || priv->id == ID_MT7988 ||
+	    priv->id == ID_EN7581)
 		mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port)));
 
 	/* CPU port gets connected to all user ports of
@@ -2207,7 +2208,7 @@ mt7530_setup_irq(struct mt7530_priv *priv)
 		return priv->irq ? : -EINVAL;
 	}
 
-	if (priv->id == ID_MT7988)
+	if (priv->id == ID_MT7988 || priv->id == ID_EN7581)
 		priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
 							 &mt7988_irq_domain_ops,
 							 priv);
@@ -2438,8 +2439,10 @@ mt7530_setup(struct dsa_switch *ds)
 		/* Clear link settings and enable force mode to force link down
 		 * on all ports until they're enabled later.
 		 */
-		mt7530_rmw(priv, MT753X_PMCR_P(i), PMCR_LINK_SETTINGS_MASK |
-			   MT7530_FORCE_MODE, MT7530_FORCE_MODE);
+		mt7530_rmw(priv, MT753X_PMCR_P(i),
+			   PMCR_LINK_SETTINGS_MASK |
+			   MT753X_FORCE_MODE(priv->id),
+			   MT753X_FORCE_MODE(priv->id));
 
 		/* Disable forwarding by default on all ports */
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
@@ -2550,8 +2553,10 @@ mt7531_setup_common(struct dsa_switch *ds)
 		/* Clear link settings and enable force mode to force link down
 		 * on all ports until they're enabled later.
 		 */
-		mt7530_rmw(priv, MT753X_PMCR_P(i), PMCR_LINK_SETTINGS_MASK |
-			   MT7531_FORCE_MODE_MASK, MT7531_FORCE_MODE_MASK);
+		mt7530_rmw(priv, MT753X_PMCR_P(i),
+			   PMCR_LINK_SETTINGS_MASK |
+			   MT753X_FORCE_MODE(priv->id),
+			   MT753X_FORCE_MODE(priv->id));
 
 		/* Disable forwarding by default on all ports */
 		mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
@@ -2783,6 +2788,28 @@ static void mt7988_mac_port_get_caps(struct dsa_switch *ds, int port,
 	}
 }
 
+static void en7581_mac_port_get_caps(struct dsa_switch *ds, int port,
+				     struct phylink_config *config)
+{
+	switch (port) {
+	/* Ports which are connected to switch PHYs. There is no MII pinout. */
+	case 0 ... 4:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+
+		config->mac_capabilities |= MAC_10 | MAC_100 | MAC_1000FD;
+		break;
+
+	/* Port 6 is connected to SoC's XGMII MAC. There is no MII pinout. */
+	case 6:
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  config->supported_interfaces);
+
+		config->mac_capabilities |= MAC_10000FD;
+		break;
+	}
+}
+
 static void
 mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
 		  phy_interface_t interface)
@@ -3220,6 +3247,16 @@ const struct mt753x_info mt753x_table[] = {
 		.phy_write_c45 = mt7531_ind_c45_phy_write,
 		.mac_port_get_caps = mt7988_mac_port_get_caps,
 	},
+	[ID_EN7581] = {
+		.id = ID_EN7581,
+		.pcs_ops = &mt7530_pcs_ops,
+		.sw_setup = mt7988_setup,
+		.phy_read_c22 = mt7531_ind_c22_phy_read,
+		.phy_write_c22 = mt7531_ind_c22_phy_write,
+		.phy_read_c45 = mt7531_ind_c45_phy_read,
+		.phy_write_c45 = mt7531_ind_c45_phy_write,
+		.mac_port_get_caps = en7581_mac_port_get_caps,
+	},
 };
 EXPORT_SYMBOL_GPL(mt753x_table);
 
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 28592123070b..6ad33a9f6b1d 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -19,6 +19,7 @@ enum mt753x_id {
 	ID_MT7621 = 1,
 	ID_MT7531 = 2,
 	ID_MT7988 = 3,
+	ID_EN7581 = 4,
 };
 
 #define	NUM_TRGMII_CTRL			5
@@ -64,25 +65,30 @@ enum mt753x_id {
 #define  MT7531_CPU_PMAP(x)		FIELD_PREP(MT7531_CPU_PMAP_MASK, x)
 
 #define MT753X_MIRROR_REG(id)		((id == ID_MT7531 || \
-					  id == ID_MT7988) ? \
+					  id == ID_MT7988 || \
+					  id == ID_EN7581) ? \
 					 MT7531_CFC : MT753X_MFC)
 
 #define MT753X_MIRROR_EN(id)		((id == ID_MT7531 || \
-					  id == ID_MT7988) ? \
+					  id == ID_MT7988 || \
+					  id == ID_EN7581) ? \
 					 MT7531_MIRROR_EN : MT7530_MIRROR_EN)
 
 #define MT753X_MIRROR_PORT_MASK(id)	((id == ID_MT7531 || \
-					  id == ID_MT7988) ? \
+					  id == ID_MT7988 || \
+					  id == ID_EN7581) ? \
 					 MT7531_MIRROR_PORT_MASK : \
 					 MT7530_MIRROR_PORT_MASK)
 
 #define MT753X_MIRROR_PORT_GET(id, val)	((id == ID_MT7531 || \
-					  id == ID_MT7988) ? \
+					  id == ID_MT7988 || \
+					  id == ID_EN7581) ? \
 					 MT7531_MIRROR_PORT_GET(val) : \
 					 MT7530_MIRROR_PORT_GET(val))
 
 #define MT753X_MIRROR_PORT_SET(id, val)	((id == ID_MT7531 || \
-					  id == ID_MT7988) ? \
+					  id == ID_MT7988 || \
+					  id == ID_EN7581) ? \
 					 MT7531_MIRROR_PORT_SET(val) : \
 					 MT7530_MIRROR_PORT_SET(val))
 
@@ -355,6 +361,10 @@ enum mt7530_vlan_port_acc_frm {
 					 MT7531_FORCE_MODE_TX_FC | \
 					 MT7531_FORCE_MODE_EEE100 | \
 					 MT7531_FORCE_MODE_EEE1G)
+#define  MT753X_FORCE_MODE(id)		((id == ID_MT7531 || \
+					  id == ID_MT7988) ? \
+					 MT7531_FORCE_MODE_MASK : \
+					 MT7530_FORCE_MODE)
 #define  PMCR_LINK_SETTINGS_MASK	(PMCR_MAC_TX_EN | PMCR_MAC_RX_EN | \
 					 PMCR_FORCE_EEE1G | \
 					 PMCR_FORCE_EEE100 | \
-- 
cgit v1.3-3-g829e


From ef5e8d34bb9a2f6c13fa35a2209709d345ac1017 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 28 Jun 2024 22:17:54 -0400
Subject: dt-bindings: can: fsl,flexcan: add common 'can-transceiver' for
 fsl,flexcan

Add common 'can-transceiver' children node for fsl,flexcan.

Fix below warning:
arch/arm64/boot/dts/freescale/fsl-ls1028a-rdb.dtb: can@2180000: 'can-transceiver' does not match any of the regexes: 'pinctrl-[0-9]+'
        from schema $id: http://devicetree.org/schemas/net/can/fsl,flexcan.yaml#

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/all/20240629021754.3583641-1-Frank.Li@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
index f197d9b516bb..a4261a201fdb 100644
--- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -80,6 +80,10 @@ properties:
       node then controller is assumed to be little endian. If this property is
       present then controller is assumed to be big endian.
 
+  can-transceiver:
+    $ref: can-transceiver.yaml#
+    unevaluatedProperties: false
+
   fsl,stop-mode:
     description: |
       Register bits of stop mode control.
-- 
cgit v1.3-3-g829e


From c89cca307b20917da739567a255a68a0798ee129 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 1 Aug 2024 17:19:56 -0700
Subject: net: skbuff: sprinkle more __GFP_NOWARN on ingress allocs

build_skb() and frag allocations done with GFP_ATOMIC will
fail in real life, when system is under memory pressure,
and there's nothing we can do about that. So no point
printing warnings.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 83f8cd8aa2d1..de2a044cc665 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -314,8 +314,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
 	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
-	data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
-				       align_mask);
+	data = __page_frag_alloc_align(&nc->page, fragsz,
+				       GFP_ATOMIC | __GFP_NOWARN, align_mask);
 	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 	return data;
 
@@ -330,7 +330,8 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 		struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
 
 		fragsz = SKB_DATA_ALIGN(fragsz);
-		data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC,
+		data = __page_frag_alloc_align(nc, fragsz,
+					       GFP_ATOMIC | __GFP_NOWARN,
 					       align_mask);
 	} else {
 		local_bh_disable();
@@ -349,7 +350,7 @@ static struct sk_buff *napi_skb_cache_get(void)
 	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
 	if (unlikely(!nc->skb_count)) {
 		nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
-						      GFP_ATOMIC,
+						      GFP_ATOMIC | __GFP_NOWARN,
 						      NAPI_SKB_CACHE_BULK,
 						      nc->skb_cache);
 		if (unlikely(!nc->skb_count)) {
@@ -418,7 +419,8 @@ struct sk_buff *slab_build_skb(void *data)
 	struct sk_buff *skb;
 	unsigned int size;
 
-	skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
+	skb = kmem_cache_alloc(net_hotdata.skbuff_cache,
+			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -469,7 +471,8 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct sk_buff *skb;
 
-	skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC);
+	skb = kmem_cache_alloc(net_hotdata.skbuff_cache,
+			       GFP_ATOMIC | __GFP_NOWARN);
 	if (unlikely(!skb))
 		return NULL;
 
-- 
cgit v1.3-3-g829e


From ac4c59390a877e02967b1da9ef6bc565150e9e7e Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Fri, 2 Aug 2024 07:16:09 +0200
Subject: net: phy: vitesse: implement downshift in vsc73xx phys

This commit implements downshift feature in vsc73xx family phys.

By default downshift was enabled with maximum tries.

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/vitesse.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)

diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 897b979ec03c..67ac4a2756ca 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -10,8 +10,10 @@
 #include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/phy.h>
+#include <linux/bitfield.h>
 
 /* Vitesse Extended Page Magic Register(s) */
+#define MII_VSC73XX_EXT_PAGE_1E		0x01
 #define MII_VSC82X4_EXT_PAGE_16E	0x10
 #define MII_VSC82X4_EXT_PAGE_17E	0x11
 #define MII_VSC82X4_EXT_PAGE_18E	0x12
@@ -60,6 +62,15 @@
 /* Vitesse Extended Page Access Register */
 #define MII_VSC82X4_EXT_PAGE_ACCESS	0x1f
 
+/* Vitesse VSC73XX Extended Control Register */
+#define MII_VSC73XX_PHY_CTRL_EXT3		0x14
+
+#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN	BIT(4)
+#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT	GENMASK(3, 2)
+#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_STA	BIT(1)
+#define MII_VSC73XX_DOWNSHIFT_MAX		5
+#define MII_VSC73XX_DOWNSHIFT_INVAL		1
+
 /* Vitesse VSC8601 Extended PHY Control Register 1 */
 #define MII_VSC8601_EPHY_CTL		0x17
 #define MII_VSC8601_EPHY_CTL_RGMII_SKEW	(1 << 8)
@@ -128,6 +139,74 @@ static int vsc73xx_write_page(struct phy_device *phydev, int page)
 	return __phy_write(phydev, VSC73XX_EXT_PAGE_ACCESS, page);
 }
 
+static int vsc73xx_get_downshift(struct phy_device *phydev, u8 *data)
+{
+	int val, enable, cnt;
+
+	val = phy_read_paged(phydev, MII_VSC73XX_EXT_PAGE_1E,
+			     MII_VSC73XX_PHY_CTRL_EXT3);
+	if (val < 0)
+		return val;
+
+	enable = FIELD_GET(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN, val);
+	cnt = FIELD_GET(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT, val) + 2;
+
+	*data = enable ? cnt : DOWNSHIFT_DEV_DISABLE;
+
+	return 0;
+}
+
+static int vsc73xx_set_downshift(struct phy_device *phydev, u8 cnt)
+{
+	u16 mask, val;
+	int ret;
+
+	if (cnt > MII_VSC73XX_DOWNSHIFT_MAX)
+		return -E2BIG;
+	else if (cnt == MII_VSC73XX_DOWNSHIFT_INVAL)
+		return -EINVAL;
+
+	mask = MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN;
+
+	if (!cnt) {
+		val = 0;
+	} else {
+		mask |= MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT;
+		val = MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN |
+		      FIELD_PREP(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT,
+				 cnt - 2);
+	}
+
+	ret = phy_modify_paged(phydev, MII_VSC73XX_EXT_PAGE_1E,
+			       MII_VSC73XX_PHY_CTRL_EXT3, mask, val);
+	if (ret < 0)
+		return ret;
+
+	return genphy_soft_reset(phydev);
+}
+
+static int vsc73xx_get_tunable(struct phy_device *phydev,
+			       struct ethtool_tunable *tuna, void *data)
+{
+	switch (tuna->id) {
+	case ETHTOOL_PHY_DOWNSHIFT:
+		return vsc73xx_get_downshift(phydev, data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int vsc73xx_set_tunable(struct phy_device *phydev,
+			       struct ethtool_tunable *tuna, const void *data)
+{
+	switch (tuna->id) {
+	case ETHTOOL_PHY_DOWNSHIFT:
+		return vsc73xx_set_downshift(phydev, *(const u8 *)data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static void vsc73xx_config_init(struct phy_device *phydev)
 {
 	/* Receiver init */
@@ -137,6 +216,9 @@ static void vsc73xx_config_init(struct phy_device *phydev)
 
 	/* Config LEDs 0x61 */
 	phy_modify(phydev, MII_TPISTATUS, 0xff00, 0x0061);
+
+	/* Enable downshift by default */
+	vsc73xx_set_downshift(phydev, MII_VSC73XX_DOWNSHIFT_MAX);
 }
 
 static int vsc738x_config_init(struct phy_device *phydev)
@@ -447,6 +529,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_aneg    = vsc73xx_config_aneg,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
+	.get_tunable    = vsc73xx_get_tunable,
+	.set_tunable    = vsc73xx_set_tunable,
 }, {
 	.phy_id         = PHY_ID_VSC7388,
 	.name           = "Vitesse VSC7388",
@@ -456,6 +540,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_aneg    = vsc73xx_config_aneg,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
+	.get_tunable    = vsc73xx_get_tunable,
+	.set_tunable    = vsc73xx_set_tunable,
 }, {
 	.phy_id         = PHY_ID_VSC7395,
 	.name           = "Vitesse VSC7395",
@@ -465,6 +551,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_aneg    = vsc73xx_config_aneg,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
+	.get_tunable    = vsc73xx_get_tunable,
+	.set_tunable    = vsc73xx_set_tunable,
 }, {
 	.phy_id         = PHY_ID_VSC7398,
 	.name           = "Vitesse VSC7398",
@@ -474,6 +562,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_aneg    = vsc73xx_config_aneg,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
+	.get_tunable    = vsc73xx_get_tunable,
+	.set_tunable    = vsc73xx_set_tunable,
 }, {
 	.phy_id         = PHY_ID_VSC8662,
 	.name           = "Vitesse VSC8662",
-- 
cgit v1.3-3-g829e


From 10a6545f0bdcbb920c6a8a033fe342111d204915 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 2 Aug 2024 01:07:23 -0700
Subject: net: netconsole: Fix MODULE_AUTHOR format

Update the MODULE_AUTHOR for netconsole, according to the format, as
stated in module.h:

	use "Name <email>" or just "Name"

Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 9c09293b5258..ffedf7648bed 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -38,7 +38,7 @@
 #include <linux/etherdevice.h>
 #include <linux/utsname.h>
 
-MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>");
+MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>");
 MODULE_DESCRIPTION("Console driver for network interfaces");
 MODULE_LICENSE("GPL");
 
-- 
cgit v1.3-3-g829e


From 3eea16ba7c69ecab78bc458795ccd08de6fc4b1c Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Wed, 31 Jul 2024 20:00:25 -0400
Subject: dt-bindings: can: fsl,flexcan: move fsl,imx95-flexcan standalone

The flexcan in iMX95 is not compatible with imx93 because wakeup method is
difference. Make fsl,imx95-flexcan not fallback to fsl,imx93-flexcan.

Reviewed-by: Han Xu <han.xu@nxp.com>
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/all/20240731-flexcan-v4-1-82ece66e5a76@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
index a4261a201fdb..97dd1a7c5ed2 100644
--- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -17,6 +17,7 @@ properties:
   compatible:
     oneOf:
       - enum:
+          - fsl,imx95-flexcan
           - fsl,imx93-flexcan
           - fsl,imx8qm-flexcan
           - fsl,imx8mp-flexcan
@@ -38,9 +39,6 @@ properties:
               - fsl,imx6ul-flexcan
               - fsl,imx6sx-flexcan
           - const: fsl,imx6q-flexcan
-      - items:
-          - const: fsl,imx95-flexcan
-          - const: fsl,imx93-flexcan
       - items:
           - enum:
               - fsl,ls1028ar1-flexcan
-- 
cgit v1.3-3-g829e


From 5b512f42e098df280f0b3f680ac806827a25d1dd Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Wed, 31 Jul 2024 20:00:26 -0400
Subject: can: flexcan: add wakeup support for imx95

iMX95 defines a bit in GPR that sets/unsets the IPG_STOP signal to the
FlexCAN module, controlling its entry into STOP mode. Wakeup should work
even if FlexCAN is in STOP mode.

Due to iMX95 architecture design, the A-Core cannot access GPR; only the
system manager (SM) can configure GPR. To support the wakeup feature,
follow these steps:

- For suspend:
  1) During Linux suspend, when CAN suspends, do nothing for GPR and keep
     CAN-related clocks on.
  2) In ATF, check whether CAN needs to support wakeup; if yes, send a
     request to SM through the SCMI protocol.
  3) In SM, configure the GPR and unset IPG_STOP.
  4) A-Core suspends.

- For wakeup and resume:
  1) A-Core wakeup event arrives.
  2) In SM, deassert IPG_STOP.
  3) Linux resumes.

Add a new fsl_imx95_devtype_data and FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI to
reflect this.

Reviewed-by: Han Xu <han.xu@nxp.com>
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/all/20240731-flexcan-v4-2-82ece66e5a76@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 50 +++++++++++++++++++++++++++++-----
 drivers/net/can/flexcan/flexcan.h      |  2 ++
 2 files changed, 45 insertions(+), 7 deletions(-)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index 8ea7f2795551..d11411029330 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -354,6 +354,14 @@ static struct flexcan_devtype_data fsl_imx93_devtype_data = {
 		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR,
 };
 
+static const struct flexcan_devtype_data fsl_imx95_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_RX_MAILBOX |
+		FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_FD |
+		FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR | FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI,
+};
+
 static const struct flexcan_devtype_data fsl_vf610_devtype_data = {
 	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
 		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_RX_MAILBOX |
@@ -544,6 +552,13 @@ static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv)
 	} else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR) {
 		regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr,
 				   1 << priv->stm.req_bit, 1 << priv->stm.req_bit);
+	} else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI) {
+		/* For the SCMI mode, driver do nothing, ATF will send request to
+		 * SM(system manager, M33 core) through SCMI protocol after linux
+		 * suspend. Once SM get this request, it will send IPG_STOP signal
+		 * to Flex_CAN, let CAN in STOP mode.
+		 */
+		return 0;
 	}
 
 	return flexcan_low_power_enter_ack(priv);
@@ -555,7 +570,11 @@ static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv)
 	u32 reg_mcr;
 	int ret;
 
-	/* remove stop request */
+	/* Remove stop request, for FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI,
+	 * do nothing here, because ATF already send request to SM before
+	 * linux resume. Once SM get this request, it will deassert the
+	 * IPG_STOP signal to Flex_CAN.
+	 */
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCFW) {
 		ret = flexcan_stop_mode_enable_scfw(priv, false);
 		if (ret < 0)
@@ -1983,6 +2002,9 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev)
 		ret = flexcan_setup_stop_mode_scfw(pdev);
 	else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR)
 		ret = flexcan_setup_stop_mode_gpr(pdev);
+	else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)
+		/* ATF will handle all STOP_IPG related work */
+		ret = 0;
 	else
 		/* return 0 directly if doesn't support stop mode feature */
 		return 0;
@@ -2009,6 +2031,7 @@ static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,imx8qm-flexcan", .data = &fsl_imx8qm_devtype_data, },
 	{ .compatible = "fsl,imx8mp-flexcan", .data = &fsl_imx8mp_devtype_data, },
 	{ .compatible = "fsl,imx93-flexcan", .data = &fsl_imx93_devtype_data, },
+	{ .compatible = "fsl,imx95-flexcan", .data = &fsl_imx95_devtype_data, },
 	{ .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, },
 	{ .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, },
 	{ .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, },
@@ -2309,9 +2332,19 @@ static int __maybe_unused flexcan_noirq_suspend(struct device *device)
 		if (device_may_wakeup(device))
 			flexcan_enable_wakeup_irq(priv, true);
 
-		err = pm_runtime_force_suspend(device);
-		if (err)
-			return err;
+		/* For FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, it need ATF to send
+		 * to SM through SCMI protocol, SM will assert the IPG_STOP
+		 * signal. But all this works need the CAN clocks keep on.
+		 * After the CAN module get the IPG_STOP mode, and switch to
+		 * STOP mode, whether still keep the CAN clocks on or gate them
+		 * off depend on the Hardware design.
+		 */
+		if (!(device_may_wakeup(device) &&
+		      priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)) {
+			err = pm_runtime_force_suspend(device);
+			if (err)
+				return err;
+		}
 	}
 
 	return 0;
@@ -2325,9 +2358,12 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device)
 	if (netif_running(dev)) {
 		int err;
 
-		err = pm_runtime_force_resume(device);
-		if (err)
-			return err;
+		if (!(device_may_wakeup(device) &&
+		      priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)) {
+			err = pm_runtime_force_resume(device);
+			if (err)
+				return err;
+		}
 
 		if (device_may_wakeup(device))
 			flexcan_enable_wakeup_irq(priv, false);
diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h
index 025c3417031f..4933d8c7439e 100644
--- a/drivers/net/can/flexcan/flexcan.h
+++ b/drivers/net/can/flexcan/flexcan.h
@@ -68,6 +68,8 @@
 #define FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR BIT(15)
 /* Device supports RX via FIFO */
 #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16)
+/* Setup stop mode with ATF SCMI protocol to support wakeup */
+#define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17)
 
 struct flexcan_devtype_data {
 	u32 quirks;		/* quirks needed for different IP cores */
-- 
cgit v1.3-3-g829e


From 3e6cb3f2fb4344db54b35601effc1ff46ebd9698 Mon Sep 17 00:00:00 2001
From: Stefan Mätje <stefan.maetje@esd.eu>
Date: Wed, 17 Jul 2024 23:44:08 +0200
Subject: can: esd_402_pci: Rename esdACC CTRL register macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename macros to use for esdACC CTRL register access to match the
internal documentation and to make the macro prefix consistent.

- ACC_CORE_OF_CTRL_MODE -> ACC_CORE_OF_CTRL
  Makes the name match the documentation.
- ACC_REG_CONTROL_MASK_MODE_ -> ACC_REG_CTRL_MASK_
  ACC_REG_CONTROL_MASK_ -> ACC_REG_CTRL_MASK_
  Makes the prefix consistent for macros describing masks in the same
  register (CTRL).

Signed-off-by: Stefan Mätje <stefan.maetje@esd.eu>
Link: https://lore.kernel.org/all/20240717214409.3934333-2-stefan.maetje@esd.eu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/esd/esdacc.c | 46 ++++++++++++++++++++++----------------------
 drivers/net/can/esd/esdacc.h | 37 ++++++++++++++++++-----------------
 2 files changed, 42 insertions(+), 41 deletions(-)

diff --git a/drivers/net/can/esd/esdacc.c b/drivers/net/can/esd/esdacc.c
index 121cbbf81458..ef33d2ccd220 100644
--- a/drivers/net/can/esd/esdacc.c
+++ b/drivers/net/can/esd/esdacc.c
@@ -43,8 +43,8 @@
 
 static void acc_resetmode_enter(struct acc_core *core)
 {
-	acc_set_bits(core, ACC_CORE_OF_CTRL_MODE,
-		     ACC_REG_CONTROL_MASK_MODE_RESETMODE);
+	acc_set_bits(core, ACC_CORE_OF_CTRL,
+		     ACC_REG_CTRL_MASK_RESETMODE);
 
 	/* Read back reset mode bit to flush PCI write posting */
 	acc_resetmode_entered(core);
@@ -52,8 +52,8 @@ static void acc_resetmode_enter(struct acc_core *core)
 
 static void acc_resetmode_leave(struct acc_core *core)
 {
-	acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE,
-		       ACC_REG_CONTROL_MASK_MODE_RESETMODE);
+	acc_clear_bits(core, ACC_CORE_OF_CTRL,
+		       ACC_REG_CTRL_MASK_RESETMODE);
 
 	/* Read back reset mode bit to flush PCI write posting */
 	acc_resetmode_entered(core);
@@ -172,7 +172,7 @@ int acc_open(struct net_device *netdev)
 	struct acc_net_priv *priv = netdev_priv(netdev);
 	struct acc_core *core = priv->core;
 	u32 tx_fifo_status;
-	u32 ctrl_mode;
+	u32 ctrl;
 	int err;
 
 	/* Retry to enter RESET mode if out of sync. */
@@ -187,19 +187,19 @@ int acc_open(struct net_device *netdev)
 	if (err)
 		return err;
 
-	ctrl_mode = ACC_REG_CONTROL_MASK_IE_RXTX |
-			ACC_REG_CONTROL_MASK_IE_TXERROR |
-			ACC_REG_CONTROL_MASK_IE_ERRWARN |
-			ACC_REG_CONTROL_MASK_IE_OVERRUN |
-			ACC_REG_CONTROL_MASK_IE_ERRPASS;
+	ctrl = ACC_REG_CTRL_MASK_IE_RXTX |
+		ACC_REG_CTRL_MASK_IE_TXERROR |
+		ACC_REG_CTRL_MASK_IE_ERRWARN |
+		ACC_REG_CTRL_MASK_IE_OVERRUN |
+		ACC_REG_CTRL_MASK_IE_ERRPASS;
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING)
-		ctrl_mode |= ACC_REG_CONTROL_MASK_IE_BUSERR;
+		ctrl |= ACC_REG_CTRL_MASK_IE_BUSERR;
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
-		ctrl_mode |= ACC_REG_CONTROL_MASK_MODE_LOM;
+		ctrl |= ACC_REG_CTRL_MASK_LOM;
 
-	acc_set_bits(core, ACC_CORE_OF_CTRL_MODE, ctrl_mode);
+	acc_set_bits(core, ACC_CORE_OF_CTRL, ctrl);
 
 	acc_resetmode_leave(core);
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
@@ -218,13 +218,13 @@ int acc_close(struct net_device *netdev)
 	struct acc_net_priv *priv = netdev_priv(netdev);
 	struct acc_core *core = priv->core;
 
-	acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE,
-		       ACC_REG_CONTROL_MASK_IE_RXTX |
-		       ACC_REG_CONTROL_MASK_IE_TXERROR |
-		       ACC_REG_CONTROL_MASK_IE_ERRWARN |
-		       ACC_REG_CONTROL_MASK_IE_OVERRUN |
-		       ACC_REG_CONTROL_MASK_IE_ERRPASS |
-		       ACC_REG_CONTROL_MASK_IE_BUSERR);
+	acc_clear_bits(core, ACC_CORE_OF_CTRL,
+		       ACC_REG_CTRL_MASK_IE_RXTX |
+		       ACC_REG_CTRL_MASK_IE_TXERROR |
+		       ACC_REG_CTRL_MASK_IE_ERRWARN |
+		       ACC_REG_CTRL_MASK_IE_OVERRUN |
+		       ACC_REG_CTRL_MASK_IE_ERRPASS |
+		       ACC_REG_CTRL_MASK_IE_BUSERR);
 
 	netif_stop_queue(netdev);
 	acc_resetmode_enter(core);
@@ -233,9 +233,9 @@ int acc_close(struct net_device *netdev)
 	/* Mark pending TX requests to be aborted after controller restart. */
 	acc_write32(core, ACC_CORE_OF_TX_ABORT_MASK, 0xffff);
 
-	/* ACC_REG_CONTROL_MASK_MODE_LOM is only accessible in RESET mode */
-	acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE,
-		       ACC_REG_CONTROL_MASK_MODE_LOM);
+	/* ACC_REG_CTRL_MASK_LOM is only accessible in RESET mode */
+	acc_clear_bits(core, ACC_CORE_OF_CTRL,
+		       ACC_REG_CTRL_MASK_LOM);
 
 	close_candev(netdev);
 	return 0;
diff --git a/drivers/net/can/esd/esdacc.h b/drivers/net/can/esd/esdacc.h
index a70488b25d39..d13dfa60703a 100644
--- a/drivers/net/can/esd/esdacc.h
+++ b/drivers/net/can/esd/esdacc.h
@@ -50,7 +50,7 @@
 #define ACC_OV_REG_MODE_MASK_FPGA_RESET BIT(31)
 
 /* esdACC CAN Core Module */
-#define ACC_CORE_OF_CTRL_MODE 0x0000
+#define ACC_CORE_OF_CTRL 0x0000
 #define ACC_CORE_OF_STATUS_IRQ 0x0008
 #define ACC_CORE_OF_BRP	0x000c
 #define ACC_CORE_OF_BTR	0x0010
@@ -66,21 +66,22 @@
 #define ACC_CORE_OF_TXFIFO_DATA_0 0x00c8
 #define ACC_CORE_OF_TXFIFO_DATA_1 0x00cc
 
-#define ACC_REG_CONTROL_MASK_MODE_RESETMODE BIT(0)
-#define ACC_REG_CONTROL_MASK_MODE_LOM BIT(1)
-#define ACC_REG_CONTROL_MASK_MODE_STM BIT(2)
-#define ACC_REG_CONTROL_MASK_MODE_TRANSEN BIT(5)
-#define ACC_REG_CONTROL_MASK_MODE_TS BIT(6)
-#define ACC_REG_CONTROL_MASK_MODE_SCHEDULE BIT(7)
-
-#define ACC_REG_CONTROL_MASK_IE_RXTX BIT(8)
-#define ACC_REG_CONTROL_MASK_IE_TXERROR BIT(9)
-#define ACC_REG_CONTROL_MASK_IE_ERRWARN BIT(10)
-#define ACC_REG_CONTROL_MASK_IE_OVERRUN BIT(11)
-#define ACC_REG_CONTROL_MASK_IE_TSI BIT(12)
-#define ACC_REG_CONTROL_MASK_IE_ERRPASS BIT(13)
-#define ACC_REG_CONTROL_MASK_IE_ALI BIT(14)
-#define ACC_REG_CONTROL_MASK_IE_BUSERR BIT(15)
+/* CTRL register layout */
+#define ACC_REG_CTRL_MASK_RESETMODE BIT(0)
+#define ACC_REG_CTRL_MASK_LOM BIT(1)
+#define ACC_REG_CTRL_MASK_STM BIT(2)
+#define ACC_REG_CTRL_MASK_TRANSEN BIT(5)
+#define ACC_REG_CTRL_MASK_TS BIT(6)
+#define ACC_REG_CTRL_MASK_SCHEDULE BIT(7)
+
+#define ACC_REG_CTRL_MASK_IE_RXTX BIT(8)
+#define ACC_REG_CTRL_MASK_IE_TXERROR BIT(9)
+#define ACC_REG_CTRL_MASK_IE_ERRWARN BIT(10)
+#define ACC_REG_CTRL_MASK_IE_OVERRUN BIT(11)
+#define ACC_REG_CTRL_MASK_IE_TSI BIT(12)
+#define ACC_REG_CTRL_MASK_IE_ERRPASS BIT(13)
+#define ACC_REG_CTRL_MASK_IE_ALI BIT(14)
+#define ACC_REG_CTRL_MASK_IE_BUSERR BIT(15)
 
 /* BRP and BTR register layout for CAN-Classic version */
 #define ACC_REG_BRP_CL_MASK_BRP GENMASK(8, 0)
@@ -300,9 +301,9 @@ static inline void acc_clear_bits(struct acc_core *core,
 
 static inline int acc_resetmode_entered(struct acc_core *core)
 {
-	u32 ctrl = acc_read32(core, ACC_CORE_OF_CTRL_MODE);
+	u32 ctrl = acc_read32(core, ACC_CORE_OF_CTRL);
 
-	return (ctrl & ACC_REG_CONTROL_MASK_MODE_RESETMODE) != 0;
+	return (ctrl & ACC_REG_CTRL_MASK_RESETMODE) != 0;
 }
 
 static inline u32 acc_ov_read32(struct acc_ov *ov, unsigned short offs)
-- 
cgit v1.3-3-g829e


From c20ff3e0d9ebdc9f7fd84b8c59c2cba9442324c3 Mon Sep 17 00:00:00 2001
From: Stefan Mätje <stefan.maetje@esd.eu>
Date: Wed, 17 Jul 2024 23:44:09 +0200
Subject: can: esd_402_pci: Add support for one-shot mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds support for one-shot mode. In this mode there happens no
automatic retransmission in the case of an arbitration lost error or on
any bus error.

Signed-off-by: Stefan Mätje <stefan.maetje@esd.eu>
Link: https://lore.kernel.org/all/20240717214409.3934333-3-stefan.maetje@esd.eu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/esd/esd_402_pci-core.c | 5 +++--
 drivers/net/can/esd/esdacc.c           | 9 +++++++--
 drivers/net/can/esd/esdacc.h           | 1 +
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/esd/esd_402_pci-core.c b/drivers/net/can/esd/esd_402_pci-core.c
index b7cdcffd0e45..5d6d2828cd04 100644
--- a/drivers/net/can/esd/esd_402_pci-core.c
+++ b/drivers/net/can/esd/esd_402_pci-core.c
@@ -369,12 +369,13 @@ static int pci402_init_cores(struct pci_dev *pdev)
 		SET_NETDEV_DEV(netdev, &pdev->dev);
 
 		priv = netdev_priv(netdev);
+		priv->can.clock.freq = card->ov.core_frequency;
 		priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 			CAN_CTRLMODE_LISTENONLY |
 			CAN_CTRLMODE_BERR_REPORTING |
 			CAN_CTRLMODE_CC_LEN8_DLC;
-
-		priv->can.clock.freq = card->ov.core_frequency;
+		if (card->ov.features & ACC_OV_REG_FEAT_MASK_DAR)
+			priv->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
 		if (card->ov.features & ACC_OV_REG_FEAT_MASK_CANFD)
 			priv->can.bittiming_const = &pci402_bittiming_const_canfd;
 		else
diff --git a/drivers/net/can/esd/esdacc.c b/drivers/net/can/esd/esdacc.c
index ef33d2ccd220..c80032bc1a52 100644
--- a/drivers/net/can/esd/esdacc.c
+++ b/drivers/net/can/esd/esdacc.c
@@ -17,6 +17,9 @@
 /* esdACC DLC register layout */
 #define ACC_DLC_DLC_MASK GENMASK(3, 0)
 #define ACC_DLC_RTR_FLAG BIT(4)
+#define ACC_DLC_SSTX_FLAG BIT(24)	/* Single Shot TX */
+
+/* esdACC DLC in struct acc_bmmsg_rxtxdone::acc_dlc.len only! */
 #define ACC_DLC_TXD_FLAG BIT(5)
 
 /* ecc value of esdACC equals SJA1000's ECC register */
@@ -59,7 +62,7 @@ static void acc_resetmode_leave(struct acc_core *core)
 	acc_resetmode_entered(core);
 }
 
-static void acc_txq_put(struct acc_core *core, u32 acc_id, u8 acc_dlc,
+static void acc_txq_put(struct acc_core *core, u32 acc_id, u32 acc_dlc,
 			const void *data)
 {
 	acc_write32_noswap(core, ACC_CORE_OF_TXFIFO_DATA_1,
@@ -249,7 +252,7 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	u8 tx_fifo_head = core->tx_fifo_head;
 	int fifo_usage;
 	u32 acc_id;
-	u8 acc_dlc;
+	u32 acc_dlc;
 
 	if (can_dropped_invalid_skb(netdev, skb))
 		return NETDEV_TX_OK;
@@ -274,6 +277,8 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 	acc_dlc = can_get_cc_dlc(cf, priv->can.ctrlmode);
 	if (cf->can_id & CAN_RTR_FLAG)
 		acc_dlc |= ACC_DLC_RTR_FLAG;
+	if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+		acc_dlc |= ACC_DLC_SSTX_FLAG;
 
 	if (cf->can_id & CAN_EFF_FLAG) {
 		acc_id = cf->can_id & CAN_EFF_MASK;
diff --git a/drivers/net/can/esd/esdacc.h b/drivers/net/can/esd/esdacc.h
index d13dfa60703a..6b7ebd8c91b2 100644
--- a/drivers/net/can/esd/esdacc.h
+++ b/drivers/net/can/esd/esdacc.h
@@ -35,6 +35,7 @@
  */
 #define ACC_OV_REG_FEAT_MASK_CANFD BIT(27 - 16)
 #define ACC_OV_REG_FEAT_MASK_NEW_PSC BIT(28 - 16)
+#define ACC_OV_REG_FEAT_MASK_DAR BIT(30 - 16)
 
 #define ACC_OV_REG_MODE_MASK_ENDIAN_LITTLE BIT(0)
 #define ACC_OV_REG_MODE_MASK_BM_ENABLE BIT(1)
-- 
cgit v1.3-3-g829e


From 7d102d0e4c6378a24ae90fc99618a44ea52e2766 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:22 +0200
Subject: can: kvaser_usb: Add helper functions to convert device timestamp
 into ktime

Add helper function kvaser_usb_ticks_to_ktime() that converts from
device ticks to ktime.
And kvaser_usb_timestamp{48,64}_to_ktime() that converts from device
48-bit or 64-bit timestamp, to ktime.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-2-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb.h       | 24 +++++++++++++++++++++++
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 10 ++++------
 2 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index ff10b3790d84..4256a0caae20 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -22,6 +22,8 @@
  */
 
 #include <linux/completion.h>
+#include <linux/ktime.h>
+#include <linux/math64.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/usb.h>
@@ -216,4 +218,26 @@ int kvaser_usb_can_rx_over_error(struct net_device *netdev);
 
 extern const struct can_bittiming_const kvaser_usb_flexc_bittiming_const;
 
+static inline ktime_t kvaser_usb_ticks_to_ktime(const struct kvaser_usb_dev_cfg *cfg,
+						u64 ticks)
+{
+	return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq));
+}
+
+static inline ktime_t kvaser_usb_timestamp48_to_ktime(const struct kvaser_usb_dev_cfg *cfg,
+						      const __le16 *timestamp)
+{
+	u64 ticks = le16_to_cpu(timestamp[0]) |
+		    (u64)(le16_to_cpu(timestamp[1])) << 16 |
+		    (u64)(le16_to_cpu(timestamp[2])) << 32;
+
+	return kvaser_usb_ticks_to_ktime(cfg, ticks);
+}
+
+static inline ktime_t kvaser_usb_timestamp64_to_ktime(const struct kvaser_usb_dev_cfg *cfg,
+						      __le64 timestamp)
+{
+	return kvaser_usb_ticks_to_ktime(cfg, le64_to_cpu(timestamp));
+}
+
 #endif /* KVASER_USB_H */
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index c7ba768dfe17..ad1c6101a0cd 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -526,19 +526,17 @@ static ktime_t
 kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg,
 				   const struct kvaser_cmd *cmd)
 {
-	u64 ticks;
+	ktime_t hwtstamp = 0;
 
 	if (cmd->header.cmd_no == CMD_EXTENDED) {
 		struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd;
 
-		ticks = le64_to_cpu(cmd_ext->rx_can.timestamp);
+		hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->rx_can.timestamp);
 	} else {
-		ticks = le16_to_cpu(cmd->rx_can.timestamp[0]);
-		ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[1])) << 16;
-		ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[2])) << 32;
+		hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->rx_can.timestamp);
 	}
 
-	return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq));
+	return hwtstamp;
 }
 
 static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev,
-- 
cgit v1.3-3-g829e


From 7cb0450c1da579f1d6372ed38da9a03a6312db47 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:23 +0200
Subject: can: kvaser_usb: hydra: kvaser_usb_hydra_ktime_from_rx_cmd: Drop
 {rx_} in function name

Rename function, since this function will be used for more than just the
rx commands.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-3-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index ad1c6101a0cd..84f1f1f9c107 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -522,9 +522,8 @@ kvaser_usb_hydra_net_priv_from_cmd(const struct kvaser_usb *dev,
 	return priv;
 }
 
-static ktime_t
-kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg,
-				   const struct kvaser_cmd *cmd)
+static ktime_t kvaser_usb_hydra_ktime_from_cmd(const struct kvaser_usb_dev_cfg *cfg,
+					       const struct kvaser_cmd *cmd)
 {
 	ktime_t hwtstamp = 0;
 
@@ -1232,7 +1231,7 @@ static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev,
 	stats = &priv->netdev->stats;
 
 	flags = cmd->rx_can.flags;
-	hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, cmd);
+	hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, cmd);
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) {
 		kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data,
@@ -1300,7 +1299,7 @@ static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev,
 		KVASER_USB_KCAN_DATA_DLC_SHIFT;
 
 	flags = le32_to_cpu(cmd->rx_can.flags);
-	hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, std_cmd);
+	hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, std_cmd);
 
 	if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) {
 		kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data,
-- 
cgit v1.3-3-g829e


From 0512cc691a3abe51aa3daf72ce161f3ab1d3bedc Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:24 +0200
Subject: can: kvaser_usb: hydra: Add struct for Tx ACK commands

Add, struct kvaser_cmd_tx_ack, for standard Tx ACK commands.

Expand kvaser_usb_hydra_ktime_from_cmd() to extract timestamps from both
standard and extended Tx ACK commands. Unsupported commands are silently
ignored, and 0 is returned.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-4-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 84f1f1f9c107..f102f9de7d16 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -261,6 +261,15 @@ struct kvaser_cmd_tx_can {
 	u8 reserved[11];
 } __packed;
 
+struct kvaser_cmd_tx_ack {
+	__le32 id;
+	u8 data[8];
+	u8 dlc;
+	u8 flags;
+	__le16 timestamp[3];
+	u8 reserved0[8];
+} __packed;
+
 struct kvaser_cmd_header {
 	u8 cmd_no;
 	/* The destination HE address is stored in 0..5 of he_addr.
@@ -297,6 +306,7 @@ struct kvaser_cmd {
 
 		struct kvaser_cmd_rx_can rx_can;
 		struct kvaser_cmd_tx_can tx_can;
+		struct kvaser_cmd_tx_ack tx_ack;
 	} __packed;
 } __packed;
 
@@ -530,9 +540,14 @@ static ktime_t kvaser_usb_hydra_ktime_from_cmd(const struct kvaser_usb_dev_cfg *
 	if (cmd->header.cmd_no == CMD_EXTENDED) {
 		struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd;
 
-		hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->rx_can.timestamp);
-	} else {
+		if (cmd_ext->cmd_no_ext == CMD_RX_MESSAGE_FD)
+			hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->rx_can.timestamp);
+		else if (cmd_ext->cmd_no_ext == CMD_TX_ACKNOWLEDGE_FD)
+			hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->tx_ack.timestamp);
+	} else if (cmd->header.cmd_no == CMD_RX_MESSAGE) {
 		hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->rx_can.timestamp);
+	} else if (cmd->header.cmd_no == CMD_TX_ACKNOWLEDGE) {
+		hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->tx_ack.timestamp);
 	}
 
 	return hwtstamp;
-- 
cgit v1.3-3-g829e


From d920dd289ee5967c14026357635cb771cdfef11e Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:25 +0200
Subject: can: kvaser_usb: hydra: Set hardware timestamp on transmitted packets

Set hardware timestamp on transmitted packets.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-5-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index f102f9de7d16..3764b263add3 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -10,7 +10,6 @@
  *  - Transition from CAN_STATE_ERROR_WARNING to CAN_STATE_ERROR_ACTIVE is only
  *    reported after a call to do_get_berr_counter(), since firmware does not
  *    distinguish between ERROR_WARNING and ERROR_ACTIVE.
- *  - Hardware timestamps are not set for CAN Tx frames.
  */
 
 #include <linux/completion.h>
@@ -1187,6 +1186,7 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev,
 	bool one_shot_fail = false;
 	bool is_err_frame = false;
 	u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd);
+	struct sk_buff *skb;
 
 	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
 	if (!priv)
@@ -1213,6 +1213,9 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev,
 
 	spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags);
 
+	skb = priv->can.echo_skb[context->echo_index];
+	if (skb)
+		skb_hwtstamps(skb)->hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, cmd);
 	len = can_get_echo_skb(priv->netdev, context->echo_index, NULL);
 	context->echo_index = dev->max_tx_urbs;
 	--priv->active_tx_contexts;
-- 
cgit v1.3-3-g829e


From 8e7895942ea5fa5add3a2ceafe6e1e9284184806 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:26 +0200
Subject: can: kvaser_usb: leaf: Add struct for Tx ACK commands

Add, struct leaf_cmd_tx_acknowledge, for Tx ACK commands received from leaf
devices (M32C and leafimx28).

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-6-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 23bd7574b1c7..70511e151a3b 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -235,6 +235,13 @@ struct kvaser_cmd_tx_acknowledge_header {
 	u8 tid;
 } __packed;
 
+struct leaf_cmd_tx_acknowledge {
+	u8 channel;
+	u8 tid;
+	__le16 time[3];
+	u8 padding[2];
+} __packed;
+
 struct leaf_cmd_can_error_event {
 	u8 tid;
 	u8 flags;
@@ -347,6 +354,7 @@ struct kvaser_cmd {
 			struct leaf_cmd_error_event error_event;
 			struct kvaser_cmd_cap_req cap_req;
 			struct kvaser_cmd_cap_res cap_res;
+			struct leaf_cmd_tx_acknowledge tx_ack;
 		} __packed leaf;
 
 		union {
@@ -370,7 +378,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = {
 	[CMD_START_CHIP_REPLY]		= kvaser_fsize(u.simple),
 	[CMD_STOP_CHIP_REPLY]		= kvaser_fsize(u.simple),
 	[CMD_GET_CARD_INFO_REPLY]	= kvaser_fsize(u.cardinfo),
-	[CMD_TX_ACKNOWLEDGE]		= kvaser_fsize(u.tx_acknowledge_header),
+	[CMD_TX_ACKNOWLEDGE]		= kvaser_fsize(u.leaf.tx_ack),
 	[CMD_GET_SOFTWARE_INFO_REPLY]	= kvaser_fsize(u.leaf.softinfo),
 	[CMD_RX_STD_MESSAGE]		= kvaser_fsize(u.leaf.rx_can),
 	[CMD_RX_EXT_MESSAGE]		= kvaser_fsize(u.leaf.rx_can),
-- 
cgit v1.3-3-g829e


From dcc8c203318a471cd5cb4e1ccdca56a766fa1a9d Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:27 +0200
Subject: can: kvaser_usb: leaf: Assign correct timestamp_freq for
 kvaser_usb_leaf_imx_dev_cfg_{16,24,32}mhz

Assign correct timestamp_freq to kvaser_usb_leaf_imx_dev_cfg_{16,24,32}mhz.
Since the driver didn't utilize the value, this didn't cause any problems.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-7-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 70511e151a3b..00fe7410e36d 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -483,7 +483,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_16mhz = {
 	.clock = {
 		.freq = 16 * MEGA /* Hz */,
 	},
-	.timestamp_freq = 1,
+	.timestamp_freq = 16,
 	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
@@ -491,7 +491,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_24mhz = {
 	.clock = {
 		.freq = 24 * MEGA /* Hz */,
 	},
-	.timestamp_freq = 1,
+	.timestamp_freq = 24,
 	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
@@ -499,7 +499,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_32mhz = {
 	.clock = {
 		.freq = 32 * MEGA /* Hz */,
 	},
-	.timestamp_freq = 1,
+	.timestamp_freq = 32,
 	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
-- 
cgit v1.3-3-g829e


From 9e1cd0d27276ff221368c0e72e3038e7df98d9b9 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:28 +0200
Subject: can: kvaser_usb: leaf: Replace kvaser_usb_leaf_m32c_dev_cfg with
 kvaser_usb_leaf_m32c_dev_cfg_{16,24,32}mhz

Add new struct kvaser_usb_dev_cfg constants,
kvaser_usb_leaf_m32c_dev_cfg_{16,24,32}mhz,
for M32C based leaf devices.

Note that the bittiming parameters are always calculated for 16MHz clock,
while the timestamps are in the actual clock frequency of the device.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-8-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 33 +++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 00fe7410e36d..3245471e906b 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -471,11 +471,27 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_usbcan_dev_cfg = {
 	.bittiming_const = &kvaser_usb_leaf_m16c_bittiming_const,
 };
 
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg = {
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_16mhz = {
 	.clock = {
 		.freq = 16 * MEGA /* Hz */,
 	},
-	.timestamp_freq = 1,
+	.timestamp_freq = 16,
+	.bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_24mhz = {
+	.clock = {
+		.freq = 16 * MEGA /* Hz */,
+	},
+	.timestamp_freq = 24,
+	.bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_32mhz = {
+	.clock = {
+		.freq = 16 * MEGA /* Hz */,
+	},
+	.timestamp_freq = 32,
 	.bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const,
 };
 
@@ -686,8 +702,19 @@ static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev,
 	if (dev->driver_info->quirks & KVASER_USB_QUIRK_IGNORE_CLK_FREQ) {
 		/* Firmware expects bittiming parameters calculated for 16MHz
 		 * clock, regardless of the actual clock
+		 * Though, the reported freq is used for timestamps
 		 */
-		dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg;
+		switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) {
+		case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK:
+			dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_16mhz;
+			break;
+		case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK:
+			dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_24mhz;
+			break;
+		case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK:
+			dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_32mhz;
+			break;
+		}
 	} else {
 		switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) {
 		case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK:
-- 
cgit v1.3-3-g829e


From 7f3823759751654ff2a59afd3e7c747b71bcb98f Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:29 +0200
Subject: can: kvaser_usb: leaf: kvaser_usb_leaf_tx_acknowledge: Rename local
 variable

Rename local variable skb to err_skb.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-9-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 3245471e906b..caef1f26a95c 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -936,14 +936,14 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
 
 	/* Sometimes the state change doesn't come after a bus-off event */
 	if (priv->can.restart_ms && priv->can.state == CAN_STATE_BUS_OFF) {
-		struct sk_buff *skb;
+		struct sk_buff *err_skb;
 		struct can_frame *cf;
 
-		skb = alloc_can_err_skb(priv->netdev, &cf);
-		if (skb) {
+		err_skb = alloc_can_err_skb(priv->netdev, &cf);
+		if (err_skb) {
 			cf->can_id |= CAN_ERR_RESTARTED;
 
-			netif_rx(skb);
+			netif_rx(err_skb);
 		} else {
 			netdev_err(priv->netdev,
 				   "No memory left for err_skb\n");
-- 
cgit v1.3-3-g829e


From 8a52e5a0361f227fe9b8ee7277222751326e1e2d Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:30 +0200
Subject: can: kvaser_usb: leaf: Add hardware timestamp support to leaf based
 devices

Add hardware timestamp support to leaf based devices (M32C and leafimx).

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-10-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 11 +++++++----
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 15 +++++++++++++++
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index daa34b532aa8..b5d762d38d5d 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -106,14 +106,16 @@ static const struct kvaser_usb_driver_info kvaser_usb_driver_info_usbcan = {
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf = {
-	.quirks = KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
+	.quirks = KVASER_USB_QUIRK_IGNORE_CLK_FREQ |
+		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err = {
 	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
-		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
+		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ |
+		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
@@ -121,13 +123,14 @@ static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err = {
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err_listen = {
 	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
 		  KVASER_USB_QUIRK_HAS_SILENT_MODE |
-		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
+		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ |
+		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leafimx = {
-	.quirks = 0,
+	.quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index caef1f26a95c..5839333eb5ae 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -915,6 +915,8 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
 	struct kvaser_usb_net_priv *priv;
 	unsigned long flags;
 	u8 channel, tid;
+	struct sk_buff *skb;
+	ktime_t hwtstamp = 0;
 
 	channel = cmd->u.tx_acknowledge_header.channel;
 	tid = cmd->u.tx_acknowledge_header.tid;
@@ -954,9 +956,19 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
 
 		priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	}
+	switch (dev->driver_info->family) {
+	case KVASER_LEAF:
+		hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.tx_ack.time);
+		break;
+	case KVASER_USBCAN:
+		break;
+	}
 
 	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
 
+	skb = priv->can.echo_skb[context->echo_index];
+	if (skb)
+		skb_hwtstamps(skb)->hwtstamp = hwtstamp;
 	stats->tx_packets++;
 	stats->tx_bytes += can_get_echo_skb(priv->netdev,
 					    context->echo_index, NULL);
@@ -1334,6 +1346,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 	struct net_device_stats *stats;
 	u8 channel = cmd->u.rx_can_header.channel;
 	const u8 *rx_data = NULL;	/* GCC */
+	ktime_t hwtstamp = 0;
 
 	if (channel >= dev->nchannels) {
 		dev_err(&dev->intf->dev,
@@ -1364,6 +1377,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 	switch (dev->driver_info->family) {
 	case KVASER_LEAF:
 		rx_data = cmd->u.leaf.rx_can.data;
+		hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.rx_can.time);
 		break;
 	case KVASER_USBCAN:
 		rx_data = cmd->u.usbcan.rx_can.data;
@@ -1410,6 +1424,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 			memcpy(cf->data, &rx_data[6], cf->len);
 	}
 
+	skb_hwtstamps(skb)->hwtstamp = hwtstamp;
 	stats->rx_packets++;
 	if (!(cf->can_id & CAN_RTR_FLAG))
 		stats->rx_bytes += cf->len;
-- 
cgit v1.3-3-g829e


From a7cfb2200d8592f7d9fa54baf9181703a35ac0fa Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:31 +0200
Subject: can: kvaser_usb: leaf: Add structs for Tx ACK and clock overflow
 commands

For usbcan devices (M16C), add struct usbcan_cmd_tx_acknowledge for Tx ACK
commands and struct usbcan_cmd_clk_overflow_event for clock overflow event
commands.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-11-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 5839333eb5ae..2c0313c8f63e 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -242,6 +242,13 @@ struct leaf_cmd_tx_acknowledge {
 	u8 padding[2];
 } __packed;
 
+struct usbcan_cmd_tx_acknowledge {
+	u8 channel;
+	u8 tid;
+	__le16 time;
+	u8 padding[2];
+} __packed;
+
 struct leaf_cmd_can_error_event {
 	u8 tid;
 	u8 flags;
@@ -288,6 +295,12 @@ struct usbcan_cmd_error_event {
 	__le16 padding;
 } __packed;
 
+struct usbcan_cmd_clk_overflow_event {
+	u8 tid;
+	u8 padding;
+	__le32 time;
+} __packed;
+
 struct kvaser_cmd_ctrl_mode {
 	u8 tid;
 	u8 channel;
@@ -363,6 +376,8 @@ struct kvaser_cmd {
 			struct usbcan_cmd_chip_state_event chip_state_event;
 			struct usbcan_cmd_can_error_event can_error_event;
 			struct usbcan_cmd_error_event error_event;
+			struct usbcan_cmd_tx_acknowledge tx_ack;
+			struct usbcan_cmd_clk_overflow_event clk_overflow_event;
 		} __packed usbcan;
 
 		struct kvaser_cmd_tx_can tx_can;
@@ -396,7 +411,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = {
 	[CMD_START_CHIP_REPLY]		= kvaser_fsize(u.simple),
 	[CMD_STOP_CHIP_REPLY]		= kvaser_fsize(u.simple),
 	[CMD_GET_CARD_INFO_REPLY]	= kvaser_fsize(u.cardinfo),
-	[CMD_TX_ACKNOWLEDGE]		= kvaser_fsize(u.tx_acknowledge_header),
+	[CMD_TX_ACKNOWLEDGE]		= kvaser_fsize(u.usbcan.tx_ack),
 	[CMD_GET_SOFTWARE_INFO_REPLY]	= kvaser_fsize(u.usbcan.softinfo),
 	[CMD_RX_STD_MESSAGE]		= kvaser_fsize(u.usbcan.rx_can),
 	[CMD_RX_EXT_MESSAGE]		= kvaser_fsize(u.usbcan.rx_can),
@@ -404,7 +419,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = {
 	[CMD_CAN_ERROR_EVENT]		= kvaser_fsize(u.usbcan.can_error_event),
 	[CMD_ERROR_EVENT]		= kvaser_fsize(u.usbcan.error_event),
 	/* ignored events: */
-	[CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = CMD_SIZE_ANY,
+	[CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = kvaser_fsize(u.usbcan.clk_overflow_event),
 };
 
 /* Summary of a kvaser error event, for a unified Leaf/Usbcan error
-- 
cgit v1.3-3-g829e


From c644c9698d8dcd1a09934976d1d0720925f7bd78 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:32 +0200
Subject: can: kvaser_usb: leaf: Store MSB of timestamp

Store MSB of timestamp, provided from the device via the clock overflow
event, for usbcan devices (M16C).

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-12-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb.h      |  1 +
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 11 ++++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index 4256a0caae20..591f707d2895 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -70,6 +70,7 @@ struct kvaser_usb_dev_card_data {
 	u32 ctrlmode_supported;
 	u32 capabilities;
 	struct kvaser_usb_dev_card_data_hydra hydra;
+	u32 usbcan_timestamp_msb;
 };
 
 /* Context for an outstanding, not yet ACKed, transmission */
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 2c0313c8f63e..465707174f2e 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -119,6 +119,9 @@
 /* Extended CAN identifier flag */
 #define KVASER_EXTENDED_FRAME		BIT(31)
 
+/* USBCanII timestamp */
+#define KVASER_USB_USBCAN_CLK_OVERFLOW_MASK GENMASK(31, 16)
+
 struct kvaser_cmd_simple {
 	u8 tid;
 	u8 channel;
@@ -418,7 +421,6 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = {
 	[CMD_CHIP_STATE_EVENT]		= kvaser_fsize(u.usbcan.chip_state_event),
 	[CMD_CAN_ERROR_EVENT]		= kvaser_fsize(u.usbcan.can_error_event),
 	[CMD_ERROR_EVENT]		= kvaser_fsize(u.usbcan.error_event),
-	/* ignored events: */
 	[CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = kvaser_fsize(u.usbcan.clk_overflow_event),
 };
 
@@ -1573,7 +1575,7 @@ static void kvaser_usb_leaf_get_busparams_reply(const struct kvaser_usb *dev,
 	complete(&priv->get_busparams_comp);
 }
 
-static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev,
+static void kvaser_usb_leaf_handle_command(struct kvaser_usb *dev,
 					   const struct kvaser_cmd *cmd)
 {
 	if (kvaser_usb_leaf_verify_size(dev, cmd) < 0)
@@ -1619,12 +1621,15 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev,
 		kvaser_usb_leaf_get_busparams_reply(dev, cmd);
 		break;
 
-	/* Ignored commands */
 	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
 		if (dev->driver_info->family != KVASER_USBCAN)
 			goto warn;
+		dev->card_data.usbcan_timestamp_msb =
+					le32_to_cpu(cmd->u.usbcan.clk_overflow_event.time) &
+					KVASER_USB_USBCAN_CLK_OVERFLOW_MASK;
 		break;
 
+	/* Ignored commands */
 	case CMD_FLUSH_QUEUE_REPLY:
 		if (dev->driver_info->family != KVASER_LEAF)
 			goto warn;
-- 
cgit v1.3-3-g829e


From 0aa639d3b3b9a90fd7ee198de58f368bf4add580 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:33 +0200
Subject: can: kvaser_usb: leaf: Add hardware timestamp support to usbcan
 devices

Add hardware timestamp support for all usbcan based devices (M16C).
The usbcan firmware is slightly different compared to the other Kvaser USB
interfaces:
  - The timestamp is provided by a 32-bit counter, with 10us resolution.
    Hence, the hardware timestamp will wrap after less than 12 hours.
  - Each Rx CAN or Tx ACK command only contains the 16-bits LSB of the
    timestamp counter.
  - The 16-bits MSB are sent in an asynchronous event (command), if any
    change occurred in the MSB since the last event.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-13-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c |  3 ++-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 12 ++++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index b5d762d38d5d..576ddf932f47 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -100,7 +100,8 @@ static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = {
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_usbcan = {
 	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
-		  KVASER_USB_QUIRK_HAS_SILENT_MODE,
+		  KVASER_USB_QUIRK_HAS_SILENT_MODE |
+		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
 	.family = KVASER_USBCAN,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 465707174f2e..6b9122ab1464 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -121,6 +121,7 @@
 
 /* USBCanII timestamp */
 #define KVASER_USB_USBCAN_CLK_OVERFLOW_MASK GENMASK(31, 16)
+#define KVASER_USB_USBCAN_TIMESTAMP_FACTOR 10
 
 struct kvaser_cmd_simple {
 	u8 tid;
@@ -536,6 +537,15 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_32mhz = {
 	.bittiming_const = &kvaser_usb_flexc_bittiming_const,
 };
 
+static inline ktime_t kvaser_usb_usbcan_timestamp_to_ktime(const struct kvaser_usb *dev,
+							   __le16 timestamp)
+{
+	u64 ticks = le16_to_cpu(timestamp) |
+		    dev->card_data.usbcan_timestamp_msb;
+
+	return kvaser_usb_ticks_to_ktime(dev->cfg, ticks * KVASER_USB_USBCAN_TIMESTAMP_FACTOR);
+}
+
 static int kvaser_usb_leaf_verify_size(const struct kvaser_usb *dev,
 				       const struct kvaser_cmd *cmd)
 {
@@ -978,6 +988,7 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
 		hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.tx_ack.time);
 		break;
 	case KVASER_USBCAN:
+		hwtstamp = kvaser_usb_usbcan_timestamp_to_ktime(dev, cmd->u.usbcan.tx_ack.time);
 		break;
 	}
 
@@ -1398,6 +1409,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
 		break;
 	case KVASER_USBCAN:
 		rx_data = cmd->u.usbcan.rx_can.data;
+		hwtstamp = kvaser_usb_usbcan_timestamp_to_ktime(dev, cmd->u.usbcan.rx_can.time);
 		break;
 	}
 
-- 
cgit v1.3-3-g829e


From 51b56a25ed60d95a9f7c9e38b0b483811a1d5089 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:34 +0200
Subject: can: kvaser_usb: Remove KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP

Remove KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP, since all devices got
hardware timestamp support.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-14-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb.h      |  1 -
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 26 ++++++++----------------
 2 files changed, 8 insertions(+), 19 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index 591f707d2895..078496d9b7ba 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -41,7 +41,6 @@
 #define KVASER_USB_QUIRK_HAS_SILENT_MODE	BIT(0)
 #define KVASER_USB_QUIRK_HAS_TXRX_ERRORS	BIT(1)
 #define KVASER_USB_QUIRK_IGNORE_CLK_FREQ	BIT(2)
-#define KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP	BIT(3)
 
 /* Device capabilities */
 #define KVASER_USB_CAP_BERR_CAP			0x01
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 576ddf932f47..a4f32d57173a 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -94,29 +94,26 @@
 #define USB_MINI_PCIE_1XCAN_PRODUCT_ID 0x011B
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = {
-	.quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
+	.quirks = 0,
 	.ops = &kvaser_usb_hydra_dev_ops,
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_usbcan = {
 	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
-		  KVASER_USB_QUIRK_HAS_SILENT_MODE |
-		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
+		  KVASER_USB_QUIRK_HAS_SILENT_MODE,
 	.family = KVASER_USBCAN,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf = {
-	.quirks = KVASER_USB_QUIRK_IGNORE_CLK_FREQ |
-		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
+	.quirks = KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err = {
 	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
-		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ |
-		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
+		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
@@ -124,14 +121,13 @@ static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err = {
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leaf_err_listen = {
 	.quirks = KVASER_USB_QUIRK_HAS_TXRX_ERRORS |
 		  KVASER_USB_QUIRK_HAS_SILENT_MODE |
-		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ |
-		  KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
+		  KVASER_USB_QUIRK_IGNORE_CLK_FREQ,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
 
 static const struct kvaser_usb_driver_info kvaser_usb_driver_info_leafimx = {
-	.quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP,
+	.quirks = 0,
 	.family = KVASER_LEAF,
 	.ops = &kvaser_usb_leaf_dev_ops,
 };
@@ -862,14 +858,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 
 	netdev->flags |= IFF_ECHO;
 
-	netdev->netdev_ops = &kvaser_usb_netdev_ops;
-	if (driver_info->quirks & KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP) {
-		netdev->netdev_ops = &kvaser_usb_netdev_ops_hwts;
-		netdev->ethtool_ops = &kvaser_usb_ethtool_ops_hwts;
-	} else {
-		netdev->netdev_ops = &kvaser_usb_netdev_ops;
-		netdev->ethtool_ops = &kvaser_usb_ethtool_ops;
-	}
+	netdev->netdev_ops = &kvaser_usb_netdev_ops_hwts;
+	netdev->ethtool_ops = &kvaser_usb_ethtool_ops_hwts;
 	SET_NETDEV_DEV(netdev, &dev->intf->dev);
 	netdev->dev_id = channel;
 
-- 
cgit v1.3-3-g829e


From 1a6b249e4b1951be850c99a1d6e57730d76d8071 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:35 +0200
Subject: can: kvaser_usb: Remove struct variables
 kvaser_usb_{ethtool,netdev}_ops

Remove no longer used struct variables, kvaser_usb_ethtool_ops and
kvaser_usb_netdev_ops.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-15-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index a4f32d57173a..4b6c23121b5d 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -753,13 +753,6 @@ freeurb:
 	return ret;
 }
 
-static const struct net_device_ops kvaser_usb_netdev_ops = {
-	.ndo_open = kvaser_usb_open,
-	.ndo_stop = kvaser_usb_close,
-	.ndo_start_xmit = kvaser_usb_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
-};
-
 static const struct net_device_ops kvaser_usb_netdev_ops_hwts = {
 	.ndo_open = kvaser_usb_open,
 	.ndo_stop = kvaser_usb_close,
@@ -768,10 +761,6 @@ static const struct net_device_ops kvaser_usb_netdev_ops_hwts = {
 	.ndo_change_mtu = can_change_mtu,
 };
 
-static const struct ethtool_ops kvaser_usb_ethtool_ops = {
-	.get_ts_info = ethtool_op_get_ts_info,
-};
-
 static const struct ethtool_ops kvaser_usb_ethtool_ops_hwts = {
 	.get_ts_info = can_ethtool_op_get_ts_info_hwts,
 };
-- 
cgit v1.3-3-g829e


From 88371f85461adbdff4df3c09f6f1ffcbb5a88546 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Mon, 1 Jul 2024 17:49:36 +0200
Subject: can: kvaser_usb: Rename kvaser_usb_{ethtool,netdev}_ops_hwts to
 kvaser_usb_{ethtool,netdev}_ops

Now when we only got one set of ethtool_ops and netdev_ops, remove the
"hwts" suffix from the struct variables
kvaser_usb_{ethtool,netdev}_ops_hwts.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://lore.kernel.org/all/20240701154936.92633-16-extja@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 4b6c23121b5d..35b4132b0639 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -753,7 +753,7 @@ freeurb:
 	return ret;
 }
 
-static const struct net_device_ops kvaser_usb_netdev_ops_hwts = {
+static const struct net_device_ops kvaser_usb_netdev_ops = {
 	.ndo_open = kvaser_usb_open,
 	.ndo_stop = kvaser_usb_close,
 	.ndo_eth_ioctl = can_eth_ioctl_hwts,
@@ -761,7 +761,7 @@ static const struct net_device_ops kvaser_usb_netdev_ops_hwts = {
 	.ndo_change_mtu = can_change_mtu,
 };
 
-static const struct ethtool_ops kvaser_usb_ethtool_ops_hwts = {
+static const struct ethtool_ops kvaser_usb_ethtool_ops = {
 	.get_ts_info = can_ethtool_op_get_ts_info_hwts,
 };
 
@@ -847,8 +847,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel)
 
 	netdev->flags |= IFF_ECHO;
 
-	netdev->netdev_ops = &kvaser_usb_netdev_ops_hwts;
-	netdev->ethtool_ops = &kvaser_usb_ethtool_ops_hwts;
+	netdev->netdev_ops = &kvaser_usb_netdev_ops;
+	netdev->ethtool_ops = &kvaser_usb_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->intf->dev);
 	netdev->dev_id = channel;
 
-- 
cgit v1.3-3-g829e


From a2dc7bee4f77266ebb8e3a8544fc5f7812835f8c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Aug 2024 13:40:25 +0000
Subject: inet: constify inet_sk_bound_dev_eq() net parameter

inet_sk_bound_dev_eq() and its callers do not modify the net structure.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240802134029.3748005-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet6_hashtables.h | 2 +-
 include/net/inet_hashtables.h  | 2 +-
 include/net/inet_sock.h        | 3 ++-
 net/ipv4/inet_hashtables.c     | 2 +-
 net/ipv6/inet6_hashtables.c    | 2 +-
 5 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 533a7337865a..591cbf5e4d5f 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -175,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
 
 int inet6_hash(struct sock *sk);
 
-static inline bool inet6_match(struct net *net, const struct sock *sk,
+static inline bool inet6_match(const struct net *net, const struct sock *sk,
 			       const struct in6_addr *saddr,
 			       const struct in6_addr *daddr,
 			       const __portpair ports,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 7f1b38458743..1cc8b7ca20a1 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -351,7 +351,7 @@ static inline struct sock *inet_lookup_listener(struct net *net,
 				   ((__force __u64)(__be32)(__saddr)))
 #endif /* __BIG_ENDIAN */
 
-static inline bool inet_match(struct net *net, const struct sock *sk,
+static inline bool inet_match(const struct net *net, const struct sock *sk,
 			      const __addrpair cookie, const __portpair ports,
 			      int dif, int sdif)
 {
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index f9ddd47dc4f8..394c3b66065e 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -150,7 +150,8 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if,
 	return bound_dev_if == dif || bound_dev_if == sdif;
 }
 
-static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+static inline bool inet_sk_bound_dev_eq(const struct net *net,
+					int bound_dev_if,
 					int dif, int sdif)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 48d0d494185b..3d913dbd0284 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -310,7 +310,7 @@ inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk)
 	return inet_lhash2_bucket(h, hash);
 }
 
-static inline int compute_score(struct sock *sk, struct net *net,
+static inline int compute_score(struct sock *sk, const struct net *net,
 				const unsigned short hnum, const __be32 daddr,
 				const int dif, const int sdif)
 {
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 6db71bb1cd30..f29f094e57a4 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -89,7 +89,7 @@ found:
 }
 EXPORT_SYMBOL(__inet6_lookup_established);
 
-static inline int compute_score(struct sock *sk, struct net *net,
+static inline int compute_score(struct sock *sk, const struct net *net,
 				const unsigned short hnum,
 				const struct in6_addr *daddr,
 				const int dif, const int sdif)
-- 
cgit v1.3-3-g829e


From d4433e8b405a882fa2ef29601c4ad262ba6e5526 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Aug 2024 13:40:26 +0000
Subject: inet: constify 'struct net' parameter of various lookup helpers

Following helpers do not touch their struct net argument:

- bpf_sk_lookup_run_v4()
- inet_lookup_reuseport()
- inet_lhash2_lookup()
- inet_lookup_run_sk_lookup()
- __inet_lookup_listener()
- __inet_lookup_established()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240802134029.3748005-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/filter.h        |  2 +-
 include/net/inet_hashtables.h |  8 ++++----
 net/ipv4/inet_hashtables.c    | 10 +++++-----
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index b6672ff61407..4acd1da4dac6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1616,7 +1616,7 @@ extern struct static_key_false bpf_sk_lookup_enabled;
 		_all_pass || _selected_sk ? SK_PASS : SK_DROP;		\
 	 })
 
-static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
+static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol,
 					const __be32 saddr, const __be16 sport,
 					const __be32 daddr, const u16 dport,
 					const int ifindex, struct sock **psk)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 1cc8b7ca20a1..5eea47f135a4 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -304,7 +304,7 @@ int __inet_hash(struct sock *sk, struct sock *osk);
 int inet_hash(struct sock *sk);
 void inet_unhash(struct sock *sk);
 
-struct sock *__inet_lookup_listener(struct net *net,
+struct sock *__inet_lookup_listener(const struct net *net,
 				    struct inet_hashinfo *hashinfo,
 				    struct sk_buff *skb, int doff,
 				    const __be32 saddr, const __be16 sport,
@@ -368,7 +368,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk,
 /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
  * not check it for lookups anymore, thanks Alexey. -DaveM
  */
-struct sock *__inet_lookup_established(struct net *net,
+struct sock *__inet_lookup_established(const struct net *net,
 				       struct inet_hashinfo *hashinfo,
 				       const __be32 saddr, const __be16 sport,
 				       const __be32 daddr, const u16 hnum,
@@ -382,13 +382,13 @@ inet_ehashfn_t inet_ehashfn;
 
 INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn);
 
-struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
+struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk,
 				   struct sk_buff *skb, int doff,
 				   __be32 saddr, __be16 sport,
 				   __be32 daddr, unsigned short hnum,
 				   inet_ehashfn_t *ehashfn);
 
-struct sock *inet_lookup_run_sk_lookup(struct net *net,
+struct sock *inet_lookup_run_sk_lookup(const struct net *net,
 				       int protocol,
 				       struct sk_buff *skb, int doff,
 				       __be32 saddr, __be16 sport,
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 3d913dbd0284..9bfcfd016e18 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -348,7 +348,7 @@ static inline int compute_score(struct sock *sk, const struct net *net,
  * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
  *         the selected sock or an error.
  */
-struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk,
+struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk,
 				   struct sk_buff *skb, int doff,
 				   __be32 saddr, __be16 sport,
 				   __be32 daddr, unsigned short hnum,
@@ -374,7 +374,7 @@ EXPORT_SYMBOL_GPL(inet_lookup_reuseport);
  */
 
 /* called with rcu_read_lock() : No refcount taken on the socket */
-static struct sock *inet_lhash2_lookup(struct net *net,
+static struct sock *inet_lhash2_lookup(const struct net *net,
 				struct inet_listen_hashbucket *ilb2,
 				struct sk_buff *skb, int doff,
 				const __be32 saddr, __be16 sport,
@@ -401,7 +401,7 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 	return result;
 }
 
-struct sock *inet_lookup_run_sk_lookup(struct net *net,
+struct sock *inet_lookup_run_sk_lookup(const struct net *net,
 				       int protocol,
 				       struct sk_buff *skb, int doff,
 				       __be32 saddr, __be16 sport,
@@ -423,7 +423,7 @@ struct sock *inet_lookup_run_sk_lookup(struct net *net,
 	return sk;
 }
 
-struct sock *__inet_lookup_listener(struct net *net,
+struct sock *__inet_lookup_listener(const struct net *net,
 				    struct inet_hashinfo *hashinfo,
 				    struct sk_buff *skb, int doff,
 				    const __be32 saddr, __be16 sport,
@@ -488,7 +488,7 @@ void sock_edemux(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sock_edemux);
 
-struct sock *__inet_lookup_established(struct net *net,
+struct sock *__inet_lookup_established(const struct net *net,
 				  struct inet_hashinfo *hashinfo,
 				  const __be32 saddr, const __be16 sport,
 				  const __be32 daddr, const u16 hnum,
-- 
cgit v1.3-3-g829e


From b9abcbb1239cd782f76532397a7c45458de9a73e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Aug 2024 13:40:27 +0000
Subject: udp: constify 'struct net' parameter of socket lookups

Following helpers do not touch their 'struct net' argument.

- udp_sk_bound_dev_eq()
- udp4_lib_lookup()
- __udp4_lib_lookup()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240802134029.3748005-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/udp.h | 10 ++++++----
 net/ipv4/udp.c    |  8 ++++----
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/net/udp.h b/include/net/udp.h
index c4e05b14b648..a0217e3cfe4f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -79,7 +79,8 @@ struct udp_table {
 extern struct udp_table udp_table;
 void udp_table_init(struct udp_table *, const char *);
 static inline struct udp_hslot *udp_hashslot(struct udp_table *table,
-					     struct net *net, unsigned int num)
+					     const struct net *net,
+					     unsigned int num)
 {
 	return &table->hash[udp_hashfn(net, num, table->mask)];
 }
@@ -245,7 +246,7 @@ static inline int udp_rqueue_get(struct sock *sk)
 	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
 }
 
-static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if,
 				       int dif, int sdif)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
@@ -296,9 +297,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		       sockptr_t optval, unsigned int optlen,
 		       int (*push_pending_frames)(struct sock *));
-struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport,
 			     __be32 daddr, __be16 dport, int dif);
-struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr,
+			       __be16 sport,
 			       __be32 daddr, __be16 dport, int dif, int sdif,
 			       struct udp_table *tbl, struct sk_buff *skb);
 struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 49c622e743e8..ddb86baaea6c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -365,7 +365,7 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 	return udp_lib_get_port(sk, snum, hash2_nulladdr);
 }
 
-static int compute_score(struct sock *sk, struct net *net,
+static int compute_score(struct sock *sk, const struct net *net,
 			 __be32 saddr, __be16 sport,
 			 __be32 daddr, unsigned short hnum,
 			 int dif, int sdif)
@@ -420,7 +420,7 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
 }
 
 /* called with rcu_read_lock() */
-static struct sock *udp4_lib_lookup2(struct net *net,
+static struct sock *udp4_lib_lookup2(const struct net *net,
 				     __be32 saddr, __be16 sport,
 				     __be32 daddr, unsigned int hnum,
 				     int dif, int sdif,
@@ -480,7 +480,7 @@ rescore:
 /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
  * harder than this. -DaveM
  */
-struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
+struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr,
 		__be16 sport, __be32 daddr, __be16 dport, int dif,
 		int sdif, struct udp_table *udptable, struct sk_buff *skb)
 {
@@ -561,7 +561,7 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
  * Does increment socket refcount.
  */
 #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4)
-struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport,
 			     __be32 daddr, __be16 dport, int dif)
 {
 	struct sock *sk;
-- 
cgit v1.3-3-g829e


From 10b2a44ccb0cdf85480b6f73a23530aa3ac722de Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Aug 2024 13:40:28 +0000
Subject: inet6: constify 'struct net' parameter of various lookup helpers

Following helpers do not touch their struct net argument:

- bpf_sk_lookup_run_v6()
- __inet6_lookup_established()
- inet6_lookup_reuseport()
- inet6_lookup_listener()
- inet6_lookup_run_sk_lookup()
- __inet6_lookup()
- inet6_lookup()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240802134029.3748005-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/filter.h         |  2 +-
 include/net/inet6_hashtables.h | 12 ++++++------
 net/ipv6/inet6_hashtables.c    | 13 +++++++------
 3 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4acd1da4dac6..64e1506fefb8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1653,7 +1653,7 @@ static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
+static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol,
 					const struct in6_addr *saddr,
 					const __be16 sport,
 					const struct in6_addr *daddr,
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 591cbf5e4d5f..74dd90ff5f12 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash,
  *
  * The sockhash lock must be held as a reader here.
  */
-struct sock *__inet6_lookup_established(struct net *net,
+struct sock *__inet6_lookup_established(const struct net *net,
 					struct inet_hashinfo *hashinfo,
 					const struct in6_addr *saddr,
 					const __be16 sport,
@@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn;
 
 INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn);
 
-struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk,
 				    struct sk_buff *skb, int doff,
 				    const struct in6_addr *saddr,
 				    __be16 sport,
@@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
 				    unsigned short hnum,
 				    inet6_ehashfn_t *ehashfn);
 
-struct sock *inet6_lookup_listener(struct net *net,
+struct sock *inet6_lookup_listener(const struct net *net,
 				   struct inet_hashinfo *hashinfo,
 				   struct sk_buff *skb, int doff,
 				   const struct in6_addr *saddr,
@@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net,
 				   const unsigned short hnum,
 				   const int dif, const int sdif);
 
-struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+struct sock *inet6_lookup_run_sk_lookup(const struct net *net,
 					int protocol,
 					struct sk_buff *skb, int doff,
 					const struct in6_addr *saddr,
@@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net,
 					const u16 hnum, const int dif,
 					inet6_ehashfn_t *ehashfn);
 
-static inline struct sock *__inet6_lookup(struct net *net,
+static inline struct sock *__inet6_lookup(const struct net *net,
 					  struct inet_hashinfo *hashinfo,
 					  struct sk_buff *skb, int doff,
 					  const struct in6_addr *saddr,
@@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 			      iif, sdif, refcounted);
 }
 
-struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
+struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo,
 			  struct sk_buff *skb, int doff,
 			  const struct in6_addr *saddr, const __be16 sport,
 			  const struct in6_addr *daddr, const __be16 dport,
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index f29f094e57a4..9ec05e354baa 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -46,7 +46,7 @@ EXPORT_SYMBOL_GPL(inet6_ehashfn);
  *
  * The sockhash lock must be held as a reader here.
  */
-struct sock *__inet6_lookup_established(struct net *net,
+struct sock *__inet6_lookup_established(const struct net *net,
 					struct inet_hashinfo *hashinfo,
 					   const struct in6_addr *saddr,
 					   const __be16 sport,
@@ -126,7 +126,7 @@ static inline int compute_score(struct sock *sk, const struct net *net,
  * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to
  *         the selected sock or an error.
  */
-struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
+struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk,
 				    struct sk_buff *skb, int doff,
 				    const struct in6_addr *saddr,
 				    __be16 sport,
@@ -147,7 +147,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk,
 EXPORT_SYMBOL_GPL(inet6_lookup_reuseport);
 
 /* called with rcu_read_lock() */
-static struct sock *inet6_lhash2_lookup(struct net *net,
+static struct sock *inet6_lhash2_lookup(const struct net *net,
 		struct inet_listen_hashbucket *ilb2,
 		struct sk_buff *skb, int doff,
 		const struct in6_addr *saddr,
@@ -174,7 +174,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 	return result;
 }
 
-struct sock *inet6_lookup_run_sk_lookup(struct net *net,
+struct sock *inet6_lookup_run_sk_lookup(const struct net *net,
 					int protocol,
 					struct sk_buff *skb, int doff,
 					const struct in6_addr *saddr,
@@ -199,7 +199,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net,
 }
 EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup);
 
-struct sock *inet6_lookup_listener(struct net *net,
+struct sock *inet6_lookup_listener(const struct net *net,
 		struct inet_hashinfo *hashinfo,
 		struct sk_buff *skb, int doff,
 		const struct in6_addr *saddr,
@@ -243,7 +243,8 @@ done:
 }
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
 
-struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
+struct sock *inet6_lookup(const struct net *net,
+			  struct inet_hashinfo *hashinfo,
 			  struct sk_buff *skb, int doff,
 			  const struct in6_addr *saddr, const __be16 sport,
 			  const struct in6_addr *daddr, const __be16 dport,
-- 
cgit v1.3-3-g829e


From 87d973e8ddeeddf1777e6689df86d5d369cbcbb3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 2 Aug 2024 13:40:29 +0000
Subject: ipv6: udp: constify 'struct net' parameter of socket lookups

Following helpers do not touch their 'struct net' argument.

- udp6_lib_lookup()
- __udp6_lib_lookup()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240802134029.3748005-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ipv6_stubs.h | 2 +-
 include/net/udp.h        | 4 ++--
 net/ipv6/udp.c           | 8 ++++----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h
index 11cefd50704d..8a3465c8c2c5 100644
--- a/include/net/ipv6_stubs.h
+++ b/include/net/ipv6_stubs.h
@@ -82,7 +82,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly;
 struct ipv6_bpf_stub {
 	int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			  u32 flags);
-	struct sock *(*udp6_lib_lookup)(struct net *net,
+	struct sock *(*udp6_lib_lookup)(const struct net *net,
 				     const struct in6_addr *saddr, __be16 sport,
 				     const struct in6_addr *daddr, __be16 dport,
 				     int dif, int sdif, struct udp_table *tbl,
diff --git a/include/net/udp.h b/include/net/udp.h
index a0217e3cfe4f..5ca53b1cec67 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -305,11 +305,11 @@ struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr,
 			       struct udp_table *tbl, struct sk_buff *skb);
 struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport);
-struct sock *udp6_lib_lookup(struct net *net,
+struct sock *udp6_lib_lookup(const struct net *net,
 			     const struct in6_addr *saddr, __be16 sport,
 			     const struct in6_addr *daddr, __be16 dport,
 			     int dif);
-struct sock *__udp6_lib_lookup(struct net *net,
+struct sock *__udp6_lib_lookup(const struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
 			       const struct in6_addr *daddr, __be16 dport,
 			       int dif, int sdif, struct udp_table *tbl,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6602a2e9cdb5..52dfbb2ff1a8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -114,7 +114,7 @@ void udp_v6_rehash(struct sock *sk)
 	udp_lib_rehash(sk, new_hash);
 }
 
-static int compute_score(struct sock *sk, struct net *net,
+static int compute_score(struct sock *sk, const struct net *net,
 			 const struct in6_addr *saddr, __be16 sport,
 			 const struct in6_addr *daddr, unsigned short hnum,
 			 int dif, int sdif)
@@ -160,7 +160,7 @@ static int compute_score(struct sock *sk, struct net *net,
 }
 
 /* called with rcu_read_lock() */
-static struct sock *udp6_lib_lookup2(struct net *net,
+static struct sock *udp6_lib_lookup2(const struct net *net,
 		const struct in6_addr *saddr, __be16 sport,
 		const struct in6_addr *daddr, unsigned int hnum,
 		int dif, int sdif, struct udp_hslot *hslot2,
@@ -217,7 +217,7 @@ rescore:
 }
 
 /* rcu_read_lock() must be held */
-struct sock *__udp6_lib_lookup(struct net *net,
+struct sock *__udp6_lib_lookup(const struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
 			       const struct in6_addr *daddr, __be16 dport,
 			       int dif, int sdif, struct udp_table *udptable,
@@ -300,7 +300,7 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
  * Does increment socket refcount.
  */
 #if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
-struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
+struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport,
 			     const struct in6_addr *daddr, __be16 dport, int dif)
 {
 	struct sock *sk;
-- 
cgit v1.3-3-g829e


From e8fc78eb658a1ebcb871e93bbe4f18e9d51fdd3a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 2 Aug 2024 12:34:36 +0100
Subject: tools: ynl: remove extraneous ; after statements

There are a couple of statements with two following semicolons,
replace these with just one semicolon.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20240802113436.448939-1-colin.i.king@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/ynl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index fcb18a5a6d70..e16cef160bc2 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -696,14 +696,14 @@ ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse)
 	addr.nl_family = AF_NETLINK;
 	if (bind(ys->socket, (struct sockaddr *)&addr, sizeof(addr)) < 0) {
 		__perr(yse, "unable to bind to a socket address");
-		goto err_close_sock;;
+		goto err_close_sock;
 	}
 
 	memset(&addr, 0, sizeof(addr));
 	addrlen = sizeof(addr);
 	if (getsockname(ys->socket, (struct sockaddr *)&addr, &addrlen) < 0) {
 		__perr(yse, "unable to read socket address");
-		goto err_close_sock;;
+		goto err_close_sock;
 	}
 	ys->portid = addr.nl_pid;
 	ys->seq = random();
-- 
cgit v1.3-3-g829e


From 7e45c1e9edc0004b914e2d5a33245908a06f072c Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Tue, 30 Jul 2024 16:40:52 +0300
Subject: net/mlx5: Add support for MTPTM and MTCTR registers

Make Management Precision Time Measurement (MTPTM) register and Management
Cross Timestamp (MTCTR) register usable in mlx5 driver.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20240730134055.1835261-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c |  1 +
 include/linux/mlx5/device.h                  |  7 ++++-
 include/linux/mlx5/driver.h                  |  2 ++
 include/linux/mlx5/mlx5_ifc.h                | 43 ++++++++++++++++++++++++++++
 4 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index b61b7d966114..76ad46bf477d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -224,6 +224,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, mcam_reg)) {
 		mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128);
 		mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F);
+		mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9180_0x91FF);
 	}
 
 	if (MLX5_CAP_GEN(dev, qcam_reg))
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index ba875a619b97..a94bc9e3af96 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1243,7 +1243,8 @@ enum mlx5_pcam_feature_groups {
 enum mlx5_mcam_reg_groups {
 	MLX5_MCAM_REGS_FIRST_128                    = 0x0,
 	MLX5_MCAM_REGS_0x9100_0x917F                = 0x2,
-	MLX5_MCAM_REGS_NUM                          = 0x3,
+	MLX5_MCAM_REGS_0x9180_0x91FF                = 0x3,
+	MLX5_MCAM_REGS_NUM                          = 0x4,
 };
 
 enum mlx5_mcam_feature_groups {
@@ -1392,6 +1393,10 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \
 		 mng_access_reg_cap_mask.access_regs2.reg)
 
+#define MLX5_CAP_MCAM_REG3(mdev, reg) \
+	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9180_0x91FF], \
+		 mng_access_reg_cap_mask.access_regs3.reg)
+
 #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a96438ded15f..9f42834f57c5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -159,6 +159,8 @@ enum {
 	MLX5_REG_MSECQ		 = 0x9155,
 	MLX5_REG_MSEES		 = 0x9156,
 	MLX5_REG_MIRC		 = 0x9162,
+	MLX5_REG_MTPTM		 = 0x9180,
+	MLX5_REG_MTCTR		 = 0x9181,
 	MLX5_REG_SBCAM		 = 0xB01F,
 	MLX5_REG_RESOURCE_DUMP   = 0xC000,
 	MLX5_REG_DTOR            = 0xC00E,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index cab228cf51c6..234ad6f16e92 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10401,6 +10401,18 @@ struct mlx5_ifc_mcam_access_reg_bits2 {
 	u8         regs_31_to_0[0x20];
 };
 
+struct mlx5_ifc_mcam_access_reg_bits3 {
+	u8         regs_127_to_96[0x20];
+
+	u8         regs_95_to_64[0x20];
+
+	u8         regs_63_to_32[0x20];
+
+	u8         regs_31_to_2[0x1e];
+	u8         mtctr[0x1];
+	u8         mtptm[0x1];
+};
+
 struct mlx5_ifc_mcam_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         feature_group[0x8];
@@ -10413,6 +10425,7 @@ struct mlx5_ifc_mcam_reg_bits {
 		struct mlx5_ifc_mcam_access_reg_bits access_regs;
 		struct mlx5_ifc_mcam_access_reg_bits1 access_regs1;
 		struct mlx5_ifc_mcam_access_reg_bits2 access_regs2;
+		struct mlx5_ifc_mcam_access_reg_bits3 access_regs3;
 		u8         reserved_at_0[0x80];
 	} mng_access_reg_cap_mask;
 
@@ -11166,6 +11179,34 @@ struct mlx5_ifc_mtmp_reg_bits {
 	u8         sensor_name_lo[0x20];
 };
 
+struct mlx5_ifc_mtptm_reg_bits {
+	u8         reserved_at_0[0x10];
+	u8         psta[0x1];
+	u8         reserved_at_11[0xf];
+
+	u8         reserved_at_20[0x60];
+};
+
+enum {
+	MLX5_MTCTR_REQUEST_NOP = 0x0,
+	MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK = 0x1,
+	MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER = 0x2,
+	MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK = 0x3,
+};
+
+struct mlx5_ifc_mtctr_reg_bits {
+	u8         first_clock_timestamp_request[0x8];
+	u8         second_clock_timestamp_request[0x8];
+	u8         reserved_at_10[0x10];
+
+	u8         first_clock_valid[0x1];
+	u8         second_clock_valid[0x1];
+	u8         reserved_at_22[0x1e];
+
+	u8         first_clock_timestamp[0x40];
+	u8         second_clock_timestamp[0x40];
+};
+
 union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_bufferx_reg_bits bufferx_reg;
 	struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout;
@@ -11230,6 +11271,8 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_mrtc_reg_bits mrtc_reg;
 	struct mlx5_ifc_mtcap_reg_bits mtcap_reg;
 	struct mlx5_ifc_mtmp_reg_bits mtmp_reg;
+	struct mlx5_ifc_mtptm_reg_bits mtptm_reg;
+	struct mlx5_ifc_mtctr_reg_bits mtctr_reg;
 	u8         reserved_at_0[0x60e0];
 };
 
-- 
cgit v1.3-3-g829e


From bec6d85d43eb7fa0834b4284bdc62f7d3a23288f Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Tue, 30 Jul 2024 16:40:53 +0300
Subject: net/mlx5: Add support for enabling PTM PCI capability

Since the kernel doesn't support enabling Precision Time Measurement
for an endpoint device, enable the PTM PCI capability in the driver.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20240730134055.1835261-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 5b7e6f4b5c7e..4b88d969a66c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -923,6 +923,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	}
 
 	mlx5_pci_vsc_init(dev);
+
+	err = pci_enable_ptm(pdev, NULL);
+	if (err)
+		mlx5_core_info(dev, "PTM is not supported by PCIe\n");
+
 	return 0;
 
 err_clr_master:
@@ -939,6 +944,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev)
 	 * before removing the pci bars
 	 */
 	mlx5_drain_health_wq(dev);
+	pci_disable_ptm(dev->pdev);
 	iounmap(dev->iseg);
 	release_bar(dev->pdev);
 	mlx5_pci_disable_device(dev);
-- 
cgit v1.3-3-g829e


From d17125fb0923228fb3cc1e03790de4ee88f7f95f Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Tue, 30 Jul 2024 16:40:54 +0300
Subject: net/mlx5: Implement PTM cross timestamping support

Expose Precision Time Measurement support through related PTP ioctl.

The performance of PTM on ConnectX-7 was evaluated using both real-time
(RTC) and free-running (FRC) clocks under traffic and no traffic
conditions. Tests with phc2sys measured the maximum offset values at a 50Hz
rate, with and without PTM.

Results:

1. No traffic
+-----+--------+--------+
|     | No-PTM | PTM    |
+-----+--------+--------+
| FRC | 125 ns | <29 ns |
+-----+--------+--------+
| RTC | 248 ns | <34 ns |
+-----+--------+--------+

2. With traffic
+-----+--------+--------+
|     | No-PTM | PTM    |
+-----+--------+--------+
| FRC | 254 ns | <40 ns |
+-----+--------+--------+
| RTC | 255 ns | <45 ns |
+-----+--------+--------+

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Co-developed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20240730134055.1835261-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/lib/clock.c    | 91 ++++++++++++++++++++++
 1 file changed, 91 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 0361741632a6..b306ae79bf97 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -38,6 +38,10 @@
 #include "lib/eq.h"
 #include "en.h"
 #include "clock.h"
+#ifdef CONFIG_X86
+#include <linux/timekeeping.h>
+#include <linux/cpufeature.h>
+#endif /* CONFIG_X86 */
 
 enum {
 	MLX5_PIN_MODE_IN		= 0x0,
@@ -148,6 +152,87 @@ static int mlx5_set_mtutc(struct mlx5_core_dev *dev, u32 *mtutc, u32 size)
 				    MLX5_REG_MTUTC, 0, 1);
 }
 
+#ifdef CONFIG_X86
+static bool mlx5_is_ptm_source_time_available(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(mtptm_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtptm_reg)] = {0};
+	int err;
+
+	if (!MLX5_CAP_MCAM_REG3(dev, mtptm))
+		return false;
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTPTM,
+				   0, 0);
+	if (err)
+		return false;
+
+	return !!MLX5_GET(mtptm_reg, out, psta);
+}
+
+static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
+				     struct system_counterval_t *sys_counterval,
+				     void *ctx)
+{
+	u32 out[MLX5_ST_SZ_DW(mtctr_reg)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtctr_reg)] = {0};
+	struct mlx5_core_dev *mdev = ctx;
+	bool real_time_mode;
+	u64 host, device;
+	int err;
+
+	real_time_mode = mlx5_real_time_mode(mdev);
+
+	MLX5_SET(mtctr_reg, in, first_clock_timestamp_request,
+		 MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK);
+	MLX5_SET(mtctr_reg, in, second_clock_timestamp_request,
+		 real_time_mode ? MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK :
+		 MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER);
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTCTR,
+				   0, 0);
+	if (err)
+		return err;
+
+	if (!MLX5_GET(mtctr_reg, out, first_clock_valid) ||
+	    !MLX5_GET(mtctr_reg, out, second_clock_valid))
+		return -EINVAL;
+
+	host = MLX5_GET64(mtctr_reg, out, first_clock_timestamp);
+	*sys_counterval = (struct system_counterval_t) {
+			.cycles = host,
+			.cs_id = CSID_X86_ART,
+			.use_nsecs = true,
+	};
+
+	device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp);
+	if (real_time_mode)
+		*device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX));
+	else
+		*device_time = mlx5_timecounter_cyc2time(&mdev->clock, device);
+
+	return 0;
+}
+
+static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
+				   struct system_device_crosststamp *cts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct system_time_snapshot history_begin = {0};
+	struct mlx5_core_dev *mdev;
+
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
+	if (!mlx5_is_ptm_source_time_available(mdev))
+		return -EBUSY;
+
+	ktime_get_snapshot(&history_begin);
+
+	return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
+					     &history_begin, cts);
+}
+#endif /* CONFIG_X86 */
+
 static u64 mlx5_read_time(struct mlx5_core_dev *dev,
 			  struct ptp_system_timestamp *sts,
 			  bool real_time)
@@ -1034,6 +1119,12 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 	if (MLX5_CAP_MCAM_REG(mdev, mtutc))
 		mlx5_init_timer_max_freq_adjustment(mdev);
 
+#ifdef CONFIG_X86
+	if (MLX5_CAP_MCAM_REG3(mdev, mtptm) &&
+	    MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART))
+		clock->ptp_info.getcrosststamp = mlx5_ptp_getcrosststamp;
+#endif /* CONFIG_X86 */
+
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
 	mlx5_init_overflow_period(clock);
-- 
cgit v1.3-3-g829e


From c4e2ced14af0a95463eb2e84b474601eaf600a74 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Mon, 5 Aug 2024 08:22:02 +0300
Subject: MAINTAINERS: Update Mellanox website links

Point to the nvidia.com domain.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240805052202.2005316-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8766f3e5e87e..a9dace908305 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14489,7 +14489,7 @@ MELLANOX ETHERNET DRIVER (mlx4_en)
 M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx4/en_*
 
@@ -14498,7 +14498,7 @@ M:	Saeed Mahameed <saeedm@nvidia.com>
 M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_*
 
@@ -14506,7 +14506,7 @@ MELLANOX ETHERNET INNOVA DRIVERS
 R:	Boris Pismenny <borisp@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx5/core/en_accel/*
 F:	drivers/net/ethernet/mellanox/mlx5/core/fpga/*
@@ -14517,7 +14517,7 @@ M:	Ido Schimmel <idosch@nvidia.com>
 M:	Petr Machata <petrm@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlxsw/
 F:	tools/testing/selftests/drivers/net/mlxsw/
@@ -14526,7 +14526,7 @@ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw)
 M:	mlxsw@nvidia.com
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlxfw/
 
@@ -14545,7 +14545,7 @@ M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlx4/
 F:	include/linux/mlx4/
@@ -14554,7 +14554,7 @@ MELLANOX MLX4 IB driver
 M:	Yishai Hadas <yishaih@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/hw/mlx4/
 F:	include/linux/mlx4/
@@ -14567,7 +14567,7 @@ M:	Tariq Toukan <tariqt@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	Documentation/networking/device_drivers/ethernet/mellanox/
 F:	drivers/net/ethernet/mellanox/mlx5/core/
@@ -14577,7 +14577,7 @@ MELLANOX MLX5 IB driver
 M:	Leon Romanovsky <leonro@nvidia.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
-W:	http://www.mellanox.com
+W:	https://www.nvidia.com/networking/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 F:	drivers/infiniband/hw/mlx5/
 F:	include/linux/mlx5/
-- 
cgit v1.3-3-g829e


From 63a796b4988c3dca83176a534890b510d44f105a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 3 Aug 2024 17:50:50 +0200
Subject: net: airoha: honor reset return value in airoha_hw_init()

Take into account return value from reset_control_bulk_assert and
reset_control_bulk_deassert routines in airoha_hw_init().

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/f49dc04a87653e0155f4fab3e3eb584785c8ad6a.1722699555.git.lorenzo@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index db4267225fa4..1fb46db0c1e9 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -2071,13 +2071,21 @@ static int airoha_hw_init(struct platform_device *pdev,
 	int err, i;
 
 	/* disable xsi */
-	reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), eth->xsi_rsts);
+	err = reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts),
+					eth->xsi_rsts);
+	if (err)
+		return err;
+
+	err = reset_control_bulk_assert(ARRAY_SIZE(eth->rsts), eth->rsts);
+	if (err)
+		return err;
 
-	reset_control_bulk_assert(ARRAY_SIZE(eth->rsts), eth->rsts);
-	msleep(20);
-	reset_control_bulk_deassert(ARRAY_SIZE(eth->rsts), eth->rsts);
 	msleep(20);
+	err = reset_control_bulk_deassert(ARRAY_SIZE(eth->rsts), eth->rsts);
+	if (err)
+		return err;
 
+	msleep(20);
 	err = airoha_fe_init(eth);
 	if (err)
 		return err;
-- 
cgit v1.3-3-g829e


From 871cdea0f82ebcfa1d86ef527b054a20a6dff8a2 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 4 Aug 2024 08:20:17 +0200
Subject: tcp: Use clamp() in htcp_alpha_update()

Using clamp instead of min(max()) is easier to read and it matches even
better the comment just above it.

It also reduces the size of the preprocessed files by ~ 2.5 ko.
(see [1] for a discussion about it)

$ ls -l net/ipv4/tcp_htcp*.i
 5576024 27 juil. 10:19 net/ipv4/tcp_htcp.old.i
 5573550 27 juil. 10:21 net/ipv4/tcp_htcp.new.i

[1]: https://lore.kernel.org/all/23bdb6fc8d884ceebeb6e8b8653b8cfe@AcuMS.aculab.com/

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/561bb4974499a328ac39aff31858465d9bd12b1c.1722752370.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_htcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 52b1f2665dfa..81b96331b2bb 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -185,7 +185,7 @@ static inline void htcp_alpha_update(struct htcp *ca)
 		u32 scale = (HZ << 3) / (10 * minRTT);
 
 		/* clamping ratio to interval [0.5,10]<<3 */
-		scale = min(max(scale, 1U << 2), 10U << 3);
+		scale = clamp(scale, 1U << 2, 10U << 3);
 		factor = (factor << 3) / scale;
 		if (!factor)
 			factor = 1;
-- 
cgit v1.3-3-g829e


From edfa53dd617f682cb43a1488bf08aca9a3e4236c Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 3 Aug 2024 19:22:13 +0800
Subject: ethtool: cmis_cdb: Remove unused declaration ethtool_cmis_page_fini()

ethtool_cmis_page_fini() is declared but never implemented.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Danielle Ratson <danieller@nvidia.com>
Link: https://patch.msgid.link/20240803112213.4044015-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/cmis.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ethtool/cmis.h b/net/ethtool/cmis.h
index e71cc3e1b7eb..3e7c293af78c 100644
--- a/net/ethtool/cmis.h
+++ b/net/ethtool/cmis.h
@@ -108,7 +108,6 @@ void ethtool_cmis_cdb_check_completion_flag(u8 cmis_rev, u8 *flags);
 
 void ethtool_cmis_page_init(struct ethtool_module_eeprom *page_data,
 			    u8 page, u32 offset, u32 length);
-void ethtool_cmis_page_fini(struct ethtool_module_eeprom *page_data);
 
 struct ethtool_cmis_cdb *
 ethtool_cmis_cdb_init(struct net_device *dev,
-- 
cgit v1.3-3-g829e


From 45160cebd6ac84fe8cc2b7f6fec2550398e144cd Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 5 Aug 2024 02:40:11 -0700
Subject: net: veth: Disable netpoll support

The current implementation of netpoll in veth devices leads to
suboptimal behavior, as it triggers warnings due to the invocation of
__netif_rx() within a softirq context. This is not compliant with
expected practices, as __netif_rx() has the following statement:

	lockdep_assert_once(hardirq_count() | softirq_count());

Given that veth devices typically do not benefit from the
functionalities provided by netpoll, Disable netpoll for veth
interfaces.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20240805094012.1843247-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/veth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 426e68a95067..34499b91a8bd 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1696,6 +1696,7 @@ static void veth_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
+	dev->priv_flags |= IFF_DISABLE_NETPOLL;
 
 	dev->netdev_ops = &veth_netdev_ops;
 	dev->xdp_metadata_ops = &veth_xdp_metadata_ops;
-- 
cgit v1.3-3-g829e


From 4f534b7f0c8d2a9ec557f9c7d77f96d29518c666 Mon Sep 17 00:00:00 2001
From: Youwan Wang <youwan@nfschina.com>
Date: Wed, 31 Jul 2024 17:15:37 +0800
Subject: net: phy: phy_device: fix PHY WOL enabled, PM failed to suspend

If the PHY of the mido bus is enabled with Wake-on-LAN (WOL),
we cannot suspend the PHY. Although the WOL status has been
checked in phy_suspend(), returning -EBUSY(-16) would cause
the Power Management (PM) to fail to suspend. Since
phy_suspend() is an exported symbol (EXPORT_SYMBOL),
timely error reporting is needed. Therefore, an additional
check is performed here. If the PHY of the mido bus is enabled
with WOL, we skip calling phy_suspend() to avoid PM failure.

From the following logs, it has been observed that the phydev->attached_dev
is NULL, phydev is "stmmac-0:01", it not attached, but it will affect suspend
and resume.The actually attached "stmmac-0:00" will not dpm_run_callback():
mdio_bus_phy_suspend().

init log:
[    5.932502] YT8521 Gigabit Ethernet stmmac-0:00: attached PHY driver
(mii_bus:phy_addr=stmmac-0:00, irq=POLL)
[    5.932512] YT8521 Gigabit Ethernet stmmac-0:01: attached PHY driver
(mii_bus:phy_addr=stmmac-0:01, irq=POLL)
[   24.566289] YT8521 Gigabit Ethernet stmmac-0:00: yt8521_read_status,
link down, media: UTP

suspend log:
[  322.631362] OOM killer disabled.
[  322.631364] Freezing remaining freezable tasks
[  322.632536] Freezing remaining freezable tasks completed (elapsed 0.001 seconds)
[  322.632540] printk: Suspending console(s) (use no_console_suspend to debug)
[  322.633052] YT8521 Gigabit Ethernet stmmac-0:01:
PM: dpm_run_callback(): mdio_bus_phy_suspend+0x0/0x110 [libphy] returns -16
[  322.633071] YT8521 Gigabit Ethernet stmmac-0:01:
PM: failed to suspend: error -16
[  322.669699] PM: Some devices failed to suspend, or early wake event detected
[  322.669949] OOM killer enabled.
[  322.669951] Restarting tasks ... done.
[  322.671008] random: crng reseeded on system resumption
[  322.671014] PM: suspend exit

Add a function that phylib can inquire of the driver whether WoL
has been enabled at the PHY.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Youwan Wang <youwan@nfschina.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Link: https://patch.msgid.link/20240731091537.771391-1-youwan@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7752e9386b40..34752a87f98f 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -279,6 +279,15 @@ static struct phy_driver genphy_driver;
 static LIST_HEAD(phy_fixup_list);
 static DEFINE_MUTEX(phy_fixup_lock);
 
+static bool phy_drv_wol_enabled(struct phy_device *phydev)
+{
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+
+	phy_ethtool_get_wol(phydev, &wol);
+
+	return wol.wolopts != 0;
+}
+
 static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 {
 	struct device_driver *drv = phydev->mdio.dev.driver;
@@ -288,6 +297,12 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
 	if (!drv || !phydrv->suspend)
 		return false;
 
+	/* If the PHY on the mido bus is not attached but has WOL enabled
+	 * we cannot suspend the PHY.
+	 */
+	if (!netdev && phy_drv_wol_enabled(phydev))
+		return false;
+
 	/* PHY not attached? May suspend if the PHY has not already been
 	 * suspended as part of a prior call to phy_disconnect() ->
 	 * phy_detach() -> phy_suspend() because the parent netdev might be the
@@ -1975,7 +1990,6 @@ EXPORT_SYMBOL(phy_detach);
 
 int phy_suspend(struct phy_device *phydev)
 {
-	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
 	struct net_device *netdev = phydev->attached_dev;
 	const struct phy_driver *phydrv = phydev->drv;
 	int ret;
@@ -1983,8 +1997,7 @@ int phy_suspend(struct phy_device *phydev)
 	if (phydev->suspended || !phydrv)
 		return 0;
 
-	phy_ethtool_get_wol(phydev, &wol);
-	phydev->wol_enabled = wol.wolopts ||
+	phydev->wol_enabled = phy_drv_wol_enabled(phydev) ||
 			      (netdev && netdev->ethtool->wol_enabled);
 	/* If the device has WOL enabled, we cannot suspend the PHY */
 	if (phydev->wol_enabled && !(phydrv->flags & PHY_ALWAYS_CALL_SUSPEND))
-- 
cgit v1.3-3-g829e


From acd221a6507c9d936728ed297f5b1e4bcc7585ec Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Sun, 4 Aug 2024 17:46:09 +0200
Subject: net/chelsio/libcxgb: Add __percpu annotations to libcxgb_ppm.c

Compiling libcxgb_ppm.c results in several sparse warnings:

libcxgb_ppm.c:368:15: warning: incorrect type in assignment (different address spaces)
libcxgb_ppm.c:368:15:    expected struct cxgbi_ppm_pool *pools
libcxgb_ppm.c:368:15:    got void [noderef] __percpu *_res
libcxgb_ppm.c:374:48: warning: incorrect type in initializer (different address spaces)
libcxgb_ppm.c:374:48:    expected void const [noderef] __percpu *__vpp_verify
libcxgb_ppm.c:374:48:    got struct cxgbi_ppm_pool *
libcxgb_ppm.c:484:19: warning: incorrect type in assignment (different address spaces)
libcxgb_ppm.c:484:19:    expected struct cxgbi_ppm_pool [noderef] __percpu *pool
libcxgb_ppm.c:484:19:    got struct cxgbi_ppm_pool *[assigned] pool
libcxgb_ppm.c:511:21: warning: incorrect type in argument 1 (different address spaces)
libcxgb_ppm.c:511:21:    expected void [noderef] __percpu *__pdata
libcxgb_ppm.c:511:21:    got struct cxgbi_ppm_pool *[assigned] pool

Add __percpu annotation to *pools and *pool percpu pointers and to
ppm_alloc_cpu_pool() function that returns percpu pointer to fix
these warnings.

Compile tested only, but there is no difference in the resulting object file.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240804154635.4249-1-ubizjak@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
index 854d87e1125c..2e3973a32d9d 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
@@ -342,10 +342,10 @@ int cxgbi_ppm_release(struct cxgbi_ppm *ppm)
 }
 EXPORT_SYMBOL(cxgbi_ppm_release);
 
-static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total,
-						 unsigned int *pcpu_ppmax)
+static struct cxgbi_ppm_pool __percpu *
+ppm_alloc_cpu_pool(unsigned int *total, unsigned int *pcpu_ppmax)
 {
-	struct cxgbi_ppm_pool *pools;
+	struct cxgbi_ppm_pool __percpu *pools;
 	unsigned int ppmax = (*total) / num_possible_cpus();
 	unsigned int max = (PCPU_MIN_UNIT_SIZE - sizeof(*pools)) << 3;
 	unsigned int bmap;
@@ -392,7 +392,7 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 		   unsigned int iscsi_edram_size)
 {
 	struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp);
-	struct cxgbi_ppm_pool *pool = NULL;
+	struct cxgbi_ppm_pool __percpu *pool = NULL;
 	unsigned int pool_index_max = 0;
 	unsigned int ppmax_pool = 0;
 	unsigned int ppod_bmap_size;
-- 
cgit v1.3-3-g829e


From ca33c15a936088525533cf2e0b111ec1744802c4 Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Wed, 31 Jul 2024 15:05:02 +0800
Subject: wifi: rtw89: 8922a: new implementation for RFK pre-notify H2C

For firmware version 0.35.31 and above, update H2C RFK
pre-notify to new implementation. Rename existing H2C
to v0 for backward compatibility.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240731070506.46100-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  1 +
 drivers/net/wireless/realtek/rtw89/fw.c   | 62 ++++++++++++++++++++-----------
 drivers/net/wireless/realtek/rtw89/fw.h   | 12 +++++-
 3 files changed, 53 insertions(+), 22 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index fc31655d9e7c..fec28f743eae 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4368,6 +4368,7 @@ enum rtw89_fw_feature {
 	RTW89_FW_FEATURE_BEACON_FILTER,
 	RTW89_FW_FEATURE_MACID_PAUSE_SLEEP,
 	RTW89_FW_FEATURE_WOW_REASON_V1,
+	RTW89_FW_FEATURE_RFK_PRE_NOTIFY_V0,
 };
 
 struct rtw89_fw_suit {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index b9bf9ae3a512..fcbc7de48ddd 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -685,6 +685,7 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = {
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 34, 35, 0, SCAN_OFFLOAD),
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 35, 12, 0, BEACON_FILTER),
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 35, 22, 0, WOW_REASON_V1),
+	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 31, 0, RFK_PRE_NOTIFY_V0),
 };
 
 static void rtw89_fw_iterate_feature_cfg(struct rtw89_fw_info *fw,
@@ -5136,14 +5137,21 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy_idx)
 {
 	struct rtw89_rfk_mcc_info *rfk_mcc = &rtwdev->rfk_mcc;
+	struct rtw89_fw_h2c_rfk_pre_info_v0 *h2c_v0;
 	struct rtw89_fw_h2c_rfk_pre_info *h2c;
 	u8 tbl_sel = rfk_mcc->table_idx;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
+	u8 ver = U8_MAX;
 	u8 tbl, path;
 	u32 val32;
 	int ret;
 
+	if (RTW89_CHK_FW_FEATURE(RFK_PRE_NOTIFY_V0, &rtwdev->fw)) {
+		len = sizeof(*h2c_v0);
+		ver = 0;
+	}
+
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
 		rtw89_err(rtwdev, "failed to alloc skb for h2c rfk_pre_ntfy\n");
@@ -5152,41 +5160,53 @@ int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev,
 	skb_put(skb, len);
 	h2c = (struct rtw89_fw_h2c_rfk_pre_info *)skb->data;
 
-	h2c->mlo_mode = cpu_to_le32(rtwdev->mlo_dbcc_mode);
+	h2c->common.mlo_mode = cpu_to_le32(rtwdev->mlo_dbcc_mode);
 
 	BUILD_BUG_ON(NUM_OF_RTW89_FW_RFK_TBL > RTW89_RFK_CHS_NR);
 
 	for (tbl = 0; tbl < NUM_OF_RTW89_FW_RFK_TBL; tbl++) {
 		for (path = 0; path < NUM_OF_RTW89_FW_RFK_PATH; path++) {
-			h2c->dbcc.ch[path][tbl] = cpu_to_le32(rfk_mcc->ch[tbl]);
-			h2c->dbcc.band[path][tbl] = cpu_to_le32(rfk_mcc->band[tbl]);
+			h2c->common.dbcc.ch[path][tbl] =
+				cpu_to_le32(rfk_mcc->ch[tbl]);
+			h2c->common.dbcc.band[path][tbl] =
+				cpu_to_le32(rfk_mcc->band[tbl]);
 		}
 	}
 
 	for (path = 0; path < NUM_OF_RTW89_FW_RFK_PATH; path++) {
-		h2c->tbl.cur_ch[path] = cpu_to_le32(rfk_mcc->ch[tbl_sel]);
-		h2c->tbl.cur_band[path] = cpu_to_le32(rfk_mcc->band[tbl_sel]);
+		h2c->common.tbl.cur_ch[path] = cpu_to_le32(rfk_mcc->ch[tbl_sel]);
+		h2c->common.tbl.cur_band[path] = cpu_to_le32(rfk_mcc->band[tbl_sel]);
 	}
 
-	h2c->phy_idx = cpu_to_le32(phy_idx);
-	h2c->cur_band = cpu_to_le32(rfk_mcc->band[tbl_sel]);
-	h2c->cur_bw = cpu_to_le32(rfk_mcc->bw[tbl_sel]);
-	h2c->cur_center_ch = cpu_to_le32(rfk_mcc->ch[tbl_sel]);
-
-	val32 = rtw89_phy_read32_mask(rtwdev, R_COEF_SEL, B_COEF_SEL_IQC_V1);
-	h2c->ktbl_sel0 = cpu_to_le32(val32);
-	val32 = rtw89_phy_read32_mask(rtwdev, R_COEF_SEL_C1, B_COEF_SEL_IQC_V1);
-	h2c->ktbl_sel1 = cpu_to_le32(val32);
-	val32 = rtw89_read_rf(rtwdev, RF_PATH_A, RR_CFGCH, RFREG_MASK);
-	h2c->rfmod0 = cpu_to_le32(val32);
-	val32 = rtw89_read_rf(rtwdev, RF_PATH_B, RR_CFGCH, RFREG_MASK);
-	h2c->rfmod1 = cpu_to_le32(val32);
+	h2c->common.phy_idx = cpu_to_le32(phy_idx);
 
-	if (rtw89_is_mlo_1_1(rtwdev))
-		h2c->mlo_1_1 = cpu_to_le32(1);
+	if (ver == 0) { /* RFK_PRE_NOTIFY_V0 */
+		h2c_v0 = (struct rtw89_fw_h2c_rfk_pre_info_v0 *)skb->data;
+
+		h2c_v0->cur_band = cpu_to_le32(rfk_mcc->band[tbl_sel]);
+		h2c_v0->cur_bw = cpu_to_le32(rfk_mcc->bw[tbl_sel]);
+		h2c_v0->cur_center_ch = cpu_to_le32(rfk_mcc->ch[tbl_sel]);
+
+		val32 = rtw89_phy_read32_mask(rtwdev, R_COEF_SEL, B_COEF_SEL_IQC_V1);
+		h2c_v0->ktbl_sel0 = cpu_to_le32(val32);
+		val32 = rtw89_phy_read32_mask(rtwdev, R_COEF_SEL_C1, B_COEF_SEL_IQC_V1);
+		h2c_v0->ktbl_sel1 = cpu_to_le32(val32);
+		val32 = rtw89_read_rf(rtwdev, RF_PATH_A, RR_CFGCH, RFREG_MASK);
+		h2c_v0->rfmod0 = cpu_to_le32(val32);
+		val32 = rtw89_read_rf(rtwdev, RF_PATH_B, RR_CFGCH, RFREG_MASK);
+		h2c_v0->rfmod1 = cpu_to_le32(val32);
 
-	h2c->rfe_type = cpu_to_le32(rtwdev->efuse.rfe_type);
+		if (rtw89_is_mlo_1_1(rtwdev))
+			h2c_v0->mlo_1_1 = cpu_to_le32(1);
 
+		h2c_v0->rfe_type = cpu_to_le32(rtwdev->efuse.rfe_type);
+
+		goto done;
+	}
+
+	if (rtw89_is_mlo_1_1(rtwdev))
+		h2c->mlo_1_1 = cpu_to_le32(1);
+done:
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
 			      H2C_CAT_OUTSRC, H2C_CL_OUTSRC_RF_FW_RFK,
 			      H2C_FUNC_RFK_PRE_NOTIFY, 0, 0,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 7d48383c6244..dccda3a12616 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4106,7 +4106,7 @@ struct rtw89_fw_h2c_rf_get_mccch {
 #define NUM_OF_RTW89_FW_RFK_PATH 2
 #define NUM_OF_RTW89_FW_RFK_TBL 3
 
-struct rtw89_fw_h2c_rfk_pre_info {
+struct rtw89_fw_h2c_rfk_pre_info_common {
 	struct {
 		__le32 ch[NUM_OF_RTW89_FW_RFK_PATH][NUM_OF_RTW89_FW_RFK_TBL];
 		__le32 band[NUM_OF_RTW89_FW_RFK_PATH][NUM_OF_RTW89_FW_RFK_TBL];
@@ -4119,6 +4119,11 @@ struct rtw89_fw_h2c_rfk_pre_info {
 	} __packed tbl;
 
 	__le32 phy_idx;
+} __packed;
+
+struct rtw89_fw_h2c_rfk_pre_info_v0 {
+	struct rtw89_fw_h2c_rfk_pre_info_common common;
+
 	__le32 cur_band;
 	__le32 cur_bw;
 	__le32 cur_center_ch;
@@ -4138,6 +4143,11 @@ struct rtw89_fw_h2c_rfk_pre_info {
 	} __packed mlo;
 } __packed;
 
+struct rtw89_fw_h2c_rfk_pre_info {
+	struct rtw89_fw_h2c_rfk_pre_info_common common;
+	__le32 mlo_1_1;
+} __packed;
+
 struct rtw89_h2c_rf_tssi {
 	__le16 len;
 	u8 phy;
-- 
cgit v1.3-3-g829e


From 6ca6b918f280d3f1724c4494b8a04d81727629e1 Mon Sep 17 00:00:00 2001
From: Po-Hao Huang <phhuang@realtek.com>
Date: Wed, 31 Jul 2024 15:05:03 +0800
Subject: wifi: rtw89: 8922a: Add new fields for scan offload H2C command

Update scan offload H2C format to fit firmware version 35.21.
The new fields indicate lengths of variable length members, so
when driver and firmware are using mismatch version, FW could
handle the parsing better.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240731070506.46100-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |  1 +
 drivers/net/wireless/realtek/rtw89/fw.c       | 22 +++++++++++++++++++---
 drivers/net/wireless/realtek/rtw89/fw.h       |  7 ++++++-
 drivers/net/wireless/realtek/rtw89/rtw8922a.c |  4 ++--
 4 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index fec28f743eae..7a3a31dfbab0 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4367,6 +4367,7 @@ enum rtw89_fw_feature {
 	RTW89_FW_FEATURE_NO_LPS_PG,
 	RTW89_FW_FEATURE_BEACON_FILTER,
 	RTW89_FW_FEATURE_MACID_PAUSE_SLEEP,
+	RTW89_FW_FEATURE_SCAN_OFFLOAD_BE_V0,
 	RTW89_FW_FEATURE_WOW_REASON_V1,
 	RTW89_FW_FEATURE_RFK_PRE_NOTIFY_V0,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index fcbc7de48ddd..4c0a1aed6efd 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -683,6 +683,7 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = {
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 34, 30, 0, CRASH_TRIGGER),
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 34, 11, 0, MACID_PAUSE_SLEEP),
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 34, 35, 0, SCAN_OFFLOAD),
+	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 21, 0, SCAN_OFFLOAD_BE_V0),
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 35, 12, 0, BEACON_FILTER),
 	__CFG_FW_FEAT(RTL8922A, ge, 0, 35, 22, 0, WOW_REASON_V1),
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 31, 0, RFK_PRE_NOTIFY_V0),
@@ -4907,6 +4908,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 	u8 macc_role_size = sizeof(*macc_role) * option->num_macc_role;
 	u8 opch_size = sizeof(*opch) * option->num_opch;
 	u8 probe_id[NUM_NL80211_BANDS];
+	u8 cfg_len = sizeof(*h2c);
 	unsigned int cond;
 	void *ptr;
 	int ret;
@@ -4915,7 +4917,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 
 	rtw89_scan_get_6g_disabled_chan(rtwdev, option);
 
-	len = sizeof(*h2c) + macc_role_size + opch_size;
+	len = cfg_len + macc_role_size + opch_size;
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
 		rtw89_err(rtwdev, "failed to alloc skb for h2c scan offload\n");
@@ -4980,10 +4982,24 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 			  le32_encode_bits(RTW89_HW_RATE_OFDM6,
 					   RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_6GHZ);
 	}
-	ptr += sizeof(*h2c);
+
+	if (RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD_BE_V0, &rtwdev->fw)) {
+		cfg_len = offsetofend(typeof(*h2c), w8);
+		goto flex_member;
+	}
+
+	h2c->w9 = le32_encode_bits(sizeof(*h2c) / sizeof(h2c->w0),
+				   RTW89_H2C_SCANOFLD_BE_W9_SIZE_CFG) |
+		  le32_encode_bits(sizeof(*macc_role) / sizeof(macc_role->w0),
+				   RTW89_H2C_SCANOFLD_BE_W9_SIZE_MACC) |
+		  le32_encode_bits(sizeof(*opch) / sizeof(opch->w0),
+				   RTW89_H2C_SCANOFLD_BE_W9_SIZE_OP);
+
+flex_member:
+	ptr += cfg_len;
 
 	for (i = 0; i < option->num_macc_role; i++) {
-		macc_role = (struct rtw89_h2c_scanofld_be_macc_role *)&h2c->role[i];
+		macc_role = ptr;
 		macc_role->w0 =
 			le32_encode_bits(0, RTW89_H2C_SCANOFLD_BE_MACC_ROLE_W0_BAND) |
 			le32_encode_bits(0, RTW89_H2C_SCANOFLD_BE_MACC_ROLE_W0_PORT) |
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index dccda3a12616..0b0c5b5c6bb9 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -2711,7 +2711,9 @@ struct rtw89_h2c_scanofld_be {
 	__le32 w6;
 	__le32 w7;
 	__le32 w8;
-	struct rtw89_h2c_scanofld_be_macc_role role[];
+	__le32 w9; /* Added after SCAN_OFFLOAD_BE_V1 */
+	/* struct rtw89_h2c_scanofld_be_macc_role (flexible number) */
+	/* struct rtw89_h2c_scanofld_be_opch (flexible number) */
 } __packed;
 
 #define RTW89_H2C_SCANOFLD_BE_W0_OP GENMASK(1, 0)
@@ -2742,6 +2744,9 @@ struct rtw89_h2c_scanofld_be {
 #define RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_2GHZ GENMASK(7, 0)
 #define RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_5GHZ GENMASK(15, 8)
 #define RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_6GHZ GENMASK(23, 16)
+#define RTW89_H2C_SCANOFLD_BE_W9_SIZE_CFG GENMASK(7, 0)
+#define RTW89_H2C_SCANOFLD_BE_W9_SIZE_MACC GENMASK(15, 8)
+#define RTW89_H2C_SCANOFLD_BE_W9_SIZE_OP GENMASK(23, 16)
 
 static inline void RTW89_SET_FWCMD_P2P_MACID(void *cmd, u32 val)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 8921a1b9e791..554b21e77e64 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -13,10 +13,10 @@
 #include "rtw8922a_rfk.h"
 #include "util.h"
 
-#define RTW8922A_FW_FORMAT_MAX 0
+#define RTW8922A_FW_FORMAT_MAX 1
 #define RTW8922A_FW_BASENAME "rtw89/rtw8922a_fw"
 #define RTW8922A_MODULE_FIRMWARE \
-	RTW8922A_FW_BASENAME ".bin"
+	RTW8922A_FW_BASENAME "-" __stringify(RTW8922A_FW_FORMAT_MAX) ".bin"
 
 #define HE_N_USER_MAX_8922A 4
 
-- 
cgit v1.3-3-g829e


From 7dd5d2514a8ea58f12096e888b0bd050d7eae20a Mon Sep 17 00:00:00 2001
From: Chih-Kang Chang <gary.chang@realtek.com>
Date: Wed, 31 Jul 2024 15:05:04 +0800
Subject: wifi: rtw89: avoid to add interface to list twice when SER

If SER L2 occurs during the WoWLAN resume flow, the add interface flow
is triggered by ieee80211_reconfig(). However, due to
rtw89_wow_resume() return failure, it will cause the add interface flow
to be executed again, resulting in a double add list and causing a kernel
panic. Therefore, we have added a check to prevent double adding of the
list.

list_add double add: new=ffff99d6992e2010, prev=ffff99d6992e2010, next=ffff99d695302628.
------------[ cut here ]------------
kernel BUG at lib/list_debug.c:37!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 0 PID: 9 Comm: kworker/0:1 Tainted: G        W  O       6.6.30-02659-gc18865c4dfbd #1 770df2933251a0e3c888ba69d1053a817a6376a7
Hardware name: HP Grunt/Grunt, BIOS Google_Grunt.11031.169.0 06/24/2021
Workqueue: events_freezable ieee80211_restart_work [mac80211]
RIP: 0010:__list_add_valid_or_report+0x5e/0xb0
Code: c7 74 18 48 39 ce 74 13 b0 01 59 5a 5e 5f 41 58 41 59 41 5a 5d e9 e2 d6 03 00 cc 48 c7 c7 8d 4f 17 83 48 89 c2 e8 02 c0 00 00 <0f> 0b 48 c7 c7 aa 8c 1c 83 e8 f4 bf 00 00 0f 0b 48 c7 c7 c8 bc 12
RSP: 0018:ffffa91b8007bc50 EFLAGS: 00010246
RAX: 0000000000000058 RBX: ffff99d6992e0900 RCX: a014d76c70ef3900
RDX: ffffa91b8007bae8 RSI: 00000000ffffdfff RDI: 0000000000000001
RBP: ffffa91b8007bc88 R08: 0000000000000000 R09: ffffa91b8007bae0
R10: 00000000ffffdfff R11: ffffffff83a79800 R12: ffff99d695302060
R13: ffff99d695300900 R14: ffff99d6992e1be0 R15: ffff99d6992e2010
FS:  0000000000000000(0000) GS:ffff99d6aac00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000078fbdba43480 CR3: 000000010e464000 CR4: 00000000001506f0
Call Trace:
 <TASK>
 ? __die_body+0x1f/0x70
 ? die+0x3d/0x60
 ? do_trap+0xa4/0x110
 ? __list_add_valid_or_report+0x5e/0xb0
 ? do_error_trap+0x6d/0x90
 ? __list_add_valid_or_report+0x5e/0xb0
 ? handle_invalid_op+0x30/0x40
 ? __list_add_valid_or_report+0x5e/0xb0
 ? exc_invalid_op+0x3c/0x50
 ? asm_exc_invalid_op+0x16/0x20
 ? __list_add_valid_or_report+0x5e/0xb0
 rtw89_ops_add_interface+0x309/0x310 [rtw89_core 7c32b1ee6854761c0321027c8a58c5160e41f48f]
 drv_add_interface+0x5c/0x130 [mac80211 83e989e6e616bd5b4b8a2b0a9f9352a2c385a3bc]
 ieee80211_reconfig+0x241/0x13d0 [mac80211 83e989e6e616bd5b4b8a2b0a9f9352a2c385a3bc]
 ? finish_wait+0x3e/0x90
 ? synchronize_rcu_expedited+0x174/0x260
 ? sync_rcu_exp_done_unlocked+0x50/0x50
 ? wake_bit_function+0x40/0x40
 ieee80211_restart_work+0xf0/0x140 [mac80211 83e989e6e616bd5b4b8a2b0a9f9352a2c385a3bc]
 process_scheduled_works+0x1e5/0x480
 worker_thread+0xea/0x1e0
 kthread+0xdb/0x110
 ? move_linked_works+0x90/0x90
 ? kthread_associate_blkcg+0xa0/0xa0
 ret_from_fork+0x3b/0x50
 ? kthread_associate_blkcg+0xa0/0xa0
 ret_from_fork_asm+0x11/0x20
 </TASK>
Modules linked in: dm_integrity async_xor xor async_tx lz4 lz4_compress zstd zstd_compress zram zsmalloc rfcomm cmac uinput algif_hash algif_skcipher af_alg btusb btrtl iio_trig_hrtimer industrialio_sw_trigger btmtk industrialio_configfs btbcm btintel uvcvideo videobuf2_vmalloc iio_trig_sysfs videobuf2_memops videobuf2_v4l2 videobuf2_common uvc snd_hda_codec_hdmi veth snd_hda_intel snd_intel_dspcfg acpi_als snd_hda_codec industrialio_triggered_buffer kfifo_buf snd_hwdep industrialio i2c_piix4 snd_hda_core designware_i2s ip6table_nat snd_soc_max98357a xt_MASQUERADE xt_cgroup snd_soc_acp_rt5682_mach fuse rtw89_8922ae(O) rtw89_8922a(O) rtw89_pci(O) rtw89_core(O) 8021q mac80211(O) bluetooth ecdh_generic ecc cfg80211 r8152 mii joydev
gsmi: Log Shutdown Reason 0x03
---[ end trace 0000000000000000 ]---

Signed-off-by: Chih-Kang Chang <gary.chang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240731070506.46100-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac80211.c |  4 +++-
 drivers/net/wireless/realtek/rtw89/util.h     | 18 ++++++++++++++++++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index ed7990a2827b..48ad0d0f76bf 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -126,7 +126,9 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 	rtwvif->rtwdev = rtwdev;
 	rtwvif->roc.state = RTW89_ROC_IDLE;
 	rtwvif->offchan = false;
-	list_add_tail(&rtwvif->list, &rtwdev->rtwvifs_list);
+	if (!rtw89_rtwvif_in_list(rtwdev, rtwvif))
+		list_add_tail(&rtwvif->list, &rtwdev->rtwvifs_list);
+
 	INIT_WORK(&rtwvif->update_beacon_work, rtw89_core_update_beacon_work);
 	INIT_DELAYED_WORK(&rtwvif->roc.roc_work, rtw89_roc_work);
 	rtw89_leave_ps_mode(rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/util.h b/drivers/net/wireless/realtek/rtw89/util.h
index e82e7df052d8..e669544cafd3 100644
--- a/drivers/net/wireless/realtek/rtw89/util.h
+++ b/drivers/net/wireless/realtek/rtw89/util.h
@@ -16,6 +16,24 @@
 #define rtw89_for_each_rtwvif(rtwdev, rtwvif)				       \
 	list_for_each_entry(rtwvif, &(rtwdev)->rtwvifs_list, list)
 
+/* Before adding rtwvif to list, we need to check if it already exist, beacase
+ * in some case such as SER L2 happen during WoWLAN flow, calling reconfig
+ * twice cause the list to be added twice.
+ */
+static inline bool rtw89_rtwvif_in_list(struct rtw89_dev *rtwdev,
+					struct rtw89_vif *new)
+{
+	struct rtw89_vif *rtwvif;
+
+	lockdep_assert_held(&rtwdev->mutex);
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif)
+		if (rtwvif == new)
+			return true;
+
+	return false;
+}
+
 /* The result of negative dividend and positive divisor is undefined, but it
  * should be one case of round-down or round-up. So, make it round-down if the
  * result is round-up.
-- 
cgit v1.3-3-g829e


From 50961f88612c2200170111cf8d11e591d354fe1a Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Wed, 31 Jul 2024 15:05:05 +0800
Subject: wifi: rtw89: add support for HW encryption in unicast management
 frames

Add hardware encryption support for unicast management frames for
8922AE and 8852CE. Other chips will continue to use software
encryption for unicast management frames.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240731070506.46100-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/cam.c       | 12 +++++++----
 drivers/net/wireless/realtek/rtw89/core.c      | 29 ++++++++++++++++----------
 drivers/net/wireless/realtek/rtw89/core.h      |  1 +
 drivers/net/wireless/realtek/rtw89/mac.c       |  7 +++++++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  |  1 +
 10 files changed, 40 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c
index 4557c6e035a9..4476fc7e53db 100644
--- a/drivers/net/wireless/realtek/rtw89/cam.c
+++ b/drivers/net/wireless/realtek/rtw89/cam.c
@@ -384,20 +384,24 @@ int rtw89_cam_sec_key_add(struct rtw89_dev *rtwdev,
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 		hw_key_type = RTW89_SEC_KEY_TYPE_CCMP128;
-		key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+		if (!chip->hw_mgmt_tx_encrypt)
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP_256:
 		hw_key_type = RTW89_SEC_KEY_TYPE_CCMP256;
-		key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+		if (!chip->hw_mgmt_tx_encrypt)
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
 		ext_key = true;
 		break;
 	case WLAN_CIPHER_SUITE_GCMP:
 		hw_key_type = RTW89_SEC_KEY_TYPE_GCMP128;
-		key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+		if (!chip->hw_mgmt_tx_encrypt)
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
 		break;
 	case WLAN_CIPHER_SUITE_GCMP_256:
 		hw_key_type = RTW89_SEC_KEY_TYPE_GCMP256;
-		key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+		if (!chip->hw_mgmt_tx_encrypt)
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
 		ext_key = true;
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 894b03d77a05..a71c1147d3ce 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -602,15 +602,28 @@ static u8 rtw89_core_tx_get_mac_id(struct rtw89_dev *rtwdev,
 	return rtwsta->mac_id;
 }
 
+static void rtw89_core_tx_update_llc_hdr(struct rtw89_dev *rtwdev,
+					 struct rtw89_tx_desc_info *desc_info,
+					 struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	__le16 fc = hdr->frame_control;
+
+	desc_info->hdr_llc_len = ieee80211_hdrlen(fc);
+	desc_info->hdr_llc_len >>= 1; /* in unit of 2 bytes */
+}
+
 static void
 rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev,
 			       struct rtw89_core_tx_request *tx_req)
 {
+	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct ieee80211_vif *vif = tx_req->vif;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv;
 	struct rtw89_tx_desc_info *desc_info = &tx_req->desc_info;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
 						       rtwvif->chanctx_idx);
+	struct sk_buff *skb = tx_req->skb;
 	u8 qsel, ch_dma;
 
 	qsel = desc_info->hiq ? RTW89_TX_QSEL_B0_HI : RTW89_TX_QSEL_B0_MGMT;
@@ -629,6 +642,11 @@ rtw89_core_tx_update_mgmt_info(struct rtw89_dev *rtwdev,
 	desc_info->dis_data_fb = true;
 	desc_info->data_rate = rtw89_core_get_mgmt_rate(rtwdev, tx_req, chan);
 
+	if (chip->hw_mgmt_tx_encrypt && IEEE80211_SKB_CB(skb)->control.hw_key) {
+		rtw89_core_tx_update_sec_key(rtwdev, tx_req);
+		rtw89_core_tx_update_llc_hdr(rtwdev, desc_info, skb);
+	}
+
 	rtw89_debug(rtwdev, RTW89_DBG_TXRX,
 		    "tx mgmt frame with rate 0x%x on channel %d (band %d, bw %d)\n",
 		    desc_info->data_rate, chan->channel, chan->band_type,
@@ -862,17 +880,6 @@ rtw89_core_tx_btc_spec_pkt_notify(struct rtw89_dev *rtwdev,
 	return PACKET_MAX;
 }
 
-static void rtw89_core_tx_update_llc_hdr(struct rtw89_dev *rtwdev,
-					 struct rtw89_tx_desc_info *desc_info,
-					 struct sk_buff *skb)
-{
-	struct ieee80211_hdr *hdr = (void *)skb->data;
-	__le16 fc = hdr->frame_control;
-
-	desc_info->hdr_llc_len = ieee80211_hdrlen(fc);
-	desc_info->hdr_llc_len >>= 1; /* in unit of 2 bytes */
-}
-
 static void
 rtw89_core_tx_wake(struct rtw89_dev *rtwdev,
 		   struct rtw89_core_tx_request *tx_req)
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 7a3a31dfbab0..ecef3b154f3e 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4183,6 +4183,7 @@ struct rtw89_chip_info {
 	bool ul_tb_waveform_ctrl;
 	bool ul_tb_pwr_diff;
 	bool hw_sec_hdr;
+	bool hw_mgmt_tx_encrypt;
 	u8 rf_path_num;
 	u8 tx_nss;
 	u8 rx_nss;
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 6c2cef134d9b..149fb1b16239 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -2032,11 +2032,16 @@ int rtw89_mac_resize_ple_rx_quota(struct rtw89_dev *rtwdev, bool wow)
 
 void rtw89_mac_hw_mgnt_sec(struct rtw89_dev *rtwdev, bool enable)
 {
+	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u32 msk32 = B_AX_UC_MGNT_DEC | B_AX_BMC_MGNT_DEC;
 
 	if (rtwdev->chip->chip_gen != RTW89_CHIP_AX)
 		return;
 
+	/* 8852C enable B_AX_UC_MGNT_DEC by default */
+	if (chip->chip_id == RTL8852C)
+		msk32 = B_AX_BMC_MGNT_DEC;
+
 	if (enable)
 		rtw89_write32_set(rtwdev, R_AX_SEC_ENG_CTRL, msk32);
 	else
@@ -2261,6 +2266,8 @@ static int sec_eng_init_ax(struct rtw89_dev *rtwdev)
 	/* init TX encryption */
 	val |= (B_AX_SEC_TX_ENC | B_AX_SEC_RX_DEC);
 	val |= (B_AX_MC_DEC | B_AX_BC_DEC);
+	if (chip->chip_id == RTL8852C)
+		val |= B_AX_UC_MGNT_DEC;
 	if (chip->chip_id == RTL8852A || chip->chip_id == RTL8852B ||
 	    chip->chip_id == RTL8851B)
 		val &= ~B_AX_TX_PARTIAL_MODE;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index cfaea0193d35..e6463035a7af 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2473,6 +2473,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
+	.hw_mgmt_tx_encrypt	= false,
 	.rf_path_num		= 1,
 	.tx_nss			= 1,
 	.rx_nss			= 1,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index ec9f7bc5c6d2..7ea388fa0657 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2188,6 +2188,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
+	.hw_mgmt_tx_encrypt	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 71c166202560..f26979b89cc9 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -828,6 +828,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
+	.hw_mgmt_tx_encrypt	= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 9aa2106a64b7..fb98ef9dbc54 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -761,6 +761,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
+	.hw_mgmt_tx_encrypt     = false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index e0c1cf8811a2..d9d7b3ff338a 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2969,6 +2969,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= true,
 	.hw_sec_hdr		= true,
+	.hw_mgmt_tx_encrypt	= true,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 554b21e77e64..6004a622d244 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2572,6 +2572,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= true,
+	.hw_mgmt_tx_encrypt	= true,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
-- 
cgit v1.3-3-g829e


From 89a4c16cbdc961f69a636685f6bedc18d3813d45 Mon Sep 17 00:00:00 2001
From: Dian-Syuan Yang <dian_syuan0116@realtek.com>
Date: Wed, 31 Jul 2024 15:05:06 +0800
Subject: wifi: rtw89: correct VHT TX rate on 20MHz connection

It may get wrong bitrate when connecting to AP set VHT 20MHz,
and thus we fix it to follow Wi-Fi spec.

Signed-off-by: Dian-Syuan Yang <dian_syuan0116@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240731070506.46100-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/phy.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 118d09b3eadd..aa4fc9115995 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -341,8 +341,11 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 
 		mode |= RTW89_RA_MODE_VHT;
 		csi_mode = RTW89_RA_RPT_MODE_VHT;
-		/* MCS9, MCS8, MCS7 */
-		ra_mask |= get_mcs_ra_mask(mcs_map, 9, 1);
+		/* MCS9 (non-20MHz), MCS8, MCS7 */
+		if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_20)
+			ra_mask |= get_mcs_ra_mask(mcs_map, 8, 1);
+		else
+			ra_mask |= get_mcs_ra_mask(mcs_map, 9, 1);
 		high_rate_masks = rtw89_ra_mask_vht_rates;
 		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXSTBC_MASK)
 			stbc_en = 1;
-- 
cgit v1.3-3-g829e


From 92da4ce847bc5d942ddfdb102dba92f4e2797a59 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 31 Jul 2024 14:02:40 -0700
Subject: wifi: ath9k: use devm for request_irq()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoids having to manually call free_irq(). Simplifies code slightly.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240731210243.7467-1-rosenp@gmail.com
---
 drivers/net/wireless/ath/ath9k/ahb.c | 7 ++-----
 drivers/net/wireless/ath/ath9k/pci.c | 9 +++------
 2 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ahb.c b/drivers/net/wireless/ath/ath9k/ahb.c
index 1a6697b6e3b4..29f67ded8fe2 100644
--- a/drivers/net/wireless/ath/ath9k/ahb.c
+++ b/drivers/net/wireless/ath/ath9k/ahb.c
@@ -118,7 +118,7 @@ static int ath_ahb_probe(struct platform_device *pdev)
 	sc->mem = mem;
 	sc->irq = irq;
 
-	ret = request_irq(irq, ath_isr, IRQF_SHARED, "ath9k", sc);
+	ret = devm_request_irq(&pdev->dev, irq, ath_isr, IRQF_SHARED, "ath9k", sc);
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq failed\n");
 		goto err_free_hw;
@@ -127,7 +127,7 @@ static int ath_ahb_probe(struct platform_device *pdev)
 	ret = ath9k_init_device(id->driver_data, sc, &ath_ahb_bus_ops);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to initialize device\n");
-		goto err_irq;
+		goto err_free_hw;
 	}
 
 	ah = sc->sc_ah;
@@ -137,8 +137,6 @@ static int ath_ahb_probe(struct platform_device *pdev)
 
 	return 0;
 
- err_irq:
-	free_irq(irq, sc);
  err_free_hw:
 	ieee80211_free_hw(hw);
 	return ret;
@@ -152,7 +150,6 @@ static void ath_ahb_remove(struct platform_device *pdev)
 		struct ath_softc *sc = hw->priv;
 
 		ath9k_deinit_device(sc);
-		free_irq(sc->irq, sc);
 		ieee80211_free_hw(sc->hw);
 	}
 }
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index 1ff53520f0a3..ccf73886199a 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -965,9 +965,9 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	if (!msi_enabled)
-		ret = request_irq(pdev->irq, ath_isr, IRQF_SHARED, "ath9k", sc);
+		ret = devm_request_irq(&pdev->dev, pdev->irq, ath_isr, IRQF_SHARED, "ath9k", sc);
 	else
-		ret = request_irq(pdev->irq, ath_isr, 0, "ath9k", sc);
+		ret = devm_request_irq(&pdev->dev, pdev->irq, ath_isr, 0, "ath9k", sc);
 
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq failed\n");
@@ -979,7 +979,7 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = ath9k_init_device(id->device, sc, &ath_pci_bus_ops);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize device\n");
-		goto err_init;
+		goto err_irq;
 	}
 
 	sc->sc_ah->msi_enabled = msi_enabled;
@@ -991,8 +991,6 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
-err_init:
-	free_irq(sc->irq, sc);
 err_irq:
 	ieee80211_free_hw(hw);
 	return ret;
@@ -1006,7 +1004,6 @@ static void ath_pci_remove(struct pci_dev *pdev)
 	if (!is_ath9k_unloaded)
 		sc->sc_ah->ah_flags |= AH_UNPLUGGED;
 	ath9k_deinit_device(sc);
-	free_irq(sc->irq, sc);
 	ieee80211_free_hw(sc->hw);
 }
 
-- 
cgit v1.3-3-g829e


From 8aabc03c7d226992b758a7bf5a53e05fc8a9ab01 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 31 Jul 2024 14:03:08 -0700
Subject: wifi: ath9k: use devm for gpio_request_one()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using devm_gpio_request_one() is simpler as then we don't need to call
gpio_free().

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240731210312.7622-1-rosenp@gmail.com
---
 drivers/net/wireless/ath/ath9k/hw.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 5982e0db45f9..04a4b9ea61c3 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -2732,7 +2732,7 @@ static void ath9k_hw_gpio_cfg_soc(struct ath_hw *ah, u32 gpio, bool out,
 	if (ah->caps.gpio_requested & BIT(gpio))
 		return;
 
-	err = gpio_request_one(gpio, out ? GPIOF_OUT_INIT_LOW : GPIOF_IN, label);
+	err = devm_gpio_request_one(ah->dev, gpio, out ? GPIOF_OUT_INIT_LOW : GPIOF_IN, label);
 	if (err) {
 		ath_err(ath9k_hw_common(ah), "request GPIO%d failed:%d\n",
 			gpio, err);
@@ -2801,10 +2801,8 @@ void ath9k_hw_gpio_free(struct ath_hw *ah, u32 gpio)
 
 	WARN_ON(gpio >= ah->caps.num_gpio_pins);
 
-	if (ah->caps.gpio_requested & BIT(gpio)) {
-		gpio_free(gpio);
+	if (ah->caps.gpio_requested & BIT(gpio))
 		ah->caps.gpio_requested &= ~BIT(gpio);
-	}
 }
 EXPORT_SYMBOL(ath9k_hw_gpio_free);
 
-- 
cgit v1.3-3-g829e


From f6ffe7f0184792c2f99aca6ae5b916683973d7d3 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Mon, 5 Aug 2024 13:02:22 +0200
Subject: wifi: ath9k: Remove error checks when creating debugfs entries
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We should not be checking the return values from debugfs creation at all: the
debugfs functions are designed to handle errors of previously called functions
and just transparently abort the creation of debugfs entries when debugfs is
disabled. If we check the return value and abort driver initialisation, we break
the driver if debugfs is disabled (such as when booting with debugfs=off).

Earlier versions of ath9k accidentally did the right thing by checking the
return value, but only for NULL, not for IS_ERR(). This was "fixed" by the two
commits referenced below, breaking ath9k with debugfs=off starting from the 6.6
kernel (as reported in the Bugzilla linked below).

Restore functionality by just getting rid of the return value check entirely.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=219122
Fixes: 1e4134610d93 ("wifi: ath9k: use IS_ERR() with debugfs_create_dir()")
Fixes: 6edb4ba6fb5b ("wifi: ath9k: fix parameter check in ath9k_init_debug()")
Reported-by: Daniel Tobias <dan.g.tob@gmail.com>
Tested-by: Daniel Tobias <dan.g.tob@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240805110225.19690-1-toke@toke.dk
---
 drivers/net/wireless/ath/ath9k/debug.c         | 2 --
 drivers/net/wireless/ath/ath9k/htc_drv_debug.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index 886a102e5b02..51abc470125b 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -1380,8 +1380,6 @@ int ath9k_init_debug(struct ath_hw *ah)
 
 	sc->debug.debugfs_phy = debugfs_create_dir("ath9k",
 						   sc->hw->wiphy->debugfsdir);
-	if (IS_ERR(sc->debug.debugfs_phy))
-		return -ENOMEM;
 
 #ifdef CONFIG_ATH_DEBUG
 	debugfs_create_file("debug", 0600, sc->debug.debugfs_phy,
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
index f7c6d9bc9311..9437d69877cc 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
@@ -486,8 +486,6 @@ int ath9k_htc_init_debug(struct ath_hw *ah)
 
 	priv->debug.debugfs_phy = debugfs_create_dir(KBUILD_MODNAME,
 					     priv->hw->wiphy->debugfsdir);
-	if (IS_ERR(priv->debug.debugfs_phy))
-		return -ENOMEM;
 
 	ath9k_cmn_spectral_init_debug(&priv->spec_priv, priv->debug.debugfs_phy);
 
-- 
cgit v1.3-3-g829e


From 8be12629b428084be2610041d61b132074d334f6 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Tue, 9 Jul 2024 11:28:17 +0530
Subject: wifi: ath12k: restore ASPM for supported hardwares only

During PCI based hardware device start up, ASPM is disabled for all. And
once firmware is ready, it is restored back. However, not all hardwares
(for example QCN9274) supports ASPM. Hence there is a need to conditionally
restore ASPM back. Or else, for such hardwares, issue can be seen during
sending and receiving packets.

Introduce a new hardware param supports_aspm which identifies whether a
given hardware supports ASPM or not and then accordingly restore it.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240709055817.3371406-1-quic_adisi@quicinc.com
---
 drivers/net/wireless/ath/ath12k/hw.c  | 6 ++++++
 drivers/net/wireless/ath/ath12k/hw.h  | 1 +
 drivers/net/wireless/ath/ath12k/pci.c | 3 ++-
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 2e11ea763574..76c0e07a88de 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -924,6 +924,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 
 		.acpi_guid = NULL,
 		.supports_dynamic_smps_6ghz = true,
+
+		.supports_aspm = false,
 	},
 	{
 		.name = "wcn7850 hw2.0",
@@ -1000,6 +1002,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 
 		.acpi_guid = &wcn7850_uuid,
 		.supports_dynamic_smps_6ghz = false,
+
+		.supports_aspm = true,
 	},
 	{
 		.name = "qcn9274 hw2.0",
@@ -1072,6 +1076,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 
 		.acpi_guid = NULL,
 		.supports_dynamic_smps_6ghz = true,
+
+		.supports_aspm = false,
 	},
 };
 
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index e792eb6b249b..4cfbb240bbf4 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -187,6 +187,7 @@ struct ath12k_hw_params {
 	bool tcl_ring_retry:1;
 	bool reoq_lut_support:1;
 	bool supports_shadow_regs:1;
+	bool supports_aspm:1;
 
 	u32 num_tcl_banks;
 	u32 max_tx_ring;
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 876c029f58f6..ff2199f7754c 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -953,7 +953,8 @@ static void ath12k_pci_update_qrtr_node_id(struct ath12k_base *ab)
 
 static void ath12k_pci_aspm_restore(struct ath12k_pci *ab_pci)
 {
-	if (test_and_clear_bit(ATH12K_PCI_ASPM_RESTORE, &ab_pci->flags))
+	if (ab_pci->ab->hw_params->supports_aspm &&
+	    test_and_clear_bit(ATH12K_PCI_ASPM_RESTORE, &ab_pci->flags))
 		pcie_capability_clear_and_set_word(ab_pci->pdev, PCI_EXP_LNKCTL,
 						   PCI_EXP_LNKCTL_ASPMC,
 						   ab_pci->link_ctl &
-- 
cgit v1.3-3-g829e


From 59529c982f85047650fd473db903b23006a796c6 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 1 Apr 2024 00:02:31 +0530
Subject: wifi: ath12k: fix BSS chan info request WMI command

Currently, the firmware returns incorrect pdev_id information in
WMI_PDEV_BSS_CHAN_INFO_EVENTID, leading to incorrect filling of
the pdev's survey information.

To prevent this issue, when requesting BSS channel information
through WMI_PDEV_BSS_CHAN_INFO_REQUEST_CMDID, firmware expects
pdev_id as one of the arguments in this WMI command.

Add pdev_id to the struct wmi_pdev_bss_chan_info_req_cmd and fill it
during ath12k_wmi_pdev_bss_chan_info_request(). This resolves the
issue of sending the correct pdev_id in WMI_PDEV_BSS_CHAN_INFO_EVENTID.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240331183232.2158756-2-quic_kathirve@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.c | 1 +
 drivers/net/wireless/ath/ath12k/wmi.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 9f6be557365e..a76413320dbf 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1538,6 +1538,7 @@ int ath12k_wmi_pdev_bss_chan_info_request(struct ath12k *ar,
 	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_PDEV_BSS_CHAN_INFO_REQUEST,
 						 sizeof(*cmd));
 	cmd->req_type = cpu_to_le32(type);
+	cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id);
 
 	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
 		   "WMI bss chan info req type %d\n", type);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index f1f52175a52b..9f4c2f026b4c 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -3121,6 +3121,7 @@ struct wmi_pdev_bss_chan_info_req_cmd {
 	__le32 tlv_header;
 	/* ref wmi_bss_chan_info_req_type */
 	__le32 req_type;
+	__le32 pdev_id;
 } __packed;
 
 struct wmi_ap_ps_peer_cmd {
-- 
cgit v1.3-3-g829e


From dd98d54db29fb553839f43ade5f547baa93392c8 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 1 Apr 2024 00:02:32 +0530
Subject: wifi: ath12k: match WMI BSS chan info structure with firmware
 definition

struct wmi_pdev_bss_chan_info_event is not similar to the firmware
struct definition, this will cause some random failures.

Fix by matching the struct wmi_pdev_bss_chan_info_event with the
firmware structure definition.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: Karthikeyan Kathirvel <quic_kathirve@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240331183232.2158756-3-quic_kathirve@quicinc.com
---
 drivers/net/wireless/ath/ath12k/wmi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 9f4c2f026b4c..6a913f9b8315 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -4086,7 +4086,6 @@ struct wmi_vdev_stopped_event {
 } __packed;
 
 struct wmi_pdev_bss_chan_info_event {
-	__le32 pdev_id;
 	__le32 freq;	/* Units in MHz */
 	__le32 noise_floor;	/* units are dBm */
 	/* rx clear - how often the channel was unused */
@@ -4104,6 +4103,7 @@ struct wmi_pdev_bss_chan_info_event {
 	/*rx_cycle cnt for my bss in 64bits format */
 	__le32 rx_bss_cycle_count_low;
 	__le32 rx_bss_cycle_count_high;
+	__le32 pdev_id;
 } __packed;
 
 #define WMI_VDEV_INSTALL_KEY_COMPL_STATUS_SUCCESS 0
-- 
cgit v1.3-3-g829e


From a66de2d0f22b1740f3f9777776ad98c4bee62dff Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Wed, 10 Jul 2024 10:18:19 +0800
Subject: wifi: ath12k: fix invalid AMPDU factor calculation in
 ath12k_peer_assoc_h_he()

Currently ampdu_factor is wrongly calculated in ath12k_peer_assoc_h_he(), fix it.

This is found during code review.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240710021819.87216-1-quic_bqiang@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 8106297f0bc1..a7b86e6a2655 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -2196,9 +2196,8 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar,
 	 * request, then use MAX_AMPDU_LEN_FACTOR as 16 to calculate max_ampdu
 	 * length.
 	 */
-	ampdu_factor = (he_cap->he_cap_elem.mac_cap_info[3] &
-			IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) >>
-			IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK;
+	ampdu_factor = u8_get_bits(he_cap->he_cap_elem.mac_cap_info[3],
+				   IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK);
 
 	if (ampdu_factor) {
 		if (sta->deflink.vht_cap.vht_supported)
-- 
cgit v1.3-3-g829e


From 90c36325c796cc7111329607a649c34f4979c78e Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:06 +0800
Subject: tcp: rstreason: introduce SK_RST_REASON_TCP_ABORT_ON_CLOSE for active
 reset

Introducing a new type TCP_ABORT_ON_CLOSE for tcp reset reason to handle
the case where more data is unread in closing phase.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rstreason.h | 6 ++++++
 net/ipv4/tcp.c          | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index 2575c85d7f7a..fa6bfd0d7d69 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -17,6 +17,7 @@
 	FN(TCP_ABORT_ON_DATA)		\
 	FN(TCP_TIMEWAIT_SOCKET)		\
 	FN(INVALID_SYN)			\
+	FN(TCP_ABORT_ON_CLOSE)		\
 	FN(MPTCP_RST_EUNSPEC)		\
 	FN(MPTCP_RST_EMPTCP)		\
 	FN(MPTCP_RST_ERESOURCE)		\
@@ -84,6 +85,11 @@ enum sk_rst_reason {
 	 * an error, send a reset"
 	 */
 	SK_RST_REASON_INVALID_SYN,
+	/**
+	 * @SK_RST_REASON_TCP_ABORT_ON_CLOSE: abort on close
+	 * corresponding to LINUX_MIB_TCPABORTONCLOSE
+	 */
+	SK_RST_REASON_TCP_ABORT_ON_CLOSE,
 
 	/* Copy from include/uapi/linux/mptcp.h.
 	 * These reset fields will not be changed since they adhere to
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e03a342c9162..2e010add0317 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2833,7 +2833,7 @@ void __tcp_close(struct sock *sk, long timeout)
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
 		tcp_set_state(sk, TCP_CLOSE);
 		tcp_send_active_reset(sk, sk->sk_allocation,
-				      SK_RST_REASON_NOT_SPECIFIED);
+				      SK_RST_REASON_TCP_ABORT_ON_CLOSE);
 	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
 		/* Check zero linger _after_ checking for unread data. */
 		sk->sk_prot->disconnect(sk, 0);
-- 
cgit v1.3-3-g829e


From edc92b48abc5b21c98eca5d05b98a560d7df2e4d Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:07 +0800
Subject: tcp: rstreason: introduce SK_RST_REASON_TCP_ABORT_ON_LINGER for
 active reset

Introducing a new type TCP_ABORT_ON_LINGER for tcp reset reason to handle
negative linger value case.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rstreason.h | 6 ++++++
 net/ipv4/tcp.c          | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index fa6bfd0d7d69..fbbaeb969e6a 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -18,6 +18,7 @@
 	FN(TCP_TIMEWAIT_SOCKET)		\
 	FN(INVALID_SYN)			\
 	FN(TCP_ABORT_ON_CLOSE)		\
+	FN(TCP_ABORT_ON_LINGER)		\
 	FN(MPTCP_RST_EUNSPEC)		\
 	FN(MPTCP_RST_EMPTCP)		\
 	FN(MPTCP_RST_ERESOURCE)		\
@@ -90,6 +91,11 @@ enum sk_rst_reason {
 	 * corresponding to LINUX_MIB_TCPABORTONCLOSE
 	 */
 	SK_RST_REASON_TCP_ABORT_ON_CLOSE,
+	/**
+	 * @SK_RST_REASON_TCP_ABORT_ON_LINGER: abort on linger
+	 * corresponding to LINUX_MIB_TCPABORTONLINGER
+	 */
+	SK_RST_REASON_TCP_ABORT_ON_LINGER,
 
 	/* Copy from include/uapi/linux/mptcp.h.
 	 * These reset fields will not be changed since they adhere to
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2e010add0317..5b0f1d1fc697 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2908,7 +2908,7 @@ adjudge_to_death:
 		if (READ_ONCE(tp->linger2) < 0) {
 			tcp_set_state(sk, TCP_CLOSE);
 			tcp_send_active_reset(sk, GFP_ATOMIC,
-					      SK_RST_REASON_NOT_SPECIFIED);
+					      SK_RST_REASON_TCP_ABORT_ON_LINGER);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONLINGER);
 		} else {
-- 
cgit v1.3-3-g829e


From 8407994f0c3594eb3854e3799af86224f4a8e6e6 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:08 +0800
Subject: tcp: rstreason: introduce SK_RST_REASON_TCP_ABORT_ON_MEMORY for
 active reset

Introducing a new type TCP_ABORT_ON_MEMORY for tcp reset reason to handle
out of memory case.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rstreason.h | 6 ++++++
 net/ipv4/tcp.c          | 2 +-
 net/ipv4/tcp_timer.c    | 2 +-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index fbbaeb969e6a..eef658da8952 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -19,6 +19,7 @@
 	FN(INVALID_SYN)			\
 	FN(TCP_ABORT_ON_CLOSE)		\
 	FN(TCP_ABORT_ON_LINGER)		\
+	FN(TCP_ABORT_ON_MEMORY)		\
 	FN(MPTCP_RST_EUNSPEC)		\
 	FN(MPTCP_RST_EMPTCP)		\
 	FN(MPTCP_RST_ERESOURCE)		\
@@ -96,6 +97,11 @@ enum sk_rst_reason {
 	 * corresponding to LINUX_MIB_TCPABORTONLINGER
 	 */
 	SK_RST_REASON_TCP_ABORT_ON_LINGER,
+	/**
+	 * @SK_RST_REASON_TCP_ABORT_ON_MEMORY: abort on memory
+	 * corresponding to LINUX_MIB_TCPABORTONMEMORY
+	 */
+	SK_RST_REASON_TCP_ABORT_ON_MEMORY,
 
 	/* Copy from include/uapi/linux/mptcp.h.
 	 * These reset fields will not be changed since they adhere to
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5b0f1d1fc697..fd928c447ce8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2927,7 +2927,7 @@ adjudge_to_death:
 		if (tcp_check_oom(sk, 0)) {
 			tcp_set_state(sk, TCP_CLOSE);
 			tcp_send_active_reset(sk, GFP_ATOMIC,
-					      SK_RST_REASON_NOT_SPECIFIED);
+					      SK_RST_REASON_TCP_ABORT_ON_MEMORY);
 			__NET_INC_STATS(sock_net(sk),
 					LINUX_MIB_TCPABORTONMEMORY);
 		} else if (!check_net(sock_net(sk))) {
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4d40615dc8fc..0fba4a4fb988 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -125,7 +125,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 			do_reset = true;
 		if (do_reset)
 			tcp_send_active_reset(sk, GFP_ATOMIC,
-					      SK_RST_REASON_NOT_SPECIFIED);
+					      SK_RST_REASON_TCP_ABORT_ON_MEMORY);
 		tcp_done(sk);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
 		return 1;
-- 
cgit v1.3-3-g829e


From edefba66d929eb2d023df93a0a8175a4ffe82684 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:09 +0800
Subject: tcp: rstreason: introduce SK_RST_REASON_TCP_STATE for active reset

Introducing a new type TCP_STATE to handle some reset conditions
appearing in RFC 793 due to its socket state. Actually, we can look
into RFC 9293 which has no discrepancy about this part.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rstreason.h |  6 ++++++
 net/ipv4/tcp.c          | 10 ++++++----
 net/ipv4/tcp_timer.c    |  2 +-
 3 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index eef658da8952..bbf20d0bbde7 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -20,6 +20,7 @@
 	FN(TCP_ABORT_ON_CLOSE)		\
 	FN(TCP_ABORT_ON_LINGER)		\
 	FN(TCP_ABORT_ON_MEMORY)		\
+	FN(TCP_STATE)			\
 	FN(MPTCP_RST_EUNSPEC)		\
 	FN(MPTCP_RST_EMPTCP)		\
 	FN(MPTCP_RST_ERESOURCE)		\
@@ -102,6 +103,11 @@ enum sk_rst_reason {
 	 * corresponding to LINUX_MIB_TCPABORTONMEMORY
 	 */
 	SK_RST_REASON_TCP_ABORT_ON_MEMORY,
+	/**
+	 * @SK_RST_REASON_TCP_STATE: abort on tcp state
+	 * Please see RFC 9293 for all possible reset conditions
+	 */
+	SK_RST_REASON_TCP_STATE,
 
 	/* Copy from include/uapi/linux/mptcp.h.
 	 * These reset fields will not be changed since they adhere to
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fd928c447ce8..24777e48bcc8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3025,9 +3025,11 @@ int tcp_disconnect(struct sock *sk, int flags)
 		inet_csk_listen_stop(sk);
 	} else if (unlikely(tp->repair)) {
 		WRITE_ONCE(sk->sk_err, ECONNABORTED);
-	} else if (tcp_need_reset(old_state) ||
-		   (tp->snd_nxt != tp->write_seq &&
-		    (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) {
+	} else if (tcp_need_reset(old_state)) {
+		tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE);
+		WRITE_ONCE(sk->sk_err, ECONNRESET);
+	} else if (tp->snd_nxt != tp->write_seq &&
+		   (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
 		/* The last check adjusts for discrepancy of Linux wrt. RFC
 		 * states
 		 */
@@ -4649,7 +4651,7 @@ int tcp_abort(struct sock *sk, int err)
 	if (!sock_flag(sk, SOCK_DEAD)) {
 		if (tcp_need_reset(sk->sk_state))
 			tcp_send_active_reset(sk, GFP_ATOMIC,
-					      SK_RST_REASON_NOT_SPECIFIED);
+					      SK_RST_REASON_TCP_STATE);
 		tcp_done_with_error(sk, err);
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 0fba4a4fb988..3910f6d8614e 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -779,7 +779,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 				goto out;
 			}
 		}
-		tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED);
+		tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE);
 		goto death;
 	}
 
-- 
cgit v1.3-3-g829e


From 0a399892a596055c8f069a17b4775fe5ab66d32a Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:10 +0800
Subject: tcp: rstreason: introduce SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT for
 active reset

Introducing this to show the users the reason of keepalive timeout.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rstreason.h | 7 +++++++
 net/ipv4/tcp_timer.c    | 2 +-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index bbf20d0bbde7..9c0c46df0e73 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -21,6 +21,7 @@
 	FN(TCP_ABORT_ON_LINGER)		\
 	FN(TCP_ABORT_ON_MEMORY)		\
 	FN(TCP_STATE)			\
+	FN(TCP_KEEPALIVE_TIMEOUT)	\
 	FN(MPTCP_RST_EUNSPEC)		\
 	FN(MPTCP_RST_EMPTCP)		\
 	FN(MPTCP_RST_ERESOURCE)		\
@@ -108,6 +109,12 @@ enum sk_rst_reason {
 	 * Please see RFC 9293 for all possible reset conditions
 	 */
 	SK_RST_REASON_TCP_STATE,
+	/**
+	 * @SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT: time to timeout
+	 * When we have already run out of all the chances, which means
+	 * keepalive timeout, we have to reset the connection
+	 */
+	SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT,
 
 	/* Copy from include/uapi/linux/mptcp.h.
 	 * These reset fields will not be changed since they adhere to
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3910f6d8614e..86169127e4d1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -807,7 +807,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 		    (user_timeout == 0 &&
 		    icsk->icsk_probes_out >= keepalive_probes(tp))) {
 			tcp_send_active_reset(sk, GFP_ATOMIC,
-					      SK_RST_REASON_NOT_SPECIFIED);
+					      SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT);
 			tcp_write_err(sk);
 			goto out;
 		}
-- 
cgit v1.3-3-g829e


From c026c6562f86b24dd2dfef501fb1e64cc3884a79 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:11 +0800
Subject: tcp: rstreason: introduce SK_RST_REASON_TCP_DISCONNECT_WITH_DATA for
 active reset

When user tries to disconnect a socket and there are more data written
into tcp write queue, we should tell users about this reset reason.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/rstreason.h | 8 ++++++++
 net/ipv4/tcp.c          | 3 ++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/net/rstreason.h b/include/net/rstreason.h
index 9c0c46df0e73..69cb2e52b7da 100644
--- a/include/net/rstreason.h
+++ b/include/net/rstreason.h
@@ -22,6 +22,7 @@
 	FN(TCP_ABORT_ON_MEMORY)		\
 	FN(TCP_STATE)			\
 	FN(TCP_KEEPALIVE_TIMEOUT)	\
+	FN(TCP_DISCONNECT_WITH_DATA)	\
 	FN(MPTCP_RST_EUNSPEC)		\
 	FN(MPTCP_RST_EMPTCP)		\
 	FN(MPTCP_RST_ERESOURCE)		\
@@ -115,6 +116,13 @@ enum sk_rst_reason {
 	 * keepalive timeout, we have to reset the connection
 	 */
 	SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT,
+	/**
+	 * @SK_RST_REASON_TCP_DISCONNECT_WITH_DATA: disconnect when write
+	 * queue is not empty
+	 * It means user has written data into the write queue when doing
+	 * disconnecting, so we have to send an RST.
+	 */
+	SK_RST_REASON_TCP_DISCONNECT_WITH_DATA,
 
 	/* Copy from include/uapi/linux/mptcp.h.
 	 * These reset fields will not be changed since they adhere to
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 24777e48bcc8..8514257f4ecd 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3033,7 +3033,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 		/* The last check adjusts for discrepancy of Linux wrt. RFC
 		 * states
 		 */
-		tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED);
+		tcp_send_active_reset(sk, gfp_any(),
+				      SK_RST_REASON_TCP_DISCONNECT_WITH_DATA);
 		WRITE_ONCE(sk->sk_err, ECONNRESET);
 	} else if (old_state == TCP_SYN_SENT)
 		WRITE_ONCE(sk->sk_err, ECONNRESET);
-- 
cgit v1.3-3-g829e


From ba0ca286c919508ac32d036509b082b3968c0bb2 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 2 Aug 2024 18:21:12 +0800
Subject: tcp: rstreason: let it work finally in tcp_send_active_reset()

Now it's time to let it work by using the 'reason' parameter in
the trace world :)

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 16c48df8df4c..cdd0def14427 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3649,7 +3649,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority,
 	/* skb of trace_tcp_send_reset() keeps the skb that caused RST,
 	 * skb here is different to the troublesome skb, so use NULL
 	 */
-	trace_tcp_send_reset(sk, NULL, SK_RST_REASON_NOT_SPECIFIED);
+	trace_tcp_send_reset(sk, NULL, reason);
 }
 
 /* Send a crossed SYN-ACK during socket establishment.
-- 
cgit v1.3-3-g829e


From 4ab9f870a6335af27507d1f3bfb29635d956af48 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 4 Aug 2024 08:32:44 +0200
Subject: wifi: b43: Constify struct lpphy_tx_gain_table_entry
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'struct lpphy_tx_gain_table_entry' are not modified in this driver.

Constifying this structure moves some data to a read-only section, so
increase overall security.

On a x86_64, with allmodconfig:
Before:
======
   text	   data	    bss	    dec	    hex	filename
  16481	   6232	      0	  22713	   58b9	drivers/net/wireless/broadcom/b43/tables_lpphy.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
  22305	    395	      0	  22700	   58ac	drivers/net/wireless/broadcom/b43/tables_lpphy.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-By: Michael Büsch <m@bues.ch>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/e33bc9e6dff4a5b6cd8d0ab5399aa1abac5bef9d.1722753127.git.christophe.jaillet@wanadoo.fr
---
 drivers/net/wireless/broadcom/b43/tables_lpphy.c | 20 ++++++++++----------
 drivers/net/wireless/broadcom/b43/tables_lpphy.h |  2 +-
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/broadcom/b43/tables_lpphy.c b/drivers/net/wireless/broadcom/b43/tables_lpphy.c
index 71a7cd8dc787..fb70a1e3544b 100644
--- a/drivers/net/wireless/broadcom/b43/tables_lpphy.c
+++ b/drivers/net/wireless/broadcom/b43/tables_lpphy.c
@@ -1066,7 +1066,7 @@ static const u32 lpphy_papd_mult_table[] = {
 	0x00036963, 0x000339f2, 0x00030a89, 0x0002db28,
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev0_nopa_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev0_nopa_tx_gain_table[] = {
 	{ .gm = 7, .pga = 15, .pad = 14, .dac = 0, .bb_mult = 152, },
 	{ .gm = 7, .pga = 15, .pad = 14, .dac = 0, .bb_mult = 147, },
 	{ .gm = 7, .pga = 15, .pad = 14, .dac = 0, .bb_mult = 143, },
@@ -1197,7 +1197,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev0_nopa_tx_gain_table[] = {
 	{ .gm = 7, .pga = 11, .pad = 6, .dac = 0, .bb_mult = 71, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev0_2ghz_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev0_2ghz_tx_gain_table[] = {
 	{ .gm = 4, .pga = 15, .pad = 9, .dac = 0, .bb_mult = 64, },
 	{ .gm = 4, .pga = 15, .pad = 9, .dac = 0, .bb_mult = 62, },
 	{ .gm = 4, .pga = 15, .pad = 9, .dac = 0, .bb_mult = 60, },
@@ -1328,7 +1328,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev0_2ghz_tx_gain_table[] = {
 	{ .gm = 4, .pga = 4, .pad = 2, .dac = 0, .bb_mult = 72, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev0_5ghz_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev0_5ghz_tx_gain_table[] = {
 	{ .gm = 7, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 99, },
 	{ .gm = 7, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 96, },
 	{ .gm = 7, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 93, },
@@ -1459,7 +1459,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev0_5ghz_tx_gain_table[] = {
 	{ .gm = 7, .pga = 11, .pad = 6, .dac = 0, .bb_mult = 60, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev1_nopa_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev1_nopa_tx_gain_table[] = {
 	{ .gm = 7, .pga = 15, .pad = 14, .dac = 0, .bb_mult = 152, },
 	{ .gm = 7, .pga = 15, .pad = 14, .dac = 0, .bb_mult = 147, },
 	{ .gm = 7, .pga = 15, .pad = 14, .dac = 0, .bb_mult = 143, },
@@ -1599,7 +1599,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev1_nopa_tx_gain_table[] = {
 	{ .gm = 7, .pga = 11, .pad = 6, .dac = 0, .bb_mult = 71, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev1_2ghz_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev1_2ghz_tx_gain_table[] = {
 	{ .gm = 4, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 90, },
 	{ .gm = 4, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 88, },
 	{ .gm = 4, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 85, },
@@ -1730,7 +1730,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev1_2ghz_tx_gain_table[] = {
 	{ .gm = 4, .pga = 10, .pad = 6, .dac = 0, .bb_mult = 60, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev1_5ghz_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev1_5ghz_tx_gain_table[] = {
 	{ .gm = 7, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 99, },
 	{ .gm = 7, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 96, },
 	{ .gm = 7, .pga = 15, .pad = 15, .dac = 0, .bb_mult = 93, },
@@ -1861,7 +1861,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev1_5ghz_tx_gain_table[] = {
 	{ .gm = 7, .pga = 11, .pad = 6, .dac = 0, .bb_mult = 60, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev2_nopa_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev2_nopa_tx_gain_table[] = {
 	{ .gm = 255, .pga = 255, .pad = 203, .dac = 0, .bb_mult = 152, },
 	{ .gm = 255, .pga = 255, .pad = 203, .dac = 0, .bb_mult = 147, },
 	{ .gm = 255, .pga = 255, .pad = 203, .dac = 0, .bb_mult = 143, },
@@ -1992,7 +1992,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev2_nopa_tx_gain_table[] = {
 	{ .gm = 255, .pga = 111, .pad = 29, .dac = 0, .bb_mult = 64, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev2_2ghz_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev2_2ghz_tx_gain_table[] = {
 	{ .gm = 7, .pga = 99, .pad = 255, .dac = 0, .bb_mult = 64, },
 	{ .gm = 7, .pga = 96, .pad = 255, .dac = 0, .bb_mult = 64, },
 	{ .gm = 7, .pga = 93, .pad = 255, .dac = 0, .bb_mult = 64, },
@@ -2123,7 +2123,7 @@ static struct lpphy_tx_gain_table_entry lpphy_rev2_2ghz_tx_gain_table[] = {
 	{ .gm = 7, .pga = 13, .pad = 52, .dac = 0, .bb_mult = 64, },
 };
 
-static struct lpphy_tx_gain_table_entry lpphy_rev2_5ghz_tx_gain_table[] = {
+static const struct lpphy_tx_gain_table_entry lpphy_rev2_5ghz_tx_gain_table[] = {
 	{ .gm = 255, .pga = 255, .pad = 255, .dac = 0, .bb_mult = 152, },
 	{ .gm = 255, .pga = 255, .pad = 255, .dac = 0, .bb_mult = 147, },
 	{ .gm = 255, .pga = 255, .pad = 255, .dac = 0, .bb_mult = 143, },
@@ -2392,7 +2392,7 @@ void lpphy_write_gain_table(struct b43_wldev *dev, int offset,
 }
 
 void lpphy_write_gain_table_bulk(struct b43_wldev *dev, int offset, int count,
-				 struct lpphy_tx_gain_table_entry *table)
+				 const struct lpphy_tx_gain_table_entry *table)
 {
 	int i;
 
diff --git a/drivers/net/wireless/broadcom/b43/tables_lpphy.h b/drivers/net/wireless/broadcom/b43/tables_lpphy.h
index 62002098bbda..1971ccccabf8 100644
--- a/drivers/net/wireless/broadcom/b43/tables_lpphy.h
+++ b/drivers/net/wireless/broadcom/b43/tables_lpphy.h
@@ -36,7 +36,7 @@ struct lpphy_tx_gain_table_entry {
 void lpphy_write_gain_table(struct b43_wldev *dev, int offset,
 			    struct lpphy_tx_gain_table_entry data);
 void lpphy_write_gain_table_bulk(struct b43_wldev *dev, int offset, int count,
-				 struct lpphy_tx_gain_table_entry *table);
+				 const struct lpphy_tx_gain_table_entry *table);
 
 void lpphy_rev0_1_table_init(struct b43_wldev *dev);
 void lpphy_rev2plus_table_init(struct b43_wldev *dev);
-- 
cgit v1.3-3-g829e


From 3f49edf44bd660d393b68a2b1d77a0841fb7f21d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 5 Aug 2024 09:30:26 -0600
Subject: net/fungible: Avoid -Wflex-array-member-not-at-end warning

Use the `DEFINE_RAW_FLEX()` helper for an on-stack definition of
a flexible structure where the size of the flexible-array member
is known at compile-time, and refactor the rest of the code,
accordingly.

So, with these changes, fix the following warning:
drivers/net/ethernet/fungible/funcore/fun_dev.c:550:43: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/ZrDwEugW7DR/FlP5@cute
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/fungible/funcore/fun_dev.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c
index a7fbd4cd560a..ce97b76f9ae0 100644
--- a/drivers/net/ethernet/fungible/funcore/fun_dev.c
+++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c
@@ -546,17 +546,14 @@ int fun_bind(struct fun_dev *fdev, enum fun_admin_bind_type type0,
 	     unsigned int id0, enum fun_admin_bind_type type1,
 	     unsigned int id1)
 {
-	struct {
-		struct fun_admin_bind_req req;
-		struct fun_admin_bind_entry entry[2];
-	} cmd = {
-		.req.common = FUN_ADMIN_REQ_COMMON_INIT2(FUN_ADMIN_OP_BIND,
-							 sizeof(cmd)),
-		.entry[0] = FUN_ADMIN_BIND_ENTRY_INIT(type0, id0),
-		.entry[1] = FUN_ADMIN_BIND_ENTRY_INIT(type1, id1),
-	};
+	DEFINE_RAW_FLEX(struct fun_admin_bind_req, cmd, entry, 2);
+
+	cmd->common = FUN_ADMIN_REQ_COMMON_INIT2(FUN_ADMIN_OP_BIND,
+						 __struct_size(cmd));
+	cmd->entry[0] = FUN_ADMIN_BIND_ENTRY_INIT(type0, id0);
+	cmd->entry[1] = FUN_ADMIN_BIND_ENTRY_INIT(type1, id1);
 
-	return fun_submit_admin_sync_cmd(fdev, &cmd.req.common, NULL, 0, 0);
+	return fun_submit_admin_sync_cmd(fdev, &cmd->common, NULL, 0, 0);
 }
 EXPORT_SYMBOL_GPL(fun_bind);
 
-- 
cgit v1.3-3-g829e


From de6c7b9ada33046481a094be073b85a25dcffcaf Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@denx.de>
Date: Mon, 5 Aug 2024 23:16:28 -0300
Subject: net: fec: Switch to RUNTIME/SYSTEM_SLEEP_PM_OPS()

Replace SET_RUNTIME_PM_OPS()/SET SYSTEM_SLEEP_PM_OPS() with their modern
RUNTIME_PM_OPS() and SYSTEM_SLEEP_PM_OPS() alternatives.

The combined usage of pm_ptr() and RUNTIME_PM_OPS/SYSTEM_SLEEP_PM_OPS()
allows the compiler to evaluate if the runtime suspend/resume() functions
are used at build time or are simply dead code.

This allows removing the __maybe_unused notation from the runtime
suspend/resume() functions.

Signed-off-by: Fabio Estevam <festevam@denx.de>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20240806021628.2524089-1-festevam@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index a923cb95cdc6..8c3bf0faba63 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -4606,7 +4606,7 @@ fec_drv_remove(struct platform_device *pdev)
 	free_netdev(ndev);
 }
 
-static int __maybe_unused fec_suspend(struct device *dev)
+static int fec_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -4659,7 +4659,7 @@ static int __maybe_unused fec_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused fec_resume(struct device *dev)
+static int fec_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -4714,7 +4714,7 @@ failed_clk:
 	return ret;
 }
 
-static int __maybe_unused fec_runtime_suspend(struct device *dev)
+static int fec_runtime_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -4725,7 +4725,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev)
 	return 0;
 }
 
-static int __maybe_unused fec_runtime_resume(struct device *dev)
+static int fec_runtime_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
@@ -4746,14 +4746,14 @@ failed_clk_ipg:
 }
 
 static const struct dev_pm_ops fec_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
-	SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
+	SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
+	RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
 };
 
 static struct platform_driver fec_driver = {
 	.driver	= {
 		.name	= DRIVER_NAME,
-		.pm	= &fec_pm_ops,
+		.pm	= pm_ptr(&fec_pm_ops),
 		.of_match_table = fec_dt_ids,
 		.suppress_bind_attrs = true,
 	},
-- 
cgit v1.3-3-g829e


From 93b828cc8e2a87355ee5e852d27c21fdee27591b Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 6 Aug 2024 10:56:52 +0100
Subject: bonding: Pass string literal as format argument of
 alloc_ordered_workqueue()

Recently I noticed that both gcc-14 and clang-18 report that passing
a non-string literal as the format argument of alloc_ordered_workqueue
is potentially insecure.

F.e. clang-18 says:

.../bond_main.c:6384:37: warning: format string is not a string literal (potentially insecure) [-Wformat-security]
 6384 |         bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
      |                                            ^~~~~~~~~~~~~~
.../workqueue.h:524:18: note: expanded from macro 'alloc_ordered_workqueue'
  524 |         alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
      |                         ^~~
.../bond_main.c:6384:37: note: treat the string as an argument to avoid this
 6384 |         bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
      |                                            ^
      |                                            "%s",
..../workqueue.h:524:18: note: expanded from macro 'alloc_ordered_workqueue'
  524 |         alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
      |                         ^

Perhaps it is always the case where the contents of bond_dev->name is
safe to pass as the format argument. That is, in my understanding, it
never contains any format escape sequences.

But, it seems better to be safe than sorry. And, as a bonus, compiler
output becomes less verbose by addressing this issue as suggested by
clang-18.

Signed-off-by: Simon Horman <horms@kernel.org>
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Link: https://patch.msgid.link/20240806-bonding-fmt-v1-1-e75027e45775@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1cd92c12e782..f9633a6f8571 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -6338,7 +6338,8 @@ static int bond_init(struct net_device *bond_dev)
 
 	netdev_dbg(bond_dev, "Begin bond_init\n");
 
-	bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM);
+	bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
+					   bond_dev->name);
 	if (!bond->wq)
 		return -ENOMEM;
 
-- 
cgit v1.3-3-g829e


From 7d70ed9f9c6a9537379ff645d6befea4c203aa98 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Tue, 6 Aug 2024 13:45:31 +0300
Subject: doc/netlink/specs: add netkit support to rt_link.yaml

Add netkit support to rt_link.yaml. Only forward(PASS) and
blackhole(DROP) policies are allowed to be set by user-space so I've
added only them to the yaml to avoid confusion.

Example:
  $ ./tools/net/ynl/cli.py \
     --spec Documentation/netlink/specs/rt_link.yaml \
     --do getlink --json '{"ifname": "netkit0"}' --output-json | jq
  ...
  "linkinfo": {
    "kind": "netkit",
    "data": {
      "primary": 1,
      "policy": "blackhole",
      "mode": "l2",
      "peer-policy": "forward"
    }
  },
  ...

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20240806104531.3296718-1-razor@blackwall.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml | 41 ++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index de08c12fd56f..0c4d5d40cae9 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -903,6 +903,22 @@ definitions:
       - cfm-config
       - cfm-status
       - mst
+  -
+    name: netkit-policy
+    type: enum
+    entries:
+      -
+        name: forward
+        value: 0
+      -
+        name: blackhole
+        value: 2
+  -
+    name: netkit-mode
+    type: enum
+    entries:
+      - name: l2
+      - name: l3
 
 attribute-sets:
   -
@@ -2109,6 +2125,28 @@ attribute-sets:
       -
         name: id
         type: u32
+  -
+    name: linkinfo-netkit-attrs
+    name-prefix: ifla-netkit-
+    attributes:
+      -
+        name: peer-info
+        type: binary
+      -
+        name: primary
+        type: u8
+      -
+        name: policy
+        type: u32
+        enum: netkit-policy
+      -
+        name: peer-policy
+        type: u32
+        enum: netkit-policy
+      -
+        name: mode
+        type: u32
+        enum: netkit-mode
 
 sub-messages:
   -
@@ -2147,6 +2185,9 @@ sub-messages:
       -
         value: vrf
         attribute-set: linkinfo-vrf-attrs
+      -
+        value: netkit
+        attribute-set: linkinfo-netkit-attrs
   -
     name: linkinfo-member-data-msg
     formats:
-- 
cgit v1.3-3-g829e


From 91d516d4de48532d967a77967834e00c8c53dfe6 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 6 Aug 2024 12:28:24 +0100
Subject: net: mvpp2: Increase size of queue_name buffer

Increase size of queue_name buffer from 30 to 31 to accommodate
the largest string written to it. This avoids truncation in
the possibly unlikely case where the string is name is the
maximum size.

Flagged by gcc-14:

  .../mvpp2_main.c: In function 'mvpp2_probe':
  .../mvpp2_main.c:7636:32: warning: 'snprintf' output may be truncated before the last format character [-Wformat-truncation=]
   7636 |                  "stats-wq-%s%s", netdev_name(priv->port_list[0]->dev),
        |                                ^
  .../mvpp2_main.c:7635:9: note: 'snprintf' output between 10 and 31 bytes into a destination of size 30
   7635 |         snprintf(priv->queue_name, sizeof(priv->queue_name),
        |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   7636 |                  "stats-wq-%s%s", netdev_name(priv->port_list[0]->dev),
        |                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   7637 |                  priv->port_count > 1 ? "+" : "");
        |                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Introduced by commit 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics").
I am not flagging this as a bug as I am not aware that it is one.

Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Marcin Wojtas <marcin.s.wojtas@gmail.com>
Link: https://patch.msgid.link/20240806-mvpp2-namelen-v1-1-6dc773653f2f@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index e809f91c08fb..9e02e4367bec 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -1088,7 +1088,7 @@ struct mvpp2 {
 	unsigned int max_port_rxqs;
 
 	/* Workqueue to gather hardware statistics */
-	char queue_name[30];
+	char queue_name[31];
 	struct workqueue_struct *stats_queue;
 
 	/* Debugfs root entry */
-- 
cgit v1.3-3-g829e


From 3882dccf48f9fbe787b5df3187d708ef348ac860 Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 8 Aug 2024 16:05:57 +0100
Subject: bpf/bpf_get,set_sockopt: add option to set TCP-BPF sock ops flags

Currently the only opportunity to set sock ops flags dictating
which callbacks fire for a socket is from within a TCP-BPF sockops
program.  This is problematic if the connection is already set up
as there is no further chance to specify callbacks for that socket.
Add TCP_BPF_SOCK_OPS_CB_FLAGS to bpf_setsockopt() and bpf_getsockopt()
to allow users to specify callbacks later, either via an iterator
over sockets or via a socket-specific program triggered by a
setsockopt() on the socket.

Previous discussion on this here [1].

[1] https://lore.kernel.org/bpf/f42f157b-6e52-dd4d-3d97-9b86c84c0b00@oracle.com/

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/r/20240808150558.1035626-2-alan.maguire@oracle.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/uapi/linux/bpf.h       |  3 ++-
 net/core/filter.c              | 16 ++++++++++++++++
 tools/include/uapi/linux/bpf.h |  3 ++-
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 35bcf52dbc65..e05b39e39c3f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2851,7 +2851,7 @@ union bpf_attr {
  * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 		  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 		  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- * 		  **TCP_BPF_RTO_MIN**.
+ *		  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -7080,6 +7080,7 @@ enum {
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
+	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 };
 
 enum {
diff --git a/net/core/filter.c b/net/core/filter.c
index f3c72cf86099..d96a50f3f016 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5278,6 +5278,11 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 			return -EINVAL;
 		inet_csk(sk)->icsk_rto_min = timeout;
 		break;
+	case TCP_BPF_SOCK_OPS_CB_FLAGS:
+		if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS))
+			return -EINVAL;
+		tp->bpf_sock_ops_cb_flags = val;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -5366,6 +5371,17 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 		if (*optlen < 1)
 			return -EINVAL;
 		break;
+	case TCP_BPF_SOCK_OPS_CB_FLAGS:
+		if (*optlen != sizeof(int))
+			return -EINVAL;
+		if (getopt) {
+			struct tcp_sock *tp = tcp_sk(sk);
+			int cb_flags = tp->bpf_sock_ops_cb_flags;
+
+			memcpy(optval, &cb_flags, *optlen);
+			return 0;
+		}
+		return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen);
 	default:
 		if (getopt)
 			return -EINVAL;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 35bcf52dbc65..e05b39e39c3f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2851,7 +2851,7 @@ union bpf_attr {
  * 		  **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**,
  * 		  **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**,
  * 		  **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**,
- * 		  **TCP_BPF_RTO_MIN**.
+ *		  **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**.
  * 		* **IPPROTO_IP**, which supports *optname* **IP_TOS**.
  * 		* **IPPROTO_IPV6**, which supports the following *optname*\ s:
  * 		  **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**.
@@ -7080,6 +7080,7 @@ enum {
 	TCP_BPF_SYN		= 1005, /* Copy the TCP header */
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
+	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
 };
 
 enum {
-- 
cgit v1.3-3-g829e


From d53050934e66dbee64caed1309cef963a416c52f Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Thu, 8 Aug 2024 16:05:58 +0100
Subject: selftests/bpf: add sockopt tests for TCP_BPF_SOCK_OPS_CB_FLAGS

Add tests to set TCP sockopt TCP_BPF_SOCK_OPS_CB_FLAGS via
bpf_setsockopt() and use a cgroup/getsockopt program to retrieve
the value to verify it was set.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/r/20240808150558.1035626-3-alan.maguire@oracle.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/setget_sockopt.c      | 47 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/setget_sockopt.c | 26 ++++++++++--
 2 files changed, 70 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index 7d4a9b3d3722..e12255121c15 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -154,6 +154,51 @@ err_out:
 	close(sfd);
 }
 
+static void test_nonstandard_opt(int family)
+{
+	struct setget_sockopt__bss *bss = skel->bss;
+	struct bpf_link *getsockopt_link = NULL;
+	int sfd = -1, fd = -1, cfd = -1, flags;
+	socklen_t flagslen = sizeof(flags);
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		return;
+
+	fd = connect_to_fd(sfd, 0);
+	if (!ASSERT_GE(fd, 0, "connect_to_fd_server"))
+		goto err_out;
+
+	/* cgroup/getsockopt prog will intercept getsockopt() below and
+	 * retrieve the tcp socket bpf_sock_ops_cb_flags value for the
+	 * accept()ed socket; this was set earlier in the passive established
+	 * callback for the accept()ed socket via bpf_setsockopt().
+	 */
+	getsockopt_link = bpf_program__attach_cgroup(skel->progs._getsockopt, cg_fd);
+	if (!ASSERT_OK_PTR(getsockopt_link, "getsockopt prog"))
+		goto err_out;
+
+	cfd = accept(sfd, NULL, 0);
+	if (!ASSERT_GE(cfd, 0, "accept"))
+		goto err_out;
+
+	if (!ASSERT_OK(getsockopt(cfd, SOL_TCP, TCP_BPF_SOCK_OPS_CB_FLAGS, &flags, &flagslen),
+		       "getsockopt_flags"))
+		goto err_out;
+	ASSERT_EQ(flags & BPF_SOCK_OPS_STATE_CB_FLAG, BPF_SOCK_OPS_STATE_CB_FLAG,
+		  "cb_flags_set");
+err_out:
+	close(sfd);
+	if (fd != -1)
+		close(fd);
+	if (cfd != -1)
+		close(cfd);
+	bpf_link__destroy(getsockopt_link);
+}
+
 void test_setget_sockopt(void)
 {
 	cg_fd = test__join_cgroup(CG_NAME);
@@ -191,6 +236,8 @@ void test_setget_sockopt(void)
 	test_udp(AF_INET);
 	test_ktls(AF_INET6);
 	test_ktls(AF_INET);
+	test_nonstandard_opt(AF_INET);
+	test_nonstandard_opt(AF_INET6);
 
 done:
 	setget_sockopt__destroy(skel);
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 60518aed1ffc..6dd4318debbf 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -59,6 +59,8 @@ static const struct sockopt_test sol_tcp_tests[] = {
 	{ .opt = TCP_THIN_LINEAR_TIMEOUTS, .flip = 1, },
 	{ .opt = TCP_USER_TIMEOUT, .new = 123400, .expected = 123400, },
 	{ .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, },
+	{ .opt = TCP_BPF_SOCK_OPS_CB_FLAGS, .new = BPF_SOCK_OPS_ALL_CB_FLAGS,
+	  .expected = BPF_SOCK_OPS_ALL_CB_FLAGS, },
 	{ .opt = 0, },
 };
 
@@ -353,11 +355,30 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family,
 	return 1;
 }
 
+SEC("cgroup/getsockopt")
+int _getsockopt(struct bpf_sockopt *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	int *optval = ctx->optval;
+	struct tcp_sock *tp;
+
+	if (!sk || ctx->level != SOL_TCP || ctx->optname != TCP_BPF_SOCK_OPS_CB_FLAGS)
+		return 1;
+
+	tp = bpf_core_cast(sk, struct tcp_sock);
+	if (ctx->optval + sizeof(int) <= ctx->optval_end) {
+		*optval = tp->bpf_sock_ops_cb_flags;
+		ctx->retval = 0;
+	}
+	return 1;
+}
+
 SEC("sockops")
 int skops_sockopt(struct bpf_sock_ops *skops)
 {
 	struct bpf_sock *bpf_sk = skops->sk;
 	struct sock *sk;
+	int flags;
 
 	if (!bpf_sk)
 		return 1;
@@ -384,9 +405,8 @@ int skops_sockopt(struct bpf_sock_ops *skops)
 		nr_passive += !(bpf_test_sockopt(skops, sk) ||
 				test_tcp_maxseg(skops, sk) ||
 				test_tcp_saved_syn(skops, sk));
-		bpf_sock_ops_cb_flags_set(skops,
-					  skops->bpf_sock_ops_cb_flags |
-					  BPF_SOCK_OPS_STATE_CB_FLAG);
+		flags = skops->bpf_sock_ops_cb_flags | BPF_SOCK_OPS_STATE_CB_FLAG;
+		bpf_setsockopt(skops, SOL_TCP, TCP_BPF_SOCK_OPS_CB_FLAGS, &flags, sizeof(flags));
 		break;
 	case BPF_SOCK_OPS_STATE_CB:
 		if (skops->args[1] == BPF_TCP_CLOSE_WAIT)
-- 
cgit v1.3-3-g829e


From 45ae0e8cf8c75f41da8bfc588038864dc82614f9 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 5 Aug 2024 17:00:24 +0800
Subject: wifi: rtw89: 8852c: support firmware format up to v1

Driver has supported different WoWLAN reason code by commit 0e5210217768
("wifi: rtw89: wow: update WoWLAN reason register for different FW")
since firmware version 0.27.80.0. The old driver can't support two
kinds of WoWLAN reason, so increase firmware format to v1.

Also driver tables of BB and RF registers and power values will be added
into v1 format.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240805090028.27768-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852c.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index d9d7b3ff338a..244f50e72549 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -14,10 +14,10 @@
 #include "rtw8852c_table.h"
 #include "util.h"
 
-#define RTW8852C_FW_FORMAT_MAX 0
+#define RTW8852C_FW_FORMAT_MAX 1
 #define RTW8852C_FW_BASENAME "rtw89/rtw8852c_fw"
 #define RTW8852C_MODULE_FIRMWARE \
-	RTW8852C_FW_BASENAME ".bin"
+	RTW8852C_FW_BASENAME "-" __stringify(RTW8852C_FW_FORMAT_MAX) ".bin"
 
 static const struct rtw89_hfc_ch_cfg rtw8852c_hfc_chcfg_pcie[] = {
 	{13, 1614, grp_0}, /* ACH 0 */
-- 
cgit v1.3-3-g829e


From 0f683c2cf673da99b08b718db79e11451c42dc7e Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 5 Aug 2024 17:00:25 +0800
Subject: wifi: rtw89: wow: implement PS mode for net-detect

When net-detect is enabled, WoWLAN firmware will periodically
scan until beacon or probe response of configured networks are
received. To reduce power consumption, the FW-IPS mode is
implemented to keep WiFi chip in idle mode between each scan.
The FW-IPS is controlled by WoWLAN firmware to turn of some critical
electrical components, and is different from the original IPS mode
which most electrical components are turned off.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240805090028.27768-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c  | 36 ++++++++++++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h  | 10 +++++++++
 drivers/net/wireless/realtek/rtw89/wow.c | 34 +++++++++++++++++++++++-------
 drivers/net/wireless/realtek/rtw89/wow.h | 16 ++++++++++++++
 4 files changed, 89 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 4c0a1aed6efd..e545d2a7fb49 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -6856,7 +6856,43 @@ hdr:
 		goto fail;
 	}
 	return 0;
+fail:
+	dev_kfree_skb_any(skb);
+
+	return ret;
+}
+
+int rtw89_fw_h2c_fwips(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+		       bool enable)
+{
+	struct rtw89_h2c_fwips *h2c;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
+	int ret;
+
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
+	if (!skb) {
+		rtw89_err(rtwdev, "failed to alloc skb for fw ips\n");
+		return -ENOMEM;
+	}
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_fwips *)skb->data;
+
+	h2c->w0 = le32_encode_bits(rtwvif->mac_id, RTW89_H2C_FW_IPS_W0_MACID) |
+		  le32_encode_bits(enable, RTW89_H2C_FW_IPS_W0_ENABLE);
+
+	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
+			      H2C_CAT_MAC,
+			      H2C_CL_MAC_PS,
+			      H2C_FUNC_IPS_CFG, 0, 1,
+			      len);
 
+	ret = rtw89_h2c_tx(rtwdev, skb, false);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to send h2c\n");
+		goto fail;
+	}
+	return 0;
 fail:
 	dev_kfree_skb_any(skb);
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 0b0c5b5c6bb9..1bbdf0613ca4 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -2748,6 +2748,13 @@ struct rtw89_h2c_scanofld_be {
 #define RTW89_H2C_SCANOFLD_BE_W9_SIZE_MACC GENMASK(15, 8)
 #define RTW89_H2C_SCANOFLD_BE_W9_SIZE_OP GENMASK(23, 16)
 
+struct rtw89_h2c_fwips {
+	__le32 w0;
+} __packed;
+
+#define RTW89_H2C_FW_IPS_W0_MACID GENMASK(7, 0)
+#define RTW89_H2C_FW_IPS_W0_ENABLE BIT(8)
+
 static inline void RTW89_SET_FWCMD_P2P_MACID(void *cmd, u32 val)
 {
 	le32p_replace_bits((__le32 *)cmd, val, GENMASK(7, 0));
@@ -3965,6 +3972,7 @@ enum rtw89_wow_h2c_func {
 #define H2C_CL_MAC_PS			0x2
 #define H2C_FUNC_MAC_LPS_PARM		0x0
 #define H2C_FUNC_P2P_ACT		0x1
+#define H2C_FUNC_IPS_CFG		0x3
 
 /* CLASS 3 - FW download */
 #define H2C_CL_MAC_FWDL		0x3
@@ -4446,6 +4454,8 @@ int rtw89_fw_h2c_lps_parm(struct rtw89_dev *rtwdev,
 			  struct rtw89_lps_parm *lps_param);
 int rtw89_fw_h2c_lps_ch_info(struct rtw89_dev *rtwdev,
 			     struct rtw89_vif *rtwvif);
+int rtw89_fw_h2c_fwips(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+		       bool enable);
 struct sk_buff *rtw89_fw_h2c_alloc_skb_with_hdr(struct rtw89_dev *rtwdev, u32 len);
 struct sk_buff *rtw89_fw_h2c_alloc_skb_no_hdr(struct rtw89_dev *rtwdev, u32 len);
 int rtw89_fw_msg_reg(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 9882064ef68d..fa7fd6571051 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -687,17 +687,30 @@ static void rtw89_wow_enter_deep_ps(struct rtw89_dev *rtwdev)
 	__rtw89_enter_ps_mode(rtwdev, rtwvif);
 }
 
-static void rtw89_wow_enter_lps(struct rtw89_dev *rtwdev)
+static void rtw89_wow_enter_ps(struct rtw89_dev *rtwdev)
 {
 	struct ieee80211_vif *wow_vif = rtwdev->wow.wow_vif;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
 
-	rtw89_enter_lps(rtwdev, rtwvif, false);
+	if (rtw89_wow_mgd_linked(rtwdev))
+		rtw89_enter_lps(rtwdev, rtwvif, false);
+	else if (rtw89_wow_no_link(rtwdev))
+		rtw89_fw_h2c_fwips(rtwdev, rtwvif, true);
 }
 
-static void rtw89_wow_leave_lps(struct rtw89_dev *rtwdev)
+static void rtw89_wow_leave_ps(struct rtw89_dev *rtwdev, bool enable_wow)
 {
-	rtw89_leave_lps(rtwdev);
+	struct ieee80211_vif *wow_vif = rtwdev->wow.wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+
+	if (rtw89_wow_mgd_linked(rtwdev)) {
+		rtw89_leave_lps(rtwdev);
+	} else if (rtw89_wow_no_link(rtwdev)) {
+		if (enable_wow)
+			rtw89_leave_ips(rtwdev);
+		else
+			rtw89_fw_h2c_fwips(rtwdev, rtwvif, false);
+	}
 }
 
 static int rtw89_wow_config_mac(struct rtw89_dev *rtwdev, bool enable_wow)
@@ -1430,7 +1443,7 @@ static int rtw89_wow_enable(struct rtw89_dev *rtwdev)
 		goto out;
 	}
 
-	rtw89_wow_enter_lps(rtwdev);
+	rtw89_wow_enter_ps(rtwdev);
 
 	ret = rtw89_wow_enable_trx_post(rtwdev);
 	if (ret) {
@@ -1455,7 +1468,7 @@ static int rtw89_wow_disable(struct rtw89_dev *rtwdev)
 		goto out;
 	}
 
-	rtw89_wow_leave_lps(rtwdev);
+	rtw89_wow_leave_ps(rtwdev, false);
 
 	ret = rtw89_wow_fw_stop(rtwdev);
 	if (ret) {
@@ -1480,6 +1493,12 @@ out:
 	return ret;
 }
 
+static void rtw89_wow_restore_ps(struct rtw89_dev *rtwdev)
+{
+	if (rtw89_wow_no_link(rtwdev))
+		rtw89_enter_ips(rtwdev);
+}
+
 int rtw89_wow_resume(struct rtw89_dev *rtwdev)
 {
 	int ret;
@@ -1504,6 +1523,7 @@ int rtw89_wow_resume(struct rtw89_dev *rtwdev)
 	if (ret)
 		rtw89_err(rtwdev, "failed to disable wow\n");
 
+	rtw89_wow_restore_ps(rtwdev);
 out:
 	rtw89_wow_clear_wakeups(rtwdev);
 	return ret;
@@ -1519,7 +1539,7 @@ int rtw89_wow_suspend(struct rtw89_dev *rtwdev, struct cfg80211_wowlan *wowlan)
 		return ret;
 	}
 
-	rtw89_wow_leave_lps(rtwdev);
+	rtw89_wow_leave_ps(rtwdev, true);
 
 	ret = rtw89_wow_enable(rtwdev);
 	if (ret) {
diff --git a/drivers/net/wireless/realtek/rtw89/wow.h b/drivers/net/wireless/realtek/rtw89/wow.h
index 0d90add0e88d..5eff3084119b 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.h
+++ b/drivers/net/wireless/realtek/rtw89/wow.h
@@ -95,6 +95,22 @@ static inline int rtw89_wow_get_sec_hdr_len(struct rtw89_dev *rtwdev)
 }
 
 #ifdef CONFIG_PM
+static inline bool rtw89_wow_mgd_linked(struct rtw89_dev *rtwdev)
+{
+	struct ieee80211_vif *wow_vif = rtwdev->wow.wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+
+	return rtwvif->net_type == RTW89_NET_TYPE_INFRA;
+}
+
+static inline bool rtw89_wow_no_link(struct rtw89_dev *rtwdev)
+{
+	struct ieee80211_vif *wow_vif = rtwdev->wow.wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+
+	return rtwvif->net_type == RTW89_NET_TYPE_NO_LINK;
+}
+
 int rtw89_wow_suspend(struct rtw89_dev *rtwdev, struct cfg80211_wowlan *wowlan);
 int rtw89_wow_resume(struct rtw89_dev *rtwdev);
 void rtw89_wow_parse_akm(struct rtw89_dev *rtwdev, struct sk_buff *skb);
-- 
cgit v1.3-3-g829e


From c0bc1bce12e4cb9fd96559377fe79433e5d35161 Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 5 Aug 2024 17:00:26 +0800
Subject: wifi: rtw89: wow: add WoWLAN net-detect support

Net-detect is an option of WoWLAN to allow the device to
be woken up from suspend mode when configured network is detected.

When user enables net-detect and lets the device enter suspend
state, WoWLAN firmware will periodically scan until beacon or
probe response of configured networks are received. If configured
networks are detected, WoWLAN firmware will trigger resume process.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240805090028.27768-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c   |   1 +
 drivers/net/wireless/realtek/rtw89/core.h   |   6 +
 drivers/net/wireless/realtek/rtw89/fw.c     | 277 +++++++++++++++++++++++--
 drivers/net/wireless/realtek/rtw89/fw.h     |  43 +++-
 drivers/net/wireless/realtek/rtw89/mac.c    |   5 +-
 drivers/net/wireless/realtek/rtw89/mac.h    |   5 +-
 drivers/net/wireless/realtek/rtw89/mac_be.c |   1 +
 drivers/net/wireless/realtek/rtw89/wow.c    | 301 +++++++++++++++++++++++-----
 drivers/net/wireless/realtek/rtw89/wow.h    |   7 +
 9 files changed, 568 insertions(+), 78 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index a71c1147d3ce..7b28f2c2a08e 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4688,6 +4688,7 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 
 #ifdef CONFIG_PM
 	hw->wiphy->wowlan = rtwdev->chip->wowlan_stub;
+	hw->wiphy->max_sched_scan_ssids = RTW89_SCANOFLD_MAX_SSID;
 #endif
 
 	hw->wiphy->tid_config_support.vif |= BIT(NL80211_TID_CONFIG_ATTR_AMPDU_CTRL);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index ecef3b154f3e..f40475a94d11 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -927,10 +927,12 @@ enum rtw89_sc_offset {
 	RTW89_SC_40_LOWER	= 10,
 };
 
+/* only mgd features can be added to the enum */
 enum rtw89_wow_flags {
 	RTW89_WOW_FLAG_EN_MAGIC_PKT,
 	RTW89_WOW_FLAG_EN_REKEY_PKT,
 	RTW89_WOW_FLAG_EN_DISCONNECT,
+	RTW89_WOW_FLAG_EN_PATTERN,
 	RTW89_WOW_FLAG_NUM,
 };
 
@@ -5308,6 +5310,10 @@ struct rtw89_wow_param {
 	u8 gtk_alg;
 	u8 ptk_keyidx;
 	u8 akm;
+
+	bool pno_inited;
+	struct list_head pno_pkt_list;
+	struct cfg80211_sched_scan_request *nd_config;
 };
 
 struct rtw89_mcc_limit {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index e545d2a7fb49..2a55f47a0ac8 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -4808,9 +4808,10 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num,
 	return 0;
 }
 
-int rtw89_fw_h2c_scan_offload(struct rtw89_dev *rtwdev,
-			      struct rtw89_scan_option *option,
-			      struct rtw89_vif *rtwvif)
+int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
+				 struct rtw89_scan_option *option,
+				 struct rtw89_vif *rtwvif,
+				 bool wowlan)
 {
 	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
 	struct rtw89_chan *op = &rtwdev->scan_info.op_chan;
@@ -4838,7 +4839,10 @@ int rtw89_fw_h2c_scan_offload(struct rtw89_dev *rtwdev,
 				   RTW89_H2C_SCANOFLD_W1_TARGET_CH_MODE) |
 		  le32_encode_bits(RTW89_SCAN_IMMEDIATE,
 				   RTW89_H2C_SCANOFLD_W1_START_MODE) |
-		  le32_encode_bits(RTW89_SCAN_ONCE, RTW89_H2C_SCANOFLD_W1_SCAN_TYPE);
+		  le32_encode_bits(option->repeat, RTW89_H2C_SCANOFLD_W1_SCAN_TYPE);
+
+	h2c->w2 = le32_encode_bits(option->norm_pd, RTW89_H2C_SCANOFLD_W2_NORM_PD) |
+		  le32_encode_bits(option->slow_pd, RTW89_H2C_SCANOFLD_W2_SLOW_PD);
 
 	if (option->target_ch_mode) {
 		h2c->w1 |= le32_encode_bits(op->band_width,
@@ -4894,7 +4898,8 @@ static void rtw89_scan_get_6g_disabled_chan(struct rtw89_dev *rtwdev,
 
 int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 				 struct rtw89_scan_option *option,
-				 struct rtw89_vif *rtwvif)
+				 struct rtw89_vif *rtwvif,
+				 bool wowlan)
 {
 	struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info;
 	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
@@ -4930,11 +4935,13 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 
 	memset(probe_id, RTW89_SCANOFLD_PKT_NONE, sizeof(probe_id));
 
-	list_for_each_entry(pkt_info, &scan_info->pkt_list[NL80211_BAND_6GHZ], list) {
-		if (pkt_info->wildcard_6ghz) {
-			/* Provide wildcard as template */
-			probe_id[NL80211_BAND_6GHZ] = pkt_info->id;
-			break;
+	if (!wowlan) {
+		list_for_each_entry(pkt_info, &scan_info->pkt_list[NL80211_BAND_6GHZ], list) {
+			if (pkt_info->wildcard_6ghz) {
+				/* Provide wildcard as template */
+				probe_id[NL80211_BAND_6GHZ] = pkt_info->id;
+				break;
+			}
 		}
 	}
 
@@ -4973,7 +4980,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 				   RTW89_H2C_SCANOFLD_BE_W6_CHAN_PROHIB_LOW);
 	h2c->w7 = le32_encode_bits(option->prohib_chan >> 32,
 				   RTW89_H2C_SCANOFLD_BE_W7_CHAN_PROHIB_HIGH);
-	if (req->no_cck) {
+	if (!wowlan && req->no_cck) {
 		h2c->w0 |= le32_encode_bits(true, RTW89_H2C_SCANOFLD_BE_W0_PROBE_WITH_RATE);
 		h2c->w8 = le32_encode_bits(RTW89_HW_RATE_OFDM6,
 					   RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_2GHZ) |
@@ -5966,6 +5973,56 @@ out:
 	return ret;
 }
 
+static void rtw89_pno_scan_add_chan_ax(struct rtw89_dev *rtwdev,
+				       int chan_type, int ssid_num,
+				       struct rtw89_mac_chinfo *ch_info)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct rtw89_pktofld_info *info;
+	u8 probe_count = 0;
+
+	ch_info->notify_action = RTW89_SCANOFLD_DEBUG_MASK;
+	ch_info->dfs_ch = chan_type == RTW89_CHAN_DFS;
+	ch_info->bw = RTW89_SCAN_WIDTH;
+	ch_info->tx_pkt = true;
+	ch_info->cfg_tx_pwr = false;
+	ch_info->tx_pwr_idx = 0;
+	ch_info->tx_null = false;
+	ch_info->pause_data = false;
+	ch_info->probe_id = RTW89_SCANOFLD_PKT_NONE;
+
+	if (ssid_num) {
+		list_for_each_entry(info, &rtw_wow->pno_pkt_list, list) {
+			if (info->channel_6ghz &&
+			    ch_info->pri_ch != info->channel_6ghz)
+				continue;
+			else if (info->channel_6ghz && probe_count != 0)
+				ch_info->period += RTW89_CHANNEL_TIME_6G;
+
+			if (info->wildcard_6ghz)
+				continue;
+
+			ch_info->pkt_id[probe_count++] = info->id;
+			if (probe_count >= RTW89_SCANOFLD_MAX_SSID)
+				break;
+		}
+		ch_info->num_pkt = probe_count;
+	}
+
+	switch (chan_type) {
+	case RTW89_CHAN_DFS:
+		if (ch_info->ch_band != RTW89_BAND_6G)
+			ch_info->period = max_t(u8, ch_info->period,
+						RTW89_DFS_CHAN_TIME);
+		ch_info->dwell_time = RTW89_DWELL_TIME;
+		break;
+	case RTW89_CHAN_ACTIVE:
+		break;
+	default:
+		rtw89_err(rtwdev, "Channel type out of bound\n");
+	}
+}
+
 static void rtw89_hw_scan_add_chan(struct rtw89_dev *rtwdev, int chan_type,
 				   int ssid_num,
 				   struct rtw89_mac_chinfo *ch_info)
@@ -6044,6 +6101,45 @@ static void rtw89_hw_scan_add_chan(struct rtw89_dev *rtwdev, int chan_type,
 	}
 }
 
+static void rtw89_pno_scan_add_chan_be(struct rtw89_dev *rtwdev, int chan_type,
+				       int ssid_num,
+				       struct rtw89_mac_chinfo_be *ch_info)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct rtw89_pktofld_info *info;
+	u8 probe_count = 0, i;
+
+	ch_info->notify_action = RTW89_SCANOFLD_DEBUG_MASK;
+	ch_info->dfs_ch = chan_type == RTW89_CHAN_DFS;
+	ch_info->bw = RTW89_SCAN_WIDTH;
+	ch_info->tx_null = false;
+	ch_info->pause_data = false;
+	ch_info->probe_id = RTW89_SCANOFLD_PKT_NONE;
+
+	if (ssid_num) {
+		list_for_each_entry(info, &rtw_wow->pno_pkt_list, list) {
+			ch_info->pkt_id[probe_count++] = info->id;
+			if (probe_count >= RTW89_SCANOFLD_MAX_SSID)
+				break;
+		}
+	}
+
+	for (i = probe_count; i < RTW89_SCANOFLD_MAX_SSID; i++)
+		ch_info->pkt_id[i] = RTW89_SCANOFLD_PKT_NONE;
+
+	switch (chan_type) {
+	case RTW89_CHAN_DFS:
+		ch_info->period = max_t(u8, ch_info->period, RTW89_DFS_CHAN_TIME);
+		ch_info->dwell_time = RTW89_DWELL_TIME;
+		break;
+	case RTW89_CHAN_ACTIVE:
+		break;
+	default:
+		rtw89_warn(rtwdev, "Channel type out of bound\n");
+		break;
+	}
+}
+
 static void rtw89_hw_scan_add_chan_be(struct rtw89_dev *rtwdev, int chan_type,
 				      int ssid_num,
 				      struct rtw89_mac_chinfo_be *ch_info)
@@ -6106,8 +6202,58 @@ static void rtw89_hw_scan_add_chan_be(struct rtw89_dev *rtwdev, int chan_type,
 	}
 }
 
-int rtw89_hw_scan_add_chan_list(struct rtw89_dev *rtwdev,
-				struct rtw89_vif *rtwvif, bool connected)
+int rtw89_pno_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif *rtwvif)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct cfg80211_sched_scan_request *nd_config = rtw_wow->nd_config;
+	struct rtw89_mac_chinfo	*ch_info, *tmp;
+	struct ieee80211_channel *channel;
+	struct list_head chan_list;
+	int list_len;
+	enum rtw89_chan_type type;
+	int ret = 0;
+	u32 idx;
+
+	INIT_LIST_HEAD(&chan_list);
+	for (idx = 0, list_len = 0;
+	     idx < nd_config->n_channels && list_len < RTW89_SCAN_LIST_LIMIT;
+	     idx++, list_len++) {
+		channel = nd_config->channels[idx];
+		ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL);
+		if (!ch_info) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ch_info->period = RTW89_CHANNEL_TIME;
+		ch_info->ch_band = rtw89_nl80211_to_hw_band(channel->band);
+		ch_info->central_ch = channel->hw_value;
+		ch_info->pri_ch = channel->hw_value;
+		ch_info->is_psc = cfg80211_channel_is_psc(channel);
+
+		if (channel->flags &
+		    (IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IR))
+			type = RTW89_CHAN_DFS;
+		else
+			type = RTW89_CHAN_ACTIVE;
+
+		rtw89_pno_scan_add_chan_ax(rtwdev, type, nd_config->n_match_sets, ch_info);
+		list_add_tail(&ch_info->list, &chan_list);
+	}
+	ret = rtw89_fw_h2c_scan_list_offload(rtwdev, list_len, &chan_list);
+
+out:
+	list_for_each_entry_safe(ch_info, tmp, &chan_list, list) {
+		list_del(&ch_info->list);
+		kfree(ch_info);
+	}
+
+	return ret;
+}
+
+int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
+				   struct rtw89_vif *rtwvif, bool connected)
 {
 	struct cfg80211_scan_request *req = rtwvif->scan_req;
 	struct rtw89_mac_chinfo	*ch_info, *tmp;
@@ -6183,6 +6329,58 @@ out:
 	return ret;
 }
 
+int rtw89_pno_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif *rtwvif)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct cfg80211_sched_scan_request *nd_config = rtw_wow->nd_config;
+	struct rtw89_mac_chinfo_be *ch_info, *tmp;
+	struct ieee80211_channel *channel;
+	struct list_head chan_list;
+	enum rtw89_chan_type type;
+	int list_len, ret;
+	u32 idx;
+
+	INIT_LIST_HEAD(&chan_list);
+
+	for (idx = 0, list_len = 0;
+	     idx < nd_config->n_channels && list_len < RTW89_SCAN_LIST_LIMIT;
+	     idx++, list_len++) {
+		channel = nd_config->channels[idx];
+		ch_info = kzalloc(sizeof(*ch_info), GFP_KERNEL);
+		if (!ch_info) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		ch_info->period = RTW89_CHANNEL_TIME;
+		ch_info->ch_band = rtw89_nl80211_to_hw_band(channel->band);
+		ch_info->central_ch = channel->hw_value;
+		ch_info->pri_ch = channel->hw_value;
+		ch_info->is_psc = cfg80211_channel_is_psc(channel);
+
+		if (channel->flags &
+		    (IEEE80211_CHAN_RADAR | IEEE80211_CHAN_NO_IR))
+			type = RTW89_CHAN_DFS;
+		else
+			type = RTW89_CHAN_ACTIVE;
+
+		rtw89_pno_scan_add_chan_be(rtwdev, type,
+					   nd_config->n_match_sets, ch_info);
+		list_add_tail(&ch_info->list, &chan_list);
+	}
+
+	ret = rtw89_fw_h2c_scan_list_offload_be(rtwdev, list_len, &chan_list);
+
+out:
+	list_for_each_entry_safe(ch_info, tmp, &chan_list, list) {
+		list_del(&ch_info->list);
+		kfree(ch_info);
+	}
+
+	return ret;
+}
+
 int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
 				   struct rtw89_vif *rtwvif, bool connected)
 {
@@ -6392,7 +6590,7 @@ int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 		opt.opch_end = connected ? 0 : RTW89_CHAN_INVALID;
 	}
 
-	ret = mac->scan_offload(rtwdev, &opt, rtwvif);
+	ret = mac->scan_offload(rtwdev, &opt, rtwvif, false);
 out:
 	return ret;
 }
@@ -6642,6 +6840,57 @@ fail:
 	return ret;
 }
 
+int rtw89_fw_h2c_cfg_pno(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			 bool enable)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct cfg80211_sched_scan_request *nd_config = rtw_wow->nd_config;
+	struct rtw89_h2c_cfg_nlo *h2c;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
+	int ret, i;
+
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
+	if (!skb) {
+		rtw89_err(rtwdev, "failed to alloc skb for nlo\n");
+		return -ENOMEM;
+	}
+
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_cfg_nlo *)skb->data;
+
+	h2c->w0 = le32_encode_bits(enable, RTW89_H2C_NLO_W0_ENABLE) |
+		  le32_encode_bits(enable, RTW89_H2C_NLO_W0_IGNORE_CIPHER) |
+		  le32_encode_bits(rtwvif->mac_id, RTW89_H2C_NLO_W0_MACID);
+
+	if (enable) {
+		h2c->nlo_cnt = nd_config->n_match_sets;
+		for (i = 0 ; i < nd_config->n_match_sets; i++) {
+			h2c->ssid_len[i] = nd_config->match_sets[i].ssid.ssid_len;
+			memcpy(h2c->ssid[i], nd_config->match_sets[i].ssid.ssid,
+			       nd_config->match_sets[i].ssid.ssid_len);
+		}
+	}
+
+	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
+			      H2C_CAT_MAC,
+			      H2C_CL_MAC_WOW,
+			      H2C_FUNC_NLO, 0, 1,
+			      len);
+
+	ret = rtw89_h2c_tx(rtwdev, skb, false);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to send h2c\n");
+		goto fail;
+	}
+
+	return 0;
+
+fail:
+	dev_kfree_skb_any(skb);
+	return ret;
+}
+
 int rtw89_fw_h2c_wow_global(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			    bool enable)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 1bbdf0613ca4..d45355e5b2e8 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -1898,6 +1898,24 @@ struct rtw89_h2c_wow_global {
 #define RTW89_H2C_WOW_GLOBAL_W0_PAIRWISE_SEC_ALGO GENMASK(23, 16)
 #define RTW89_H2C_WOW_GLOBAL_W0_GROUP_SEC_ALGO GENMASK(31, 24)
 
+#define RTW89_MAX_SUPPORT_NL_NUM	16
+struct rtw89_h2c_cfg_nlo {
+	__le32 w0;
+	u8 nlo_cnt;
+	u8 rsvd[3];
+	__le32 patterncheck;
+	__le32 rsvd1;
+	__le32 rsvd2;
+	u8 ssid_len[RTW89_MAX_SUPPORT_NL_NUM];
+	u8 chiper[RTW89_MAX_SUPPORT_NL_NUM];
+	u8 rsvd3[24];
+	u8 ssid[RTW89_MAX_SUPPORT_NL_NUM][IEEE80211_MAX_SSID_LEN];
+} __packed;
+
+#define RTW89_H2C_NLO_W0_ENABLE BIT(0)
+#define RTW89_H2C_NLO_W0_IGNORE_CIPHER BIT(2)
+#define RTW89_H2C_NLO_W0_MACID GENMASK(31, 24)
+
 static inline void RTW89_SET_WOW_WAKEUP_CTRL_PATTERN_MATCH_ENABLE(void *h2c, u32 val)
 {
 	le32p_replace_bits((__le32 *)h2c, val, BIT(0));
@@ -2093,6 +2111,10 @@ enum rtw89_scan_mode {
 
 enum rtw89_scan_type {
 	RTW89_SCAN_ONCE,
+	RTW89_SCAN_NORMAL,
+	RTW89_SCAN_NORMAL_SLOW,
+	RTW89_SCAN_SEAMLESS,
+	RTW89_SCAN_MAX,
 };
 
 static inline void RTW89_SET_FWCMD_CXHDR_TYPE(void *cmd, u8 val)
@@ -3958,6 +3980,7 @@ enum rtw89_wow_h2c_func {
 	H2C_FUNC_WOW_GLOBAL		= 0x2,
 	H2C_FUNC_GTK_OFLD		= 0x3,
 	H2C_FUNC_ARP_OFLD		= 0x4,
+	H2C_FUNC_NLO			= 0x7,
 	H2C_FUNC_WAKEUP_CTRL		= 0x8,
 	H2C_FUNC_WOW_CAM_UPD		= 0xC,
 	H2C_FUNC_AOAC_REPORT_REQ	= 0xD,
@@ -4412,12 +4435,14 @@ int rtw89_fw_h2c_scan_list_offload(struct rtw89_dev *rtwdev, int ch_num,
 				   struct list_head *chan_list);
 int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num,
 				      struct list_head *chan_list);
-int rtw89_fw_h2c_scan_offload(struct rtw89_dev *rtwdev,
-			      struct rtw89_scan_option *opt,
-			      struct rtw89_vif *vif);
+int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
+				 struct rtw89_scan_option *opt,
+				 struct rtw89_vif *vif,
+				 bool wowlan);
 int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 				 struct rtw89_scan_option *opt,
-				 struct rtw89_vif *vif);
+				 struct rtw89_vif *vif,
+				 bool wowlan);
 int rtw89_fw_h2c_rf_reg(struct rtw89_dev *rtwdev,
 			struct rtw89_fw_h2c_rf_reg_info *info,
 			u16 len, u8 page);
@@ -4470,10 +4495,14 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif,
 			  bool enable);
 void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif);
-int rtw89_hw_scan_add_chan_list(struct rtw89_dev *rtwdev,
-				struct rtw89_vif *rtwvif, bool connected);
+int rtw89_hw_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
+				   struct rtw89_vif *rtwvif, bool connected);
+int rtw89_pno_scan_add_chan_list_ax(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif *rtwvif);
 int rtw89_hw_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
 				   struct rtw89_vif *rtwvif, bool connected);
+int rtw89_pno_scan_add_chan_list_be(struct rtw89_dev *rtwdev,
+				    struct rtw89_vif *rtwvif);
 int rtw89_fw_h2c_trigger_cpu_exception(struct rtw89_dev *rtwdev);
 int rtw89_fw_h2c_pkt_drop(struct rtw89_dev *rtwdev,
 			  const struct rtw89_pkt_drop_params *params);
@@ -4486,6 +4515,8 @@ int rtw89_fw_h2c_wow_global(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			    bool enable);
 int rtw89_fw_h2c_wow_wakeup_ctrl(struct rtw89_dev *rtwdev,
 				 struct rtw89_vif *rtwvif, bool enable);
+int rtw89_fw_h2c_cfg_pno(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
+			 bool enable);
 int rtw89_fw_h2c_keep_alive(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			    bool enable);
 int rtw89_fw_h2c_arp_offload(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 149fb1b16239..89875f59d722 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -6527,8 +6527,9 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
 
 	.is_txq_empty = mac_is_txq_empty_ax,
 
-	.add_chan_list = rtw89_hw_scan_add_chan_list,
-	.scan_offload = rtw89_fw_h2c_scan_offload,
+	.add_chan_list = rtw89_hw_scan_add_chan_list_ax,
+	.add_chan_list_pno = rtw89_pno_scan_add_chan_list_ax,
+	.scan_offload = rtw89_fw_h2c_scan_offload_ax,
 
 	.wow_config_mac = rtw89_wow_config_mac_ax,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 02052fbbec1a..9d3be36ffb6e 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -1006,9 +1006,12 @@ struct rtw89_mac_gen_def {
 
 	int (*add_chan_list)(struct rtw89_dev *rtwdev,
 			     struct rtw89_vif *rtwvif, bool connected);
+	int (*add_chan_list_pno)(struct rtw89_dev *rtwdev,
+				 struct rtw89_vif *rtwvif);
 	int (*scan_offload)(struct rtw89_dev *rtwdev,
 			    struct rtw89_scan_option *option,
-			    struct rtw89_vif *rtwvif);
+			    struct rtw89_vif *rtwvif,
+			    bool wowlan);
 
 	int (*wow_config_mac)(struct rtw89_dev *rtwdev, bool enable_wow);
 };
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index f212b67771d5..31f0a5225b11 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -2599,6 +2599,7 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 	.is_txq_empty = mac_is_txq_empty_be,
 
 	.add_chan_list = rtw89_hw_scan_add_chan_list_be,
+	.add_chan_list_pno = rtw89_pno_scan_add_chan_list_be,
 	.scan_offload = rtw89_fw_h2c_scan_offload_be,
 
 	.wow_config_mac = rtw89_wow_config_mac_be,
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index fa7fd6571051..3bf563998ddf 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -794,17 +794,22 @@ static void rtw89_wow_vif_iter(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvi
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif);
 
-	/* Current wowlan function support setting of only one STATION vif.
-	 * So when one suitable vif is found, stop the iteration.
+	/* Current WoWLAN function support setting of only vif in
+	 * infra mode or no link mode. When one suitable vif is found,
+	 * stop the iteration.
 	 */
 	if (rtw_wow->wow_vif || vif->type != NL80211_IFTYPE_STATION)
 		return;
 
 	switch (rtwvif->net_type) {
 	case RTW89_NET_TYPE_INFRA:
-		rtw_wow->wow_vif = vif;
+		if (rtw_wow_has_mgd_features(rtwdev))
+			rtw_wow->wow_vif = vif;
 		break;
 	case RTW89_NET_TYPE_NO_LINK:
+		if (rtw_wow->pno_inited)
+			rtw_wow->wow_vif = vif;
+		break;
 	default:
 		break;
 	}
@@ -1038,6 +1043,23 @@ static void rtw89_wow_clear_wakeups(struct rtw89_dev *rtwdev)
 	rtw_wow->wow_vif = NULL;
 	rtw89_core_release_all_bits_map(rtw_wow->flags, RTW89_WOW_FLAG_NUM);
 	rtw_wow->pattern_cnt = 0;
+	rtw_wow->pno_inited = false;
+}
+
+static void rtw89_wow_init_pno(struct rtw89_dev *rtwdev,
+			       struct cfg80211_sched_scan_request *nd_config)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+
+	if (!nd_config->n_match_sets || !nd_config->n_channels)
+		return;
+
+	rtw_wow->nd_config = nd_config;
+	rtw_wow->pno_inited = true;
+
+	INIT_LIST_HEAD(&rtw_wow->pno_pkt_list);
+
+	rtw89_debug(rtwdev, RTW89_DBG_WOW, "WOW: net-detect is enabled\n");
 }
 
 static int rtw89_wow_set_wakeups(struct rtw89_dev *rtwdev,
@@ -1050,6 +1072,11 @@ static int rtw89_wow_set_wakeups(struct rtw89_dev *rtwdev,
 		set_bit(RTW89_WOW_FLAG_EN_DISCONNECT, rtw_wow->flags);
 	if (wowlan->magic_pkt)
 		set_bit(RTW89_WOW_FLAG_EN_MAGIC_PKT, rtw_wow->flags);
+	if (wowlan->n_patterns && wowlan->patterns)
+		set_bit(RTW89_WOW_FLAG_EN_PATTERN, rtw_wow->flags);
+
+	if (wowlan->nd_config)
+		rtw89_wow_init_pno(rtwdev, wowlan->nd_config);
 
 	rtw89_for_each_rtwvif(rtwdev, rtwvif)
 		rtw89_wow_vif_iter(rtwdev, rtwvif);
@@ -1061,6 +1088,34 @@ static int rtw89_wow_set_wakeups(struct rtw89_dev *rtwdev,
 	return rtw89_wow_parse_patterns(rtwdev, rtwvif, wowlan);
 }
 
+static int rtw89_wow_cfg_wake_pno(struct rtw89_dev *rtwdev, bool wow)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct ieee80211_vif *wow_vif = rtw_wow->wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+	int ret;
+
+	ret = rtw89_fw_h2c_cfg_pno(rtwdev, rtwvif, true);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to config pno\n");
+		return ret;
+	}
+
+	ret = rtw89_fw_h2c_wow_wakeup_ctrl(rtwdev, rtwvif, wow);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to fw wow wakeup ctrl\n");
+		return ret;
+	}
+
+	ret = rtw89_fw_h2c_wow_global(rtwdev, rtwvif, wow);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to fw wow global\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 static int rtw89_wow_cfg_wake(struct rtw89_dev *rtwdev, bool wow)
 {
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
@@ -1321,100 +1376,236 @@ static int rtw89_wow_disable_trx_post(struct rtw89_dev *rtwdev)
 	return ret;
 }
 
-static int rtw89_wow_fw_start(struct rtw89_dev *rtwdev)
+static void rtw89_fw_release_pno_pkt_list(struct rtw89_dev *rtwdev,
+					  struct rtw89_vif *rtwvif)
 {
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
-	struct rtw89_vif *rtwvif = (struct rtw89_vif *)rtw_wow->wow_vif->drv_priv;
+	struct list_head *pkt_list = &rtw_wow->pno_pkt_list;
+	struct rtw89_pktofld_info *info, *tmp;
+
+	list_for_each_entry_safe(info, tmp, pkt_list, list) {
+		rtw89_fw_h2c_del_pkt_offload(rtwdev, info->id);
+		list_del(&info->list);
+		kfree(info);
+	}
+}
+
+static int rtw89_pno_scan_update_probe_req(struct rtw89_dev *rtwdev,
+					   struct rtw89_vif *rtwvif)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct cfg80211_sched_scan_request *nd_config = rtw_wow->nd_config;
+	u8 num = nd_config->n_match_sets, i;
+	struct rtw89_pktofld_info *info;
+	struct sk_buff *skb;
 	int ret;
 
-	rtw89_wow_pattern_write(rtwdev);
-	rtw89_wow_construct_key_info(rtwdev);
+	for (i = 0; i < num; i++) {
+		skb = ieee80211_probereq_get(rtwdev->hw, rtwvif->mac_addr,
+					     nd_config->match_sets[i].ssid.ssid,
+					     nd_config->match_sets[i].ssid.ssid_len,
+					     nd_config->ie_len);
+		if (!skb)
+			return -ENOMEM;
+
+		skb_put_data(skb, nd_config->ie, nd_config->ie_len);
+
+		info = kzalloc(sizeof(*info), GFP_KERNEL);
+		if (!info) {
+			kfree_skb(skb);
+			rtw89_fw_release_pno_pkt_list(rtwdev, rtwvif);
+			return -ENOMEM;
+		}
 
-	ret = rtw89_fw_h2c_keep_alive(rtwdev, rtwvif, true);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to enable keep alive\n");
-		return ret;
+		ret = rtw89_fw_h2c_add_pkt_offload(rtwdev, &info->id, skb);
+		if (ret) {
+			kfree_skb(skb);
+			kfree(info);
+			rtw89_fw_release_pno_pkt_list(rtwdev, rtwvif);
+			return ret;
+		}
+
+		list_add_tail(&info->list, &rtw_wow->pno_pkt_list);
+		kfree_skb(skb);
 	}
 
-	ret = rtw89_fw_h2c_disconnect_detect(rtwdev, rtwvif, true);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to enable disconnect detect\n");
-		goto out;
+	return 0;
+}
+
+static int rtw89_pno_scan_offload(struct rtw89_dev *rtwdev, bool enable)
+{
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct ieee80211_vif *wow_vif = rtw_wow->wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+	struct rtw89_scan_option opt = {};
+	int ret;
+
+	if (enable) {
+		ret = rtw89_pno_scan_update_probe_req(rtwdev, rtwvif);
+		if (ret) {
+			rtw89_err(rtwdev, "Update probe request failed\n");
+			return ret;
+		}
+
+		ret = mac->add_chan_list_pno(rtwdev, rtwvif);
+		if (ret) {
+			rtw89_err(rtwdev, "Update channel list failed\n");
+			return ret;
+		}
 	}
 
-	ret = rtw89_fw_h2c_wow_gtk_ofld(rtwdev, rtwvif, true);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to enable GTK offload\n");
-		goto out;
+	opt.enable = enable;
+	opt.repeat = RTW89_SCAN_NORMAL;
+	opt.norm_pd = 10; /* in unit of 100ms */
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE) {
+		opt.operation = enable ? RTW89_SCAN_OP_START : RTW89_SCAN_OP_STOP;
+		opt.scan_mode = RTW89_SCAN_MODE_SA;
+		opt.band = RTW89_PHY_0;
+		opt.num_macc_role = 0;
+		opt.mlo_mode = rtwdev->mlo_dbcc_mode;
+		opt.num_opch = 0;
+		opt.opch_end = RTW89_CHAN_INVALID;
 	}
 
-	ret = rtw89_fw_h2c_arp_offload(rtwdev, rtwvif, true);
-	if (ret)
-		rtw89_warn(rtwdev, "wow: failed to enable arp offload\n");
+	mac->scan_offload(rtwdev, &opt, rtwvif, true);
 
-	ret = rtw89_wow_cfg_wake(rtwdev, true);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to config wake\n");
-		goto out;
+	return 0;
+}
+
+static int rtw89_wow_fw_start(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+	struct ieee80211_vif *wow_vif = rtw_wow->wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+	int ret;
+
+	if (rtw89_wow_no_link(rtwdev)) {
+		ret = rtw89_pno_scan_offload(rtwdev, false);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to disable pno scan offload\n");
+			return ret;
+		}
+
+		ret = rtw89_pno_scan_offload(rtwdev, true);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to enable pno scan offload\n");
+			return ret;
+		}
+	} else {
+		rtw89_wow_pattern_write(rtwdev);
+		rtw89_wow_construct_key_info(rtwdev);
+
+		ret = rtw89_fw_h2c_keep_alive(rtwdev, rtwvif, true);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to enable keep alive\n");
+			return ret;
+		}
+
+		ret = rtw89_fw_h2c_disconnect_detect(rtwdev, rtwvif, true);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to enable disconnect detect\n");
+			return ret;
+		}
+
+		ret = rtw89_fw_h2c_wow_gtk_ofld(rtwdev, rtwvif, true);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to enable GTK offload\n");
+			return ret;
+		}
+
+		ret = rtw89_fw_h2c_arp_offload(rtwdev, rtwvif, true);
+		if (ret)
+			rtw89_warn(rtwdev, "wow: failed to enable arp offload\n");
+	}
+
+	if (rtw89_wow_no_link(rtwdev)) {
+		ret = rtw89_wow_cfg_wake_pno(rtwdev, true);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to config wake PNO\n");
+			return ret;
+		}
+	} else {
+		ret = rtw89_wow_cfg_wake(rtwdev, true);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to config wake\n");
+			return ret;
+		}
 	}
 
 	ret = rtw89_wow_check_fw_status(rtwdev, true);
 	if (ret) {
 		rtw89_err(rtwdev, "wow: failed to check enable fw ready\n");
-		goto out;
+		return ret;
 	}
 
-out:
-	return ret;
+	return 0;
 }
 
 static int rtw89_wow_fw_stop(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
-	struct rtw89_vif *rtwvif = (struct rtw89_vif *)rtw_wow->wow_vif->drv_priv;
+	struct ieee80211_vif *wow_vif = rtw_wow->wow_vif;
+	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
 	int ret;
 
-	rtw89_wow_pattern_clear(rtwdev);
+	if (rtw89_wow_no_link(rtwdev)) {
+		ret = rtw89_pno_scan_offload(rtwdev, false);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to disable pno scan offload\n");
+			return ret;
+		}
 
-	ret = rtw89_fw_h2c_keep_alive(rtwdev, rtwvif, false);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to disable keep alive\n");
-		goto out;
-	}
+		ret = rtw89_fw_h2c_cfg_pno(rtwdev, rtwvif, false);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to disable pno\n");
+			return ret;
+		}
 
-	ret = rtw89_fw_h2c_disconnect_detect(rtwdev, rtwvif, false);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to disable disconnect detect\n");
-		goto out;
-	}
+		rtw89_fw_release_pno_pkt_list(rtwdev, rtwvif);
+	} else {
+		rtw89_wow_pattern_clear(rtwdev);
 
-	ret = rtw89_fw_h2c_wow_gtk_ofld(rtwdev, rtwvif, false);
-	if (ret) {
-		rtw89_err(rtwdev, "wow: failed to disable GTK offload\n");
-		goto out;
-	}
+		ret = rtw89_fw_h2c_keep_alive(rtwdev, rtwvif, false);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to disable keep alive\n");
+			return ret;
+		}
 
-	ret = rtw89_fw_h2c_arp_offload(rtwdev, rtwvif, false);
-	if (ret)
-		rtw89_warn(rtwdev, "wow: failed to disable arp offload\n");
+		ret = rtw89_fw_h2c_disconnect_detect(rtwdev, rtwvif, false);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to disable disconnect detect\n");
+			return ret;
+		}
+
+		ret = rtw89_fw_h2c_wow_gtk_ofld(rtwdev, rtwvif, false);
+		if (ret) {
+			rtw89_err(rtwdev, "wow: failed to disable GTK offload\n");
+			return ret;
+		}
+
+		ret = rtw89_fw_h2c_arp_offload(rtwdev, rtwvif, false);
+		if (ret)
+			rtw89_warn(rtwdev, "wow: failed to disable arp offload\n");
+
+		rtw89_wow_key_clear(rtwdev);
+		rtw89_fw_release_general_pkt_list(rtwdev, true);
+	}
 
-	rtw89_wow_key_clear(rtwdev);
-	rtw89_fw_release_general_pkt_list(rtwdev, true);
 
 	ret = rtw89_wow_cfg_wake(rtwdev, false);
 	if (ret) {
 		rtw89_err(rtwdev, "wow: failed to disable config wake\n");
-		goto out;
+		return ret;
 	}
 
 	ret = rtw89_wow_check_fw_status(rtwdev, false);
 	if (ret) {
 		rtw89_err(rtwdev, "wow: failed to check disable fw ready\n");
-		goto out;
+		return ret;
 	}
 
-out:
-	return ret;
+	return 0;
 }
 
 static int rtw89_wow_enable(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/wow.h b/drivers/net/wireless/realtek/rtw89/wow.h
index 5eff3084119b..3fbc2b87c058 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.h
+++ b/drivers/net/wireless/realtek/rtw89/wow.h
@@ -111,6 +111,13 @@ static inline bool rtw89_wow_no_link(struct rtw89_dev *rtwdev)
 	return rtwvif->net_type == RTW89_NET_TYPE_NO_LINK;
 }
 
+static inline bool rtw_wow_has_mgd_features(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
+
+	return !bitmap_empty(rtw_wow->flags, RTW89_WOW_FLAG_NUM);
+}
+
 int rtw89_wow_suspend(struct rtw89_dev *rtwdev, struct cfg80211_wowlan *wowlan);
 int rtw89_wow_resume(struct rtw89_dev *rtwdev);
 void rtw89_wow_parse_akm(struct rtw89_dev *rtwdev, struct sk_buff *skb);
-- 
cgit v1.3-3-g829e


From e99dd80c8a183561de891a2cceb5a2bbcf64c88f Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 5 Aug 2024 17:00:27 +0800
Subject: wifi: rtw89: wow: add delay option for net-detect

The delay option is the period in unit of second for WoWLAN firmware
to wait before the first scan. We get the option from cfg80211 and
practice it. Another, in some platform, WoWLAN firmware may found
configured network and then trigger resume process, before suspend
process is completed, lead to the wakeup function failed.
So the default value is set one to avoid the issue.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240805090028.27768-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  1 +
 drivers/net/wireless/realtek/rtw89/fw.c   | 24 +++++++++++++++++++++---
 drivers/net/wireless/realtek/rtw89/fw.h   |  3 +++
 drivers/net/wireless/realtek/rtw89/wow.c  |  2 ++
 4 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index f40475a94d11..b42a33b9868a 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3677,6 +3677,7 @@ struct rtw89_scan_option {
 	u16 slow_pd;
 	u16 norm_cy;
 	u8 opch_end;
+	u16 delay;
 	u64 prohib_chan;
 	enum rtw89_phy_idx band;
 	enum rtw89_scan_be_operation operation;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 2a55f47a0ac8..47aa365991c1 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -4808,6 +4808,7 @@ int rtw89_fw_h2c_scan_list_offload_be(struct rtw89_dev *rtwdev, int ch_num,
 	return 0;
 }
 
+#define RTW89_SCAN_DELAY_TSF_UNIT 104800
 int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 				 struct rtw89_scan_option *option,
 				 struct rtw89_vif *rtwvif,
@@ -4815,10 +4816,12 @@ int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
 	struct rtw89_chan *op = &rtwdev->scan_info.op_chan;
+	enum rtw89_scan_mode scan_mode = RTW89_SCAN_IMMEDIATE;
 	struct rtw89_h2c_scanofld *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
 	unsigned int cond;
+	u64 tsf = 0;
 	int ret;
 
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
@@ -4829,6 +4832,17 @@ int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 	skb_put(skb, len);
 	h2c = (struct rtw89_h2c_scanofld *)skb->data;
 
+	if (option->delay) {
+		ret = rtw89_mac_port_get_tsf(rtwdev, rtwvif, &tsf);
+		if (ret) {
+			rtw89_warn(rtwdev, "NLO failed to get port tsf: %d\n", ret);
+			scan_mode = RTW89_SCAN_IMMEDIATE;
+		} else {
+			scan_mode = RTW89_SCAN_DELAY;
+			tsf += option->delay * RTW89_SCAN_DELAY_TSF_UNIT;
+		}
+	}
+
 	h2c->w0 = le32_encode_bits(rtwvif->mac_id, RTW89_H2C_SCANOFLD_W0_MACID) |
 		  le32_encode_bits(rtwvif->port, RTW89_H2C_SCANOFLD_W0_PORT_ID) |
 		  le32_encode_bits(RTW89_PHY_0, RTW89_H2C_SCANOFLD_W0_BAND) |
@@ -4837,8 +4851,7 @@ int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 	h2c->w1 = le32_encode_bits(true, RTW89_H2C_SCANOFLD_W1_NOTIFY_END) |
 		  le32_encode_bits(option->target_ch_mode,
 				   RTW89_H2C_SCANOFLD_W1_TARGET_CH_MODE) |
-		  le32_encode_bits(RTW89_SCAN_IMMEDIATE,
-				   RTW89_H2C_SCANOFLD_W1_START_MODE) |
+		  le32_encode_bits(scan_mode, RTW89_H2C_SCANOFLD_W1_START_MODE) |
 		  le32_encode_bits(option->repeat, RTW89_H2C_SCANOFLD_W1_SCAN_TYPE);
 
 	h2c->w2 = le32_encode_bits(option->norm_pd, RTW89_H2C_SCANOFLD_W2_NORM_PD) |
@@ -4855,6 +4868,11 @@ int rtw89_fw_h2c_scan_offload_ax(struct rtw89_dev *rtwdev,
 					    RTW89_H2C_SCANOFLD_W0_TARGET_CH_BAND);
 	}
 
+	h2c->tsf_high = le32_encode_bits(upper_32_bits(tsf),
+					 RTW89_H2C_SCANOFLD_W3_TSF_HIGH);
+	h2c->tsf_low = le32_encode_bits(lower_32_bits(tsf),
+					RTW89_H2C_SCANOFLD_W4_TSF_LOW);
+
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
 			      H2C_CAT_MAC, H2C_CL_MAC_FW_OFLD,
 			      H2C_FUNC_SCANOFLD, 1, 1,
@@ -4972,7 +4990,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 				   RTW89_H2C_SCANOFLD_BE_W4_PROBE_5G) |
 		  le32_encode_bits(probe_id[NL80211_BAND_6GHZ],
 				   RTW89_H2C_SCANOFLD_BE_W4_PROBE_6G) |
-		  le32_encode_bits(0, RTW89_H2C_SCANOFLD_BE_W4_DELAY_START);
+		  le32_encode_bits(option->delay, RTW89_H2C_SCANOFLD_BE_W4_DELAY_START);
 
 	h2c->w5 = le32_encode_bits(option->mlo_mode, RTW89_H2C_SCANOFLD_BE_W5_MLO_MODE);
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index d45355e5b2e8..663eda5d0452 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -2107,6 +2107,7 @@ enum rtw89_btc_cxdrvinfo {
 
 enum rtw89_scan_mode {
 	RTW89_SCAN_IMMEDIATE,
+	RTW89_SCAN_DELAY,
 };
 
 enum rtw89_scan_type {
@@ -2686,6 +2687,8 @@ struct rtw89_h2c_scanofld {
 #define RTW89_H2C_SCANOFLD_W1_PROBE_REQ_PKT_ID GENMASK(31, 24)
 #define RTW89_H2C_SCANOFLD_W2_NORM_PD GENMASK(15, 0)
 #define RTW89_H2C_SCANOFLD_W2_SLOW_PD GENMASK(23, 16)
+#define RTW89_H2C_SCANOFLD_W3_TSF_HIGH GENMASK(31, 0)
+#define RTW89_H2C_SCANOFLD_W4_TSF_LOW GENMASK(31, 0)
 
 struct rtw89_h2c_scanofld_be_macc_role {
 	__le32 w0;
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 3bf563998ddf..0f0f4beec4d9 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -1458,6 +1458,8 @@ static int rtw89_pno_scan_offload(struct rtw89_dev *rtwdev, bool enable)
 	opt.enable = enable;
 	opt.repeat = RTW89_SCAN_NORMAL;
 	opt.norm_pd = 10; /* in unit of 100ms */
+	opt.delay = max(rtw_wow->nd_config->delay, 1);
+
 	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE) {
 		opt.operation = enable ? RTW89_SCAN_OP_START : RTW89_SCAN_OP_STOP;
 		opt.scan_mode = RTW89_SCAN_MODE_SA;
-- 
cgit v1.3-3-g829e


From 9fd284aaaeada93f51f27fc4fff8fbcc7353d9a3 Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 5 Aug 2024 17:00:28 +0800
Subject: wifi: rtw89: wow: add net-detect support for 8852c

Enable net-detect in WoWLan stub of 8852c, and declare
net-detect support up to 8 SSIDs.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240805090028.27768-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852c.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 244f50e72549..dc1da9ff055c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2850,10 +2850,12 @@ static const struct rtw89_chanctx_listener rtw8852c_chanctx_listener = {
 
 #ifdef CONFIG_PM
 static const struct wiphy_wowlan_support rtw_wowlan_stub_8852c = {
-	.flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT,
+	.flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT |
+		 WIPHY_WOWLAN_NET_DETECT,
 	.n_patterns = RTW89_MAX_PATTERN_NUM,
 	.pattern_max_len = RTW89_MAX_PATTERN_SIZE,
 	.pattern_min_len = 1,
+	.max_nd_match_sets = RTW89_SCANOFLD_MAX_SSID,
 };
 #endif
 
-- 
cgit v1.3-3-g829e


From 1b84378b8fe12e516cdc6c62f38aa6521d0a6582 Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Mon, 5 Aug 2024 23:19:04 +0100
Subject: wifi: rtl8xxxu: drop reference to staging drivers

The Kconfig notes mention staging drivers that have
since been removed so update the driver's description
so it no longer references the staging rtl8723au and
rtl8192u drivers which have now been deleted.

Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240805221910.3765214-1-pbrobinson@gmail.com
---
 drivers/net/wireless/realtek/rtl8xxxu/Kconfig | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/Kconfig b/drivers/net/wireless/realtek/rtl8xxxu/Kconfig
index 44ad94757a03..14d0343368ac 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/Kconfig
+++ b/drivers/net/wireless/realtek/rtl8xxxu/Kconfig
@@ -20,9 +20,8 @@ config RTL8XXXU
 	  memory footprint than the vendor drivers and benefits
 	  from the in kernel mac80211 stack.
 
-	  It can coexist with drivers from drivers/staging/rtl8723au,
-	  drivers/staging/rtl8192u, and drivers/net/wireless/rtlwifi,
-	  but you will need to control which module you wish to load.
+	  It can coexist with the rtlwifi driver but you will need
+	  to control which module you wish to load.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called rtl8xxxu.  If unsure, say N.
-- 
cgit v1.3-3-g829e


From e24f825a93e2d0775eedd40a4f17fb2c0f6df26b Mon Sep 17 00:00:00 2001
From: Peter Robinson <pbrobinson@gmail.com>
Date: Tue, 6 Aug 2024 09:22:31 +0100
Subject: wifi: rtl8xxxu: add missing rtl8192cu USB IDs

The rtl8xxxu has all the rtl8192cu USB IDs except for the
following 3 so add them to the untested section so they
can be used with the rtl8xxxu as the rtl8192cu are well
supported.

Signed-off-by: Peter Robinson <pbrobinson@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240806082233.3837436-1-pbrobinson@gmail.com
---
 drivers/net/wireless/realtek/rtl8xxxu/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c
index 043fa364e701..7891c988dd5f 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c
@@ -8110,6 +8110,12 @@ static const struct usb_device_id dev_table[] = {
 	.driver_info = (unsigned long)&rtl8192cu_fops},
 {USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x817f, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x819a, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x8754, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
+{USB_DEVICE_AND_INTERFACE_INFO(USB_VENDOR_ID_REALTEK, 0x817c, 0xff, 0xff, 0xff),
+	.driver_info = (unsigned long)&rtl8192cu_fops},
 /* Tested by Larry Finger */
 {USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0x7811, 0xff, 0xff, 0xff),
 	.driver_info = (unsigned long)&rtl8192cu_fops},
-- 
cgit v1.3-3-g829e


From fbbd8cb347e25b68d25c4f3871821afc495ee7a9 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 8 Aug 2024 01:19:36 +0300
Subject: wifi: rtw88: usb: Init RX burst length according to USB speed

This is needed in order to make USB RX aggregation work with RTL8811CU
(and presumably RTL8822BU and RTL8822CU also).

I don't know what BIT_DMA_BURST_CNT, BIT_DMA_MODE, and BIT_DROP_DATA_EN
are doing.

Tested with RTL8822CU, RTL8811CU, and RTL8723DU.

The RX speed is unchanged in my tests.

Tested-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/ac569c6f-7129-4341-b523-901fe10cabff@gmail.com
---
 drivers/net/wireless/realtek/rtw88/reg.h |  6 ++++++
 drivers/net/wireless/realtek/rtw88/usb.c | 23 ++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
index e7b24465f549..4d9b8668e8b0 100644
--- a/drivers/net/wireless/realtek/rtw88/reg.h
+++ b/drivers/net/wireless/realtek/rtw88/reg.h
@@ -322,6 +322,12 @@
 #define REG_RXDMA_DPR		0x028C
 #define REG_RXDMA_MODE		0x0290
 #define BIT_DMA_MODE		BIT(1)
+#define BIT_DMA_BURST_CNT	GENMASK(3, 2)
+#define BIT_DMA_BURST_SIZE	GENMASK(5, 4)
+#define BIT_DMA_BURST_SIZE_64	2
+#define BIT_DMA_BURST_SIZE_512	1
+#define BIT_DMA_BURST_SIZE_1024	0
+
 #define REG_RXPKTNUM		0x02B0
 
 #define REG_INT_MIG		0x0304
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 9145c11a063e..1c40d46a7eb4 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -720,9 +720,30 @@ static void rtw_usb_link_ps(struct rtw_dev *rtwdev, bool enter)
 	/* empty function for rtw_hci_ops */
 }
 
+static void rtw_usb_init_burst_pkt_len(struct rtw_dev *rtwdev)
+{
+	struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
+	enum usb_device_speed speed = rtwusb->udev->speed;
+	u8 rxdma, burst_size;
+
+	rxdma = BIT_DMA_BURST_CNT | BIT_DMA_MODE;
+
+	if (speed == USB_SPEED_SUPER)
+		burst_size = BIT_DMA_BURST_SIZE_1024;
+	else if (speed == USB_SPEED_HIGH)
+		burst_size = BIT_DMA_BURST_SIZE_512;
+	else
+		burst_size = BIT_DMA_BURST_SIZE_64;
+
+	u8p_replace_bits(&rxdma, burst_size, BIT_DMA_BURST_SIZE);
+
+	rtw_write8(rtwdev, REG_RXDMA_MODE, rxdma);
+	rtw_write16_set(rtwdev, REG_TXDMA_OFFSET_CHK, BIT_DROP_DATA_EN);
+}
+
 static void rtw_usb_interface_cfg(struct rtw_dev *rtwdev)
 {
-	/* empty function for rtw_hci_ops */
+	rtw_usb_init_burst_pkt_len(rtwdev);
 }
 
 static struct rtw_hci_ops rtw_usb_ops = {
-- 
cgit v1.3-3-g829e


From 38ea04a79ad0f8cc30bb5e9ad98d665e4ae5060c Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 8 Aug 2024 01:20:36 +0300
Subject: wifi: rtw88: usb: Update the RX stats after every frame

Update the number of received unicast data frames and bytes every time
a frame is received. This is what the PCI and SDIO drivers do.

This has an influence on the power saving, bluetooth coexistence, and
(in a future patch) the use of RX aggregation.

Tested with RTL8822CU, RTL8811CU, and RTL8723DU.

Tested-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/75a2ca52-8f01-45c5-926f-d3a68ae3b284@gmail.com
---
 drivers/net/wireless/realtek/rtw88/usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 1c40d46a7eb4..10f1d724370e 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -581,6 +581,7 @@ static void rtw_usb_rx_handler(struct work_struct *work)
 		skb_reserve(skb, pkt_offset);
 
 		rtw_update_rx_freq_for_invalid(rtwdev, skb, &rx_status, &pkt_stat);
+		rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
 		memcpy(skb->cb, &rx_status, sizeof(rx_status));
 		ieee80211_rx_irqsafe(rtwdev->hw, skb);
 	}
-- 
cgit v1.3-3-g829e


From df3d8f463b1dfc7cb8f4fb52b1b81d290b850d03 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 8 Aug 2024 01:21:36 +0300
Subject: wifi: rtw88: usb: Support RX aggregation

The chips can be configured to aggregate several frames into a single
USB transfer. Modify rtw_usb_rx_handler() to support this case.

RX aggregation improves the RX speed of RTL8811CU on certain ARM
systems, like the NanoPi NEO Core2. It also improves the RX speed of
RTL8822CU on some x86_64 systems.

Currently none of the chips are configured to aggregate frames.

Tested with RTL8822CU, RTL8811CU, and RTL8723DU.

Reviewed-by: Sascha Hauer <s.hauer@pengutronix.de>
Tested-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/f845826d-de71-492d-9a22-e48c07989a1f@gmail.com
---
 drivers/net/wireless/realtek/rtw88/usb.c | 61 +++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 10f1d724370e..64d68366812c 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -546,11 +546,12 @@ static void rtw_usb_rx_handler(struct work_struct *work)
 	struct rtw_usb *rtwusb = container_of(work, struct rtw_usb, rx_work);
 	struct rtw_dev *rtwdev = rtwusb->rtwdev;
 	const struct rtw_chip_info *chip = rtwdev->chip;
-	struct rtw_rx_pkt_stat pkt_stat;
+	u32 pkt_desc_sz = chip->rx_pkt_desc_sz;
 	struct ieee80211_rx_status rx_status;
+	u32 pkt_offset, next_pkt, urb_len;
+	struct rtw_rx_pkt_stat pkt_stat;
+	struct sk_buff *next_skb;
 	struct sk_buff *skb;
-	u32 pkt_desc_sz = chip->rx_pkt_desc_sz;
-	u32 pkt_offset;
 	u8 *rx_desc;
 	int limit;
 
@@ -559,31 +560,48 @@ static void rtw_usb_rx_handler(struct work_struct *work)
 		if (!skb)
 			break;
 
-		rx_desc = skb->data;
-		chip->ops->query_rx_desc(rtwdev, rx_desc, &pkt_stat,
-					 &rx_status);
-		pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz +
-			     pkt_stat.shift;
-
-		if (pkt_stat.is_c2h) {
-			skb_put(skb, pkt_stat.pkt_len + pkt_offset);
-			rtw_fw_c2h_cmd_rx_irqsafe(rtwdev, pkt_offset, skb);
-			continue;
-		}
-
 		if (skb_queue_len(&rtwusb->rx_queue) >= RTW_USB_MAX_RXQ_LEN) {
 			dev_dbg_ratelimited(rtwdev->dev, "failed to get rx_queue, overflow\n");
 			dev_kfree_skb_any(skb);
 			continue;
 		}
 
-		skb_put(skb, pkt_stat.pkt_len);
-		skb_reserve(skb, pkt_offset);
+		urb_len = skb->len;
+
+		do {
+			rx_desc = skb->data;
+			chip->ops->query_rx_desc(rtwdev, rx_desc, &pkt_stat,
+						 &rx_status);
+			pkt_offset = pkt_desc_sz + pkt_stat.drv_info_sz +
+				     pkt_stat.shift;
+
+			next_pkt = round_up(pkt_stat.pkt_len + pkt_offset, 8);
+
+			if (urb_len >= next_pkt + pkt_desc_sz)
+				next_skb = skb_clone(skb, GFP_KERNEL);
+			else
+				next_skb = NULL;
+
+			if (pkt_stat.is_c2h) {
+				skb_trim(skb, pkt_stat.pkt_len + pkt_offset);
+				rtw_fw_c2h_cmd_rx_irqsafe(rtwdev, pkt_offset, skb);
+			} else {
+				skb_pull(skb, pkt_offset);
+				skb_trim(skb, pkt_stat.pkt_len);
+				rtw_update_rx_freq_for_invalid(rtwdev, skb,
+							       &rx_status,
+							       &pkt_stat);
+				rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
+				memcpy(skb->cb, &rx_status, sizeof(rx_status));
+				ieee80211_rx_irqsafe(rtwdev->hw, skb);
+			}
+
+			skb = next_skb;
+			if (skb)
+				skb_pull(skb, next_pkt);
 
-		rtw_update_rx_freq_for_invalid(rtwdev, skb, &rx_status, &pkt_stat);
-		rtw_rx_stats(rtwdev, pkt_stat.vif, skb);
-		memcpy(skb->cb, &rx_status, sizeof(rx_status));
-		ieee80211_rx_irqsafe(rtwdev->hw, skb);
+			urb_len -= next_pkt;
+		} while (skb);
 	}
 }
 
@@ -627,6 +645,7 @@ static void rtw_usb_read_port_complete(struct urb *urb)
 			if (skb)
 				dev_kfree_skb_any(skb);
 		} else {
+			skb_put(skb, urb->actual_length);
 			skb_queue_tail(&rtwusb->rx_queue, skb);
 			queue_work(rtwusb->rxwq, &rtwusb->rx_work);
 		}
-- 
cgit v1.3-3-g829e


From 002a5db9a52a0e7af0fa9a450d31049748435748 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Thu, 8 Aug 2024 01:23:06 +0300
Subject: wifi: rtw88: Enable USB RX aggregation for 8822c/8822b/8821c

Enable USB RX aggregation when there is at least 1 Mbps RX or TX
traffic, otherwise disable it.

USB RX aggregation improves the RX speed of RTL8811CU on certain ARM
systems, like the NanoPi NEO Core2. Before: 28 Mbps, after: 231 Mbps.

It also improves the RX speed of RTL8822CU on some x86_64 systems.
Before: ~200 Mbps, after: ~300 Mbps.

The official drivers for these chips use the same logic for SDIO, but
for some reason the SDIO driver in rtw88 always enables RX aggregation,
so this patch only toggles aggregation for USB devices.

RTL8703B is likely not found in USB devices, and RTL8723DU doesn't like
aggregation.

Tested-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/b4c0d54c-6755-4b0f-9dd7-f9196fd74b68@gmail.com
---
 drivers/net/wireless/realtek/rtw88/hci.h  |  7 ++++++
 drivers/net/wireless/realtek/rtw88/main.c | 13 ++++++----
 drivers/net/wireless/realtek/rtw88/pci.c  |  1 +
 drivers/net/wireless/realtek/rtw88/sdio.c |  1 +
 drivers/net/wireless/realtek/rtw88/usb.c  | 40 +++++++++++++++++++++++++++++++
 5 files changed, 58 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/hci.h b/drivers/net/wireless/realtek/rtw88/hci.h
index 830d7532f2a3..96aeda26014e 100644
--- a/drivers/net/wireless/realtek/rtw88/hci.h
+++ b/drivers/net/wireless/realtek/rtw88/hci.h
@@ -18,6 +18,7 @@ struct rtw_hci_ops {
 	void (*deep_ps)(struct rtw_dev *rtwdev, bool enter);
 	void (*link_ps)(struct rtw_dev *rtwdev, bool enter);
 	void (*interface_cfg)(struct rtw_dev *rtwdev);
+	void (*dynamic_rx_agg)(struct rtw_dev *rtwdev, bool enable);
 
 	int (*write_data_rsvd_page)(struct rtw_dev *rtwdev, u8 *buf, u32 size);
 	int (*write_data_h2c)(struct rtw_dev *rtwdev, u8 *buf, u32 size);
@@ -72,6 +73,12 @@ static inline void rtw_hci_interface_cfg(struct rtw_dev *rtwdev)
 	rtwdev->hci.ops->interface_cfg(rtwdev);
 }
 
+static inline void rtw_hci_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable)
+{
+	if (rtwdev->hci.ops->dynamic_rx_agg)
+		rtwdev->hci.ops->dynamic_rx_agg(rtwdev, enable);
+}
+
 static inline int
 rtw_hci_write_data_rsvd_page(struct rtw_dev *rtwdev, u8 *buf, u32 size)
 {
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 9c58b7a41b95..b0c9b0ff7017 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -212,6 +212,7 @@ static void rtw_watch_dog_work(struct work_struct *work)
 	struct rtw_traffic_stats *stats = &rtwdev->stats;
 	struct rtw_watch_dog_iter_data data = {};
 	bool busy_traffic = test_bit(RTW_FLAG_BUSY_TRAFFIC, rtwdev->flags);
+	u32 tx_unicast_mbps, rx_unicast_mbps;
 	bool ps_active;
 
 	mutex_lock(&rtwdev->mutex);
@@ -236,10 +237,11 @@ static void rtw_watch_dog_work(struct work_struct *work)
 	else
 		ps_active = false;
 
-	ewma_tp_add(&stats->tx_ewma_tp,
-		    (u32)(stats->tx_unicast >> RTW_TP_SHIFT));
-	ewma_tp_add(&stats->rx_ewma_tp,
-		    (u32)(stats->rx_unicast >> RTW_TP_SHIFT));
+	tx_unicast_mbps = stats->tx_unicast >> RTW_TP_SHIFT;
+	rx_unicast_mbps = stats->rx_unicast >> RTW_TP_SHIFT;
+
+	ewma_tp_add(&stats->tx_ewma_tp, tx_unicast_mbps);
+	ewma_tp_add(&stats->rx_ewma_tp, rx_unicast_mbps);
 	stats->tx_throughput = ewma_tp_read(&stats->tx_ewma_tp);
 	stats->rx_throughput = ewma_tp_read(&stats->rx_ewma_tp);
 
@@ -259,6 +261,9 @@ static void rtw_watch_dog_work(struct work_struct *work)
 
 	rtw_phy_dynamic_mechanism(rtwdev);
 
+	rtw_hci_dynamic_rx_agg(rtwdev,
+			       tx_unicast_mbps >= 1 || rx_unicast_mbps >= 1);
+
 	data.rtwdev = rtwdev;
 	/* rtw_iterate_vifs internally uses an atomic iterator which is needed
 	 * to avoid taking local->iflist_mtx mutex
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 5d0580da13fb..0b9b8807af2c 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -1601,6 +1601,7 @@ static struct rtw_hci_ops rtw_pci_ops = {
 	.deep_ps = rtw_pci_deep_ps,
 	.link_ps = rtw_pci_link_ps,
 	.interface_cfg = rtw_pci_interface_cfg,
+	.dynamic_rx_agg = NULL,
 
 	.read8 = rtw_pci_read8,
 	.read16 = rtw_pci_read16,
diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c
index 763aa8212a4b..21d0754dd7f6 100644
--- a/drivers/net/wireless/realtek/rtw88/sdio.c
+++ b/drivers/net/wireless/realtek/rtw88/sdio.c
@@ -1157,6 +1157,7 @@ static struct rtw_hci_ops rtw_sdio_ops = {
 	.deep_ps = rtw_sdio_deep_ps,
 	.link_ps = rtw_sdio_link_ps,
 	.interface_cfg = rtw_sdio_interface_cfg,
+	.dynamic_rx_agg = NULL,
 
 	.read8 = rtw_sdio_read8,
 	.read16 = rtw_sdio_read16,
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index 64d68366812c..e83ab6fb83f5 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -766,6 +766,45 @@ static void rtw_usb_interface_cfg(struct rtw_dev *rtwdev)
 	rtw_usb_init_burst_pkt_len(rtwdev);
 }
 
+static void rtw_usb_dynamic_rx_agg_v1(struct rtw_dev *rtwdev, bool enable)
+{
+	u8 size, timeout;
+	u16 val16;
+
+	rtw_write32_set(rtwdev, REG_RXDMA_AGG_PG_TH, BIT_EN_PRE_CALC);
+	rtw_write8_set(rtwdev, REG_TXDMA_PQ_MAP, BIT_RXDMA_AGG_EN);
+	rtw_write8_clr(rtwdev, REG_RXDMA_AGG_PG_TH + 3, BIT(7));
+
+	if (enable) {
+		size = 0x5;
+		timeout = 0x20;
+	} else {
+		size = 0x0;
+		timeout = 0x1;
+	}
+	val16 = u16_encode_bits(size, BIT_RXDMA_AGG_PG_TH) |
+		u16_encode_bits(timeout, BIT_DMA_AGG_TO_V1);
+
+	rtw_write16(rtwdev, REG_RXDMA_AGG_PG_TH, val16);
+}
+
+static void rtw_usb_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable)
+{
+	switch (rtwdev->chip->id) {
+	case RTW_CHIP_TYPE_8822C:
+	case RTW_CHIP_TYPE_8822B:
+	case RTW_CHIP_TYPE_8821C:
+		rtw_usb_dynamic_rx_agg_v1(rtwdev, enable);
+		break;
+	case RTW_CHIP_TYPE_8723D:
+		/* Doesn't like aggregation. */
+		break;
+	case RTW_CHIP_TYPE_8703B:
+		/* Likely not found in USB devices. */
+		break;
+	}
+}
+
 static struct rtw_hci_ops rtw_usb_ops = {
 	.tx_write = rtw_usb_tx_write,
 	.tx_kick_off = rtw_usb_tx_kick_off,
@@ -775,6 +814,7 @@ static struct rtw_hci_ops rtw_usb_ops = {
 	.deep_ps = rtw_usb_deep_ps,
 	.link_ps = rtw_usb_link_ps,
 	.interface_cfg = rtw_usb_interface_cfg,
+	.dynamic_rx_agg = rtw_usb_dynamic_rx_agg,
 
 	.write8  = rtw_usb_write8,
 	.write16 = rtw_usb_write16,
-- 
cgit v1.3-3-g829e


From a39036847fa3a0cc09895e1693ef3ab5b74dce1e Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 6 Aug 2024 11:56:01 +0100
Subject: bnx2x: Provide declaration of dmae_reg_go_c in header

Provide declaration of dmae_reg_go_c in header.
This symbol is defined in bnx2x_main.c.
And used in that file and bnx2x_stats.c.

However, Sparse complains that there is no declaration
of the symbol in dmae_reg_go_c nor is the symbol static.

 .../bnx2x_main.c:291:11: warning: symbol 'dmae_reg_go_c' was not declared. Should it be static?

Address this by moving the declaration from bnx2x_stats.c to bnx2x_reg.h.

No functional change intended.
Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240806-bnx2x-dec-v1-1-ae844ec785e4@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h   | 2 ++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 4e9215bce4ad..a018f251d198 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -868,6 +868,8 @@
 #define DORQ_REG_VF_TYPE_VALUE_0				 0x170258
 #define DORQ_REG_VF_USAGE_CT_LIMIT				 0x170340
 
+extern const u32 dmae_reg_go_c[];
+
 /* [RW 4] Initial activity counter value on the load request; when the
    shortcut is done. */
 #define DORQ_REG_SHRT_ACT_CNT					 0x170070
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 2bb133ae61c3..ba6729f2f9c0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -23,8 +23,6 @@
 #include "bnx2x_cmn.h"
 #include "bnx2x_sriov.h"
 
-extern const u32 dmae_reg_go_c[];
-
 /* Statistics */
 
 /*
-- 
cgit v1.3-3-g829e


From df665ab188cdca8b8b3e0cca84a6511c395f9ece Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 7 Aug 2024 12:02:53 -0700
Subject: net: atlantic: use ethtool_sprintf

Allows simplifying get_strings and avoids manual pointer manipulation.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20240807190303.6143-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index d0aecd1d7357..38f22918c699 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -279,18 +279,16 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 
 			for (i = 0; i < cfg->vecs; i++) {
 				for (si = 0; si < rx_stat_cnt; si++) {
-					snprintf(p, ETH_GSTRING_LEN,
+					ethtool_sprintf(&p,
 					     aq_ethtool_queue_rx_stat_names[si],
 					     tc_string,
 					     AQ_NIC_CFG_TCVEC2RING(cfg, tc, i));
-					p += ETH_GSTRING_LEN;
 				}
 				for (si = 0; si < tx_stat_cnt; si++) {
-					snprintf(p, ETH_GSTRING_LEN,
+					ethtool_sprintf(&p,
 					     aq_ethtool_queue_tx_stat_names[si],
 					     tc_string,
 					     AQ_NIC_CFG_TCVEC2RING(cfg, tc, i));
-					p += ETH_GSTRING_LEN;
 				}
 			}
 		}
@@ -305,20 +303,18 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 
 			for (i = 0; i < max(rx_ring_cnt, tx_ring_cnt); i++) {
 				for (si = 0; si < rx_stat_cnt; si++) {
-					snprintf(p, ETH_GSTRING_LEN,
+					ethtool_sprintf(&p,
 						 aq_ethtool_queue_rx_stat_names[si],
 						 tc_string,
 						 i ? PTP_HWST_RING_IDX : ptp_ring_idx);
-					p += ETH_GSTRING_LEN;
 				}
 				if (i >= tx_ring_cnt)
 					continue;
 				for (si = 0; si < tx_stat_cnt; si++) {
-					snprintf(p, ETH_GSTRING_LEN,
+					ethtool_sprintf(&p,
 						 aq_ethtool_queue_tx_stat_names[si],
 						 tc_string,
 						 i ? PTP_HWST_RING_IDX : ptp_ring_idx);
-					p += ETH_GSTRING_LEN;
 				}
 			}
 		}
@@ -338,9 +334,8 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 			for (si = 0;
 				si < ARRAY_SIZE(aq_macsec_txsc_stat_names);
 				si++) {
-				snprintf(p, ETH_GSTRING_LEN,
+				ethtool_sprintf(&p,
 					 aq_macsec_txsc_stat_names[si], i);
-				p += ETH_GSTRING_LEN;
 			}
 			aq_txsc = &nic->macsec_cfg->aq_txsc[i];
 			for (sa = 0; sa < MACSEC_NUM_AN; sa++) {
@@ -349,10 +344,9 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 				for (si = 0;
 				     si < ARRAY_SIZE(aq_macsec_txsa_stat_names);
 				     si++) {
-					snprintf(p, ETH_GSTRING_LEN,
+					ethtool_sprintf(&p,
 						 aq_macsec_txsa_stat_names[si],
 						 i, sa);
-					p += ETH_GSTRING_LEN;
 				}
 			}
 		}
@@ -369,10 +363,9 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 				for (si = 0;
 				     si < ARRAY_SIZE(aq_macsec_rxsa_stat_names);
 				     si++) {
-					snprintf(p, ETH_GSTRING_LEN,
+					ethtool_sprintf(&p,
 						 aq_macsec_rxsa_stat_names[si],
 						 i, sa);
-					p += ETH_GSTRING_LEN;
 				}
 			}
 		}
-- 
cgit v1.3-3-g829e


From ceb627435b00fe3bcee5957aeb3e5282a1f06eb6 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Wed, 7 Aug 2024 17:06:13 +0100
Subject: net: ethtool: check rxfh_max_num_contexts != 1 at register time

A value of 1 doesn't make sense, as it implies the only allowed
 context ID is 0, which is reserved for the default context - in
 which case the driver should just not claim to support custom
 RSS contexts at all.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://lore.kernel.org/c07725b3a3d0b0a63b85e230f9c77af59d4d07f8.1723045898.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 07032babd1b6..5f714bbbef19 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -654,6 +654,8 @@ int ethtool_check_ops(const struct ethtool_ops *ops)
 {
 	if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params))
 		return -EINVAL;
+	if (WARN_ON(ops->rxfh_max_num_contexts == 1))
+		return -EINVAL;
 	/* NOTE: sufficiently insane drivers may swap ethtool_ops at runtime,
 	 * the fact that ops are checked at registration time does not
 	 * mean the ops attached to a netdev later on are sane.
-- 
cgit v1.3-3-g829e


From 09612576046a3cd29bd2b2b88c5813b1dfe96775 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Wed, 7 Aug 2024 14:22:26 +0200
Subject: net: sungem_phy: Constify struct mii_phy_def

'struct mii_phy_def' are not modified in this driver.

Constifying these structures moves some data to a read-only section, so
increase overall security.

While at it fix the checkpatch warning related to this patch (some missing
newlines and spaces around *)

On a x86_64, with allmodconfig:
Before:
======
  27709	    928	      0	  28637	   6fdd	drivers/net/sungem_phy.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
  28157	    476	      0	  28633	   6fd9	drivers/net/sungem_phy.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/54c3b30930f80f4895e6fa2f4234714fdea4ef4e.1723033266.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/sungem_phy.c   | 35 +++++++++++++++++++----------------
 include/linux/sungem_phy.h |  2 +-
 2 files changed, 20 insertions(+), 17 deletions(-)

diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index d591e33268e5..55aa8d0c8e1f 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -893,7 +893,7 @@ static const struct mii_phy_ops bcm5201_phy_ops = {
 	.read_link	= genmii_read_link,
 };
 
-static struct mii_phy_def bcm5201_phy_def = {
+static const struct mii_phy_def bcm5201_phy_def = {
 	.phy_id		= 0x00406210,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5201",
@@ -912,7 +912,7 @@ static const struct mii_phy_ops bcm5221_phy_ops = {
 	.read_link	= genmii_read_link,
 };
 
-static struct mii_phy_def bcm5221_phy_def = {
+static const struct mii_phy_def bcm5221_phy_def = {
 	.phy_id		= 0x004061e0,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5221",
@@ -930,7 +930,8 @@ static const struct mii_phy_ops bcm5241_phy_ops = {
 	.poll_link	= genmii_poll_link,
 	.read_link	= genmii_read_link,
 };
-static struct mii_phy_def bcm5241_phy_def = {
+
+static const struct mii_phy_def bcm5241_phy_def = {
 	.phy_id		= 0x0143bc30,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5241",
@@ -949,7 +950,7 @@ static const struct mii_phy_ops bcm5400_phy_ops = {
 	.read_link	= bcm54xx_read_link,
 };
 
-static struct mii_phy_def bcm5400_phy_def = {
+static const struct mii_phy_def bcm5400_phy_def = {
 	.phy_id		= 0x00206040,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5400",
@@ -968,7 +969,7 @@ static const struct mii_phy_ops bcm5401_phy_ops = {
 	.read_link	= bcm54xx_read_link,
 };
 
-static struct mii_phy_def bcm5401_phy_def = {
+static const struct mii_phy_def bcm5401_phy_def = {
 	.phy_id		= 0x00206050,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5401",
@@ -987,7 +988,7 @@ static const struct mii_phy_ops bcm5411_phy_ops = {
 	.read_link	= bcm54xx_read_link,
 };
 
-static struct mii_phy_def bcm5411_phy_def = {
+static const struct mii_phy_def bcm5411_phy_def = {
 	.phy_id		= 0x00206070,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5411",
@@ -1007,7 +1008,7 @@ static const struct mii_phy_ops bcm5421_phy_ops = {
 	.enable_fiber   = bcm5421_enable_fiber,
 };
 
-static struct mii_phy_def bcm5421_phy_def = {
+static const struct mii_phy_def bcm5421_phy_def = {
 	.phy_id		= 0x002060e0,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5421",
@@ -1026,7 +1027,7 @@ static const struct mii_phy_ops bcm5421k2_phy_ops = {
 	.read_link	= bcm54xx_read_link,
 };
 
-static struct mii_phy_def bcm5421k2_phy_def = {
+static const struct mii_phy_def bcm5421k2_phy_def = {
 	.phy_id		= 0x002062e0,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5421-K2",
@@ -1045,7 +1046,7 @@ static const struct mii_phy_ops bcm5461_phy_ops = {
 	.enable_fiber   = bcm5461_enable_fiber,
 };
 
-static struct mii_phy_def bcm5461_phy_def = {
+static const struct mii_phy_def bcm5461_phy_def = {
 	.phy_id		= 0x002060c0,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5461",
@@ -1064,7 +1065,7 @@ static const struct mii_phy_ops bcm5462V_phy_ops = {
 	.read_link	= bcm54xx_read_link,
 };
 
-static struct mii_phy_def bcm5462V_phy_def = {
+static const struct mii_phy_def bcm5462V_phy_def = {
 	.phy_id		= 0x002060d0,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "BCM5462-Vesta",
@@ -1094,7 +1095,7 @@ static const struct mii_phy_ops marvell88e1111_phy_ops = {
 /* two revs in darwin for the 88e1101 ... I could use a datasheet
  * to get the proper names...
  */
-static struct mii_phy_def marvell88e1101v1_phy_def = {
+static const struct mii_phy_def marvell88e1101v1_phy_def = {
 	.phy_id		= 0x01410c20,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Marvell 88E1101v1",
@@ -1102,7 +1103,8 @@ static struct mii_phy_def marvell88e1101v1_phy_def = {
 	.magic_aneg	= 1,
 	.ops		= &marvell88e1101_phy_ops
 };
-static struct mii_phy_def marvell88e1101v2_phy_def = {
+
+static const struct mii_phy_def marvell88e1101v2_phy_def = {
 	.phy_id		= 0x01410c60,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Marvell 88E1101v2",
@@ -1110,7 +1112,8 @@ static struct mii_phy_def marvell88e1101v2_phy_def = {
 	.magic_aneg	= 1,
 	.ops		= &marvell88e1101_phy_ops
 };
-static struct mii_phy_def marvell88e1111_phy_def = {
+
+static const struct mii_phy_def marvell88e1111_phy_def = {
 	.phy_id		= 0x01410cc0,
 	.phy_id_mask	= 0xfffffff0,
 	.name		= "Marvell 88E1111",
@@ -1127,7 +1130,7 @@ static const struct mii_phy_ops generic_phy_ops = {
 	.read_link	= genmii_read_link
 };
 
-static struct mii_phy_def genmii_phy_def = {
+static const struct mii_phy_def genmii_phy_def = {
 	.phy_id		= 0x00000000,
 	.phy_id_mask	= 0x00000000,
 	.name		= "Generic MII",
@@ -1136,7 +1139,7 @@ static struct mii_phy_def genmii_phy_def = {
 	.ops		= &generic_phy_ops
 };
 
-static struct mii_phy_def* mii_phy_table[] = {
+static const struct mii_phy_def *mii_phy_table[] = {
 	&bcm5201_phy_def,
 	&bcm5221_phy_def,
 	&bcm5241_phy_def,
@@ -1156,9 +1159,9 @@ static struct mii_phy_def* mii_phy_table[] = {
 
 int sungem_phy_probe(struct mii_phy *phy, int mii_id)
 {
+	const struct mii_phy_def *def;
 	int rc;
 	u32 id;
-	struct mii_phy_def* def;
 	int i;
 
 	/* We do not reset the mii_phy structure as the driver
diff --git a/include/linux/sungem_phy.h b/include/linux/sungem_phy.h
index c505f30e8b68..eecc7eb63bfb 100644
--- a/include/linux/sungem_phy.h
+++ b/include/linux/sungem_phy.h
@@ -40,7 +40,7 @@ enum {
 /* An instance of a PHY, partially borrowed from mii_if_info */
 struct mii_phy
 {
-	struct mii_phy_def*	def;
+	const struct mii_phy_def *def;
 	u32			advertising;
 	int			mii_id;
 
-- 
cgit v1.3-3-g829e


From eb3ab13d997a2f12ec9d557b6ae2aea4e28e2bc3 Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Date: Wed, 7 Aug 2024 14:12:15 +0200
Subject: net: ti: icssg_prueth: populate netdev of_node

Allow of_find_net_device_by_node() to find icssg_prueth ports and make
the individual ports' of_nodes available in sysfs.

Signed-off-by: Matthias Schiffer <matthias.schiffer@ew.tq-group.com>
Reviewed-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240807121215.3178964-1-matthias.schiffer@ew.tq-group.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c     | 1 +
 drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 9dc9de39bb8f..53a3e44b99a2 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -857,6 +857,7 @@ static int prueth_netdev_init(struct prueth *prueth,
 	}
 	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
 
+	ndev->dev.of_node = eth_node;
 	ndev->min_mtu = PRUETH_MIN_PKT_SIZE;
 	ndev->max_mtu = PRUETH_MAX_MTU;
 	ndev->netdev_ops = &emac_netdev_ops;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
index 54b7e27608ce..292f04d29f4f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -847,6 +847,7 @@ static int prueth_netdev_init(struct prueth *prueth,
 	}
 	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
 
+	ndev->dev.of_node = eth_node;
 	ndev->min_mtu = PRUETH_MIN_PKT_SIZE;
 	ndev->max_mtu = PRUETH_MAX_MTU;
 	ndev->netdev_ops = &emac_netdev_ops;
-- 
cgit v1.3-3-g829e


From 2524d6c28bdcb114372e86354c88d2e47eb1019d Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Mon, 5 Aug 2024 23:23:22 +0200
Subject: net: dsa: vsc73xx: use defined values in phy operations

This commit changes magic numbers in phy operations.
Some shifted registers was replaced with bitfield macros.

No functional changes done.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/vitesse-vsc73xx-core.c | 45 +++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 12 deletions(-)

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index 1711e780e65b..a82b550a9e40 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -21,6 +21,7 @@
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/bitops.h>
+#include <linux/bitfield.h>
 #include <linux/if_bridge.h>
 #include <linux/if_vlan.h>
 #include <linux/etherdevice.h>
@@ -41,7 +42,8 @@
 #define VSC73XX_BLOCK_SYSTEM	0x7 /* Only subblock 0 */
 
 /* MII Block subblock */
-#define VSC73XX_BLOCK_MII_INTERNAL     0x0 /* Internal MDIO subblock */
+#define VSC73XX_BLOCK_MII_INTERNAL	0x0 /* Internal MDIO subblock */
+#define VSC73XX_BLOCK_MII_EXTERNAL	0x1 /* External MDIO subblock */
 
 #define CPU_PORT	6 /* CPU port */
 
@@ -224,10 +226,23 @@
 #define VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE	3
 
 /* MII block 3 registers */
-#define VSC73XX_MII_STAT	0x0
-#define VSC73XX_MII_CMD		0x1
-#define VSC73XX_MII_DATA	0x2
-#define VSC73XX_MII_MPRES	0x3
+#define VSC73XX_MII_STAT		0x0
+#define VSC73XX_MII_CMD			0x1
+#define VSC73XX_MII_DATA		0x2
+#define VSC73XX_MII_MPRES		0x3
+
+#define VSC73XX_MII_STAT_BUSY		BIT(3)
+#define VSC73XX_MII_STAT_READ		BIT(2)
+#define VSC73XX_MII_STAT_WRITE		BIT(1)
+
+#define VSC73XX_MII_CMD_SCAN		BIT(27)
+#define VSC73XX_MII_CMD_OPERATION	BIT(26)
+#define VSC73XX_MII_CMD_PHY_ADDR	GENMASK(25, 21)
+#define VSC73XX_MII_CMD_PHY_REG		GENMASK(20, 16)
+#define VSC73XX_MII_CMD_WRITE_DATA	GENMASK(15, 0)
+
+#define VSC73XX_MII_DATA_FAILURE	BIT(16)
+#define VSC73XX_MII_DATA_READ_DATA	GENMASK(15, 0)
 
 #define VSC73XX_MII_MPRES_NOPREAMBLE	BIT(6)
 #define VSC73XX_MII_MPRES_PRESCALEVAL	GENMASK(5, 0)
@@ -543,20 +558,24 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
 	int ret;
 
 	/* Setting bit 26 means "read" */
-	cmd = BIT(26) | (phy << 21) | (regnum << 16);
-	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+	cmd = VSC73XX_MII_CMD_OPERATION |
+	      FIELD_PREP(VSC73XX_MII_CMD_PHY_ADDR, phy) |
+	      FIELD_PREP(VSC73XX_MII_CMD_PHY_REG, regnum);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL,
+			    VSC73XX_MII_CMD, cmd);
 	if (ret)
 		return ret;
 	msleep(2);
-	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val);
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL,
+			   VSC73XX_MII_DATA, &val);
 	if (ret)
 		return ret;
-	if (val & BIT(16)) {
+	if (val & VSC73XX_MII_DATA_FAILURE) {
 		dev_err(vsc->dev, "reading reg %02x from phy%d failed\n",
 			regnum, phy);
 		return -EIO;
 	}
-	val &= 0xFFFFU;
+	val &= VSC73XX_MII_DATA_READ_DATA;
 
 	dev_dbg(vsc->dev, "read reg %02x from phy%d = %04x\n",
 		regnum, phy, val);
@@ -582,8 +601,10 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
 		return 0;
 	}
 
-	cmd = (phy << 21) | (regnum << 16);
-	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+	cmd = FIELD_PREP(VSC73XX_MII_CMD_PHY_ADDR, phy) |
+	      FIELD_PREP(VSC73XX_MII_CMD_PHY_REG, regnum);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL,
+			    VSC73XX_MII_CMD, cmd);
 	if (ret)
 		return ret;
 
-- 
cgit v1.3-3-g829e


From 36fb51479e3c1112013f60f01e3b9725f8f9baf7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 6 Aug 2024 11:52:01 +0100
Subject: net: stmmac: xgmac: use const char arrays for string constants

Jiri Slaby advises me that the preferred mechanism for declaring
string constants is static char arrays, so use that here.

This mostly reverts
commit 1692b9775e74 ("net: stmmac: xgmac: use #define for string constants")

That commit was a fix for
commit 46eba193d04f ("net: stmmac: xgmac: fix handling of DPP safety error for DMA channels").
The fix being replacing const char * with #defines in order to address
compilation failures observed on GCC 6 through 10.

Compile tested only.
No functional change intended.

Suggested-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/netdev/485dbc5a-a04b-40c2-9481-955eaa5ce2e2@kernel.org/
Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/stmicro/stmmac/dwxgmac2_core.c    | 69 +++++++++++-----------
 1 file changed, 34 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index f196cd99d510..cbf2dd976ab1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -846,42 +846,41 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= {
 	{ false, "UNKNOWN", "Unknown Error" }, /* 31 */
 };
 
-#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error"
-#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error"
-
+static const char dpp_rx_err[] = "Read Rx Descriptor Parity checker Error";
+static const char dpp_tx_err[] = "Read Tx Descriptor Parity checker Error";
 static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = {
-	{ true, "TDPES0", DPP_TX_ERR },
-	{ true, "TDPES1", DPP_TX_ERR },
-	{ true, "TDPES2", DPP_TX_ERR },
-	{ true, "TDPES3", DPP_TX_ERR },
-	{ true, "TDPES4", DPP_TX_ERR },
-	{ true, "TDPES5", DPP_TX_ERR },
-	{ true, "TDPES6", DPP_TX_ERR },
-	{ true, "TDPES7", DPP_TX_ERR },
-	{ true, "TDPES8", DPP_TX_ERR },
-	{ true, "TDPES9", DPP_TX_ERR },
-	{ true, "TDPES10", DPP_TX_ERR },
-	{ true, "TDPES11", DPP_TX_ERR },
-	{ true, "TDPES12", DPP_TX_ERR },
-	{ true, "TDPES13", DPP_TX_ERR },
-	{ true, "TDPES14", DPP_TX_ERR },
-	{ true, "TDPES15", DPP_TX_ERR },
-	{ true, "RDPES0", DPP_RX_ERR },
-	{ true, "RDPES1", DPP_RX_ERR },
-	{ true, "RDPES2", DPP_RX_ERR },
-	{ true, "RDPES3", DPP_RX_ERR },
-	{ true, "RDPES4", DPP_RX_ERR },
-	{ true, "RDPES5", DPP_RX_ERR },
-	{ true, "RDPES6", DPP_RX_ERR },
-	{ true, "RDPES7", DPP_RX_ERR },
-	{ true, "RDPES8", DPP_RX_ERR },
-	{ true, "RDPES9", DPP_RX_ERR },
-	{ true, "RDPES10", DPP_RX_ERR },
-	{ true, "RDPES11", DPP_RX_ERR },
-	{ true, "RDPES12", DPP_RX_ERR },
-	{ true, "RDPES13", DPP_RX_ERR },
-	{ true, "RDPES14", DPP_RX_ERR },
-	{ true, "RDPES15", DPP_RX_ERR },
+	{ true, "TDPES0", dpp_tx_err },
+	{ true, "TDPES1", dpp_tx_err },
+	{ true, "TDPES2", dpp_tx_err },
+	{ true, "TDPES3", dpp_tx_err },
+	{ true, "TDPES4", dpp_tx_err },
+	{ true, "TDPES5", dpp_tx_err },
+	{ true, "TDPES6", dpp_tx_err },
+	{ true, "TDPES7", dpp_tx_err },
+	{ true, "TDPES8", dpp_tx_err },
+	{ true, "TDPES9", dpp_tx_err },
+	{ true, "TDPES10", dpp_tx_err },
+	{ true, "TDPES11", dpp_tx_err },
+	{ true, "TDPES12", dpp_tx_err },
+	{ true, "TDPES13", dpp_tx_err },
+	{ true, "TDPES14", dpp_tx_err },
+	{ true, "TDPES15", dpp_tx_err },
+	{ true, "RDPES0", dpp_rx_err },
+	{ true, "RDPES1", dpp_rx_err },
+	{ true, "RDPES2", dpp_rx_err },
+	{ true, "RDPES3", dpp_rx_err },
+	{ true, "RDPES4", dpp_rx_err },
+	{ true, "RDPES5", dpp_rx_err },
+	{ true, "RDPES6", dpp_rx_err },
+	{ true, "RDPES7", dpp_rx_err },
+	{ true, "RDPES8", dpp_rx_err },
+	{ true, "RDPES9", dpp_rx_err },
+	{ true, "RDPES10", dpp_rx_err },
+	{ true, "RDPES11", dpp_rx_err },
+	{ true, "RDPES12", dpp_rx_err },
+	{ true, "RDPES13", dpp_rx_err },
+	{ true, "RDPES14", dpp_rx_err },
+	{ true, "RDPES15", dpp_rx_err },
 };
 
 static void dwxgmac3_handle_dma_err(struct net_device *ndev,
-- 
cgit v1.3-3-g829e


From a0f6e5e9f1f8a0837a9e3ccc5a1f98cbfd2a6cf4 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Tue, 6 Aug 2024 08:38:07 -0700
Subject: .gitignore: add .gcda files

These files contain the runtime coverage data generated by gcov.

Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.gitignore b/.gitignore
index 7902adf4f7f1..38b7ab9e7dc4 100644
--- a/.gitignore
+++ b/.gitignore
@@ -24,6 +24,7 @@
 *.dwo
 *.elf
 *.gcno
+*.gcda
 *.gz
 *.i
 *.ko
-- 
cgit v1.3-3-g829e


From bc75dcc3cea797974913c6ccdbe17ed470be3da6 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Tue, 6 Aug 2024 08:38:08 -0700
Subject: net: rds: add option for GCOV profiling

To better our unit tests we need code coverage to be part of the kernel.
This patch borrows heavily from how CONFIG_GCOV_PROFILE_FTRACE is
implemented

Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/Kconfig  | 9 +++++++++
 net/rds/Makefile | 5 +++++
 2 files changed, 14 insertions(+)

diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 75cd696963b2..f007730aa2bb 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -26,3 +26,12 @@ config RDS_DEBUG
 	bool "RDS debugging messages"
 	depends on RDS
 	default n
+
+config GCOV_PROFILE_RDS
+	bool "Enable GCOV profiling on RDS"
+	depends on GCOV_KERNEL
+	help
+	  Enable GCOV profiling on RDS for checking which functions/lines
+	  are executed.
+
+	  If unsure, say N.
diff --git a/net/rds/Makefile b/net/rds/Makefile
index 8fdc118e2927..3af1ca1d965c 100644
--- a/net/rds/Makefile
+++ b/net/rds/Makefile
@@ -15,3 +15,8 @@ rds_tcp-y :=		tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \
 			tcp_send.o tcp_stats.o
 
 ccflags-$(CONFIG_RDS_DEBUG)	:=	-DRDS_DEBUG
+
+# for GCOV coverage profiling
+ifdef CONFIG_GCOV_PROFILE_RDS
+GCOV_PROFILE := y
+endif
-- 
cgit v1.3-3-g829e


From 3ade6ce1255e6e97f91b8ba77408dce9d2292df2 Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@oracle.com>
Date: Tue, 6 Aug 2024 08:38:09 -0700
Subject: selftests: rds: add testing infrastructure

This adds some basic self-testing infrastructure for RDS-TCP.

Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Allison Henderson <allison.henderson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/dev-tools/gcov.rst           |  11 ++
 MAINTAINERS                                |   1 +
 tools/testing/selftests/Makefile           |   1 +
 tools/testing/selftests/net/rds/Makefile   |  12 ++
 tools/testing/selftests/net/rds/README.txt |  41 +++++
 tools/testing/selftests/net/rds/config.sh  |  53 ++++++
 tools/testing/selftests/net/rds/run.sh     | 224 ++++++++++++++++++++++++
 tools/testing/selftests/net/rds/test.py    | 262 +++++++++++++++++++++++++++++
 8 files changed, 605 insertions(+)
 create mode 100644 tools/testing/selftests/net/rds/Makefile
 create mode 100644 tools/testing/selftests/net/rds/README.txt
 create mode 100755 tools/testing/selftests/net/rds/config.sh
 create mode 100755 tools/testing/selftests/net/rds/run.sh
 create mode 100644 tools/testing/selftests/net/rds/test.py

diff --git a/Documentation/dev-tools/gcov.rst b/Documentation/dev-tools/gcov.rst
index 5fce2b06f229..dbd26b02ff3c 100644
--- a/Documentation/dev-tools/gcov.rst
+++ b/Documentation/dev-tools/gcov.rst
@@ -75,6 +75,17 @@ Only files which are linked to the main kernel image or are compiled as
 kernel modules are supported by this mechanism.
 
 
+Module specific configs
+-----------------------
+
+Gcov kernel configs for specific modules are described below:
+
+CONFIG_GCOV_PROFILE_RDS:
+        Enables GCOV profiling on RDS for checking which functions or
+        lines are executed. This config is used by the rds selftest to
+        generate coverage reports. If left unset the report is omitted.
+
+
 Files
 -----
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 1a7ea5c7c710..7b291c3a9aa4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19197,6 +19197,7 @@ S:	Supported
 W:	https://oss.oracle.com/projects/rds/
 F:	Documentation/networking/rds.rst
 F:	net/rds/
+F:	tools/testing/selftests/net/rds/
 
 RDT - RESOURCE ALLOCATION
 M:	Fenghua Yu <fenghua.yu@intel.com>
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index bc8fe9e8f7f2..a5f1c0c27dff 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -68,6 +68,7 @@ TARGETS += net/mptcp
 TARGETS += net/openvswitch
 TARGETS += net/tcp_ao
 TARGETS += net/netfilter
+TARGETS += net/rds
 TARGETS += nsfs
 TARGETS += perf_events
 TARGETS += pidfd
diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile
new file mode 100644
index 000000000000..da9714bc7aad
--- /dev/null
+++ b/tools/testing/selftests/net/rds/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+
+all:
+	@echo mk_build_dir="$(shell pwd)" > include.sh
+
+TEST_PROGS := run.sh \
+	include.sh \
+	test.py
+
+EXTRA_CLEAN := /tmp/rds_logs
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/rds/README.txt b/tools/testing/selftests/net/rds/README.txt
new file mode 100644
index 000000000000..cbde2951ab13
--- /dev/null
+++ b/tools/testing/selftests/net/rds/README.txt
@@ -0,0 +1,41 @@
+RDS self-tests
+==============
+
+These scripts provide a coverage test for RDS-TCP by creating two
+network namespaces and running rds packets between them. A loopback
+network is provisioned with optional probability of packet loss or
+corruption. A workload of 50000 hashes, each 64 characters in size,
+are passed over an RDS socket on this test network. A passing test means
+the RDS-TCP stack was able to recover properly.  The provided config.sh
+can be used to compile the kernel with the necessary gcov options.  The
+kernel may optionally be configured to omit the coverage report as well.
+
+USAGE:
+	run.sh [-d logdir] [-l packet_loss] [-c packet_corruption]
+	       [-u packet_duplcate]
+
+OPTIONS:
+	-d	Log directory.  Defaults to tools/testing/selftests/net/rds/rds_logs
+
+	-l	Simulates a percentage of packet loss
+
+	-c	Simulates a percentage of packet corruption
+
+	-u	Simulates a percentage of packet duplication.
+
+EXAMPLE:
+
+    # Create a suitable gcov enabled .config
+    tools/testing/selftests/net/rds/config.sh -g
+
+    # Alternatly create a gcov disabled .config
+    tools/testing/selftests/net/rds/config.sh
+
+    # build the kernel
+    vng --build  --config tools/testing/selftests/net/config
+
+    # launch the tests in a VM
+    vng -v --rwdir ./ --run . --user root --cpus 4 -- \
+        "export PYTHONPATH=tools/testing/selftests/net/; tools/testing/selftests/net/rds/run.sh"
+
+An HTML coverage report will be output in tools/testing/selftests/net/rds/rds_logs/coverage/.
diff --git a/tools/testing/selftests/net/rds/config.sh b/tools/testing/selftests/net/rds/config.sh
new file mode 100755
index 000000000000..791c8dbe1095
--- /dev/null
+++ b/tools/testing/selftests/net/rds/config.sh
@@ -0,0 +1,53 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -u
+set -x
+
+unset KBUILD_OUTPUT
+
+GENERATE_GCOV_REPORT=0
+while getopts "g" opt; do
+  case ${opt} in
+    g)
+      GENERATE_GCOV_REPORT=1
+      ;;
+    :)
+      echo "USAGE: config.sh [-g]"
+      exit 1
+      ;;
+    ?)
+      echo "Invalid option: -${OPTARG}."
+      exit 1
+      ;;
+  esac
+done
+
+CONF_FILE="tools/testing/selftests/net/config"
+
+# no modules
+scripts/config --file "$CONF_FILE" --disable CONFIG_MODULES
+
+# enable RDS
+scripts/config --file "$CONF_FILE" --enable CONFIG_RDS
+scripts/config --file "$CONF_FILE" --enable CONFIG_RDS_TCP
+
+if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then
+	# instrument RDS and only RDS
+	scripts/config --file "$CONF_FILE" --enable CONFIG_GCOV_KERNEL
+	scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL
+	scripts/config --file "$CONF_FILE" --enable GCOV_PROFILE_RDS
+else
+	scripts/config --file "$CONF_FILE" --disable CONFIG_GCOV_KERNEL
+	scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL
+	scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_RDS
+fi
+
+# need network namespaces to run tests with veth network interfaces
+scripts/config --file "$CONF_FILE" --enable CONFIG_NET_NS
+scripts/config --file "$CONF_FILE" --enable CONFIG_VETH
+
+# simulate packet loss
+scripts/config --file "$CONF_FILE" --enable CONFIG_NET_SCH_NETEM
+
diff --git a/tools/testing/selftests/net/rds/run.sh b/tools/testing/selftests/net/rds/run.sh
new file mode 100755
index 000000000000..8aee244f582a
--- /dev/null
+++ b/tools/testing/selftests/net/rds/run.sh
@@ -0,0 +1,224 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -u
+
+unset KBUILD_OUTPUT
+
+current_dir="$(realpath "$(dirname "$0")")"
+build_dir="$current_dir"
+
+build_include="$current_dir/include.sh"
+if test -f "$build_include"; then
+	# this include will define "$mk_build_dir" as the location the test was
+	# built.  We will need this if the tests are installed in a location
+	# other than the kernel source
+
+	source "$build_include"
+	build_dir="$mk_build_dir"
+fi
+
+# This test requires kernel source and the *.gcda data therein
+# Locate the top level of the kernel source, and the net/rds
+# subfolder with the appropriate *.gcno object files
+ksrc_dir="$(realpath "$build_dir"/../../../../../)"
+kconfig="$ksrc_dir/.config"
+obj_dir="$ksrc_dir/net/rds"
+
+GCOV_CMD=gcov
+
+#check to see if the host has the required packages to generate a gcov report
+check_gcov_env()
+{
+	if ! which "$GCOV_CMD" > /dev/null 2>&1; then
+		echo "Warning: Could not find gcov. "
+		GENERATE_GCOV_REPORT=0
+		return
+	fi
+
+	# the gcov version must match the gcc version
+	GCC_VER=$(gcc -dumpfullversion)
+	GCOV_VER=$($GCOV_CMD -v | grep gcov | awk '{print $3}'| awk 'BEGIN {FS="-"}{print $1}')
+	if [ "$GCOV_VER" != "$GCC_VER" ]; then
+		#attempt to find a matching gcov version
+		GCOV_CMD=gcov-$(gcc -dumpversion)
+
+		if ! which "$GCOV_CMD" > /dev/null 2>&1; then
+			echo "Warning: Could not find an appropriate gcov installation. \
+				gcov version must match gcc version"
+			GENERATE_GCOV_REPORT=0
+			return
+		fi
+
+		#recheck version number of found gcov executable
+		GCOV_VER=$($GCOV_CMD -v | grep gcov | awk '{print $3}'| \
+			awk 'BEGIN {FS="-"}{print $1}')
+		if [ "$GCOV_VER" != "$GCC_VER" ]; then
+			echo "Warning: Could not find an appropriate gcov installation. \
+				gcov version must match gcc version"
+			GENERATE_GCOV_REPORT=0
+		else
+			echo "Warning: Mismatched gcc and gcov detected.  Using $GCOV_CMD"
+		fi
+	fi
+}
+
+# Check to see if the kconfig has the required configs to generate a coverage report
+check_gcov_conf()
+{
+	if ! grep -x "CONFIG_GCOV_PROFILE_RDS=y" "$kconfig" > /dev/null 2>&1; then
+		echo "INFO: CONFIG_GCOV_PROFILE_RDS should be enabled for coverage reports"
+		GENERATE_GCOV_REPORT=0
+	fi
+	if ! grep -x "CONFIG_GCOV_KERNEL=y" "$kconfig" > /dev/null 2>&1; then
+		echo "INFO: CONFIG_GCOV_KERNEL should be enabled for coverage reports"
+		GENERATE_GCOV_REPORT=0
+	fi
+	if grep -x "CONFIG_GCOV_PROFILE_ALL=y" "$kconfig" > /dev/null 2>&1; then
+		echo "INFO: CONFIG_GCOV_PROFILE_ALL should be disabled for coverage reports"
+		GENERATE_GCOV_REPORT=0
+	fi
+
+	if [ "$GENERATE_GCOV_REPORT" -eq 0 ]; then
+		echo "To enable gcov reports, please run "\
+			"\"tools/testing/selftests/net/rds/config.sh -g\" and rebuild the kernel"
+	else
+		# if we have the required kernel configs, proceed to check the environment to
+		# ensure we have the required gcov packages
+		check_gcov_env
+	fi
+}
+
+# Kselftest framework requirement - SKIP code is 4.
+check_conf_enabled() {
+	if ! grep -x "$1=y" "$kconfig" > /dev/null 2>&1; then
+		echo "selftests: [SKIP] This test requires $1 enabled"
+		echo "Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel"
+		exit 4
+	fi
+}
+check_conf_disabled() {
+	if grep -x "$1=y" "$kconfig" > /dev/null 2>&1; then
+		echo "selftests: [SKIP] This test requires $1 disabled"
+		echo "Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel"
+		exit 4
+	fi
+}
+check_conf() {
+	check_conf_enabled CONFIG_NET_SCH_NETEM
+	check_conf_enabled CONFIG_VETH
+	check_conf_enabled CONFIG_NET_NS
+	check_conf_enabled CONFIG_RDS_TCP
+	check_conf_enabled CONFIG_RDS
+	check_conf_disabled CONFIG_MODULES
+}
+
+check_env()
+{
+	if ! test -d "$obj_dir"; then
+		echo "selftests: [SKIP] This test requires a kernel source tree"
+		exit 4
+	fi
+	if ! test -e "$kconfig"; then
+		echo "selftests: [SKIP] This test requires a configured kernel source tree"
+		exit 4
+	fi
+	if ! which strace > /dev/null 2>&1; then
+		echo "selftests: [SKIP] Could not run test without strace"
+		exit 4
+	fi
+	if ! which tcpdump > /dev/null 2>&1; then
+		echo "selftests: [SKIP] Could not run test without tcpdump"
+		exit 4
+	fi
+
+	if ! which python3 > /dev/null 2>&1; then
+		echo "selftests: [SKIP] Could not run test without python3"
+		exit 4
+	fi
+
+	python_major=$(python3 -c "import sys; print(sys.version_info[0])")
+	python_minor=$(python3 -c "import sys; print(sys.version_info[1])")
+	if [[ python_major -lt 3 || ( python_major -eq 3 && python_minor -lt 9 ) ]] ; then
+		echo "selftests: [SKIP] Could not run test without at least python3.9"
+		python3 -V
+		exit 4
+	fi
+}
+
+LOG_DIR="$current_dir"/rds_logs
+PLOSS=0
+PCORRUPT=0
+PDUP=0
+GENERATE_GCOV_REPORT=1
+while getopts "d:l:c:u:" opt; do
+  case ${opt} in
+    d)
+      LOG_DIR=${OPTARG}
+      ;;
+    l)
+      PLOSS=${OPTARG}
+      ;;
+    c)
+      PCORRUPT=${OPTARG}
+      ;;
+    u)
+      PDUP=${OPTARG}
+      ;;
+    :)
+      echo "USAGE: run.sh [-d logdir] [-l packet_loss] [-c packet_corruption]" \
+           "[-u packet_duplcate] [-g]"
+      exit 1
+      ;;
+    ?)
+      echo "Invalid option: -${OPTARG}."
+      exit 1
+      ;;
+  esac
+done
+
+
+check_env
+check_conf
+check_gcov_conf
+
+
+rm -fr "$LOG_DIR"
+TRACE_FILE="${LOG_DIR}/rds-strace.txt"
+COVR_DIR="${LOG_DIR}/coverage/"
+mkdir -p  "$LOG_DIR"
+mkdir -p "$COVR_DIR"
+
+set +e
+echo running RDS tests...
+echo Traces will be logged to "$TRACE_FILE"
+rm -f "$TRACE_FILE"
+strace -T -tt -o "$TRACE_FILE" python3 "$(dirname "$0")/test.py" --timeout 400 -d "$LOG_DIR" \
+       -l "$PLOSS" -c "$PCORRUPT" -u "$PDUP"
+
+test_rc=$?
+dmesg > "${LOG_DIR}/dmesg.out"
+
+if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then
+       echo saving coverage data...
+       (set +x; cd /sys/kernel/debug/gcov; find ./* -name '*.gcda' | \
+       while read -r f
+       do
+               cat < "/sys/kernel/debug/gcov/$f" > "/$f"
+       done)
+
+       echo running gcovr...
+       gcovr -s --html-details --gcov-executable "$GCOV_CMD" --gcov-ignore-parse-errors \
+             -o "${COVR_DIR}/gcovr" "${ksrc_dir}/net/rds/"
+else
+       echo "Coverage report will be skipped"
+fi
+
+if [ "$test_rc" -eq 0 ]; then
+	echo "PASS: Test completed successfully"
+else
+	echo "FAIL: Test failed"
+fi
+
+exit "$test_rc"
diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py
new file mode 100644
index 000000000000..e6bb109bcead
--- /dev/null
+++ b/tools/testing/selftests/net/rds/test.py
@@ -0,0 +1,262 @@
+#! /usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import argparse
+import ctypes
+import errno
+import hashlib
+import os
+import select
+import signal
+import socket
+import subprocess
+import sys
+import atexit
+from pwd import getpwuid
+from os import stat
+from lib.py import ip
+
+
+libc = ctypes.cdll.LoadLibrary('libc.so.6')
+setns = libc.setns
+
+net0 = 'net0'
+net1 = 'net1'
+
+veth0 = 'veth0'
+veth1 = 'veth1'
+
+# Helper function for creating a socket inside a network namespace.
+# We need this because otherwise RDS will detect that the two TCP
+# sockets are on the same interface and use the loop transport instead
+# of the TCP transport.
+def netns_socket(netns, *args):
+    u0, u1 = socket.socketpair(socket.AF_UNIX, socket.SOCK_SEQPACKET)
+
+    child = os.fork()
+    if child == 0:
+        # change network namespace
+        with open(f'/var/run/netns/{netns}') as f:
+            try:
+                ret = setns(f.fileno(), 0)
+            except IOError as e:
+                print(e.errno)
+                print(e)
+
+        # create socket in target namespace
+        s = socket.socket(*args)
+
+        # send resulting socket to parent
+        socket.send_fds(u0, [], [s.fileno()])
+
+        sys.exit(0)
+
+    # receive socket from child
+    _, s, _, _ = socket.recv_fds(u1, 0, 1)
+    os.waitpid(child, 0)
+    u0.close()
+    u1.close()
+    return socket.fromfd(s[0], *args)
+
+def signal_handler(sig, frame):
+    print('Test timed out')
+    sys.exit(1)
+
+#Parse out command line arguments.  We take an optional
+# timeout parameter and an optional log output folder
+parser = argparse.ArgumentParser(description="init script args",
+                  formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+parser.add_argument("-d", "--logdir", action="store",
+                    help="directory to store logs", default="/tmp")
+parser.add_argument('--timeout', help="timeout to terminate hung test",
+                    type=int, default=0)
+parser.add_argument('-l', '--loss', help="Simulate tcp packet loss",
+                    type=int, default=0)
+parser.add_argument('-c', '--corruption', help="Simulate tcp packet corruption",
+                    type=int, default=0)
+parser.add_argument('-u', '--duplicate', help="Simulate tcp packet duplication",
+                    type=int, default=0)
+args = parser.parse_args()
+logdir=args.logdir
+packet_loss=str(args.loss)+'%'
+packet_corruption=str(args.corruption)+'%'
+packet_duplicate=str(args.duplicate)+'%'
+
+ip(f"netns add {net0}")
+ip(f"netns add {net1}")
+ip(f"link add type veth")
+
+addrs = [
+    # we technically don't need different port numbers, but this will
+    # help identify traffic in the network analyzer
+    ('10.0.0.1', 10000),
+    ('10.0.0.2', 20000),
+]
+
+# move interfaces to separate namespaces so they can no longer be
+# bound directly; this prevents rds from switching over from the tcp
+# transport to the loop transport.
+ip(f"link set {veth0} netns {net0} up")
+ip(f"link set {veth1} netns {net1} up")
+
+
+
+# add addresses
+ip(f"-n {net0} addr add {addrs[0][0]}/32 dev {veth0}")
+ip(f"-n {net1} addr add {addrs[1][0]}/32 dev {veth1}")
+
+# add routes
+ip(f"-n {net0} route add {addrs[1][0]}/32 dev {veth0}")
+ip(f"-n {net1} route add {addrs[0][0]}/32 dev {veth1}")
+
+# sanity check that our two interfaces/addresses are correctly set up
+# and communicating by doing a single ping
+ip(f"netns exec {net0} ping -c 1 {addrs[1][0]}")
+
+# Start a packet capture on each network
+for net in [net0, net1]:
+    tcpdump_pid = os.fork()
+    if tcpdump_pid == 0:
+        pcap = logdir+'/'+net+'.pcap'
+        subprocess.check_call(['touch', pcap])
+        user = getpwuid(stat(pcap).st_uid).pw_name
+        ip(f"netns exec {net} /usr/sbin/tcpdump -Z {user} -i any -w {pcap}")
+        sys.exit(0)
+
+# simulate packet loss, duplication and corruption
+for net, iface in [(net0, veth0), (net1, veth1)]:
+    ip(f"netns exec {net} /usr/sbin/tc qdisc add dev {iface} root netem  \
+         corrupt {packet_corruption} loss {packet_loss} duplicate  \
+         {packet_duplicate}")
+
+# add a timeout
+if args.timeout > 0:
+    signal.alarm(args.timeout)
+    signal.signal(signal.SIGALRM, signal_handler)
+
+sockets = [
+    netns_socket(net0, socket.AF_RDS, socket.SOCK_SEQPACKET),
+    netns_socket(net1, socket.AF_RDS, socket.SOCK_SEQPACKET),
+]
+
+for s, addr in zip(sockets, addrs):
+    s.bind(addr)
+    s.setblocking(0)
+
+fileno_to_socket = {
+    s.fileno(): s for s in sockets
+}
+
+addr_to_socket = {
+    addr: s for addr, s in zip(addrs, sockets)
+}
+
+socket_to_addr = {
+    s: addr for addr, s in zip(addrs, sockets)
+}
+
+send_hashes = {}
+recv_hashes = {}
+
+ep = select.epoll()
+
+for s in sockets:
+    ep.register(s, select.EPOLLRDNORM)
+
+n = 50000
+nr_send = 0
+nr_recv = 0
+
+while nr_send < n:
+    # Send as much as we can without blocking
+    print("sending...", nr_send, nr_recv)
+    while nr_send < n:
+        send_data = hashlib.sha256(
+            f'packet {nr_send}'.encode('utf-8')).hexdigest().encode('utf-8')
+
+        # pseudo-random send/receive pattern
+        sender = sockets[nr_send % 2]
+        receiver = sockets[1 - (nr_send % 3) % 2]
+
+        try:
+            sender.sendto(send_data, socket_to_addr[receiver])
+            send_hashes.setdefault((sender.fileno(), receiver.fileno()),
+                    hashlib.sha256()).update(f'<{send_data}>'.encode('utf-8'))
+            nr_send = nr_send + 1
+        except BlockingIOError as e:
+            break
+        except OSError as e:
+            if e.errno in [errno.ENOBUFS, errno.ECONNRESET, errno.EPIPE]:
+                break
+            raise
+
+    # Receive as much as we can without blocking
+    print("receiving...", nr_send, nr_recv)
+    while nr_recv < nr_send:
+        for fileno, eventmask in ep.poll():
+            receiver = fileno_to_socket[fileno]
+
+            if eventmask & select.EPOLLRDNORM:
+                while True:
+                    try:
+                        recv_data, address = receiver.recvfrom(1024)
+                        sender = addr_to_socket[address]
+                        recv_hashes.setdefault((sender.fileno(),
+                            receiver.fileno()), hashlib.sha256()).update(
+                                    f'<{recv_data}>'.encode('utf-8'))
+                        nr_recv = nr_recv + 1
+                    except BlockingIOError as e:
+                        break
+
+    # exercise net/rds/tcp.c:rds_tcp_sysctl_reset()
+    for net in [net0, net1]:
+        ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_rcvbuf=10000")
+        ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_sndbuf=10000")
+
+print("done", nr_send, nr_recv)
+
+# the Python socket module doesn't know these
+RDS_INFO_FIRST = 10000
+RDS_INFO_LAST = 10017
+
+nr_success = 0
+nr_error = 0
+
+for s in sockets:
+    for optname in range(RDS_INFO_FIRST, RDS_INFO_LAST + 1):
+        # Sigh, the Python socket module doesn't allow us to pass
+        # buffer lengths greater than 1024 for some reason. RDS
+        # wants multiple pages.
+        try:
+            s.getsockopt(socket.SOL_RDS, optname, 1024)
+            nr_success = nr_success + 1
+        except OSError as e:
+            nr_error = nr_error + 1
+            if e.errno == errno.ENOSPC:
+                # ignore
+                pass
+
+print(f"getsockopt(): {nr_success}/{nr_error}")
+
+print("Stopping network packet captures")
+subprocess.check_call(['killall', '-q', 'tcpdump'])
+
+# We're done sending and receiving stuff, now let's check if what
+# we received is what we sent.
+for (sender, receiver), send_hash in send_hashes.items():
+    recv_hash = recv_hashes.get((sender, receiver))
+
+    if recv_hash is None:
+        print("FAIL: No data received")
+        sys.exit(1)
+
+    if send_hash.hexdigest() != recv_hash.hexdigest():
+        print("FAIL: Send/recv mismatch")
+        print("hash expected:", send_hash.hexdigest())
+        print("hash received:", recv_hash.hexdigest())
+        sys.exit(1)
+
+    print(f"{sender}/{receiver}: ok")
+
+print("Success")
+sys.exit(0)
-- 
cgit v1.3-3-g829e


From 916b7d31f7eef81fe20f86ef52c36938fa971872 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Thu, 8 Aug 2024 20:53:45 +0000
Subject: ethtool: refactor checking max channels

Currently ethtool_set_channel calls separate functions to check whether
the new channel number violates rss configuration or flow steering
configuration.

Very soon we need to check whether the new channel number violates
memory provider configuration as well.

To do all 3 checks cleanly, add a wrapper around
ethtool_get_max_rxnfc_channel() and ethtool_get_max_rxfh_channel(),
which does both checks. We can later extend this wrapper to add the
memory provider check in one place.

Note that in the current code, we put a descriptive genl error message
when we run into issues. To preserve the error message, we pass the
genl_info* to the common helper. The ioctl calls can pass NULL instead.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20240808205345.2141858-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/channels.c | 20 ++++----------------
 net/ethtool/common.c   | 32 ++++++++++++++++++++++++++++++--
 net/ethtool/common.h   |  7 +++++--
 net/ethtool/ioctl.c    | 13 +++----------
 4 files changed, 42 insertions(+), 30 deletions(-)

diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index cee188da54f8..ca4f80282448 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -114,8 +114,7 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info)
 	struct net_device *dev = req_info->dev;
 	struct ethtool_channels channels = {};
 	struct nlattr **tb = info->attrs;
-	u32 err_attr, max_rxfh_in_use;
-	u64 max_rxnfc_in_use;
+	u32 err_attr;
 	int ret;
 
 	dev->ethtool_ops->get_channels(dev, &channels);
@@ -166,20 +165,9 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	/* ensure the new Rx count fits within the configured Rx flow
-	 * indirection table/rxnfc settings
-	 */
-	if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use))
-		max_rxnfc_in_use = 0;
-	max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev);
-	if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) {
-		GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use);
-		return -EINVAL;
-	}
-	if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) {
-		GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings");
-		return -EINVAL;
-	}
+	ret = ethtool_check_max_channel(dev, channels, info);
+	if (ret)
+		return ret;
 
 	/* Disabling channels, query zero-copy AF_XDP sockets */
 	from_channel = channels.combined_count +
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 5f714bbbef19..7257ae272296 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -6,6 +6,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/ptp_clock_kernel.h>
 
+#include "netlink.h"
 #include "common.h"
 
 const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
@@ -539,7 +540,7 @@ static int ethtool_get_rxnfc_rule_count(struct net_device *dev)
 	return info.rule_cnt;
 }
 
-int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max)
+static int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct ethtool_rxnfc *info;
@@ -609,7 +610,7 @@ static u32 ethtool_get_max_rss_ctx_channel(struct net_device *dev)
 	return max_ring;
 }
 
-u32 ethtool_get_max_rxfh_channel(struct net_device *dev)
+static u32 ethtool_get_max_rxfh_channel(struct net_device *dev)
 {
 	struct ethtool_rxfh_param rxfh = {};
 	u32 dev_size, current_max;
@@ -650,6 +651,33 @@ out_free:
 	return current_max;
 }
 
+int ethtool_check_max_channel(struct net_device *dev,
+			      struct ethtool_channels channels,
+			      struct genl_info *info)
+{
+	u64 max_rxnfc_in_use;
+	u32 max_rxfh_in_use;
+
+	/* ensure the new Rx count fits within the configured Rx flow
+	 * indirection table/rxnfc settings
+	 */
+	if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use))
+		max_rxnfc_in_use = 0;
+	max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev);
+	if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) {
+		if (info)
+			GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use);
+		return -EINVAL;
+	}
+	if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) {
+		if (info)
+			GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int ethtool_check_ops(const struct ethtool_ops *ops)
 {
 	if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params))
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index 863806fcf01a..d55d5201b085 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -20,6 +20,8 @@ struct link_mode_info {
 	u8				duplex;
 };
 
+struct genl_info;
+
 extern const char
 netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN];
 extern const char
@@ -42,8 +44,9 @@ int __ethtool_get_link(struct net_device *dev);
 bool convert_legacy_settings_to_link_ksettings(
 	struct ethtool_link_ksettings *link_ksettings,
 	const struct ethtool_cmd *legacy_settings);
-u32 ethtool_get_max_rxfh_channel(struct net_device *dev);
-int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max);
+int ethtool_check_max_channel(struct net_device *dev,
+			      struct ethtool_channels channels,
+			      struct genl_info *info);
 int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info);
 
 extern const struct ethtool_phy_ops *ethtool_phy_ops;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index e18823bf2330..ba8630eb02ef 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2069,8 +2069,6 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 {
 	struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS };
 	u16 from_channel, to_channel;
-	u64 max_rxnfc_in_use;
-	u32 max_rxfh_in_use;
 	unsigned int i;
 	int ret;
 
@@ -2100,14 +2098,9 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 	    (!channels.rx_count || !channels.tx_count))
 		return -EINVAL;
 
-	/* ensure the new Rx count fits within the configured Rx flow
-	 * indirection table/rxnfc settings */
-	if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use))
-		max_rxnfc_in_use = 0;
-	max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev);
-	if (channels.combined_count + channels.rx_count <=
-	    max_t(u64, max_rxnfc_in_use, max_rxfh_in_use))
-		return -EINVAL;
+	ret = ethtool_check_max_channel(dev, channels, NULL);
+	if (ret)
+		return ret;
 
 	/* Disabling channels, query zero-copy AF_XDP sockets */
 	from_channel = channels.combined_count +
-- 
cgit v1.3-3-g829e


From 2d5c9dd2cde33150f9dbb8ee091eff05eb6c7df3 Mon Sep 17 00:00:00 2001
From: zhangxiangqian <zhangxiangqian@kylinos.cn>
Date: Thu, 8 Aug 2024 17:39:45 +0800
Subject: net: usb: cdc_ether: don't spew notifications

The usbnet_link_change function is not called, if the link has not changed.

...
[16913.807393][ 3] cdc_ether 1-2:2.0 enx00e0995fd1ac: kevent 12 may have been dropped
[16913.822266][ 2] cdc_ether 1-2:2.0 enx00e0995fd1ac: kevent 12 may have been dropped
[16913.826296][ 2] cdc_ether 1-2:2.0 enx00e0995fd1ac: kevent 11 may have been dropped
...

kevent 11 is scheduled too frequently and may affect other event schedules.

Signed-off-by: zhangxiangqian <zhangxiangqian@kylinos.cn>
Acked-by: Oliver Neukum <oneukum@suse.com>
Link: https://patch.msgid.link/1723109985-11996-1-git-send-email-zhangxiangqian@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_ether.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 6d61052353f0..a6469235d904 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -418,7 +418,8 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb)
 	case USB_CDC_NOTIFY_NETWORK_CONNECTION:
 		netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n",
 			  event->wValue ? "on" : "off");
-		usbnet_link_change(dev, !!event->wValue, 0);
+		if (netif_carrier_ok(dev->net) != !!event->wValue)
+			usbnet_link_change(dev, !!event->wValue, 0);
 		break;
 	case USB_CDC_NOTIFY_SPEED_CHANGE:	/* tx/rx rates */
 		netif_dbg(dev, timer, dev->net, "CDC: speed change (len %d)\n",
-- 
cgit v1.3-3-g829e


From c146f3d191147a12d6c9ac61c4e48ac2dc53edc0 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Thu, 8 Aug 2024 09:16:48 +0200
Subject: net: fs_enet: Fix warning due to wrong type

Building fs_enet on powerpc e500 leads to following warning:

    CC      drivers/net/ethernet/freescale/fs_enet/mac-scc.o
  In file included from ./include/linux/build_bug.h:5,
                   from ./include/linux/container_of.h:5,
                   from ./include/linux/list.h:5,
                   from ./include/linux/module.h:12,
                   from drivers/net/ethernet/freescale/fs_enet/mac-scc.c:15:
  drivers/net/ethernet/freescale/fs_enet/mac-scc.c: In function 'allocate_bd':
  ./include/linux/err.h:28:49: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
     28 | #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO)
        |                                                 ^
  ./include/linux/compiler.h:77:45: note: in definition of macro 'unlikely'
     77 | # define unlikely(x)    __builtin_expect(!!(x), 0)
        |                                             ^
  drivers/net/ethernet/freescale/fs_enet/mac-scc.c:138:13: note: in expansion of macro 'IS_ERR_VALUE'
    138 |         if (IS_ERR_VALUE(fep->ring_mem_addr))
        |             ^~~~~~~~~~~~

This is due to fep->ring_mem_addr not being a pointer but a DMA
address which is 64 bits on that platform while pointers are
32 bits as this is a 32 bits platform with wider physical bus.

However, using fep->ring_mem_addr is just wrong because
cpm_muram_alloc() returns an offset within the muram and not
a physical address directly. So use fpi->dpram_offset instead.

Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/ec67ea3a3bef7e58b8dc959f7c17d405af0d27e4.1723101144.git.christophe.leroy@csgroup.eu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index a64cb6270515..9e89ac2b6ce3 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -131,15 +131,14 @@ static int setup_data(struct net_device *dev)
 static int allocate_bd(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
-	const struct fs_platform_info *fpi = fep->fpi;
+	struct fs_platform_info *fpi = fep->fpi;
 
-	fep->ring_mem_addr = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) *
-					     sizeof(cbd_t), 8);
-	if (IS_ERR_VALUE(fep->ring_mem_addr))
+	fpi->dpram_offset = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) *
+					    sizeof(cbd_t), 8);
+	if (IS_ERR_VALUE(fpi->dpram_offset))
 		return -ENOMEM;
 
-	fep->ring_base = (void __iomem __force*)
-		cpm_muram_addr(fep->ring_mem_addr);
+	fep->ring_base = cpm_muram_addr(fpi->dpram_offset);
 
 	return 0;
 }
@@ -147,9 +146,10 @@ static int allocate_bd(struct net_device *dev)
 static void free_bd(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
+	const struct fs_platform_info *fpi = fep->fpi;
 
 	if (fep->ring_base)
-		cpm_muram_free(fep->ring_mem_addr);
+		cpm_muram_free(fpi->dpram_offset);
 }
 
 static void cleanup_data(struct net_device *dev)
@@ -247,9 +247,9 @@ static void restart(struct net_device *dev)
 		__fs_out8((u8 __iomem *)ep + i, 0);
 
 	/* point to bds */
-	W16(ep, sen_genscc.scc_rbase, fep->ring_mem_addr);
+	W16(ep, sen_genscc.scc_rbase, fpi->dpram_offset);
 	W16(ep, sen_genscc.scc_tbase,
-	    fep->ring_mem_addr + sizeof(cbd_t) * fpi->rx_ring);
+	    fpi->dpram_offset + sizeof(cbd_t) * fpi->rx_ring);
 
 	/* Initialize function code registers for big-endian.
 	 */
-- 
cgit v1.3-3-g829e


From dda10fc801a9d81829e624ef75ecdfc94f39b310 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:03 -0500
Subject: ibmvnic: Only replenish rx pool when resources are getting low

Previously, the driver would replenish the rx pool if the polling
function consumed less than the budget. The logic being that the driver
did not exhaust its budget so that must mean that the driver is not busy
and has cycles to spare for replenishing the pool.

So pool replenishment happens on every poll which did not consume
the budget. This can very costly during request-response tests.

In fact, an extra ~100pps can be seen in TCP_RR_150 tests when we remove
this conditional. Trace results (ftrace, graph-time=1) for the poll
function are below:
Previous results:
    ibmvnic_poll = 64951846.0 us / 4167628.0 hits = AVG 15.58
    replenish_rx_pool = 17602846.0 us / 4710437.0 hits = AVG 3.74
Now:
    ibmvnic_poll = 57673941.0 us / 4791737.0 hits = AVG 12.04
    replenish_rx_pool = 3938171.6 us / 4314.0 hits = AVG 912.88

While the replenish function takes longer, it is hit less frequently
meaning the ibmvnic_poll function, on average, is faster.

Furthermore, this change does not have a negative effect on
performance bandwidth/latency measurements.

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-2-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 23ebeb143987..857d585bd229 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -3527,9 +3527,8 @@ restart_poll:
 	}
 
 	if (adapter->state != VNIC_CLOSING &&
-	    ((atomic_read(&adapter->rx_pool[scrq_num].available) <
-	      adapter->req_rx_add_entries_per_subcrq / 2) ||
-	      frames_processed < budget))
+	    (atomic_read(&adapter->rx_pool[scrq_num].available) <
+	      adapter->req_rx_add_entries_per_subcrq / 2))
 		replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]);
 	if (frames_processed < budget) {
 		if (napi_complete_done(napi, frames_processed)) {
-- 
cgit v1.3-3-g829e


From b41b45ecee6ba74bd590b113be9f349c6b818b46 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:04 -0500
Subject: ibmvnic: Use header len helper functions on tx

Use the header length helper functions rather than trying to calculate
it within the driver. There are defined functions for mac and network
headers (skb_mac_header_len and skb_network_header_len) but no such
function exists for the transport header length.

Also, hdr_data was memset during allocation to all 0's so no need to
memset again.

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-3-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 857d585bd229..7d552d4bbe15 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2156,36 +2156,28 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
 	int len = 0;
 	u8 *hdr;
 
-	if (skb_vlan_tagged(skb) && !skb_vlan_tag_present(skb))
-		hdr_len[0] = sizeof(struct vlan_ethhdr);
-	else
-		hdr_len[0] = sizeof(struct ethhdr);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
-		hdr_len[1] = ip_hdr(skb)->ihl * 4;
 		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
 			hdr_len[2] = tcp_hdrlen(skb);
 		else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
 			hdr_len[2] = sizeof(struct udphdr);
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-		hdr_len[1] = sizeof(struct ipv6hdr);
 		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
 			hdr_len[2] = tcp_hdrlen(skb);
 		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
 			hdr_len[2] = sizeof(struct udphdr);
-	} else if (skb->protocol == htons(ETH_P_ARP)) {
-		hdr_len[1] = arp_hdr_len(skb->dev);
-		hdr_len[2] = 0;
 	}
 
-	memset(hdr_data, 0, 120);
 	if ((hdr_field >> 6) & 1) {
+		hdr_len[0] = skb_mac_header_len(skb);
 		hdr = skb_mac_header(skb);
 		memcpy(hdr_data, hdr, hdr_len[0]);
 		len += hdr_len[0];
 	}
 
 	if ((hdr_field >> 5) & 1) {
+		hdr_len[1] = skb_network_header_len(skb);
 		hdr = skb_network_header(skb);
 		memcpy(hdr_data + len, hdr, hdr_len[1]);
 		len += hdr_len[1];
@@ -2196,6 +2188,7 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
 		memcpy(hdr_data + len, hdr, hdr_len[2]);
 		len += hdr_len[2];
 	}
+
 	return len;
 }
 
-- 
cgit v1.3-3-g829e


From d95f749a0b5e42a30d7025d19c15a11c1a570e72 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:05 -0500
Subject: ibmvnic: Reduce memcpys in tx descriptor generation

Previously when creating the header descriptors, the driver would:
1. allocate a temporary buffer on the stack (in build_hdr_descs_arr)
2. memcpy the header info into the temporary buffer (in build_hdr_data)
3. memcpy the temp buffer into a local variable (in create_hdr_descs)
4. copy the local variable into the return buffer (in create_hdr_descs)

Since, there is no opportunity for errors during this process, the temp
buffer is not needed and work can be done on the return buffer directly.

Repurpose build_hdr_data() to only calculate the header lengths. Rename
it to get_hdr_lens().
Edit create_hdr_descs() to read from the skb directly and copy directly
into the returned useful buffer.

The process now involves less memory and write operations while
also being more readable.

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-4-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 89 +++++++++++++++++---------------------
 1 file changed, 40 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 7d552d4bbe15..58a517ecbda3 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2140,56 +2140,49 @@ static int ibmvnic_close(struct net_device *netdev)
 }
 
 /**
- * build_hdr_data - creates L2/L3/L4 header data buffer
+ * get_hdr_lens - fills list of L2/L3/L4 hdr lens
  * @hdr_field: bitfield determining needed headers
  * @skb: socket buffer
- * @hdr_len: array of header lengths
- * @hdr_data: buffer to write the header to
+ * @hdr_len: array of header lengths to be filled
  *
  * Reads hdr_field to determine which headers are needed by firmware.
  * Builds a buffer containing these headers.  Saves individual header
  * lengths and total buffer length to be used to build descriptors.
+ *
+ * Return: total len of all headers
  */
-static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
-			  int *hdr_len, u8 *hdr_data)
+static int get_hdr_lens(u8 hdr_field, struct sk_buff *skb,
+			int *hdr_len)
 {
 	int len = 0;
-	u8 *hdr;
-
 
-	if (skb->protocol == htons(ETH_P_IP)) {
-		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
-			hdr_len[2] = tcp_hdrlen(skb);
-		else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
-			hdr_len[2] = sizeof(struct udphdr);
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
-			hdr_len[2] = tcp_hdrlen(skb);
-		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
-			hdr_len[2] = sizeof(struct udphdr);
-	}
 
 	if ((hdr_field >> 6) & 1) {
 		hdr_len[0] = skb_mac_header_len(skb);
-		hdr = skb_mac_header(skb);
-		memcpy(hdr_data, hdr, hdr_len[0]);
 		len += hdr_len[0];
 	}
 
 	if ((hdr_field >> 5) & 1) {
 		hdr_len[1] = skb_network_header_len(skb);
-		hdr = skb_network_header(skb);
-		memcpy(hdr_data + len, hdr, hdr_len[1]);
 		len += hdr_len[1];
 	}
 
-	if ((hdr_field >> 4) & 1) {
-		hdr = skb_transport_header(skb);
-		memcpy(hdr_data + len, hdr, hdr_len[2]);
-		len += hdr_len[2];
+	if (!((hdr_field >> 4) & 1))
+		return len;
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
+			hdr_len[2] = tcp_hdrlen(skb);
+		else if (ip_hdr(skb)->protocol == IPPROTO_UDP)
+			hdr_len[2] = sizeof(struct udphdr);
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP)
+			hdr_len[2] = tcp_hdrlen(skb);
+		else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)
+			hdr_len[2] = sizeof(struct udphdr);
 	}
 
-	return len;
+	return len + hdr_len[2];
 }
 
 /**
@@ -2202,12 +2195,14 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb,
  *
  * Creates header and, if needed, header extension descriptors and
  * places them in a descriptor array, scrq_arr
+ *
+ * Return: Number of header descs
  */
 
 static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
 			    union sub_crq *scrq_arr)
 {
-	union sub_crq hdr_desc;
+	union sub_crq *hdr_desc;
 	int tmp_len = len;
 	int num_descs = 0;
 	u8 *data, *cur;
@@ -2216,28 +2211,26 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len,
 	while (tmp_len > 0) {
 		cur = hdr_data + len - tmp_len;
 
-		memset(&hdr_desc, 0, sizeof(hdr_desc));
-		if (cur != hdr_data) {
-			data = hdr_desc.hdr_ext.data;
+		hdr_desc = &scrq_arr[num_descs];
+		if (num_descs) {
+			data = hdr_desc->hdr_ext.data;
 			tmp = tmp_len > 29 ? 29 : tmp_len;
-			hdr_desc.hdr_ext.first = IBMVNIC_CRQ_CMD;
-			hdr_desc.hdr_ext.type = IBMVNIC_HDR_EXT_DESC;
-			hdr_desc.hdr_ext.len = tmp;
+			hdr_desc->hdr_ext.first = IBMVNIC_CRQ_CMD;
+			hdr_desc->hdr_ext.type = IBMVNIC_HDR_EXT_DESC;
+			hdr_desc->hdr_ext.len = tmp;
 		} else {
-			data = hdr_desc.hdr.data;
+			data = hdr_desc->hdr.data;
 			tmp = tmp_len > 24 ? 24 : tmp_len;
-			hdr_desc.hdr.first = IBMVNIC_CRQ_CMD;
-			hdr_desc.hdr.type = IBMVNIC_HDR_DESC;
-			hdr_desc.hdr.len = tmp;
-			hdr_desc.hdr.l2_len = (u8)hdr_len[0];
-			hdr_desc.hdr.l3_len = cpu_to_be16((u16)hdr_len[1]);
-			hdr_desc.hdr.l4_len = (u8)hdr_len[2];
-			hdr_desc.hdr.flag = hdr_field << 1;
+			hdr_desc->hdr.first = IBMVNIC_CRQ_CMD;
+			hdr_desc->hdr.type = IBMVNIC_HDR_DESC;
+			hdr_desc->hdr.len = tmp;
+			hdr_desc->hdr.l2_len = (u8)hdr_len[0];
+			hdr_desc->hdr.l3_len = cpu_to_be16((u16)hdr_len[1]);
+			hdr_desc->hdr.l4_len = (u8)hdr_len[2];
+			hdr_desc->hdr.flag = hdr_field << 1;
 		}
 		memcpy(data, cur, tmp);
 		tmp_len -= tmp;
-		*scrq_arr = hdr_desc;
-		scrq_arr++;
 		num_descs++;
 	}
 
@@ -2260,13 +2253,11 @@ static void build_hdr_descs_arr(struct sk_buff *skb,
 				int *num_entries, u8 hdr_field)
 {
 	int hdr_len[3] = {0, 0, 0};
-	u8 hdr_data[140] = {0};
 	int tot_len;
 
-	tot_len = build_hdr_data(hdr_field, skb, hdr_len,
-				 hdr_data);
-	*num_entries += create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len,
-					 indir_arr + 1);
+	tot_len = get_hdr_lens(hdr_field, skb, hdr_len);
+	*num_entries += create_hdr_descs(hdr_field, skb_mac_header(skb),
+					 tot_len, hdr_len, indir_arr + 1);
 }
 
 static int ibmvnic_xmit_workarounds(struct sk_buff *skb,
-- 
cgit v1.3-3-g829e


From 6e7a57581abea5335cbf29d738724d25d3c302d7 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:06 -0500
Subject: ibmvnic: Remove duplicate memory barriers in tx

send_subcrq_[in]direct() already has a dma memory barrier.
Remove the earlier one.

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-5-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 58a517ecbda3..256feac588ef 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2459,9 +2459,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		skb_copy_from_linear_data(skb, dst, skb->len);
 	}
 
-	/* post changes to long_term_buff *dst before VIOS accessing it */
-	dma_wmb();
-
 	tx_pool->consumer_index =
 	    (tx_pool->consumer_index + 1) % tx_pool->num_buffers;
 
-- 
cgit v1.3-3-g829e


From 74839f7a82689bf5a21a5447cae8e3a7b7a606d2 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:07 -0500
Subject: ibmvnic: Introduce send sub-crq direct

Firmware supports two hcalls to send a sub-crq request:
H_SEND_SUB_CRQ_INDIRECT and H_SEND_SUB_CRQ. The indirect hcall allows
for submission of batched messages while the other hcall is limited to
only one message. This protocol is defined in PAPR section 17.2.3.3.

Previously, the ibmvnic xmit function only used the indirect hcall. This
allowed the driver to batch it's skbs. A single skb can occupy a few
entries per hcall depending on if FW requires skb header information or
not. The FW only needs header information if the packet is segmented.

By this logic, if an skb is not GSO then it can fit in one sub-crq
message and therefore is a candidate for H_SEND_SUB_CRQ.
Batching skb transmission is only useful when there are more packets
coming down the line (ie netdev_xmit_more is true).

As it turns out, H_SEND_SUB_CRQ induces less latency than
H_SEND_SUB_CRQ_INDIRECT. Therefore, use H_SEND_SUB_CRQ where
appropriate.

Small latency gains seen when doing TCP_RR_150 (request/response
workload). Ftrace results (graph-time=1):
  Previous:
     ibmvnic_xmit = 29618270.83 us / 8860058.0 hits = AVG 3.34
     ibmvnic_tx_scrq_flush = 21972231.02 us / 6553972.0 hits = AVG 3.35
  Now:
     ibmvnic_xmit = 22153350.96 us / 8438942.0 hits = AVG 2.63
     ibmvnic_tx_scrq_flush = 15858922.4 us / 6244076.0 hits = AVG 2.54

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-6-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 52 +++++++++++++++++++++++++++++++++-----
 1 file changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 256feac588ef..d7262674eab7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -117,6 +117,7 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter,
 				struct ibmvnic_long_term_buff *ltb);
 static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter);
 static void flush_reset_queue(struct ibmvnic_adapter *adapter);
+static void print_subcrq_error(struct device *dev, int rc, const char *func);
 
 struct ibmvnic_stat {
 	char name[ETH_GSTRING_LEN];
@@ -2334,8 +2335,29 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter,
 	}
 }
 
+static int send_subcrq_direct(struct ibmvnic_adapter *adapter,
+			      u64 remote_handle, u64 *entry)
+{
+	unsigned int ua = adapter->vdev->unit_address;
+	struct device *dev = &adapter->vdev->dev;
+	int rc;
+
+	/* Make sure the hypervisor sees the complete request */
+	dma_wmb();
+	rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua,
+				cpu_to_be64(remote_handle),
+				cpu_to_be64(entry[0]), cpu_to_be64(entry[1]),
+				cpu_to_be64(entry[2]), cpu_to_be64(entry[3]));
+
+	if (rc)
+		print_subcrq_error(dev, rc, __func__);
+
+	return rc;
+}
+
 static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
-				 struct ibmvnic_sub_crq_queue *tx_scrq)
+				 struct ibmvnic_sub_crq_queue *tx_scrq,
+				 bool indirect)
 {
 	struct ibmvnic_ind_xmit_queue *ind_bufp;
 	u64 dma_addr;
@@ -2350,7 +2372,13 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter,
 
 	if (!entries)
 		return 0;
-	rc = send_subcrq_indirect(adapter, handle, dma_addr, entries);
+
+	if (indirect)
+		rc = send_subcrq_indirect(adapter, handle, dma_addr, entries);
+	else
+		rc = send_subcrq_direct(adapter, handle,
+					(u64 *)ind_bufp->indir_arr);
+
 	if (rc)
 		ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq);
 	else
@@ -2408,7 +2436,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_dropped++;
 		tx_send_failed++;
 		ret = NETDEV_TX_OK;
-		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
 		goto out;
@@ -2426,7 +2454,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_send_failed++;
 		tx_dropped++;
 		ret = NETDEV_TX_OK;
-		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
 		goto out;
@@ -2521,6 +2549,16 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
 		tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
 		hdrs += 2;
+	} else if (!ind_bufp->index && !netdev_xmit_more()) {
+		ind_bufp->indir_arr[0] = tx_crq;
+		ind_bufp->index = 1;
+		tx_buff->num_entries = 1;
+		netdev_tx_sent_queue(txq, skb->len);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, false);
+		if (lpar_rc != H_SUCCESS)
+			goto tx_err;
+
+		goto early_exit;
 	}
 
 	if ((*hdrs >> 7) & 1)
@@ -2530,7 +2568,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	tx_buff->num_entries = num_entries;
 	/* flush buffer if current entry can not fit */
 	if (num_entries + ind_bufp->index > IBMVNIC_MAX_IND_DESCS) {
-		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_flush_err;
 	}
@@ -2538,15 +2576,17 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	indir_arr[0] = tx_crq;
 	memcpy(&ind_bufp->indir_arr[ind_bufp->index], &indir_arr[0],
 	       num_entries * sizeof(struct ibmvnic_generic_scrq));
+
 	ind_bufp->index += num_entries;
 	if (__netdev_tx_sent_queue(txq, skb->len,
 				   netdev_xmit_more() &&
 				   ind_bufp->index < IBMVNIC_MAX_IND_DESCS)) {
-		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq);
+		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
 	}
 
+early_exit:
 	if (atomic_add_return(num_entries, &tx_scrq->used)
 					>= adapter->req_tx_entries_per_subcrq) {
 		netdev_dbg(netdev, "Stopping queue %d\n", queue_num);
-- 
cgit v1.3-3-g829e


From 1c33e29245ccb1182876eb57319777456f9e509c Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:08 -0500
Subject: ibmvnic: Only record tx completed bytes once per handler

Byte Queue Limits depends on dql_completed being called once per tx
completion round in order to adjust its algorithm appropriately. The
dql->limit value is an approximation of the amount of bytes that the NIC
can consume per irq interval. If this approximation is too high then the
NIC will become over-saturated. Too low and the NIC will starve.

The dql->limit depends on dql->prev-* stats to calculate an optimal
value. If dql_completed() is called more than once per irq handler then
those prev-* values become unreliable (because they are not an accurate
representation of the previous state of the NIC) resulting in a
sub-optimal limit value.

Therefore, move the call to netdev_tx_completed_queue() to the end of
ibmvnic_complete_tx().

When performing 150 sessions of TCP rr (request-response 1 byte packets)
workloads, one could observe:
  PREVIOUSLY: - limit and inflight values hovering around 130
              - transaction rate of around 750k pps.

  NOW:        - limit rises and falls in response to inflight (130-900)
              - transaction rate of around 1M pps (33% improvement)

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-7-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index d7262674eab7..b687e5396e11 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -4189,20 +4189,17 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
 			       struct ibmvnic_sub_crq_queue *scrq)
 {
 	struct device *dev = &adapter->vdev->dev;
+	int num_packets = 0, total_bytes = 0;
 	struct ibmvnic_tx_pool *tx_pool;
 	struct ibmvnic_tx_buff *txbuff;
 	struct netdev_queue *txq;
 	union sub_crq *next;
-	int index;
-	int i;
+	int index, i;
 
 restart_loop:
 	while (pending_scrq(adapter, scrq)) {
 		unsigned int pool = scrq->pool_index;
 		int num_entries = 0;
-		int total_bytes = 0;
-		int num_packets = 0;
-
 		next = ibmvnic_next_scrq(adapter, scrq);
 		for (i = 0; i < next->tx_comp.num_comps; i++) {
 			index = be32_to_cpu(next->tx_comp.correlators[i]);
@@ -4238,8 +4235,6 @@ restart_loop:
 		/* remove tx_comp scrq*/
 		next->tx_comp.first = 0;
 
-		txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index);
-		netdev_tx_completed_queue(txq, num_packets, total_bytes);
 
 		if (atomic_sub_return(num_entries, &scrq->used) <=
 		    (adapter->req_tx_entries_per_subcrq / 2) &&
@@ -4264,6 +4259,9 @@ restart_loop:
 		goto restart_loop;
 	}
 
+	txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index);
+	netdev_tx_completed_queue(txq, num_packets, total_bytes);
+
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From e633e32b60fd6701bed73599b273a2a03621ea54 Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Wed, 7 Aug 2024 16:18:09 -0500
Subject: ibmvnic: Perform tx CSO during send scrq direct

During initialization with the vnic server, a bitstring is communicated
to the client regarding header info needed during CSO (See "VNIC
Capabilities" in PAPR). Most of the time, to be safe, vnic server
requests header info for CSO. When header info is needed, multiple TX
descriptors are required per skb; This limits the driver to use
send_subcrq_indirect instead of send_subcrq_direct.

Previously, the vnic server request for header info was ignored. This
allowed the use of send_sub_crq_direct. Transmissions were successful
because the bitstring returned by vnic server is broad and over
cautionary. It was observed that mlx backing devices could actually
transmit and handle CSO packets without the vnic server receiving
header info (despite the fact that the bitstring requested it).

There was a trust issue: The bitstring was overcautionary. This extra
precaution (requesting header info when the backing device may not use
it) comes at the cost of performance (using direct vs indirect hcalls
has a 30% delta in small packet RR transaction rate). So it has been
requested that the vnic server team tries to ensure that the bitstring
is more exact. In the meantime, disable CSO when it is possible to use
the skb in the send_subcrq_direct path. In other words, calculate the
checksum before handing the packet to FW when the packet is not
segmented and xmit_more is false.

Since the code path is only possible if the skb is non GSO and xmit_more
is false, the cost of doing checksum in the send_subcrq_direct path is
minimal. Any large segmented skb will have xmit_more set to true more
frequently and it is inexpensive to do checksumming on a small skb.
The worst-case workload would be a 9000 MTU TCP_RR test with close
to MTU sized packets (and TSO off). This allows xmit_more to be false
more frequently and open the code path up to use send_subcrq_direct.
Observing trace data (graph-time = 1) and packet rate with this workload
shows minimal performance degradation:

1. NIC does checksum w headers, safely use send_subcrq_indirect:
  - Packet rate: 631k txs
  - Trace data:
    ibmvnic_xmit = 44344685.87 us / 6234576 hits = AVG 7.11 us
      skb_checksum_help = 4.07 us / 2 hits = AVG 2.04 us
       ^ Notice hits, tracing this just for reassurance
      ibmvnic_tx_scrq_flush = 33040649.69 us / 5638441 hits = AVG 5.86 us
        send_subcrq_indirect = 37438922.24 us / 6030859 hits = AVG 6.21 us

2. NIC does checksum w/o headers, dangerously use send_subcrq_direct:
  - Packet rate: 831k txs
  - Trace data:
    ibmvnic_xmit = 48940092.29 us / 8187630 hits = AVG 5.98 us
      skb_checksum_help = 2.03 us / 1 hits = AVG 2.03
      ibmvnic_tx_scrq_flush = 31141879.57 us / 7948960 hits = AVG 3.92 us
        send_subcrq_indirect = 8412506.03 us / 728781 hits = AVG 11.54
         ^ notice hits is much lower b/c send_subcrq_direct was called
                                            ^ wasn't traceable

3. driver does checksum, safely use send_subcrq_direct (THIS PATCH):
  - Packet rate: 829k txs
  - Trace data:
    ibmvnic_xmit = 56696077.63 us / 8066168 hits = AVG 7.03 us
      skb_checksum_help = 8587456.16 us / 7526072 hits = AVG 1.14 us
      ibmvnic_tx_scrq_flush = 30219545.55 us / 7782409 hits = AVG 3.88 us
        send_subcrq_indirect = 8638326.44 us / 763693 hits = AVG 11.31 us

When the bitstring ever specifies that CSO does not require headers
(dependent on VIOS vnic server changes), then this patch should be
removed and replaced with one that investigates the bitstring before
using send_subcrq_direct.

Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Link: https://patch.msgid.link/20240807211809.1259563-8-nnac123@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index b687e5396e11..87e693a81433 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2409,6 +2409,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	unsigned long lpar_rc;
 	union sub_crq tx_crq;
 	unsigned int offset;
+	bool use_scrq_send_direct = false;
 	int num_entries = 1;
 	unsigned char *dst;
 	int bufidx = 0;
@@ -2468,6 +2469,18 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 	memset(dst, 0, tx_pool->buf_size);
 	data_dma_addr = ltb->addr + offset;
 
+	/* if we are going to send_subcrq_direct this then we need to
+	 * update the checksum before copying the data into ltb. Essentially
+	 * these packets force disable CSO so that we can guarantee that
+	 * FW does not need header info and we can send direct.
+	 */
+	if (!skb_is_gso(skb) && !ind_bufp->index && !netdev_xmit_more()) {
+		use_scrq_send_direct = true;
+		if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		    skb_checksum_help(skb))
+			use_scrq_send_direct = false;
+	}
+
 	if (skb_shinfo(skb)->nr_frags) {
 		int cur, i;
 
@@ -2549,11 +2562,13 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 		tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
 		tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
 		hdrs += 2;
-	} else if (!ind_bufp->index && !netdev_xmit_more()) {
-		ind_bufp->indir_arr[0] = tx_crq;
+	} else if (use_scrq_send_direct) {
+		/* See above comment, CSO disabled with direct xmit */
+		tx_crq.v1.flags1 &= ~(IBMVNIC_TX_CHKSUM_OFFLOAD);
 		ind_bufp->index = 1;
 		tx_buff->num_entries = 1;
 		netdev_tx_sent_queue(txq, skb->len);
+		ind_bufp->indir_arr[0] = tx_crq;
 		lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, false);
 		if (lpar_rc != H_SUCCESS)
 			goto tx_err;
-- 
cgit v1.3-3-g829e


From 1862923bf6ae9d023826abf79d9795a06aecb350 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 7 Aug 2024 14:58:27 -0700
Subject: net: ag71xx: use phylink_mii_ioctl

f1294617d2f38bd2b9f6cce516b0326858b61182 removed the custom function for
ndo_eth_ioctl and used the standard phy_do_ioctl which calls
phy_mii_ioctl. However since then, this driver was ported to phylink
where it makes more sense to call phylink_mii_ioctl.

Bring back custom function that calls phylink_mii_ioctl.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240807215834.33980-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index a38be924cdaa..2916fdb1970b 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -447,6 +447,13 @@ static void ag71xx_int_disable(struct ag71xx *ag, u32 ints)
 	ag71xx_cb(ag, AG71XX_REG_INT_ENABLE, ints);
 }
 
+static int ag71xx_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+	struct ag71xx *ag = netdev_priv(ndev);
+
+	return phylink_mii_ioctl(ag->phylink, ifr, cmd);
+}
+
 static void ag71xx_get_drvinfo(struct net_device *ndev,
 			       struct ethtool_drvinfo *info)
 {
@@ -1799,7 +1806,7 @@ static const struct net_device_ops ag71xx_netdev_ops = {
 	.ndo_open		= ag71xx_open,
 	.ndo_stop		= ag71xx_stop,
 	.ndo_start_xmit		= ag71xx_hard_start_xmit,
-	.ndo_eth_ioctl		= phy_do_ioctl,
+	.ndo_eth_ioctl		= ag71xx_do_ioctl,
 	.ndo_tx_timeout		= ag71xx_tx_timeout,
 	.ndo_change_mtu		= ag71xx_change_mtu,
 	.ndo_set_mac_address	= eth_mac_addr,
-- 
cgit v1.3-3-g829e


From 6e20d538fb1dfb9c477a8e991da1fca3064ce0f7 Mon Sep 17 00:00:00 2001
From: Chris Mi <cmi@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:17 +0300
Subject: net/mlx5: E-Switch, Increase max int port number for offload

Currently MLX5E_TC_MAX_INT_PORT_NUM is 8. Usually int port has one
ingress and one egress rules. But sometimes, a temporary rule can be
offloaded as well, eg:

recirc_id(0),in_port(br-phy),eth(src=10:70:fd:87:57:c0,dst=33:33:00:00:00:16),
	eth_type(0x86dd),ipv6(frag=no), packets:2, bytes:180, used:0.060s,
	actions:enp8s0f0

If one int port device offloads 3 rules, only 2 devices can offload.
Other devices will hit the limit and fail to offload. Actually it is
insufficient for customers. So increase the number to 32.

Signed-off-by: Chris Mi <cmi@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index c24bda56b2b5..b982e648ea48 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -139,7 +139,7 @@ struct mlx5_rx_tun_attr {
 #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16
 #define MLX5E_TC_TABLE_CHAIN_TAG_MASK GENMASK(MLX5E_TC_TABLE_CHAIN_TAG_BITS - 1, 0)
 
-#define MLX5E_TC_MAX_INT_PORT_NUM (8)
+#define MLX5E_TC_MAX_INT_PORT_NUM (32)
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 
-- 
cgit v1.3-3-g829e


From 88c46f6103e232e819b35ca811e96454d70a7138 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:18 +0300
Subject: net/mlx5e: Enable remove flow for hard packet limit

In the commit a2a73ea14b1a ("net/mlx5e: Don't listen to remove flows
event"), remove_flow_enable event is removed, and the hard limit
usually relies on software mechanism added in commit b2f7b01d36a9
("net/mlx5e: Simulate missing IPsec TX limits hardware
functionality"). But the delayed work is rescheduled every one second,
which is slow for fast traffic. As a result, traffic can't be blocked
even reaches the hard limit, which usually happens when soft and hard
limits are very close.

In reality it won't happen because soft limit is much lower than hard
limit. But, as an optimization for RX to block traffic when reaching
hard limit, need to set remove_flow_enable. When remove flow is
enabled, IPSEC HARD_LIFETIME ASO syndrome will be set in the metadata
defined in the ASO return register if packets reach hard lifetime
threshold. And those packets are dropped immediately by the steering
table.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 797db853de36..53cfa39188cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -127,6 +127,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn,
 		MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt,
 			 attrs->lft.hard_packet_limit);
 		MLX5_SET(ipsec_aso, aso_ctx, hard_lft_arm, 1);
+		MLX5_SET(ipsec_aso, aso_ctx, remove_flow_enable, 1);
 	}
 
 	if (attrs->lft.soft_packet_limit != XFRM_INF) {
-- 
cgit v1.3-3-g829e


From 16bb8c613379e20d4adabc639ea6aecdaeba2ff1 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:19 +0300
Subject: net/mlx5e: TC, Offload rewrite and mirror on tunnel over ovs internal
 port

To offload the encap rule when the tunnel IP is configured on an
openvswitch internal port, driver need to overwrite vport metadata in
reg_c0 to the value assigned to the internal port, then forward
packets to root table to be processed again by the rules matching on
the metadata for such internal port.

When such rule is combined with header rewrite and mirror, openvswitch
generates the rule like the following, because it resets mirror after
packets are modified.
    in_port(enp8s0f0npf0sf1),..,
        actions:enp8s0f0npf0sf2,set(tunnel(...)),set(ipv4(...)),vxlan_sys_4789,enp8s0f0npf0sf2

The split_count was introduced before to support rewrite and mirror.
Driver splits the rule into two different hardware rules in order to
offload it. But it's not enough to offload the above complicated rule
because of the limitations, in both driver and firmware.

To resolve this issue, the destination array is split again after the
destination indexed by split_count. An extra rule is added for the
leftover destinations (in the above example, it is enp8s0f0npf0sf2),
and is inserted to post_act table. And the extra destination is added
in the original rule to forward to post_act table, so the extra mirror
is done there.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc_priv.h   |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 103 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.h    |   1 +
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c |   7 ++
 4 files changed, 112 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 6cc23af66b5b..efb34de4cb7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -109,6 +109,7 @@ struct mlx5e_tc_flow {
 	struct completion init_done;
 	struct completion del_hw_done;
 	struct mlx5_flow_attr *attr;
+	struct mlx5_flow_attr *extra_split_attr;
 	struct list_head attrs;
 	u32 chain_mapping;
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 30673292e15f..a28bf05d98f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1739,11 +1739,102 @@ has_encap_dests(struct mlx5_flow_attr *attr)
 	return false;
 }
 
+static int
+extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr)
+{
+	struct mlx5_esw_flow_attr *esw_attr;
+
+	if (flow->attr != attr ||
+	    !list_is_first(&attr->list, &flow->attrs))
+		return 0;
+
+	esw_attr = attr->esw_attr;
+	if (!esw_attr->split_count ||
+	    esw_attr->split_count == esw_attr->out_count - 1)
+		return 0;
+
+	if (esw_attr->dest_int_port &&
+	    (esw_attr->dests[esw_attr->split_count].flags &
+	     MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE))
+		return esw_attr->split_count + 1;
+
+	return 0;
+}
+
+static int
+extra_split_attr_dests(struct mlx5e_tc_flow *flow,
+		       struct mlx5_flow_attr *attr, int split_count)
+{
+	struct mlx5e_post_act *post_act = get_post_action(flow->priv);
+	struct mlx5e_tc_flow_parse_attr *parse_attr, *parse_attr2;
+	struct mlx5_esw_flow_attr *esw_attr, *esw_attr2;
+	struct mlx5e_post_act_handle *handle;
+	struct mlx5_flow_attr *attr2;
+	int i, j, err;
+
+	if (IS_ERR(post_act))
+		return PTR_ERR(post_act);
+
+	attr2 = mlx5_alloc_flow_attr(mlx5e_get_flow_namespace(flow));
+	parse_attr2 = kvzalloc(sizeof(*parse_attr), GFP_KERNEL);
+	if (!attr2 || !parse_attr2) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+	attr2->parse_attr = parse_attr2;
+
+	handle = mlx5e_tc_post_act_add(post_act, attr2);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto err_free;
+	}
+
+	esw_attr = attr->esw_attr;
+	esw_attr2 = attr2->esw_attr;
+	esw_attr2->in_rep = esw_attr->in_rep;
+
+	parse_attr = attr->parse_attr;
+	parse_attr2->filter_dev = parse_attr->filter_dev;
+
+	for (i = split_count, j = 0; i < esw_attr->out_count; i++, j++)
+		esw_attr2->dests[j] = esw_attr->dests[i];
+
+	esw_attr2->out_count = j;
+	attr2->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+
+	err = mlx5e_tc_post_act_offload(post_act, handle);
+	if (err)
+		goto err_post_act_offload;
+
+	err = mlx5e_tc_post_act_set_handle(flow->priv->mdev, handle,
+					   &parse_attr->mod_hdr_acts);
+	if (err)
+		goto err_post_act_set_handle;
+
+	esw_attr->out_count = split_count;
+	attr->extra_split_ft = mlx5e_tc_post_act_get_ft(post_act);
+	flow->extra_split_attr = attr2;
+
+	attr2->post_act_handle = handle;
+
+	return 0;
+
+err_post_act_set_handle:
+	mlx5e_tc_post_act_unoffload(post_act, handle);
+err_post_act_offload:
+	mlx5e_tc_post_act_del(post_act, handle);
+err_free:
+	kvfree(parse_attr2);
+	kfree(attr2);
+	return err;
+}
+
 static int
 post_process_attr(struct mlx5e_tc_flow *flow,
 		  struct mlx5_flow_attr *attr,
 		  struct netlink_ext_ack *extack)
 {
+	int extra_split;
 	bool vf_tun;
 	int err = 0;
 
@@ -1757,6 +1848,13 @@ post_process_attr(struct mlx5e_tc_flow *flow,
 			goto err_out;
 	}
 
+	extra_split = extra_split_attr_dests_needed(flow, attr);
+	if (extra_split > 0) {
+		err = extra_split_attr_dests(flow, attr, extra_split);
+		if (err)
+			goto err_out;
+	}
+
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr);
 		if (err)
@@ -1971,6 +2069,11 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	mlx5e_tc_act_stats_del_flow(get_act_stats_handle(priv), flow);
 
 	free_flow_post_acts(flow);
+	if (flow->extra_split_attr) {
+		mlx5_free_flow_attr_actions(flow, flow->extra_split_attr);
+		kvfree(flow->extra_split_attr->parse_attr);
+		kfree(flow->extra_split_attr);
+	}
 	mlx5_free_flow_attr_actions(flow, attr);
 
 	kvfree(attr->esw_attr->rx_tun_attr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index b982e648ea48..e1b8cb78369f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -86,6 +86,7 @@ struct mlx5_flow_attr {
 	u32 dest_chain;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_table *dest_ft;
+	struct mlx5_flow_table *extra_split_ft;
 	u8 inner_match_level;
 	u8 outer_match_level;
 	u8 tun_ip_version;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 768199d2255a..f24f91d213f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -613,6 +613,13 @@ esw_setup_dests(struct mlx5_flow_destination *dest,
 		}
 	}
 
+	if (attr->extra_split_ft) {
+		flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
+		dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+		dest[*i].ft = attr->extra_split_ft;
+		(*i)++;
+	}
+
 out:
 	return err;
 }
-- 
cgit v1.3-3-g829e


From b11bde56246ee85a67364efa0e181b479543dfef Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:20 +0300
Subject: net/mlx5e: TC, Offload rewrite and mirror to both internal and
 external dests

Firmware has the limitation that it cannot offload a rule with rewrite
and mirror to internal and external destinations simultaneously.

This patch adds a workaround to this issue. Here the destination array
is split again, just like what's done in previous commit, but after
the action indexed by split_count - 1. An extra rule is added for the
leftover destinations. Such rule can be offloaded, even there are
destinations to both internal and external destinations, because the
header rewrite is left in the original FTE.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a28bf05d98f1..6b3b1afe8312 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1742,12 +1742,17 @@ has_encap_dests(struct mlx5_flow_attr *attr)
 static int
 extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr)
 {
+	bool int_dest = false, ext_dest = false;
 	struct mlx5_esw_flow_attr *esw_attr;
+	int i;
 
 	if (flow->attr != attr ||
 	    !list_is_first(&attr->list, &flow->attrs))
 		return 0;
 
+	if (flow_flag_test(flow, SLOW))
+		return 0;
+
 	esw_attr = attr->esw_attr;
 	if (!esw_attr->split_count ||
 	    esw_attr->split_count == esw_attr->out_count - 1)
@@ -1758,6 +1763,18 @@ extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr
 	     MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE))
 		return esw_attr->split_count + 1;
 
+	for (i = esw_attr->split_count; i < esw_attr->out_count; i++) {
+		/* external dest with encap is considered as internal by firmware */
+		if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK &&
+		    !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID))
+			ext_dest = true;
+		else
+			int_dest = true;
+
+		if (ext_dest && int_dest)
+			return esw_attr->split_count;
+	}
+
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From 4384bcff035e3699ab97286875d190f3661acc15 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:21 +0300
Subject: net/mlx5e: Be consistent with bitmap handling of link modes

Use the bitmap operations when accessing the advertised/supported link
modes and remove places that access them as arrays of unsigned longs
(underlying implementation of the bitmap), this makes the code much more
readable and clear.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 23 +++++++++++-----------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 36845872ae94..5fd81253d6b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -83,17 +83,15 @@ struct ptys2ethtool_config ptys2ext_ethtool_table[MLX5E_EXT_LINK_MODES_NUMBER];
 	({                                                              \
 		struct ptys2ethtool_config *cfg;                        \
 		const unsigned int modes[] = { __VA_ARGS__ };           \
-		unsigned int i, bit, idx;                               \
+		unsigned int i;                                         \
 		cfg = &ptys2##table##_ethtool_table[reg_];		\
 		bitmap_zero(cfg->supported,                             \
 			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
 		bitmap_zero(cfg->advertised,                            \
 			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
 		for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) {             \
-			bit = modes[i] % 64;                            \
-			idx = modes[i] / 64;                            \
-			__set_bit(bit, &cfg->supported[idx]);           \
-			__set_bit(bit, &cfg->advertised[idx]);          \
+			bitmap_set(cfg->supported, modes[i], 1);        \
+			bitmap_set(cfg->advertised, modes[i], 1);       \
 		}                                                       \
 	})
 
@@ -1299,7 +1297,8 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 	u32 i, ptys_modes = 0;
 
 	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (*ptys2legacy_ethtool_table[i].advertised == 0)
+		if (bitmap_empty(ptys2legacy_ethtool_table[i].advertised,
+				 __ETHTOOL_LINK_MODE_MASK_NBITS))
 			continue;
 		if (bitmap_intersects(ptys2legacy_ethtool_table[i].advertised,
 				      link_modes,
@@ -1313,18 +1312,18 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
-	unsigned long modes[2];
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes);
 
 	for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) {
-		if (ptys2ext_ethtool_table[i].advertised[0] == 0 &&
-		    ptys2ext_ethtool_table[i].advertised[1] == 0)
+		if (bitmap_empty(ptys2ext_ethtool_table[i].advertised,
+				 __ETHTOOL_LINK_MODE_MASK_NBITS))
 			continue;
-		memset(modes, 0, sizeof(modes));
+		bitmap_zero(modes, __ETHTOOL_LINK_MODE_MASK_NBITS);
 		bitmap_and(modes, ptys2ext_ethtool_table[i].advertised,
 			   link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS);
 
-		if (modes[0] == ptys2ext_ethtool_table[i].advertised[0] &&
-		    modes[1] == ptys2ext_ethtool_table[i].advertised[1])
+		if (bitmap_equal(modes, ptys2ext_ethtool_table[i].advertised,
+				 __ETHTOOL_LINK_MODE_MASK_NBITS))
 			ptys_modes |= MLX5E_PROT_MASK(i);
 	}
 	return ptys_modes;
-- 
cgit v1.3-3-g829e


From ab666b5287e898fcafc0ad1f2d4506cc3a1bfd23 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:22 +0300
Subject: net/mlx5e: Use extack in set ringparams callback

In case of errors in set ringparams, reflect it through extack instead
of a dmesg print.
While at it, make the messages more human friendly and remove two
redundant checks that are already validated by the core.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  3 ++-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 28 +++++++---------------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  2 +-
 .../ethernet/mellanox/mlx5/core/ipoib/ethtool.c    |  2 +-
 4 files changed, 13 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 5fd82c67b6ab..01781b70434c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1172,7 +1172,8 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv,
 				 struct ethtool_ringparam *param,
 				 struct kernel_ethtool_ringparam *kernel_param);
 int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
-				struct ethtool_ringparam *param);
+				struct ethtool_ringparam *param,
+				struct netlink_ext_ack *extack);
 void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv,
 				struct ethtool_channels *ch);
 int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 5fd81253d6b9..51624053722a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -352,35 +352,25 @@ static void mlx5e_get_ringparam(struct net_device *dev,
 }
 
 int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
-				struct ethtool_ringparam *param)
+				struct ethtool_ringparam *param,
+				struct netlink_ext_ack *extack)
 {
 	struct mlx5e_params new_params;
 	u8 log_rq_size;
 	u8 log_sq_size;
 	int err = 0;
 
-	if (param->rx_jumbo_pending) {
-		netdev_info(priv->netdev, "%s: rx_jumbo_pending not supported\n",
-			    __func__);
-		return -EINVAL;
-	}
-	if (param->rx_mini_pending) {
-		netdev_info(priv->netdev, "%s: rx_mini_pending not supported\n",
-			    __func__);
-		return -EINVAL;
-	}
-
 	if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) {
-		netdev_info(priv->netdev, "%s: rx_pending (%d) < min (%d)\n",
-			    __func__, param->rx_pending,
-			    1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "rx (%d) < min (%d)",
+				       param->rx_pending,
+				       1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE);
 		return -EINVAL;
 	}
 
 	if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) {
-		netdev_info(priv->netdev, "%s: tx_pending (%d) < min (%d)\n",
-			    __func__, param->tx_pending,
-			    1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "tx (%d) < min (%d)",
+				       param->tx_pending,
+				       1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE);
 		return -EINVAL;
 	}
 
@@ -416,7 +406,7 @@ static int mlx5e_set_ringparam(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	return mlx5e_ethtool_set_ringparam(priv, param);
+	return mlx5e_ethtool_set_ringparam(priv, param, extack);
 }
 
 void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 8790d57dc6db..916ba0db29f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -360,7 +360,7 @@ mlx5e_rep_set_ringparam(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
-	return mlx5e_ethtool_set_ringparam(priv, param);
+	return mlx5e_ethtool_set_ringparam(priv, param, extack);
 }
 
 static void mlx5e_rep_get_channels(struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 26f8a11b8906..424ff39db28d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -74,7 +74,7 @@ static int mlx5i_set_ringparam(struct net_device *dev,
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(dev);
 
-	return mlx5e_ethtool_set_ringparam(priv, param);
+	return mlx5e_ethtool_set_ringparam(priv, param, extack);
 }
 
 static void mlx5i_get_ringparam(struct net_device *dev,
-- 
cgit v1.3-3-g829e


From 29a943d71d231e2df81fd3834e75264904a77535 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:23 +0300
Subject: net/mlx5e: Use extack in get coalesce callback

In case of errors in get coalesce, reflect it through extack instead of
a dmesg print.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-8-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h            | 3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c    | 9 ++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c        | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 2 +-
 4 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 01781b70434c..7832f6b6c8a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -1180,7 +1180,8 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 			       struct ethtool_channels *ch);
 int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal,
-			       struct kernel_ethtool_coalesce *kernel_coal);
+			       struct kernel_ethtool_coalesce *kernel_coal,
+			       struct netlink_ext_ack *extack);
 int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal,
 			       struct kernel_ethtool_coalesce *kernel_coal,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 51624053722a..9760215926db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -545,12 +545,15 @@ static int mlx5e_set_channels(struct net_device *dev,
 
 int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal,
-			       struct kernel_ethtool_coalesce *kernel_coal)
+			       struct kernel_ethtool_coalesce *kernel_coal,
+			       struct netlink_ext_ack *extack)
 {
 	struct dim_cq_moder *rx_moder, *tx_moder;
 
-	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
+	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) {
+		NL_SET_ERR_MSG_MOD(extack, "CQ moderation not supported");
 		return -EOPNOTSUPP;
+	}
 
 	rx_moder = &priv->channels.params.rx_cq_moderation;
 	coal->rx_coalesce_usecs		= rx_moder->usec;
@@ -574,7 +577,7 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal);
+	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack);
 }
 
 static int mlx5e_ethtool_get_per_queue_coalesce(struct mlx5e_priv *priv, u32 queue,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 916ba0db29f2..b885042eef14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -386,7 +386,7 @@ static int mlx5e_rep_get_coalesce(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal);
+	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack);
 }
 
 static int mlx5e_rep_set_coalesce(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
index 424ff39db28d..9772327d5124 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c
@@ -132,7 +132,7 @@ static int mlx5i_get_coalesce(struct net_device *netdev,
 {
 	struct mlx5e_priv *priv = mlx5i_epriv(netdev);
 
-	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal);
+	return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack);
 }
 
 static int mlx5i_get_ts_info(struct net_device *netdev,
-- 
cgit v1.3-3-g829e


From 9c4298b466b19651203c8c8847fcbfe3e37ef6b7 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:24 +0300
Subject: net/mlx5e: Use extack in set coalesce callback

In case of errors in set coalesce, reflect it through extack instead of
a dmesg print.
While at it, make the messages more human friendly.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-9-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 9760215926db..c14a5542ae9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -699,26 +699,34 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 	int err = 0;
 
 	if (!MLX5_CAP_GEN(mdev, cq_moderation) ||
-	    !MLX5_CAP_GEN(mdev, cq_period_mode_modify))
+	    !MLX5_CAP_GEN(mdev, cq_period_mode_modify)) {
+		NL_SET_ERR_MSG_MOD(extack, "CQ moderation not supported");
 		return -EOPNOTSUPP;
+	}
 
 	if (coal->tx_coalesce_usecs > MLX5E_MAX_COAL_TIME ||
 	    coal->rx_coalesce_usecs > MLX5E_MAX_COAL_TIME) {
-		netdev_info(priv->netdev, "%s: maximum coalesce time supported is %lu usecs\n",
-			    __func__, MLX5E_MAX_COAL_TIME);
+		NL_SET_ERR_MSG_FMT_MOD(
+			extack,
+			"Max coalesce time %lu usecs, tx-usecs (%u) rx-usecs (%u)",
+			MLX5E_MAX_COAL_TIME, coal->tx_coalesce_usecs,
+			coal->rx_coalesce_usecs);
 		return -ERANGE;
 	}
 
 	if (coal->tx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES ||
 	    coal->rx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES) {
-		netdev_info(priv->netdev, "%s: maximum coalesced frames supported is %lu\n",
-			    __func__, MLX5E_MAX_COAL_FRAMES);
+		NL_SET_ERR_MSG_FMT_MOD(
+			extack,
+			"Max coalesce frames %lu, tx-frames (%u) rx-frames (%u)",
+			MLX5E_MAX_COAL_FRAMES, coal->tx_max_coalesced_frames,
+			coal->rx_max_coalesced_frames);
 		return -ERANGE;
 	}
 
 	if ((kernel_coal->use_cqe_mode_rx || kernel_coal->use_cqe_mode_tx) &&
 	    !MLX5_CAP_GEN(priv->mdev, cq_period_start_from_cqe)) {
-		NL_SET_ERR_MSG_MOD(extack, "cqe_mode_rx/tx is not supported on this device");
+		NL_SET_ERR_MSG_MOD(extack, "cqe-mode-rx/tx is not supported on this device");
 		return -EOPNOTSUPP;
 	}
 
-- 
cgit v1.3-3-g829e


From b5100b72da688282558b28255c03a2d72241a729 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:25 +0300
Subject: net/mlx5e: Use extack in get module eeprom by page callback

In case of errors in get module eeprom by page, reflect it through
extack instead of a dmesg print.
While at it, make the messages more human friendly.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-10-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c14a5542ae9c..56bdb4d07b7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2015,8 +2015,10 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev,
 		if (size_read == -EINVAL)
 			return -EINVAL;
 		if (size_read < 0) {
-			netdev_err(priv->netdev, "%s: mlx5_query_module_eeprom_by_page failed:0x%x\n",
-				   __func__, size_read);
+			NL_SET_ERR_MSG_FMT_MOD(
+				extack,
+				"Query module eeprom by page failed, read %u bytes, err %d\n",
+				i, size_read);
 			return i;
 		}
 
-- 
cgit v1.3-3-g829e


From 486aeb2db55b4509039f2e6017b2d06836893ee2 Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:26 +0300
Subject: net/mlx5e: CT: 'update' rules instead of 'replace'

Offloaded rules can be updated with a new modify header action
containing a changed restore cookie. This was done using the verb
'replace', while in some configurations 'update' is a better fit.

This commit renames the functions used to reflect that.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-11-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 34 +++++++++++-----------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index 71a168746ebe..ccee07d6ba1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -876,10 +876,10 @@ err_attr:
 }
 
 static int
-mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv,
-			      struct flow_rule *flow_rule,
-			      struct mlx5_ct_entry *entry,
-			      bool nat, u8 zone_restore_id)
+mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv,
+			     struct flow_rule *flow_rule,
+			     struct mlx5_ct_entry *entry,
+			     bool nat, u8 zone_restore_id)
 {
 	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
 	struct mlx5_flow_attr *attr = zone_rule->attr, *old_attr;
@@ -924,7 +924,7 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv,
 
 	kfree(old_attr);
 	kvfree(spec);
-	ct_dbg("Replaced ct entry rule in zone %d", entry->tuple.zone);
+	ct_dbg("Updated ct entry rule in zone %d", entry->tuple.zone);
 
 	return 0;
 
@@ -1141,23 +1141,23 @@ err_orig:
 }
 
 static int
-mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv,
-			       struct flow_rule *flow_rule,
-			       struct mlx5_ct_entry *entry,
-			       u8 zone_restore_id)
+mlx5_tc_ct_entry_update_rules(struct mlx5_tc_ct_priv *ct_priv,
+			      struct flow_rule *flow_rule,
+			      struct mlx5_ct_entry *entry,
+			      u8 zone_restore_id)
 {
 	int err = 0;
 
 	if (mlx5_tc_ct_entry_in_ct_table(entry)) {
-		err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, false,
-						    zone_restore_id);
+		err = mlx5_tc_ct_entry_update_rule(ct_priv, flow_rule, entry, false,
+						   zone_restore_id);
 		if (err)
 			return err;
 	}
 
 	if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) {
-		err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, true,
-						    zone_restore_id);
+		err = mlx5_tc_ct_entry_update_rule(ct_priv, flow_rule, entry, true,
+						   zone_restore_id);
 		if (err && mlx5_tc_ct_entry_in_ct_table(entry))
 			mlx5_tc_ct_entry_del_rule(ct_priv, entry, false);
 	}
@@ -1165,13 +1165,13 @@ mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv,
 }
 
 static int
-mlx5_tc_ct_block_flow_offload_replace(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule,
-				      struct mlx5_ct_entry *entry, unsigned long cookie)
+mlx5_tc_ct_block_flow_offload_update(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule,
+				     struct mlx5_ct_entry *entry, unsigned long cookie)
 {
 	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
 	int err;
 
-	err = mlx5_tc_ct_entry_replace_rules(ct_priv, flow_rule, entry, ft->zone_restore_id);
+	err = mlx5_tc_ct_entry_update_rules(ct_priv, flow_rule, entry, ft->zone_restore_id);
 	if (!err)
 		return 0;
 
@@ -1216,7 +1216,7 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft,
 		entry->restore_cookie = meta_action->ct_metadata.cookie;
 		spin_unlock_bh(&ct_priv->ht_lock);
 
-		err = mlx5_tc_ct_block_flow_offload_replace(ft, flow_rule, entry, cookie);
+		err = mlx5_tc_ct_block_flow_offload_update(ft, flow_rule, entry, cookie);
 		mlx5_tc_ct_entry_put(entry);
 		return err;
 	}
-- 
cgit v1.3-3-g829e


From 6b5662b75960b38cee4930284c93bd645b8e03ab Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Thu, 8 Aug 2024 08:59:27 +0300
Subject: net/mlx5e: CT: Update connection tracking steering entries

Previously, replacing a connection tracking steering entry was done by
adding a new rule (with the same tag but possibly different mod hdr
actions/labels) then removing the old rule.

This approach doesn't work in hardware steering because two steering
entries with the same tag cannot coexist in a hardware steering table.

This commit prepares for that by adding a new ct_rule_update operation on
the ct_fs_ops struct which is used instead of add+delete.
Implementations for both dmfs (firmware steering) and smfs (software
steering) are provided, which simply add the new rule and delete the old
one.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240808055927.2059700-12-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h  |  2 ++
 .../ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c | 21 +++++++++++++++++
 .../ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c | 26 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 12 ++++------
 4 files changed, 53 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
index bb6b1a979ba1..62b3f7ff5562 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h
@@ -25,6 +25,8 @@ struct mlx5_ct_fs_ops {
 						struct mlx5_flow_attr *attr,
 						struct flow_rule *flow_rule);
 	void (*ct_rule_del)(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule);
+	int (*ct_rule_update)(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule,
+			      struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr);
 
 	size_t priv_size;
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c
index ae4f55be48ce..64a82aafaaca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c
@@ -65,9 +65,30 @@ mlx5_ct_fs_dmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_ru
 	kfree(dmfs_rule);
 }
 
+static int mlx5_ct_fs_dmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule,
+					  struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr)
+{
+	struct mlx5_ct_fs_dmfs_rule *dmfs_rule = container_of(fs_rule,
+							      struct mlx5_ct_fs_dmfs_rule,
+							      fs_rule);
+	struct mlx5e_priv *priv = netdev_priv(fs->netdev);
+	struct mlx5_flow_handle *rule;
+
+	rule = mlx5_tc_rule_insert(priv, spec, attr);
+	if (IS_ERR(rule))
+		return PTR_ERR(rule);
+	mlx5_tc_rule_delete(priv, dmfs_rule->rule, dmfs_rule->attr);
+
+	dmfs_rule->rule = rule;
+	dmfs_rule->attr = attr;
+
+	return 0;
+}
+
 static struct mlx5_ct_fs_ops dmfs_ops = {
 	.ct_rule_add = mlx5_ct_fs_dmfs_ct_rule_add,
 	.ct_rule_del = mlx5_ct_fs_dmfs_ct_rule_del,
+	.ct_rule_update = mlx5_ct_fs_dmfs_ct_rule_update,
 
 	.init = mlx5_ct_fs_dmfs_init,
 	.destroy = mlx5_ct_fs_dmfs_destroy,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
index 8c531f4ec912..1c062a2e8996 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c
@@ -368,9 +368,35 @@ mlx5_ct_fs_smfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_ru
 	kfree(smfs_rule);
 }
 
+static int mlx5_ct_fs_smfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule,
+					  struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr)
+{
+	struct mlx5_ct_fs_smfs_rule *smfs_rule = container_of(fs_rule,
+							      struct mlx5_ct_fs_smfs_rule,
+							      fs_rule);
+	struct mlx5_ct_fs_smfs *fs_smfs = mlx5_ct_fs_priv(fs);
+	struct mlx5dr_action *actions[3];  /* We only need to create 3 actions, see below. */
+	struct mlx5dr_rule *rule;
+
+	actions[0] = smfs_rule->count_action;
+	actions[1] = attr->modify_hdr->action.dr_action;
+	actions[2] = fs_smfs->fwd_action;
+
+	rule = mlx5_smfs_rule_create(smfs_rule->smfs_matcher->dr_matcher, spec,
+				     ARRAY_SIZE(actions), actions, spec->flow_context.flow_source);
+	if (!rule)
+		return -EINVAL;
+
+	mlx5_smfs_rule_destroy(smfs_rule->rule);
+	smfs_rule->rule = rule;
+
+	return 0;
+}
+
 static struct mlx5_ct_fs_ops fs_smfs_ops = {
 	.ct_rule_add = mlx5_ct_fs_smfs_ct_rule_add,
 	.ct_rule_del = mlx5_ct_fs_smfs_ct_rule_del,
+	.ct_rule_update = mlx5_ct_fs_smfs_ct_rule_update,
 
 	.init = mlx5_ct_fs_smfs_init,
 	.destroy = mlx5_ct_fs_smfs_destroy,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index ccee07d6ba1d..dcfccaaa8d91 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -884,7 +884,6 @@ mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv,
 	struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat];
 	struct mlx5_flow_attr *attr = zone_rule->attr, *old_attr;
 	struct mlx5e_mod_hdr_handle *mh;
-	struct mlx5_ct_fs_rule *rule;
 	struct mlx5_flow_spec *spec;
 	int err;
 
@@ -902,22 +901,19 @@ mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv,
 	err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule, &mh, zone_restore_id,
 					      nat, mlx5_tc_ct_entry_in_ct_nat_table(entry));
 	if (err) {
-		ct_dbg("Failed to create ct entry mod hdr");
+		ct_dbg("Failed to create ct entry mod hdr, err: %d", err);
 		goto err_mod_hdr;
 	}
 
 	mlx5_tc_ct_set_tuple_match(ct_priv, spec, flow_rule);
 	mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG, entry->tuple.zone, MLX5_CT_ZONE_MASK);
 
-	rule = ct_priv->fs_ops->ct_rule_add(ct_priv->fs, spec, attr, flow_rule);
-	if (IS_ERR(rule)) {
-		err = PTR_ERR(rule);
-		ct_dbg("Failed to add replacement ct entry rule, nat: %d", nat);
+	err = ct_priv->fs_ops->ct_rule_update(ct_priv->fs, zone_rule->rule, spec, attr);
+	if (err) {
+		ct_dbg("Failed to update ct entry rule, nat: %d, err: %d", nat, err);
 		goto err_rule;
 	}
 
-	ct_priv->fs_ops->ct_rule_del(ct_priv->fs, zone_rule->rule);
-	zone_rule->rule = rule;
 	mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, old_attr, zone_rule->mh);
 	zone_rule->mh = mh;
 	mlx5_put_label_mapping(ct_priv, old_attr->ct_attr.ct_labels_id);
-- 
cgit v1.3-3-g829e


From 89fbe672bd0e5e5c39600fcc7a3bca0b8a212d23 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Thu, 8 Aug 2024 12:37:57 +0200
Subject: Revert "wifi: ath9k: use devm for request_irq()"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 92da4ce847bc5d942ddfdb102dba92f4e2797a59.

Felix pointed out that moving to devm for request_irq() can lead to a use after
free, and that avoiding that means having explicit frees that makes the devm
thing pretty pointless. So let's just revert the patch.

Link: https://lore.kernel.org/r/201f06b6-14f5-41bb-8897-49665cf14b66@nbd.name
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240808103758.11696-1-toke@toke.dk
---
 drivers/net/wireless/ath/ath9k/ahb.c | 7 +++++--
 drivers/net/wireless/ath/ath9k/pci.c | 9 ++++++---
 2 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ahb.c b/drivers/net/wireless/ath/ath9k/ahb.c
index 29f67ded8fe2..1a6697b6e3b4 100644
--- a/drivers/net/wireless/ath/ath9k/ahb.c
+++ b/drivers/net/wireless/ath/ath9k/ahb.c
@@ -118,7 +118,7 @@ static int ath_ahb_probe(struct platform_device *pdev)
 	sc->mem = mem;
 	sc->irq = irq;
 
-	ret = devm_request_irq(&pdev->dev, irq, ath_isr, IRQF_SHARED, "ath9k", sc);
+	ret = request_irq(irq, ath_isr, IRQF_SHARED, "ath9k", sc);
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq failed\n");
 		goto err_free_hw;
@@ -127,7 +127,7 @@ static int ath_ahb_probe(struct platform_device *pdev)
 	ret = ath9k_init_device(id->driver_data, sc, &ath_ahb_bus_ops);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to initialize device\n");
-		goto err_free_hw;
+		goto err_irq;
 	}
 
 	ah = sc->sc_ah;
@@ -137,6 +137,8 @@ static int ath_ahb_probe(struct platform_device *pdev)
 
 	return 0;
 
+ err_irq:
+	free_irq(irq, sc);
  err_free_hw:
 	ieee80211_free_hw(hw);
 	return ret;
@@ -150,6 +152,7 @@ static void ath_ahb_remove(struct platform_device *pdev)
 		struct ath_softc *sc = hw->priv;
 
 		ath9k_deinit_device(sc);
+		free_irq(sc->irq, sc);
 		ieee80211_free_hw(sc->hw);
 	}
 }
diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index ccf73886199a..1ff53520f0a3 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -965,9 +965,9 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	if (!msi_enabled)
-		ret = devm_request_irq(&pdev->dev, pdev->irq, ath_isr, IRQF_SHARED, "ath9k", sc);
+		ret = request_irq(pdev->irq, ath_isr, IRQF_SHARED, "ath9k", sc);
 	else
-		ret = devm_request_irq(&pdev->dev, pdev->irq, ath_isr, 0, "ath9k", sc);
+		ret = request_irq(pdev->irq, ath_isr, 0, "ath9k", sc);
 
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq failed\n");
@@ -979,7 +979,7 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = ath9k_init_device(id->device, sc, &ath_pci_bus_ops);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to initialize device\n");
-		goto err_irq;
+		goto err_init;
 	}
 
 	sc->sc_ah->msi_enabled = msi_enabled;
@@ -991,6 +991,8 @@ static int ath_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+err_init:
+	free_irq(sc->irq, sc);
 err_irq:
 	ieee80211_free_hw(hw);
 	return ret;
@@ -1004,6 +1006,7 @@ static void ath_pci_remove(struct pci_dev *pdev)
 	if (!is_ath9k_unloaded)
 		sc->sc_ah->ah_flags |= AH_UNPLUGGED;
 	ath9k_deinit_device(sc);
+	free_irq(sc->irq, sc);
 	ieee80211_free_hw(sc->hw);
 }
 
-- 
cgit v1.3-3-g829e


From eb84567e7208491cd6733cc867d849ab07dabd67 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Mon, 5 Aug 2024 08:39:13 +0200
Subject: wifi: mwifiex: simplify WPA flags setting

The WPA flags setting only depends on the wpa_versions bitfield and not
on the AKM suite, so move it out of the switch/case to simplify the code
a bit. Also set bss_config->protocol to zero explicitly. This is done
only to make the code clearer, bss_config has been zero alloced by the
caller, so should be zero already. No functional change intended.

Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Link: https://lore.kernel.org/r/20240723-mwifiex-wpa-psk-sha256-v3-1-025168a91da1@pengutronix.de
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240805-mwifiex-wpa-psk-sha256-v4-1-e1eee80508e6@pengutronix.de
---
 drivers/net/wireless/marvell/mwifiex/uap_cmd.c | 29 +++++++-------------------
 1 file changed, 8 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
index 073c665183b3..51fcae8726ed 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
@@ -46,34 +46,21 @@ int mwifiex_set_secure_params(struct mwifiex_private *priv,
 
 	bss_config->key_mgmt_operation |= KEY_MGMT_ON_HOST;
 
+	bss_config->protocol = 0;
+	if (params->crypto.wpa_versions & NL80211_WPA_VERSION_1)
+		bss_config->protocol |= PROTOCOL_WPA;
+	if (params->crypto.wpa_versions & NL80211_WPA_VERSION_2)
+		bss_config->protocol |= PROTOCOL_WPA2;
+
 	for (i = 0; i < params->crypto.n_akm_suites; i++) {
 		switch (params->crypto.akm_suites[i]) {
 		case WLAN_AKM_SUITE_8021X:
-			if (params->crypto.wpa_versions &
-			    NL80211_WPA_VERSION_1) {
-				bss_config->protocol = PROTOCOL_WPA;
-				bss_config->key_mgmt = KEY_MGMT_EAP;
-			}
-			if (params->crypto.wpa_versions &
-			    NL80211_WPA_VERSION_2) {
-				bss_config->protocol |= PROTOCOL_WPA2;
-				bss_config->key_mgmt = KEY_MGMT_EAP;
-			}
+			bss_config->key_mgmt = KEY_MGMT_EAP;
 			break;
 		case WLAN_AKM_SUITE_PSK:
-			if (params->crypto.wpa_versions &
-			    NL80211_WPA_VERSION_1) {
-				bss_config->protocol = PROTOCOL_WPA;
-				bss_config->key_mgmt = KEY_MGMT_PSK;
-			}
-			if (params->crypto.wpa_versions &
-			    NL80211_WPA_VERSION_2) {
-				bss_config->protocol |= PROTOCOL_WPA2;
-				bss_config->key_mgmt = KEY_MGMT_PSK;
-			}
+			bss_config->key_mgmt = KEY_MGMT_PSK;
 			break;
 		case WLAN_AKM_SUITE_SAE:
-			bss_config->protocol = PROTOCOL_WPA2;
 			bss_config->key_mgmt = KEY_MGMT_SAE;
 			break;
 		default:
-- 
cgit v1.3-3-g829e


From 36aa649915439aa924fb45aec3a6a9acea04a501 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Mon, 5 Aug 2024 08:39:14 +0200
Subject: wifi: mwifiex: fix key_mgmt setting

bss_config->key_mgmt specifies the AKM suites that are usable in
hardware. This variable is set to specific values while iterating
over the advertised AKM suites. This means the final value of the
variable depends on the order of the entries in the AKM suites
array. Instead of setting the variable, just set the relevant bits
in the key_mgmt bit field to make us independent of the order of
entries.
This behaviour is derived from the downstream driver that does the
same.
Also, set bss_config->key_mgmt to zero explicitly right before the
loop. bss_config has been zero allocated by the caller already, but
do so again to save the reader from following the code path.

Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Link: https://lore.kernel.org/r/20240723-mwifiex-wpa-psk-sha256-v3-2-025168a91da1@pengutronix.de
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240805-mwifiex-wpa-psk-sha256-v4-2-e1eee80508e6@pengutronix.de
---
 drivers/net/wireless/marvell/mwifiex/uap_cmd.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
index 51fcae8726ed..7214b6cf304a 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
@@ -52,16 +52,17 @@ int mwifiex_set_secure_params(struct mwifiex_private *priv,
 	if (params->crypto.wpa_versions & NL80211_WPA_VERSION_2)
 		bss_config->protocol |= PROTOCOL_WPA2;
 
+	bss_config->key_mgmt = 0;
 	for (i = 0; i < params->crypto.n_akm_suites; i++) {
 		switch (params->crypto.akm_suites[i]) {
 		case WLAN_AKM_SUITE_8021X:
-			bss_config->key_mgmt = KEY_MGMT_EAP;
+			bss_config->key_mgmt |= KEY_MGMT_EAP;
 			break;
 		case WLAN_AKM_SUITE_PSK:
-			bss_config->key_mgmt = KEY_MGMT_PSK;
+			bss_config->key_mgmt |= KEY_MGMT_PSK;
 			break;
 		case WLAN_AKM_SUITE_SAE:
-			bss_config->key_mgmt = KEY_MGMT_SAE;
+			bss_config->key_mgmt |= KEY_MGMT_SAE;
 			break;
 		default:
 			break;
-- 
cgit v1.3-3-g829e


From ca0107c3aa304a50899baadf324bdb3f9db3a87e Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Mon, 5 Aug 2024 08:39:15 +0200
Subject: wifi: mwifiex: add support for WPA-PSK-SHA256

This adds support for the WPA-PSK AKM suite with SHA256 as hashing
method (WPA-PSK-SHA256). Tested with a wpa_supplicant provided AP
using key_mgmt=WPA-PSK-SHA256.

Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://lore.kernel.org/r/20240717-mwifiex-wpa-psk-sha256-v2-2-eb53d5082b62@pengutronix.de
Acked-by: Brian Norris <briannorris@chromium.org>
Link: https://lore.kernel.org/r/20240723-mwifiex-wpa-psk-sha256-v3-3-025168a91da1@pengutronix.de
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240805-mwifiex-wpa-psk-sha256-v4-3-e1eee80508e6@pengutronix.de
---
 drivers/net/wireless/marvell/mwifiex/fw.h      | 1 +
 drivers/net/wireless/marvell/mwifiex/uap_cmd.c | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 65799ae3bc72..e91def0afa14 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -419,6 +419,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER {
 #define KEY_MGMT_NONE               0x04
 #define KEY_MGMT_PSK                0x02
 #define KEY_MGMT_EAP                0x01
+#define KEY_MGMT_PSK_SHA256         0x100
 #define KEY_MGMT_SAE                0x400
 #define CIPHER_TKIP                 0x04
 #define CIPHER_AES_CCMP             0x08
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
index 7214b6cf304a..1c0ceac6b27f 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_cmd.c
@@ -61,6 +61,9 @@ int mwifiex_set_secure_params(struct mwifiex_private *priv,
 		case WLAN_AKM_SUITE_PSK:
 			bss_config->key_mgmt |= KEY_MGMT_PSK;
 			break;
+		case WLAN_AKM_SUITE_PSK_SHA256:
+			bss_config->key_mgmt |= KEY_MGMT_PSK_SHA256;
+			break;
 		case WLAN_AKM_SUITE_SAE:
 			bss_config->key_mgmt |= KEY_MGMT_SAE;
 			break;
-- 
cgit v1.3-3-g829e


From 089332e703b681c8f62210ae5ef507df10324356 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 6 Aug 2024 12:25:57 -0600
Subject: wifi: ipw2x00: libipw: Avoid -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in order to avoid ending up with a flexible-array member in the
middle of multiple other structs, we use the `__struct_group()`
helper to create a new tagged `struct libipw_hdr_3addr_hdr`.
This structure groups together all the members of the flexible
`struct libipw_hdr_3addr` except the flexible array.

As a result, the array is effectively separated from the rest of the
members without modifying the memory layout of the flexible structure.
We then change the type of the middle struct members currently causing
trouble from `struct libipw_hdr_3addr` to `struct libipw_hdr_3addr_hdr`.

We also want to ensure that when new members need to be added to the
flexible structure, they are always included within the newly created
tagged struct. For this, we use `static_assert()`. This ensures that the
memory layout for both the flexible structure and the new tagged struct
is the same after any changes.

This approach avoids having to implement `struct libipw_hdr_3addr_hdr`
as a completely separate structure, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

Also, remove a couple of unused structures `struct libipw_ibss_dfs` and
`struct libipw_assoc_request`.

So, with these changes, fix the following warnings:

drivers/net/wireless/intel/ipw2x00/libipw.h:403:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:420:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:433:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:441:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:447:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:460:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:468:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:476:33: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:592:36: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/ZrJqtUpCI+uCeb4D@cute
---
 drivers/net/wireless/intel/ipw2x00/libipw.h | 46 +++++++++++------------------
 1 file changed, 18 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/libipw.h b/drivers/net/wireless/intel/ipw2x00/libipw.h
index 9065ca5b0208..bad080d33c07 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw.h
+++ b/drivers/net/wireless/intel/ipw2x00/libipw.h
@@ -345,14 +345,19 @@ struct libipw_hdr_2addr {
 } __packed;
 
 struct libipw_hdr_3addr {
-	__le16 frame_ctl;
-	__le16 duration_id;
-	u8 addr1[ETH_ALEN];
-	u8 addr2[ETH_ALEN];
-	u8 addr3[ETH_ALEN];
-	__le16 seq_ctl;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(libipw_hdr_3addr_hdr, hdr, __packed,
+		__le16 frame_ctl;
+		__le16 duration_id;
+		u8 addr1[ETH_ALEN];
+		u8 addr2[ETH_ALEN];
+		u8 addr3[ETH_ALEN];
+		__le16 seq_ctl;
+	);
 	u8 payload[];
 } __packed;
+static_assert(offsetof(struct libipw_hdr_3addr, payload) == sizeof(struct libipw_hdr_3addr_hdr),
+	      "struct member likely outside of __struct_group()");
 
 struct libipw_hdr_4addr {
 	__le16 frame_ctl;
@@ -400,7 +405,7 @@ struct libipw_info_element {
 */
 
 struct libipw_auth {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	__le16 algorithm;
 	__le16 transaction;
 	__le16 status;
@@ -417,7 +422,7 @@ struct libipw_channel_switch {
 } __packed;
 
 struct libipw_action {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	u8 category;
 	u8 action;
 	union {
@@ -430,7 +435,7 @@ struct libipw_action {
 } __packed;
 
 struct libipw_disassoc {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	__le16 reason;
 } __packed;
 
@@ -438,13 +443,13 @@ struct libipw_disassoc {
 #define libipw_deauth libipw_disassoc
 
 struct libipw_probe_request {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	/* SSID, supported rates */
 	u8 variable[];
 } __packed;
 
 struct libipw_probe_response {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	__le32 time_stamp[2];
 	__le16 beacon_interval;
 	__le16 capability;
@@ -456,16 +461,8 @@ struct libipw_probe_response {
 /* Alias beacon for probe_response */
 #define libipw_beacon libipw_probe_response
 
-struct libipw_assoc_request {
-	struct libipw_hdr_3addr header;
-	__le16 capability;
-	__le16 listen_interval;
-	/* SSID, supported rates, RSN */
-	u8 variable[];
-} __packed;
-
 struct libipw_reassoc_request {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	__le16 capability;
 	__le16 listen_interval;
 	u8 current_ap[ETH_ALEN];
@@ -473,7 +470,7 @@ struct libipw_reassoc_request {
 } __packed;
 
 struct libipw_assoc_response {
-	struct libipw_hdr_3addr header;
+	struct libipw_hdr_3addr_hdr header;
 	__le16 capability;
 	__le16 status;
 	__le16 aid;
@@ -588,13 +585,6 @@ struct libipw_channel_map {
 	u8 map;
 } __packed;
 
-struct libipw_ibss_dfs {
-	struct libipw_info_element ie;
-	u8 owner[ETH_ALEN];
-	u8 recovery_interval;
-	struct libipw_channel_map channel_map[];
-};
-
 struct libipw_csa {
 	u8 mode;
 	u8 channel;
-- 
cgit v1.3-3-g829e


From e2b1762cf32fb9be1e662ec1e8f3b8b36a9b293d Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:44 +0100
Subject: documentation/networking: update l2tp docs

l2tp no longer uses sk_user_data in tunnel sockets and now manages
tunnel/session lifetimes slightly differently. Update docs to cover
this.

CC: linux-doc@vger.kernel.org
CC: corbet@lwn.net
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/l2tp.rst | 54 +++++++++++++++------------------------
 1 file changed, 20 insertions(+), 34 deletions(-)

diff --git a/Documentation/networking/l2tp.rst b/Documentation/networking/l2tp.rst
index 8496b467dea4..e8cf8b3e60ac 100644
--- a/Documentation/networking/l2tp.rst
+++ b/Documentation/networking/l2tp.rst
@@ -638,9 +638,8 @@ Tunnels are identified by a unique tunnel id. The id is 16-bit for
 L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit
 value.
 
-Tunnels are kept in a per-net list, indexed by tunnel id. The tunnel
-id namespace is shared by L2TPv2 and L2TPv3. The tunnel context can be
-derived from the socket's sk_user_data.
+Tunnels are kept in a per-net list, indexed by tunnel id. The
+tunnel id namespace is shared by L2TPv2 and L2TPv3.
 
 Handling tunnel socket close is perhaps the most tricky part of the
 L2TP implementation. If userspace closes a tunnel socket, the L2TP
@@ -652,9 +651,7 @@ socket's encap_destroy handler is invoked, which L2TP uses to initiate
 its tunnel close actions. For L2TPIP sockets, the socket's close
 handler initiates the same tunnel close actions. All sessions are
 first closed. Each session drops its tunnel ref. When the tunnel ref
-reaches zero, the tunnel puts its socket ref. When the socket is
-eventually destroyed, its sk_destruct finally frees the L2TP tunnel
-context.
+reaches zero, the tunnel drops its socket ref.
 
 Sessions
 --------
@@ -667,10 +664,7 @@ pseudowire) or other data types such as PPP, ATM, HDLC or Frame
 Relay. Linux currently implements only Ethernet and PPP session types.
 
 Some L2TP session types also have a socket (PPP pseudowires) while
-others do not (Ethernet pseudowires). We can't therefore use the
-socket reference count as the reference count for session
-contexts. The L2TP implementation therefore has its own internal
-reference counts on the session contexts.
+others do not (Ethernet pseudowires).
 
 Like tunnels, L2TP sessions are identified by a unique
 session id. Just as with tunnel ids, the session id is 16-bit for
@@ -680,21 +674,19 @@ value.
 Sessions hold a ref on their parent tunnel to ensure that the tunnel
 stays extant while one or more sessions references it.
 
-Sessions are kept in a per-tunnel list, indexed by session id. L2TPv3
-sessions are also kept in a per-net list indexed by session id,
-because L2TPv3 session ids are unique across all tunnels and L2TPv3
-data packets do not contain a tunnel id in the header. This list is
-therefore needed to find the session context associated with a
-received data packet when the tunnel context cannot be derived from
-the tunnel socket.
+Sessions are kept in a per-net list. L2TPv2 sessions and L2TPv3
+sessions are stored in separate lists. L2TPv2 sessions are keyed
+by a 32-bit key made up of the 16-bit tunnel ID and 16-bit
+session ID. L2TPv3 sessions are keyed by the 32-bit session ID, since
+L2TPv3 session ids are unique across all tunnels.
 
 Although the L2TPv3 RFC specifies that L2TPv3 session ids are not
-scoped by the tunnel, the kernel does not police this for L2TPv3 UDP
-tunnels and does not add sessions of L2TPv3 UDP tunnels into the
-per-net session list. In the UDP receive code, we must trust that the
-tunnel can be identified using the tunnel socket's sk_user_data and
-lookup the session in the tunnel's session list instead of the per-net
-session list.
+scoped by the tunnel, the Linux implementation has historically
+allowed this. Such session id collisions are supported using a per-net
+hash table keyed by sk and session ID. When looking up L2TPv3
+sessions, the list entry may link to multiple sessions with that
+session ID, in which case the session matching the given sk (tunnel)
+is used.
 
 PPP
 ---
@@ -714,10 +706,9 @@ The L2TP PPP implementation handles the closing of a PPPoL2TP socket
 by closing its corresponding L2TP session. This is complicated because
 it must consider racing with netlink session create/destroy requests
 and pppol2tp_connect trying to reconnect with a session that is in the
-process of being closed. Unlike tunnels, PPP sessions do not hold a
-ref on their associated socket, so code must be careful to sock_hold
-the socket where necessary. For all the details, see commit
-3d609342cc04129ff7568e19316ce3d7451a27e8.
+process of being closed. PPP sessions hold a ref on their associated
+socket in order that the socket remains extants while the session
+references it.
 
 Ethernet
 --------
@@ -761,15 +752,10 @@ Limitations
 
 The current implementation has a number of limitations:
 
-  1) Multiple UDP sockets with the same 5-tuple address cannot be
-     used. The kernel's tunnel context is identified using private
-     data associated with the socket so it is important that each
-     socket is uniquely identified by its address.
-
-  2) Interfacing with openvswitch is not yet implemented. It may be
+  1) Interfacing with openvswitch is not yet implemented. It may be
      useful to map OVS Ethernet and VLAN ports into L2TPv3 tunnels.
 
-  3) VLAN pseudowires are implemented using an ``l2tpethN`` interface
+  2) VLAN pseudowires are implemented using an ``l2tpethN`` interface
      configured with a VLAN sub-interface. Since L2TPv3 VLAN
      pseudowires carry one and only one VLAN, it may be better to use
      a single netdevice rather than an ``l2tpethN`` and ``l2tpethN``:M
-- 
cgit v1.3-3-g829e


From 168464c19e1ab7ddc5fb80d9c9560cfbcce6211d Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:45 +0100
Subject: l2tp: remove inline from functions in c sources

Update l2tp to remove the inline keyword from several functions in C
sources, since this is now discouraged.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 6 +++---
 net/l2tp/l2tp_ip.c   | 2 +-
 net/l2tp/l2tp_ip6.c  | 2 +-
 net/l2tp/l2tp_ppp.c  | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ce3b316e2327..70c231fcaa2e 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -117,12 +117,12 @@ struct l2tp_net {
 	struct hlist_head l2tp_v3_session_htable[16];
 };
 
-static inline u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id)
+static u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id)
 {
 	return ((u32)tunnel_id) << 16 | session_id;
 }
 
-static inline unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id)
+static unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id)
 {
 	return ((unsigned long)sk) + session_id;
 }
@@ -135,7 +135,7 @@ static bool l2tp_sk_is_v6(struct sock *sk)
 }
 #endif
 
-static inline struct l2tp_net *l2tp_pernet(const struct net *net)
+static struct l2tp_net *l2tp_pernet(const struct net *net)
 {
 	return net_generic(net, l2tp_net_id);
 }
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index f21dcbf3efd5..9bd29667ae34 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -37,7 +37,7 @@ static DEFINE_RWLOCK(l2tp_ip_lock);
 static struct hlist_head l2tp_ip_table;
 static struct hlist_head l2tp_ip_bind_table;
 
-static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk)
+static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk)
 {
 	return (struct l2tp_ip_sock *)sk;
 }
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 3b0465f2d60d..a7b7626ca2c6 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -43,7 +43,7 @@ static DEFINE_RWLOCK(l2tp_ip6_lock);
 static struct hlist_head l2tp_ip6_table;
 static struct hlist_head l2tp_ip6_bind_table;
 
-static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
+static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
 {
 	return (struct l2tp_ip6_sock *)sk;
 }
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 9b4273fd518a..c25dd8e36074 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -149,7 +149,7 @@ static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session)
 
 /* Helpers to obtain tunnel/session contexts from sockets.
  */
-static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
+static struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
 {
 	struct l2tp_session *session;
 
-- 
cgit v1.3-3-g829e


From ebed6606b95954b94df6229db806978b32f3fa23 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:46 +0100
Subject: l2tp: move l2tp_ip and l2tp_ip6 data to pernet

l2tp_ip[6] have always used global socket tables. It is therefore not
possible to create l2tpip sockets in different namespaces with the
same socket address.

To support this, move l2tpip socket tables to pernet data.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ip.c  | 108 +++++++++++++++++++++++++++++++++++++++------------
 net/l2tp/l2tp_ip6.c | 110 ++++++++++++++++++++++++++++++++++++++++------------
 2 files changed, 168 insertions(+), 50 deletions(-)

diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 9bd29667ae34..f563c8afd8f3 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -22,9 +22,19 @@
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include "l2tp_core.h"
 
+/* per-net private data for this module */
+static unsigned int l2tp_ip_net_id;
+struct l2tp_ip_net {
+	rwlock_t l2tp_ip_lock;
+	struct hlist_head l2tp_ip_table;
+	struct hlist_head l2tp_ip_bind_table;
+};
+
 struct l2tp_ip_sock {
 	/* inet_sock has to be the first member of l2tp_ip_sock */
 	struct inet_sock	inet;
@@ -33,21 +43,23 @@ struct l2tp_ip_sock {
 	u32			peer_conn_id;
 };
 
-static DEFINE_RWLOCK(l2tp_ip_lock);
-static struct hlist_head l2tp_ip_table;
-static struct hlist_head l2tp_ip_bind_table;
-
 static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk)
 {
 	return (struct l2tp_ip_sock *)sk;
 }
 
+static struct l2tp_ip_net *l2tp_ip_pernet(const struct net *net)
+{
+	return net_generic(net, l2tp_ip_net_id);
+}
+
 static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr,
 					  __be32 raddr, int dif, u32 tunnel_id)
 {
+	struct l2tp_ip_net *pn = l2tp_ip_pernet(net);
 	struct sock *sk;
 
-	sk_for_each_bound(sk, &l2tp_ip_bind_table) {
+	sk_for_each_bound(sk, &pn->l2tp_ip_bind_table) {
 		const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk);
 		const struct inet_sock *inet = inet_sk(sk);
 		int bound_dev_if;
@@ -113,6 +125,7 @@ found:
 static int l2tp_ip_recv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct l2tp_ip_net *pn;
 	struct sock *sk;
 	u32 session_id;
 	u32 tunnel_id;
@@ -121,6 +134,8 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	struct iphdr *iph;
 
+	pn = l2tp_ip_pernet(net);
+
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
@@ -167,15 +182,15 @@ pass_up:
 	tunnel_id = ntohl(*(__be32 *)&skb->data[4]);
 	iph = (struct iphdr *)skb_network_header(skb);
 
-	read_lock_bh(&l2tp_ip_lock);
+	read_lock_bh(&pn->l2tp_ip_lock);
 	sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb),
 				   tunnel_id);
 	if (!sk) {
-		read_unlock_bh(&l2tp_ip_lock);
+		read_unlock_bh(&pn->l2tp_ip_lock);
 		goto discard;
 	}
 	sock_hold(sk);
-	read_unlock_bh(&l2tp_ip_lock);
+	read_unlock_bh(&pn->l2tp_ip_lock);
 
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_put;
@@ -198,21 +213,25 @@ discard:
 
 static int l2tp_ip_hash(struct sock *sk)
 {
+	struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk));
+
 	if (sk_unhashed(sk)) {
-		write_lock_bh(&l2tp_ip_lock);
-		sk_add_node(sk, &l2tp_ip_table);
-		write_unlock_bh(&l2tp_ip_lock);
+		write_lock_bh(&pn->l2tp_ip_lock);
+		sk_add_node(sk, &pn->l2tp_ip_table);
+		write_unlock_bh(&pn->l2tp_ip_lock);
 	}
 	return 0;
 }
 
 static void l2tp_ip_unhash(struct sock *sk)
 {
+	struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk));
+
 	if (sk_unhashed(sk))
 		return;
-	write_lock_bh(&l2tp_ip_lock);
+	write_lock_bh(&pn->l2tp_ip_lock);
 	sk_del_node_init(sk);
-	write_unlock_bh(&l2tp_ip_lock);
+	write_unlock_bh(&pn->l2tp_ip_lock);
 }
 
 static int l2tp_ip_open(struct sock *sk)
@@ -226,10 +245,12 @@ static int l2tp_ip_open(struct sock *sk)
 
 static void l2tp_ip_close(struct sock *sk, long timeout)
 {
-	write_lock_bh(&l2tp_ip_lock);
+	struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk));
+
+	write_lock_bh(&pn->l2tp_ip_lock);
 	hlist_del_init(&sk->sk_bind_node);
 	sk_del_node_init(sk);
-	write_unlock_bh(&l2tp_ip_lock);
+	write_unlock_bh(&pn->l2tp_ip_lock);
 	sk_common_release(sk);
 }
 
@@ -253,6 +274,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr;
 	struct net *net = sock_net(sk);
+	struct l2tp_ip_net *pn;
 	int ret;
 	int chk_addr_ret;
 
@@ -283,10 +305,11 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
 		inet->inet_saddr = 0;  /* Use device */
 
-	write_lock_bh(&l2tp_ip_lock);
+	pn = l2tp_ip_pernet(net);
+	write_lock_bh(&pn->l2tp_ip_lock);
 	if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0,
 				  sk->sk_bound_dev_if, addr->l2tp_conn_id)) {
-		write_unlock_bh(&l2tp_ip_lock);
+		write_unlock_bh(&pn->l2tp_ip_lock);
 		ret = -EADDRINUSE;
 		goto out;
 	}
@@ -294,9 +317,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk_dst_reset(sk);
 	l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id;
 
-	sk_add_bind_node(sk, &l2tp_ip_bind_table);
+	sk_add_bind_node(sk, &pn->l2tp_ip_bind_table);
 	sk_del_node_init(sk);
-	write_unlock_bh(&l2tp_ip_lock);
+	write_unlock_bh(&pn->l2tp_ip_lock);
 
 	ret = 0;
 	sock_reset_flag(sk, SOCK_ZAPPED);
@@ -310,6 +333,7 @@ out:
 static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr;
+	struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk));
 	int rc;
 
 	if (addr_len < sizeof(*lsa))
@@ -332,10 +356,10 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 
 	l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
 
-	write_lock_bh(&l2tp_ip_lock);
+	write_lock_bh(&pn->l2tp_ip_lock);
 	hlist_del_init(&sk->sk_bind_node);
-	sk_add_bind_node(sk, &l2tp_ip_bind_table);
-	write_unlock_bh(&l2tp_ip_lock);
+	sk_add_bind_node(sk, &pn->l2tp_ip_bind_table);
+	write_unlock_bh(&pn->l2tp_ip_lock);
 
 out_sk:
 	release_sock(sk);
@@ -640,25 +664,58 @@ static struct net_protocol l2tp_ip_protocol __read_mostly = {
 	.handler	= l2tp_ip_recv,
 };
 
+static __net_init int l2tp_ip_init_net(struct net *net)
+{
+	struct l2tp_ip_net *pn = net_generic(net, l2tp_ip_net_id);
+
+	rwlock_init(&pn->l2tp_ip_lock);
+	INIT_HLIST_HEAD(&pn->l2tp_ip_table);
+	INIT_HLIST_HEAD(&pn->l2tp_ip_bind_table);
+	return 0;
+}
+
+static __net_exit void l2tp_ip_exit_net(struct net *net)
+{
+	struct l2tp_ip_net *pn = l2tp_ip_pernet(net);
+
+	write_lock_bh(&pn->l2tp_ip_lock);
+	WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_table) != 0);
+	WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_bind_table) != 0);
+	write_unlock_bh(&pn->l2tp_ip_lock);
+}
+
+static struct pernet_operations l2tp_ip_net_ops = {
+	.init = l2tp_ip_init_net,
+	.exit = l2tp_ip_exit_net,
+	.id   = &l2tp_ip_net_id,
+	.size = sizeof(struct l2tp_ip_net),
+};
+
 static int __init l2tp_ip_init(void)
 {
 	int err;
 
 	pr_info("L2TP IP encapsulation support (L2TPv3)\n");
 
+	err = register_pernet_device(&l2tp_ip_net_ops);
+	if (err)
+		goto out;
+
 	err = proto_register(&l2tp_ip_prot, 1);
 	if (err != 0)
-		goto out;
+		goto out1;
 
 	err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP);
 	if (err)
-		goto out1;
+		goto out2;
 
 	inet_register_protosw(&l2tp_ip_protosw);
 	return 0;
 
-out1:
+out2:
 	proto_unregister(&l2tp_ip_prot);
+out1:
+	unregister_pernet_device(&l2tp_ip_net_ops);
 out:
 	return err;
 }
@@ -668,6 +725,7 @@ static void __exit l2tp_ip_exit(void)
 	inet_unregister_protosw(&l2tp_ip_protosw);
 	inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP);
 	proto_unregister(&l2tp_ip_prot);
+	unregister_pernet_device(&l2tp_ip_net_ops);
 }
 
 module_init(l2tp_ip_init);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index a7b7626ca2c6..dcec1de2898e 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -22,6 +22,8 @@
 #include <net/tcp_states.h>
 #include <net/protocol.h>
 #include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include <net/transp_v6.h>
 #include <net/addrconf.h>
@@ -29,6 +31,14 @@
 
 #include "l2tp_core.h"
 
+/* per-net private data for this module */
+static unsigned int l2tp_ip6_net_id;
+struct l2tp_ip6_net {
+	rwlock_t l2tp_ip6_lock;
+	struct hlist_head l2tp_ip6_table;
+	struct hlist_head l2tp_ip6_bind_table;
+};
+
 struct l2tp_ip6_sock {
 	/* inet_sock has to be the first member of l2tp_ip6_sock */
 	struct inet_sock	inet;
@@ -39,23 +49,25 @@ struct l2tp_ip6_sock {
 	struct ipv6_pinfo	inet6;
 };
 
-static DEFINE_RWLOCK(l2tp_ip6_lock);
-static struct hlist_head l2tp_ip6_table;
-static struct hlist_head l2tp_ip6_bind_table;
-
 static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
 {
 	return (struct l2tp_ip6_sock *)sk;
 }
 
+static struct l2tp_ip6_net *l2tp_ip6_pernet(const struct net *net)
+{
+	return net_generic(net, l2tp_ip6_net_id);
+}
+
 static struct sock *__l2tp_ip6_bind_lookup(const struct net *net,
 					   const struct in6_addr *laddr,
 					   const struct in6_addr *raddr,
 					   int dif, u32 tunnel_id)
 {
+	struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net);
 	struct sock *sk;
 
-	sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
+	sk_for_each_bound(sk, &pn->l2tp_ip6_bind_table) {
 		const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk);
 		const struct in6_addr *sk_raddr = &sk->sk_v6_daddr;
 		const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
@@ -123,6 +135,7 @@ found:
 static int l2tp_ip6_recv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	struct l2tp_ip6_net *pn;
 	struct sock *sk;
 	u32 session_id;
 	u32 tunnel_id;
@@ -131,6 +144,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_tunnel *tunnel = NULL;
 	struct ipv6hdr *iph;
 
+	pn = l2tp_ip6_pernet(net);
+
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
 
@@ -177,15 +192,15 @@ pass_up:
 	tunnel_id = ntohl(*(__be32 *)&skb->data[4]);
 	iph = ipv6_hdr(skb);
 
-	read_lock_bh(&l2tp_ip6_lock);
+	read_lock_bh(&pn->l2tp_ip6_lock);
 	sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
 				    inet6_iif(skb), tunnel_id);
 	if (!sk) {
-		read_unlock_bh(&l2tp_ip6_lock);
+		read_unlock_bh(&pn->l2tp_ip6_lock);
 		goto discard;
 	}
 	sock_hold(sk);
-	read_unlock_bh(&l2tp_ip6_lock);
+	read_unlock_bh(&pn->l2tp_ip6_lock);
 
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_put;
@@ -208,21 +223,25 @@ discard:
 
 static int l2tp_ip6_hash(struct sock *sk)
 {
+	struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk));
+
 	if (sk_unhashed(sk)) {
-		write_lock_bh(&l2tp_ip6_lock);
-		sk_add_node(sk, &l2tp_ip6_table);
-		write_unlock_bh(&l2tp_ip6_lock);
+		write_lock_bh(&pn->l2tp_ip6_lock);
+		sk_add_node(sk, &pn->l2tp_ip6_table);
+		write_unlock_bh(&pn->l2tp_ip6_lock);
 	}
 	return 0;
 }
 
 static void l2tp_ip6_unhash(struct sock *sk)
 {
+	struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk));
+
 	if (sk_unhashed(sk))
 		return;
-	write_lock_bh(&l2tp_ip6_lock);
+	write_lock_bh(&pn->l2tp_ip6_lock);
 	sk_del_node_init(sk);
-	write_unlock_bh(&l2tp_ip6_lock);
+	write_unlock_bh(&pn->l2tp_ip6_lock);
 }
 
 static int l2tp_ip6_open(struct sock *sk)
@@ -236,10 +255,12 @@ static int l2tp_ip6_open(struct sock *sk)
 
 static void l2tp_ip6_close(struct sock *sk, long timeout)
 {
-	write_lock_bh(&l2tp_ip6_lock);
+	struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk));
+
+	write_lock_bh(&pn->l2tp_ip6_lock);
 	hlist_del_init(&sk->sk_bind_node);
 	sk_del_node_init(sk);
-	write_unlock_bh(&l2tp_ip6_lock);
+	write_unlock_bh(&pn->l2tp_ip6_lock);
 
 	sk_common_release(sk);
 }
@@ -265,11 +286,14 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *)uaddr;
 	struct net *net = sock_net(sk);
+	struct l2tp_ip6_net *pn;
 	__be32 v4addr = 0;
 	int bound_dev_if;
 	int addr_type;
 	int err;
 
+	pn = l2tp_ip6_pernet(net);
+
 	if (addr->l2tp_family != AF_INET6)
 		return -EINVAL;
 	if (addr_len < sizeof(*addr))
@@ -327,10 +351,10 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 	rcu_read_unlock();
 
-	write_lock_bh(&l2tp_ip6_lock);
+	write_lock_bh(&pn->l2tp_ip6_lock);
 	if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if,
 				   addr->l2tp_conn_id)) {
-		write_unlock_bh(&l2tp_ip6_lock);
+		write_unlock_bh(&pn->l2tp_ip6_lock);
 		err = -EADDRINUSE;
 		goto out_unlock;
 	}
@@ -343,9 +367,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;
 
-	sk_add_bind_node(sk, &l2tp_ip6_bind_table);
+	sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table);
 	sk_del_node_init(sk);
-	write_unlock_bh(&l2tp_ip6_lock);
+	write_unlock_bh(&pn->l2tp_ip6_lock);
 
 	sock_reset_flag(sk, SOCK_ZAPPED);
 	release_sock(sk);
@@ -367,6 +391,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
 	struct in6_addr	*daddr;
 	int	addr_type;
 	int rc;
+	struct l2tp_ip6_net *pn;
 
 	if (addr_len < sizeof(*lsa))
 		return -EINVAL;
@@ -398,10 +423,11 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
 
-	write_lock_bh(&l2tp_ip6_lock);
+	pn = l2tp_ip6_pernet(sock_net(sk));
+	write_lock_bh(&pn->l2tp_ip6_lock);
 	hlist_del_init(&sk->sk_bind_node);
-	sk_add_bind_node(sk, &l2tp_ip6_bind_table);
-	write_unlock_bh(&l2tp_ip6_lock);
+	sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table);
+	write_unlock_bh(&pn->l2tp_ip6_lock);
 
 out_sk:
 	release_sock(sk);
@@ -768,25 +794,58 @@ static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
 	.handler	= l2tp_ip6_recv,
 };
 
+static __net_init int l2tp_ip6_init_net(struct net *net)
+{
+	struct l2tp_ip6_net *pn = net_generic(net, l2tp_ip6_net_id);
+
+	rwlock_init(&pn->l2tp_ip6_lock);
+	INIT_HLIST_HEAD(&pn->l2tp_ip6_table);
+	INIT_HLIST_HEAD(&pn->l2tp_ip6_bind_table);
+	return 0;
+}
+
+static __net_exit void l2tp_ip6_exit_net(struct net *net)
+{
+	struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net);
+
+	write_lock_bh(&pn->l2tp_ip6_lock);
+	WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_table) != 0);
+	WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_bind_table) != 0);
+	write_unlock_bh(&pn->l2tp_ip6_lock);
+}
+
+static struct pernet_operations l2tp_ip6_net_ops = {
+	.init = l2tp_ip6_init_net,
+	.exit = l2tp_ip6_exit_net,
+	.id   = &l2tp_ip6_net_id,
+	.size = sizeof(struct l2tp_ip6_net),
+};
+
 static int __init l2tp_ip6_init(void)
 {
 	int err;
 
 	pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n");
 
+	err = register_pernet_device(&l2tp_ip6_net_ops);
+	if (err)
+		goto out;
+
 	err = proto_register(&l2tp_ip6_prot, 1);
 	if (err != 0)
-		goto out;
+		goto out1;
 
 	err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
 	if (err)
-		goto out1;
+		goto out2;
 
 	inet6_register_protosw(&l2tp_ip6_protosw);
 	return 0;
 
-out1:
+out2:
 	proto_unregister(&l2tp_ip6_prot);
+out1:
+	unregister_pernet_device(&l2tp_ip6_net_ops);
 out:
 	return err;
 }
@@ -796,6 +855,7 @@ static void __exit l2tp_ip6_exit(void)
 	inet6_unregister_protosw(&l2tp_ip6_protosw);
 	inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
 	proto_unregister(&l2tp_ip6_prot);
+	unregister_pernet_device(&l2tp_ip6_net_ops);
 }
 
 module_init(l2tp_ip6_init);
-- 
cgit v1.3-3-g829e


From b0a8deda060d51ebe4614ed6e1829d933139ba1a Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:47 +0100
Subject: l2tp: handle hash key collisions in l2tp_v3_session_get

To handle colliding l2tpv3 session IDs, l2tp_v3_session_get searches a
hashed list keyed by ID and sk. Although unlikely, if hash keys
collide, it is possible that hash_for_each_possible loops over a
session which doesn't have the ID that we are searching for. So check
for session ID match when looping over possible hash key matches.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 70c231fcaa2e..3b34e549fb79 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -291,7 +291,8 @@ struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk,
 			 */
 			struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel);
 
-			if (tunnel && tunnel->sock == sk &&
+			if (session->session_id == session_id &&
+			    tunnel && tunnel->sock == sk &&
 			    refcount_inc_not_zero(&session->ref_count)) {
 				rcu_read_unlock_bh();
 				return session;
-- 
cgit v1.3-3-g829e


From aa92c1cec92b146fe499fb693688d6d3d6bafad9 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:48 +0100
Subject: l2tp: add tunnel/session get_next helpers

l2tp management APIs and procfs/debugfs iterate over l2tp tunnel and
session lists. Since these lists are now implemented using IDR, we can
use IDR get_next APIs to iterate them. Add tunnel/session get_next
functions to do so.

The session get_next functions get the next session in a given tunnel
and need to account for l2tpv2 and l2tpv3 differences:

 * l2tpv2 sessions are keyed by tunnel ID / session ID. Iteration for
   a given tunnel ID, TID, can therefore start with a key given by
   TID/0 and finish when the next entry's tunnel ID is not TID. This
   is possible only because the tunnel ID part of the key is the upper
   16 bits and the session ID part the lower 16 bits; when idr_next
   increments the key value, it therefore finds the next sessions of
   the current tunnel before those of the next tunnel. Entries with
   session ID 0 are always skipped because they are used internally by
   pppol2tp.

 * l2tpv3 sessions are keyed by session ID. Iteration starts at the
   first IDR entry and skips entries where the tunnel does not
   match. Iteration must also consider session ID collisions and walk
   the list of colliding sessions (if any) for one which matches the
   supplied tunnel.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 126 +++++++++++++++++++++++++++++++++++++++++++++++++++
 net/l2tp/l2tp_core.h |   3 ++
 2 files changed, 129 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 3b34e549fb79..5e36f45e906b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -262,6 +262,28 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
 
+struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key)
+{
+	struct l2tp_net *pn = l2tp_pernet(net);
+	struct l2tp_tunnel *tunnel = NULL;
+
+	rcu_read_lock_bh();
+again:
+	tunnel = idr_get_next_ul(&pn->l2tp_tunnel_idr, key);
+	if (tunnel) {
+		if (refcount_inc_not_zero(&tunnel->ref_count)) {
+			rcu_read_unlock_bh();
+			return tunnel;
+		}
+		(*key)++;
+		goto again;
+	}
+	rcu_read_unlock_bh();
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_get_next);
+
 struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id)
 {
 	const struct l2tp_net *pn = l2tp_pernet(net);
@@ -352,6 +374,110 @@ struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth)
 }
 EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
 
+static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net,
+						     u16 tid,
+						     unsigned long *key)
+{
+	struct l2tp_net *pn = l2tp_pernet(net);
+	struct l2tp_session *session = NULL;
+
+	/* Start searching within the range of the tid */
+	if (*key == 0)
+		*key = l2tp_v2_session_key(tid, 0);
+
+	rcu_read_lock_bh();
+again:
+	session = idr_get_next_ul(&pn->l2tp_v2_session_idr, key);
+	if (session) {
+		struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel);
+
+		/* ignore sessions with id 0 as they are internal for pppol2tp */
+		if (session->session_id == 0) {
+			(*key)++;
+			goto again;
+		}
+
+		if (tunnel && tunnel->tunnel_id == tid &&
+		    refcount_inc_not_zero(&session->ref_count)) {
+			rcu_read_unlock_bh();
+			return session;
+		}
+
+		(*key)++;
+		if (tunnel->tunnel_id == tid)
+			goto again;
+	}
+	rcu_read_unlock_bh();
+
+	return NULL;
+}
+
+static struct l2tp_session *l2tp_v3_session_get_next(const struct net *net,
+						     u32 tid, struct sock *sk,
+						     unsigned long *key)
+{
+	struct l2tp_net *pn = l2tp_pernet(net);
+	struct l2tp_session *session = NULL;
+
+	rcu_read_lock_bh();
+again:
+	session = idr_get_next_ul(&pn->l2tp_v3_session_idr, key);
+	if (session && !hash_hashed(&session->hlist)) {
+		struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel);
+
+		if (tunnel && tunnel->tunnel_id == tid &&
+		    refcount_inc_not_zero(&session->ref_count)) {
+			rcu_read_unlock_bh();
+			return session;
+		}
+
+		(*key)++;
+		goto again;
+	}
+
+	/* If we get here and session is non-NULL, the IDR entry may be one
+	 * where the session_id collides with one in another tunnel. Check
+	 * session_htable for a match. There can only be one session of a given
+	 * ID per tunnel so we can return as soon as a match is found.
+	 */
+	if (session && hash_hashed(&session->hlist)) {
+		unsigned long hkey = l2tp_v3_session_hashkey(sk, session->session_id);
+		u32 sid = session->session_id;
+
+		hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session,
+					   hlist, hkey) {
+			struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel);
+
+			if (session->session_id == sid &&
+			    tunnel && tunnel->tunnel_id == tid &&
+			    refcount_inc_not_zero(&session->ref_count)) {
+				rcu_read_unlock_bh();
+				return session;
+			}
+		}
+
+		/* If no match found, the colliding session ID isn't in our
+		 * tunnel so try the next session ID.
+		 */
+		(*key)++;
+		goto again;
+	}
+
+	rcu_read_unlock_bh();
+
+	return NULL;
+}
+
+struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver,
+					   u32 tunnel_id, unsigned long *key)
+{
+	if (pver == L2TP_HDR_VER_2)
+		return l2tp_v2_session_get_next(net, tunnel_id, key);
+	else
+		return l2tp_v3_session_get_next(net, tunnel_id, sk, key);
+}
+EXPORT_SYMBOL_GPL(l2tp_session_get_next);
+
 /* Lookup a session by interface name.
  * This is very inefficient but is only used by management interfaces.
  */
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index c907687705b9..cc464982a7d9 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -220,12 +220,15 @@ void l2tp_session_dec_refcount(struct l2tp_session *session);
  */
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key);
 
 struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id);
 struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id);
 struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver,
 				      u32 tunnel_id, u32 session_id);
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
+struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver,
+					   u32 tunnel_id, unsigned long *key);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
 
-- 
cgit v1.3-3-g829e


From 1f4c3dce9112d23145b4f8bbfd3793a1c4c517ab Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:49 +0100
Subject: l2tp: use get_next APIs for management requests and procfs/debugfs

l2tp netlink and procfs/debugfs iterate over tunnel and session lists
to obtain data. They currently use very inefficient get_nth functions
to do so. Replace these with get_next.

For netlink, use nl cb->ctx[] for passing state instead of the
obsolete cb->args[].

l2tp_tunnel_get_nth and l2tp_session_get_nth are no longer used so
they can be removed.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 40 ----------------------------------------
 net/l2tp/l2tp_core.h    |  2 --
 net/l2tp/l2tp_debugfs.c | 16 +++++++++-------
 net/l2tp/l2tp_netlink.c | 34 +++++++++++++++++++++-------------
 net/l2tp/l2tp_ppp.c     | 16 +++++++++-------
 5 files changed, 39 insertions(+), 69 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 5e36f45e906b..2e60957ee821 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -241,27 +241,6 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_get);
 
-struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
-{
-	struct l2tp_net *pn = l2tp_pernet(net);
-	unsigned long tunnel_id, tmp;
-	struct l2tp_tunnel *tunnel;
-	int count = 0;
-
-	rcu_read_lock_bh();
-	idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) {
-		if (tunnel && ++count > nth &&
-		    refcount_inc_not_zero(&tunnel->ref_count)) {
-			rcu_read_unlock_bh();
-			return tunnel;
-		}
-	}
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
-
 struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
@@ -355,25 +334,6 @@ struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, in
 }
 EXPORT_SYMBOL_GPL(l2tp_session_get);
 
-struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth)
-{
-	struct l2tp_session *session;
-	int count = 0;
-
-	rcu_read_lock_bh();
-	list_for_each_entry_rcu(session, &tunnel->session_list, list) {
-		if (++count > nth) {
-			l2tp_session_inc_refcount(session);
-			rcu_read_unlock_bh();
-			return session;
-		}
-	}
-	rcu_read_unlock_bh();
-
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
-
 static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net,
 						     u16 tid,
 						     unsigned long *key)
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index cc464982a7d9..0fabacffc3f3 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -219,14 +219,12 @@ void l2tp_session_dec_refcount(struct l2tp_session *session);
  * the caller must ensure that the reference is dropped appropriately.
  */
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
-struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
 struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key);
 
 struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id);
 struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id);
 struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver,
 				      u32 tunnel_id, u32 session_id);
-struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver,
 					   u32 tunnel_id, unsigned long *key);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 8755ae521154..b2134b57ed18 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -34,8 +34,8 @@ static struct dentry *rootdir;
 struct l2tp_dfs_seq_data {
 	struct net	*net;
 	netns_tracker	ns_tracker;
-	int tunnel_idx;			/* current tunnel */
-	int session_idx;		/* index of session within current tunnel */
+	unsigned long tkey;		/* lookup key of current tunnel */
+	unsigned long skey;		/* lookup key of current session */
 	struct l2tp_tunnel *tunnel;
 	struct l2tp_session *session;	/* NULL means get next tunnel */
 };
@@ -46,8 +46,8 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 	if (pd->tunnel)
 		l2tp_tunnel_dec_refcount(pd->tunnel);
 
-	pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx);
-	pd->tunnel_idx++;
+	pd->tunnel = l2tp_tunnel_get_next(pd->net, &pd->tkey);
+	pd->tkey++;
 }
 
 static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
@@ -56,11 +56,13 @@ static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 	if (pd->session)
 		l2tp_session_dec_refcount(pd->session);
 
-	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx);
-	pd->session_idx++;
+	pd->session = l2tp_session_get_next(pd->net, pd->tunnel->sock,
+					    pd->tunnel->version,
+					    pd->tunnel->tunnel_id, &pd->skey);
+	pd->skey++;
 
 	if (!pd->session) {
-		pd->session_idx = 0;
+		pd->skey = 0;
 		l2tp_dfs_next_tunnel(pd);
 	}
 }
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index fc43ecbd128c..0598b97a0bca 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -491,14 +491,20 @@ err:
 	return ret;
 }
 
+struct l2tp_nl_cb_data {
+	unsigned long tkey;
+	unsigned long skey;
+};
+
 static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	int ti = cb->args[0];
+	struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0];
+	unsigned long key = cbd->tkey;
 	struct l2tp_tunnel *tunnel;
 	struct net *net = sock_net(skb->sk);
 
 	for (;;) {
-		tunnel = l2tp_tunnel_get_nth(net, ti);
+		tunnel = l2tp_tunnel_get_next(net, &key);
 		if (!tunnel)
 			goto out;
 
@@ -510,11 +516,11 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 		}
 		l2tp_tunnel_dec_refcount(tunnel);
 
-		ti++;
+		key++;
 	}
 
 out:
-	cb->args[0] = ti;
+	cbd->tkey = key;
 
 	return skb->len;
 }
@@ -832,25 +838,27 @@ err:
 
 static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0];
 	struct net *net = sock_net(skb->sk);
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel = NULL;
-	int ti = cb->args[0];
-	int si = cb->args[1];
+	unsigned long tkey = cbd->tkey;
+	unsigned long skey = cbd->skey;
 
 	for (;;) {
 		if (!tunnel) {
-			tunnel = l2tp_tunnel_get_nth(net, ti);
+			tunnel = l2tp_tunnel_get_next(net, &tkey);
 			if (!tunnel)
 				goto out;
 		}
 
-		session = l2tp_session_get_nth(tunnel, si);
+		session = l2tp_session_get_next(net, tunnel->sock, tunnel->version,
+						tunnel->tunnel_id, &skey);
 		if (!session) {
-			ti++;
+			tkey++;
 			l2tp_tunnel_dec_refcount(tunnel);
 			tunnel = NULL;
-			si = 0;
+			skey = 0;
 			continue;
 		}
 
@@ -863,12 +871,12 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 		}
 		l2tp_session_dec_refcount(session);
 
-		si++;
+		skey++;
 	}
 
 out:
-	cb->args[0] = ti;
-	cb->args[1] = si;
+	cbd->tkey = tkey;
+	cbd->skey = skey;
 
 	return skb->len;
 }
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index c25dd8e36074..8459e5159430 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1397,8 +1397,8 @@ end:
 
 struct pppol2tp_seq_data {
 	struct seq_net_private p;
-	int tunnel_idx;			/* current tunnel */
-	int session_idx;		/* index of session within current tunnel */
+	unsigned long tkey;		/* lookup key of current tunnel */
+	unsigned long skey;		/* lookup key of current session */
 	struct l2tp_tunnel *tunnel;
 	struct l2tp_session *session;	/* NULL means get next tunnel */
 };
@@ -1410,8 +1410,8 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 		l2tp_tunnel_dec_refcount(pd->tunnel);
 
 	for (;;) {
-		pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx);
-		pd->tunnel_idx++;
+		pd->tunnel = l2tp_tunnel_get_next(net, &pd->tkey);
+		pd->tkey++;
 
 		/* Only accept L2TPv2 tunnels */
 		if (!pd->tunnel || pd->tunnel->version == 2)
@@ -1427,11 +1427,13 @@ static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 	if (pd->session)
 		l2tp_session_dec_refcount(pd->session);
 
-	pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx);
-	pd->session_idx++;
+	pd->session = l2tp_session_get_next(net, pd->tunnel->sock,
+					    pd->tunnel->version,
+					    pd->tunnel->tunnel_id, &pd->skey);
+	pd->skey++;
 
 	if (!pd->session) {
-		pd->session_idx = 0;
+		pd->skey = 0;
 		pppol2tp_next_tunnel(net, pd);
 	}
 }
-- 
cgit v1.3-3-g829e


From abe7a1a7d0b69e63b1bca5f9531023a52336784f Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:50 +0100
Subject: l2tp: improve tunnel/session refcount helpers

l2tp_tunnel_inc_refcount and l2tp_session_inc_refcount wrap
refcount_inc. They add no value so just use the refcount APIs directly
and drop l2tp's helpers. l2tp already uses refcount_inc_not_zero
anyway.

Rename l2tp_tunnel_dec_refcount and l2tp_session_dec_refcount to
l2tp_tunnel_put and l2tp_session_put to better match their use pairing
various _get getters.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 52 +++++++++++++++++++------------------------------
 net/l2tp/l2tp_core.h    |  6 ++----
 net/l2tp/l2tp_debugfs.c |  8 ++++----
 net/l2tp/l2tp_eth.c     | 10 +++++-----
 net/l2tp/l2tp_ip.c      |  6 +++---
 net/l2tp/l2tp_ip6.c     |  6 +++---
 net/l2tp/l2tp_netlink.c | 38 ++++++++++++++++++------------------
 net/l2tp/l2tp_ppp.c     | 46 +++++++++++++++++++++----------------------
 8 files changed, 79 insertions(+), 93 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 2e60957ee821..b0bf0ae08e85 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -170,7 +170,7 @@ static void l2tp_session_free(struct l2tp_session *session)
 {
 	trace_free_session(session);
 	if (session->tunnel)
-		l2tp_tunnel_dec_refcount(session->tunnel);
+		l2tp_tunnel_put(session->tunnel);
 	kfree_rcu(session, rcu);
 }
 
@@ -197,31 +197,19 @@ struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel);
 
-void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel)
-{
-	refcount_inc(&tunnel->ref_count);
-}
-EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount);
-
-void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel)
+void l2tp_tunnel_put(struct l2tp_tunnel *tunnel)
 {
 	if (refcount_dec_and_test(&tunnel->ref_count))
 		l2tp_tunnel_free(tunnel);
 }
-EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount);
-
-void l2tp_session_inc_refcount(struct l2tp_session *session)
-{
-	refcount_inc(&session->ref_count);
-}
-EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount);
+EXPORT_SYMBOL_GPL(l2tp_tunnel_put);
 
-void l2tp_session_dec_refcount(struct l2tp_session *session)
+void l2tp_session_put(struct l2tp_session *session)
 {
 	if (refcount_dec_and_test(&session->ref_count))
 		l2tp_session_free(session);
 }
-EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount);
+EXPORT_SYMBOL_GPL(l2tp_session_put);
 
 /* Lookup a tunnel. A new reference is held on the returned tunnel. */
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
@@ -454,7 +442,7 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 		if (tunnel) {
 			list_for_each_entry_rcu(session, &tunnel->session_list, list) {
 				if (!strcmp(session->ifname, ifname)) {
-					l2tp_session_inc_refcount(session);
+					refcount_inc(&session->ref_count);
 					rcu_read_unlock_bh();
 
 					return session;
@@ -471,7 +459,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
 static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist,
 				       struct l2tp_session *session)
 {
-	l2tp_session_inc_refcount(session);
+	refcount_inc(&session->ref_count);
 	WARN_ON_ONCE(session->coll_list);
 	session->coll_list = clist;
 	spin_lock(&clist->lock);
@@ -557,7 +545,7 @@ static void l2tp_session_collision_del(struct l2tp_net *pn,
 		spin_unlock(&clist->lock);
 		if (refcount_dec_and_test(&clist->ref_count))
 			kfree(clist);
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 	}
 }
 
@@ -606,7 +594,7 @@ int l2tp_session_register(struct l2tp_session *session,
 		goto out;
 	}
 
-	l2tp_tunnel_inc_refcount(tunnel);
+	refcount_inc(&tunnel->ref_count);
 	WRITE_ONCE(session->tunnel, tunnel);
 	list_add_rcu(&session->list, &tunnel->session_list);
 
@@ -1089,7 +1077,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	if (!session || !session->recv_skb) {
 		if (session)
-			l2tp_session_dec_refcount(session);
+			l2tp_session_put(session);
 
 		/* Not found? Pass to userspace to deal with */
 		goto pass;
@@ -1103,12 +1091,12 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	if (version == L2TP_HDR_VER_3 &&
 	    l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) {
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 		goto invalid;
 	}
 
 	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return 0;
 
@@ -1408,7 +1396,7 @@ static void l2tp_udp_encap_destroy(struct sock *sk)
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
 		l2tp_tunnel_delete(tunnel);
-		l2tp_tunnel_dec_refcount(tunnel);
+		l2tp_tunnel_put(tunnel);
 	}
 }
 
@@ -1443,10 +1431,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 
 	l2tp_tunnel_remove(tunnel->l2tp_net, tunnel);
 	/* drop initial ref */
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 
 	/* drop workqueue ref */
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
@@ -1634,7 +1622,7 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
-		l2tp_tunnel_dec_refcount(tunnel);
+		l2tp_tunnel_put(tunnel);
 		return -EBUSY;
 	}
 
@@ -1726,7 +1714,7 @@ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
 	if (!test_and_set_bit(0, &tunnel->dead)) {
 		trace_delete_tunnel(tunnel);
-		l2tp_tunnel_inc_refcount(tunnel);
+		refcount_inc(&tunnel->ref_count);
 		queue_work(l2tp_wq, &tunnel->del_work);
 	}
 }
@@ -1736,7 +1724,7 @@ void l2tp_session_delete(struct l2tp_session *session)
 {
 	if (!test_and_set_bit(0, &session->dead)) {
 		trace_delete_session(session);
-		l2tp_session_inc_refcount(session);
+		refcount_inc(&session->ref_count);
 		queue_work(l2tp_wq, &session->del_work);
 	}
 }
@@ -1754,10 +1742,10 @@ static void l2tp_session_del_work(struct work_struct *work)
 		(*session->session_close)(session);
 
 	/* drop initial ref */
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	/* drop workqueue ref */
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 }
 
 /* We come here whenever a session's send_seq, cookie_len or
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 0fabacffc3f3..ffd8ced3a51f 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -209,10 +209,8 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 }
 
 /* Tunnel and session refcounts */
-void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel);
-void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel);
-void l2tp_session_inc_refcount(struct l2tp_session *session);
-void l2tp_session_dec_refcount(struct l2tp_session *session);
+void l2tp_tunnel_put(struct l2tp_tunnel *tunnel);
+void l2tp_session_put(struct l2tp_session *session);
 
 /* Tunnel and session lookup.
  * These functions take a reference on the instances they return, so
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index b2134b57ed18..2d0c8275a3a8 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -44,7 +44,7 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd)
 {
 	/* Drop reference taken during previous invocation */
 	if (pd->tunnel)
-		l2tp_tunnel_dec_refcount(pd->tunnel);
+		l2tp_tunnel_put(pd->tunnel);
 
 	pd->tunnel = l2tp_tunnel_get_next(pd->net, &pd->tkey);
 	pd->tkey++;
@@ -54,7 +54,7 @@ static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
 {
 	/* Drop reference taken during previous invocation */
 	if (pd->session)
-		l2tp_session_dec_refcount(pd->session);
+		l2tp_session_put(pd->session);
 
 	pd->session = l2tp_session_get_next(pd->net, pd->tunnel->sock,
 					    pd->tunnel->version,
@@ -111,11 +111,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v)
 	 * or l2tp_dfs_next_tunnel().
 	 */
 	if (pd->session) {
-		l2tp_session_dec_refcount(pd->session);
+		l2tp_session_put(pd->session);
 		pd->session = NULL;
 	}
 	if (pd->tunnel) {
-		l2tp_tunnel_dec_refcount(pd->tunnel);
+		l2tp_tunnel_put(pd->tunnel);
 		pd->tunnel = NULL;
 	}
 }
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index cc8a3ce716e9..e94549668e10 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -283,7 +283,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 
 	spriv = l2tp_session_priv(session);
 
-	l2tp_session_inc_refcount(session);
+	refcount_inc(&session->ref_count);
 
 	rtnl_lock();
 
@@ -301,7 +301,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 	if (rc < 0) {
 		rtnl_unlock();
 		l2tp_session_delete(session);
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 		free_netdev(dev);
 
 		return rc;
@@ -312,17 +312,17 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 
 	rtnl_unlock();
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	__module_get(THIS_MODULE);
 
 	return 0;
 
 err_sess_dev:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 	free_netdev(dev);
 err_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 err:
 	return rc;
 }
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index f563c8afd8f3..39f3f1334c4a 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -167,7 +167,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		goto discard_sess;
 
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return 0;
 
@@ -200,7 +200,7 @@ pass_up:
 	return sk_receive_skb(sk, skb, 1);
 
 discard_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 	goto discard;
 
 discard_put:
@@ -265,7 +265,7 @@ static void l2tp_ip_destroy_sock(struct sock *sk)
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
 		l2tp_tunnel_delete(tunnel);
-		l2tp_tunnel_dec_refcount(tunnel);
+		l2tp_tunnel_put(tunnel);
 	}
 }
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index dcec1de2898e..f4c1da070826 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -177,7 +177,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		goto discard_sess;
 
 	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return 0;
 
@@ -210,7 +210,7 @@ pass_up:
 	return sk_receive_skb(sk, skb, 1);
 
 discard_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 	goto discard;
 
 discard_put:
@@ -276,7 +276,7 @@ static void l2tp_ip6_destroy_sock(struct sock *sk)
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
 		l2tp_tunnel_delete(tunnel);
-		l2tp_tunnel_dec_refcount(tunnel);
+		l2tp_tunnel_put(tunnel);
 	}
 }
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 0598b97a0bca..284f1dec1b56 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -63,7 +63,7 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info)
 		if (tunnel) {
 			session = l2tp_session_get(net, tunnel->sock, tunnel->version,
 						   tunnel_id, session_id);
-			l2tp_tunnel_dec_refcount(tunnel);
+			l2tp_tunnel_put(tunnel);
 		}
 	}
 
@@ -242,7 +242,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 	if (ret < 0)
 		goto out;
 
-	l2tp_tunnel_inc_refcount(tunnel);
+	refcount_inc(&tunnel->ref_count);
 	ret = l2tp_tunnel_register(tunnel, net, &cfg);
 	if (ret < 0) {
 		kfree(tunnel);
@@ -250,7 +250,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 	}
 	ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel,
 				 L2TP_CMD_TUNNEL_CREATE);
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 
 out:
 	return ret;
@@ -280,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info
 
 	l2tp_tunnel_delete(tunnel);
 
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 
 out:
 	return ret;
@@ -308,7 +308,7 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info
 	ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
 				 tunnel, L2TP_CMD_TUNNEL_MODIFY);
 
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 
 out:
 	return ret;
@@ -479,12 +479,12 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto err_nlmsg_tunnel;
 
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 
 	return genlmsg_unicast(net, msg, info->snd_portid);
 
 err_nlmsg_tunnel:
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 err_nlmsg:
 	nlmsg_free(msg);
 err:
@@ -511,10 +511,10 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback
 		if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid,
 					cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					tunnel, L2TP_CMD_TUNNEL_GET) < 0) {
-			l2tp_tunnel_dec_refcount(tunnel);
+			l2tp_tunnel_put(tunnel);
 			goto out;
 		}
-		l2tp_tunnel_dec_refcount(tunnel);
+		l2tp_tunnel_put(tunnel);
 
 		key++;
 	}
@@ -647,12 +647,12 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 		if (session) {
 			ret = l2tp_session_notify(&l2tp_nl_family, info, session,
 						  L2TP_CMD_SESSION_CREATE);
-			l2tp_session_dec_refcount(session);
+			l2tp_session_put(session);
 		}
 	}
 
 out_tunnel:
-	l2tp_tunnel_dec_refcount(tunnel);
+	l2tp_tunnel_put(tunnel);
 out:
 	return ret;
 }
@@ -677,7 +677,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf
 		if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
 			l2tp_nl_cmd_ops[pw_type]->session_delete(session);
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 out:
 	return ret;
@@ -713,7 +713,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	ret = l2tp_session_notify(&l2tp_nl_family, info,
 				  session, L2TP_CMD_SESSION_MODIFY);
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 out:
 	return ret;
@@ -824,14 +824,14 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
 
 	ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return ret;
 
 err_ref_msg:
 	nlmsg_free(msg);
 err_ref:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 err:
 	return ret;
 }
@@ -856,7 +856,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 						tunnel->tunnel_id, &skey);
 		if (!session) {
 			tkey++;
-			l2tp_tunnel_dec_refcount(tunnel);
+			l2tp_tunnel_put(tunnel);
 			tunnel = NULL;
 			skey = 0;
 			continue;
@@ -865,11 +865,11 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback
 		if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					 session, L2TP_CMD_SESSION_GET) < 0) {
-			l2tp_session_dec_refcount(session);
-			l2tp_tunnel_dec_refcount(tunnel);
+			l2tp_session_put(session);
+			l2tp_tunnel_put(tunnel);
 			break;
 		}
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 
 		skey++;
 	}
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 8459e5159430..53baf2dd5d5d 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -313,12 +313,12 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m,
 	l2tp_xmit_skb(session, skb);
 	local_bh_enable();
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return total_len;
 
 error_put_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 error:
 	return error;
 }
@@ -372,12 +372,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	l2tp_xmit_skb(session, skb);
 	local_bh_enable();
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return 1;
 
 abort_put_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 abort:
 	/* Free the original skb */
 	kfree_skb(skb);
@@ -413,7 +413,7 @@ static void pppol2tp_session_close(struct l2tp_session *session)
 		sock_put(ps->__sk);
 
 		/* drop ref taken when we referenced socket via sk_user_data */
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 	}
 }
 
@@ -444,7 +444,7 @@ static int pppol2tp_release(struct socket *sock)
 	if (session) {
 		l2tp_session_delete(session);
 		/* drop ref taken by pppol2tp_sock_to_session */
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 	}
 
 	release_sock(sk);
@@ -668,7 +668,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net,
 			if (error < 0)
 				return ERR_PTR(error);
 
-			l2tp_tunnel_inc_refcount(tunnel);
+			refcount_inc(&tunnel->ref_count);
 			error = l2tp_tunnel_register(tunnel, net, &tcfg);
 			if (error < 0) {
 				kfree(tunnel);
@@ -684,7 +684,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net,
 
 		/* Error if socket is not prepped */
 		if (!tunnel->sock) {
-			l2tp_tunnel_dec_refcount(tunnel);
+			l2tp_tunnel_put(tunnel);
 			return ERR_PTR(-ENOENT);
 		}
 	}
@@ -774,13 +774,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 		pppol2tp_session_init(session);
 		ps = l2tp_session_priv(session);
-		l2tp_session_inc_refcount(session);
+		refcount_inc(&session->ref_count);
 
 		mutex_lock(&ps->sk_lock);
 		error = l2tp_session_register(session, tunnel);
 		if (error < 0) {
 			mutex_unlock(&ps->sk_lock);
-			l2tp_session_dec_refcount(session);
+			l2tp_session_put(session);
 			goto end;
 		}
 
@@ -836,8 +836,8 @@ end:
 			l2tp_tunnel_delete(tunnel);
 	}
 	if (drop_refcnt)
-		l2tp_session_dec_refcount(session);
-	l2tp_tunnel_dec_refcount(tunnel);
+		l2tp_session_put(session);
+	l2tp_tunnel_put(tunnel);
 	release_sock(sk);
 
 	return error;
@@ -877,7 +877,7 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
 	return 0;
 
 err_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 err:
 	return error;
 }
@@ -988,7 +988,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
 
 	error = len;
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 end:
 	return error;
 }
@@ -1038,12 +1038,12 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats,
 		return -EBADR;
 
 	if (session->pwtype != L2TP_PWTYPE_PPP) {
-		l2tp_session_dec_refcount(session);
+		l2tp_session_put(session);
 		return -EBADR;
 	}
 
 	pppol2tp_copy_stats(stats, &session->stats);
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 
 	return 0;
 }
@@ -1261,7 +1261,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
 		err = pppol2tp_session_setsockopt(sk, session, optname, val);
 	}
 
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 end:
 	return err;
 }
@@ -1382,7 +1382,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname,
 	err = 0;
 
 end_put_sess:
-	l2tp_session_dec_refcount(session);
+	l2tp_session_put(session);
 end:
 	return err;
 }
@@ -1407,7 +1407,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 {
 	/* Drop reference taken during previous invocation */
 	if (pd->tunnel)
-		l2tp_tunnel_dec_refcount(pd->tunnel);
+		l2tp_tunnel_put(pd->tunnel);
 
 	for (;;) {
 		pd->tunnel = l2tp_tunnel_get_next(net, &pd->tkey);
@@ -1417,7 +1417,7 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
 		if (!pd->tunnel || pd->tunnel->version == 2)
 			return;
 
-		l2tp_tunnel_dec_refcount(pd->tunnel);
+		l2tp_tunnel_put(pd->tunnel);
 	}
 }
 
@@ -1425,7 +1425,7 @@ static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
 {
 	/* Drop reference taken during previous invocation */
 	if (pd->session)
-		l2tp_session_dec_refcount(pd->session);
+		l2tp_session_put(pd->session);
 
 	pd->session = l2tp_session_get_next(net, pd->tunnel->sock,
 					    pd->tunnel->version,
@@ -1485,11 +1485,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v)
 	 * or pppol2tp_next_tunnel().
 	 */
 	if (pd->session) {
-		l2tp_session_dec_refcount(pd->session);
+		l2tp_session_put(pd->session);
 		pd->session = NULL;
 	}
 	if (pd->tunnel) {
-		l2tp_tunnel_dec_refcount(pd->tunnel);
+		l2tp_tunnel_put(pd->tunnel);
 		pd->tunnel = NULL;
 	}
 }
-- 
cgit v1.3-3-g829e


From dcc59d3e328e3afe54df4f395796042735b1c420 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:51 +0100
Subject: l2tp: l2tp_eth: use per-cpu counters from dev->tstats

l2tp_eth uses old-style dev->stats for fastpath packet/byte
counters. Convert it to use dev->tstats per-cpu counters.

Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_eth.c | 32 ++++++++++----------------------
 1 file changed, 10 insertions(+), 22 deletions(-)

diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index e94549668e10..15a862f33f76 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -72,31 +72,19 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev
 	unsigned int len = skb->len;
 	int ret = l2tp_xmit_skb(session, skb);
 
-	if (likely(ret == NET_XMIT_SUCCESS)) {
-		DEV_STATS_ADD(dev, tx_bytes, len);
-		DEV_STATS_INC(dev, tx_packets);
-	} else {
+	if (likely(ret == NET_XMIT_SUCCESS))
+		dev_sw_netstats_tx_add(dev, 1, len);
+	else
 		DEV_STATS_INC(dev, tx_dropped);
-	}
-	return NETDEV_TX_OK;
-}
 
-static void l2tp_eth_get_stats64(struct net_device *dev,
-				 struct rtnl_link_stats64 *stats)
-{
-	stats->tx_bytes   = DEV_STATS_READ(dev, tx_bytes);
-	stats->tx_packets = DEV_STATS_READ(dev, tx_packets);
-	stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped);
-	stats->rx_bytes   = DEV_STATS_READ(dev, rx_bytes);
-	stats->rx_packets = DEV_STATS_READ(dev, rx_packets);
-	stats->rx_errors  = DEV_STATS_READ(dev, rx_errors);
+	return NETDEV_TX_OK;
 }
 
 static const struct net_device_ops l2tp_eth_netdev_ops = {
 	.ndo_init		= l2tp_eth_dev_init,
 	.ndo_uninit		= l2tp_eth_dev_uninit,
 	.ndo_start_xmit		= l2tp_eth_dev_xmit,
-	.ndo_get_stats64	= l2tp_eth_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_set_mac_address	= eth_mac_addr,
 };
 
@@ -112,6 +100,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
 	dev->features		|= NETIF_F_LLTX;
 	dev->netdev_ops		= &l2tp_eth_netdev_ops;
 	dev->needs_free_netdev	= true;
+	dev->pcpu_stat_type	= NETDEV_PCPU_STAT_TSTATS;
 }
 
 static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
@@ -138,12 +127,11 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
 	if (!dev)
 		goto error_rcu;
 
-	if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
-		DEV_STATS_INC(dev, rx_packets);
-		DEV_STATS_ADD(dev, rx_bytes, data_len);
-	} else {
+	if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS)
+		dev_sw_netstats_rx_add(dev, data_len);
+	else
 		DEV_STATS_INC(dev, rx_errors);
-	}
+
 	rcu_read_unlock();
 
 	return;
-- 
cgit v1.3-3-g829e


From c1b2e36b8776a20a1fbdeb9d3be0637c00d671b0 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Wed, 7 Aug 2024 07:54:52 +0100
Subject: l2tp: flush workqueue before draining it

syzbot exposes a race where a net used by l2tp is removed while an
existing pppol2tp socket is closed. In l2tp_pre_exit_net, l2tp queues
TUNNEL_DELETE work items to close each tunnel in the net. When these
are run, new SESSION_DELETE work items are queued to delete each
session in the tunnel. This all happens in drain_workqueue. However,
drain_workqueue allows only new work items if they are queued by other
work items which are already in the queue. If pppol2tp_release runs
after drain_workqueue has started, it may queue a SESSION_DELETE work
item, which results in the warning below in drain_workqueue.

Address this by flushing the workqueue before drain_workqueue such
that all queued TUNNEL_DELETE work items run before drain_workqueue is
started. This will queue SESSION_DELETE work items for each session in
the tunnel, hence pppol2tp_release or other API requests won't queue
SESSION_DELETE requests once drain_workqueue is started.

  WARNING: CPU: 1 PID: 5467 at kernel/workqueue.c:2259 __queue_work+0xcd3/0xf50 kernel/workqueue.c:2258
  Modules linked in:
  CPU: 1 UID: 0 PID: 5467 Comm: syz.3.43 Not tainted 6.11.0-rc1-syzkaller-00247-g3608d6aca5e7 #0
  Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024
  RIP: 0010:__queue_work+0xcd3/0xf50 kernel/workqueue.c:2258
  Code: ff e8 11 84 36 00 90 0f 0b 90 e9 1e fd ff ff e8 03 84 36 00 eb 13 e8 fc 83 36 00 eb 0c e8 f5 83 36 00 eb 05 e8 ee 83 36 00 90 <0f> 0b 90 48 83 c4 60 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc
  RSP: 0018:ffffc90004607b48 EFLAGS: 00010093
  RAX: ffffffff815ce274 RBX: ffff8880661fda00 RCX: ffff8880661fda00
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
  RBP: 0000000000000000 R08: ffffffff815cd6d4 R09: 0000000000000000
  R10: ffffc90004607c20 R11: fffff520008c0f85 R12: ffff88802ac33800
  R13: ffff88802ac339c0 R14: dffffc0000000000 R15: 0000000000000008
  FS:  00005555713eb500(0000) GS:ffff8880b9300000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000008 CR3: 000000001eda6000 CR4: 00000000003506f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   queue_work_on+0x1c2/0x380 kernel/workqueue.c:2392
   pppol2tp_release+0x163/0x230 net/l2tp/l2tp_ppp.c:445
   __sock_release net/socket.c:659 [inline]
   sock_close+0xbc/0x240 net/socket.c:1421
   __fput+0x24a/0x8a0 fs/file_table.c:422
   task_work_run+0x24f/0x310 kernel/task_work.c:228
   resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
   exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
   exit_to_user_mode_prepare include/linux/entry-common.h:328 [inline]
   __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
   syscall_exit_to_user_mode+0x168/0x370 kernel/entry/common.c:218
   do_syscall_64+0x100/0x230 arch/x86/entry/common.c:89
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f061e9779f9
  Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007ffff1c1fce8 EFLAGS: 00000246 ORIG_RAX: 00000000000001b4
  RAX: 0000000000000000 RBX: 000000000001017d RCX: 00007f061e9779f9
  RDX: 0000000000000000 RSI: 000000000000001e RDI: 0000000000000003
  RBP: 00007ffff1c1fdc0 R08: 0000000000000001 R09: 00007ffff1c1ffcf
  R10: 00007f061e800000 R11: 0000000000000246 R12: 0000000000000032
  R13: 00007ffff1c1fde0 R14: 00007ffff1c1fe00 R15: ffffffffffffffff
  </TASK>

Fixes: fc7ec7f554d7 ("l2tp: delete sessions using work queue")
Reported-by: syzbot+0e85b10481d2f5478053@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=0e85b10481d2f5478053
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index b0bf0ae08e85..af87c781d6a6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1855,8 +1855,16 @@ static __net_exit void l2tp_pre_exit_net(struct net *net)
 	}
 	rcu_read_unlock_bh();
 
-	if (l2tp_wq)
+	if (l2tp_wq) {
+		/* ensure that all TUNNEL_DELETE work items are run before
+		 * draining the work queue since TUNNEL_DELETE requests may
+		 * queue SESSION_DELETE work items for each session in the
+		 * tunnel. drain_workqueue may otherwise warn if SESSION_DELETE
+		 * requests are queued while the work queue is being drained.
+		 */
+		__flush_workqueue(l2tp_wq);
 		drain_workqueue(l2tp_wq);
+	}
 }
 
 static __net_exit void l2tp_exit_net(struct net *net)
-- 
cgit v1.3-3-g829e


From fbda8ee64b7404a6a48af8481ed788f9d7946284 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 7 Aug 2024 22:15:13 -0700
Subject: bnxt_en: Update firmware interface to 1.10.3.68

The main changes are:

1. HWRM_VNIC_UPDATE used to safely disable and enable an RX ring within
the VNIC.

2. New flag in HWRM_VNIC_QCAPS to indicate FW will do the proper flush
during HWRM_VNIC_UPDATE.

3. New flag in HWRM_FUNC_QCAPS to indicate that reservations for some
resources such as VNIC can be reduced.

4. New backing store memory types not used by the driver yet.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 389 +++++++++++++++++---------
 1 file changed, 249 insertions(+), 140 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index f219709f9563..f8ef6f1a1964 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -403,6 +403,9 @@ struct cmd_nums {
 	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
 	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
 	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
+	#define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD         0x1c2UL
+	#define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE      0x1c3UL
+	#define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY       0x1c4UL
 	#define HWRM_SELFTEST_QLIST                       0x200UL
 	#define HWRM_SELFTEST_EXEC                        0x201UL
 	#define HWRM_SELFTEST_IRQ                         0x202UL
@@ -430,6 +433,9 @@ struct cmd_nums {
 	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
 	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
 	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
+	#define HWRM_MFG_TESTS                            0x21bUL
+	#define HWRM_PORT_POE_CFG                         0x230UL
+	#define HWRM_PORT_POE_QCFG                        0x231UL
 	#define HWRM_UDCC_QCAPS                           0x258UL
 	#define HWRM_UDCC_CFG                             0x259UL
 	#define HWRM_UDCC_QCFG                            0x25aUL
@@ -439,6 +445,9 @@ struct cmd_nums {
 	#define HWRM_UDCC_COMP_CFG                        0x25eUL
 	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
 	#define HWRM_UDCC_COMP_QUERY                      0x260UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS            0x261UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_CFG              0x262UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG             0x263UL
 	#define HWRM_TF                                   0x2bcUL
 	#define HWRM_TF_VERSION_GET                       0x2bdUL
 	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
@@ -500,10 +509,8 @@ struct cmd_nums {
 	#define HWRM_TFC_IF_TBL_GET                       0x399UL
 	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
 	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS            0x39cUL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_CFG              0x39dUL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG             0x39eUL
 	#define HWRM_SV                                   0x400UL
+	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
 	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
 	#define HWRM_DBG_READ_DIRECT                      0xff10UL
 	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
@@ -533,6 +540,9 @@ struct cmd_nums {
 	#define HWRM_DBG_USEQ_RUN                         0xff29UL
 	#define HWRM_DBG_USEQ_DELIVERY_REQ                0xff2aUL
 	#define HWRM_DBG_USEQ_RESP_HDR                    0xff2bUL
+	#define HWRM_DBG_COREDUMP_CAPTURE                 0xff2cUL
+	#define HWRM_DBG_PTRACE                           0xff2dUL
+	#define HWRM_DBG_SIM_CABLE_STATE                  0xff2eUL
 	#define HWRM_NVM_GET_VPD_FIELD_INFO               0xffeaUL
 	#define HWRM_NVM_SET_VPD_FIELD_INFO               0xffebUL
 	#define HWRM_NVM_DEFRAG                           0xffecUL
@@ -582,6 +592,7 @@ struct ret_codes {
 	#define HWRM_ERR_CODE_RESOURCE_LOCKED              0x11UL
 	#define HWRM_ERR_CODE_PF_UNAVAILABLE               0x12UL
 	#define HWRM_ERR_CODE_ENTITY_NOT_PRESENT           0x13UL
+	#define HWRM_ERR_CODE_SECURE_SOC_ERROR             0x14UL
 	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
 	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
 	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
@@ -613,8 +624,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 3
-#define HWRM_VERSION_RSVD 44
-#define HWRM_VERSION_STR "1.10.3.44"
+#define HWRM_VERSION_RSVD 68
+#define HWRM_VERSION_STR "1.10.3.68"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -850,7 +861,10 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER                0x4cUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE                0x4dUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x4eUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE         0x4eUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE                  0x4fUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP                   0x50UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x51UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
@@ -1691,7 +1705,7 @@ struct hwrm_func_qcaps_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcaps_output (size:1088b/136B) */
+/* hwrm_func_qcaps_output (size:1152b/144B) */
 struct hwrm_func_qcaps_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1824,6 +1838,9 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED          0x4000000UL
 	#define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED       0x8000000UL
 	#define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED                   0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED             0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED            0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED               0x80000000UL
 	__le16	tunnel_disable_flag;
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
 	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
@@ -1845,7 +1862,9 @@ struct hwrm_func_qcaps_output {
 	__le32	roce_vf_max_qp;
 	__le32	roce_vf_max_srq;
 	__le32	roce_vf_max_gid;
-	u8	unused_3[3];
+	__le32	flags_ext3;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP     0x1UL
+	u8	unused_3[7];
 	u8	valid;
 };
 
@@ -2021,7 +2040,8 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
 	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
 	__le16	host_mtu;
-	u8	unused_3[2];
+	__le16	flags2;
+	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
 	u8	unused_4[2];
 	u8	port_kdnet_mode;
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
@@ -3671,33 +3691,38 @@ struct hwrm_func_backing_store_cfg_v2_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	type;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP              0x0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ             0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ              0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC            0x3UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT            0x4UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING     0x5UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING     0x6UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV            0xeUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM             0xfUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK           0x13UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK           0x14UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING     0x15UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW    0x16UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW    0x17UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW   0x18UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW    0x19UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE       0x1cUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION   0x1dUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE       0x1eUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE      0x1fUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE       0x20UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE      0x21UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE     0x22UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE   0x23UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID         0xffffUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST           FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
 	__le16	instance;
 	__le32	flags;
 	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE        0x1UL
@@ -3772,6 +3797,11 @@ struct hwrm_func_backing_store_qcfg_v2_input {
 	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
 	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
 	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
 	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
 	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
 	__le16	instance;
@@ -3785,29 +3815,34 @@ struct hwrm_func_backing_store_qcfg_v2_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP              0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ             0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ              0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC            0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT            0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING     0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING     0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV            0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM             0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK           0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK           0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING     0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE       0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION   0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE       0x1eUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE      0x1fUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE       0x20UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE      0x21UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE     0x22UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE   0x23UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID         0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST           FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
 	__le16	instance;
 	__le32	flags;
 	__le64	page_dir;
@@ -3883,6 +3918,13 @@ struct ts_split_entries {
 	__le32	rsvd2[2];
 };
 
+/* ck_split_entries (size:128b/16B) */
+struct ck_split_entries {
+	__le32	num_quic_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
 /* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
 struct hwrm_func_backing_store_qcaps_v2_input {
 	__le16	req_type;
@@ -3891,33 +3933,38 @@ struct hwrm_func_backing_store_qcaps_v2_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	type;
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP              0x0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ             0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ              0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC            0x3UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT            0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING     0x5UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING     0x6UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV            0xeUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM             0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK           0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK           0x14UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING     0x15UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW    0x16UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW    0x17UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW   0x18UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW    0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE       0x1cUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION   0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE       0x1eUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE      0x1fUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE       0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE      0x21UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE     0x22UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE   0x23UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID         0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST           FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
 	u8	rsvd[6];
 };
 
@@ -3928,39 +3975,45 @@ struct hwrm_func_backing_store_qcaps_v2_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	__le16	type;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP              0x0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ             0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ              0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC            0x3UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT            0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING     0x5UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING     0x6UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV            0xeUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM             0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK           0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK           0x14UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING     0x15UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW    0x16UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW    0x17UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW   0x18UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW    0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE       0x1cUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION   0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE       0x1eUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE      0x1fUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE       0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE      0x21UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE     0x22UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE   0x23UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID         0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST           FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
 	__le16	entry_size;
 	__le32	flags;
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT            0x1UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID                      0x2UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY           0x4UL
 	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE                    0x10UL
 	__le32	instance_bit_map;
 	u8	ctx_init_value;
 	u8	ctx_init_offset;
@@ -4410,6 +4463,7 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN       0x3UL
 	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED   0x4UL
 	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT  0x5UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED    0x6UL
 	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL
 	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST         PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE
 	__le32	preemphasis;
@@ -4941,7 +4995,9 @@ struct hwrm_port_qstats_output {
 	__le16	resp_len;
 	__le16	tx_stat_size;
 	__le16	rx_stat_size;
-	u8	unused_0[3];
+	u8	flags;
+	#define PORT_QSTATS_RESP_FLAGS_CLEARED     0x1UL
+	u8	unused_0[2];
 	u8	valid;
 };
 
@@ -5074,6 +5130,7 @@ struct hwrm_port_qstats_ext_output {
 	__le16	total_active_cos_queues;
 	u8	flags;
 	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED     0x1UL
+	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED                           0x2UL
 	u8	valid;
 };
 
@@ -6510,6 +6567,43 @@ struct hwrm_vnic_alloc_output {
 	u8	valid;
 };
 
+/* hwrm_vnic_update_input (size:256b/32B) */
+struct hwrm_vnic_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	__le32	enables;
+	#define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID               0x1UL
+	#define VNIC_UPDATE_REQ_ENABLES_MRU_VALID                      0x2UL
+	#define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID     0x4UL
+	u8	vnic_state;
+	#define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL
+	#define VNIC_UPDATE_REQ_VNIC_STATE_DROP   0x1UL
+	#define VNIC_UPDATE_REQ_VNIC_STATE_LAST  VNIC_UPDATE_REQ_VNIC_STATE_DROP
+	u8	metadata_format_type;
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4
+	__le16	mru;
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_update_output (size:128b/16B) */
+struct hwrm_vnic_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
 /* hwrm_vnic_free_input (size:192b/24B) */
 struct hwrm_vnic_free_input {
 	__le16	req_type;
@@ -6640,6 +6734,7 @@ struct hwrm_vnic_qcaps_output {
 	#define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED              0x8000000UL
 	#define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP                  0x10000000UL
 	#define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP                       0x20000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP                            0x40000000UL
 	__le16	max_aggs_supported;
 	u8	unused_1[5];
 	u8	valid;
@@ -7484,23 +7579,24 @@ struct hwrm_cfa_l2_filter_cfg_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le32	flags;
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH                0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX               0x0UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX               0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST            CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP                0x2UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK        0xcUL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT         2
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2    (0x0UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2            (0x1UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE          (0x2UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST         CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK       0x30UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT        4
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE    (0x0UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP  (0x1UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP  (0x2UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST        CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH                  0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX                 0x0UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX                 0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST              CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP                  0x2UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK          0xcUL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT           2
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2      (0x0UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2              (0x1UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE            (0x2UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST           CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK         0x30UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT          4
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE      (0x0UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP    (0x1UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP    (0x2UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP  (0x3UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST          CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP
 	__le32	enables;
 	#define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID                 0x1UL
 	#define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID     0x2UL
@@ -8766,7 +8862,7 @@ struct ctx_hw_stats_ext {
 	__le64	rx_tpa_events;
 };
 
-/* hwrm_stat_ctx_alloc_input (size:320b/40B) */
+/* hwrm_stat_ctx_alloc_input (size:384b/48B) */
 struct hwrm_stat_ctx_alloc_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -8776,13 +8872,16 @@ struct hwrm_stat_ctx_alloc_input {
 	__le64	stats_dma_addr;
 	__le32	update_period_ms;
 	u8	stat_ctx_flags;
-	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE     0x1UL
+	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE             0x1UL
+	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF     0x2UL
 	u8	unused_0;
 	__le16	stats_dma_length;
 	__le16	flags;
 	#define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID     0x1UL
 	__le16	steering_tag;
-	__le32	unused_1;
+	__le32	stat_ctx_id;
+	__le16	alloc_seq_id;
+	u8	unused_1[6];
 };
 
 /* hwrm_stat_ctx_alloc_output (size:128b/16B) */
@@ -9650,10 +9749,13 @@ struct hwrm_dbg_qcaps_output {
 	__le32	coredump_component_disable_caps;
 	#define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM     0x1UL
 	__le32	flags;
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM          0x1UL
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR     0x2UL
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR      0x4UL
-	#define DBG_QCAPS_RESP_FLAGS_USEQ                   0x8UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM             0x1UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR        0x2UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR         0x4UL
+	#define DBG_QCAPS_RESP_FLAGS_USEQ                      0x8UL
+	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR         0x10UL
+	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE     0x20UL
+	#define DBG_QCAPS_RESP_FLAGS_PTRACE                    0x40UL
 	u8	unused_1[3];
 	u8	valid;
 };
@@ -10092,16 +10194,19 @@ struct hwrm_nvm_erase_dir_entry_output {
 	u8	valid;
 };
 
-/* hwrm_nvm_get_dev_info_input (size:128b/16B) */
+/* hwrm_nvm_get_dev_info_input (size:192b/24B) */
 struct hwrm_nvm_get_dev_info_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
 	__le16	seq_id;
 	__le16	target_id;
 	__le64	resp_addr;
+	u8	flags;
+	#define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM     0x1UL
+	u8	unused_0[7];
 };
 
-/* hwrm_nvm_get_dev_info_output (size:704b/88B) */
+/* hwrm_nvm_get_dev_info_output (size:768b/96B) */
 struct hwrm_nvm_get_dev_info_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -10135,6 +10240,10 @@ struct hwrm_nvm_get_dev_info_output {
 	__le16	netctrl_fw_minor;
 	__le16	netctrl_fw_build;
 	__le16	netctrl_fw_patch;
+	__le16	srt2_fw_major;
+	__le16	srt2_fw_minor;
+	__le16	srt2_fw_build;
+	__le16	srt2_fw_patch;
 	u8	unused_0[7];
 	u8	valid;
 };
-- 
cgit v1.3-3-g829e


From f2878cdeb7549437c7c47029b4020e535735c5c9 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 7 Aug 2024 22:15:14 -0700
Subject: bnxt_en: Add support to call FW to update a VNIC

Add the function bnxt_hwrm_vnic_update() to call FW to update
a VNIC.  This call can be used when disabling and enabling a
receive ring within a VNIC.  The mru which is the maximum receive
size of packets received by the VNIC can be updated.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 20 ++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  3 +++
 2 files changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e27e1082ee33..6c0c65bed604 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10089,6 +10089,26 @@ vnic_setup_err:
 	return rc;
 }
 
+int bnxt_hwrm_vnic_update(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			  u8 valid)
+{
+	struct hwrm_vnic_update_input *req;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_VNIC_UPDATE);
+	if (rc)
+		return rc;
+
+	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
+
+	if (valid & VNIC_UPDATE_REQ_ENABLES_MRU_VALID)
+		req->mru = cpu_to_le16(vnic->mru);
+
+	req->enables = cpu_to_le32(valid);
+
+	return hwrm_req_send(bp, req);
+}
+
 int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	int rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6bbdc718c3a7..5de67f718993 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1250,6 +1250,7 @@ struct bnxt_vnic_info {
 #define BNXT_MAX_CTX_PER_VNIC	8
 	u16		fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC];
 	u16		fw_l2_ctx_id;
+	u16		mru;
 #define BNXT_MAX_UC_ADDRS	4
 	struct bnxt_l2_filter *l2_filters[BNXT_MAX_UC_ADDRS];
 				/* index 0 always dev_addr */
@@ -2838,6 +2839,8 @@ int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
 int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all);
 int bnxt_hwrm_func_qcaps(struct bnxt *bp);
 int bnxt_hwrm_fw_set_time(struct bnxt *);
+int bnxt_hwrm_vnic_update(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			  u8 valid);
 int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
 int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
 void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
-- 
cgit v1.3-3-g829e


From 6e360862c08756b13f3eb4b1dcbf0b9b9e4d7382 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 7 Aug 2024 22:15:15 -0700
Subject: bnxt_en: Check the FW's VNIC flush capability

Check the HWRM_VNIC_QCAPS FW response for the receive engine flush
capability.  This capability indicates that we can reliably support
RX ring restart when calling HWRM_VNIC_UPDATE with MRU set to 0.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 ++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6c0c65bed604..599ca00e0be3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6715,6 +6715,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 			bp->rss_cap |= BNXT_RSS_CAP_ESP_V4_RSS_CAP;
 		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP)
 			bp->rss_cap |= BNXT_RSS_CAP_ESP_V6_RSS_CAP;
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP)
+			bp->fw_cap |= BNXT_FW_CAP_VNIC_RE_FLUSH;
 	}
 	hwrm_req_drop(bp, req);
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 5de67f718993..a2233b2d9329 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2438,6 +2438,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_VNIC_TUNNEL_TPA		BIT_ULL(37)
 	#define BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO	BIT_ULL(38)
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3	BIT_ULL(39)
+	#define BNXT_FW_CAP_VNIC_RE_FLUSH		BIT_ULL(40)
 
 	u32			fw_dbg_cap;
 
-- 
cgit v1.3-3-g829e


From d41575f76a6d870b386b2aa75143c5cf9543fb45 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Wed, 7 Aug 2024 22:15:16 -0700
Subject: bnxt_en: set vnic->mru in bnxt_hwrm_vnic_cfg()

Set the newly added vnic->mru field in bnxt_hwrm_vnic_cfg().

Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 599ca00e0be3..10ca0edc4aab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6579,7 +6579,8 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 	req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id);
 	req->lb_rule = cpu_to_le16(0xffff);
 vnic_mru:
-	req->mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + VLAN_HLEN);
+	vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
+	req->mru = cpu_to_le16(vnic->mru);
 
 	req->vnic_id = cpu_to_le16(vnic->fw_vnic_id);
 #ifdef CONFIG_BNXT_SRIOV
-- 
cgit v1.3-3-g829e


From b9d2956e869c78bb356a71dd0a75346da9fd191f Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Wed, 7 Aug 2024 22:15:17 -0700
Subject: bnxt_en: stop packet flow during bnxt_queue_stop/start

The current implementation when resetting a queue while packets are
flowing puts the queue into an inconsistent state.

There needs to be some synchronisation with the FW. Add calls to
bnxt_hwrm_vnic_update() to set the MRU for both the default and ntuple
vnic during queue start/stop. When the MRU is set to 0, flow is stopped.
Each Rx queue belongs to either the default or the ntuple vnic.

With calling bnxt_hwrm_vnic_update() the calls to napi_enable() and
napi_disable() must be removed for reset to work on a queue that has
active traffic flowing e.g. iperf3.

Co-developed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 10ca0edc4aab..e1eadab82261 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15177,7 +15177,8 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr, *clone;
 	struct bnxt_cp_ring_info *cpr;
-	int rc;
+	struct bnxt_vnic_info *vnic;
+	int i, rc;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
@@ -15202,11 +15203,16 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 
-	napi_enable(&rxr->bnapi->napi);
-
 	cpr = &rxr->bnapi->cp_ring;
 	cpr->sw_stats->rx.rx_resets++;
 
+	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+		vnic = &bp->vnic_info[i];
+		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
+		bnxt_hwrm_vnic_update(bp, vnic,
+				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+	}
+
 	return 0;
 
 err_free_hwrm_rx_ring:
@@ -15218,9 +15224,17 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr;
+	struct bnxt_vnic_info *vnic;
+	int i;
+
+	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+		vnic = &bp->vnic_info[i];
+		vnic->mru = 0;
+		bnxt_hwrm_vnic_update(bp, vnic,
+				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+	}
 
 	rxr = &bp->rx_ring[idx];
-	napi_disable(&rxr->bnapi->napi);
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
 	rxr->rx_next_cons = 0;
-- 
cgit v1.3-3-g829e


From 97cbf3d0accce0f29db0be3ac1b50d9d561d3206 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Wed, 7 Aug 2024 22:15:18 -0700
Subject: bnxt_en: only set dev->queue_mgmt_ops if supported by FW

The queue API calls bnxt_hwrm_vnic_update() to stop/start the flow of
packets, which can only properly flush the pipeline if FW indicates
support.

Add a macro BNXT_SUPPORTS_QUEUE_API that checks for the required flags
and only set queue_mgmt_ops if true.

Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 3 +++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e1eadab82261..75e2cfed5769 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15718,7 +15718,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->stat_ops = &bnxt_stat_ops;
 	dev->watchdog_timeo = BNXT_TX_TIMEOUT;
 	dev->ethtool_ops = &bnxt_ethtool_ops;
-	dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
 	pci_set_drvdata(pdev, dev);
 
 	rc = bnxt_alloc_hwrm_resources(bp);
@@ -15899,6 +15898,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
 		bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX;
+	if (BNXT_SUPPORTS_QUEUE_API(bp))
+		dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
 
 	rc = register_netdev(dev);
 	if (rc)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index a2233b2d9329..62e637c5be31 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2451,6 +2451,9 @@ struct bnxt {
 #define BNXT_SUPPORTS_MULTI_RSS_CTX(bp)				\
 	(BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) &&	\
 	 ((bp)->rss_cap & BNXT_RSS_CAP_MULTI_RSS_CTX))
+#define BNXT_SUPPORTS_QUEUE_API(bp)				\
+	(BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) &&	\
+	 ((bp)->fw_cap & BNXT_FW_CAP_VNIC_RE_FLUSH))
 
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
-- 
cgit v1.3-3-g829e


From e81d00a6b3b7d619060223d0754ca02e7d4ba90f Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Thu, 8 Aug 2024 11:47:32 +0200
Subject: net: mvpp2: use port_count to remove ports

As discussed in [1], there is no need to iterate over child nodes to
remove the list of ports. Instead, a loop up to `port_count` ports can
be used, and is in fact more reliable in case the child node
availability changes.

The suggested approach removes the need for the `fwnode` and
`port_fwnode` variables in mvpp2_remove() as well.

Link: https://lore.kernel.org/all/ZqdRgDkK1PzoI2Pf@shell.armlinux.org.uk/ [1]
Suggested-by: Russell King <linux@armlinux.org.uk>
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0d62a33afa80..0b5b2425de12 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7655,12 +7655,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 err_port_probe:
 	fwnode_handle_put(port_fwnode);
 
-	i = 0;
-	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
-		if (priv->port_list[i])
-			mvpp2_port_remove(priv->port_list[i]);
-		i++;
-	}
+	for (i = 0; i < priv->port_count; i++)
+		mvpp2_port_remove(priv->port_list[i]);
 err_axi_clk:
 	clk_disable_unprepare(priv->axi_clk);
 err_mg_core_clk:
@@ -7677,18 +7673,13 @@ err_pp_clk:
 static void mvpp2_remove(struct platform_device *pdev)
 {
 	struct mvpp2 *priv = platform_get_drvdata(pdev);
-	struct fwnode_handle *fwnode = pdev->dev.fwnode;
-	int i = 0, poolnum = MVPP2_BM_POOLS_NUM;
-	struct fwnode_handle *port_fwnode;
+	int i, poolnum = MVPP2_BM_POOLS_NUM;
 
 	mvpp2_dbgfs_cleanup(priv);
 
-	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
-		if (priv->port_list[i]) {
-			mutex_destroy(&priv->port_list[i]->gather_stats_lock);
-			mvpp2_port_remove(priv->port_list[i]);
-		}
-		i++;
+	for (i = 0; i < priv->port_count; i++) {
+		mutex_destroy(&priv->port_list[i]->gather_stats_lock);
+		mvpp2_port_remove(priv->port_list[i]);
 	}
 
 	destroy_workqueue(priv->stats_queue);
@@ -7711,7 +7702,7 @@ static void mvpp2_remove(struct platform_device *pdev)
 				  aggr_txq->descs_dma);
 	}
 
-	if (is_acpi_node(port_fwnode))
+	if (!dev_of_node(&pdev->dev))
 		return;
 
 	clk_disable_unprepare(priv->axi_clk);
-- 
cgit v1.3-3-g829e


From a7b32744475cb774b4fce599f58394f4ef0acb68 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Thu, 8 Aug 2024 11:47:33 +0200
Subject: net: mvpp2: use device_for_each_child_node() to access device child
 nodes

The iterated nodes are direct children of the device node, and the
`device_for_each_child_node()` macro accounts for child node
availability.

`fwnode_for_each_available_child_node()` is meant to access the child
nodes of an fwnode, and therefore not direct child nodes of the device
node.

The child nodes within mvpp2_probe are not accessed outside the loops,
and the scoped version of the macro can be used to automatically
decrement the refcount on early exits.

Use `device_for_each_child_node()` and its scoped variant to indicate
device's direct child nodes.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0b5b2425de12..216cc7b860d6 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7417,8 +7417,6 @@ static int mvpp2_get_sram(struct platform_device *pdev,
 
 static int mvpp2_probe(struct platform_device *pdev)
 {
-	struct fwnode_handle *fwnode = pdev->dev.fwnode;
-	struct fwnode_handle *port_fwnode;
 	struct mvpp2 *priv;
 	struct resource *res;
 	void __iomem *base;
@@ -7591,7 +7589,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 	}
 
 	/* Map DTS-active ports. Should be done before FIFO mvpp2_init */
-	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
+	device_for_each_child_node_scoped(&pdev->dev, port_fwnode) {
 		if (!fwnode_property_read_u32(port_fwnode, "port-id", &i))
 			priv->port_map |= BIT(i);
 	}
@@ -7614,7 +7612,7 @@ static int mvpp2_probe(struct platform_device *pdev)
 		goto err_axi_clk;
 
 	/* Initialize ports */
-	fwnode_for_each_available_child_node(fwnode, port_fwnode) {
+	device_for_each_child_node_scoped(&pdev->dev, port_fwnode) {
 		err = mvpp2_port_probe(pdev, port_fwnode, priv);
 		if (err < 0)
 			goto err_port_probe;
@@ -7653,8 +7651,6 @@ static int mvpp2_probe(struct platform_device *pdev)
 	return 0;
 
 err_port_probe:
-	fwnode_handle_put(port_fwnode);
-
 	for (i = 0; i < priv->port_count; i++)
 		mvpp2_port_remove(priv->port_list[i]);
 err_axi_clk:
-- 
cgit v1.3-3-g829e


From aa9fbc5dd9da9e095a8b1a58540cf20cb06f595f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 8 Aug 2024 12:41:17 +0100
Subject: net: mii: constify advertising mask

Constify the advertising mask to linkmode functions that only read from
the advertising mask.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mii.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/mii.h b/include/linux/mii.h
index d5a959ce4877..b8f26d4513c3 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -140,7 +140,7 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv)
  * settings to phy autonegotiation advertisements for the
  * MII_ADVERTISE register.
  */
-static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising)
+static inline u32 linkmode_adv_to_mii_adv_t(const unsigned long *advertising)
 {
 	u32 result = 0;
 
@@ -215,7 +215,8 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv)
  * settings to phy autonegotiation advertisements for the
  * MII_CTRL1000 register when in 1000T mode.
  */
-static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising)
+static inline u32
+linkmode_adv_to_mii_ctrl1000_t(const unsigned long *advertising)
 {
 	u32 result = 0;
 
@@ -453,7 +454,7 @@ static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising,
  * A small helper function that translates linkmode advertising to LVL
  * pause capabilities.
  */
-static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising)
+static inline u32 linkmode_adv_to_lcl_adv_t(const unsigned long *advertising)
 {
 	u32 lcl_adv = 0;
 
-- 
cgit v1.3-3-g829e


From 6ff3cddc365beae1fbe185fd470cc0b86e895574 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 8 Aug 2024 12:41:22 +0100
Subject: net: phylib: do not disable autoneg for fixed speeds >= 1G

We have an increasing number of drivers that are forcing
auto-negotiation to be enabled for speeds of 1G or faster.

It would appear that auto-negotiation is mandatory for speeds above
100M. In 802.3, Annex 40C's state diagrams seems to imply that
mr_autoneg_enable (BMCR AN ENABLE) doesn't affect whether or not the
AN state machines work for 1000base-T, and some PHY datasheets (e.g.
Marvell Alaska) state that disabling mr_autoneg_enable leaves AN
enabled but forced to 1G full duplex.

Other PHY datasheets imply that BMCR AN ENABLE should not be cleared
for >= 1G.

Thus, this should be handled in phylib rather than in each driver.

Rather than erroring out, arrange to implement the Marvell Alaska
solution but in software for all PHYs: generate an appropriate
single-speed advertisement for the requested speed, and keep AN
enabled to the PHY driver. However, to avoid userspace API breakage,
continue to report to userspace that we have AN disabled.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 34752a87f98f..159e71c1c972 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2108,22 +2108,20 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable);
 /**
  * genphy_config_advert - sanitize and advertise auto-negotiation parameters
  * @phydev: target phy_device struct
+ * @advert: auto-negotiation parameters to advertise
  *
  * Description: Writes MII_ADVERTISE with the appropriate values,
  *   after sanitizing the values to make sure we only advertise
  *   what is supported.  Returns < 0 on error, 0 if the PHY's advertisement
  *   hasn't changed, and > 0 if it has changed.
  */
-static int genphy_config_advert(struct phy_device *phydev)
+static int genphy_config_advert(struct phy_device *phydev,
+				const unsigned long *advert)
 {
 	int err, bmsr, changed = 0;
 	u32 adv;
 
-	/* Only allow advertising what this PHY supports */
-	linkmode_and(phydev->advertising, phydev->advertising,
-		     phydev->supported);
-
-	adv = linkmode_adv_to_mii_adv_t(phydev->advertising);
+	adv = linkmode_adv_to_mii_adv_t(advert);
 
 	/* Setup standard advertisement */
 	err = phy_modify_changed(phydev, MII_ADVERTISE,
@@ -2146,7 +2144,7 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (!(bmsr & BMSR_ESTATEN))
 		return changed;
 
-	adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising);
+	adv = linkmode_adv_to_mii_ctrl1000_t(advert);
 
 	err = phy_modify_changed(phydev, MII_CTRL1000,
 				 ADVERTISE_1000FULL | ADVERTISE_1000HALF,
@@ -2370,6 +2368,9 @@ EXPORT_SYMBOL(genphy_check_and_restart_aneg);
  */
 int __genphy_config_aneg(struct phy_device *phydev, bool changed)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(fixed_advert);
+	const struct phy_setting *set;
+	unsigned long *advert;
 	int err;
 
 	err = genphy_c45_an_config_eee_aneg(phydev);
@@ -2384,10 +2385,25 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed)
 	else if (err)
 		changed = true;
 
-	if (AUTONEG_ENABLE != phydev->autoneg)
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		/* Only allow advertising what this PHY supports */
+		linkmode_and(phydev->advertising, phydev->advertising,
+			     phydev->supported);
+		advert = phydev->advertising;
+	} else if (phydev->speed < SPEED_1000) {
 		return genphy_setup_forced(phydev);
+	} else {
+		linkmode_zero(fixed_advert);
+
+		set = phy_lookup_setting(phydev->speed, phydev->duplex,
+					 phydev->supported, true);
+		if (set)
+			linkmode_set_bit(set->bit, fixed_advert);
+
+		advert = fixed_advert;
+	}
 
-	err = genphy_config_advert(phydev);
+	err = genphy_config_advert(phydev, advert);
 	if (err < 0) /* error */
 		return err;
 	else if (err)
-- 
cgit v1.3-3-g829e


From c4e82c025b3f2561823b4ba7c5f112a2005f442b Mon Sep 17 00:00:00 2001
From: Enguerrand de Ribaucourt <enguerrand.de-ribaucourt@savoirfairelinux.com>
Date: Thu, 8 Aug 2024 15:14:21 +0000
Subject: net: dsa: microchip: ksz9477: split half-duplex monitoring function

In order to respect the 80 columns limit, split the half-duplex
monitoring function in two.

This is just a styling change, no functional change.

Signed-off-by: Enguerrand de Ribaucourt <enguerrand.de-ribaucourt@savoirfairelinux.com>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477.c | 91 ++++++++++++++++++++++---------------
 1 file changed, 54 insertions(+), 37 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 425e20daf1e9..1e2293aa00dc 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -427,54 +427,71 @@ void ksz9477_freeze_mib(struct ksz_device *dev, int port, bool freeze)
 	mutex_unlock(&p->mib.cnt_mutex);
 }
 
-int ksz9477_errata_monitor(struct ksz_device *dev, int port,
-			   u64 tx_late_col)
+static int ksz9477_half_duplex_monitor(struct ksz_device *dev, int port,
+				       u64 tx_late_col)
 {
+	u8 lue_ctrl;
 	u32 pmavbc;
-	u8 status;
 	u16 pqm;
 	int ret;
 
-	ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status);
+	/* Errata DS80000754 recommends monitoring potential faults in
+	 * half-duplex mode. The switch might not be able to communicate anymore
+	 * in these states. If you see this message, please read the
+	 * errata-sheet for more information:
+	 * https://ww1.microchip.com/downloads/aemDocuments/documents
+	 * /UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf
+	 * To workaround this issue, half-duplex mode should be avoided.
+	 * A software reset could be implemented to recover from this state.
+	 */
+	dev_warn_once(dev->dev,
+		      "Half-duplex detected on port %d, transmission halt may occur\n",
+		      port);
+	if (tx_late_col != 0) {
+		/* Transmission halt with late collisions */
+		dev_crit_once(dev->dev,
+			      "TX late collisions detected, transmission may be halted on port %d\n",
+			      port);
+	}
+	ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &lue_ctrl);
 	if (ret)
 		return ret;
-	if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) == PORT_INTF_SPEED_NONE) &&
-	    !(status & PORT_INTF_FULL_DUPLEX)) {
-		/* Errata DS80000754 recommends monitoring potential faults in
-		 * half-duplex mode. The switch might not be able to communicate anymore
-		 * in these states.
-		 * If you see this message, please read the errata-sheet for more information:
-		 * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf
-		 * To workaround this issue, half-duplex mode should be avoided.
-		 * A software reset could be implemented to recover from this state.
-		 */
-		dev_warn_once(dev->dev,
-			      "Half-duplex detected on port %d, transmission halt may occur\n",
-			      port);
-		if (tx_late_col != 0) {
-			/* Transmission halt with late collisions */
-			dev_crit_once(dev->dev,
-				      "TX late collisions detected, transmission may be halted on port %d\n",
-				      port);
-		}
-		ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &status);
+	if (lue_ctrl & SW_VLAN_ENABLE) {
+		ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm);
 		if (ret)
 			return ret;
-		if (status & SW_VLAN_ENABLE) {
-			ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm);
-			if (ret)
-				return ret;
-			ret = ksz_read32(dev, REG_PMAVBC, &pmavbc);
-			if (ret)
-				return ret;
-			if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) ||
-			    (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) {
-				/* Transmission halt with Half-Duplex and VLAN */
-				dev_crit_once(dev->dev,
-					      "resources out of limits, transmission may be halted\n");
-			}
+
+		ret = ksz_read32(dev, REG_PMAVBC, &pmavbc);
+		if (ret)
+			return ret;
+
+		if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) ||
+		    (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) {
+			/* Transmission halt with Half-Duplex and VLAN */
+			dev_crit_once(dev->dev,
+				      "resources out of limits, transmission may be halted\n");
 		}
 	}
+
+	return ret;
+}
+
+int ksz9477_errata_monitor(struct ksz_device *dev, int port,
+			   u64 tx_late_col)
+{
+	u8 status;
+	int ret;
+
+	ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status);
+	if (ret)
+		return ret;
+
+	if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status)
+	      == PORT_INTF_SPEED_NONE) &&
+	    !(status & PORT_INTF_FULL_DUPLEX)) {
+		ret = ksz9477_half_duplex_monitor(dev, port, tx_late_col);
+	}
+
 	return ret;
 }
 
-- 
cgit v1.3-3-g829e


From f547e956dd84a585c6b75d3f52e1a1bb9c36c0e2 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Fri, 9 Aug 2024 13:55:18 -0700
Subject: net: sunvnet: use ethtool_sprintf/puts

Simpler and allows avoiding manual pointer addition.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/sunvnet.c | 34 ++++++++++------------------------
 1 file changed, 10 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 2f30715e9b67..1e887d951a04 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -114,37 +114,23 @@ static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 {
 	struct vnet *vp = (struct vnet *)netdev_priv(dev);
 	struct vnet_port *port;
-	char *p = (char *)buf;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
 		memcpy(buf, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
-		p += sizeof(ethtool_stats_keys);
+		buf += sizeof(ethtool_stats_keys);
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(port, &vp->port_list, list) {
-			snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM",
-				 port->q_index, port->switch_port ? "s" : "q",
-				 port->raddr);
-			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets",
-				 port->q_index);
-			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets",
-				 port->q_index);
-			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes",
-				 port->q_index);
-			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes",
-				 port->q_index);
-			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "p%u.event_up",
-				 port->q_index);
-			p += ETH_GSTRING_LEN;
-			snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset",
-				 port->q_index);
-			p += ETH_GSTRING_LEN;
+			ethtool_sprintf(&buf, "p%u.%s-%pM", port->q_index,
+					port->switch_port ? "s" : "q",
+					port->raddr);
+			ethtool_sprintf(&buf, "p%u.rx_packets", port->q_index);
+			ethtool_sprintf(&buf, "p%u.tx_packets", port->q_index);
+			ethtool_sprintf(&buf, "p%u.rx_bytes", port->q_index);
+			ethtool_sprintf(&buf, "p%u.tx_bytes", port->q_index);
+			ethtool_sprintf(&buf, "p%u.event_up", port->q_index);
+			ethtool_sprintf(&buf, "p%u.event_reset", port->q_index);
 		}
 		rcu_read_unlock();
 		break;
-- 
cgit v1.3-3-g829e


From 6b8a024d25ebf7535eb4a3e926309aa693cfe1bd Mon Sep 17 00:00:00 2001
From: Menglong Dong <menglong8.dong@gmail.com>
Date: Sat, 10 Aug 2024 10:06:32 +0800
Subject: net: vxlan: remove duplicated initialization in vxlan_xmit

The variable "did_rsc" is initialized twice, which is unnecessary. Just
remove one of them.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan/vxlan_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index ba59e92ab941..8983e75e9881 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2690,11 +2690,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *rdst, *fdst = NULL;
 	const struct ip_tunnel_info *info;
-	bool did_rsc = false;
 	struct vxlan_fdb *f;
 	struct ethhdr *eth;
 	__be32 vni = 0;
 	u32 nhid = 0;
+	bool did_rsc;
 
 	info = skb_tunnel_info(skb);
 
-- 
cgit v1.3-3-g829e


From 10fbe8c082fdde74b1f0814bc30e194cf330cdf7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:17 -0700
Subject: selftests: drv-net: rss_ctx: add identifier to traffic comments

Include the "name" of the context in the comment for traffic
checks. Makes it easier to reason about which context failed
when we loop over 32 contexts (it may matter if we failed in
first vs last, for example).

Reviewed-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 011508ca604b..1da6b214f4fe 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -90,10 +90,10 @@ def _send_traffic_check(cfg, port, name, params):
     ksft_ge(directed, 20000, f"traffic on {name}: " + str(cnts))
     if params.get('noise'):
         ksft_lt(sum(cnts[i] for i in params['noise']), directed / 2,
-                "traffic on other queues:" + str(cnts))
+                f"traffic on other queues ({name})':" + str(cnts))
     if params.get('empty'):
         ksft_eq(sum(cnts[i] for i in params['empty']), 0,
-                "traffic on inactive queues: " + str(cnts))
+                f"traffic on inactive queues ({name}): " + str(cnts))
 
 
 def test_rss_key_indir(cfg):
-- 
cgit v1.3-3-g829e


From f203fd85e6669d72fb3bfa3ce485a9642a4a9583 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:18 -0700
Subject: eth: mvpp2: implement new RSS context API

Implement the separate create/modify/delete ops for RSS.

No problems with IDs - even tho RSS tables are per device
the driver already seems to allocate IDs linearly per port.
There's a translation table from per-port context ID
to device context ID.

mvpp2 doesn't have a key for the hash, it defaults to
an empty/previous indir table.

Note that there is no key at all, so we don't have to be
concerned with reporting the wrong one (which is addressed
by a patch later in the series).

Compile-tested only.

Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c  | 18 ++----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h  |  2 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 82 +++++++++++++++++++------
 3 files changed, 69 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 40aeaa7bd739..1641791a2d5b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1522,29 +1522,19 @@ static int mvpp22_rss_context_create(struct mvpp2_port *port, u32 *rss_ctx)
 	return 0;
 }
 
-int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *port_ctx)
+int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 port_ctx)
 {
 	u32 rss_ctx;
-	int ret, i;
+	int ret;
 
 	ret = mvpp22_rss_context_create(port, &rss_ctx);
 	if (ret)
 		return ret;
 
-	/* Find the first available context number in the port, starting from 1.
-	 * Context 0 on each port is reserved for the default context.
-	 */
-	for (i = 1; i < MVPP22_N_RSS_TABLES; i++) {
-		if (port->rss_ctx[i] < 0)
-			break;
-	}
-
-	if (i == MVPP22_N_RSS_TABLES)
+	if (WARN_ON_ONCE(port->rss_ctx[port_ctx] >= 0))
 		return -EINVAL;
 
-	port->rss_ctx[i] = rss_ctx;
-	*port_ctx = i;
-
+	port->rss_ctx[port_ctx] = rss_ctx;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 663157dc8062..85c9c6e80678 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -264,7 +264,7 @@ int mvpp22_port_rss_init(struct mvpp2_port *port);
 int mvpp22_port_rss_enable(struct mvpp2_port *port);
 int mvpp22_port_rss_disable(struct mvpp2_port *port);
 
-int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *rss_ctx);
+int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 rss_ctx);
 int mvpp22_port_rss_ctx_delete(struct mvpp2_port *port, u32 rss_ctx);
 
 int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 rss_ctx,
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 216cc7b860d6..4a7098f5681c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5696,40 +5696,82 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev,
 	return ret;
 }
 
-static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
-				  struct ethtool_rxfh_param *rxfh,
-				  struct netlink_ext_ack *extack)
+static bool mvpp2_ethtool_rxfh_okay(struct mvpp2_port *port,
+				    const struct ethtool_rxfh_param *rxfh)
 {
-	struct mvpp2_port *port = netdev_priv(dev);
-	u32 *rss_context = &rxfh->rss_context;
-	int ret = 0;
-
 	if (!mvpp22_rss_is_supported(port))
-		return -EOPNOTSUPP;
+		return false;
 
 	if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
 	    rxfh->hfunc != ETH_RSS_HASH_CRC32)
-		return -EOPNOTSUPP;
+		return false;
 
 	if (rxfh->key)
+		return false;
+
+	return true;
+}
+
+static int mvpp2_create_rxfh_context(struct net_device *dev,
+				     struct ethtool_rxfh_context *ctx,
+				     const struct ethtool_rxfh_param *rxfh,
+				     struct netlink_ext_ack *extack)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
+
+	if (!mvpp2_ethtool_rxfh_okay(port, rxfh))
 		return -EOPNOTSUPP;
 
-	if (*rss_context && rxfh->rss_delete)
-		return mvpp22_port_rss_ctx_delete(port, *rss_context);
+	ctx->hfunc = ETH_RSS_HASH_CRC32;
 
-	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		ret = mvpp22_port_rss_ctx_create(port, rss_context);
-		if (ret)
-			return ret;
-	}
+	ret = mvpp22_port_rss_ctx_create(port, rxfh->rss_context);
+	if (ret)
+		return ret;
 
-	if (rxfh->indir)
-		ret = mvpp22_port_rss_ctx_indir_set(port, *rss_context,
+	if (!rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_get(port, rxfh->rss_context,
+						    ethtool_rxfh_context_indir(ctx));
+	else
+		ret = mvpp22_port_rss_ctx_indir_set(port, rxfh->rss_context,
 						    rxfh->indir);
+	return ret;
+}
+
+static int mvpp2_modify_rxfh_context(struct net_device *dev,
+				     struct ethtool_rxfh_context *ctx,
+				     const struct ethtool_rxfh_param *rxfh,
+				     struct netlink_ext_ack *extack)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
+
+	if (!mvpp2_ethtool_rxfh_okay(port, rxfh))
+		return -EOPNOTSUPP;
 
+	if (rxfh->indir)
+		ret = mvpp22_port_rss_ctx_indir_set(port, rxfh->rss_context,
+						    rxfh->indir);
 	return ret;
 }
 
+static int mvpp2_remove_rxfh_context(struct net_device *dev,
+				     struct ethtool_rxfh_context *ctx,
+				     u32 rss_context,
+				     struct netlink_ext_ack *extack)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	return mvpp22_port_rss_ctx_delete(port, rss_context);
+}
+
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev,
+				  struct ethtool_rxfh_param *rxfh,
+				  struct netlink_ext_ack *extack)
+{
+	return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack);
+}
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -5750,6 +5792,7 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.cap_rss_ctx_supported	= true,
+	.rxfh_max_num_contexts	= MVPP22_N_RSS_TABLES,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
 	.nway_reset		= mvpp2_ethtool_nway_reset,
@@ -5772,6 +5815,9 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= mvpp2_ethtool_get_rxfh,
 	.set_rxfh		= mvpp2_ethtool_set_rxfh,
+	.create_rxfh_context	= mvpp2_create_rxfh_context,
+	.modify_rxfh_context	= mvpp2_modify_rxfh_context,
+	.remove_rxfh_context	= mvpp2_remove_rxfh_context,
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
-- 
cgit v1.3-3-g829e


From a7f6f56f604a396f91d891321edb29f286a80069 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:19 -0700
Subject: eth: mlx5: allow disabling queues when RSS contexts exist

Since commit 24ac7e544081 ("ethtool: use the rss context XArray
in ring deactivation safety-check") core will prevent queues from
being disabled while being used by additional RSS contexts.
The safety check is no longer necessary, and core will do a more
accurate job of only rejecting changes which can actually break
things.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 56bdb4d07b7a..8af509397f63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -433,7 +433,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 	unsigned int count = ch->combined_count;
 	struct mlx5e_params new_params;
 	bool arfs_enabled;
-	int rss_cnt;
 	bool opened;
 	int err = 0;
 
@@ -487,17 +486,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	/* Don't allow changing the number of channels if non-default RSS contexts exist,
-	 * the kernel doesn't protect against set_channels operations that break them.
-	 */
-	rss_cnt = mlx5e_rx_res_rss_cnt(priv->rx_res) - 1;
-	if (rss_cnt) {
-		err = -EINVAL;
-		netdev_err(priv->netdev, "%s: Non-default RSS contexts exist (%d), cannot change the number of channels\n",
-			   __func__, rss_cnt);
-		goto out;
-	}
-
 	/* Don't allow changing the number of channels if MQPRIO mode channel offload is active,
 	 * because it defines a partition over the channels queues.
 	 */
-- 
cgit v1.3-3-g829e


From ce056504e2e53b22c1f789cff2ad6a0a135dc24d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:20 -0700
Subject: ethtool: make ethtool_ops::cap_rss_ctx_supported optional

cap_rss_ctx_supported was created because the API for creating
and configuring additional contexts is mux'ed with the normal
RSS API. Presence of ops does not imply driver can actually
support rss_context != 0 (in fact drivers mostly ignore that
field). cap_rss_ctx_supported lets core check that the driver
is context-aware before calling it.

Now that we have .create_rxfh_context, there is no such
ambiguity. We can depend on presence of the op.
Make setting the bit optional.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h | 3 ++-
 net/ethtool/ioctl.c     | 6 ++++--
 net/ethtool/rss.c       | 3 ++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 989c94eddb2b..a149485904d8 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -727,7 +727,8 @@ struct kernel_ethtool_ts_info {
  * @cap_link_lanes_supported: indicates if the driver supports lanes
  *	parameter.
  * @cap_rss_ctx_supported: indicates if the driver supports RSS
- *	contexts.
+ *	contexts via legacy API, drivers implementing @create_rxfh_context
+ *	do not have to set this bit.
  * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor
  *	RSS.
  * @rxfh_indir_space: max size of RSS indirection tables, if indirection table
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index ba8630eb02ef..1698b73812ce 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1227,7 +1227,8 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
+	if (rxfh.rss_context && !(ops->cap_rss_ctx_supported ||
+				  ops->create_rxfh_context))
 		return -EOPNOTSUPP;
 
 	rxfh.indir_size = rxfh_dev.indir_size;
@@ -1357,7 +1358,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !ops->cap_rss_ctx_supported)
+	if (rxfh.rss_context && !(ops->cap_rss_ctx_supported ||
+				  ops->create_rxfh_context))
 		return -EOPNOTSUPP;
 	/* Check input data transformation capabilities */
 	if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR &&
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 5c4c4505ab9a..a06bdac8b8a2 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -60,7 +60,8 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		return -EOPNOTSUPP;
 
 	/* Some drivers don't handle rss_context */
-	if (request->rss_context && !ops->cap_rss_ctx_supported)
+	if (request->rss_context && !(ops->cap_rss_ctx_supported ||
+				      ops->create_rxfh_context))
 		return -EOPNOTSUPP;
 
 	ret = ethnl_ops_begin(dev);
-- 
cgit v1.3-3-g829e


From fb770fe7584fb855620216193a34c6fb81830aa6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:21 -0700
Subject: eth: remove .cap_rss_ctx_supported from updated drivers

Remove .cap_rss_ctx_supported from drivers which moved to the new API.
This makes it easy to grep for drivers which still need to be converted.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 -
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c   | 1 -
 drivers/net/ethernet/sfc/ef100_ethtool.c          | 1 -
 drivers/net/ethernet/sfc/ethtool.c                | 1 -
 4 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9dadc89378f0..44076e4ebf1a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -5289,7 +5289,6 @@ void bnxt_ethtool_free(struct bnxt *bp)
 
 const struct ethtool_ops bnxt_ethtool_ops = {
 	.cap_link_lanes_supported	= 1,
-	.cap_rss_ctx_supported		= 1,
 	.rxfh_max_num_contexts		= BNXT_MAX_ETH_RSS_CTX + 1,
 	.rxfh_indir_space		= BNXT_MAX_RSS_TABLE_ENTRIES_P5,
 	.rxfh_priv_size			= sizeof(struct bnxt_rss_ctx),
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 4a7098f5681c..2fe8bae4eb3c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5791,7 +5791,6 @@ static const struct net_device_ops mvpp2_netdev_ops = {
 };
 
 static const struct ethtool_ops mvpp2_eth_tool_ops = {
-	.cap_rss_ctx_supported	= true,
 	.rxfh_max_num_contexts	= MVPP22_N_RSS_TABLES,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c
index 896ffca4aee2..746b5314acb5 100644
--- a/drivers/net/ethernet/sfc/ef100_ethtool.c
+++ b/drivers/net/ethernet/sfc/ef100_ethtool.c
@@ -37,7 +37,6 @@ ef100_ethtool_get_ringparam(struct net_device *net_dev,
 /*	Ethtool options available
  */
 const struct ethtool_ops ef100_ethtool_ops = {
-	.cap_rss_ctx_supported	= true,
 	.get_drvinfo		= efx_ethtool_get_drvinfo,
 	.get_msglevel		= efx_ethtool_get_msglevel,
 	.set_msglevel		= efx_ethtool_set_msglevel,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 7c887160e2ef..15245720c949 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -240,7 +240,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 }
 
 const struct ethtool_ops efx_ethtool_ops = {
-	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USECS_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
-- 
cgit v1.3-3-g829e


From ec6e57beaf8bc64ea0c2dc0cc360afcc7f504425 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:22 -0700
Subject: ethtool: rss: don't report key if device doesn't support it

marvell/otx2 and mvpp2 do not support setting different
keys for different RSS contexts. Contexts have separate
indirection tables but key is shared with all other contexts.
This is likely fine, indirection table is the most important
piece.

Don't report the key-related parameters from such drivers.
This prevents driver-errors, e.g. otx2 always writes
the main key, even when user asks to change per-context key.
The second reason is that without this change tracking
the keys by the core gets complicated. Even if the driver
correctly reject setting key with rss_context != 0,
change of the main key would have to be reflected in
the XArray for all additional contexts.

Since the additional contexts don't have their own keys
not including the attributes (in Netlink speak) seems
intuitive. ethtool CLI seems to deal with it just fine.

Having to set the flag in majority of the drivers is
a bit tedious but not reporting the key is a safer
default.

Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  |  1 +
 drivers/net/ethernet/intel/ice/ice_ethtool.c       |  1 +
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  1 +
 drivers/net/ethernet/sfc/ef100_ethtool.c           |  1 +
 drivers/net/ethernet/sfc/ethtool.c                 |  1 +
 include/linux/ethtool.h                            |  4 ++++
 net/ethtool/ioctl.c                                | 25 ++++++++++++++++++----
 net/ethtool/rss.c                                  | 21 ++++++++++++------
 8 files changed, 45 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 44076e4ebf1a..61d6afc3cacb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -5289,6 +5289,7 @@ void bnxt_ethtool_free(struct bnxt *bp)
 
 const struct ethtool_ops bnxt_ethtool_ops = {
 	.cap_link_lanes_supported	= 1,
+	.rxfh_per_ctx_key		= 1,
 	.rxfh_max_num_contexts		= BNXT_MAX_ETH_RSS_CTX + 1,
 	.rxfh_indir_space		= BNXT_MAX_RSS_TABLE_ENTRIES_P5,
 	.rxfh_priv_size			= sizeof(struct bnxt_rss_ctx),
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index bc79ba974e49..c7641d326ba5 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4725,6 +4725,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH,
 	.cap_rss_sym_xor_supported = true,
+	.rxfh_per_ctx_key	= true,
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
 	.get_fec_stats		= ice_get_fec_stats,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 8af509397f63..4d123dae912c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2595,6 +2595,7 @@ static void mlx5e_get_ts_stats(struct net_device *netdev,
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.cap_rss_ctx_supported	= true,
+	.rxfh_per_ctx_key	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c
index 746b5314acb5..5c2551369812 100644
--- a/drivers/net/ethernet/sfc/ef100_ethtool.c
+++ b/drivers/net/ethernet/sfc/ef100_ethtool.c
@@ -58,6 +58,7 @@ const struct ethtool_ops ef100_ethtool_ops = {
 
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
+	.rxfh_per_ctx_key	= true,
 	.rxfh_priv_size		= sizeof(struct efx_rss_context_priv),
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 15245720c949..848b1923133a 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -267,6 +267,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.set_rxnfc		= efx_ethtool_set_rxnfc,
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
+	.rxfh_per_ctx_key	= true,
 	.rxfh_priv_size		= sizeof(struct efx_rss_context_priv),
 	.get_rxfh		= efx_ethtool_get_rxfh,
 	.set_rxfh		= efx_ethtool_set_rxfh,
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index a149485904d8..12f6dc567598 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -731,6 +731,9 @@ struct kernel_ethtool_ts_info {
  *	do not have to set this bit.
  * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor
  *	RSS.
+ * @rxfh_per_ctx_key: device supports setting different RSS key for each
+ *	additional context. Netlink API should report hfunc, key, and input_xfrm
+ *	for every context, not just context 0.
  * @rxfh_indir_space: max size of RSS indirection tables, if indirection table
  *	size as returned by @get_rxfh_indir_size may change during lifetime
  *	of the device. Leave as 0 if the table size is constant.
@@ -952,6 +955,7 @@ struct ethtool_ops {
 	u32     cap_link_lanes_supported:1;
 	u32     cap_rss_ctx_supported:1;
 	u32	cap_rss_sym_xor_supported:1;
+	u32	rxfh_per_ctx_key:1;
 	u32	rxfh_indir_space;
 	u16	rxfh_key_space;
 	u16	rxfh_priv_size;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 1698b73812ce..18cf9fa32ae3 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1261,10 +1261,15 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 		if (rxfh_dev.indir)
 			memcpy(rxfh_dev.indir, ethtool_rxfh_context_indir(ctx),
 			       indir_bytes);
-		if (rxfh_dev.key)
-			memcpy(rxfh_dev.key, ethtool_rxfh_context_key(ctx),
-			       user_key_size);
-		rxfh_dev.hfunc = ctx->hfunc;
+		if (!ops->rxfh_per_ctx_key) {
+			rxfh_dev.key_size = 0;
+		} else {
+			if (rxfh_dev.key)
+				memcpy(rxfh_dev.key,
+				       ethtool_rxfh_context_key(ctx),
+				       user_key_size);
+			rxfh_dev.hfunc = ctx->hfunc;
+		}
 		rxfh_dev.input_xfrm = ctx->input_xfrm;
 		ret = 0;
 	} else {
@@ -1281,6 +1286,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 				&rxfh_dev.input_xfrm,
 				sizeof(rxfh.input_xfrm))) {
 		ret = -EFAULT;
+	} else if (copy_to_user(useraddr +
+				offsetof(struct ethtool_rxfh, key_size),
+				&rxfh_dev.key_size,
+				sizeof(rxfh.key_size))) {
+		ret = -EFAULT;
 	} else if (copy_to_user(useraddr +
 			      offsetof(struct ethtool_rxfh, rss_config[0]),
 			      rss_config, total_size)) {
@@ -1389,6 +1399,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 
 	indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]);
 
+	/* Check settings which may be global rather than per RSS-context */
+	if (rxfh.rss_context && !ops->rxfh_per_ctx_key)
+		if (rxfh.key_size ||
+		    (rxfh.hfunc && rxfh.hfunc != ETH_RSS_HASH_NO_CHANGE) ||
+		    (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE))
+			return -EOPNOTSUPP;
+
 	rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER);
 	if (!rss_config)
 		return -ENOMEM;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index a06bdac8b8a2..cd8100d81919 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -10,6 +10,7 @@ struct rss_req_info {
 
 struct rss_reply_data {
 	struct ethnl_reply_data		base;
+	bool				no_key_fields;
 	u32				indir_size;
 	u32				hkey_size;
 	u32				hfunc;
@@ -60,9 +61,12 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		return -EOPNOTSUPP;
 
 	/* Some drivers don't handle rss_context */
-	if (request->rss_context && !(ops->cap_rss_ctx_supported ||
-				      ops->create_rxfh_context))
-		return -EOPNOTSUPP;
+	if (request->rss_context) {
+		if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context)
+			return -EOPNOTSUPP;
+
+		data->no_key_fields = !ops->rxfh_per_ctx_key;
+	}
 
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
@@ -132,13 +136,18 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
 	    nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context))
 		return -EMSGSIZE;
 
+	if ((data->indir_size &&
+	     nla_put(skb, ETHTOOL_A_RSS_INDIR,
+		     sizeof(u32) * data->indir_size, data->indir_table)))
+		return -EMSGSIZE;
+
+	if (data->no_key_fields)
+		return 0;
+
 	if ((data->hfunc &&
 	     nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
 	    (data->input_xfrm &&
 	     nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) ||
-	    (data->indir_size &&
-	     nla_put(skb, ETHTOOL_A_RSS_INDIR,
-		     sizeof(u32) * data->indir_size, data->indir_table)) ||
 	    (data->hkey_size &&
 	     nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey)))
 		return -EMSGSIZE;
-- 
cgit v1.3-3-g829e


From a7ddfd5d57036caaaf2e1e896ff7aeed6530a0ca Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:23 -0700
Subject: ethtool: rss: move the device op invocation out of rss_prepare_data()

Factor calling device ops out of rss_prepare_data().
Next patch will add alternative path using xarray.
No functional changes.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/rss.c | 43 +++++++++++++++++++++++++++----------------
 1 file changed, 27 insertions(+), 16 deletions(-)

diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index cd8100d81919..5c477cc36251 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -43,13 +43,9 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb,
 }
 
 static int
-rss_prepare_data(const struct ethnl_req_info *req_base,
-		 struct ethnl_reply_data *reply_base,
-		 const struct genl_info *info)
+rss_prepare_get(const struct rss_req_info *request, struct net_device *dev,
+		struct rss_reply_data *data, const struct genl_info *info)
 {
-	struct rss_reply_data *data = RSS_REPDATA(reply_base);
-	struct rss_req_info *request = RSS_REQINFO(req_base);
-	struct net_device *dev = reply_base->dev;
 	struct ethtool_rxfh_param rxfh = {};
 	const struct ethtool_ops *ops;
 	u32 total_size, indir_bytes;
@@ -57,16 +53,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 	int ret;
 
 	ops = dev->ethtool_ops;
-	if (!ops->get_rxfh)
-		return -EOPNOTSUPP;
-
-	/* Some drivers don't handle rss_context */
-	if (request->rss_context) {
-		if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context)
-			return -EOPNOTSUPP;
-
-		data->no_key_fields = !ops->rxfh_per_ctx_key;
-	}
 
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
@@ -109,6 +95,31 @@ out_ops:
 	return ret;
 }
 
+static int
+rss_prepare_data(const struct ethnl_req_info *req_base,
+		 struct ethnl_reply_data *reply_base,
+		 const struct genl_info *info)
+{
+	struct rss_reply_data *data = RSS_REPDATA(reply_base);
+	struct rss_req_info *request = RSS_REQINFO(req_base);
+	struct net_device *dev = reply_base->dev;
+	const struct ethtool_ops *ops;
+
+	ops = dev->ethtool_ops;
+	if (!ops->get_rxfh)
+		return -EOPNOTSUPP;
+
+	/* Some drivers don't handle rss_context */
+	if (request->rss_context) {
+		if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context)
+			return -EOPNOTSUPP;
+
+		data->no_key_fields = !ops->rxfh_per_ctx_key;
+	}
+
+	return rss_prepare_get(request, dev, data, info);
+}
+
 static int
 rss_reply_size(const struct ethnl_req_info *req_base,
 	       const struct ethnl_reply_data *reply_base)
-- 
cgit v1.3-3-g829e


From bb87f2c7968eaebafa130f0618dea554700bb74b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:24 -0700
Subject: ethtool: rss: report info about additional contexts from XArray

IOCTL already uses the XArray when reporting info about additional
contexts. Do the same thing in netlink code.

Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/rss.c | 37 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 5c477cc36251..023782ca1230 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -82,7 +82,6 @@ rss_prepare_get(const struct rss_req_info *request, struct net_device *dev,
 	rxfh.indir = data->indir_table;
 	rxfh.key_size = data->hkey_size;
 	rxfh.key = data->hkey;
-	rxfh.rss_context = request->rss_context;
 
 	ret = ops->get_rxfh(dev, &rxfh);
 	if (ret)
@@ -95,6 +94,41 @@ out_ops:
 	return ret;
 }
 
+static int
+rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev,
+		struct rss_reply_data *data, const struct genl_info *info)
+{
+	struct ethtool_rxfh_context *ctx;
+	u32 total_size, indir_bytes;
+	u8 *rss_config;
+
+	ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context);
+	if (!ctx)
+		return -ENOENT;
+
+	data->indir_size = ctx->indir_size;
+	data->hkey_size = ctx->key_size;
+	data->hfunc = ctx->hfunc;
+	data->input_xfrm = ctx->input_xfrm;
+
+	indir_bytes = data->indir_size * sizeof(u32);
+	total_size = indir_bytes + data->hkey_size;
+	rss_config = kzalloc(total_size, GFP_KERNEL);
+	if (!rss_config)
+		return -ENOMEM;
+
+	data->indir_table = (u32 *)rss_config;
+	memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), indir_bytes);
+
+	if (data->hkey_size) {
+		data->hkey = rss_config + indir_bytes;
+		memcpy(data->hkey, ethtool_rxfh_context_key(ctx),
+		       data->hkey_size);
+	}
+
+	return 0;
+}
+
 static int
 rss_prepare_data(const struct ethnl_req_info *req_base,
 		 struct ethnl_reply_data *reply_base,
@@ -115,6 +149,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 			return -EOPNOTSUPP;
 
 		data->no_key_fields = !ops->rxfh_per_ctx_key;
+		return rss_prepare_ctx(request, dev, data, info);
 	}
 
 	return rss_prepare_get(request, dev, data, info);
-- 
cgit v1.3-3-g829e


From f6122900f4e28bfcb8abc76e1f7b83a1e0d8afd3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:25 -0700
Subject: ethtool: rss: support dumping RSS contexts

Now that we track RSS contexts in the core we can easily dump
them. This is a major introspection improvement, as previously
the only way to find all contexts would be to try all ids
(of which there may be 2^32 - 1).

Don't use the XArray iterators (like xa_for_each_start()) as they
do not move the index past the end of the array once done, which
caused multiple bugs in Netlink dumps in the past.

Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/specs/ethtool.yaml |   9 ++-
 net/ethtool/netlink.c                    |   2 +
 net/ethtool/netlink.h                    |   2 +
 net/ethtool/rss.c                        | 135 +++++++++++++++++++++++++++++++
 4 files changed, 146 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index ea21fe135b97..cf69eedae51d 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1749,12 +1749,12 @@ operations:
 
       attribute-set: rss
 
-      do: &rss-get-op
+      do:
         request:
           attributes:
             - header
             - context
-        reply:
+        reply: &rss-reply
           attributes:
             - header
             - context
@@ -1762,6 +1762,11 @@ operations:
             - indir
             - hkey
             - input_xfrm
+      dump:
+        request:
+          attributes:
+            - header
+        reply: *rss-reply
     -
       name: plca-get-cfg
       doc: Get PLCA params.
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index cb1eea00e349..041548e5f5e6 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -1128,6 +1128,8 @@ static const struct genl_ops ethtool_genl_ops[] = {
 	{
 		.cmd	= ETHTOOL_MSG_RSS_GET,
 		.doit	= ethnl_default_doit,
+		.start	= ethnl_rss_dump_start,
+		.dumpit	= ethnl_rss_dumpit,
 		.policy = ethnl_rss_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1,
 	},
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 46ec273a87c5..919371383b23 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -464,6 +464,8 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_start(struct netlink_callback *cb);
 int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info);
+int ethnl_rss_dump_start(struct netlink_callback *cb);
+int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 
 extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN];
 extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN];
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 023782ca1230..2865720ff583 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -208,6 +208,141 @@ static void rss_cleanup_data(struct ethnl_reply_data *reply_base)
 	kfree(data->indir_table);
 }
 
+struct rss_nl_dump_ctx {
+	unsigned long		ifindex;
+	unsigned long		ctx_idx;
+
+	/* User wants to only dump contexts from given ifindex */
+	unsigned int		match_ifindex;
+};
+
+static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb)
+{
+	NL_ASSERT_DUMP_CTX_FITS(struct rss_nl_dump_ctx);
+
+	return (struct rss_nl_dump_ctx *)cb->ctx;
+}
+
+int ethnl_rss_dump_start(struct netlink_callback *cb)
+{
+	const struct genl_info *info = genl_info_dump(cb);
+	struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb);
+	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
+	int ret;
+
+	/* Filtering by context not supported */
+	if (tb[ETHTOOL_A_RSS_CONTEXT]) {
+		NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]);
+		return -EINVAL;
+	}
+
+	ret = ethnl_parse_header_dev_get(&req_info,
+					 tb[ETHTOOL_A_RSS_HEADER],
+					 sock_net(cb->skb->sk), cb->extack,
+					 false);
+	if (req_info.dev) {
+		ctx->match_ifindex = req_info.dev->ifindex;
+		ctx->ifindex = ctx->match_ifindex;
+		ethnl_parse_header_dev_put(&req_info);
+		req_info.dev = NULL;
+	}
+
+	return ret;
+}
+
+static int
+rss_dump_one_ctx(struct sk_buff *skb, struct netlink_callback *cb,
+		 struct net_device *dev, u32 rss_context)
+{
+	const struct genl_info *info = genl_info_dump(cb);
+	struct rss_reply_data data = {};
+	struct rss_req_info req = {};
+	void *ehdr;
+	int ret;
+
+	req.rss_context = rss_context;
+
+	ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_RSS_GET_REPLY);
+	if (!ehdr)
+		return -EMSGSIZE;
+
+	ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_RSS_HEADER);
+	if (ret < 0)
+		goto err_cancel;
+
+	/* Context 0 is not currently storred or cached in the XArray */
+	if (!rss_context)
+		ret = rss_prepare_get(&req, dev, &data, info);
+	else
+		ret = rss_prepare_ctx(&req, dev, &data, info);
+	if (ret)
+		goto err_cancel;
+
+	ret = rss_fill_reply(skb, &req.base, &data.base);
+	if (ret)
+		goto err_cleanup;
+	genlmsg_end(skb, ehdr);
+
+	rss_cleanup_data(&data.base);
+	return 0;
+
+err_cleanup:
+	rss_cleanup_data(&data.base);
+err_cancel:
+	genlmsg_cancel(skb, ehdr);
+	return ret;
+}
+
+static int
+rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb,
+		 struct net_device *dev)
+{
+	struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb);
+	int ret;
+
+	if (!dev->ethtool_ops->get_rxfh)
+		return 0;
+
+	if (!ctx->ctx_idx) {
+		ret = rss_dump_one_ctx(skb, cb, dev, 0);
+		if (ret)
+			return ret;
+		ctx->ctx_idx++;
+	}
+
+	for (; xa_find(&dev->ethtool->rss_ctx, &ctx->ctx_idx,
+		       ULONG_MAX, XA_PRESENT); ctx->ctx_idx++) {
+		ret = rss_dump_one_ctx(skb, cb, dev, ctx->ctx_idx);
+		if (ret)
+			return ret;
+	}
+	ctx->ctx_idx = 0;
+
+	return 0;
+}
+
+int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+	for_each_netdev_dump(net, dev, ctx->ifindex) {
+		if (ctx->match_ifindex && ctx->match_ifindex != ctx->ifindex)
+			break;
+
+		ret = rss_dump_one_dev(skb, cb, dev);
+		if (ret)
+			break;
+	}
+	rtnl_unlock();
+
+	return ret;
+}
+
 const struct ethnl_request_ops ethnl_rss_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_RSS_GET,
 	.reply_cmd		= ETHTOOL_MSG_RSS_GET_REPLY,
-- 
cgit v1.3-3-g829e


From 3d50c66c0609c8b64fb22e9c188fca88f34e7c98 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:26 -0700
Subject: ethtool: rss: support skipping contexts during dump

Applications may want to deal with dynamic RSS contexts only.
So dumping context 0 will be counter-productive for them.
Support starting the dump from a given context ID.

Alternative would be to implement a dump flag to skip just
context 0, not sure which is better...

Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/specs/ethtool.yaml     |  4 ++++
 Documentation/networking/ethtool-netlink.rst | 12 ++++++++++--
 include/uapi/linux/ethtool_netlink.h         |  1 +
 net/ethtool/netlink.h                        |  2 +-
 net/ethtool/rss.c                            | 12 +++++++++++-
 5 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index cf69eedae51d..4c2334c213b0 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1028,6 +1028,9 @@ attribute-sets:
       -
         name: input_xfrm
         type: u32
+      -
+        name: start-context
+        type: u32
   -
     name: plca
     attributes:
@@ -1766,6 +1769,7 @@ operations:
         request:
           attributes:
             - header
+            - start-context
         reply: *rss-reply
     -
       name: plca-get-cfg
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index d5f246aceb9f..82c5542c80ce 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1866,10 +1866,18 @@ RSS context of an interface similar to ``ETHTOOL_GRSSH`` ioctl request.
 
 Request contents:
 
-=====================================  ======  ==========================
+=====================================  ======  ============================
   ``ETHTOOL_A_RSS_HEADER``             nested  request header
   ``ETHTOOL_A_RSS_CONTEXT``            u32     context number
-=====================================  ======  ==========================
+  ``ETHTOOL_A_RSS_START_CONTEXT``      u32     start context number (dumps)
+=====================================  ======  ============================
+
+``ETHTOOL_A_RSS_CONTEXT`` specifies which RSS context number to query,
+if not set context 0 (the main context) is queried. Dumps can be filtered
+by device (only listing contexts of a given netdev). Filtering single
+context number is not supported but ``ETHTOOL_A_RSS_START_CONTEXT``
+can be used to start dumping context from the given number (primarily
+used to ignore context 0s and only dump additional contexts).
 
 Kernel response contents:
 
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 6d5bdcc67631..93c57525a975 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -965,6 +965,7 @@ enum {
 	ETHTOOL_A_RSS_INDIR,		/* binary */
 	ETHTOOL_A_RSS_HKEY,		/* binary */
 	ETHTOOL_A_RSS_INPUT_XFRM,	/* u32 */
+	ETHTOOL_A_RSS_START_CONTEXT,	/* u32 */
 
 	__ETHTOOL_A_RSS_CNT,
 	ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1),
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 919371383b23..236c189fc968 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -449,7 +449,7 @@ extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER +
 extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1];
 extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1];
 extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1];
-extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1];
+extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_START_CONTEXT + 1];
 extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1];
 extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1];
 extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1];
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 2865720ff583..e07386275e14 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -28,6 +28,7 @@ struct rss_reply_data {
 const struct nla_policy ethnl_rss_get_policy[] = {
 	[ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 },
+	[ETHTOOL_A_RSS_START_CONTEXT] = { .type = NLA_U32 },
 };
 
 static int
@@ -38,6 +39,10 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb,
 
 	if (tb[ETHTOOL_A_RSS_CONTEXT])
 		request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]);
+	if (tb[ETHTOOL_A_RSS_START_CONTEXT]) {
+		NL_SET_BAD_ATTR(extack, tb[ETHTOOL_A_RSS_START_CONTEXT]);
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -214,6 +219,7 @@ struct rss_nl_dump_ctx {
 
 	/* User wants to only dump contexts from given ifindex */
 	unsigned int		match_ifindex;
+	unsigned int		start_ctx;
 };
 
 static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb)
@@ -236,6 +242,10 @@ int ethnl_rss_dump_start(struct netlink_callback *cb)
 		NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]);
 		return -EINVAL;
 	}
+	if (tb[ETHTOOL_A_RSS_START_CONTEXT]) {
+		ctx->start_ctx = nla_get_u32(tb[ETHTOOL_A_RSS_START_CONTEXT]);
+		ctx->ctx_idx = ctx->start_ctx;
+	}
 
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_RSS_HEADER],
@@ -317,7 +327,7 @@ rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb,
 		if (ret)
 			return ret;
 	}
-	ctx->ctx_idx = 0;
+	ctx->ctx_idx = ctx->start_ctx;
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 8ad3be135212a99fe16961de0e6d7d0ddd8268a2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:27 -0700
Subject: netlink: specs: decode indirection table as u32 array

Indirection table is dumped as a raw u32 array, decode it.
It's tempting to decode hash key, too, but it is an actual
bitstream, so leave it be for now.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/specs/ethtool.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 4c2334c213b0..1bbeaba5c644 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1022,6 +1022,7 @@ attribute-sets:
       -
         name: indir
         type: binary
+        sub-type: u32
       -
         name: hkey
         type: binary
-- 
cgit v1.3-3-g829e


From c1ad8ef804e40fc1ef3cb008e0113d76f4acc1a0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:37:28 -0700
Subject: selftests: drv-net: rss_ctx: test dumping RSS contexts

Add a test for dumping RSS contexts. Make sure indir table
and key are sane when contexts are created with various
combination of inputs. Test the dump filtering by ifname
and start-context.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 76 ++++++++++++++++++++++-
 tools/testing/selftests/net/lib/py/ksft.py        |  6 ++
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 1da6b214f4fe..9d7adb3cf33b 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -3,7 +3,7 @@
 
 import datetime
 import random
-from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ge, ksft_lt
+from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx
@@ -302,6 +302,78 @@ def test_hitless_key_update(cfg):
     ksft_eq(carrier1 - carrier0, 0)
 
 
+def test_rss_context_dump(cfg):
+    """
+    Test dumping RSS contexts. This tests mostly exercises the kernel APIs.
+    """
+
+    # Get a random key of the right size
+    data = get_rss(cfg)
+    if 'rss-hash-key' in data:
+        key_data = _rss_key_rand(len(data['rss-hash-key']))
+        key = _rss_key_str(key_data)
+    else:
+        key_data = []
+        key = "ba:ad"
+
+    ids = []
+    try:
+        ids.append(ethtool_create(cfg, "-X", f"context new"))
+        defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete")
+
+        ids.append(ethtool_create(cfg, "-X", f"context new weight 1 1"))
+        defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete")
+
+        ids.append(ethtool_create(cfg, "-X", f"context new hkey {key}"))
+        defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete")
+    except CmdExitFailure:
+        if not ids:
+            raise KsftSkipEx("Unable to add any contexts")
+        ksft_pr(f"Added only {len(ids)} out of 3 contexts")
+
+    expect_tuples = set([(cfg.ifname, -1)] + [(cfg.ifname, ctx_id) for ctx_id in ids])
+
+    # Dump all
+    ctxs = cfg.ethnl.rss_get({}, dump=True)
+    tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]
+    ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump")
+    ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname])
+    ksft_eq(expect_tuples, ctx_tuples)
+
+    # Sanity-check the results
+    for data in ctxs:
+        ksft_ne(set(data['indir']), {0}, "indir table is all zero")
+        ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero")
+
+        # More specific checks
+        if len(ids) > 1 and data.get('context') == ids[1]:
+            ksft_eq(set(data['indir']), {0, 1},
+                    "ctx1 - indir table mismatch")
+        if len(ids) > 2 and data.get('context') == ids[2]:
+            ksft_eq(data['hkey'], bytes(key_data), "ctx2 - key mismatch")
+
+    # Ifindex filter
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True)
+    tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]
+    ctx_tuples = set(tuples)
+    ksft_eq(len(tuples), len(ctx_tuples), "duplicates in context dump")
+    ksft_eq(expect_tuples, ctx_tuples)
+
+    # Skip ctx 0
+    expect_tuples.remove((cfg.ifname, -1))
+
+    ctxs = cfg.ethnl.rss_get({'start-context': 1}, dump=True)
+    tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]
+    ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump")
+    ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname])
+    ksft_eq(expect_tuples, ctx_tuples)
+
+    # And finally both with ifindex and skip main
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}, 'start-context': 1}, dump=True)
+    ctx_tuples = set([(c['header']['dev-name'], c.get('context', -1)) for c in ctxs])
+    ksft_eq(expect_tuples, ctx_tuples)
+
+
 def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
     """
     Test separating traffic into RSS contexts.
@@ -542,7 +614,7 @@ def main() -> None:
         ksft_run([test_rss_key_indir, test_rss_queue_reconfigure,
                   test_rss_resize, test_hitless_key_update,
                   test_rss_context, test_rss_context4, test_rss_context32,
-                  test_rss_context_queue_reconfigure,
+                  test_rss_context_dump, test_rss_context_queue_reconfigure,
                   test_rss_context_overlap, test_rss_context_overlap2,
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg],
                  args=(cfg, ))
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index f663e0daec0d..477ae76de93d 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -55,6 +55,12 @@ def ksft_eq(a, b, comment=""):
         _fail("Check failed", a, "!=", b, comment)
 
 
+def ksft_ne(a, b, comment=""):
+    global KSFT_RESULT
+    if a == b:
+        _fail("Check failed", a, "==", b, comment)
+
+
 def ksft_true(a, comment=""):
     if not a:
         _fail("Check failed", a, "does not eval to True", comment)
-- 
cgit v1.3-3-g829e


From 45d84008ccbe2592206c110bd526c7dc140f7bd8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 9 Aug 2024 22:43:21 -0700
Subject: eth: fbnic: add basic rtnl stats

Count packets, bytes and drop on the datapath, and report
to the user. Since queues are completely freed when the
device is down - accumulate the stats in the main netdev struct.
This means that per-queue stats will only report values since
last reset (per qstat recommendation).

Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20240810054322.2766421-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.c | 69 ++++++++++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.h |  3 ++
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c   | 51 ++++++++++++++++++-
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h   | 10 ++++
 4 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index b7ce6da68543..a048e4a617eb 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -316,6 +316,74 @@ void fbnic_clear_rx_mode(struct net_device *netdev)
 	__dev_mc_unsync(netdev, NULL);
 }
 
+static void fbnic_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *stats64)
+{
+	u64 tx_bytes, tx_packets, tx_dropped = 0;
+	u64 rx_bytes, rx_packets, rx_dropped = 0;
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_queue_stats *stats;
+	unsigned int start, i;
+
+	stats = &fbn->tx_stats;
+
+	tx_bytes = stats->bytes;
+	tx_packets = stats->packets;
+	tx_dropped = stats->dropped;
+
+	stats64->tx_bytes = tx_bytes;
+	stats64->tx_packets = tx_packets;
+	stats64->tx_dropped = tx_dropped;
+
+	for (i = 0; i < fbn->num_tx_queues; i++) {
+		struct fbnic_ring *txr = fbn->tx[i];
+
+		if (!txr)
+			continue;
+
+		stats = &txr->stats;
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			tx_bytes = stats->bytes;
+			tx_packets = stats->packets;
+			tx_dropped = stats->dropped;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		stats64->tx_bytes += tx_bytes;
+		stats64->tx_packets += tx_packets;
+		stats64->tx_dropped += tx_dropped;
+	}
+
+	stats = &fbn->rx_stats;
+
+	rx_bytes = stats->bytes;
+	rx_packets = stats->packets;
+	rx_dropped = stats->dropped;
+
+	stats64->rx_bytes = rx_bytes;
+	stats64->rx_packets = rx_packets;
+	stats64->rx_dropped = rx_dropped;
+
+	for (i = 0; i < fbn->num_rx_queues; i++) {
+		struct fbnic_ring *rxr = fbn->rx[i];
+
+		if (!rxr)
+			continue;
+
+		stats = &rxr->stats;
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			rx_bytes = stats->bytes;
+			rx_packets = stats->packets;
+			rx_dropped = stats->dropped;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		stats64->rx_bytes += rx_bytes;
+		stats64->rx_packets += rx_packets;
+		stats64->rx_dropped += rx_dropped;
+	}
+}
+
 static const struct net_device_ops fbnic_netdev_ops = {
 	.ndo_open		= fbnic_open,
 	.ndo_stop		= fbnic_stop,
@@ -324,6 +392,7 @@ static const struct net_device_ops fbnic_netdev_ops = {
 	.ndo_features_check	= fbnic_features_check,
 	.ndo_set_mac_address	= fbnic_set_mac,
 	.ndo_set_rx_mode	= fbnic_set_rx_mode,
+	.ndo_get_stats64	= fbnic_get_stats64,
 };
 
 void fbnic_reset_queues(struct fbnic_net *fbn,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
index 6bc0ebeb8182..60199e634468 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
@@ -40,6 +40,9 @@ struct fbnic_net {
 	u32 rss_key[FBNIC_RPC_RSS_KEY_DWORD_LEN];
 	u32 rss_flow_hash[FBNIC_NUM_HASH_OPT];
 
+	/* Storage for stats after ring destruction */
+	struct fbnic_queue_stats tx_stats;
+	struct fbnic_queue_stats rx_stats;
 	u64 link_down_events;
 
 	struct list_head napis;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 0ed4c9fff5d8..4d0406af297f 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -273,6 +273,9 @@ fbnic_xmit_frame_ring(struct sk_buff *skb, struct fbnic_ring *ring)
 err_free:
 	dev_kfree_skb_any(skb);
 err_count:
+	u64_stats_update_begin(&ring->stats.syncp);
+	ring->stats.dropped++;
+	u64_stats_update_end(&ring->stats.syncp);
 	return NETDEV_TX_OK;
 }
 
@@ -363,10 +366,19 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 	txq = txring_txq(nv->napi.dev, ring);
 
 	if (unlikely(discard)) {
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.dropped += total_packets;
+		u64_stats_update_end(&ring->stats.syncp);
+
 		netdev_tx_completed_queue(txq, total_packets, total_bytes);
 		return;
 	}
 
+	u64_stats_update_begin(&ring->stats.syncp);
+	ring->stats.bytes += total_bytes;
+	ring->stats.packets += total_packets;
+	u64_stats_update_end(&ring->stats.syncp);
+
 	netif_txq_completed_wake(txq, total_packets, total_bytes,
 				 fbnic_desc_unused(ring),
 				 FBNIC_TX_DESC_WAKEUP);
@@ -730,12 +742,12 @@ static bool fbnic_rcd_metadata_err(u64 rcd)
 static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 			   struct fbnic_q_triad *qt, int budget)
 {
+	unsigned int packets = 0, bytes = 0, dropped = 0;
 	struct fbnic_ring *rcq = &qt->cmpl;
 	struct fbnic_pkt_buff *pkt;
 	s32 head0 = -1, head1 = -1;
 	__le64 *raw_rcd, done;
 	u32 head = rcq->head;
-	u64 packets = 0;
 
 	done = (head & (rcq->size_mask + 1)) ? cpu_to_le64(FBNIC_RCD_DONE) : 0;
 	raw_rcd = &rcq->desc[head & rcq->size_mask];
@@ -780,9 +792,11 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 				fbnic_populate_skb_fields(nv, rcd, skb, qt);
 
 				packets++;
+				bytes += skb->len;
 
 				napi_gro_receive(&nv->napi, skb);
 			} else {
+				dropped++;
 				fbnic_put_pkt_buff(nv, pkt, 1);
 			}
 
@@ -799,6 +813,14 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 		}
 	}
 
+	u64_stats_update_begin(&rcq->stats.syncp);
+	rcq->stats.packets += packets;
+	rcq->stats.bytes += bytes;
+	/* Re-add ethernet header length (removed in fbnic_build_skb) */
+	rcq->stats.bytes += ETH_HLEN * packets;
+	rcq->stats.dropped += dropped;
+	u64_stats_update_end(&rcq->stats.syncp);
+
 	/* Unmap and free processed buffers */
 	if (head0 >= 0)
 		fbnic_clean_bdq(nv, budget, &qt->sub0, head0);
@@ -865,12 +887,36 @@ static irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
+					     struct fbnic_ring *rxr)
+{
+	struct fbnic_queue_stats *stats = &rxr->stats;
+
+	/* Capture stats from queues before dissasociating them */
+	fbn->rx_stats.bytes += stats->bytes;
+	fbn->rx_stats.packets += stats->packets;
+	fbn->rx_stats.dropped += stats->dropped;
+}
+
+static void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
+					     struct fbnic_ring *txr)
+{
+	struct fbnic_queue_stats *stats = &txr->stats;
+
+	/* Capture stats from queues before dissasociating them */
+	fbn->tx_stats.bytes += stats->bytes;
+	fbn->tx_stats.packets += stats->packets;
+	fbn->tx_stats.dropped += stats->dropped;
+}
+
 static void fbnic_remove_tx_ring(struct fbnic_net *fbn,
 				 struct fbnic_ring *txr)
 {
 	if (!(txr->flags & FBNIC_RING_F_STATS))
 		return;
 
+	fbnic_aggregate_ring_tx_counters(fbn, txr);
+
 	/* Remove pointer to the Tx ring */
 	WARN_ON(fbn->tx[txr->q_idx] && fbn->tx[txr->q_idx] != txr);
 	fbn->tx[txr->q_idx] = NULL;
@@ -882,6 +928,8 @@ static void fbnic_remove_rx_ring(struct fbnic_net *fbn,
 	if (!(rxr->flags & FBNIC_RING_F_STATS))
 		return;
 
+	fbnic_aggregate_ring_rx_counters(fbn, rxr);
+
 	/* Remove pointer to the Rx ring */
 	WARN_ON(fbn->rx[rxr->q_idx] && fbn->rx[rxr->q_idx] != rxr);
 	fbn->rx[rxr->q_idx] = NULL;
@@ -974,6 +1022,7 @@ static int fbnic_alloc_nv_page_pool(struct fbnic_net *fbn,
 static void fbnic_ring_init(struct fbnic_ring *ring, u32 __iomem *doorbell,
 			    int q_idx, u8 flags)
 {
+	u64_stats_init(&ring->stats.syncp);
 	ring->doorbell = doorbell;
 	ring->q_idx = q_idx;
 	ring->flags = flags;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 4a206c0e7192..2f91f68d11d5 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -7,6 +7,7 @@
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
+#include <linux/u64_stats_sync.h>
 #include <net/xdp.h>
 
 struct fbnic_net;
@@ -51,6 +52,13 @@ struct fbnic_pkt_buff {
 	u16 nr_frags;
 };
 
+struct fbnic_queue_stats {
+	u64 packets;
+	u64 bytes;
+	u64 dropped;
+	struct u64_stats_sync syncp;
+};
+
 /* Pagecnt bias is long max to reserve the last bit to catch overflow
  * cases where if we overcharge the bias it will flip over to be negative.
  */
@@ -77,6 +85,8 @@ struct fbnic_ring {
 
 	u32 head, tail;			/* Head/Tail of ring */
 
+	struct fbnic_queue_stats stats;
+
 	/* Slow path fields follow */
 	dma_addr_t dma;			/* Phys addr of descriptor memory */
 	size_t size;			/* Size of descriptor ring in memory */
-- 
cgit v1.3-3-g829e


From 8be1bd91db71fb52be17890586f34cf9403ace89 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Fri, 9 Aug 2024 22:43:22 -0700
Subject: eth: fbnic: add support for basic qstats

Implement netdev_stat_ops and export the basic per-queue stats.

This interface expect users to set the values that are used
either to zero or to some other preserved value (they are 0xff by
default). So here we export bytes/packets/drops from tx and rx_stats
plus set some of the values that are exposed by queue stats
to zero.

  $ cd tools/testing/selftests/drivers/net && ./stats.py
  [...]
  Totals: pass:4 fail:0 xfail:0 xpass:0 skip:0 error:0

Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20240810054322.2766421-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.c | 67 ++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index a048e4a617eb..571374361259 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -4,6 +4,7 @@
 #include <linux/etherdevice.h>
 #include <linux/ipv6.h>
 #include <linux/types.h>
+#include <net/netdev_queues.h>
 
 #include "fbnic.h"
 #include "fbnic_netdev.h"
@@ -395,6 +396,71 @@ static const struct net_device_ops fbnic_netdev_ops = {
 	.ndo_get_stats64	= fbnic_get_stats64,
 };
 
+static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
+				     struct netdev_queue_stats_rx *rx)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_ring *rxr = fbn->rx[idx];
+	struct fbnic_queue_stats *stats;
+	unsigned int start;
+	u64 bytes, packets;
+
+	if (!rxr)
+		return;
+
+	stats = &rxr->stats;
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		bytes = stats->bytes;
+		packets = stats->packets;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+	rx->bytes = bytes;
+	rx->packets = packets;
+}
+
+static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
+				     struct netdev_queue_stats_tx *tx)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_ring *txr = fbn->tx[idx];
+	struct fbnic_queue_stats *stats;
+	unsigned int start;
+	u64 bytes, packets;
+
+	if (!txr)
+		return;
+
+	stats = &txr->stats;
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		bytes = stats->bytes;
+		packets = stats->packets;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+	tx->bytes = bytes;
+	tx->packets = packets;
+}
+
+static void fbnic_get_base_stats(struct net_device *dev,
+				 struct netdev_queue_stats_rx *rx,
+				 struct netdev_queue_stats_tx *tx)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+
+	tx->bytes = fbn->tx_stats.bytes;
+	tx->packets = fbn->tx_stats.packets;
+
+	rx->bytes = fbn->rx_stats.bytes;
+	rx->packets = fbn->rx_stats.packets;
+}
+
+static const struct netdev_stat_ops fbnic_stat_ops = {
+	.get_queue_stats_rx	= fbnic_get_queue_stats_rx,
+	.get_queue_stats_tx	= fbnic_get_queue_stats_tx,
+	.get_base_stats		= fbnic_get_base_stats,
+};
+
 void fbnic_reset_queues(struct fbnic_net *fbn,
 			unsigned int tx, unsigned int rx)
 {
@@ -453,6 +519,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	fbd->netdev = netdev;
 
 	netdev->netdev_ops = &fbnic_netdev_ops;
+	netdev->stat_ops = &fbnic_stat_ops;
 
 	fbn = netdev_priv(netdev);
 
-- 
cgit v1.3-3-g829e


From 246ef40670b71fef0c3e2cd11404279bc6d6468e Mon Sep 17 00:00:00 2001
From: Maciej Żenczykowski <maze@google.com>
Date: Mon, 29 Jul 2024 17:30:10 -0700
Subject: ipv6: eliminate ndisc_ops_is_useropt()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

as it doesn't seem to offer anything of value.

There's only 1 trivial user:
  int lowpan_ndisc_is_useropt(u8 nd_opt_type) {
    return nd_opt_type == ND_OPT_6CO;
  }

but there's no harm to always treating that as
a useropt...

Cc: David Ahern <dsahern@kernel.org>
Cc: YOSHIFUJI Hideaki / 吉藤英明 <yoshfuji@linux-ipv6.org>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Link: https://patch.msgid.link/20240730003010.156977-1-maze@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ndisc.h | 15 ---------------
 net/6lowpan/ndisc.c |  6 ------
 net/ipv6/ndisc.c    |  4 ++--
 3 files changed, 2 insertions(+), 23 deletions(-)

diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 7a533d5b1d59..3c88d5bc5eed 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -147,11 +147,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data,
  * The following hooks can be defined; unless noted otherwise, they are
  * optional and can be filled with a null pointer.
  *
- * int (*is_useropt)(u8 nd_opt_type):
- *     This function is called when IPv6 decide RA userspace options. if
- *     this function returns 1 then the option given by nd_opt_type will
- *     be handled as userspace option additional to the IPv6 options.
- *
  * int (*parse_options)(const struct net_device *dev,
  *			struct nd_opt_hdr *nd_opt,
  *			struct ndisc_options *ndopts):
@@ -200,7 +195,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data,
  *     addresses. E.g. 802.15.4 6LoWPAN.
  */
 struct ndisc_ops {
-	int	(*is_useropt)(u8 nd_opt_type);
 	int	(*parse_options)(const struct net_device *dev,
 				 struct nd_opt_hdr *nd_opt,
 				 struct ndisc_options *ndopts);
@@ -224,15 +218,6 @@ struct ndisc_ops {
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
-static inline int ndisc_ops_is_useropt(const struct net_device *dev,
-				       u8 nd_opt_type)
-{
-	if (dev->ndisc_ops && dev->ndisc_ops->is_useropt)
-		return dev->ndisc_ops->is_useropt(nd_opt_type);
-	else
-		return 0;
-}
-
 static inline int ndisc_ops_parse_options(const struct net_device *dev,
 					  struct nd_opt_hdr *nd_opt,
 					  struct ndisc_options *ndopts)
diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c
index 16be8f8b2f8c..c40b98f7743c 100644
--- a/net/6lowpan/ndisc.c
+++ b/net/6lowpan/ndisc.c
@@ -11,11 +11,6 @@
 
 #include "6lowpan_i.h"
 
-static int lowpan_ndisc_is_useropt(u8 nd_opt_type)
-{
-	return nd_opt_type == ND_OPT_6CO;
-}
-
 #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
 #define NDISC_802154_SHORT_ADDR_LENGTH	1
 static int lowpan_ndisc_parse_802154_options(const struct net_device *dev,
@@ -222,7 +217,6 @@ static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net,
 #endif
 
 const struct ndisc_ops lowpan_ndisc_ops = {
-	.is_useropt		= lowpan_ndisc_is_useropt,
 #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
 	.parse_options		= lowpan_ndisc_parse_options,
 	.update			= lowpan_ndisc_update,
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index b8eec1b6cc2c..1e42e40fb379 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -200,9 +200,9 @@ static inline int ndisc_is_useropt(const struct net_device *dev,
 	return opt->nd_opt_type == ND_OPT_PREFIX_INFO ||
 		opt->nd_opt_type == ND_OPT_RDNSS ||
 		opt->nd_opt_type == ND_OPT_DNSSL ||
+		opt->nd_opt_type == ND_OPT_6CO ||
 		opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
-		opt->nd_opt_type == ND_OPT_PREF64 ||
-		ndisc_ops_is_useropt(dev, opt->nd_opt_type);
+		opt->nd_opt_type == ND_OPT_PREF64;
 }
 
 static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
-- 
cgit v1.3-3-g829e


From 75bab45e6b2da379fe2ebda48ed35f8ce371a2ef Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 7 Aug 2024 16:13:46 +0200
Subject: net: nexthop: Add flag to assert that NHGRP reserved fields are zero

There are many unpatched kernel versions out there that do not initialize
the reserved fields of struct nexthop_grp. The issue with that is that if
those fields were to be used for some end (i.e. stop being reserved), old
kernels would still keep sending random data through the field, and a new
userspace could not rely on the value.

In this patch, use the existing NHA_OP_FLAGS, which is currently inbound
only, to carry flags back to the userspace. Add a flag to indicate that the
reserved fields in struct nexthop_grp are zeroed before dumping. This is
reliant on the actual fix from commit 6d745cd0e972 ("net: nexthop:
Initialize all fields in dumped nexthops").

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/21037748d4f9d8ff486151f4c09083bcf12d5df8.1723036486.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/nexthop.h |  3 +++
 net/ipv4/nexthop.c           | 12 +++++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index dd8787f9cf39..f4f060a87cc2 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -33,6 +33,9 @@ enum {
 #define NHA_OP_FLAG_DUMP_STATS		BIT(0)
 #define NHA_OP_FLAG_DUMP_HW_STATS	BIT(1)
 
+/* Response OP_FLAGS. */
+#define NHA_OP_FLAG_RESP_GRP_RESVD_0	BIT(31)	/* Dump clears resvd fields. */
+
 enum {
 	NHA_UNSPEC,
 	NHA_ID,		/* u32; id for nexthop. id == 0 means auto-assign */
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 6b9787ee8601..23caa13bf24d 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -865,7 +865,7 @@ out:
 }
 
 static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
-			    u32 op_flags)
+			    u32 op_flags, u32 *resp_op_flags)
 {
 	struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
 	struct nexthop_grp *p;
@@ -874,6 +874,8 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
 	u16 group_type = 0;
 	int i;
 
+	*resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0;
+
 	if (nhg->hash_threshold)
 		group_type = NEXTHOP_GRP_TYPE_MPATH;
 	else if (nhg->resilient)
@@ -934,10 +936,12 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh,
 
 	if (nh->is_group) {
 		struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
+		u32 resp_op_flags = 0;
 
 		if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB))
 			goto nla_put_failure;
-		if (nla_put_nh_group(skb, nh, op_flags))
+		if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) ||
+		    nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags))
 			goto nla_put_failure;
 		goto out;
 	}
@@ -1050,7 +1054,9 @@ static size_t nh_nlmsg_size(struct nexthop *nh)
 	sz += nla_total_size(4); /* NHA_ID */
 
 	if (nh->is_group)
-		sz += nh_nlmsg_size_grp(nh);
+		sz += nh_nlmsg_size_grp(nh) +
+		      nla_total_size(4) +	/* NHA_OP_FLAGS */
+		      0;
 	else
 		sz += nh_nlmsg_size_single(nh);
 
-- 
cgit v1.3-3-g829e


From b72a6a7ab9573e06d5c2fcb92eaa28614a735bfd Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 7 Aug 2024 16:13:47 +0200
Subject: net: nexthop: Increase weight to u16

In CLOS networks, as link failures occur at various points in the network,
ECMP weights of the involved nodes are adjusted to compensate. With high
fan-out of the involved nodes, and overall high number of nodes,
a (non-)ECMP weight ratio that we would like to configure does not fit into
8 bits. Instead of, say, 255:254, we might like to configure something like
1000:999. For these deployments, the 8-bit weight may not be enough.

To that end, in this patch increase the next hop weight from u8 to u16.

Increasing the width of an integral type can be tricky, because while the
code still compiles, the types may not check out anymore, and numerical
errors come up. To prevent this, the conversion was done in two steps.
First the type was changed from u8 to a single-member structure, which
invalidated all uses of the field. This allowed going through them one by
one and audit for type correctness. Then the structure was replaced with a
vanilla u16 again. This should ensure that no place was missed.

The UAPI for configuring nexthop group members is that an attribute
NHA_GROUP carries an array of struct nexthop_grp entries:

	struct nexthop_grp {
		__u32	id;	  /* nexthop id - must exist */
		__u8	weight;   /* weight of this nexthop */
		__u8	resvd1;
		__u16	resvd2;
	};

The field resvd1 is currently validated and required to be zero. We can
lift this requirement and carry high-order bits of the weight in the
reserved field:

	struct nexthop_grp {
		__u32	id;	  /* nexthop id - must exist */
		__u8	weight;   /* weight of this nexthop */
		__u8	weight_high;
		__u16	resvd2;
	};

Keeping the fields split this way was chosen in case an existing userspace
makes assumptions about the width of the weight field, and to sidestep any
endianness issues.

The weight field is currently encoded as the weight value minus one,
because weight of 0 is invalid. This same trick is impossible for the new
weight_high field, because zero must mean actual zero. With this in place:

- Old userspace is guaranteed to carry weight_high of 0, therefore
  configuring 8-bit weights as appropriate. When dumping nexthops with
  16-bit weight, it would only show the lower 8 bits. But configuring such
  nexthops implies existence of userspace aware of the extension in the
  first place.

- New userspace talking to an old kernel will work as long as it only
  attempts to configure 8-bit weights, where the high-order bits are zero.
  Old kernel will bounce attempts at configuring >8-bit weights.

Renaming reserved fields as they are allocated for some purpose is commonly
done in Linux. Whoever touches a reserved field is doing so at their own
risk. nexthop_grp::resvd1 in particular is currently used by at least
strace, however they carry an own copy of UAPI headers, and the conversion
should be trivial. A helper is provided for decoding the weight out of the
two fields. Forcing a conversion seems preferable to bending backwards and
introducing anonymous unions or whatever.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/483e2fcf4beb0d9135d62e7d27b46fa2685479d4.1723036486.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/nexthop.h        |  4 ++--
 include/uapi/linux/nexthop.h |  7 ++++++-
 net/ipv4/nexthop.c           | 37 +++++++++++++++++++++++--------------
 3 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/include/net/nexthop.h b/include/net/nexthop.h
index 68463aebcc05..d9fb44e8b321 100644
--- a/include/net/nexthop.h
+++ b/include/net/nexthop.h
@@ -105,7 +105,7 @@ struct nh_grp_entry_stats {
 struct nh_grp_entry {
 	struct nexthop	*nh;
 	struct nh_grp_entry_stats __percpu	*stats;
-	u8		weight;
+	u16		weight;
 
 	union {
 		struct {
@@ -192,7 +192,7 @@ struct nh_notifier_single_info {
 };
 
 struct nh_notifier_grp_entry_info {
-	u8 weight;
+	u16 weight;
 	struct nh_notifier_single_info nh;
 };
 
diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h
index f4f060a87cc2..bc49baf4a267 100644
--- a/include/uapi/linux/nexthop.h
+++ b/include/uapi/linux/nexthop.h
@@ -16,10 +16,15 @@ struct nhmsg {
 struct nexthop_grp {
 	__u32	id;	  /* nexthop id - must exist */
 	__u8	weight;   /* weight of this nexthop */
-	__u8	resvd1;
+	__u8	weight_high;	/* high order bits of weight */
 	__u16	resvd2;
 };
 
+static inline __u16 nexthop_grp_weight(const struct nexthop_grp *entry)
+{
+	return ((entry->weight_high << 8) | entry->weight) + 1;
+}
+
 enum {
 	NEXTHOP_GRP_TYPE_MPATH,  /* hash-threshold nexthop group
 				  * default type if not specified
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 23caa13bf24d..9db10d409074 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -872,6 +872,7 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
 	size_t len = nhg->num_nh * sizeof(*p);
 	struct nlattr *nla;
 	u16 group_type = 0;
+	u16 weight;
 	int i;
 
 	*resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0;
@@ -890,9 +891,12 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
 
 	p = nla_data(nla);
 	for (i = 0; i < nhg->num_nh; ++i) {
+		weight = nhg->nh_entries[i].weight - 1;
+
 		*p++ = (struct nexthop_grp) {
 			.id = nhg->nh_entries[i].nh->id,
-			.weight = nhg->nh_entries[i].weight - 1,
+			.weight = weight,
+			.weight_high = weight >> 8,
 		};
 	}
 
@@ -1286,11 +1290,14 @@ static int nh_check_attr_group(struct net *net,
 
 	nhg = nla_data(tb[NHA_GROUP]);
 	for (i = 0; i < len; ++i) {
-		if (nhg[i].resvd1 || nhg[i].resvd2) {
-			NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0");
+		if (nhg[i].resvd2) {
+			NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0");
 			return -EINVAL;
 		}
-		if (nhg[i].weight > 254) {
+		if (nexthop_grp_weight(&nhg[i]) == 0) {
+			/* 0xffff got passed in, representing weight of 0x10000,
+			 * which is too heavy.
+			 */
 			NL_SET_ERR_MSG(extack, "Invalid value for weight");
 			return -EINVAL;
 		}
@@ -1886,9 +1893,9 @@ static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table)
 static void nh_res_group_rebalance(struct nh_group *nhg,
 				   struct nh_res_table *res_table)
 {
-	int prev_upper_bound = 0;
-	int total = 0;
-	int w = 0;
+	u16 prev_upper_bound = 0;
+	u32 total = 0;
+	u32 w = 0;
 	int i;
 
 	INIT_LIST_HEAD(&res_table->uw_nh_entries);
@@ -1898,11 +1905,12 @@ static void nh_res_group_rebalance(struct nh_group *nhg,
 
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
-		int upper_bound;
+		u16 upper_bound;
+		u64 btw;
 
 		w += nhge->weight;
-		upper_bound = DIV_ROUND_CLOSEST(res_table->num_nh_buckets * w,
-						total);
+		btw = ((u64)res_table->num_nh_buckets) * w;
+		upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total);
 		nhge->res.wants_buckets = upper_bound - prev_upper_bound;
 		prev_upper_bound = upper_bound;
 
@@ -1968,8 +1976,8 @@ static void replace_nexthop_grp_res(struct nh_group *oldg,
 
 static void nh_hthr_group_rebalance(struct nh_group *nhg)
 {
-	int total = 0;
-	int w = 0;
+	u32 total = 0;
+	u32 w = 0;
 	int i;
 
 	for (i = 0; i < nhg->num_nh; ++i)
@@ -1977,7 +1985,7 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg)
 
 	for (i = 0; i < nhg->num_nh; ++i) {
 		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
-		int upper_bound;
+		u32 upper_bound;
 
 		w += nhge->weight;
 		upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1;
@@ -2719,7 +2727,8 @@ static struct nexthop *nexthop_create_group(struct net *net,
 			goto out_no_nh;
 		}
 		nhg->nh_entries[i].nh = nhe;
-		nhg->nh_entries[i].weight = entry[i].weight + 1;
+		nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]);
+
 		list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list);
 		nhg->nh_entries[i].nh_parent = nh;
 	}
-- 
cgit v1.3-3-g829e


From 110d3ffe9d2b42c04faaf92c3fc627004e3328c6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 7 Aug 2024 16:13:48 +0200
Subject: selftests: router_mpath: Sleep after MZ

In the context of an offloaded datapath, it may take a while for the ip
link stats to be updated. This causes the test to fail when MZ_DELAY is too
low. Sleep after the packets are sent for the link stats to get up to date.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/8b1971d948273afd7de2da3d6a2ba35200540e55.1723036486.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/router_mpath_nh.sh     | 2 ++
 tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh | 2 ++
 tools/testing/selftests/net/forwarding/router_multipath.sh    | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index 2ba44247c60a..c5a30f8f55b5 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -243,6 +243,7 @@ multipath4_test()
 
 	ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
 		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
 	t1_rp13=$(link_stats_tx_packets_get $rp13)
@@ -276,6 +277,7 @@ multipath6_test()
 
 	$MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
 		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
 	t1_rp13=$(link_stats_tx_packets_get $rp13)
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
index cd9e346436fc..bd35fe8be9aa 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
@@ -244,6 +244,7 @@ multipath4_test()
 
 	ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
 		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
 	t1_rp13=$(link_stats_tx_packets_get $rp13)
@@ -274,6 +275,7 @@ multipath6_l4_test()
 
 	$MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
 		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
 	t1_rp13=$(link_stats_tx_packets_get $rp13)
diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh
index e2be354167a1..46f365b557b7 100755
--- a/tools/testing/selftests/net/forwarding/router_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/router_multipath.sh
@@ -180,6 +180,7 @@ multipath4_test()
 
        ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
 	       -d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+       sleep 1
 
        t1_rp12=$(link_stats_tx_packets_get $rp12)
        t1_rp13=$(link_stats_tx_packets_get $rp13)
@@ -217,6 +218,7 @@ multipath6_test()
 
        $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
 	       -d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+       sleep 1
 
        t1_rp12=$(link_stats_tx_packets_get $rp12)
        t1_rp13=$(link_stats_tx_packets_get $rp13)
-- 
cgit v1.3-3-g829e


From bb89fdacf99ccbec4dfe2d04f76f870f1483d3ea Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 7 Aug 2024 16:13:49 +0200
Subject: selftests: router_mpath_nh: Test 16-bit next hop weights

Add tests that exercise full 16 bits of NH weight.

To test the 255:65535, it is necessary to run more packets than for the
other tests. On a debug kernel, the test can take up to a minute, therefore
avoid the test when KSFT_MACHINE_SLOW.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/c0c257c00ad30b07afc3fa5e2afd135925405544.1723036486.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/lib.sh      |  7 ++++
 .../selftests/net/forwarding/router_mpath_nh.sh    | 38 +++++++++++++++++-----
 .../net/forwarding/router_mpath_nh_lib.sh          | 13 ++++++++
 3 files changed, 50 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ff96bb7535ff..cb0fcd6f0293 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -509,6 +509,13 @@ xfail_on_slow()
 	fi
 }
 
+omit_on_slow()
+{
+	if [[ $KSFT_MACHINE_SLOW != yes ]]; then
+		"$@"
+	fi
+}
+
 xfail_on_veth()
 {
 	local dev=$1; shift
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index c5a30f8f55b5..a7d8399c8d4f 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -40,6 +40,7 @@ ALL_TESTS="
 	ping_ipv4
 	ping_ipv6
 	multipath_test
+	multipath16_test
 	ping_ipv4_blackhole
 	ping_ipv6_blackhole
 	nh_stats_test_v4
@@ -226,9 +227,11 @@ routing_nh_obj()
 
 multipath4_test()
 {
-	local desc="$1"
-	local weight_rp12=$2
-	local weight_rp13=$3
+	local desc=$1; shift
+	local weight_rp12=$1; shift
+	local weight_rp13=$1; shift
+	local ports=${1-sp=1024,dp=0-32768}; shift
+
 	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
 	local packets_rp12 packets_rp13
 
@@ -242,7 +245,7 @@ multipath4_test()
 	t0_rp13=$(link_stats_tx_packets_get $rp13)
 
 	ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
-		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+		-d $MZ_DELAY -t udp "$ports"
 	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
@@ -259,9 +262,11 @@ multipath4_test()
 
 multipath6_test()
 {
-	local desc="$1"
-	local weight_rp12=$2
-	local weight_rp13=$3
+	local desc=$1; shift
+	local weight_rp12=$1; shift
+	local weight_rp13=$1; shift
+	local ports=${1-sp=1024,dp=0-32768}; shift
+
 	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
 	local packets_rp12 packets_rp13
 
@@ -276,7 +281,7 @@ multipath6_test()
 	t0_rp13=$(link_stats_tx_packets_get $rp13)
 
 	$MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
-		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+		-d $MZ_DELAY -t udp "$ports"
 	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
@@ -315,6 +320,23 @@ multipath_test()
 	multipath6_test "Weighted MP 11:45" 11 45
 }
 
+multipath16_test()
+{
+	check_nhgw16 104 || return
+
+	log_info "Running 16-bit IPv4 multipath tests"
+	multipath4_test "65535:65535" 65535 65535
+	multipath4_test "128:512" 128 512
+	omit_on_slow \
+		multipath4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535
+
+	log_info "Running 16-bit IPv6 multipath tests"
+	multipath6_test "65535:65535" 65535 65535
+	multipath6_test "128:512" 128 512
+	omit_on_slow \
+		multipath6_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535
+}
+
 ping_ipv4_blackhole()
 {
 	RET=0
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh
index 2903294d8bca..507b2852dabe 100644
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh
@@ -117,3 +117,16 @@ __nh_stats_test_v6()
 			       $MZ -6 $h1 -A 2001:db8:1::2 -B 2001:db8:2::2
 	sysctl_restore net.ipv6.fib_multipath_hash_policy
 }
+
+check_nhgw16()
+{
+	local nhid=$1; shift
+
+	ip nexthop replace id 9999 group "$nhid,65535" &>/dev/null
+	if (( $? )); then
+		log_test_skip "16-bit multipath tests" \
+			      "iproute2 or the kernel do not support 16-bit next hop weights"
+		return 1
+	fi
+	ip nexthop del id 9999 ||:
+}
-- 
cgit v1.3-3-g829e


From dce0765c1d5bf810bf3cd8e66cf7f6e73d14d7e2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 7 Aug 2024 16:13:50 +0200
Subject: selftests: router_mpath_nh_res: Test 16-bit next hop weights

Add tests that exercise full 16 bits of NH weight.

Like in the previous patch, omit the 255:65535 test when KSFT_MACHINE_SLOW.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/a91d6ead9d1b1b4b7e276ca58a71ef814f42b7dd.1723036486.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/forwarding/router_mpath_nh_res.sh          | 56 ++++++++++++++++++----
 1 file changed, 48 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
index bd35fe8be9aa..88ddae05b39d 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh
@@ -40,6 +40,7 @@ ALL_TESTS="
 	ping_ipv4
 	ping_ipv6
 	multipath_test
+	multipath16_test
 	nh_stats_test_v4
 	nh_stats_test_v6
 "
@@ -228,9 +229,11 @@ routing_nh_obj()
 
 multipath4_test()
 {
-	local desc="$1"
-	local weight_rp12=$2
-	local weight_rp13=$3
+	local desc=$1; shift
+	local weight_rp12=$1; shift
+	local weight_rp13=$1; shift
+	local ports=${1-sp=1024,dp=0-32768}; shift
+
 	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
 	local packets_rp12 packets_rp13
 
@@ -243,7 +246,7 @@ multipath4_test()
 	t0_rp13=$(link_stats_tx_packets_get $rp13)
 
 	ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \
-		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+		-d $MZ_DELAY -t udp "$ports"
 	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
@@ -259,9 +262,11 @@ multipath4_test()
 
 multipath6_l4_test()
 {
-	local desc="$1"
-	local weight_rp12=$2
-	local weight_rp13=$3
+	local desc=$1; shift
+	local weight_rp12=$1; shift
+	local weight_rp13=$1; shift
+	local ports=${1-sp=1024,dp=0-32768}; shift
+
 	local t0_rp12 t0_rp13 t1_rp12 t1_rp13
 	local packets_rp12 packets_rp13
 
@@ -274,7 +279,7 @@ multipath6_l4_test()
 	t0_rp13=$(link_stats_tx_packets_get $rp13)
 
 	$MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \
-		-d $MZ_DELAY -t udp "sp=1024,dp=0-32768"
+		-d $MZ_DELAY -t udp "$ports"
 	sleep 1
 
 	t1_rp12=$(link_stats_tx_packets_get $rp12)
@@ -373,6 +378,41 @@ multipath_test()
 	ip nexthop replace id 106 group 104,1/105,1 type resilient
 }
 
+multipath16_test()
+{
+	check_nhgw16 104 || return
+
+	log_info "Running 16-bit IPv4 multipath tests"
+	ip nexthop replace id 103 group 101/102 type resilient idle_timer 0
+
+	ip nexthop replace id 103 group 101,65535/102,65535 type resilient
+	multipath4_test "65535:65535" 65535 65535
+
+	ip nexthop replace id 103 group 101,128/102,512 type resilient
+	multipath4_test "128:512" 128 512
+
+	ip nexthop replace id 103 group 101,255/102,65535 type resilient
+	omit_on_slow \
+		multipath4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535
+
+	ip nexthop replace id 103 group 101,1/102,1 type resilient
+
+	log_info "Running 16-bit IPv6 L4 hash multipath tests"
+	ip nexthop replace id 106 group 104/105 type resilient idle_timer 0
+
+	ip nexthop replace id 106 group 104,65535/105,65535 type resilient
+	multipath6_l4_test "65535:65535" 65535 65535
+
+	ip nexthop replace id 106 group 104,128/105,512 type resilient
+	multipath6_l4_test "128:512" 128 512
+
+	ip nexthop replace id 106 group 104,255/105,65535 type resilient
+	omit_on_slow \
+		multipath6_l4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535
+
+	ip nexthop replace id 106 group 104,1/105,1 type resilient
+}
+
 nh_stats_test_v4()
 {
 	__nh_stats_test_v4 resilient
-- 
cgit v1.3-3-g829e


From 4b808f44733243f981ae04046ef93a65ecc631a9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 7 Aug 2024 16:13:51 +0200
Subject: selftests: fib_nexthops: Test 16-bit next hop weights

Add tests that attempt to create NH groups that use full 16 bits of NH
weight.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/101cdd3f2bfd9511c9bec95f909d20ff56f70ba5.1723036486.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_nexthops.sh | 55 ++++++++++++++++++++++++++++-
 1 file changed, 54 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index ac0b2c6a5761..77c83d9508d3 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -78,7 +78,12 @@ log_test()
 	else
 		ret=1
 		nfail=$((nfail+1))
-		printf "TEST: %-60s  [FAIL]\n" "${msg}"
+		if [[ $rc -eq $ksft_skip ]]; then
+			printf "TEST: %-60s  [SKIP]\n" "${msg}"
+		else
+			printf "TEST: %-60s  [FAIL]\n" "${msg}"
+		fi
+
 		if [ "$VERBOSE" = "1" ]; then
 			echo "    rc=$rc, expected $expected"
 		fi
@@ -923,6 +928,29 @@ ipv6_grp_fcnal()
 
 	ipv6_grp_refs
 	log_test $? 0 "Nexthop group replace refcounts"
+
+	#
+	# 16-bit weights.
+	#
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1"
+	run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 dev veth1"
+	run_cmd "$IP nexthop add id 66 dev veth1"
+
+	run_cmd "$IP nexthop add id 103 group 62,1000"
+	if [[ $? == 0 ]]; then
+		local GRP="id 103 group 62,254/63,255/64,256/65,257/66,65535"
+		run_cmd "$IP nexthop replace $GRP"
+		check_nexthop "id 103" "$GRP"
+		rc=$?
+	else
+		rc=$ksft_skip
+	fi
+
+	$IP nexthop flush >/dev/null 2>&1
+
+	log_test $rc 0 "16-bit weights"
 }
 
 ipv6_res_grp_fcnal()
@@ -987,6 +1015,31 @@ ipv6_res_grp_fcnal()
 	check_nexthop_bucket "list id 102" \
 		"id 102 index 0 nhid 63 id 102 index 1 nhid 62 id 102 index 2 nhid 62 id 102 index 3 nhid 62"
 	log_test $? 0 "Nexthop buckets updated after replace - nECMP"
+
+	#
+	# 16-bit weights.
+	#
+	run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1"
+	run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1"
+	run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1"
+	run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 dev veth1"
+	run_cmd "$IP nexthop add id 66 dev veth1"
+
+	run_cmd "$IP nexthop add id 103 group 62,1000 type resilient buckets 32"
+	if [[ $? == 0 ]]; then
+		local GRP="id 103 group 62,254/63,255/64,256/65,257/66,65535 $(:
+			  )type resilient buckets 32 idle_timer 0 $(:
+			  )unbalanced_timer 0"
+		run_cmd "$IP nexthop replace $GRP"
+		check_nexthop "id 103" "$GRP unbalanced_time 0"
+		rc=$?
+	else
+		rc=$ksft_skip
+	fi
+
+	$IP nexthop flush >/dev/null 2>&1
+
+	log_test $rc 0 "16-bit weights"
 }
 
 ipv6_fcnal_runtime()
-- 
cgit v1.3-3-g829e


From e2d0fadd703c3a3a6ebe318ec82ea64c08d709c2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 9 Aug 2024 09:22:12 -0600
Subject: sched: act_ct: avoid -Wflex-array-member-not-at-end warning

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Remove unnecessary flex-array member `pad[]` and refactor the related
code a bit.

Fix the following warning:
net/sched/act_ct.c:57:29: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/ZrY0JMVsImbDbx6r@cute
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/act_ct.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index 3ba8e7e739b5..2197eb625658 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -44,8 +44,6 @@ static DEFINE_MUTEX(zones_mutex);
 struct zones_ht_key {
 	struct net *net;
 	u16 zone;
-	/* Note : pad[] must be the last field. */
-	u8  pad[];
 };
 
 struct tcf_ct_flow_table {
@@ -62,7 +60,7 @@ struct tcf_ct_flow_table {
 static const struct rhashtable_params zones_params = {
 	.head_offset = offsetof(struct tcf_ct_flow_table, node),
 	.key_offset = offsetof(struct tcf_ct_flow_table, key),
-	.key_len = offsetof(struct zones_ht_key, pad),
+	.key_len = offsetofend(struct zones_ht_key, zone),
 	.automatic_shrinking = true,
 };
 
-- 
cgit v1.3-3-g829e


From 46dd90fe51f3556deaf5af47aafcee10536a3978 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 8 Aug 2024 16:08:35 -0600
Subject: nfp: Use static_assert() to check struct sizes

Commit d88cabfd9abc ("nfp: Avoid -Wflex-array-member-not-at-end
warnings") introduced tagged `struct nfp_dump_tl_hdr`. We want
to ensure that when new members need to be added to the flexible
structure, they are always included within this tagged struct.

So, we use `static_assert()` to ensure that the memory layout for
both the flexible structure and the tagged struct is the same after
any changes.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/ZrVB43Hen0H5WQFP@cute
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c
index 2dd37557185e..7276e44a21d0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c
@@ -41,6 +41,8 @@ struct nfp_dump_tl {
 	);
 	char data[];
 };
+static_assert(offsetof(struct nfp_dump_tl, data) == sizeof(struct nfp_dump_tl_hdr),
+	      "struct member likely outside of struct_group_tagged()");
 
 /* NFP CPP parameters */
 struct nfp_dumpspec_cpp_isl_id {
-- 
cgit v1.3-3-g829e


From 0a3e6939d4b33d68bce89477b9db01d68b744749 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 8 Aug 2024 16:07:54 -0600
Subject: net/smc: Use static_assert() to check struct sizes

Commit 9748dbc9f265 ("net/smc: Avoid -Wflex-array-member-not-at-end
warnings") introduced tagged `struct smc_clc_v2_extension_fixed` and
`struct smc_clc_smcd_v2_extension_fixed`. We want to ensure that when
new members need to be added to the flexible structures, they are
always included within these tagged structs.

So, we use `static_assert()` to ensure that the memory layout for
both the flexible structure and the tagged struct is the same after
any changes.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Link: https://patch.msgid.link/ZrVBuiqFHAORpFxE@cute
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/smc/smc_clc.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 467effb50cd6..5625fda2960b 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -145,6 +145,8 @@ struct smc_clc_v2_extension {
 	);
 	u8 user_eids[][SMC_MAX_EID_LEN];
 };
+static_assert(offsetof(struct smc_clc_v2_extension, user_eids) == sizeof(struct smc_clc_v2_extension_fixed),
+	      "struct member likely outside of struct_group_tagged()");
 
 struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 	__be32 outgoing_subnet;	/* subnet mask */
@@ -169,6 +171,8 @@ struct smc_clc_smcd_v2_extension {
 	);
 	struct smc_clc_smcd_gid_chid gidchid[];
 };
+static_assert(offsetof(struct smc_clc_smcd_v2_extension, gidchid) == sizeof(struct smc_clc_smcd_v2_extension_fixed),
+	      "struct member likely outside of struct_group_tagged()");
 
 struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 	struct smc_clc_msg_hdr hdr;
-- 
cgit v1.3-3-g829e


From 12dbc67c3b0bcd7414b511fd8a42ba4e388705bc Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:45:28 +0800
Subject: net: stmmac: Move the atds flag to the stmmac_dma_cfg structure

ATDS (Alternate Descriptor Size) is a part of the DMA Bus Mode configs
(together with PBL, ALL, EME, etc) of the DW GMAC controllers. Seeing
it's not changed at runtime but is activated as long as the IP-core
has it supported (at least due to the Type 2 Full Checksum Offload
Engine feature), move the respective parameter from the
stmmac_dma_ops::init() callback argument to the stmmac_dma_cfg
structure, which already have the rest of the DMA-related configs
defined.

Besides the being added in the next commit DW GMAC multi-channels
support will require to add the stmmac_dma_ops::init_chan() callback
and have the ATDS flag set/cleared for each channel in there. Having
the atds-flag in the stmmac_dma_cfg structure will make the parameter
accessible from stmmac_dma_ops::init_chan() callback too.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c   | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c  | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c    | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c  | 2 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h          | 3 +--
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c   | 5 ++---
 include/linux/stmmac.h                              | 1 +
 8 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index e1b761dcfa1d..d87079016952 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -299,7 +299,7 @@ static int sun8i_dwmac_dma_reset(void __iomem *ioaddr)
  * Called from stmmac via stmmac_dma_ops->init
  */
 static void sun8i_dwmac_dma_init(void __iomem *ioaddr,
-				 struct stmmac_dma_cfg *dma_cfg, int atds)
+				 struct stmmac_dma_cfg *dma_cfg)
 {
 	writel(EMAC_RX_INT | EMAC_TX_INT, ioaddr + EMAC_INT_EN);
 	writel(0x1FFFFFF, ioaddr + EMAC_INT_STA);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index adccdd816ea9..984b809105af 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -71,7 +71,7 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 }
 
 static void dwmac1000_dma_init(void __iomem *ioaddr,
-			       struct stmmac_dma_cfg *dma_cfg, int atds)
+			       struct stmmac_dma_cfg *dma_cfg)
 {
 	u32 value = readl(ioaddr + DMA_BUS_MODE);
 	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
@@ -98,7 +98,7 @@ static void dwmac1000_dma_init(void __iomem *ioaddr,
 	if (dma_cfg->mixed_burst)
 		value |= DMA_BUS_MODE_MB;
 
-	if (atds)
+	if (dma_cfg->atds)
 		value |= DMA_BUS_MODE_ATDS;
 
 	if (dma_cfg->aal)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index b402fb54f613..82957db47c99 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -19,7 +19,7 @@
 #include "dwmac_dma.h"
 
 static void dwmac100_dma_init(void __iomem *ioaddr,
-			      struct stmmac_dma_cfg *dma_cfg, int atds)
+			      struct stmmac_dma_cfg *dma_cfg)
 {
 	/* Enable Application Access by writing to DMA CSR0 */
 	writel(DMA_BUS_MODE_DEFAULT | (dma_cfg->pbl << DMA_BUS_MODE_PBL_SHIFT),
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 84d3a8551b03..e0165358c4ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -153,7 +153,7 @@ static void dwmac410_dma_init_channel(struct stmmac_priv *priv,
 }
 
 static void dwmac4_dma_init(void __iomem *ioaddr,
-			    struct stmmac_dma_cfg *dma_cfg, int atds)
+			    struct stmmac_dma_cfg *dma_cfg)
 {
 	u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index dd2ab6185c40..7840bc403788 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -20,7 +20,7 @@ static int dwxgmac2_dma_reset(void __iomem *ioaddr)
 }
 
 static void dwxgmac2_dma_init(void __iomem *ioaddr,
-			      struct stmmac_dma_cfg *dma_cfg, int atds)
+			      struct stmmac_dma_cfg *dma_cfg)
 {
 	u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index e53c32362774..1c99c99f4627 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -175,8 +175,7 @@ struct dma_features;
 struct stmmac_dma_ops {
 	/* DMA core initialization */
 	int (*reset)(void __iomem *ioaddr);
-	void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
-		     int atds);
+	void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg);
 	void (*init_chan)(struct stmmac_priv *priv, void __iomem *ioaddr,
 			  struct stmmac_dma_cfg *dma_cfg, u32 chan);
 	void (*init_rx_chan)(struct stmmac_priv *priv, void __iomem *ioaddr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index f3a1b179aaea..9f1286835550 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3003,7 +3003,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	struct stmmac_rx_queue *rx_q;
 	struct stmmac_tx_queue *tx_q;
 	u32 chan = 0;
-	int atds = 0;
 	int ret = 0;
 
 	if (!priv->plat->dma_cfg || !priv->plat->dma_cfg->pbl) {
@@ -3012,7 +3011,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	}
 
 	if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE))
-		atds = 1;
+		priv->plat->dma_cfg->atds = 1;
 
 	ret = stmmac_reset(priv, priv->ioaddr);
 	if (ret) {
@@ -3021,7 +3020,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	}
 
 	/* DMA Configuration */
-	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
+	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg);
 
 	if (priv->plat->axi)
 		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 84e13bd5df28..338991c08f00 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -100,6 +100,7 @@ struct stmmac_dma_cfg {
 	bool eame;
 	bool multi_msi_en;
 	bool dche;
+	bool atds;
 };
 
 #define AXI_BLEN	7
-- 
cgit v1.3-3-g829e


From ad72f783de06827a1f20d7df57ca52ee102a6faf Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:45:29 +0800
Subject: net: stmmac: Add multi-channel support

DW GMAC v3.73 can be equipped with the Audio Video (AV) feature which
enables transmission of time-sensitive traffic over bridged local area
networks (DWC Ethernet QoS Product). In that case there can be up to two
additional DMA-channels available with no Tx COE support (unless there is
vendor-specific IP-core alterations). Each channel is implemented as a
separate Control and Status register (CSR) for managing the transmit and
receive functions, descriptor handling, and interrupt handling.

Add the multi-channels DW GMAC controllers support just by making sure the
already implemented DMA-configs are performed on the per-channel basis.

Note the only currently known instance of the multi-channel DW GMAC
IP-core is the LS2K2000 GNET controller, which has been released with the
vendor-specific feature extension of having eight DMA-channels. The device
support will be added in one of the following up commits.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c  |  2 +-
 .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c    | 32 ++++++++++++----------
 drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h    | 27 +++++++++++++++++-
 drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c    | 30 ++++++++++----------
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |  2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 14 ++++++----
 6 files changed, 68 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index d87079016952..cc93f73a380e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -395,7 +395,7 @@ static void sun8i_dwmac_dma_start_tx(struct stmmac_priv *priv,
 	writel(v, ioaddr + EMAC_TX_CTL1);
 }
 
-static void sun8i_dwmac_enable_dma_transmission(void __iomem *ioaddr)
+static void sun8i_dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan)
 {
 	u32 v;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index 984b809105af..b3d7eff53b18 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -70,15 +70,17 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 	writel(value, ioaddr + DMA_AXI_BUS_MODE);
 }
 
-static void dwmac1000_dma_init(void __iomem *ioaddr,
-			       struct stmmac_dma_cfg *dma_cfg)
+static void dwmac1000_dma_init_channel(struct stmmac_priv *priv,
+				       void __iomem *ioaddr,
+				       struct stmmac_dma_cfg *dma_cfg, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_BUS_MODE);
 	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
 	int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 value;
 
-	/*
-	 * Set the DMA PBL (Programmable Burst Length) mode.
+	value = readl(ioaddr + DMA_CHAN_BUS_MODE(chan));
+
+	/* Set the DMA PBL (Programmable Burst Length) mode.
 	 *
 	 * Note: before stmmac core 3.50 this mode bit was 4xPBL, and
 	 * post 3.5 mode bit acts as 8*PBL.
@@ -104,10 +106,10 @@ static void dwmac1000_dma_init(void __iomem *ioaddr,
 	if (dma_cfg->aal)
 		value |= DMA_BUS_MODE_AAL;
 
-	writel(value, ioaddr + DMA_BUS_MODE);
+	writel(value, ioaddr + DMA_CHAN_BUS_MODE(chan));
 
 	/* Mask interrupts by writing to CSR7 */
-	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
+	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 static void dwmac1000_dma_init_rx(struct stmmac_priv *priv,
@@ -116,7 +118,7 @@ static void dwmac1000_dma_init_rx(struct stmmac_priv *priv,
 				  dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* RX descriptor base address list must be written into DMA CSR3 */
-	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_CHAN_RCV_BASE_ADDR(chan));
 }
 
 static void dwmac1000_dma_init_tx(struct stmmac_priv *priv,
@@ -125,7 +127,7 @@ static void dwmac1000_dma_init_tx(struct stmmac_priv *priv,
 				  dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* TX descriptor base address list must be written into DMA CSR4 */
-	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
 }
 
 static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)
@@ -153,7 +155,7 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv,
 					    void __iomem *ioaddr, int mode,
 					    u32 channel, int fifosz, u8 qmode)
 {
-	u32 csr6 = readl(ioaddr + DMA_CONTROL);
+	u32 csr6 = readl(ioaddr + DMA_CHAN_CONTROL(channel));
 
 	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable RX store and forward mode\n");
@@ -175,14 +177,14 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv,
 	/* Configure flow control based on rx fifo size */
 	csr6 = dwmac1000_configure_fc(csr6, fifosz);
 
-	writel(csr6, ioaddr + DMA_CONTROL);
+	writel(csr6, ioaddr + DMA_CHAN_CONTROL(channel));
 }
 
 static void dwmac1000_dma_operation_mode_tx(struct stmmac_priv *priv,
 					    void __iomem *ioaddr, int mode,
 					    u32 channel, int fifosz, u8 qmode)
 {
-	u32 csr6 = readl(ioaddr + DMA_CONTROL);
+	u32 csr6 = readl(ioaddr + DMA_CHAN_CONTROL(channel));
 
 	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable TX store and forward mode\n");
@@ -209,7 +211,7 @@ static void dwmac1000_dma_operation_mode_tx(struct stmmac_priv *priv,
 			csr6 |= DMA_CONTROL_TTC_256;
 	}
 
-	writel(csr6, ioaddr + DMA_CONTROL);
+	writel(csr6, ioaddr + DMA_CHAN_CONTROL(channel));
 }
 
 static void dwmac1000_dump_dma_regs(struct stmmac_priv *priv,
@@ -271,12 +273,12 @@ static int dwmac1000_get_hw_feature(void __iomem *ioaddr,
 static void dwmac1000_rx_watchdog(struct stmmac_priv *priv,
 				  void __iomem *ioaddr, u32 riwt, u32 queue)
 {
-	writel(riwt, ioaddr + DMA_RX_WATCHDOG);
+	writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(queue));
 }
 
 const struct stmmac_dma_ops dwmac1000_dma_ops = {
 	.reset = dwmac_dma_reset,
-	.init = dwmac1000_dma_init,
+	.init_chan = dwmac1000_dma_init_channel,
 	.init_rx_chan = dwmac1000_dma_init_rx,
 	.init_tx_chan = dwmac1000_dma_init_tx,
 	.axi = dwmac1000_dma_axi,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 72672391675f..5d9c18f5bbf5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -22,6 +22,31 @@
 #define DMA_INTR_ENA		0x0000101c	/* Interrupt Enable */
 #define DMA_MISSED_FRAME_CTR	0x00001020	/* Missed Frame Counter */
 
+/* Following DMA defines are channels oriented */
+#define DMA_CHAN_BASE_OFFSET			0x100
+
+static inline u32 dma_chan_base_addr(u32 base, u32 chan)
+{
+	return base + chan * DMA_CHAN_BASE_OFFSET;
+}
+
+#define DMA_CHAN_BUS_MODE(chan)	dma_chan_base_addr(DMA_BUS_MODE, chan)
+#define DMA_CHAN_XMT_POLL_DEMAND(chan)	\
+				dma_chan_base_addr(DMA_XMT_POLL_DEMAND, chan)
+#define DMA_CHAN_RCV_POLL_DEMAND(chan)	\
+				dma_chan_base_addr(DMA_RCV_POLL_DEMAND, chan)
+#define DMA_CHAN_RCV_BASE_ADDR(chan)	\
+				dma_chan_base_addr(DMA_RCV_BASE_ADDR, chan)
+#define DMA_CHAN_TX_BASE_ADDR(chan)	\
+				dma_chan_base_addr(DMA_TX_BASE_ADDR, chan)
+#define DMA_CHAN_STATUS(chan)	dma_chan_base_addr(DMA_STATUS, chan)
+#define DMA_CHAN_CONTROL(chan)	dma_chan_base_addr(DMA_CONTROL, chan)
+#define DMA_CHAN_INTR_ENA(chan)	dma_chan_base_addr(DMA_INTR_ENA, chan)
+#define DMA_CHAN_MISSED_FRAME_CTR(chan)	\
+				dma_chan_base_addr(DMA_MISSED_FRAME_CTR, chan)
+#define DMA_CHAN_RX_WATCHDOG(chan)	\
+				dma_chan_base_addr(DMA_RX_WATCHDOG, chan)
+
 /* SW Reset */
 #define DMA_BUS_MODE_SFT_RESET	0x00000001	/* Software Reset */
 
@@ -152,7 +177,7 @@
 #define NUM_DWMAC1000_DMA_REGS	23
 #define NUM_DWMAC4_DMA_REGS	27
 
-void dwmac_enable_dma_transmission(void __iomem *ioaddr);
+void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan);
 void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
 			  u32 chan, bool rx, bool tx);
 void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
index 85e18f9a22f9..4846bf49c576 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -28,65 +28,65 @@ int dwmac_dma_reset(void __iomem *ioaddr)
 }
 
 /* CSR1 enables the transmit DMA to check for new descriptor */
-void dwmac_enable_dma_transmission(void __iomem *ioaddr)
+void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan)
 {
-	writel(1, ioaddr + DMA_XMT_POLL_DEMAND);
+	writel(1, ioaddr + DMA_CHAN_XMT_POLL_DEMAND(chan));
 }
 
 void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
 			  u32 chan, bool rx, bool tx)
 {
-	u32 value = readl(ioaddr + DMA_INTR_ENA);
+	u32 value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
 
 	if (rx)
 		value |= DMA_INTR_DEFAULT_RX;
 	if (tx)
 		value |= DMA_INTR_DEFAULT_TX;
 
-	writel(value, ioaddr + DMA_INTR_ENA);
+	writel(value, ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr,
 			   u32 chan, bool rx, bool tx)
 {
-	u32 value = readl(ioaddr + DMA_INTR_ENA);
+	u32 value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
 
 	if (rx)
 		value &= ~DMA_INTR_DEFAULT_RX;
 	if (tx)
 		value &= ~DMA_INTR_DEFAULT_TX;
 
-	writel(value, ioaddr + DMA_INTR_ENA);
+	writel(value, ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 void dwmac_dma_start_tx(struct stmmac_priv *priv, void __iomem *ioaddr,
 			u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CONTROL);
+	u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
 	value |= DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CONTROL);
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 }
 
 void dwmac_dma_stop_tx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CONTROL);
+	u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
 	value &= ~DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CONTROL);
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 }
 
 void dwmac_dma_start_rx(struct stmmac_priv *priv, void __iomem *ioaddr,
 			u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CONTROL);
+	u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
 	value |= DMA_CONTROL_SR;
-	writel(value, ioaddr + DMA_CONTROL);
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 }
 
 void dwmac_dma_stop_rx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CONTROL);
+	u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
 	value &= ~DMA_CONTROL_SR;
-	writel(value, ioaddr + DMA_CONTROL);
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 }
 
 #ifdef DWMAC_DMA_DEBUG
@@ -165,7 +165,7 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr,
 	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
 	int ret = 0;
 	/* read the status register (CSR5) */
-	u32 intr_status = readl(ioaddr + DMA_STATUS);
+	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
 
 #ifdef DWMAC_DMA_DEBUG
 	/* Enable it to monitor DMA rx/tx status in case of critical problems */
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 1c99c99f4627..7e90f34b8c88 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -197,7 +197,7 @@ struct stmmac_dma_ops {
 	/* To track extra statistic (if supported) */
 	void (*dma_diagnostic_fr)(struct stmmac_extra_stats *x,
 				  void __iomem *ioaddr);
-	void (*enable_dma_transmission) (void __iomem *ioaddr);
+	void (*enable_dma_transmission)(void __iomem *ioaddr, u32 chan);
 	void (*enable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr,
 			       u32 chan, bool rx, bool tx);
 	void (*disable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9f1286835550..d9fca8d1227c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2367,9 +2367,11 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 	if (txfifosz == 0)
 		txfifosz = priv->dma_cap.tx_fifo_size;
 
-	/* Adjust for real per queue fifo size */
-	rxfifosz /= rx_channels_count;
-	txfifosz /= tx_channels_count;
+	/* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */
+	if (priv->plat->has_gmac4 || priv->plat->has_xgmac) {
+		rxfifosz /= rx_channels_count;
+		txfifosz /= tx_channels_count;
+	}
 
 	if (priv->plat->force_thresh_dma_mode) {
 		txmode = tc;
@@ -2553,7 +2555,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 				       true, priv->mode, true, true,
 				       xdp_desc.len);
 
-		stmmac_enable_dma_transmission(priv, priv->ioaddr);
+		stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
 
 		xsk_tx_metadata_to_compl(meta,
 					 &tx_q->tx_skbuff_dma[entry].xsk_meta);
@@ -4753,7 +4755,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
-	stmmac_enable_dma_transmission(priv, priv->ioaddr);
+	stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
 
 	stmmac_flush_tx_descriptors(priv, queue);
 	stmmac_tx_timer_arm(priv, queue);
@@ -4980,7 +4982,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue,
 		u64_stats_update_end(&txq_stats->q_syncp);
 	}
 
-	stmmac_enable_dma_transmission(priv, priv->ioaddr);
+	stmmac_enable_dma_transmission(priv, priv->ioaddr, queue);
 
 	entry = STMMAC_GET_ENTRY(entry, priv->dma_conf.dma_tx_size);
 	tx_q->cur_tx = entry;
-- 
cgit v1.3-3-g829e


From 005c0f071bc1db6a6972d598a265c0e45bca4038 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:45:30 +0800
Subject: net: stmmac: Export dwmac1000_dma_ops

Export the DW GMAC DMA-ops descriptor so one could be available in
the low-level platform drivers. It will be utilized to override some
callbacks in order to handle the LS2K2000 GNET device specifics. The
GNET controller support is being added in one of the following up
commits.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index b3d7eff53b18..118a22406a2e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -296,3 +296,4 @@ const struct stmmac_dma_ops dwmac1000_dma_ops = {
 	.get_hw_feature = dwmac1000_get_hw_feature,
 	.rx_watchdog = dwmac1000_rx_watchdog,
 };
+EXPORT_SYMBOL_GPL(dwmac1000_dma_ops);
-- 
cgit v1.3-3-g829e


From 393ea68bf154a53a108bde4bd387fa85b3662181 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:47:07 +0800
Subject: net: stmmac: dwmac-loongson: Drop duplicated hash-based filter size
 init

The plat_stmmacenet_data::multicast_filter_bins field is twice
initialized in the loongson_default_data() method. Drop the redundant
initialization, but for the readability sake keep the filters init
statements defined in the same place of the method.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 9e40c28d453a..9dbd11766364 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -16,7 +16,7 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat)
 	plat->force_sf_dma_mode = 1;
 
 	/* Set default value for multicast hash bins */
-	plat->multicast_filter_bins = HASH_TABLE_SIZE;
+	plat->multicast_filter_bins = 256;
 
 	/* Set default value for unicast filter entries */
 	plat->unicast_filter_entries = 1;
@@ -41,7 +41,6 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat)
 	plat->dma_cfg->pbl = 32;
 	plat->dma_cfg->pblx8 = true;
 
-	plat->multicast_filter_bins = 256;
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From 0c979e6b55f99f939bb8158f3d8f8d2072b04e9c Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:47:08 +0800
Subject: net: stmmac: dwmac-loongson: Drop pci_enable/disable_msi calls

The Loongson GMAC driver currently doesn't utilize the MSI IRQs, but
retrieves the IRQs specified in the device DT-node. Let's drop the
direct pci_enable_msi()/pci_disable_msi() calls then as redundant

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 9dbd11766364..32814afdf321 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -114,7 +114,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	pci_set_master(pdev);
 
 	loongson_default_data(plat);
-	pci_enable_msi(pdev);
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
@@ -122,7 +121,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (res.irq < 0) {
 		dev_err(&pdev->dev, "IRQ macirq not found\n");
 		ret = -ENODEV;
-		goto err_disable_msi;
+		goto err_disable_device;
 	}
 
 	res.wol_irq = of_irq_get_byname(np, "eth_wake_irq");
@@ -135,17 +134,15 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (res.lpi_irq < 0) {
 		dev_err(&pdev->dev, "IRQ eth_lpi not found\n");
 		ret = -ENODEV;
-		goto err_disable_msi;
+		goto err_disable_device;
 	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
 	if (ret)
-		goto err_disable_msi;
+		goto err_disable_device;
 
 	return ret;
 
-err_disable_msi:
-	pci_disable_msi(pdev);
 err_disable_device:
 	pci_disable_device(pdev);
 err_put_node:
@@ -169,7 +166,6 @@ static void loongson_dwmac_remove(struct pci_dev *pdev)
 		break;
 	}
 
-	pci_disable_msi(pdev);
 	pci_disable_device(pdev);
 }
 
-- 
cgit v1.3-3-g829e


From 324d96b46520f1476f25deaad0e49d8df71377c1 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:47:09 +0800
Subject: net: stmmac: dwmac-loongson: Use PCI_DEVICE_DATA() macro for device
 identification

For the readability sake convert the hard-coded Loongson GMAC PCI ID to
the respective macro and use the PCI_DEVICE_DATA() macro-function to
create the pci_device_id array entry. The later change will be
specifically useful in order to assign the device-specific data for the
currently supported device and for about to be added Loongson GNET
controller.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 32814afdf321..f39c13a74bb5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -9,6 +9,8 @@
 #include <linux/of_irq.h>
 #include "stmmac.h"
 
+#define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
+
 static int loongson_default_data(struct plat_stmmacenet_data *plat)
 {
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
@@ -208,7 +210,7 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend,
 			 loongson_dwmac_resume);
 
 static const struct pci_device_id loongson_dwmac_id_table[] = {
-	{ PCI_VDEVICE(LOONGSON, 0x7a03) },
+	{ PCI_DEVICE_DATA(LOONGSON, GMAC, NULL) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
-- 
cgit v1.3-3-g829e


From 79afc70002c20753aaed41a5083cf936148832b1 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:47:10 +0800
Subject: net: stmmac: dwmac-loongson: Detach GMAC-specific platform data init

Loongson delivers two types of the network devices: Loongson GMAC and
Loongson GNET in the framework of four SOC/Chipsets revisions:

   Chip             Network  PCI Dev ID   Synopys Version   DMA-channel
LS2K1000 SOC         GMAC      0x7a03       v3.50a/v3.73a        1
LS7A1000 Chipset     GMAC      0x7a03       v3.50a/v3.73a        1
LS2K2000 SOC         GMAC      0x7a03          v3.73a            8
LS2K2000 SOC         GNET      0x7a13          v3.73a            8
LS7A2000 Chipset     GNET      0x7a13          v3.73a            1

The driver currently supports the chips with the Loongson GMAC network
device synthesized with a single DMA-channel available. As a
preparation before adding the Loongson GNET support detach the
Loongson GMAC-specific platform data initializations to the
loongson_gmac_data() method and preserve the common settings in the
loongson_default_data().

While at it drop the return value statement from the
loongson_default_data() method as redundant.

Note there is no intermediate vendor-specific PCS in between the MAC
and PHY on Loongson GMAC and GNET. So the plat->mac_interface field
can be freely initialized with the PHY_INTERFACE_MODE_NA value.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index f39c13a74bb5..9b2e4bdf7cc7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -11,7 +11,7 @@
 
 #define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
 
-static int loongson_default_data(struct plat_stmmacenet_data *plat)
+static void loongson_default_data(struct plat_stmmacenet_data *plat)
 {
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
 	plat->has_gmac = 1;
@@ -20,16 +20,14 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat)
 	/* Set default value for multicast hash bins */
 	plat->multicast_filter_bins = 256;
 
+	plat->mac_interface = PHY_INTERFACE_MODE_NA;
+
 	/* Set default value for unicast filter entries */
 	plat->unicast_filter_entries = 1;
 
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
 
-	/* Set default number of RX and TX queues to use */
-	plat->tx_queues_to_use = 1;
-	plat->rx_queues_to_use = 1;
-
 	/* Disable Priority config by default */
 	plat->tx_queues_cfg[0].use_prio = false;
 	plat->rx_queues_cfg[0].use_prio = false;
@@ -42,6 +40,14 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat)
 
 	plat->dma_cfg->pbl = 32;
 	plat->dma_cfg->pblx8 = true;
+}
+
+static int loongson_gmac_data(struct plat_stmmacenet_data *plat)
+{
+	loongson_default_data(plat);
+
+	plat->tx_queues_to_use = 1;
+	plat->rx_queues_to_use = 1;
 
 	return 0;
 }
@@ -111,11 +117,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	}
 
 	plat->phy_interface = phy_mode;
-	plat->mac_interface = PHY_INTERFACE_MODE_GMII;
 
 	pci_set_master(pdev);
 
-	loongson_default_data(plat);
+	loongson_gmac_data(plat);
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
-- 
cgit v1.3-3-g829e


From c70f3163681381c15686bdd2fe56bf4af9b8aaaa Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:02 +0800
Subject: net: stmmac: dwmac-loongson: Init ref and PTP clocks rate

Reference and PTP clocks rate of the Loongson GMAC devices is 125MHz.
(So is in the GNET devices which support is about to be added.) Set
the respective plat_stmmacenet_data field up in accordance with that
so to have the coalesce command and timestamping work correctly.

Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson")
Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 9b2e4bdf7cc7..327275b28dc2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -35,6 +35,9 @@ static void loongson_default_data(struct plat_stmmacenet_data *plat)
 	/* Disable RX queues routing by default */
 	plat->rx_queues_cfg[0].pkt_route = 0x0;
 
+	plat->clk_ref_rate = 125000000;
+	plat->clk_ptp_rate = 125000000;
+
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
 
-- 
cgit v1.3-3-g829e


From 849dc7341d1f48dacdeadb86eb09f6d7777b1e5e Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:03 +0800
Subject: net: stmmac: dwmac-loongson: Add phy_interface for Loongson GMAC

PHY-interface of the Loongson GMAC device is RGMII with no internal
delays added to the data lines signal. So to comply with that let's
pre-initialize the platform-data field with the respective enum
constant.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 327275b28dc2..7d3f284b9176 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -52,6 +52,8 @@ static int loongson_gmac_data(struct plat_stmmacenet_data *plat)
 	plat->tx_queues_to_use = 1;
 	plat->rx_queues_to_use = 1;
 
+	plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID;
+
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From 0ec04d32b5e7f03f1a18713a4958a056240763c8 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:04 +0800
Subject: net: stmmac: dwmac-loongson: Introduce PCI device info data

The Loongson GNET device support is about to be added in one of the
next commits. As another preparation for that introduce the PCI device
info data with a setup() callback performing the device-specific
platform data initializations. Currently it is utilized for the
already supported Loongson GMAC device only.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 7d3f284b9176..10b49bea8e3c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -11,6 +11,10 @@
 
 #define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
 
+struct stmmac_pci_info {
+	int (*setup)(struct plat_stmmacenet_data *plat);
+};
+
 static void loongson_default_data(struct plat_stmmacenet_data *plat)
 {
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
@@ -57,9 +61,14 @@ static int loongson_gmac_data(struct plat_stmmacenet_data *plat)
 	return 0;
 }
 
+static struct stmmac_pci_info loongson_gmac_pci_info = {
+	.setup = loongson_gmac_data,
+};
+
 static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct plat_stmmacenet_data *plat;
+	struct stmmac_pci_info *info;
 	struct stmmac_resources res;
 	struct device_node *np;
 	int ret, i, phy_mode;
@@ -125,10 +134,14 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 
 	pci_set_master(pdev);
 
-	loongson_gmac_data(plat);
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
+	info = (struct stmmac_pci_info *)id->driver_data;
+	ret = info->setup(plat);
+	if (ret)
+		goto err_disable_device;
+
 	res.irq = of_irq_get_byname(np, "macirq");
 	if (res.irq < 0) {
 		dev_err(&pdev->dev, "IRQ macirq not found\n");
@@ -220,7 +233,7 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend,
 			 loongson_dwmac_resume);
 
 static const struct pci_device_id loongson_dwmac_id_table[] = {
-	{ PCI_DEVICE_DATA(LOONGSON, GMAC, NULL) },
+	{ PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
-- 
cgit v1.3-3-g829e


From 126f4f96c41d2efe9ea1b949ff3e6d997010991e Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:05 +0800
Subject: net: stmmac: dwmac-loongson: Add DT-less GMAC PCI-device support

The Loongson GMAC driver currently supports the network controllers
installed on the LS2K1000 SoC and LS7A1000 chipset, for which the GMAC
devices are required to be defined in the platform device tree source.
But Loongson machines may have UEFI (implies ACPI) or PMON/UBOOT
(implies FDT) as the system bootloaders. In order to have both system
configurations support let's extend the driver functionality with the
case of having the Loongson GMAC probed on the PCI bus with no device
tree node defined for it. That requires to make the device DT-node
optional, to rely on the IRQ line detected by the PCI core and to
have the MDIO bus ID calculated using the PCIe Domain+BDF numbers.

In order to have the device probe() and remove() methods less
complicated let's move the DT- and ACPI-specific code to the
respective sub-functions.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/stmicro/stmmac/dwmac-loongson.c   | 165 +++++++++++++--------
 1 file changed, 102 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 10b49bea8e3c..c0740a41025b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -12,11 +12,15 @@
 #define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
 
 struct stmmac_pci_info {
-	int (*setup)(struct plat_stmmacenet_data *plat);
+	int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat);
 };
 
-static void loongson_default_data(struct plat_stmmacenet_data *plat)
+static void loongson_default_data(struct pci_dev *pdev,
+				  struct plat_stmmacenet_data *plat)
 {
+	/* Get bus_id, this can be overwritten later */
+	plat->bus_id = pci_dev_id(pdev);
+
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
 	plat->has_gmac = 1;
 	plat->force_sf_dma_mode = 1;
@@ -49,9 +53,10 @@ static void loongson_default_data(struct plat_stmmacenet_data *plat)
 	plat->dma_cfg->pblx8 = true;
 }
 
-static int loongson_gmac_data(struct plat_stmmacenet_data *plat)
+static int loongson_gmac_data(struct pci_dev *pdev,
+			      struct plat_stmmacenet_data *plat)
 {
-	loongson_default_data(plat);
+	loongson_default_data(pdev, plat);
 
 	plat->tx_queues_to_use = 1;
 	plat->rx_queues_to_use = 1;
@@ -65,20 +70,85 @@ static struct stmmac_pci_info loongson_gmac_pci_info = {
 	.setup = loongson_gmac_data,
 };
 
+static int loongson_dwmac_dt_config(struct pci_dev *pdev,
+				    struct plat_stmmacenet_data *plat,
+				    struct stmmac_resources *res)
+{
+	struct device_node *np = dev_of_node(&pdev->dev);
+	int ret;
+
+	plat->mdio_node = of_get_child_by_name(np, "mdio");
+	if (plat->mdio_node) {
+		dev_info(&pdev->dev, "Found MDIO subnode\n");
+		plat->mdio_bus_data->needs_reset = true;
+	}
+
+	ret = of_alias_get_id(np, "ethernet");
+	if (ret >= 0)
+		plat->bus_id = ret;
+
+	res->irq = of_irq_get_byname(np, "macirq");
+	if (res->irq < 0) {
+		dev_err(&pdev->dev, "IRQ macirq not found\n");
+		ret = -ENODEV;
+		goto err_put_node;
+	}
+
+	res->wol_irq = of_irq_get_byname(np, "eth_wake_irq");
+	if (res->wol_irq < 0) {
+		dev_info(&pdev->dev,
+			 "IRQ eth_wake_irq not found, using macirq\n");
+		res->wol_irq = res->irq;
+	}
+
+	res->lpi_irq = of_irq_get_byname(np, "eth_lpi");
+	if (res->lpi_irq < 0) {
+		dev_err(&pdev->dev, "IRQ eth_lpi not found\n");
+		ret = -ENODEV;
+		goto err_put_node;
+	}
+
+	ret = device_get_phy_mode(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "phy_mode not found\n");
+		ret = -ENODEV;
+		goto err_put_node;
+	}
+
+	plat->phy_interface = ret;
+
+	return 0;
+
+err_put_node:
+	of_node_put(plat->mdio_node);
+
+	return ret;
+}
+
+static void loongson_dwmac_dt_clear(struct pci_dev *pdev,
+				    struct plat_stmmacenet_data *plat)
+{
+	of_node_put(plat->mdio_node);
+}
+
+static int loongson_dwmac_acpi_config(struct pci_dev *pdev,
+				      struct plat_stmmacenet_data *plat,
+				      struct stmmac_resources *res)
+{
+	if (!pdev->irq)
+		return -EINVAL;
+
+	res->irq = pdev->irq;
+
+	return 0;
+}
+
 static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_pci_info *info;
 	struct stmmac_resources res;
-	struct device_node *np;
-	int ret, i, phy_mode;
-
-	np = dev_of_node(&pdev->dev);
-
-	if (!np) {
-		pr_info("dwmac_loongson_pci: No OF node\n");
-		return -ENODEV;
-	}
+	int ret, i;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
 	if (!plat)
@@ -90,25 +160,19 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (!plat->mdio_bus_data)
 		return -ENOMEM;
 
-	plat->mdio_node = of_get_child_by_name(np, "mdio");
-	if (plat->mdio_node) {
-		dev_info(&pdev->dev, "Found MDIO subnode\n");
-		plat->mdio_bus_data->needs_reset = true;
-	}
-
 	plat->dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->dma_cfg), GFP_KERNEL);
-	if (!plat->dma_cfg) {
-		ret = -ENOMEM;
-		goto err_put_node;
-	}
+	if (!plat->dma_cfg)
+		return -ENOMEM;
 
 	/* Enable pci device */
 	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__);
-		goto err_put_node;
+		return ret;
 	}
 
+	pci_set_master(pdev);
+
 	/* Get the base address of device */
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
@@ -119,59 +183,32 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 		break;
 	}
 
-	plat->bus_id = of_alias_get_id(np, "ethernet");
-	if (plat->bus_id < 0)
-		plat->bus_id = pci_dev_id(pdev);
-
-	phy_mode = device_get_phy_mode(&pdev->dev);
-	if (phy_mode < 0) {
-		dev_err(&pdev->dev, "phy_mode not found\n");
-		ret = phy_mode;
-		goto err_disable_device;
-	}
-
-	plat->phy_interface = phy_mode;
-
-	pci_set_master(pdev);
-
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
 	info = (struct stmmac_pci_info *)id->driver_data;
-	ret = info->setup(plat);
+	ret = info->setup(pdev, plat);
 	if (ret)
 		goto err_disable_device;
 
-	res.irq = of_irq_get_byname(np, "macirq");
-	if (res.irq < 0) {
-		dev_err(&pdev->dev, "IRQ macirq not found\n");
-		ret = -ENODEV;
-		goto err_disable_device;
-	}
-
-	res.wol_irq = of_irq_get_byname(np, "eth_wake_irq");
-	if (res.wol_irq < 0) {
-		dev_info(&pdev->dev, "IRQ eth_wake_irq not found, using macirq\n");
-		res.wol_irq = res.irq;
-	}
-
-	res.lpi_irq = of_irq_get_byname(np, "eth_lpi");
-	if (res.lpi_irq < 0) {
-		dev_err(&pdev->dev, "IRQ eth_lpi not found\n");
-		ret = -ENODEV;
+	if (dev_of_node(&pdev->dev))
+		ret = loongson_dwmac_dt_config(pdev, plat, &res);
+	else
+		ret = loongson_dwmac_acpi_config(pdev, plat, &res);
+	if (ret)
 		goto err_disable_device;
-	}
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
 	if (ret)
-		goto err_disable_device;
+		goto err_plat_clear;
 
-	return ret;
+	return 0;
 
+err_plat_clear:
+	if (dev_of_node(&pdev->dev))
+		loongson_dwmac_dt_clear(pdev, plat);
 err_disable_device:
 	pci_disable_device(pdev);
-err_put_node:
-	of_node_put(plat->mdio_node);
 	return ret;
 }
 
@@ -181,9 +218,11 @@ static void loongson_dwmac_remove(struct pci_dev *pdev)
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	int i;
 
-	of_node_put(priv->plat->mdio_node);
 	stmmac_dvr_remove(&pdev->dev);
 
+	if (dev_of_node(&pdev->dev))
+		loongson_dwmac_dt_clear(pdev, priv->plat);
+
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-- 
cgit v1.3-3-g829e


From 803fc61df261dee7dc71fb4f7000c0569e2afff6 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:54 +0800
Subject: net: stmmac: dwmac-loongson: Add Loongson Multi-channels GMAC support

The Loongson DWMAC driver currently supports the Loongson GMAC
devices (based on the DW GMAC v3.50a/v3.73a IP-core) installed to the
LS2K1000 SoC and LS7A1000 chipset. But recently a new generation
LS2K2000 SoC was released with the new version of the Loongson GMAC
synthesized in. The new controller is based on the DW GMAC v3.73a
IP-core with the AV-feature enabled, which implies the multi
DMA-channels support. The multi DMA-channels feature has the next
vendor-specific peculiarities:

1. Split up Tx and Rx DMA IRQ status/mask bits:
       Name              Tx          Rx
  DMA_INTR_ENA_NIE = 0x00040000 | 0x00020000;
  DMA_INTR_ENA_AIE = 0x00010000 | 0x00008000;
  DMA_STATUS_NIS   = 0x00040000 | 0x00020000;
  DMA_STATUS_AIS   = 0x00010000 | 0x00008000;
  DMA_STATUS_FBI   = 0x00002000 | 0x00001000;
2. Custom Synopsys ID hardwired into the GMAC_VERSION.SNPSVER register
field. It's 0x10 while it should have been 0x37 in accordance with
the actual DW GMAC IP-core version.
3. There are eight DMA-channels available meanwhile the Synopsys DW
GMAC IP-core supports up to three DMA-channels.
4. It's possible to have each DMA-channel IRQ independently delivered.
The MSI IRQs must be utilized for that.

Thus in order to have the multi-channels Loongson GMAC controllers
supported let's modify the Loongson DWMAC driver in accordance with
all the peculiarities described above:

1. Create the multi-channels Loongson GMAC-specific
   stmmac_dma_ops::dma_interrupt()
   stmmac_dma_ops::init_chan()
   callbacks due to the non-standard DMA IRQ CSR flags layout.
2. Create the Loongson DWMAC-specific platform setup() method
which gets to initialize the DMA-ops with the dwmac1000_dma_ops
instance and overrides the callbacks described in 1. The method also
overrides the custom Synopsys ID with the real one in order to have
the rest of the HW-specific callbacks correctly detected by the driver
core.
3. Make sure the platform setup() method enables the flow control and
duplex modes supported by the controller.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/common.h       |   1 +
 .../net/ethernet/stmicro/stmmac/dwmac-loongson.c   | 328 ++++++++++++++++++++-
 2 files changed, 327 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index cd36ff4da68c..684489156dce 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -29,6 +29,7 @@
 /* Synopsys Core versions */
 #define	DWMAC_CORE_3_40		0x34
 #define	DWMAC_CORE_3_50		0x35
+#define	DWMAC_CORE_3_70		0x37
 #define	DWMAC_CORE_4_00		0x40
 #define DWMAC_CORE_4_10		0x41
 #define DWMAC_CORE_5_00		0x50
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index c0740a41025b..48c92ba826d9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -8,8 +8,69 @@
 #include <linux/device.h>
 #include <linux/of_irq.h>
 #include "stmmac.h"
+#include "dwmac_dma.h"
+#include "dwmac1000.h"
+
+/* Normal Loongson Tx Summary */
+#define DMA_INTR_ENA_NIE_TX_LOONGSON	0x00040000
+/* Normal Loongson Rx Summary */
+#define DMA_INTR_ENA_NIE_RX_LOONGSON	0x00020000
+
+#define DMA_INTR_NORMAL_LOONGSON	(DMA_INTR_ENA_NIE_TX_LOONGSON | \
+					 DMA_INTR_ENA_NIE_RX_LOONGSON | \
+					 DMA_INTR_ENA_RIE | DMA_INTR_ENA_TIE)
+
+/* Abnormal Loongson Tx Summary */
+#define DMA_INTR_ENA_AIE_TX_LOONGSON	0x00010000
+/* Abnormal Loongson Rx Summary */
+#define DMA_INTR_ENA_AIE_RX_LOONGSON	0x00008000
+
+#define DMA_INTR_ABNORMAL_LOONGSON	(DMA_INTR_ENA_AIE_TX_LOONGSON | \
+					 DMA_INTR_ENA_AIE_RX_LOONGSON | \
+					 DMA_INTR_ENA_FBE | DMA_INTR_ENA_UNE)
+
+#define DMA_INTR_DEFAULT_MASK_LOONGSON	(DMA_INTR_NORMAL_LOONGSON | \
+					 DMA_INTR_ABNORMAL_LOONGSON)
+
+/* Normal Loongson Tx Interrupt Summary */
+#define DMA_STATUS_NIS_TX_LOONGSON	0x00040000
+/* Normal Loongson Rx Interrupt Summary */
+#define DMA_STATUS_NIS_RX_LOONGSON	0x00020000
+
+/* Abnormal Loongson Tx Interrupt Summary */
+#define DMA_STATUS_AIS_TX_LOONGSON	0x00010000
+/* Abnormal Loongson Rx Interrupt Summary */
+#define DMA_STATUS_AIS_RX_LOONGSON	0x00008000
+
+/* Fatal Loongson Tx Bus Error Interrupt */
+#define DMA_STATUS_FBI_TX_LOONGSON	0x00002000
+/* Fatal Loongson Rx Bus Error Interrupt */
+#define DMA_STATUS_FBI_RX_LOONGSON	0x00001000
+
+#define DMA_STATUS_MSK_COMMON_LOONGSON	(DMA_STATUS_NIS_TX_LOONGSON | \
+					 DMA_STATUS_NIS_RX_LOONGSON | \
+					 DMA_STATUS_AIS_TX_LOONGSON | \
+					 DMA_STATUS_AIS_RX_LOONGSON | \
+					 DMA_STATUS_FBI_TX_LOONGSON | \
+					 DMA_STATUS_FBI_RX_LOONGSON)
+
+#define DMA_STATUS_MSK_RX_LOONGSON	(DMA_STATUS_ERI | DMA_STATUS_RWT | \
+					 DMA_STATUS_RPS | DMA_STATUS_RU  | \
+					 DMA_STATUS_RI  | DMA_STATUS_OVF | \
+					 DMA_STATUS_MSK_COMMON_LOONGSON)
+
+#define DMA_STATUS_MSK_TX_LOONGSON	(DMA_STATUS_ETI | DMA_STATUS_UNF | \
+					 DMA_STATUS_TJT | DMA_STATUS_TU  | \
+					 DMA_STATUS_TPS | DMA_STATUS_TI  | \
+					 DMA_STATUS_MSK_COMMON_LOONGSON)
 
 #define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
+#define DWMAC_CORE_LS_MULTICHAN	0x10	/* Loongson custom ID */
+#define CHANNEL_NUM			8
+
+struct loongson_data {
+	u32 loongson_id;
+};
 
 struct stmmac_pci_info {
 	int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat);
@@ -56,10 +117,26 @@ static void loongson_default_data(struct pci_dev *pdev,
 static int loongson_gmac_data(struct pci_dev *pdev,
 			      struct plat_stmmacenet_data *plat)
 {
+	struct loongson_data *ld;
+	int i;
+
+	ld = plat->bsp_priv;
+
 	loongson_default_data(pdev, plat);
 
-	plat->tx_queues_to_use = 1;
-	plat->rx_queues_to_use = 1;
+	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
+		plat->rx_queues_to_use = CHANNEL_NUM;
+		plat->tx_queues_to_use = CHANNEL_NUM;
+
+		/* Only channel 0 supports checksum,
+		 * so turn off checksum to enable multiple channels.
+		 */
+		for (i = 1; i < CHANNEL_NUM; i++)
+			plat->tx_queues_cfg[i].coe_unsupported = 1;
+	} else {
+		plat->tx_queues_to_use = 1;
+		plat->rx_queues_to_use = 1;
+	}
 
 	plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID;
 
@@ -70,6 +147,233 @@ static struct stmmac_pci_info loongson_gmac_pci_info = {
 	.setup = loongson_gmac_data,
 };
 
+static void loongson_dwmac_dma_init_channel(struct stmmac_priv *priv,
+					    void __iomem *ioaddr,
+					    struct stmmac_dma_cfg *dma_cfg,
+					    u32 chan)
+{
+	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+	int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 value;
+
+	value = readl(ioaddr + DMA_CHAN_BUS_MODE(chan));
+
+	if (dma_cfg->pblx8)
+		value |= DMA_BUS_MODE_MAXPBL;
+
+	value |= DMA_BUS_MODE_USP;
+	value &= ~(DMA_BUS_MODE_PBL_MASK | DMA_BUS_MODE_RPBL_MASK);
+	value |= (txpbl << DMA_BUS_MODE_PBL_SHIFT);
+	value |= (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
+
+	/* Set the Fixed burst mode */
+	if (dma_cfg->fixed_burst)
+		value |= DMA_BUS_MODE_FB;
+
+	/* Mixed Burst has no effect when fb is set */
+	if (dma_cfg->mixed_burst)
+		value |= DMA_BUS_MODE_MB;
+
+	if (dma_cfg->atds)
+		value |= DMA_BUS_MODE_ATDS;
+
+	if (dma_cfg->aal)
+		value |= DMA_BUS_MODE_AAL;
+
+	writel(value, ioaddr + DMA_CHAN_BUS_MODE(chan));
+
+	/* Mask interrupts by writing to CSR7 */
+	writel(DMA_INTR_DEFAULT_MASK_LOONGSON, ioaddr +
+	       DMA_CHAN_INTR_ENA(chan));
+}
+
+static int loongson_dwmac_dma_interrupt(struct stmmac_priv *priv,
+					void __iomem *ioaddr,
+					struct stmmac_extra_stats *x,
+					u32 chan, u32 dir)
+{
+	struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats);
+	u32 abnor_intr_status;
+	u32 nor_intr_status;
+	u32 fb_intr_status;
+	u32 intr_status;
+	int ret = 0;
+
+	/* read the status register (CSR5) */
+	intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
+
+	if (dir == DMA_DIR_RX)
+		intr_status &= DMA_STATUS_MSK_RX_LOONGSON;
+	else if (dir == DMA_DIR_TX)
+		intr_status &= DMA_STATUS_MSK_TX_LOONGSON;
+
+	nor_intr_status = intr_status & (DMA_STATUS_NIS_TX_LOONGSON |
+		DMA_STATUS_NIS_RX_LOONGSON);
+	abnor_intr_status = intr_status & (DMA_STATUS_AIS_TX_LOONGSON |
+		DMA_STATUS_AIS_RX_LOONGSON);
+	fb_intr_status = intr_status & (DMA_STATUS_FBI_TX_LOONGSON |
+		DMA_STATUS_FBI_RX_LOONGSON);
+
+	/* ABNORMAL interrupts */
+	if (unlikely(abnor_intr_status)) {
+		if (unlikely(intr_status & DMA_STATUS_UNF)) {
+			ret = tx_hard_error_bump_tc;
+			x->tx_undeflow_irq++;
+		}
+		if (unlikely(intr_status & DMA_STATUS_TJT))
+			x->tx_jabber_irq++;
+		if (unlikely(intr_status & DMA_STATUS_OVF))
+			x->rx_overflow_irq++;
+		if (unlikely(intr_status & DMA_STATUS_RU))
+			x->rx_buf_unav_irq++;
+		if (unlikely(intr_status & DMA_STATUS_RPS))
+			x->rx_process_stopped_irq++;
+		if (unlikely(intr_status & DMA_STATUS_RWT))
+			x->rx_watchdog_irq++;
+		if (unlikely(intr_status & DMA_STATUS_ETI))
+			x->tx_early_irq++;
+		if (unlikely(intr_status & DMA_STATUS_TPS)) {
+			x->tx_process_stopped_irq++;
+			ret = tx_hard_error;
+		}
+		if (unlikely(fb_intr_status)) {
+			x->fatal_bus_error_irq++;
+			ret = tx_hard_error;
+		}
+	}
+	/* TX/RX NORMAL interrupts */
+	if (likely(nor_intr_status)) {
+		if (likely(intr_status & DMA_STATUS_RI)) {
+			u32 value = readl(ioaddr + DMA_INTR_ENA);
+			/* to schedule NAPI on real RIE event. */
+			if (likely(value & DMA_INTR_ENA_RIE)) {
+				u64_stats_update_begin(&stats->syncp);
+				u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+				u64_stats_update_end(&stats->syncp);
+				ret |= handle_rx;
+			}
+		}
+		if (likely(intr_status & DMA_STATUS_TI)) {
+			u64_stats_update_begin(&stats->syncp);
+			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+			u64_stats_update_end(&stats->syncp);
+			ret |= handle_tx;
+		}
+		if (unlikely(intr_status & DMA_STATUS_ERI))
+			x->rx_early_irq++;
+	}
+	/* Optional hardware blocks, interrupts should be disabled */
+	if (unlikely(intr_status &
+		     (DMA_STATUS_GPI | DMA_STATUS_GMI | DMA_STATUS_GLI)))
+		pr_warn("%s: unexpected status %08x\n", __func__, intr_status);
+
+	/* Clear the interrupt by writing a logic 1 to the CSR5[19-0] */
+	writel((intr_status & 0x7ffff), ioaddr + DMA_CHAN_STATUS(chan));
+
+	return ret;
+}
+
+static struct mac_device_info *loongson_dwmac_setup(void *apriv)
+{
+	struct stmmac_priv *priv = apriv;
+	struct mac_device_info *mac;
+	struct stmmac_dma_ops *dma;
+	struct loongson_data *ld;
+
+	ld = priv->plat->bsp_priv;
+
+	mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
+	if (!mac)
+		return NULL;
+
+	dma = devm_kzalloc(priv->device, sizeof(*dma), GFP_KERNEL);
+	if (!dma)
+		return NULL;
+
+	/* The Loongson GMAC devices are based on the DW GMAC
+	 * v3.50a and v3.73a IP-cores. But the HW designers have changed the
+	 * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the
+	 * network controllers with the multi-channels feature
+	 * available to emphasize the differences: multiple DMA-channels,
+	 * AV feature and GMAC_INT_STATUS CSR flags layout. Get back the
+	 * original value so the correct HW-interface would be selected.
+	 */
+	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
+		priv->synopsys_id = DWMAC_CORE_3_70;
+		*dma = dwmac1000_dma_ops;
+		dma->init_chan = loongson_dwmac_dma_init_channel;
+		dma->dma_interrupt = loongson_dwmac_dma_interrupt;
+		mac->dma = dma;
+	}
+
+	priv->dev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* Pre-initialize the respective "mac" fields as it's done in
+	 * dwmac1000_setup()
+	 */
+	mac->pcsr = priv->ioaddr;
+	mac->multicast_filter_bins = priv->plat->multicast_filter_bins;
+	mac->unicast_filter_entries = priv->plat->unicast_filter_entries;
+	mac->mcast_bits_log2 = 0;
+
+	if (mac->multicast_filter_bins)
+		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+
+	/* Loongson GMAC doesn't support the flow control. */
+	mac->link.caps = MAC_10 | MAC_100 | MAC_1000;
+
+	mac->link.duplex = GMAC_CONTROL_DM;
+	mac->link.speed10 = GMAC_CONTROL_PS;
+	mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES;
+	mac->link.speed1000 = 0;
+	mac->link.speed_mask = GMAC_CONTROL_PS | GMAC_CONTROL_FES;
+	mac->mii.addr = GMAC_MII_ADDR;
+	mac->mii.data = GMAC_MII_DATA;
+	mac->mii.addr_shift = 11;
+	mac->mii.addr_mask = 0x0000F800;
+	mac->mii.reg_shift = 6;
+	mac->mii.reg_mask = 0x000007C0;
+	mac->mii.clk_csr_shift = 2;
+	mac->mii.clk_csr_mask = GENMASK(5, 2);
+
+	return mac;
+}
+
+static int loongson_dwmac_msi_config(struct pci_dev *pdev,
+				     struct plat_stmmacenet_data *plat,
+				     struct stmmac_resources *res)
+{
+	int i, ret, vecs;
+
+	vecs = roundup_pow_of_two(CHANNEL_NUM * 2 + 1);
+	ret = pci_alloc_irq_vectors(pdev, vecs, vecs, PCI_IRQ_MSI);
+	if (ret < 0) {
+		dev_warn(&pdev->dev, "Failed to allocate MSI IRQs\n");
+		return ret;
+	}
+
+	res->irq = pci_irq_vector(pdev, 0);
+
+	for (i = 0; i < plat->rx_queues_to_use; i++) {
+		res->rx_irq[CHANNEL_NUM - 1 - i] =
+			pci_irq_vector(pdev, 1 + i * 2);
+	}
+
+	for (i = 0; i < plat->tx_queues_to_use; i++) {
+		res->tx_irq[CHANNEL_NUM - 1 - i] =
+			pci_irq_vector(pdev, 2 + i * 2);
+	}
+
+	plat->flags |= STMMAC_FLAG_MULTI_MSI_EN;
+
+	return 0;
+}
+
+static void loongson_dwmac_msi_clear(struct pci_dev *pdev)
+{
+	pci_free_irq_vectors(pdev);
+}
+
 static int loongson_dwmac_dt_config(struct pci_dev *pdev,
 				    struct plat_stmmacenet_data *plat,
 				    struct stmmac_resources *res)
@@ -148,6 +452,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_pci_info *info;
 	struct stmmac_resources res;
+	struct loongson_data *ld;
 	int ret, i;
 
 	plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL);
@@ -164,6 +469,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (!plat->dma_cfg)
 		return -ENOMEM;
 
+	ld = devm_kzalloc(&pdev->dev, sizeof(*ld), GFP_KERNEL);
+	if (!ld)
+		return -ENOMEM;
+
 	/* Enable pci device */
 	ret = pci_enable_device(pdev);
 	if (ret) {
@@ -186,6 +495,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	memset(&res, 0, sizeof(res));
 	res.addr = pcim_iomap_table(pdev)[0];
 
+	plat->bsp_priv = ld;
+	plat->setup = loongson_dwmac_setup;
+	ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff;
+
 	info = (struct stmmac_pci_info *)id->driver_data;
 	ret = info->setup(pdev, plat);
 	if (ret)
@@ -198,6 +511,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (ret)
 		goto err_disable_device;
 
+	/* Use the common MAC IRQ if per-channel MSIs allocation failed */
+	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+		loongson_dwmac_msi_config(pdev, plat, &res);
+
 	ret = stmmac_dvr_probe(&pdev->dev, plat, &res);
 	if (ret)
 		goto err_plat_clear;
@@ -207,6 +524,8 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 err_plat_clear:
 	if (dev_of_node(&pdev->dev))
 		loongson_dwmac_dt_clear(pdev, plat);
+	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+		loongson_dwmac_msi_clear(pdev);
 err_disable_device:
 	pci_disable_device(pdev);
 	return ret;
@@ -216,13 +535,18 @@ static void loongson_dwmac_remove(struct pci_dev *pdev)
 {
 	struct net_device *ndev = dev_get_drvdata(&pdev->dev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct loongson_data *ld;
 	int i;
 
+	ld = priv->plat->bsp_priv;
 	stmmac_dvr_remove(&pdev->dev);
 
 	if (dev_of_node(&pdev->dev))
 		loongson_dwmac_dt_clear(pdev, priv->plat);
 
+	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+		loongson_dwmac_msi_clear(pdev);
+
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-- 
cgit v1.3-3-g829e


From 56dbe2c290bc580ac0774e163133c2ed84ecb8f0 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:55 +0800
Subject: net: stmmac: dwmac-loongson: Add Loongson GNET support

The new generation Loongson LS2K2000 SoC and LS7A2000 chipset are
equipped with the network controllers called Loongson GNET. It's the
single and multi DMA-channels Loongson GMAC but with a PHY attached.
Here is the summary of the DW GMAC features the controller has:

   DW GMAC IP-core: v3.73a
   Speeds: 10/100/1000Mbps
   Duplex: Full (both versions), Half (LS2K2000 GNET only)
   DMA-descriptors type: enhanced
   L3/L4 filters availability: Y
   VLAN hash table filter: Y
   PHY-interface: GMII (PHY is integrated into the chips)
   Remote Wake-up support: Y
   Mac Management Counters (MMC): Y
   Number of additional MAC addresses: 5
   MAC Hash-based filter: Y
   Hash Table Size: 256
   AV feature: Y (LS2K2000 GNET only)
   DMA channels: 8 (LS2K2000 GNET), 1 (LS7A2000 GNET)

Let's update the Loongson DWMAC driver to supporting the new Loongson
GNET controller. The change is mainly trivial: the driver shall be
bound to the PCIe device with DID 0x7a13, and the device-specific
setup() method shall be called for it. The only peculiarity concerns
the integrated PHY speed change procedure. The PHY has a weird problem
with switching from the low speeds to 1000Mbps mode. The speedup
procedure requires the PHY-link re-negotiation. So the suggested
change provide the device-specific fix_mac_speed() method to overcome
the problem.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/stmicro/stmmac/dwmac-loongson.c   | 77 +++++++++++++++++++++-
 1 file changed, 74 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 48c92ba826d9..949e349ef856 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -65,11 +65,13 @@
 					 DMA_STATUS_MSK_COMMON_LOONGSON)
 
 #define PCI_DEVICE_ID_LOONGSON_GMAC	0x7a03
+#define PCI_DEVICE_ID_LOONGSON_GNET	0x7a13
 #define DWMAC_CORE_LS_MULTICHAN	0x10	/* Loongson custom ID */
 #define CHANNEL_NUM			8
 
 struct loongson_data {
 	u32 loongson_id;
+	struct device *dev;
 };
 
 struct stmmac_pci_info {
@@ -147,6 +149,60 @@ static struct stmmac_pci_info loongson_gmac_pci_info = {
 	.setup = loongson_gmac_data,
 };
 
+static void loongson_gnet_fix_speed(void *priv, unsigned int speed,
+				    unsigned int mode)
+{
+	struct loongson_data *ld = (struct loongson_data *)priv;
+	struct net_device *ndev = dev_get_drvdata(ld->dev);
+	struct stmmac_priv *ptr = netdev_priv(ndev);
+
+	/* The integrated PHY has a weird problem with switching from the low
+	 * speeds to 1000Mbps mode. The speedup procedure requires the PHY-link
+	 * re-negotiation.
+	 */
+	if (speed == SPEED_1000) {
+		if (readl(ptr->ioaddr + MAC_CTRL_REG) &
+		    GMAC_CONTROL_PS)
+			/* Word around hardware bug, restart autoneg */
+			phy_restart_aneg(ndev->phydev);
+	}
+}
+
+static int loongson_gnet_data(struct pci_dev *pdev,
+			      struct plat_stmmacenet_data *plat)
+{
+	struct loongson_data *ld;
+	int i;
+
+	ld = plat->bsp_priv;
+
+	loongson_default_data(pdev, plat);
+
+	if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) {
+		plat->rx_queues_to_use = CHANNEL_NUM;
+		plat->tx_queues_to_use = CHANNEL_NUM;
+
+		/* Only channel 0 supports checksum,
+		 * so turn off checksum to enable multiple channels.
+		 */
+		for (i = 1; i < CHANNEL_NUM; i++)
+			plat->tx_queues_cfg[i].coe_unsupported = 1;
+	} else {
+		plat->tx_queues_to_use = 1;
+		plat->rx_queues_to_use = 1;
+	}
+
+	plat->phy_interface = PHY_INTERFACE_MODE_GMII;
+	plat->mdio_bus_data->phy_mask = ~(u32)BIT(2);
+	plat->fix_mac_speed = loongson_gnet_fix_speed;
+
+	return 0;
+}
+
+static struct stmmac_pci_info loongson_gnet_pci_info = {
+	.setup = loongson_gnet_data,
+};
+
 static void loongson_dwmac_dma_init_channel(struct stmmac_priv *priv,
 					    void __iomem *ioaddr,
 					    struct stmmac_dma_cfg *dma_cfg,
@@ -279,8 +335,10 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 	struct mac_device_info *mac;
 	struct stmmac_dma_ops *dma;
 	struct loongson_data *ld;
+	struct pci_dev *pdev;
 
 	ld = priv->plat->bsp_priv;
+	pdev = to_pci_dev(priv->device);
 
 	mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL);
 	if (!mac)
@@ -290,7 +348,7 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 	if (!dma)
 		return NULL;
 
-	/* The Loongson GMAC devices are based on the DW GMAC
+	/* The Loongson GMAC and GNET devices are based on the DW GMAC
 	 * v3.50a and v3.73a IP-cores. But the HW designers have changed the
 	 * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the
 	 * network controllers with the multi-channels feature
@@ -319,8 +377,19 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv)
 	if (mac->multicast_filter_bins)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
-	/* Loongson GMAC doesn't support the flow control. */
-	mac->link.caps = MAC_10 | MAC_100 | MAC_1000;
+	/* Loongson GMAC doesn't support the flow control. LS2K2000
+	 * GNET doesn't support the half-duplex link mode.
+	 */
+	if (pdev->device == PCI_DEVICE_ID_LOONGSON_GMAC) {
+		mac->link.caps = MAC_10 | MAC_100 | MAC_1000;
+	} else {
+		if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN)
+			mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+					 MAC_10 | MAC_100 | MAC_1000;
+		else
+			mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
+					 MAC_10FD | MAC_100FD | MAC_1000FD;
+	}
 
 	mac->link.duplex = GMAC_CONTROL_DM;
 	mac->link.speed10 = GMAC_CONTROL_PS;
@@ -497,6 +566,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 
 	plat->bsp_priv = ld;
 	plat->setup = loongson_dwmac_setup;
+	ld->dev = &pdev->dev;
 	ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff;
 
 	info = (struct stmmac_pci_info *)id->driver_data;
@@ -597,6 +667,7 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend,
 
 static const struct pci_device_id loongson_dwmac_id_table[] = {
 	{ PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) },
+	{ PCI_DEVICE_DATA(LOONGSON, GNET, &loongson_gnet_pci_info) },
 	{}
 };
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
-- 
cgit v1.3-3-g829e


From 930df0990d06244c3baf43f295e3f3abbc075036 Mon Sep 17 00:00:00 2001
From: Yanteng Si <siyanteng@loongson.cn>
Date: Wed, 7 Aug 2024 21:48:56 +0800
Subject: net: stmmac: dwmac-loongson: Add loongson module author

Add Yanteng Si as MODULE_AUTHOR of Loongson DWMAC PCI driver.

Signed-off-by: Feiyang Chen <chenfeiyang@loongson.cn>
Signed-off-by: Yinggang Gu <guyinggang@loongson.cn>
Acked-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Yanteng Si <siyanteng@loongson.cn>
Tested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 949e349ef856..bfe6e2d631bd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -686,4 +686,5 @@ module_pci_driver(loongson_dwmac_driver);
 
 MODULE_DESCRIPTION("Loongson DWMAC PCI driver");
 MODULE_AUTHOR("Qing Zhang <zhangqing@loongson.cn>");
+MODULE_AUTHOR("Yanteng Si <siyanteng@loongson.cn>");
 MODULE_LICENSE("GPL v2");
-- 
cgit v1.3-3-g829e


From 1ef33652d22c69a2a7519d003cd6c79b8e514f44 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Aug 2024 05:25:07 -0700
Subject: net: netpoll: extract core of netpoll_cleanup

Extract the core part of netpoll_cleanup(), so, it could be called from
a caller that has the rtnl lock already.

Netconsole uses this in a weird way right now:

	__netpoll_cleanup(&nt->np);
	spin_lock_irqsave(&target_list_lock, flags);
	netdev_put(nt->np.dev, &nt->np.dev_tracker);
	nt->np.dev = NULL;
	nt->enabled = false;

This will be replaced by do_netpoll_cleanup() as the locking situation
is overhauled.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netpoll.h |  1 +
 net/core/netpoll.c      | 12 +++++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index bd19c4b91e31..cd4e28db0cbd 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -64,6 +64,7 @@ int netpoll_setup(struct netpoll *np);
 void __netpoll_cleanup(struct netpoll *np);
 void __netpoll_free(struct netpoll *np);
 void netpoll_cleanup(struct netpoll *np);
+void do_netpoll_cleanup(struct netpoll *np);
 netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb);
 
 #ifdef CONFIG_NETPOLL
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 55bcacf67df3..a58ea724790c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -853,14 +853,20 @@ void __netpoll_free(struct netpoll *np)
 }
 EXPORT_SYMBOL_GPL(__netpoll_free);
 
+void do_netpoll_cleanup(struct netpoll *np)
+{
+	__netpoll_cleanup(np);
+	netdev_put(np->dev, &np->dev_tracker);
+	np->dev = NULL;
+}
+EXPORT_SYMBOL(do_netpoll_cleanup);
+
 void netpoll_cleanup(struct netpoll *np)
 {
 	rtnl_lock();
 	if (!np->dev)
 		goto out;
-	__netpoll_cleanup(np);
-	netdev_put(np->dev, &np->dev_tracker);
-	np->dev = NULL;
+	do_netpoll_cleanup(np);
 out:
 	rtnl_unlock();
 }
-- 
cgit v1.3-3-g829e


From e0a2b7e4a0f926948e7ade15cea5a43038dd790c Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Aug 2024 05:25:08 -0700
Subject: net: netconsole: Correct mismatched return types

netconsole incorrectly mixes int and ssize_t types by using int for
return variables in functions that should return ssize_t.

This is fixed by updating the return variables to the appropriate
ssize_t type, ensuring consistency across the function definitions.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index ffedf7648bed..b4d2ef109e31 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -336,7 +336,7 @@ static ssize_t enabled_store(struct config_item *item,
 	struct netconsole_target *nt = to_target(item);
 	unsigned long flags;
 	bool enabled;
-	int err;
+	ssize_t err;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	err = kstrtobool(buf, &enabled);
@@ -394,7 +394,7 @@ static ssize_t release_store(struct config_item *item, const char *buf,
 {
 	struct netconsole_target *nt = to_target(item);
 	bool release;
-	int err;
+	ssize_t err;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -422,7 +422,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf,
 {
 	struct netconsole_target *nt = to_target(item);
 	bool extended;
-	int err;
+	ssize_t err;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -469,7 +469,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf,
 		size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
-	int rv = -EINVAL;
+	ssize_t rv = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -492,7 +492,7 @@ static ssize_t remote_port_store(struct config_item *item,
 		const char *buf, size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
-	int rv = -EINVAL;
+	ssize_t rv = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -685,7 +685,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf,
 	struct userdatum *udm = to_userdatum(item);
 	struct netconsole_target *nt;
 	struct userdata *ud;
-	int ret;
+	ssize_t ret;
 
 	if (count > MAX_USERDATA_VALUE_LENGTH)
 		return -EMSGSIZE;
-- 
cgit v1.3-3-g829e


From 5c4a39e8a608a0f0afa2710f469432e5bfce4562 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Aug 2024 05:25:09 -0700
Subject: net: netconsole: Standardize variable naming

Update variable names from err to ret in cases where the variable may
return non-error values.

This change facilitates a forthcoming patch that relies on ret being
used consistently to handle return values, regardless of whether they
indicate an error or not.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 50 ++++++++++++++++++++++++------------------------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index b4d2ef109e31..0e43b5088bbb 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -336,14 +336,14 @@ static ssize_t enabled_store(struct config_item *item,
 	struct netconsole_target *nt = to_target(item);
 	unsigned long flags;
 	bool enabled;
-	ssize_t err;
+	ssize_t ret;
 
 	mutex_lock(&dynamic_netconsole_mutex);
-	err = kstrtobool(buf, &enabled);
-	if (err)
+	ret = kstrtobool(buf, &enabled);
+	if (ret)
 		goto out_unlock;
 
-	err = -EINVAL;
+	ret = -EINVAL;
 	if (enabled == nt->enabled) {
 		pr_info("network logging has already %s\n",
 			nt->enabled ? "started" : "stopped");
@@ -365,8 +365,8 @@ static ssize_t enabled_store(struct config_item *item,
 		 */
 		netpoll_print_options(&nt->np);
 
-		err = netpoll_setup(&nt->np);
-		if (err)
+		ret = netpoll_setup(&nt->np);
+		if (ret)
 			goto out_unlock;
 
 		nt->enabled = true;
@@ -386,7 +386,7 @@ static ssize_t enabled_store(struct config_item *item,
 	return strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return err;
+	return ret;
 }
 
 static ssize_t release_store(struct config_item *item, const char *buf,
@@ -394,18 +394,18 @@ static ssize_t release_store(struct config_item *item, const char *buf,
 {
 	struct netconsole_target *nt = to_target(item);
 	bool release;
-	ssize_t err;
+	ssize_t ret;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
 		pr_err("target (%s) is enabled, disable to update parameters\n",
 		       config_item_name(&nt->group.cg_item));
-		err = -EINVAL;
+		ret = -EINVAL;
 		goto out_unlock;
 	}
 
-	err = kstrtobool(buf, &release);
-	if (err)
+	ret = kstrtobool(buf, &release);
+	if (ret)
 		goto out_unlock;
 
 	nt->release = release;
@@ -414,7 +414,7 @@ static ssize_t release_store(struct config_item *item, const char *buf,
 	return strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return err;
+	return ret;
 }
 
 static ssize_t extended_store(struct config_item *item, const char *buf,
@@ -422,18 +422,18 @@ static ssize_t extended_store(struct config_item *item, const char *buf,
 {
 	struct netconsole_target *nt = to_target(item);
 	bool extended;
-	ssize_t err;
+	ssize_t ret;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
 		pr_err("target (%s) is enabled, disable to update parameters\n",
 		       config_item_name(&nt->group.cg_item));
-		err = -EINVAL;
+		ret = -EINVAL;
 		goto out_unlock;
 	}
 
-	err = kstrtobool(buf, &extended);
-	if (err)
+	ret = kstrtobool(buf, &extended);
+	if (ret)
 		goto out_unlock;
 
 	nt->extended = extended;
@@ -442,7 +442,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf,
 	return strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return err;
+	return ret;
 }
 
 static ssize_t dev_name_store(struct config_item *item, const char *buf,
@@ -469,7 +469,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf,
 		size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
-	ssize_t rv = -EINVAL;
+	ssize_t ret = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -478,21 +478,21 @@ static ssize_t local_port_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 	}
 
-	rv = kstrtou16(buf, 10, &nt->np.local_port);
-	if (rv < 0)
+	ret = kstrtou16(buf, 10, &nt->np.local_port);
+	if (ret < 0)
 		goto out_unlock;
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return rv;
+	return ret;
 }
 
 static ssize_t remote_port_store(struct config_item *item,
 		const char *buf, size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
-	ssize_t rv = -EINVAL;
+	ssize_t ret = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -501,14 +501,14 @@ static ssize_t remote_port_store(struct config_item *item,
 		goto out_unlock;
 	}
 
-	rv = kstrtou16(buf, 10, &nt->np.remote_port);
-	if (rv < 0)
+	ret = kstrtou16(buf, 10, &nt->np.remote_port);
+	if (ret < 0)
 		goto out_unlock;
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return rv;
+	return ret;
 }
 
 static ssize_t local_ip_store(struct config_item *item, const char *buf,
-- 
cgit v1.3-3-g829e


From f2ab4c1a9288774b1f9c102f0cb1b478965169bb Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Aug 2024 05:25:10 -0700
Subject: net: netconsole: Unify Function Return Paths

The return flow in netconsole's dynamic functions is currently
inconsistent. This patch aims to streamline and standardize the process
by ensuring that the mutex is unlocked before returning the ret value.

Additionally, this update includes a minor functional change where
certain strnlen() operations are performed with the
dynamic_netconsole_mutex locked. This adjustment is not anticipated to
cause any issues, however, it is crucial to document this change for
clarity.

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 38 +++++++++++++++-----------------------
 1 file changed, 15 insertions(+), 23 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 0e43b5088bbb..69eeab4a1e26 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -382,8 +382,7 @@ static ssize_t enabled_store(struct config_item *item,
 		netpoll_cleanup(&nt->np);
 	}
 
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
@@ -410,8 +409,7 @@ static ssize_t release_store(struct config_item *item, const char *buf,
 
 	nt->release = release;
 
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
@@ -437,9 +435,7 @@ static ssize_t extended_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 
 	nt->extended = extended;
-
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
@@ -481,8 +477,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf,
 	ret = kstrtou16(buf, 10, &nt->np.local_port);
 	if (ret < 0)
 		goto out_unlock;
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
@@ -504,8 +499,7 @@ static ssize_t remote_port_store(struct config_item *item,
 	ret = kstrtou16(buf, 10, &nt->np.remote_port);
 	if (ret < 0)
 		goto out_unlock;
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
@@ -515,6 +509,7 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf,
 		size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
+	ssize_t ret = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -541,17 +536,17 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf,
 			goto out_unlock;
 	}
 
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return -EINVAL;
+	return ret;
 }
 
 static ssize_t remote_ip_store(struct config_item *item, const char *buf,
 	       size_t count)
 {
 	struct netconsole_target *nt = to_target(item);
+	ssize_t ret = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -578,11 +573,10 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf,
 			goto out_unlock;
 	}
 
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return -EINVAL;
+	return ret;
 }
 
 static ssize_t remote_mac_store(struct config_item *item, const char *buf,
@@ -590,6 +584,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf,
 {
 	struct netconsole_target *nt = to_target(item);
 	u8 remote_mac[ETH_ALEN];
+	ssize_t ret = -EINVAL;
 
 	mutex_lock(&dynamic_netconsole_mutex);
 	if (nt->enabled) {
@@ -604,11 +599,10 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf,
 		goto out_unlock;
 	memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN);
 
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return strnlen(buf, count);
+	ret = strnlen(buf, count);
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
-	return -EINVAL;
+	return ret;
 }
 
 struct userdatum {
@@ -700,9 +694,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf,
 	ud = to_userdata(item->ci_parent);
 	nt = userdata_to_target(ud);
 	update_userdata(nt);
-
-	mutex_unlock(&dynamic_netconsole_mutex);
-	return count;
+	ret = count;
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
-- 
cgit v1.3-3-g829e


From 97714695ef904a4bdba75ca2f339215c0ae2b1fa Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 8 Aug 2024 05:25:11 -0700
Subject: net: netconsole: Defer netpoll cleanup to avoid lock release during
 list traversal

Current issue:
- The `target_list_lock` spinlock is held while iterating over
  target_list() entries.
- Mid-loop, the lock is released to call __netpoll_cleanup(), then
  reacquired.
- This practice compromises the protection provided by
  `target_list_lock`.

Reason for current design:
1. __netpoll_cleanup() may sleep, incompatible with holding a spinlock.
2. target_list_lock must be a spinlock because write_msg() cannot sleep.
   (See commit b5427c27173e ("[NET] netconsole: Support multiple logging
    targets"))

Defer the cleanup of the netpoll structure to outside the
target_list_lock() protected area. Create another list
(target_cleanup_list) to hold the entries that need to be cleaned up,
and clean them using a mutex (target_cleanup_list_lock).

Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 83 ++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 67 insertions(+), 16 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 69eeab4a1e26..43c29b15adbf 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -37,6 +37,7 @@
 #include <linux/configfs.h>
 #include <linux/etherdevice.h>
 #include <linux/utsname.h>
+#include <linux/rtnetlink.h>
 
 MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>");
 MODULE_DESCRIPTION("Console driver for network interfaces");
@@ -72,9 +73,16 @@ __setup("netconsole=", option_setup);
 
 /* Linked list of all configured targets */
 static LIST_HEAD(target_list);
+/* target_cleanup_list is used to track targets that need to be cleaned outside
+ * of target_list_lock. It should be cleaned in the same function it is
+ * populated.
+ */
+static LIST_HEAD(target_cleanup_list);
 
 /* This needs to be a spinlock because write_msg() cannot sleep */
 static DEFINE_SPINLOCK(target_list_lock);
+/* This needs to be a mutex because netpoll_cleanup might sleep */
+static DEFINE_MUTEX(target_cleanup_list_lock);
 
 /*
  * Console driver for extended netconsoles.  Registered on the first use to
@@ -210,6 +218,33 @@ static struct netconsole_target *alloc_and_init(void)
 	return nt;
 }
 
+/* Clean up every target in the cleanup_list and move the clean targets back to
+ * the main target_list.
+ */
+static void netconsole_process_cleanups_core(void)
+{
+	struct netconsole_target *nt, *tmp;
+	unsigned long flags;
+
+	/* The cleanup needs RTNL locked */
+	ASSERT_RTNL();
+
+	mutex_lock(&target_cleanup_list_lock);
+	list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) {
+		/* all entries in the cleanup_list needs to be disabled */
+		WARN_ON_ONCE(nt->enabled);
+		do_netpoll_cleanup(&nt->np);
+		/* moved the cleaned target to target_list. Need to hold both
+		 * locks
+		 */
+		spin_lock_irqsave(&target_list_lock, flags);
+		list_move(&nt->list, &target_list);
+		spin_unlock_irqrestore(&target_list_lock, flags);
+	}
+	WARN_ON_ONCE(!list_empty(&target_cleanup_list));
+	mutex_unlock(&target_cleanup_list_lock);
+}
+
 #ifdef	CONFIG_NETCONSOLE_DYNAMIC
 
 /*
@@ -246,6 +281,19 @@ static struct netconsole_target *to_target(struct config_item *item)
 			    struct netconsole_target, group);
 }
 
+/* Do the list cleanup with the rtnl lock hold.  rtnl lock is necessary because
+ * netdev might be cleaned-up by calling __netpoll_cleanup(),
+ */
+static void netconsole_process_cleanups(void)
+{
+	/* rtnl lock is called here, because it has precedence over
+	 * target_cleanup_list_lock mutex and target_cleanup_list
+	 */
+	rtnl_lock();
+	netconsole_process_cleanups_core();
+	rtnl_unlock();
+}
+
 /* Get rid of possible trailing newline, returning the new length */
 static void trim_newline(char *s, size_t maxlen)
 {
@@ -376,13 +424,20 @@ static ssize_t enabled_store(struct config_item *item,
 		 * otherwise we might end up in write_msg() with
 		 * nt->np.dev == NULL and nt->enabled == true
 		 */
+		mutex_lock(&target_cleanup_list_lock);
 		spin_lock_irqsave(&target_list_lock, flags);
 		nt->enabled = false;
+		/* Remove the target from the list, while holding
+		 * target_list_lock
+		 */
+		list_move(&nt->list, &target_cleanup_list);
 		spin_unlock_irqrestore(&target_list_lock, flags);
-		netpoll_cleanup(&nt->np);
+		mutex_unlock(&target_cleanup_list_lock);
 	}
 
 	ret = strnlen(buf, count);
+	/* Deferred cleanup */
+	netconsole_process_cleanups();
 out_unlock:
 	mutex_unlock(&dynamic_netconsole_mutex);
 	return ret;
@@ -942,7 +997,7 @@ static int netconsole_netdev_event(struct notifier_block *this,
 				   unsigned long event, void *ptr)
 {
 	unsigned long flags;
-	struct netconsole_target *nt;
+	struct netconsole_target *nt, *tmp;
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	bool stopped = false;
 
@@ -950,9 +1005,9 @@ static int netconsole_netdev_event(struct notifier_block *this,
 	      event == NETDEV_RELEASE || event == NETDEV_JOIN))
 		goto done;
 
+	mutex_lock(&target_cleanup_list_lock);
 	spin_lock_irqsave(&target_list_lock, flags);
-restart:
-	list_for_each_entry(nt, &target_list, list) {
+	list_for_each_entry_safe(nt, tmp, &target_list, list) {
 		netconsole_target_get(nt);
 		if (nt->np.dev == dev) {
 			switch (event) {
@@ -962,25 +1017,16 @@ restart:
 			case NETDEV_RELEASE:
 			case NETDEV_JOIN:
 			case NETDEV_UNREGISTER:
-				/* rtnl_lock already held
-				 * we might sleep in __netpoll_cleanup()
-				 */
 				nt->enabled = false;
-				spin_unlock_irqrestore(&target_list_lock, flags);
-
-				__netpoll_cleanup(&nt->np);
-
-				spin_lock_irqsave(&target_list_lock, flags);
-				netdev_put(nt->np.dev, &nt->np.dev_tracker);
-				nt->np.dev = NULL;
+				list_move(&nt->list, &target_cleanup_list);
 				stopped = true;
-				netconsole_target_put(nt);
-				goto restart;
 			}
 		}
 		netconsole_target_put(nt);
 	}
 	spin_unlock_irqrestore(&target_list_lock, flags);
+	mutex_unlock(&target_cleanup_list_lock);
+
 	if (stopped) {
 		const char *msg = "had an event";
 
@@ -999,6 +1045,11 @@ restart:
 			dev->name, msg);
 	}
 
+	/* Process target_cleanup_list entries. By the end, target_cleanup_list
+	 * should be empty
+	 */
+	netconsole_process_cleanups_core();
+
 done:
 	return NOTIFY_DONE;
 }
-- 
cgit v1.3-3-g829e


From 748e21d94a34edc6e74e9ec674e93e570d3d0d3e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 8 Aug 2024 16:11:15 -0600
Subject: wifi: mwl8k: Use static_assert() to check struct sizes

Commit 5c4250092fad ("wifi: mwl8k: Avoid -Wflex-array-member-not-at-end
warnings") introduced tagged `struct mwl8k_cmd_pkt_hdr`. We want to
ensure that when new members need to be added to the flexible structure,
they are always included within this tagged struct.

We use `static_assert()` to ensure that the memory layout for both
the flexible structure and the tagged struct is the same after any
changes.

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/ZrVCg51Q9M2fTPaF@cute
---
 drivers/net/wireless/marvell/mwl8k.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c
index b130e057370f..bab9ef37a1ab 100644
--- a/drivers/net/wireless/marvell/mwl8k.c
+++ b/drivers/net/wireless/marvell/mwl8k.c
@@ -587,6 +587,7 @@ static int mwl8k_request_firmware(struct mwl8k_priv *priv, char *fw_image,
 }
 
 struct mwl8k_cmd_pkt {
+	/* New members MUST be added within the __struct_group() macro below. */
 	__struct_group(mwl8k_cmd_pkt_hdr, hdr, __packed,
 		__le16	code;
 		__le16	length;
@@ -596,6 +597,8 @@ struct mwl8k_cmd_pkt {
 	);
 	char payload[];
 } __packed;
+static_assert(offsetof(struct mwl8k_cmd_pkt, payload) == sizeof(struct mwl8k_cmd_pkt_hdr),
+	      "struct member likely outside of __struct_group()");
 
 /*
  * Firmware loading.
-- 
cgit v1.3-3-g829e


From dd1bf9f9df156b43e5122f90d97ac3f59a1a5621 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 8 Aug 2024 21:49:51 -0700
Subject: net: hinic: use ethtool_sprintf/puts

Simpler and avoids manual pointer addition.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240809044957.4534-1-rosenp@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 33 +++++++----------------
 1 file changed, 10 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
index 0304f03d4093..c559dd4291d3 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c
@@ -1471,7 +1471,6 @@ static void hinic_get_strings(struct net_device *netdev,
 			      u32 stringset, u8 *data)
 {
 	struct hinic_dev *nic_dev = netdev_priv(netdev);
-	char *p = (char *)data;
 	u16 i, j;
 
 	switch (stringset) {
@@ -1479,31 +1478,19 @@ static void hinic_get_strings(struct net_device *netdev,
 		memcpy(data, *hinic_test_strings, sizeof(hinic_test_strings));
 		return;
 	case ETH_SS_STATS:
-		for (i = 0; i < ARRAY_SIZE(hinic_function_stats); i++) {
-			memcpy(p, hinic_function_stats[i].name,
-			       ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
+		for (i = 0; i < ARRAY_SIZE(hinic_function_stats); i++)
+			ethtool_puts(&data, hinic_function_stats[i].name);
 
-		for (i = 0; i < ARRAY_SIZE(hinic_port_stats); i++) {
-			memcpy(p, hinic_port_stats[i].name,
-			       ETH_GSTRING_LEN);
-			p += ETH_GSTRING_LEN;
-		}
+		for (i = 0; i < ARRAY_SIZE(hinic_port_stats); i++)
+			ethtool_puts(&data, hinic_port_stats[i].name);
 
-		for (i = 0; i < nic_dev->num_qps; i++) {
-			for (j = 0; j < ARRAY_SIZE(hinic_tx_queue_stats); j++) {
-				sprintf(p, hinic_tx_queue_stats[j].name, i);
-				p += ETH_GSTRING_LEN;
-			}
-		}
+		for (i = 0; i < nic_dev->num_qps; i++)
+			for (j = 0; j < ARRAY_SIZE(hinic_tx_queue_stats); j++)
+				ethtool_sprintf(&data, hinic_tx_queue_stats[j].name, i);
 
-		for (i = 0; i < nic_dev->num_qps; i++) {
-			for (j = 0; j < ARRAY_SIZE(hinic_rx_queue_stats); j++) {
-				sprintf(p, hinic_rx_queue_stats[j].name, i);
-				p += ETH_GSTRING_LEN;
-			}
-		}
+		for (i = 0; i < nic_dev->num_qps; i++)
+			for (j = 0; j < ARRAY_SIZE(hinic_rx_queue_stats); j++)
+				ethtool_sprintf(&data, hinic_rx_queue_stats[j].name, i);
 
 		return;
 	default:
-- 
cgit v1.3-3-g829e


From 86ff3d79a0ee72b7662ef1cc712ba85336b77c30 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:07:57 -0600
Subject: ice: add parser create and destroy skeleton

Add new parser module which can parse a packet in binary and generate
information like ptype, protocol/offset pairs and flags which can be later
used to feed the FXP profile creation directly.

Add skeleton of the create and destroy APIs:
ice_parser_create()
ice_parser_destroy()

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Co-developed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile     |  1 +
 drivers/net/ethernet/intel/ice/ice_common.h |  1 +
 drivers/net/ethernet/intel/ice/ice_parser.c | 32 +++++++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_parser.h | 13 ++++++++++++
 4 files changed, 47 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_parser.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_parser.h

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 03500e28ac99..23fa3f7f36ef 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -28,6 +28,7 @@ ice-y := ice_main.o	\
 	 ice_vlan_mode.o \
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
+	 ice_parser.o    \
 	 ice_idc.o	\
 	 devlink/devlink.o	\
 	 devlink/devlink_port.o \
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 66f29bac783a..27208a60cece 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -10,6 +10,7 @@
 #include "ice_type.h"
 #include "ice_nvm.h"
 #include "ice_flex_pipe.h"
+#include "ice_parser.h"
 #include <linux/avf/virtchnl.h>
 #include "ice_switch.h"
 #include "ice_fdir.h"
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
new file mode 100644
index 000000000000..6c50164efae0
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "ice_common.h"
+
+/**
+ * ice_parser_create - create a parser instance
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated parser instance or ERR_PTR
+ * in case of error.
+ */
+struct ice_parser *ice_parser_create(struct ice_hw *hw)
+{
+	struct ice_parser *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	p->hw = hw;
+	return p;
+}
+
+/**
+ * ice_parser_destroy - destroy a parser instance
+ * @psr: pointer to a parser instance
+ */
+void ice_parser_destroy(struct ice_parser *psr)
+{
+	kfree(psr);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
new file mode 100644
index 000000000000..09ed380eee32
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef _ICE_PARSER_H_
+#define _ICE_PARSER_H_
+
+struct ice_parser {
+	struct ice_hw *hw; /* pointer to the hardware structure */
+};
+
+struct ice_parser *ice_parser_create(struct ice_hw *hw);
+void ice_parser_destroy(struct ice_parser *psr);
+#endif /* _ICE_PARSER_H_ */
-- 
cgit v1.3-3-g829e


From 75b4a938a947785cdda8908cb700c58e95f8ff69 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:07:58 -0600
Subject: ice: parse and init various DDP parser sections

Parse the following DDP sections:
 - ICE_SID_RXPARSER_IMEM into an array of struct ice_imem_item
 - ICE_SID_RXPARSER_METADATA_INIT into an array of struct ice_metainit_item
 - ICE_SID_RXPARSER_CAM or ICE_SID_RXPARSER_PG_SPILL into an array of
   struct ice_pg_cam_item
 - ICE_SID_RXPARSER_NOMATCH_CAM or ICE_SID_RXPARSER_NOMATCH_SPILL into an
   array of struct ice_pg_nm_cam_item
 - ICE_SID_RXPARSER_CAM into an array of ice_bst_tcam_item
 - ICE_SID_LBL_RXPARSER_TMEM into an array of ice_lbl_item
 - ICE_SID_RXPARSER_MARKER_PTYPE into an array of ice_ptype_mk_tcam_item
 - ICE_SID_RXPARSER_MARKER_GRP into an array of ice_mk_grp_item
 - ICE_SID_RXPARSER_PROTO_GRP into an array of ice_proto_grp_item
 - ICE_SID_RXPARSER_FLAG_REDIR into an array of ice_flg_rd_item
 - ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL,
   ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS into
   struct ice_xlt_kb

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Co-developed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ddp.c    |   10 +-
 drivers/net/ethernet/intel/ice/ice_ddp.h    |   13 +
 drivers/net/ethernet/intel/ice/ice_parser.c | 1383 +++++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_parser.h |  358 +++++++
 drivers/net/ethernet/intel/ice/ice_type.h   |    1 +
 5 files changed, 1760 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index f182179529b7..953262b88a58 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -289,11 +289,11 @@ void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
  * indicates a base offset of 10, and the index for the entry is 2, then
  * section handler function should set the offset to 10 + 2 = 12.
  */
-static void *ice_pkg_enum_entry(struct ice_seg *ice_seg,
-				struct ice_pkg_enum *state, u32 sect_type,
-				u32 *offset,
-				void *(*handler)(u32 sect_type, void *section,
-						 u32 index, u32 *offset))
+void *ice_pkg_enum_entry(struct ice_seg *ice_seg,
+			 struct ice_pkg_enum *state, u32 sect_type,
+			 u32 *offset,
+			 void *(*handler)(u32 sect_type, void *section,
+					  u32 index, u32 *offset))
 {
 	void *entry;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h
index 622543f08b43..97f272317475 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.h
@@ -261,10 +261,17 @@ struct ice_meta_sect {
 #define ICE_SID_CDID_KEY_BUILDER_RSS 47
 #define ICE_SID_CDID_REDIR_RSS 48
 
+#define ICE_SID_RXPARSER_CAM           50
+#define ICE_SID_RXPARSER_NOMATCH_CAM   51
+#define ICE_SID_RXPARSER_IMEM          52
 #define ICE_SID_RXPARSER_MARKER_PTYPE 55
 #define ICE_SID_RXPARSER_BOOST_TCAM 56
+#define ICE_SID_RXPARSER_PROTO_GRP     57
 #define ICE_SID_RXPARSER_METADATA_INIT 58
 #define ICE_SID_TXPARSER_BOOST_TCAM 66
+#define ICE_SID_RXPARSER_MARKER_GRP    72
+#define ICE_SID_RXPARSER_PG_SPILL      76
+#define ICE_SID_RXPARSER_NOMATCH_SPILL 78
 
 #define ICE_SID_XLT0_PE 80
 #define ICE_SID_XLT_KEY_BUILDER_PE 81
@@ -276,6 +283,7 @@ struct ice_meta_sect {
 #define ICE_SID_CDID_KEY_BUILDER_PE 87
 #define ICE_SID_CDID_REDIR_PE 88
 
+#define ICE_SID_RXPARSER_FLAG_REDIR	97
 /* Label Metadata section IDs */
 #define ICE_SID_LBL_FIRST 0x80000010
 #define ICE_SID_LBL_RXPARSER_TMEM 0x80000018
@@ -451,6 +459,11 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count);
 
 int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count);
 u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld);
+void *
+ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
+		   u32 sect_type, u32 *offset,
+		   void *(*handler)(u32 sect_type, void *section,
+				    u32 index, u32 *offset));
 void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state,
 			   u32 sect_type);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index 6c50164efae0..5fdc87034fc6 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -3,6 +3,1271 @@
 
 #include "ice_common.h"
 
+struct ice_pkg_sect_hdr {
+	__le16 count;
+	__le16 offset;
+};
+
+/**
+ * ice_parser_sect_item_get - parse an item from a section
+ * @sect_type: section type
+ * @section: section object
+ * @index: index of the item to get
+ * @offset: dummy as prototype of ice_pkg_enum_entry's last parameter
+ *
+ * Return: a pointer to the item or NULL.
+ */
+static void *ice_parser_sect_item_get(u32 sect_type, void *section,
+				      u32 index, u32 __maybe_unused *offset)
+{
+	size_t data_off = ICE_SEC_DATA_OFFSET;
+	struct ice_pkg_sect_hdr *hdr;
+	size_t size;
+
+	if (!section)
+		return NULL;
+
+	switch (sect_type) {
+	case ICE_SID_RXPARSER_IMEM:
+		size = ICE_SID_RXPARSER_IMEM_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_METADATA_INIT:
+		size = ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_CAM:
+		size = ICE_SID_RXPARSER_CAM_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_PG_SPILL:
+		size = ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_NOMATCH_CAM:
+		size = ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_NOMATCH_SPILL:
+		size = ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_BOOST_TCAM:
+		size = ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE;
+		break;
+	case ICE_SID_LBL_RXPARSER_TMEM:
+		data_off = ICE_SEC_LBL_DATA_OFFSET;
+		size = ICE_SID_LBL_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_MARKER_PTYPE:
+		size = ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_MARKER_GRP:
+		size = ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_PROTO_GRP:
+		size = ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE;
+		break;
+	case ICE_SID_RXPARSER_FLAG_REDIR:
+		size = ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE;
+		break;
+	default:
+		return NULL;
+	}
+
+	hdr = section;
+	if (index >= le16_to_cpu(hdr->count))
+		return NULL;
+
+	return section + data_off + index * size;
+}
+
+/**
+ * ice_parser_create_table - create an item table from a section
+ * @hw: pointer to the hardware structure
+ * @sect_type: section type
+ * @item_size: item size in bytes
+ * @length: number of items in the table to create
+ * @parse_item: the function to parse the item
+ * @no_offset: ignore header offset, calculate index from 0
+ *
+ * Return: a pointer to the allocated table or ERR_PTR.
+ */
+static void *
+ice_parser_create_table(struct ice_hw *hw, u32 sect_type,
+			u32 item_size, u32 length,
+			void (*parse_item)(struct ice_hw *hw, u16 idx,
+					   void *item, void *data,
+					   int size), bool no_offset)
+{
+	struct ice_pkg_enum state = {};
+	struct ice_seg *seg = hw->seg;
+	void *table, *data, *item;
+	u16 idx = 0;
+
+	if (!seg)
+		return ERR_PTR(-EINVAL);
+
+	table = kzalloc(item_size * length, GFP_KERNEL);
+	if (!table)
+		return ERR_PTR(-ENOMEM);
+
+	do {
+		data = ice_pkg_enum_entry(seg, &state, sect_type, NULL,
+					  ice_parser_sect_item_get);
+		seg = NULL;
+		if (data) {
+			struct ice_pkg_sect_hdr *hdr = state.sect;
+
+			if (!no_offset)
+				idx = le16_to_cpu(hdr->offset) +
+					state.entry_idx;
+
+			item = (void *)((uintptr_t)table + idx * item_size);
+			parse_item(hw, idx, item, data, item_size);
+
+			if (no_offset)
+				idx++;
+		}
+	} while (data);
+
+	return table;
+}
+
+/*** ICE_SID_RXPARSER_IMEM section ***/
+#define ICE_IM_BM_ALU0		BIT(0)
+#define ICE_IM_BM_ALU1		BIT(1)
+#define ICE_IM_BM_ALU2		BIT(2)
+#define ICE_IM_BM_PG		BIT(3)
+
+/**
+ * ice_imem_bm_init - parse 4 bits of Boost Main
+ * @bm: pointer to the Boost Main structure
+ * @data: Boost Main data to be parsed
+ */
+static void ice_imem_bm_init(struct ice_bst_main *bm, u8 data)
+{
+	bm->alu0	= FIELD_GET(ICE_IM_BM_ALU0, data);
+	bm->alu1	= FIELD_GET(ICE_IM_BM_ALU1, data);
+	bm->alu2	= FIELD_GET(ICE_IM_BM_ALU2, data);
+	bm->pg		= FIELD_GET(ICE_IM_BM_PG, data);
+}
+
+#define ICE_IM_BKB_PRIO		GENMASK(7, 0)
+#define ICE_IM_BKB_TSR_CTRL	BIT(8)
+
+/**
+ * ice_imem_bkb_init - parse 10 bits of Boost Main Build
+ * @bkb: pointer to the Boost Main Build structure
+ * @data: Boost Main Build data to be parsed
+ */
+static void ice_imem_bkb_init(struct ice_bst_keybuilder *bkb, u16 data)
+{
+	bkb->prio	= FIELD_GET(ICE_IM_BKB_PRIO, data);
+	bkb->tsr_ctrl	= FIELD_GET(ICE_IM_BKB_TSR_CTRL, data);
+}
+
+#define ICE_IM_NPKB_OPC		GENMASK(1, 0)
+#define ICE_IM_NPKB_S_R0	GENMASK(9, 2)
+#define ICE_IM_NPKB_L_R1	GENMASK(17, 10)
+
+/**
+ * ice_imem_npkb_init - parse 18 bits of Next Protocol Key Build
+ * @kb: pointer to the Next Protocol Key Build structure
+ * @data: Next Protocol Key Build data to be parsed
+ */
+static void ice_imem_npkb_init(struct ice_np_keybuilder *kb, u32 data)
+{
+	kb->opc		= FIELD_GET(ICE_IM_NPKB_OPC, data);
+	kb->start_reg0	= FIELD_GET(ICE_IM_NPKB_S_R0, data);
+	kb->len_reg1	= FIELD_GET(ICE_IM_NPKB_L_R1, data);
+}
+
+#define ICE_IM_PGKB_F0_ENA	BIT_ULL(0)
+#define ICE_IM_PGKB_F0_IDX	GENMASK_ULL(6, 1)
+#define ICE_IM_PGKB_F1_ENA	BIT_ULL(7)
+#define ICE_IM_PGKB_F1_IDX	GENMASK_ULL(13, 8)
+#define ICE_IM_PGKB_F2_ENA	BIT_ULL(14)
+#define ICE_IM_PGKB_F2_IDX	GENMASK_ULL(20, 15)
+#define ICE_IM_PGKB_F3_ENA	BIT_ULL(21)
+#define ICE_IM_PGKB_F3_IDX	GENMASK_ULL(27, 22)
+#define ICE_IM_PGKB_AR_IDX	GENMASK_ULL(34, 28)
+
+/**
+ * ice_imem_pgkb_init - parse 35 bits of Parse Graph Key Build
+ * @kb: pointer to the Parse Graph Key Build structure
+ * @data: Parse Graph Key Build data to be parsed
+ */
+static void ice_imem_pgkb_init(struct ice_pg_keybuilder *kb, u64 data)
+{
+	kb->flag0_ena	= FIELD_GET(ICE_IM_PGKB_F0_ENA, data);
+	kb->flag0_idx	= FIELD_GET(ICE_IM_PGKB_F0_IDX, data);
+	kb->flag1_ena	= FIELD_GET(ICE_IM_PGKB_F1_ENA, data);
+	kb->flag1_idx	= FIELD_GET(ICE_IM_PGKB_F1_IDX, data);
+	kb->flag2_ena	= FIELD_GET(ICE_IM_PGKB_F2_ENA, data);
+	kb->flag2_idx	= FIELD_GET(ICE_IM_PGKB_F2_IDX, data);
+	kb->flag3_ena	= FIELD_GET(ICE_IM_PGKB_F3_ENA, data);
+	kb->flag3_idx	= FIELD_GET(ICE_IM_PGKB_F3_IDX, data);
+	kb->alu_reg_idx	= FIELD_GET(ICE_IM_PGKB_AR_IDX, data);
+}
+
+#define ICE_IM_ALU_OPC		GENMASK_ULL(5, 0)
+#define ICE_IM_ALU_SS		GENMASK_ULL(13, 6)
+#define ICE_IM_ALU_SL		GENMASK_ULL(18, 14)
+#define ICE_IM_ALU_SXS		BIT_ULL(19)
+#define ICE_IM_ALU_SXK		GENMASK_ULL(23, 20)
+#define ICE_IM_ALU_SRID		GENMASK_ULL(30, 24)
+#define ICE_IM_ALU_DRID		GENMASK_ULL(37, 31)
+#define ICE_IM_ALU_INC0		BIT_ULL(38)
+#define ICE_IM_ALU_INC1		BIT_ULL(39)
+#define ICE_IM_ALU_POO		GENMASK_ULL(41, 40)
+#define ICE_IM_ALU_PO		GENMASK_ULL(49, 42)
+#define ICE_IM_ALU_BA_S		50	/* offset for the 2nd 64-bits field */
+#define ICE_IM_ALU_BA		GENMASK_ULL(57 - ICE_IM_ALU_BA_S, \
+					    50 - ICE_IM_ALU_BA_S)
+#define ICE_IM_ALU_IMM		GENMASK_ULL(73 - ICE_IM_ALU_BA_S, \
+					    58 - ICE_IM_ALU_BA_S)
+#define ICE_IM_ALU_DFE		BIT_ULL(74 - ICE_IM_ALU_BA_S)
+#define ICE_IM_ALU_DS		GENMASK_ULL(80 - ICE_IM_ALU_BA_S, \
+					    75 - ICE_IM_ALU_BA_S)
+#define ICE_IM_ALU_DL		GENMASK_ULL(86 - ICE_IM_ALU_BA_S, \
+					    81 - ICE_IM_ALU_BA_S)
+#define ICE_IM_ALU_FEI		BIT_ULL(87 - ICE_IM_ALU_BA_S)
+#define ICE_IM_ALU_FSI		GENMASK_ULL(95 - ICE_IM_ALU_BA_S, \
+					    88 - ICE_IM_ALU_BA_S)
+
+/**
+ * ice_imem_alu_init - parse 96 bits of ALU entry
+ * @alu: pointer to the ALU entry structure
+ * @data: ALU entry data to be parsed
+ * @off: offset of the ALU entry data
+ */
+static void ice_imem_alu_init(struct ice_alu *alu, u8 *data, u8 off)
+{
+	u64 d64;
+	u8 idd;
+
+	d64 = *((u64 *)data) >> off;
+
+	alu->opc		= FIELD_GET(ICE_IM_ALU_OPC, d64);
+	alu->src_start		= FIELD_GET(ICE_IM_ALU_SS, d64);
+	alu->src_len		= FIELD_GET(ICE_IM_ALU_SL, d64);
+	alu->shift_xlate_sel	= FIELD_GET(ICE_IM_ALU_SXS, d64);
+	alu->shift_xlate_key	= FIELD_GET(ICE_IM_ALU_SXK, d64);
+	alu->src_reg_id		= FIELD_GET(ICE_IM_ALU_SRID, d64);
+	alu->dst_reg_id		= FIELD_GET(ICE_IM_ALU_DRID, d64);
+	alu->inc0		= FIELD_GET(ICE_IM_ALU_INC0, d64);
+	alu->inc1		= FIELD_GET(ICE_IM_ALU_INC1, d64);
+	alu->proto_offset_opc	= FIELD_GET(ICE_IM_ALU_POO, d64);
+	alu->proto_offset	= FIELD_GET(ICE_IM_ALU_PO, d64);
+
+	idd = (ICE_IM_ALU_BA_S + off) / BITS_PER_BYTE;
+	off = (ICE_IM_ALU_BA_S + off) % BITS_PER_BYTE;
+	d64 = *((u64 *)(&data[idd])) >> off;
+
+	alu->branch_addr	= FIELD_GET(ICE_IM_ALU_BA, d64);
+	alu->imm		= FIELD_GET(ICE_IM_ALU_IMM, d64);
+	alu->dedicate_flags_ena	= FIELD_GET(ICE_IM_ALU_DFE, d64);
+	alu->dst_start		= FIELD_GET(ICE_IM_ALU_DS, d64);
+	alu->dst_len		= FIELD_GET(ICE_IM_ALU_DL, d64);
+	alu->flags_extr_imm	= FIELD_GET(ICE_IM_ALU_FEI, d64);
+	alu->flags_start_imm	= FIELD_GET(ICE_IM_ALU_FSI, d64);
+}
+
+#define ICE_IMEM_BM_S		0
+#define ICE_IMEM_BKB_S		4
+#define ICE_IMEM_BKB_IDD	(ICE_IMEM_BKB_S / BITS_PER_BYTE)
+#define ICE_IMEM_BKB_OFF	(ICE_IMEM_BKB_S % BITS_PER_BYTE)
+#define ICE_IMEM_PGP		GENMASK(15, 14)
+#define ICE_IMEM_NPKB_S		16
+#define ICE_IMEM_NPKB_IDD	(ICE_IMEM_NPKB_S / BITS_PER_BYTE)
+#define ICE_IMEM_NPKB_OFF	(ICE_IMEM_NPKB_S % BITS_PER_BYTE)
+#define ICE_IMEM_PGKB_S		34
+#define ICE_IMEM_PGKB_IDD	(ICE_IMEM_PGKB_S / BITS_PER_BYTE)
+#define ICE_IMEM_PGKB_OFF	(ICE_IMEM_PGKB_S % BITS_PER_BYTE)
+#define ICE_IMEM_ALU0_S		69
+#define ICE_IMEM_ALU0_IDD	(ICE_IMEM_ALU0_S / BITS_PER_BYTE)
+#define ICE_IMEM_ALU0_OFF	(ICE_IMEM_ALU0_S % BITS_PER_BYTE)
+#define ICE_IMEM_ALU1_S		165
+#define ICE_IMEM_ALU1_IDD	(ICE_IMEM_ALU1_S / BITS_PER_BYTE)
+#define ICE_IMEM_ALU1_OFF	(ICE_IMEM_ALU1_S % BITS_PER_BYTE)
+#define ICE_IMEM_ALU2_S		357
+#define ICE_IMEM_ALU2_IDD	(ICE_IMEM_ALU2_S / BITS_PER_BYTE)
+#define ICE_IMEM_ALU2_OFF	(ICE_IMEM_ALU2_S % BITS_PER_BYTE)
+
+/**
+ * ice_imem_parse_item - parse 384 bits of IMEM entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of IMEM entry
+ * @item: item of IMEM entry
+ * @data: IMEM entry data to be parsed
+ * @size: size of IMEM entry
+ */
+static void ice_imem_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				void *data, int __maybe_unused size)
+{
+	struct ice_imem_item *ii = item;
+	u8 *buf = data;
+
+	ii->idx = idx;
+
+	ice_imem_bm_init(&ii->b_m, *(u8 *)buf);
+	ice_imem_bkb_init(&ii->b_kb,
+			  *((u16 *)(&buf[ICE_IMEM_BKB_IDD])) >>
+			   ICE_IMEM_BKB_OFF);
+
+	ii->pg_prio = FIELD_GET(ICE_IMEM_PGP, *(u16 *)buf);
+
+	ice_imem_npkb_init(&ii->np_kb,
+			   *((u32 *)(&buf[ICE_IMEM_NPKB_IDD])) >>
+			    ICE_IMEM_NPKB_OFF);
+	ice_imem_pgkb_init(&ii->pg_kb,
+			   *((u64 *)(&buf[ICE_IMEM_PGKB_IDD])) >>
+			    ICE_IMEM_PGKB_OFF);
+
+	ice_imem_alu_init(&ii->alu0,
+			  &buf[ICE_IMEM_ALU0_IDD],
+			  ICE_IMEM_ALU0_OFF);
+	ice_imem_alu_init(&ii->alu1,
+			  &buf[ICE_IMEM_ALU1_IDD],
+			  ICE_IMEM_ALU1_OFF);
+	ice_imem_alu_init(&ii->alu2,
+			  &buf[ICE_IMEM_ALU2_IDD],
+			  ICE_IMEM_ALU2_OFF);
+}
+
+/**
+ * ice_imem_table_get - create an imem table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated IMEM table.
+ */
+static struct ice_imem_item *ice_imem_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_IMEM,
+				       sizeof(struct ice_imem_item),
+				       ICE_IMEM_TABLE_SIZE,
+				       ice_imem_parse_item, false);
+}
+
+/*** ICE_SID_RXPARSER_METADATA_INIT section ***/
+#define ICE_MI_TSR		GENMASK_ULL(7, 0)
+#define ICE_MI_HO		GENMASK_ULL(16, 8)
+#define ICE_MI_PC		GENMASK_ULL(24, 17)
+#define ICE_MI_PGRN		GENMASK_ULL(35, 25)
+#define ICE_MI_CD		GENMASK_ULL(38, 36)
+#define ICE_MI_GAC		BIT_ULL(39)
+#define ICE_MI_GADM		GENMASK_ULL(44, 40)
+#define ICE_MI_GADS		GENMASK_ULL(48, 45)
+#define ICE_MI_GADL		GENMASK_ULL(53, 49)
+#define ICE_MI_GAI		GENMASK_ULL(59, 56)
+#define ICE_MI_GBC		BIT_ULL(60)
+#define ICE_MI_GBDM_S		61	/* offset for the 2nd 64-bits field */
+#define ICE_MI_GBDM_IDD		(ICE_MI_GBDM_S / BITS_PER_BYTE)
+#define ICE_MI_GBDM_OFF		(ICE_MI_GBDM_S % BITS_PER_BYTE)
+
+#define ICE_MI_GBDM_GENMASK_ULL(high, low) \
+	GENMASK_ULL((high) - ICE_MI_GBDM_S, (low) - ICE_MI_GBDM_S)
+#define ICE_MI_GBDM		ICE_MI_GBDM_GENMASK_ULL(65, 61)
+#define ICE_MI_GBDS		ICE_MI_GBDM_GENMASK_ULL(69, 66)
+#define ICE_MI_GBDL		ICE_MI_GBDM_GENMASK_ULL(74, 70)
+#define ICE_MI_GBI		ICE_MI_GBDM_GENMASK_ULL(80, 77)
+#define ICE_MI_GCC		BIT_ULL(81 - ICE_MI_GBDM_S)
+#define ICE_MI_GCDM		ICE_MI_GBDM_GENMASK_ULL(86, 82)
+#define ICE_MI_GCDS		ICE_MI_GBDM_GENMASK_ULL(90, 87)
+#define ICE_MI_GCDL		ICE_MI_GBDM_GENMASK_ULL(95, 91)
+#define ICE_MI_GCI		ICE_MI_GBDM_GENMASK_ULL(101, 98)
+#define ICE_MI_GDC		BIT_ULL(102 - ICE_MI_GBDM_S)
+#define ICE_MI_GDDM		ICE_MI_GBDM_GENMASK_ULL(107, 103)
+#define ICE_MI_GDDS		ICE_MI_GBDM_GENMASK_ULL(111, 108)
+#define ICE_MI_GDDL		ICE_MI_GBDM_GENMASK_ULL(116, 112)
+#define ICE_MI_GDI		ICE_MI_GBDM_GENMASK_ULL(122, 119)
+#define ICE_MI_FLAG_S		123	/* offset for the 3rd 64-bits field */
+#define ICE_MI_FLAG_IDD		(ICE_MI_FLAG_S / BITS_PER_BYTE)
+#define ICE_MI_FLAG_OFF		(ICE_MI_FLAG_S % BITS_PER_BYTE)
+#define ICE_MI_FLAG		GENMASK_ULL(186 - ICE_MI_FLAG_S, \
+					    123 - ICE_MI_FLAG_S)
+
+/**
+ * ice_metainit_parse_item - parse 192 bits of Metadata Init entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Metadata Init entry
+ * @item: item of Metadata Init entry
+ * @data: Metadata Init entry data to be parsed
+ * @size: size of Metadata Init entry
+ */
+static void ice_metainit_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				    void *data, int __maybe_unused size)
+{
+	struct ice_metainit_item *mi = item;
+	u8 *buf = data;
+	u64 d64;
+
+	mi->idx = idx;
+
+	d64 = *(u64 *)buf;
+
+	mi->tsr			= FIELD_GET(ICE_MI_TSR, d64);
+	mi->ho			= FIELD_GET(ICE_MI_HO, d64);
+	mi->pc			= FIELD_GET(ICE_MI_PC, d64);
+	mi->pg_rn		= FIELD_GET(ICE_MI_PGRN, d64);
+	mi->cd			= FIELD_GET(ICE_MI_CD, d64);
+
+	mi->gpr_a_ctrl		= FIELD_GET(ICE_MI_GAC, d64);
+	mi->gpr_a_data_mdid	= FIELD_GET(ICE_MI_GADM, d64);
+	mi->gpr_a_data_start	= FIELD_GET(ICE_MI_GADS, d64);
+	mi->gpr_a_data_len	= FIELD_GET(ICE_MI_GADL, d64);
+	mi->gpr_a_id		= FIELD_GET(ICE_MI_GAI, d64);
+
+	mi->gpr_b_ctrl		= FIELD_GET(ICE_MI_GBC, d64);
+
+	d64 = *((u64 *)&buf[ICE_MI_GBDM_IDD]) >> ICE_MI_GBDM_OFF;
+
+	mi->gpr_b_data_mdid	= FIELD_GET(ICE_MI_GBDM, d64);
+	mi->gpr_b_data_start	= FIELD_GET(ICE_MI_GBDS, d64);
+	mi->gpr_b_data_len	= FIELD_GET(ICE_MI_GBDL, d64);
+	mi->gpr_b_id		= FIELD_GET(ICE_MI_GBI, d64);
+
+	mi->gpr_c_ctrl		= FIELD_GET(ICE_MI_GCC, d64);
+	mi->gpr_c_data_mdid	= FIELD_GET(ICE_MI_GCDM, d64);
+	mi->gpr_c_data_start	= FIELD_GET(ICE_MI_GCDS, d64);
+	mi->gpr_c_data_len	= FIELD_GET(ICE_MI_GCDL, d64);
+	mi->gpr_c_id		= FIELD_GET(ICE_MI_GCI, d64);
+
+	mi->gpr_d_ctrl		= FIELD_GET(ICE_MI_GDC, d64);
+	mi->gpr_d_data_mdid	= FIELD_GET(ICE_MI_GDDM, d64);
+	mi->gpr_d_data_start	= FIELD_GET(ICE_MI_GDDS, d64);
+	mi->gpr_d_data_len	= FIELD_GET(ICE_MI_GDDL, d64);
+	mi->gpr_d_id		= FIELD_GET(ICE_MI_GDI, d64);
+
+	d64 = *((u64 *)&buf[ICE_MI_FLAG_IDD]) >> ICE_MI_FLAG_OFF;
+
+	mi->flags		= FIELD_GET(ICE_MI_FLAG, d64);
+}
+
+/**
+ * ice_metainit_table_get - create a metainit table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Metadata initialization table.
+ */
+static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_METADATA_INIT,
+				       sizeof(struct ice_metainit_item),
+				       ICE_METAINIT_TABLE_SIZE,
+				       ice_metainit_parse_item, false);
+}
+
+/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL,
+ *    ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM
+ *    sections ***/
+#define ICE_PGCA_NN	GENMASK_ULL(10, 0)
+#define ICE_PGCA_NPC	GENMASK_ULL(18, 11)
+#define ICE_PGCA_IPG	BIT_ULL(19)
+#define ICE_PGCA_PID	GENMASK_ULL(30, 23)
+#define ICE_PGCA_IMG	BIT_ULL(31)
+#define ICE_PGCA_MID	GENMASK_ULL(39, 32)
+#define ICE_PGCA_ILR	BIT_ULL(40)
+#define ICE_PGCA_HOP	BIT_ULL(41)
+#define ICE_PGCA_HOI	GENMASK_ULL(50, 42)
+
+/**
+ * ice_pg_cam_action_init - parse 55 bits of Parse Graph CAM Action
+ * @action: pointer to the Parse Graph CAM Action structure
+ * @data: Parse Graph CAM Action data to be parsed
+ */
+static void ice_pg_cam_action_init(struct ice_pg_cam_action *action, u64 data)
+{
+	action->next_node	= FIELD_GET(ICE_PGCA_NN, data);
+	action->next_pc		= FIELD_GET(ICE_PGCA_NPC, data);
+	action->is_pg		= FIELD_GET(ICE_PGCA_IPG, data);
+	action->proto_id	= FIELD_GET(ICE_PGCA_PID, data);
+	action->is_mg		= FIELD_GET(ICE_PGCA_IMG, data);
+	action->marker_id	= FIELD_GET(ICE_PGCA_MID, data);
+	action->is_last_round	= FIELD_GET(ICE_PGCA_ILR, data);
+	action->ho_polarity	= FIELD_GET(ICE_PGCA_HOP, data);
+	action->ho_inc		= FIELD_GET(ICE_PGCA_HOI, data);
+}
+
+#define ICE_PGNCK_VLD		BIT_ULL(0)
+#define ICE_PGNCK_NID		GENMASK_ULL(11, 1)
+#define ICE_PGNCK_F0		BIT_ULL(12)
+#define ICE_PGNCK_F1		BIT_ULL(13)
+#define ICE_PGNCK_F2		BIT_ULL(14)
+#define ICE_PGNCK_F3		BIT_ULL(15)
+#define ICE_PGNCK_BH		BIT_ULL(16)
+#define ICE_PGNCK_BI		GENMASK_ULL(24, 17)
+#define ICE_PGNCK_AR		GENMASK_ULL(40, 25)
+
+/**
+ * ice_pg_nm_cam_key_init - parse 41 bits of Parse Graph NoMatch CAM Key
+ * @key: pointer to the Parse Graph NoMatch CAM Key structure
+ * @data: Parse Graph NoMatch CAM Key data to be parsed
+ */
+static void ice_pg_nm_cam_key_init(struct ice_pg_nm_cam_key *key, u64 data)
+{
+	key->valid	= FIELD_GET(ICE_PGNCK_VLD, data);
+	key->node_id	= FIELD_GET(ICE_PGNCK_NID, data);
+	key->flag0	= FIELD_GET(ICE_PGNCK_F0, data);
+	key->flag1	= FIELD_GET(ICE_PGNCK_F1, data);
+	key->flag2	= FIELD_GET(ICE_PGNCK_F2, data);
+	key->flag3	= FIELD_GET(ICE_PGNCK_F3, data);
+
+	if (FIELD_GET(ICE_PGNCK_BH, data))
+		key->boost_idx = FIELD_GET(ICE_PGNCK_BI, data);
+	else
+		key->boost_idx = 0;
+
+	key->alu_reg	= FIELD_GET(ICE_PGNCK_AR, data);
+}
+
+#define ICE_PGCK_VLD		BIT_ULL(0)
+#define ICE_PGCK_NID		GENMASK_ULL(11, 1)
+#define ICE_PGCK_F0		BIT_ULL(12)
+#define ICE_PGCK_F1		BIT_ULL(13)
+#define ICE_PGCK_F2		BIT_ULL(14)
+#define ICE_PGCK_F3		BIT_ULL(15)
+#define ICE_PGCK_BH		BIT_ULL(16)
+#define ICE_PGCK_BI		GENMASK_ULL(24, 17)
+#define ICE_PGCK_AR		GENMASK_ULL(40, 25)
+#define ICE_PGCK_NPK_S		41	/* offset for the 2nd 64-bits field */
+#define ICE_PGCK_NPK_IDD	(ICE_PGCK_NPK_S / BITS_PER_BYTE)
+#define ICE_PGCK_NPK_OFF	(ICE_PGCK_NPK_S % BITS_PER_BYTE)
+#define ICE_PGCK_NPK		GENMASK_ULL(72 - ICE_PGCK_NPK_S, \
+					    41 - ICE_PGCK_NPK_S)
+
+/**
+ * ice_pg_cam_key_init - parse 73 bits of Parse Graph CAM Key
+ * @key: pointer to the Parse Graph CAM Key structure
+ * @data: Parse Graph CAM Key data to be parsed
+ */
+static void ice_pg_cam_key_init(struct ice_pg_cam_key *key, u8 *data)
+{
+	u64 d64 = *(u64 *)data;
+
+	key->valid	= FIELD_GET(ICE_PGCK_VLD, d64);
+	key->node_id	= FIELD_GET(ICE_PGCK_NID, d64);
+	key->flag0	= FIELD_GET(ICE_PGCK_F0, d64);
+	key->flag1	= FIELD_GET(ICE_PGCK_F1, d64);
+	key->flag2	= FIELD_GET(ICE_PGCK_F2, d64);
+	key->flag3	= FIELD_GET(ICE_PGCK_F3, d64);
+
+	if (FIELD_GET(ICE_PGCK_BH, d64))
+		key->boost_idx = FIELD_GET(ICE_PGCK_BI, d64);
+	else
+		key->boost_idx = 0;
+
+	key->alu_reg	= FIELD_GET(ICE_PGCK_AR, d64);
+
+	d64 = *((u64 *)&data[ICE_PGCK_NPK_IDD]) >> ICE_PGCK_NPK_OFF;
+
+	key->next_proto	= FIELD_GET(ICE_PGCK_NPK, d64);
+}
+
+#define ICE_PG_CAM_ACT_S	73
+#define ICE_PG_CAM_ACT_IDD	(ICE_PG_CAM_ACT_S / BITS_PER_BYTE)
+#define ICE_PG_CAM_ACT_OFF	(ICE_PG_CAM_ACT_S % BITS_PER_BYTE)
+
+/**
+ * ice_pg_cam_parse_item - parse 128 bits of Parse Graph CAM Entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Parse Graph CAM Entry
+ * @item: item of Parse Graph CAM Entry
+ * @data: Parse Graph CAM Entry data to be parsed
+ * @size: size of Parse Graph CAM Entry
+ */
+static void ice_pg_cam_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				  void *data, int __maybe_unused size)
+{
+	struct ice_pg_cam_item *ci = item;
+	u8 *buf = data;
+	u64 d64;
+
+	ci->idx = idx;
+
+	ice_pg_cam_key_init(&ci->key, buf);
+
+	d64 = *((u64 *)&buf[ICE_PG_CAM_ACT_IDD]) >> ICE_PG_CAM_ACT_OFF;
+	ice_pg_cam_action_init(&ci->action, d64);
+}
+
+#define ICE_PG_SP_CAM_KEY_S	56
+#define ICE_PG_SP_CAM_KEY_IDD	(ICE_PG_SP_CAM_KEY_S / BITS_PER_BYTE)
+
+/**
+ * ice_pg_sp_cam_parse_item - parse 136 bits of Parse Graph Spill CAM Entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Parse Graph Spill CAM Entry
+ * @item: item of Parse Graph Spill CAM Entry
+ * @data: Parse Graph Spill CAM Entry data to be parsed
+ * @size: size of Parse Graph Spill CAM Entry
+ */
+static void ice_pg_sp_cam_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				     void *data, int __maybe_unused size)
+{
+	struct ice_pg_cam_item *ci = item;
+	u8 *buf = data;
+	u64 d64;
+
+	ci->idx = idx;
+
+	d64 = *(u64 *)buf;
+	ice_pg_cam_action_init(&ci->action, d64);
+
+	ice_pg_cam_key_init(&ci->key, &buf[ICE_PG_SP_CAM_KEY_IDD]);
+}
+
+#define ICE_PG_NM_CAM_ACT_S	41
+#define ICE_PG_NM_CAM_ACT_IDD	(ICE_PG_NM_CAM_ACT_S / BITS_PER_BYTE)
+#define ICE_PG_NM_CAM_ACT_OFF   (ICE_PG_NM_CAM_ACT_S % BITS_PER_BYTE)
+
+/**
+ * ice_pg_nm_cam_parse_item - parse 96 bits of Parse Graph NoMatch CAM Entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Parse Graph NoMatch CAM Entry
+ * @item: item of Parse Graph NoMatch CAM Entry
+ * @data: Parse Graph NoMatch CAM Entry data to be parsed
+ * @size: size of Parse Graph NoMatch CAM Entry
+ */
+static void ice_pg_nm_cam_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				     void *data, int __maybe_unused size)
+{
+	struct ice_pg_nm_cam_item *ci = item;
+	u8 *buf = data;
+	u64 d64;
+
+	ci->idx = idx;
+
+	d64 = *(u64 *)buf;
+	ice_pg_nm_cam_key_init(&ci->key, d64);
+
+	d64 = *((u64 *)&buf[ICE_PG_NM_CAM_ACT_IDD]) >> ICE_PG_NM_CAM_ACT_OFF;
+	ice_pg_cam_action_init(&ci->action, d64);
+}
+
+#define ICE_PG_NM_SP_CAM_ACT_S		56
+#define ICE_PG_NM_SP_CAM_ACT_IDD	(ICE_PG_NM_SP_CAM_ACT_S / BITS_PER_BYTE)
+#define ICE_PG_NM_SP_CAM_ACT_OFF	(ICE_PG_NM_SP_CAM_ACT_S % BITS_PER_BYTE)
+
+/**
+ * ice_pg_nm_sp_cam_parse_item - parse 104 bits of Parse Graph NoMatch Spill
+ *  CAM Entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Parse Graph NoMatch Spill CAM Entry
+ * @item: item of Parse Graph NoMatch Spill CAM Entry
+ * @data: Parse Graph NoMatch Spill CAM Entry data to be parsed
+ * @size: size of Parse Graph NoMatch Spill CAM Entry
+ */
+static void ice_pg_nm_sp_cam_parse_item(struct ice_hw *hw, u16 idx,
+					void *item, void *data,
+					int __maybe_unused size)
+{
+	struct ice_pg_nm_cam_item *ci = item;
+	u8 *buf = data;
+	u64 d64;
+
+	ci->idx = idx;
+
+	d64 = *(u64 *)buf;
+	ice_pg_cam_action_init(&ci->action, d64);
+
+	d64 = *((u64 *)&buf[ICE_PG_NM_SP_CAM_ACT_IDD]) >>
+		ICE_PG_NM_SP_CAM_ACT_OFF;
+	ice_pg_nm_cam_key_init(&ci->key, d64);
+}
+
+/**
+ * ice_pg_cam_table_get - create a parse graph cam table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Parse Graph CAM table.
+ */
+static struct ice_pg_cam_item *ice_pg_cam_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_CAM,
+				       sizeof(struct ice_pg_cam_item),
+				       ICE_PG_CAM_TABLE_SIZE,
+				       ice_pg_cam_parse_item, false);
+}
+
+/**
+ * ice_pg_sp_cam_table_get - create a parse graph spill cam table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Parse Graph Spill CAM table.
+ */
+static struct ice_pg_cam_item *ice_pg_sp_cam_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_PG_SPILL,
+				       sizeof(struct ice_pg_cam_item),
+				       ICE_PG_SP_CAM_TABLE_SIZE,
+				       ice_pg_sp_cam_parse_item, false);
+}
+
+/**
+ * ice_pg_nm_cam_table_get - create a parse graph no match cam table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Parse Graph No Match CAM table.
+ */
+static struct ice_pg_nm_cam_item *ice_pg_nm_cam_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_CAM,
+				       sizeof(struct ice_pg_nm_cam_item),
+				       ICE_PG_NM_CAM_TABLE_SIZE,
+				       ice_pg_nm_cam_parse_item, false);
+}
+
+/**
+ * ice_pg_nm_sp_cam_table_get - create a parse graph no match spill cam table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Parse Graph No Match Spill CAM table.
+ */
+static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_SPILL,
+				       sizeof(struct ice_pg_nm_cam_item),
+				       ICE_PG_NM_SP_CAM_TABLE_SIZE,
+				       ice_pg_nm_sp_cam_parse_item, false);
+}
+
+/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
+#define ICE_BST_ALU_OPC		GENMASK_ULL(5, 0)
+#define ICE_BST_ALU_SS		GENMASK_ULL(13, 6)
+#define ICE_BST_ALU_SL		GENMASK_ULL(18, 14)
+#define ICE_BST_ALU_SXS		BIT_ULL(19)
+#define ICE_BST_ALU_SXK		GENMASK_ULL(23, 20)
+#define ICE_BST_ALU_SRID	GENMASK_ULL(30, 24)
+#define ICE_BST_ALU_DRID	GENMASK_ULL(37, 31)
+#define ICE_BST_ALU_INC0	BIT_ULL(38)
+#define ICE_BST_ALU_INC1	BIT_ULL(39)
+#define ICE_BST_ALU_POO		GENMASK_ULL(41, 40)
+#define ICE_BST_ALU_PO		GENMASK_ULL(49, 42)
+#define ICE_BST_ALU_BA_S	50	/* offset for the 2nd 64-bits field */
+#define ICE_BST_ALU_BA		GENMASK_ULL(57 - ICE_BST_ALU_BA_S, \
+					    50 - ICE_BST_ALU_BA_S)
+#define ICE_BST_ALU_IMM		GENMASK_ULL(73 - ICE_BST_ALU_BA_S, \
+					    58 - ICE_BST_ALU_BA_S)
+#define ICE_BST_ALU_DFE		BIT_ULL(74 - ICE_BST_ALU_BA_S)
+#define ICE_BST_ALU_DS		GENMASK_ULL(80 - ICE_BST_ALU_BA_S, \
+					    75 - ICE_BST_ALU_BA_S)
+#define ICE_BST_ALU_DL		GENMASK_ULL(86 - ICE_BST_ALU_BA_S, \
+					    81 - ICE_BST_ALU_BA_S)
+#define ICE_BST_ALU_FEI		BIT_ULL(87 - ICE_BST_ALU_BA_S)
+#define ICE_BST_ALU_FSI		GENMASK_ULL(95 - ICE_BST_ALU_BA_S, \
+					    88 - ICE_BST_ALU_BA_S)
+
+/**
+ * ice_bst_alu_init - parse 96 bits of ALU entry
+ * @alu: pointer to the ALU entry structure
+ * @data: ALU entry data to be parsed
+ * @off: offset of the ALU entry data
+ */
+static void ice_bst_alu_init(struct ice_alu *alu, u8 *data, u8 off)
+{
+	u64 d64;
+	u8 idd;
+
+	d64 = *((u64 *)data) >> off;
+
+	alu->opc		= FIELD_GET(ICE_BST_ALU_OPC, d64);
+	alu->src_start		= FIELD_GET(ICE_BST_ALU_SS, d64);
+	alu->src_len		= FIELD_GET(ICE_BST_ALU_SL, d64);
+	alu->shift_xlate_sel	= FIELD_GET(ICE_BST_ALU_SXS, d64);
+	alu->shift_xlate_key	= FIELD_GET(ICE_BST_ALU_SXK, d64);
+	alu->src_reg_id		= FIELD_GET(ICE_BST_ALU_SRID, d64);
+	alu->dst_reg_id		= FIELD_GET(ICE_BST_ALU_DRID, d64);
+	alu->inc0		= FIELD_GET(ICE_BST_ALU_INC0, d64);
+	alu->inc1		= FIELD_GET(ICE_BST_ALU_INC1, d64);
+	alu->proto_offset_opc	= FIELD_GET(ICE_BST_ALU_POO, d64);
+	alu->proto_offset	= FIELD_GET(ICE_BST_ALU_PO, d64);
+
+	idd = (ICE_BST_ALU_BA_S + off) / BITS_PER_BYTE;
+	off = (ICE_BST_ALU_BA_S + off) % BITS_PER_BYTE;
+	d64 = *((u64 *)(&data[idd])) >> off;
+
+	alu->branch_addr	= FIELD_GET(ICE_BST_ALU_BA, d64);
+	alu->imm		= FIELD_GET(ICE_BST_ALU_IMM, d64);
+	alu->dedicate_flags_ena	= FIELD_GET(ICE_BST_ALU_DFE, d64);
+	alu->dst_start		= FIELD_GET(ICE_BST_ALU_DS, d64);
+	alu->dst_len		= FIELD_GET(ICE_BST_ALU_DL, d64);
+	alu->flags_extr_imm	= FIELD_GET(ICE_BST_ALU_FEI, d64);
+	alu->flags_start_imm	= FIELD_GET(ICE_BST_ALU_FSI, d64);
+}
+
+#define ICE_BST_PGKB_F0_ENA		BIT_ULL(0)
+#define ICE_BST_PGKB_F0_IDX		GENMASK_ULL(6, 1)
+#define ICE_BST_PGKB_F1_ENA		BIT_ULL(7)
+#define ICE_BST_PGKB_F1_IDX		GENMASK_ULL(13, 8)
+#define ICE_BST_PGKB_F2_ENA		BIT_ULL(14)
+#define ICE_BST_PGKB_F2_IDX		GENMASK_ULL(20, 15)
+#define ICE_BST_PGKB_F3_ENA		BIT_ULL(21)
+#define ICE_BST_PGKB_F3_IDX		GENMASK_ULL(27, 22)
+#define ICE_BST_PGKB_AR_IDX		GENMASK_ULL(34, 28)
+
+/**
+ * ice_bst_pgkb_init - parse 35 bits of Parse Graph Key Build
+ * @kb: pointer to the Parse Graph Key Build structure
+ * @data: Parse Graph Key Build data to be parsed
+ */
+static void ice_bst_pgkb_init(struct ice_pg_keybuilder *kb, u64 data)
+{
+	kb->flag0_ena	= FIELD_GET(ICE_BST_PGKB_F0_ENA, data);
+	kb->flag0_idx	= FIELD_GET(ICE_BST_PGKB_F0_IDX, data);
+	kb->flag1_ena	= FIELD_GET(ICE_BST_PGKB_F1_ENA, data);
+	kb->flag1_idx	= FIELD_GET(ICE_BST_PGKB_F1_IDX, data);
+	kb->flag2_ena	= FIELD_GET(ICE_BST_PGKB_F2_ENA, data);
+	kb->flag2_idx	= FIELD_GET(ICE_BST_PGKB_F2_IDX, data);
+	kb->flag3_ena	= FIELD_GET(ICE_BST_PGKB_F3_ENA, data);
+	kb->flag3_idx	= FIELD_GET(ICE_BST_PGKB_F3_IDX, data);
+	kb->alu_reg_idx	= FIELD_GET(ICE_BST_PGKB_AR_IDX, data);
+}
+
+#define ICE_BST_NPKB_OPC	GENMASK(1, 0)
+#define ICE_BST_NPKB_S_R0	GENMASK(9, 2)
+#define ICE_BST_NPKB_L_R1	GENMASK(17, 10)
+
+/**
+ * ice_bst_npkb_init - parse 18 bits of Next Protocol Key Build
+ * @kb: pointer to the Next Protocol Key Build structure
+ * @data: Next Protocol Key Build data to be parsed
+ */
+static void ice_bst_npkb_init(struct ice_np_keybuilder *kb, u32 data)
+{
+	kb->opc		= FIELD_GET(ICE_BST_NPKB_OPC, data);
+	kb->start_reg0	= FIELD_GET(ICE_BST_NPKB_S_R0, data);
+	kb->len_reg1	= FIELD_GET(ICE_BST_NPKB_L_R1, data);
+}
+
+#define ICE_BT_KEY_S		32
+#define ICE_BT_KEY_IDD		(ICE_BT_KEY_S / BITS_PER_BYTE)
+#define ICE_BT_KIV_S		192
+#define ICE_BT_KIV_IDD		(ICE_BT_KIV_S / BITS_PER_BYTE)
+#define ICE_BT_HIG_S		352
+#define ICE_BT_HIG_IDD		(ICE_BT_HIG_S / BITS_PER_BYTE)
+#define ICE_BT_PGP_S		360
+#define ICE_BT_PGP_IDD		(ICE_BT_PGP_S / BITS_PER_BYTE)
+#define ICE_BT_PGP_M		GENMASK(361 - ICE_BT_PGP_S, 360 - ICE_BT_PGP_S)
+#define ICE_BT_NPKB_S		362
+#define ICE_BT_NPKB_IDD		(ICE_BT_NPKB_S / BITS_PER_BYTE)
+#define ICE_BT_NPKB_OFF		(ICE_BT_NPKB_S % BITS_PER_BYTE)
+#define ICE_BT_PGKB_S		380
+#define ICE_BT_PGKB_IDD		(ICE_BT_PGKB_S / BITS_PER_BYTE)
+#define ICE_BT_PGKB_OFF		(ICE_BT_PGKB_S % BITS_PER_BYTE)
+#define ICE_BT_ALU0_S		415
+#define ICE_BT_ALU0_IDD		(ICE_BT_ALU0_S / BITS_PER_BYTE)
+#define ICE_BT_ALU0_OFF		(ICE_BT_ALU0_S % BITS_PER_BYTE)
+#define ICE_BT_ALU1_S		511
+#define ICE_BT_ALU1_IDD		(ICE_BT_ALU1_S / BITS_PER_BYTE)
+#define ICE_BT_ALU1_OFF		(ICE_BT_ALU1_S % BITS_PER_BYTE)
+#define ICE_BT_ALU2_S		607
+#define ICE_BT_ALU2_IDD		(ICE_BT_ALU2_S / BITS_PER_BYTE)
+#define ICE_BT_ALU2_OFF		(ICE_BT_ALU2_S % BITS_PER_BYTE)
+
+/**
+ * ice_bst_parse_item - parse 704 bits of Boost TCAM entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Boost TCAM entry
+ * @item: item of Boost TCAM entry
+ * @data: Boost TCAM entry data to be parsed
+ * @size: size of Boost TCAM entry
+ */
+static void ice_bst_parse_item(struct ice_hw *hw, u16 idx, void *item,
+			       void *data, int __maybe_unused size)
+{
+	struct ice_bst_tcam_item *ti = item;
+	u8 *buf = (u8 *)data;
+	int i;
+
+	ti->addr = *(u16 *)buf;
+
+	for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) {
+		ti->key[i] = buf[ICE_BT_KEY_IDD + i];
+		ti->key_inv[i] = buf[ICE_BT_KIV_IDD + i];
+	}
+	ti->hit_idx_grp	= buf[ICE_BT_HIG_IDD];
+	ti->pg_prio	= buf[ICE_BT_PGP_IDD] & ICE_BT_PGP_M;
+
+	ice_bst_npkb_init(&ti->np_kb,
+			  *((u32 *)(&buf[ICE_BT_NPKB_IDD])) >>
+			   ICE_BT_NPKB_OFF);
+	ice_bst_pgkb_init(&ti->pg_kb,
+			  *((u64 *)(&buf[ICE_BT_PGKB_IDD])) >>
+			   ICE_BT_PGKB_OFF);
+
+	ice_bst_alu_init(&ti->alu0, &buf[ICE_BT_ALU0_IDD], ICE_BT_ALU0_OFF);
+	ice_bst_alu_init(&ti->alu1, &buf[ICE_BT_ALU1_IDD], ICE_BT_ALU1_OFF);
+	ice_bst_alu_init(&ti->alu2, &buf[ICE_BT_ALU2_IDD], ICE_BT_ALU2_OFF);
+}
+
+/**
+ * ice_bst_tcam_table_get - create a boost tcam table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Boost TCAM table.
+ */
+static struct ice_bst_tcam_item *ice_bst_tcam_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_BOOST_TCAM,
+				       sizeof(struct ice_bst_tcam_item),
+				       ICE_BST_TCAM_TABLE_SIZE,
+				       ice_bst_parse_item, true);
+}
+
+static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item,
+			       void *data, int size)
+{
+	memcpy(item, data, size);
+}
+
+/**
+ * ice_bst_lbl_table_get - create a boost label table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Boost label table.
+ */
+static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_LBL_RXPARSER_TMEM,
+				       sizeof(struct ice_lbl_item),
+				       ICE_BST_TCAM_TABLE_SIZE,
+				       ice_parse_lbl_item, true);
+}
+
+/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/
+static void ice_parse_ptype_mk_tcam_item(struct ice_hw *hw, u16 idx,
+					 void *item, void *data, int size)
+{
+	memcpy(item, data, size);
+}
+
+/**
+ * ice_ptype_mk_tcam_table_get - create a ptype marker tcam table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Marker PType TCAM table.
+ */
+static
+struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_PTYPE,
+				       sizeof(struct ice_ptype_mk_tcam_item),
+				       ICE_PTYPE_MK_TCAM_TABLE_SIZE,
+				       ice_parse_ptype_mk_tcam_item, true);
+}
+
+/*** ICE_SID_RXPARSER_MARKER_GRP section ***/
+static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				  void *data, int __maybe_unused size)
+{
+	struct ice_mk_grp_item *grp = item;
+	u8 *buf = data;
+	int i;
+
+	grp->idx = idx;
+
+	for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++)
+		grp->markers[i] = buf[i];
+}
+
+/**
+ * ice_mk_grp_table_get - create a marker group table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Marker Group ID table.
+ */
+static struct ice_mk_grp_item *ice_mk_grp_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_GRP,
+				       sizeof(struct ice_mk_grp_item),
+				       ICE_MK_GRP_TABLE_SIZE,
+				       ice_mk_grp_parse_item, false);
+}
+
+/*** ICE_SID_RXPARSER_PROTO_GRP section ***/
+#define ICE_PO_POL	BIT(0)
+#define ICE_PO_PID	GENMASK(8, 1)
+#define ICE_PO_OFF	GENMASK(21, 12)
+
+/**
+ * ice_proto_off_parse - parse 22 bits of Protocol entry
+ * @po: pointer to the Protocol entry structure
+ * @data: Protocol entry data to be parsed
+ */
+static void ice_proto_off_parse(struct ice_proto_off *po, u32 data)
+{
+	po->polarity = FIELD_GET(ICE_PO_POL, data);
+	po->proto_id = FIELD_GET(ICE_PO_PID, data);
+	po->offset = FIELD_GET(ICE_PO_OFF, data);
+}
+
+/**
+ * ice_proto_grp_parse_item - parse 192 bits of Protocol Group Table entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Protocol Group Table entry
+ * @item: item of Protocol Group Table entry
+ * @data: Protocol Group Table entry data to be parsed
+ * @size: size of Protocol Group Table entry
+ */
+static void ice_proto_grp_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				     void *data, int __maybe_unused size)
+{
+	struct ice_proto_grp_item *grp = item;
+	u8 *buf = (u8 *)data;
+	u8 idd, off;
+	u32 d32;
+	int i;
+
+	grp->idx = idx;
+
+	for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) {
+		idd = (ICE_PROTO_GRP_ITEM_SIZE * i) / BITS_PER_BYTE;
+		off = (ICE_PROTO_GRP_ITEM_SIZE * i) % BITS_PER_BYTE;
+		d32 = *((u32 *)&buf[idd]) >> off;
+		ice_proto_off_parse(&grp->po[i], d32);
+	}
+}
+
+/**
+ * ice_proto_grp_table_get - create a proto group table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Protocol Group table.
+ */
+static struct ice_proto_grp_item *ice_proto_grp_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_PROTO_GRP,
+				       sizeof(struct ice_proto_grp_item),
+				       ICE_PROTO_GRP_TABLE_SIZE,
+				       ice_proto_grp_parse_item, false);
+}
+
+/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/
+#define ICE_FRT_EXPO	BIT(0)
+#define ICE_FRT_IFID	GENMASK(6, 1)
+
+/**
+ * ice_flg_rd_parse_item - parse 8 bits of Flag Redirect Table entry
+ * @hw: pointer to the hardware structure
+ * @idx: index of Flag Redirect Table entry
+ * @item: item of Flag Redirect Table entry
+ * @data: Flag Redirect Table entry data to be parsed
+ * @size: size of Flag Redirect Table entry
+ */
+static void ice_flg_rd_parse_item(struct ice_hw *hw, u16 idx, void *item,
+				  void *data, int __maybe_unused size)
+{
+	struct ice_flg_rd_item *rdi = item;
+	u8 d8 = *(u8 *)data;
+
+	rdi->idx = idx;
+	rdi->expose = FIELD_GET(ICE_FRT_EXPO, d8);
+	rdi->intr_flg_id = FIELD_GET(ICE_FRT_IFID, d8);
+}
+
+/**
+ * ice_flg_rd_table_get - create a flag redirect table
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Flags Redirection table.
+ */
+static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw)
+{
+	return ice_parser_create_table(hw, ICE_SID_RXPARSER_FLAG_REDIR,
+				       sizeof(struct ice_flg_rd_item),
+				       ICE_FLG_RD_TABLE_SIZE,
+				       ice_flg_rd_parse_item, false);
+}
+
+/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL,
+ * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS
+ * sections ***/
+#define ICE_XLT_KB_X1AS_S	32	/* offset for the 1st 64-bits field */
+#define ICE_XLT_KB_X1AS_IDD	(ICE_XLT_KB_X1AS_S / BITS_PER_BYTE)
+#define ICE_XLT_KB_X1AS_OFF	(ICE_XLT_KB_X1AS_S % BITS_PER_BYTE)
+#define ICE_XLT_KB_X1AS		GENMASK_ULL(34 - ICE_XLT_KB_X1AS_S, \
+					    32 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_X2AS		GENMASK_ULL(37 - ICE_XLT_KB_X1AS_S, \
+					    35 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL00		GENMASK_ULL(46 - ICE_XLT_KB_X1AS_S, \
+					    38 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL01		GENMASK_ULL(55 - ICE_XLT_KB_X1AS_S, \
+					    47 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL02		GENMASK_ULL(64 - ICE_XLT_KB_X1AS_S, \
+					    56 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL03		GENMASK_ULL(73 - ICE_XLT_KB_X1AS_S, \
+					    65 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL04		GENMASK_ULL(82 - ICE_XLT_KB_X1AS_S, \
+					    74 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL05		GENMASK_ULL(91 - ICE_XLT_KB_X1AS_S, \
+					    83 - ICE_XLT_KB_X1AS_S)
+#define ICE_XLT_KB_FL06_S	92	/* offset for the 2nd 64-bits field */
+#define ICE_XLT_KB_FL06_IDD	(ICE_XLT_KB_FL06_S / BITS_PER_BYTE)
+#define ICE_XLT_KB_FL06_OFF	(ICE_XLT_KB_FL06_S % BITS_PER_BYTE)
+#define ICE_XLT_KB_FL06		GENMASK_ULL(100 - ICE_XLT_KB_FL06_S, \
+					    92 - ICE_XLT_KB_FL06_S)
+#define ICE_XLT_KB_FL07		GENMASK_ULL(109 - ICE_XLT_KB_FL06_S, \
+					    101 - ICE_XLT_KB_FL06_S)
+#define ICE_XLT_KB_FL08		GENMASK_ULL(118 - ICE_XLT_KB_FL06_S, \
+					    110 - ICE_XLT_KB_FL06_S)
+#define ICE_XLT_KB_FL09		GENMASK_ULL(127 - ICE_XLT_KB_FL06_S, \
+					    119 - ICE_XLT_KB_FL06_S)
+#define ICE_XLT_KB_FL10		GENMASK_ULL(136 - ICE_XLT_KB_FL06_S, \
+					    128 - ICE_XLT_KB_FL06_S)
+#define ICE_XLT_KB_FL11		GENMASK_ULL(145 - ICE_XLT_KB_FL06_S, \
+					    137 - ICE_XLT_KB_FL06_S)
+#define ICE_XLT_KB_FL12_S	146	/* offset for the 3rd 64-bits field */
+#define ICE_XLT_KB_FL12_IDD	(ICE_XLT_KB_FL12_S / BITS_PER_BYTE)
+#define ICE_XLT_KB_FL12_OFF	(ICE_XLT_KB_FL12_S % BITS_PER_BYTE)
+#define ICE_XLT_KB_FL12		GENMASK_ULL(154 - ICE_XLT_KB_FL12_S, \
+					    146 - ICE_XLT_KB_FL12_S)
+#define ICE_XLT_KB_FL13		GENMASK_ULL(163 - ICE_XLT_KB_FL12_S, \
+					    155 - ICE_XLT_KB_FL12_S)
+#define ICE_XLT_KB_FL14		GENMASK_ULL(181 - ICE_XLT_KB_FL12_S, \
+					    164 - ICE_XLT_KB_FL12_S)
+#define ICE_XLT_KB_X1MS		GENMASK_ULL(186 - ICE_XLT_KB_FL12_S, \
+					    182 - ICE_XLT_KB_FL12_S)
+#define ICE_XLT_KB_X2MS		GENMASK_ULL(191 - ICE_XLT_KB_FL12_S, \
+					    187 - ICE_XLT_KB_FL12_S)
+
+/**
+ * ice_kb_entry_init - parse 192 bits of XLT Key Builder entry
+ * @entry: pointer to the XLT Key Builder entry structure
+ * @data: XLT Key Builder entry data to be parsed
+ */
+static void ice_kb_entry_init(struct ice_xlt_kb_entry *entry, u8 *data)
+{
+	u8 i = 0;
+	u64 d64;
+
+	d64 = *((u64 *)&data[ICE_XLT_KB_X1AS_IDD]) >> ICE_XLT_KB_X1AS_OFF;
+
+	entry->xlt1_ad_sel	= FIELD_GET(ICE_XLT_KB_X1AS, d64);
+	entry->xlt2_ad_sel	= FIELD_GET(ICE_XLT_KB_X2AS, d64);
+
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL00, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL01, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL02, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL03, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL04, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL05, d64);
+
+	d64 = *((u64 *)&data[ICE_XLT_KB_FL06_IDD]) >> ICE_XLT_KB_FL06_OFF;
+
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL06, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL07, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL08, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL09, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL10, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL11, d64);
+
+	d64 = *((u64 *)&data[ICE_XLT_KB_FL12_IDD]) >> ICE_XLT_KB_FL12_OFF;
+
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL12, d64);
+	entry->flg0_14_sel[i++]	= FIELD_GET(ICE_XLT_KB_FL13, d64);
+	entry->flg0_14_sel[i]	= FIELD_GET(ICE_XLT_KB_FL14, d64);
+
+	entry->xlt1_md_sel	= FIELD_GET(ICE_XLT_KB_X1MS, d64);
+	entry->xlt2_md_sel	= FIELD_GET(ICE_XLT_KB_X2MS, d64);
+}
+
+#define ICE_XLT_KB_X1PM_OFF	0
+#define ICE_XLT_KB_X2PM_OFF	1
+#define ICE_XLT_KB_PIPM_OFF	2
+#define ICE_XLT_KB_FL15_OFF	4
+#define ICE_XLT_KB_TBL_OFF	12
+
+/**
+ * ice_parse_kb_data - parse 204 bits of XLT Key Build Table
+ * @hw: pointer to the hardware structure
+ * @kb: pointer to the XLT Key Build Table structure
+ * @data: XLT Key Build Table data to be parsed
+ */
+static void ice_parse_kb_data(struct ice_hw *hw, struct ice_xlt_kb *kb,
+			      void *data)
+{
+	u8 *buf = data;
+	int i;
+
+	kb->xlt1_pm	= buf[ICE_XLT_KB_X1PM_OFF];
+	kb->xlt2_pm	= buf[ICE_XLT_KB_X2PM_OFF];
+	kb->prof_id_pm	= buf[ICE_XLT_KB_PIPM_OFF];
+
+	kb->flag15 = *(u64 *)&buf[ICE_XLT_KB_FL15_OFF];
+	for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++)
+		ice_kb_entry_init(&kb->entries[i],
+				  &buf[ICE_XLT_KB_TBL_OFF +
+				       i * ICE_XLT_KB_TBL_ENTRY_SIZE]);
+}
+
+static struct ice_xlt_kb *ice_xlt_kb_get(struct ice_hw *hw, u32 sect_type)
+{
+	struct ice_pkg_enum state = {};
+	struct ice_seg *seg = hw->seg;
+	struct ice_xlt_kb *kb;
+	void *data;
+
+	if (!seg)
+		return ERR_PTR(-EINVAL);
+
+	kb = kzalloc(sizeof(*kb), GFP_KERNEL);
+	if (!kb)
+		return ERR_PTR(-ENOMEM);
+
+	data = ice_pkg_enum_section(seg, &state, sect_type);
+	if (!data) {
+		ice_debug(hw, ICE_DBG_PARSER, "failed to find section type %d.\n",
+			  sect_type);
+		kfree(kb);
+		return ERR_PTR(-EINVAL);
+	}
+
+	ice_parse_kb_data(hw, kb, data);
+
+	return kb;
+}
+
+/**
+ * ice_xlt_kb_get_sw - create switch xlt key build
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Key Builder table for Switch.
+ */
+static struct ice_xlt_kb *ice_xlt_kb_get_sw(struct ice_hw *hw)
+{
+	return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_SW);
+}
+
+/**
+ * ice_xlt_kb_get_acl - create acl xlt key build
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Key Builder table for ACL.
+ */
+static struct ice_xlt_kb *ice_xlt_kb_get_acl(struct ice_hw *hw)
+{
+	return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_ACL);
+}
+
+/**
+ * ice_xlt_kb_get_fd - create fdir xlt key build
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Key Builder table for Flow Director.
+ */
+static struct ice_xlt_kb *ice_xlt_kb_get_fd(struct ice_hw *hw)
+{
+	return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_FD);
+}
+
+/**
+ * ice_xlt_kb_get_rss - create rss xlt key build
+ * @hw: pointer to the hardware structure
+ *
+ * Return: a pointer to the allocated Key Builder table for RSS.
+ */
+static struct ice_xlt_kb *ice_xlt_kb_get_rss(struct ice_hw *hw)
+{
+	return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_RSS);
+}
+
+/*** Parser API ***/
 /**
  * ice_parser_create - create a parser instance
  * @hw: pointer to the hardware structure
@@ -13,13 +1278,114 @@
 struct ice_parser *ice_parser_create(struct ice_hw *hw)
 {
 	struct ice_parser *p;
+	void *err;
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
 	p->hw = hw;
+
+	p->imem_table = ice_imem_table_get(hw);
+	if (IS_ERR(p->imem_table)) {
+		err = p->imem_table;
+		goto err;
+	}
+
+	p->mi_table = ice_metainit_table_get(hw);
+	if (IS_ERR(p->mi_table)) {
+		err = p->mi_table;
+		goto err;
+	}
+
+	p->pg_cam_table = ice_pg_cam_table_get(hw);
+	if (IS_ERR(p->pg_cam_table)) {
+		err = p->pg_cam_table;
+		goto err;
+	}
+
+	p->pg_sp_cam_table = ice_pg_sp_cam_table_get(hw);
+	if (IS_ERR(p->pg_sp_cam_table)) {
+		err = p->pg_sp_cam_table;
+		goto err;
+	}
+
+	p->pg_nm_cam_table = ice_pg_nm_cam_table_get(hw);
+	if (IS_ERR(p->pg_nm_cam_table)) {
+		err = p->pg_nm_cam_table;
+		goto err;
+	}
+
+	p->pg_nm_sp_cam_table = ice_pg_nm_sp_cam_table_get(hw);
+	if (IS_ERR(p->pg_nm_sp_cam_table)) {
+		err = p->pg_nm_sp_cam_table;
+		goto err;
+	}
+
+	p->bst_tcam_table = ice_bst_tcam_table_get(hw);
+	if (IS_ERR(p->bst_tcam_table)) {
+		err = p->bst_tcam_table;
+		goto err;
+	}
+
+	p->bst_lbl_table = ice_bst_lbl_table_get(hw);
+	if (IS_ERR(p->bst_lbl_table)) {
+		err = p->bst_lbl_table;
+		goto err;
+	}
+
+	p->ptype_mk_tcam_table = ice_ptype_mk_tcam_table_get(hw);
+	if (IS_ERR(p->ptype_mk_tcam_table)) {
+		err = p->ptype_mk_tcam_table;
+		goto err;
+	}
+
+	p->mk_grp_table = ice_mk_grp_table_get(hw);
+	if (IS_ERR(p->mk_grp_table)) {
+		err = p->mk_grp_table;
+		goto err;
+	}
+
+	p->proto_grp_table = ice_proto_grp_table_get(hw);
+	if (IS_ERR(p->proto_grp_table)) {
+		err = p->proto_grp_table;
+		goto err;
+	}
+
+	p->flg_rd_table = ice_flg_rd_table_get(hw);
+	if (IS_ERR(p->flg_rd_table)) {
+		err = p->flg_rd_table;
+		goto err;
+	}
+
+	p->xlt_kb_sw = ice_xlt_kb_get_sw(hw);
+	if (IS_ERR(p->xlt_kb_sw)) {
+		err = p->xlt_kb_sw;
+		goto err;
+	}
+
+	p->xlt_kb_acl = ice_xlt_kb_get_acl(hw);
+	if (IS_ERR(p->xlt_kb_acl)) {
+		err = p->xlt_kb_acl;
+		goto err;
+	}
+
+	p->xlt_kb_fd = ice_xlt_kb_get_fd(hw);
+	if (IS_ERR(p->xlt_kb_fd)) {
+		err = p->xlt_kb_fd;
+		goto err;
+	}
+
+	p->xlt_kb_rss = ice_xlt_kb_get_rss(hw);
+	if (IS_ERR(p->xlt_kb_rss)) {
+		err = p->xlt_kb_rss;
+		goto err;
+	}
+
 	return p;
+err:
+	ice_parser_destroy(p);
+	return err;
 }
 
 /**
@@ -28,5 +1394,22 @@ struct ice_parser *ice_parser_create(struct ice_hw *hw)
  */
 void ice_parser_destroy(struct ice_parser *psr)
 {
+	kfree(psr->imem_table);
+	kfree(psr->mi_table);
+	kfree(psr->pg_cam_table);
+	kfree(psr->pg_sp_cam_table);
+	kfree(psr->pg_nm_cam_table);
+	kfree(psr->pg_nm_sp_cam_table);
+	kfree(psr->bst_tcam_table);
+	kfree(psr->bst_lbl_table);
+	kfree(psr->ptype_mk_tcam_table);
+	kfree(psr->mk_grp_table);
+	kfree(psr->proto_grp_table);
+	kfree(psr->flg_rd_table);
+	kfree(psr->xlt_kb_sw);
+	kfree(psr->xlt_kb_acl);
+	kfree(psr->xlt_kb_fd);
+	kfree(psr->xlt_kb_rss);
+
 	kfree(psr);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 09ed380eee32..6e8054d59644 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -4,8 +4,366 @@
 #ifndef _ICE_PARSER_H_
 #define _ICE_PARSER_H_
 
+#define ICE_SEC_DATA_OFFSET				4
+#define ICE_SID_RXPARSER_IMEM_ENTRY_SIZE		48
+#define ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE	24
+#define ICE_SID_RXPARSER_CAM_ENTRY_SIZE			16
+#define ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE		17
+#define ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE		12
+#define ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE	13
+#define ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE		88
+#define ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE		24
+#define ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE		8
+#define ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE		24
+#define ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE		1
+
+#define ICE_SEC_LBL_DATA_OFFSET				2
+#define ICE_SID_LBL_ENTRY_SIZE				66
+
+/*** ICE_SID_RXPARSER_IMEM section ***/
+#define ICE_IMEM_TABLE_SIZE		192
+
+/* TCAM boost Master; if bit is set, and TCAM hit, TCAM output overrides iMEM
+ * output.
+ */
+struct ice_bst_main {
+	bool alu0;
+	bool alu1;
+	bool alu2;
+	bool pg;
+};
+
+struct ice_bst_keybuilder {
+	u8 prio;	/* 0-3: PG precedence within ALUs (3 highest) */
+	bool tsr_ctrl;	/* TCAM Search Register control */
+};
+
+/* Next protocol Key builder */
+struct ice_np_keybuilder {
+	u8 opc;
+	u8 start_reg0;
+	u8 len_reg1;
+};
+
+enum ice_np_keybuilder_opcode {
+	ICE_NPKB_OPC_EXTRACT	= 0,
+	ICE_NPKB_OPC_BUILD	= 1,
+	ICE_NPKB_OPC_BYPASS	= 2,
+};
+
+/* Parse Graph Key builder */
+struct ice_pg_keybuilder {
+	bool flag0_ena;
+	bool flag1_ena;
+	bool flag2_ena;
+	bool flag3_ena;
+	u8 flag0_idx;
+	u8 flag1_idx;
+	u8 flag2_idx;
+	u8 flag3_idx;
+	u8 alu_reg_idx;
+};
+
+enum ice_alu_idx {
+	ICE_ALU0_IDX	= 0,
+	ICE_ALU1_IDX	= 1,
+	ICE_ALU2_IDX	= 2,
+};
+
+enum ice_alu_opcode {
+	ICE_ALU_PARK	= 0,
+	ICE_ALU_MOV_ADD	= 1,
+	ICE_ALU_ADD	= 2,
+	ICE_ALU_MOV_AND	= 4,
+	ICE_ALU_AND	= 5,
+	ICE_ALU_AND_IMM	= 6,
+	ICE_ALU_MOV_OR	= 7,
+	ICE_ALU_OR	= 8,
+	ICE_ALU_MOV_XOR	= 9,
+	ICE_ALU_XOR	= 10,
+	ICE_ALU_NOP	= 11,
+	ICE_ALU_BR	= 12,
+	ICE_ALU_BREQ	= 13,
+	ICE_ALU_BRNEQ	= 14,
+	ICE_ALU_BRGT	= 15,
+	ICE_ALU_BRLT	= 16,
+	ICE_ALU_BRGEQ	= 17,
+	ICE_ALU_BRLEG	= 18,
+	ICE_ALU_SETEQ	= 19,
+	ICE_ALU_ANDEQ	= 20,
+	ICE_ALU_OREQ	= 21,
+	ICE_ALU_SETNEQ	= 22,
+	ICE_ALU_ANDNEQ	= 23,
+	ICE_ALU_ORNEQ	= 24,
+	ICE_ALU_SETGT	= 25,
+	ICE_ALU_ANDGT	= 26,
+	ICE_ALU_ORGT	= 27,
+	ICE_ALU_SETLT	= 28,
+	ICE_ALU_ANDLT	= 29,
+	ICE_ALU_ORLT	= 30,
+	ICE_ALU_MOV_SUB	= 31,
+	ICE_ALU_SUB	= 32,
+	ICE_ALU_INVALID	= 64,
+};
+
+enum ice_proto_off_opcode {
+	ICE_PO_OFF_REMAIN	= 0,
+	ICE_PO_OFF_HDR_ADD	= 1,
+	ICE_PO_OFF_HDR_SUB	= 2,
+};
+
+struct ice_alu {
+	enum ice_alu_opcode opc;
+	u8 src_start;
+	u8 src_len;
+	bool shift_xlate_sel;
+	u8 shift_xlate_key;
+	u8 src_reg_id;
+	u8 dst_reg_id;
+	bool inc0;
+	bool inc1;
+	u8 proto_offset_opc;
+	u8 proto_offset;
+	u8 branch_addr;
+	u16 imm;
+	bool dedicate_flags_ena;
+	u8 dst_start;
+	u8 dst_len;
+	bool flags_extr_imm;
+	u8 flags_start_imm;
+};
+
+/* Parser program code (iMEM) */
+struct ice_imem_item {
+	u16 idx;
+	struct ice_bst_main b_m;
+	struct ice_bst_keybuilder b_kb;
+	u8 pg_prio;
+	struct ice_np_keybuilder np_kb;
+	struct ice_pg_keybuilder pg_kb;
+	struct ice_alu alu0;
+	struct ice_alu alu1;
+	struct ice_alu alu2;
+};
+
+/*** ICE_SID_RXPARSER_METADATA_INIT section ***/
+#define ICE_METAINIT_TABLE_SIZE		16
+
+/* Metadata Initialization item  */
+struct ice_metainit_item {
+	u16 idx;
+
+	u8 tsr;		/* TCAM Search key Register */
+	u16 ho;		/* Header Offset register */
+	u16 pc;		/* Program Counter register */
+	u16 pg_rn;	/* Parse Graph Root Node */
+	u8 cd;		/* Control Domain ID */
+
+	/* General Purpose Registers */
+	bool gpr_a_ctrl;
+	u8 gpr_a_data_mdid;
+	u8 gpr_a_data_start;
+	u8 gpr_a_data_len;
+	u8 gpr_a_id;
+
+	bool gpr_b_ctrl;
+	u8 gpr_b_data_mdid;
+	u8 gpr_b_data_start;
+	u8 gpr_b_data_len;
+	u8 gpr_b_id;
+
+	bool gpr_c_ctrl;
+	u8 gpr_c_data_mdid;
+	u8 gpr_c_data_start;
+	u8 gpr_c_data_len;
+	u8 gpr_c_id;
+
+	bool gpr_d_ctrl;
+	u8 gpr_d_data_mdid;
+	u8 gpr_d_data_start;
+	u8 gpr_d_data_len;
+	u8 gpr_d_id;
+
+	u64 flags; /* Initial value for all flags */
+};
+
+/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL,
+ *    ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM
+ *    sections ***/
+#define ICE_PG_CAM_TABLE_SIZE		2048
+#define ICE_PG_SP_CAM_TABLE_SIZE	128
+#define ICE_PG_NM_CAM_TABLE_SIZE	1024
+#define ICE_PG_NM_SP_CAM_TABLE_SIZE	64
+
+struct ice_pg_cam_key {
+	bool valid;
+	u16 node_id;	/* Node ID of protocol in parse graph */
+	bool flag0;
+	bool flag1;
+	bool flag2;
+	bool flag3;
+	u8 boost_idx;	/* Boost TCAM match index */
+	u16 alu_reg;
+	u32 next_proto;	/* next Protocol value */
+};
+
+struct ice_pg_nm_cam_key {
+	bool valid;
+	u16 node_id;
+	bool flag0;
+	bool flag1;
+	bool flag2;
+	bool flag3;
+	u8 boost_idx;
+	u16 alu_reg;
+};
+
+struct ice_pg_cam_action {
+	u16 next_node;	/* Parser Node ID for the next round */
+	u8 next_pc;	/* next Program Counter */
+	bool is_pg;	/* is protocol group */
+	u8 proto_id;	/* protocol ID or proto group ID */
+	bool is_mg;	/* is marker group */
+	u8 marker_id;	/* marker ID or marker group ID */
+	bool is_last_round;
+	bool ho_polarity; /* header offset polarity */
+	u16 ho_inc;
+};
+
+/* Parse Graph item */
+struct ice_pg_cam_item {
+	u16 idx;
+	struct ice_pg_cam_key key;
+	struct ice_pg_cam_action action;
+};
+
+/* Parse Graph No Match item */
+struct ice_pg_nm_cam_item {
+	u16 idx;
+	struct ice_pg_nm_cam_key key;
+	struct ice_pg_cam_action action;
+};
+
+/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
+#define ICE_BST_TCAM_TABLE_SIZE		256
+#define ICE_BST_TCAM_KEY_SIZE		20
+#define ICE_BST_KEY_TCAM_SIZE		19
+
+/* Boost TCAM item */
+struct ice_bst_tcam_item {
+	u16 addr;
+	u8 key[ICE_BST_TCAM_KEY_SIZE];
+	u8 key_inv[ICE_BST_TCAM_KEY_SIZE];
+	u8 hit_idx_grp;
+	u8 pg_prio;
+	struct ice_np_keybuilder np_kb;
+	struct ice_pg_keybuilder pg_kb;
+	struct ice_alu alu0;
+	struct ice_alu alu1;
+	struct ice_alu alu2;
+};
+
+#define ICE_LBL_LEN			64
+struct ice_lbl_item {
+	u16 idx;
+	char label[ICE_LBL_LEN];
+};
+
+/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/
+#define ICE_PTYPE_MK_TCAM_TABLE_SIZE	1024
+#define ICE_PTYPE_MK_TCAM_KEY_SIZE	10
+
+struct ice_ptype_mk_tcam_item {
+	u16 address;
+	u16 ptype;
+	u8 key[ICE_PTYPE_MK_TCAM_KEY_SIZE];
+	u8 key_inv[ICE_PTYPE_MK_TCAM_KEY_SIZE];
+} __packed;
+
+/*** ICE_SID_RXPARSER_MARKER_GRP section ***/
+#define ICE_MK_GRP_TABLE_SIZE		128
+#define ICE_MK_COUNT_PER_GRP		8
+
+/*  Marker Group item */
+struct ice_mk_grp_item {
+	int idx;
+	u8 markers[ICE_MK_COUNT_PER_GRP];
+};
+
+/*** ICE_SID_RXPARSER_PROTO_GRP section ***/
+#define ICE_PROTO_COUNT_PER_GRP		8
+#define ICE_PROTO_GRP_TABLE_SIZE	192
+#define ICE_PROTO_GRP_ITEM_SIZE		22
+struct ice_proto_off {
+	bool polarity;	/* true: positive, false: negative */
+	u8 proto_id;
+	u16 offset;	/* 10 bit protocol offset */
+};
+
+/*  Protocol Group item */
+struct ice_proto_grp_item {
+	u16 idx;
+	struct ice_proto_off po[ICE_PROTO_COUNT_PER_GRP];
+};
+
+/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/
+#define ICE_FLG_RD_TABLE_SIZE	64
+
+/* Flags Redirection item */
+struct ice_flg_rd_item {
+	u16 idx;
+	bool expose;
+	u8 intr_flg_id;	/* Internal Flag ID */
+};
+
+/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL,
+ * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS
+ * sections ***/
+#define ICE_XLT_KB_FLAG0_14_CNT		15
+#define ICE_XLT_KB_TBL_CNT		8
+#define ICE_XLT_KB_TBL_ENTRY_SIZE	24
+
+struct ice_xlt_kb_entry {
+	u8 xlt1_ad_sel;
+	u8 xlt2_ad_sel;
+	u16 flg0_14_sel[ICE_XLT_KB_FLAG0_14_CNT];
+	u8 xlt1_md_sel;
+	u8 xlt2_md_sel;
+};
+
+/* XLT Key Builder */
+struct ice_xlt_kb {
+	u8 xlt1_pm;	/* XLT1 Partition Mode */
+	u8 xlt2_pm;	/* XLT2 Partition Mode */
+	u8 prof_id_pm;	/* Profile ID Partition Mode */
+	u64 flag15;
+
+	struct ice_xlt_kb_entry entries[ICE_XLT_KB_TBL_CNT];
+};
+
+/*** Parser API ***/
 struct ice_parser {
 	struct ice_hw *hw; /* pointer to the hardware structure */
+
+	struct ice_imem_item *imem_table;
+	struct ice_metainit_item *mi_table;
+
+	struct ice_pg_cam_item *pg_cam_table;
+	struct ice_pg_cam_item *pg_sp_cam_table;
+	struct ice_pg_nm_cam_item *pg_nm_cam_table;
+	struct ice_pg_nm_cam_item *pg_nm_sp_cam_table;
+
+	struct ice_bst_tcam_item *bst_tcam_table;
+	struct ice_lbl_item *bst_lbl_table;
+	struct ice_ptype_mk_tcam_item *ptype_mk_tcam_table;
+	struct ice_mk_grp_item *mk_grp_table;
+	struct ice_proto_grp_item *proto_grp_table;
+	struct ice_flg_rd_item *flg_rd_table;
+
+	struct ice_xlt_kb *xlt_kb_sw;
+	struct ice_xlt_kb *xlt_kb_acl;
+	struct ice_xlt_kb *xlt_kb_fd;
+	struct ice_xlt_kb *xlt_kb_rss;
 };
 
 struct ice_parser *ice_parser_create(struct ice_hw *hw);
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 96037bef3e78..b9e443232335 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -61,6 +61,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R)
 				 ICE_DBG_AQ_DESC	| \
 				 ICE_DBG_AQ_DESC_BUF	| \
 				 ICE_DBG_AQ_CMD)
+#define ICE_DBG_PARSER		BIT_ULL(28)
 
 #define ICE_DBG_USER		BIT_ULL(31)
 
-- 
cgit v1.3-3-g829e


From 68add288189a5490868ccf8cbed273320568928d Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:07:59 -0600
Subject: ice: add debugging functions for the parser sections

Add debug for all parser sections.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_parser.c | 470 ++++++++++++++++++++++++++++
 1 file changed, 470 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index 5fdc87034fc6..23ba1a36742e 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -129,6 +129,100 @@ ice_parser_create_table(struct ice_hw *hw, u32 sect_type,
 }
 
 /*** ICE_SID_RXPARSER_IMEM section ***/
+static void ice_imem_bst_bm_dump(struct ice_hw *hw, struct ice_bst_main *bm)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "boost main:\n");
+	dev_info(dev, "\talu0 = %d\n", bm->alu0);
+	dev_info(dev, "\talu1 = %d\n", bm->alu1);
+	dev_info(dev, "\talu2 = %d\n", bm->alu2);
+	dev_info(dev, "\tpg = %d\n", bm->pg);
+}
+
+static void ice_imem_bst_kb_dump(struct ice_hw *hw,
+				 struct ice_bst_keybuilder *kb)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "boost key builder:\n");
+	dev_info(dev, "\tpriority = %d\n", kb->prio);
+	dev_info(dev, "\ttsr_ctrl = %d\n", kb->tsr_ctrl);
+}
+
+static void ice_imem_np_kb_dump(struct ice_hw *hw,
+				struct ice_np_keybuilder *kb)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "next proto key builder:\n");
+	dev_info(dev, "\topc = %d\n", kb->opc);
+	dev_info(dev, "\tstart_or_reg0 = %d\n", kb->start_reg0);
+	dev_info(dev, "\tlen_or_reg1 = %d\n", kb->len_reg1);
+}
+
+static void ice_imem_pg_kb_dump(struct ice_hw *hw,
+				struct ice_pg_keybuilder *kb)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "parse graph key builder:\n");
+	dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena);
+	dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena);
+	dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena);
+	dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena);
+	dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx);
+	dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx);
+	dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx);
+	dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx);
+	dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx);
+}
+
+static void ice_imem_alu_dump(struct ice_hw *hw,
+			      struct ice_alu *alu, int index)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "alu%d:\n", index);
+	dev_info(dev, "\topc = %d\n", alu->opc);
+	dev_info(dev, "\tsrc_start = %d\n", alu->src_start);
+	dev_info(dev, "\tsrc_len = %d\n", alu->src_len);
+	dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel);
+	dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key);
+	dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id);
+	dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id);
+	dev_info(dev, "\tinc0 = %d\n", alu->inc0);
+	dev_info(dev, "\tinc1 = %d\n", alu->inc1);
+	dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc);
+	dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset);
+	dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr);
+	dev_info(dev, "\timm = %d\n", alu->imm);
+	dev_info(dev, "\tdst_start = %d\n", alu->dst_start);
+	dev_info(dev, "\tdst_len = %d\n", alu->dst_len);
+	dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm);
+	dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm);
+}
+
+/**
+ * ice_imem_dump - dump an imem item info
+ * @hw: pointer to the hardware structure
+ * @item: imem item to dump
+ */
+static void ice_imem_dump(struct ice_hw *hw, struct ice_imem_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "index = %d\n", item->idx);
+	ice_imem_bst_bm_dump(hw, &item->b_m);
+	ice_imem_bst_kb_dump(hw, &item->b_kb);
+	dev_info(dev, "pg priority = %d\n", item->pg_prio);
+	ice_imem_np_kb_dump(hw, &item->np_kb);
+	ice_imem_pg_kb_dump(hw, &item->pg_kb);
+	ice_imem_alu_dump(hw, &item->alu0, 0);
+	ice_imem_alu_dump(hw, &item->alu1, 1);
+	ice_imem_alu_dump(hw, &item->alu2, 2);
+}
+
 #define ICE_IM_BM_ALU0		BIT(0)
 #define ICE_IM_BM_ALU1		BIT(1)
 #define ICE_IM_BM_ALU2		BIT(2)
@@ -328,6 +422,9 @@ static void ice_imem_parse_item(struct ice_hw *hw, u16 idx, void *item,
 	ice_imem_alu_init(&ii->alu2,
 			  &buf[ICE_IMEM_ALU2_IDD],
 			  ICE_IMEM_ALU2_OFF);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_imem_dump(hw, ii);
 }
 
 /**
@@ -345,6 +442,50 @@ static struct ice_imem_item *ice_imem_table_get(struct ice_hw *hw)
 }
 
 /*** ICE_SID_RXPARSER_METADATA_INIT section ***/
+/**
+ * ice_metainit_dump - dump an metainit item info
+ * @hw: pointer to the hardware structure
+ * @item: metainit item to dump
+ */
+static void ice_metainit_dump(struct ice_hw *hw, struct ice_metainit_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "index = %d\n", item->idx);
+
+	dev_info(dev, "tsr = %d\n", item->tsr);
+	dev_info(dev, "ho = %d\n", item->ho);
+	dev_info(dev, "pc = %d\n", item->pc);
+	dev_info(dev, "pg_rn = %d\n", item->pg_rn);
+	dev_info(dev, "cd = %d\n", item->cd);
+
+	dev_info(dev, "gpr_a_ctrl = %d\n", item->gpr_a_ctrl);
+	dev_info(dev, "gpr_a_data_mdid = %d\n", item->gpr_a_data_mdid);
+	dev_info(dev, "gpr_a_data_start = %d\n", item->gpr_a_data_start);
+	dev_info(dev, "gpr_a_data_len = %d\n", item->gpr_a_data_len);
+	dev_info(dev, "gpr_a_id = %d\n", item->gpr_a_id);
+
+	dev_info(dev, "gpr_b_ctrl = %d\n", item->gpr_b_ctrl);
+	dev_info(dev, "gpr_b_data_mdid = %d\n", item->gpr_b_data_mdid);
+	dev_info(dev, "gpr_b_data_start = %d\n", item->gpr_b_data_start);
+	dev_info(dev, "gpr_b_data_len = %d\n", item->gpr_b_data_len);
+	dev_info(dev, "gpr_b_id = %d\n", item->gpr_b_id);
+
+	dev_info(dev, "gpr_c_ctrl = %d\n", item->gpr_c_ctrl);
+	dev_info(dev, "gpr_c_data_mdid = %d\n", item->gpr_c_data_mdid);
+	dev_info(dev, "gpr_c_data_start = %d\n", item->gpr_c_data_start);
+	dev_info(dev, "gpr_c_data_len = %d\n", item->gpr_c_data_len);
+	dev_info(dev, "gpr_c_id = %d\n", item->gpr_c_id);
+
+	dev_info(dev, "gpr_d_ctrl = %d\n", item->gpr_d_ctrl);
+	dev_info(dev, "gpr_d_data_mdid = %d\n", item->gpr_d_data_mdid);
+	dev_info(dev, "gpr_d_data_start = %d\n", item->gpr_d_data_start);
+	dev_info(dev, "gpr_d_data_len = %d\n", item->gpr_d_data_len);
+	dev_info(dev, "gpr_d_id = %d\n", item->gpr_d_id);
+
+	dev_info(dev, "flags = 0x%llx\n", (unsigned long long)(item->flags));
+}
+
 #define ICE_MI_TSR		GENMASK_ULL(7, 0)
 #define ICE_MI_HO		GENMASK_ULL(16, 8)
 #define ICE_MI_PC		GENMASK_ULL(24, 17)
@@ -437,6 +578,9 @@ static void ice_metainit_parse_item(struct ice_hw *hw, u16 idx, void *item,
 	d64 = *((u64 *)&buf[ICE_MI_FLAG_IDD]) >> ICE_MI_FLAG_OFF;
 
 	mi->flags		= FIELD_GET(ICE_MI_FLAG, d64);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_metainit_dump(hw, mi);
 }
 
 /**
@@ -456,6 +600,80 @@ static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw)
 /*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL,
  *    ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM
  *    sections ***/
+static void ice_pg_cam_key_dump(struct ice_hw *hw, struct ice_pg_cam_key *key)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "key:\n");
+	dev_info(dev, "\tvalid = %d\n", key->valid);
+	dev_info(dev, "\tnode_id = %d\n", key->node_id);
+	dev_info(dev, "\tflag0 = %d\n", key->flag0);
+	dev_info(dev, "\tflag1 = %d\n", key->flag1);
+	dev_info(dev, "\tflag2 = %d\n", key->flag2);
+	dev_info(dev, "\tflag3 = %d\n", key->flag3);
+	dev_info(dev, "\tboost_idx = %d\n", key->boost_idx);
+	dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg);
+	dev_info(dev, "\tnext_proto = 0x%08x\n", key->next_proto);
+}
+
+static void ice_pg_nm_cam_key_dump(struct ice_hw *hw,
+				   struct ice_pg_nm_cam_key *key)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "key:\n");
+	dev_info(dev, "\tvalid = %d\n", key->valid);
+	dev_info(dev, "\tnode_id = %d\n", key->node_id);
+	dev_info(dev, "\tflag0 = %d\n", key->flag0);
+	dev_info(dev, "\tflag1 = %d\n", key->flag1);
+	dev_info(dev, "\tflag2 = %d\n", key->flag2);
+	dev_info(dev, "\tflag3 = %d\n", key->flag3);
+	dev_info(dev, "\tboost_idx = %d\n", key->boost_idx);
+	dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg);
+}
+
+static void ice_pg_cam_action_dump(struct ice_hw *hw,
+				   struct ice_pg_cam_action *action)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "action:\n");
+	dev_info(dev, "\tnext_node = %d\n", action->next_node);
+	dev_info(dev, "\tnext_pc = %d\n", action->next_pc);
+	dev_info(dev, "\tis_pg = %d\n", action->is_pg);
+	dev_info(dev, "\tproto_id = %d\n", action->proto_id);
+	dev_info(dev, "\tis_mg = %d\n", action->is_mg);
+	dev_info(dev, "\tmarker_id = %d\n", action->marker_id);
+	dev_info(dev, "\tis_last_round = %d\n", action->is_last_round);
+	dev_info(dev, "\tho_polarity = %d\n", action->ho_polarity);
+	dev_info(dev, "\tho_inc = %d\n", action->ho_inc);
+}
+
+/**
+ * ice_pg_cam_dump - dump an parse graph cam info
+ * @hw: pointer to the hardware structure
+ * @item: parse graph cam to dump
+ */
+static void ice_pg_cam_dump(struct ice_hw *hw, struct ice_pg_cam_item *item)
+{
+	dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx);
+	ice_pg_cam_key_dump(hw, &item->key);
+	ice_pg_cam_action_dump(hw, &item->action);
+}
+
+/**
+ * ice_pg_nm_cam_dump - dump an parse graph no match cam info
+ * @hw: pointer to the hardware structure
+ * @item: parse graph no match cam to dump
+ */
+static void ice_pg_nm_cam_dump(struct ice_hw *hw,
+			       struct ice_pg_nm_cam_item *item)
+{
+	dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx);
+	ice_pg_nm_cam_key_dump(hw, &item->key);
+	ice_pg_cam_action_dump(hw, &item->action);
+}
+
 #define ICE_PGCA_NN	GENMASK_ULL(10, 0)
 #define ICE_PGCA_NPC	GENMASK_ULL(18, 11)
 #define ICE_PGCA_IPG	BIT_ULL(19)
@@ -584,6 +802,9 @@ static void ice_pg_cam_parse_item(struct ice_hw *hw, u16 idx, void *item,
 
 	d64 = *((u64 *)&buf[ICE_PG_CAM_ACT_IDD]) >> ICE_PG_CAM_ACT_OFF;
 	ice_pg_cam_action_init(&ci->action, d64);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_pg_cam_dump(hw, ci);
 }
 
 #define ICE_PG_SP_CAM_KEY_S	56
@@ -610,6 +831,9 @@ static void ice_pg_sp_cam_parse_item(struct ice_hw *hw, u16 idx, void *item,
 	ice_pg_cam_action_init(&ci->action, d64);
 
 	ice_pg_cam_key_init(&ci->key, &buf[ICE_PG_SP_CAM_KEY_IDD]);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_pg_cam_dump(hw, ci);
 }
 
 #define ICE_PG_NM_CAM_ACT_S	41
@@ -638,6 +862,9 @@ static void ice_pg_nm_cam_parse_item(struct ice_hw *hw, u16 idx, void *item,
 
 	d64 = *((u64 *)&buf[ICE_PG_NM_CAM_ACT_IDD]) >> ICE_PG_NM_CAM_ACT_OFF;
 	ice_pg_cam_action_init(&ci->action, d64);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_pg_nm_cam_dump(hw, ci);
 }
 
 #define ICE_PG_NM_SP_CAM_ACT_S		56
@@ -669,6 +896,9 @@ static void ice_pg_nm_sp_cam_parse_item(struct ice_hw *hw, u16 idx,
 	d64 = *((u64 *)&buf[ICE_PG_NM_SP_CAM_ACT_IDD]) >>
 		ICE_PG_NM_SP_CAM_ACT_OFF;
 	ice_pg_nm_cam_key_init(&ci->key, d64);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_pg_nm_cam_dump(hw, ci);
 }
 
 /**
@@ -728,6 +958,99 @@ static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw)
 }
 
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
+static void ice_bst_np_kb_dump(struct ice_hw *hw, struct ice_np_keybuilder *kb)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "next proto key builder:\n");
+	dev_info(dev, "\topc = %d\n", kb->opc);
+	dev_info(dev, "\tstart_reg0 = %d\n", kb->start_reg0);
+	dev_info(dev, "\tlen_reg1 = %d\n", kb->len_reg1);
+}
+
+static void ice_bst_pg_kb_dump(struct ice_hw *hw, struct ice_pg_keybuilder *kb)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "parse graph key builder:\n");
+	dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena);
+	dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena);
+	dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena);
+	dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena);
+	dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx);
+	dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx);
+	dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx);
+	dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx);
+	dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx);
+}
+
+static void ice_bst_alu_dump(struct ice_hw *hw, struct ice_alu *alu, int idx)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "alu%d:\n", idx);
+	dev_info(dev, "\topc = %d\n", alu->opc);
+	dev_info(dev, "\tsrc_start = %d\n", alu->src_start);
+	dev_info(dev, "\tsrc_len = %d\n", alu->src_len);
+	dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel);
+	dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key);
+	dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id);
+	dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id);
+	dev_info(dev, "\tinc0 = %d\n", alu->inc0);
+	dev_info(dev, "\tinc1 = %d\n", alu->inc1);
+	dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc);
+	dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset);
+	dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr);
+	dev_info(dev, "\timm = %d\n", alu->imm);
+	dev_info(dev, "\tdst_start = %d\n", alu->dst_start);
+	dev_info(dev, "\tdst_len = %d\n", alu->dst_len);
+	dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm);
+	dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm);
+}
+
+/**
+ * ice_bst_tcam_dump - dump a boost tcam info
+ * @hw: pointer to the hardware structure
+ * @item: boost tcam to dump
+ */
+static void ice_bst_tcam_dump(struct ice_hw *hw, struct ice_bst_tcam_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	int i;
+
+	dev_info(dev, "addr = %d\n", item->addr);
+
+	dev_info(dev, "key    : ");
+	for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++)
+		dev_info(dev, "%02x ", item->key[i]);
+
+	dev_info(dev, "\n");
+
+	dev_info(dev, "key_inv: ");
+	for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++)
+		dev_info(dev, "%02x ", item->key_inv[i]);
+
+	dev_info(dev, "\n");
+
+	dev_info(dev, "hit_idx_grp = %d\n", item->hit_idx_grp);
+	dev_info(dev, "pg_prio = %d\n", item->pg_prio);
+
+	ice_bst_np_kb_dump(hw, &item->np_kb);
+	ice_bst_pg_kb_dump(hw, &item->pg_kb);
+
+	ice_bst_alu_dump(hw, &item->alu0, ICE_ALU0_IDX);
+	ice_bst_alu_dump(hw, &item->alu1, ICE_ALU1_IDX);
+	ice_bst_alu_dump(hw, &item->alu2, ICE_ALU2_IDX);
+}
+
+static void ice_lbl_dump(struct ice_hw *hw, struct ice_lbl_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "index = %u\n", item->idx);
+	dev_info(dev, "label = %s\n", item->label);
+}
+
 #define ICE_BST_ALU_OPC		GENMASK_ULL(5, 0)
 #define ICE_BST_ALU_SS		GENMASK_ULL(13, 6)
 #define ICE_BST_ALU_SL		GENMASK_ULL(18, 14)
@@ -894,6 +1217,9 @@ static void ice_bst_parse_item(struct ice_hw *hw, u16 idx, void *item,
 	ice_bst_alu_init(&ti->alu0, &buf[ICE_BT_ALU0_IDD], ICE_BT_ALU0_OFF);
 	ice_bst_alu_init(&ti->alu1, &buf[ICE_BT_ALU1_IDD], ICE_BT_ALU1_OFF);
 	ice_bst_alu_init(&ti->alu2, &buf[ICE_BT_ALU2_IDD], ICE_BT_ALU2_OFF);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_bst_tcam_dump(hw, ti);
 }
 
 /**
@@ -914,6 +1240,9 @@ static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item,
 			       void *data, int size)
 {
 	memcpy(item, data, size);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_lbl_dump(hw, (struct ice_lbl_item *)item);
 }
 
 /**
@@ -931,10 +1260,41 @@ static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw)
 }
 
 /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/
+/**
+ * ice_ptype_mk_tcam_dump - dump an ptype marker tcam info
+ * @hw: pointer to the hardware structure
+ * @item: ptype marker tcam to dump
+ */
+static void ice_ptype_mk_tcam_dump(struct ice_hw *hw,
+				   struct ice_ptype_mk_tcam_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	int i;
+
+	dev_info(dev, "address = %d\n", item->address);
+	dev_info(dev, "ptype = %d\n", item->ptype);
+
+	dev_info(dev, "key    :");
+	for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++)
+		dev_info(dev, "%02x ", item->key[i]);
+
+	dev_info(dev, "\n");
+
+	dev_info(dev, "key_inv:");
+	for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++)
+		dev_info(dev, "%02x ", item->key_inv[i]);
+
+	dev_info(dev, "\n");
+}
+
 static void ice_parse_ptype_mk_tcam_item(struct ice_hw *hw, u16 idx,
 					 void *item, void *data, int size)
 {
 	memcpy(item, data, size);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_ptype_mk_tcam_dump(hw,
+				       (struct ice_ptype_mk_tcam_item *)item);
 }
 
 /**
@@ -953,6 +1313,25 @@ struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw)
 }
 
 /*** ICE_SID_RXPARSER_MARKER_GRP section ***/
+/**
+ * ice_mk_grp_dump - dump an marker group item info
+ * @hw: pointer to the hardware structure
+ * @item: marker group item to dump
+ */
+static void ice_mk_grp_dump(struct ice_hw *hw, struct ice_mk_grp_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	int i;
+
+	dev_info(dev, "index = %d\n", item->idx);
+
+	dev_info(dev, "markers: ");
+	for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++)
+		dev_info(dev, "%d ", item->markers[i]);
+
+	dev_info(dev, "\n");
+}
+
 static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item,
 				  void *data, int __maybe_unused size)
 {
@@ -964,6 +1343,9 @@ static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item,
 
 	for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++)
 		grp->markers[i] = buf[i];
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_mk_grp_dump(hw, grp);
 }
 
 /**
@@ -981,6 +1363,33 @@ static struct ice_mk_grp_item *ice_mk_grp_table_get(struct ice_hw *hw)
 }
 
 /*** ICE_SID_RXPARSER_PROTO_GRP section ***/
+static void ice_proto_off_dump(struct ice_hw *hw,
+			       struct ice_proto_off *po, int idx)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "proto %d\n", idx);
+	dev_info(dev, "\tpolarity = %d\n", po->polarity);
+	dev_info(dev, "\tproto_id = %d\n", po->proto_id);
+	dev_info(dev, "\toffset = %d\n", po->offset);
+}
+
+/**
+ * ice_proto_grp_dump - dump a proto group item info
+ * @hw: pointer to the hardware structure
+ * @item: proto group item to dump
+ */
+static void ice_proto_grp_dump(struct ice_hw *hw,
+			       struct ice_proto_grp_item *item)
+{
+	int i;
+
+	dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx);
+
+	for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++)
+		ice_proto_off_dump(hw, &item->po[i], i);
+}
+
 #define ICE_PO_POL	BIT(0)
 #define ICE_PO_PID	GENMASK(8, 1)
 #define ICE_PO_OFF	GENMASK(21, 12)
@@ -1022,6 +1431,9 @@ static void ice_proto_grp_parse_item(struct ice_hw *hw, u16 idx, void *item,
 		d32 = *((u32 *)&buf[idd]) >> off;
 		ice_proto_off_parse(&grp->po[i], d32);
 	}
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_proto_grp_dump(hw, grp);
 }
 
 /**
@@ -1039,6 +1451,20 @@ static struct ice_proto_grp_item *ice_proto_grp_table_get(struct ice_hw *hw)
 }
 
 /*** ICE_SID_RXPARSER_FLAG_REDIR section ***/
+/**
+ * ice_flg_rd_dump - dump a flag redirect item info
+ * @hw: pointer to the hardware structure
+ * @item: flag redirect item to dump
+ */
+static void ice_flg_rd_dump(struct ice_hw *hw, struct ice_flg_rd_item *item)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+
+	dev_info(dev, "index = %d\n", item->idx);
+	dev_info(dev, "expose = %d\n", item->expose);
+	dev_info(dev, "intr_flg_id = %d\n", item->intr_flg_id);
+}
+
 #define ICE_FRT_EXPO	BIT(0)
 #define ICE_FRT_IFID	GENMASK(6, 1)
 
@@ -1059,6 +1485,9 @@ static void ice_flg_rd_parse_item(struct ice_hw *hw, u16 idx, void *item,
 	rdi->idx = idx;
 	rdi->expose = FIELD_GET(ICE_FRT_EXPO, d8);
 	rdi->intr_flg_id = FIELD_GET(ICE_FRT_IFID, d8);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_flg_rd_dump(hw, rdi);
 }
 
 /**
@@ -1078,6 +1507,44 @@ static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw)
 /*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL,
  * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS
  * sections ***/
+static void ice_xlt_kb_entry_dump(struct ice_hw *hw,
+				  struct ice_xlt_kb_entry *entry, int idx)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	int i;
+
+	dev_info(dev, "key builder entry %d\n", idx);
+	dev_info(dev, "\txlt1_ad_sel = %d\n", entry->xlt1_ad_sel);
+	dev_info(dev, "\txlt2_ad_sel = %d\n", entry->xlt2_ad_sel);
+
+	for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++)
+		dev_info(dev, "\tflg%d_sel = %d\n", i, entry->flg0_14_sel[i]);
+
+	dev_info(dev, "\txlt1_md_sel = %d\n", entry->xlt1_md_sel);
+	dev_info(dev, "\txlt2_md_sel = %d\n", entry->xlt2_md_sel);
+}
+
+/**
+ * ice_xlt_kb_dump - dump a xlt key build info
+ * @hw: pointer to the hardware structure
+ * @kb: key build to dump
+ */
+static void ice_xlt_kb_dump(struct ice_hw *hw, struct ice_xlt_kb *kb)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	int i;
+
+	dev_info(dev, "xlt1_pm = %d\n", kb->xlt1_pm);
+	dev_info(dev, "xlt2_pm = %d\n", kb->xlt2_pm);
+	dev_info(dev, "prof_id_pm = %d\n", kb->prof_id_pm);
+	dev_info(dev, "flag15 lo = 0x%08x\n", (u32)kb->flag15);
+	dev_info(dev, "flag15 hi = 0x%08x\n",
+		 (u32)(kb->flag15 >> (sizeof(u32) * BITS_PER_BYTE)));
+
+	for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++)
+		ice_xlt_kb_entry_dump(hw, &kb->entries[i], i);
+}
+
 #define ICE_XLT_KB_X1AS_S	32	/* offset for the 1st 64-bits field */
 #define ICE_XLT_KB_X1AS_IDD	(ICE_XLT_KB_X1AS_S / BITS_PER_BYTE)
 #define ICE_XLT_KB_X1AS_OFF	(ICE_XLT_KB_X1AS_S % BITS_PER_BYTE)
@@ -1194,6 +1661,9 @@ static void ice_parse_kb_data(struct ice_hw *hw, struct ice_xlt_kb *kb,
 		ice_kb_entry_init(&kb->entries[i],
 				  &buf[ICE_XLT_KB_TBL_OFF +
 				       i * ICE_XLT_KB_TBL_ENTRY_SIZE]);
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_xlt_kb_dump(hw, kb);
 }
 
 static struct ice_xlt_kb *ice_xlt_kb_get(struct ice_hw *hw, u32 sect_type)
-- 
cgit v1.3-3-g829e


From 4851f12c8d8a0dc89d1bf83ec9d7f34bd4f65572 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:00 -0600
Subject: ice: add parser internal helper functions

Add the following internal helper functions:

- ice_bst_tcam_match():
  to perform ternary match on boost TCAM.

- ice_pg_cam_match():
  to perform parse graph key match in cam table.

- ice_pg_nm_cam_match():
  to perform parse graph key no match in cam table.

- ice_ptype_mk_tcam_match():
  to perform ptype markers match in tcam table.

- ice_flg_redirect():
  to redirect parser flags to packet flags.

- ice_xlt_kb_flag_get():
  to aggregate 64 bit packet flag into 16 bit key builder flags.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_parser.c | 208 ++++++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_parser.h |  51 +++++--
 2 files changed, 244 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index 23ba1a36742e..f44310e94150 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -957,6 +957,109 @@ static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw)
 				       ice_pg_nm_sp_cam_parse_item, false);
 }
 
+static bool __ice_pg_cam_match(struct ice_pg_cam_item *item,
+			       struct ice_pg_cam_key *key)
+{
+	return (item->key.valid &&
+		!memcmp(&item->key.val, &key->val, sizeof(key->val)));
+}
+
+static bool __ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *item,
+				  struct ice_pg_cam_key *key)
+{
+	return (item->key.valid &&
+		!memcmp(&item->key.val, &key->val, sizeof(item->key.val)));
+}
+
+/**
+ * ice_pg_cam_match - search parse graph cam table by key
+ * @table: parse graph cam table to search
+ * @size: cam table size
+ * @key: search key
+ *
+ * Return: a pointer to the matching PG CAM item or NULL.
+ */
+struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table,
+					 int size, struct ice_pg_cam_key *key)
+{
+	int i;
+
+	for (i = 0; i < size; i++) {
+		struct ice_pg_cam_item *item = &table[i];
+
+		if (__ice_pg_cam_match(item, key))
+			return item;
+	}
+
+	return NULL;
+}
+
+/**
+ * ice_pg_nm_cam_match - search parse graph no match cam table by key
+ * @table: parse graph no match cam table to search
+ * @size: cam table size
+ * @key: search key
+ *
+ * Return: a pointer to the matching PG No Match CAM item or NULL.
+ */
+struct ice_pg_nm_cam_item *
+ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size,
+		    struct ice_pg_cam_key *key)
+{
+	int i;
+
+	for (i = 0; i < size; i++) {
+		struct ice_pg_nm_cam_item *item = &table[i];
+
+		if (__ice_pg_nm_cam_match(item, key))
+			return item;
+	}
+
+	return NULL;
+}
+
+/*** Ternary match ***/
+/* Perform a ternary match on a 1-byte pattern (@pat) given @key and @key_inv
+ * Rules (per bit):
+ *     Key == 0 and Key_inv == 0 : Never match (Don't care)
+ *     Key == 0 and Key_inv == 1 : Match on bit == 1
+ *     Key == 1 and Key_inv == 0 : Match on bit == 0
+ *     Key == 1 and Key_inv == 1 : Always match (Don't care)
+ *
+ * Return: true if all bits match, false otherwise.
+ */
+static bool ice_ternary_match_byte(u8 key, u8 key_inv, u8 pat)
+{
+	u8 bit_key, bit_key_inv, bit_pat;
+	int i;
+
+	for (i = 0; i < BITS_PER_BYTE; i++) {
+		bit_key = key & BIT(i);
+		bit_key_inv = key_inv & BIT(i);
+		bit_pat = pat & BIT(i);
+
+		if (bit_key != 0 && bit_key_inv != 0)
+			continue;
+
+		if ((bit_key == 0 && bit_key_inv == 0) || bit_key == bit_pat)
+			return false;
+	}
+
+	return true;
+}
+
+static bool ice_ternary_match(const u8 *key, const u8 *key_inv,
+			      const u8 *pat, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		if (!ice_ternary_match_byte(key[i], key_inv[i], pat[i]))
+			return false;
+
+	return true;
+}
+
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
 static void ice_bst_np_kb_dump(struct ice_hw *hw, struct ice_np_keybuilder *kb)
 {
@@ -1259,6 +1362,31 @@ static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw)
 				       ice_parse_lbl_item, true);
 }
 
+/**
+ * ice_bst_tcam_match - match a pattern on the boost tcam table
+ * @tcam_table: boost tcam table to search
+ * @pat: pattern to match
+ *
+ * Return: a pointer to the matching Boost TCAM item or NULL.
+ */
+struct ice_bst_tcam_item *
+ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat)
+{
+	int i;
+
+	for (i = 0; i < ICE_BST_TCAM_TABLE_SIZE; i++) {
+		struct ice_bst_tcam_item *item = &tcam_table[i];
+
+		if (item->hit_idx_grp == 0)
+			continue;
+		if (ice_ternary_match(item->key, item->key_inv, pat,
+				      ICE_BST_TCAM_KEY_SIZE))
+			return item;
+	}
+
+	return NULL;
+}
+
 /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/
 /**
  * ice_ptype_mk_tcam_dump - dump an ptype marker tcam info
@@ -1312,6 +1440,30 @@ struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw)
 				       ice_parse_ptype_mk_tcam_item, true);
 }
 
+/**
+ * ice_ptype_mk_tcam_match - match a pattern on a ptype marker tcam table
+ * @table: ptype marker tcam table to search
+ * @pat: pattern to match
+ * @len: length of the pattern
+ *
+ * Return: a pointer to the matching Marker PType item or NULL.
+ */
+struct ice_ptype_mk_tcam_item *
+ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table,
+			u8 *pat, int len)
+{
+	int i;
+
+	for (i = 0; i < ICE_PTYPE_MK_TCAM_TABLE_SIZE; i++) {
+		struct ice_ptype_mk_tcam_item *item = &table[i];
+
+		if (ice_ternary_match(item->key, item->key_inv, pat, len))
+			return item;
+	}
+
+	return NULL;
+}
+
 /*** ICE_SID_RXPARSER_MARKER_GRP section ***/
 /**
  * ice_mk_grp_dump - dump an marker group item info
@@ -1504,6 +1656,31 @@ static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw)
 				       ice_flg_rd_parse_item, false);
 }
 
+/**
+ * ice_flg_redirect - redirect a parser flag to packet flag
+ * @table: flag redirect table
+ * @psr_flg: parser flag to redirect
+ *
+ * Return: flag or 0 if @psr_flag = 0.
+ */
+u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg)
+{
+	u64 flg = 0;
+	int i;
+
+	for (i = 0; i < ICE_FLG_RDT_SIZE; i++) {
+		struct ice_flg_rd_item *item = &table[i];
+
+		if (!item->expose)
+			continue;
+
+		if (psr_flg & BIT(item->intr_flg_id))
+			flg |= BIT(i);
+	}
+
+	return flg;
+}
+
 /*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL,
  * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS
  * sections ***/
@@ -1737,6 +1914,37 @@ static struct ice_xlt_kb *ice_xlt_kb_get_rss(struct ice_hw *hw)
 	return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_RSS);
 }
 
+#define ICE_XLT_KB_MASK		GENMASK_ULL(5, 0)
+
+/**
+ * ice_xlt_kb_flag_get - aggregate 64 bits packet flag into 16 bits xlt flag
+ * @kb: xlt key build
+ * @pkt_flag: 64 bits packet flag
+ *
+ * Return: XLT flag or 0 if @pkt_flag = 0.
+ */
+u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag)
+{
+	struct ice_xlt_kb_entry *entry = &kb->entries[0];
+	u16 flag = 0;
+	int i;
+
+	/* check flag 15 */
+	if (kb->flag15 & pkt_flag)
+		flag = BIT(ICE_XLT_KB_FLAG0_14_CNT);
+
+	/* check flag 0 - 14 */
+	for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) {
+		/* only check first entry */
+		u16 idx = entry->flg0_14_sel[i] & ICE_XLT_KB_MASK;
+
+		if (pkt_flag & BIT(idx))
+			flag |= (u16)BIT(i);
+	}
+
+	return flag;
+}
+
 /*** Parser API ***/
 /**
  * ice_parser_create - create a parser instance
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 6e8054d59644..1d2453890d8e 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -197,25 +197,29 @@ struct ice_metainit_item {
 
 struct ice_pg_cam_key {
 	bool valid;
-	u16 node_id;	/* Node ID of protocol in parse graph */
-	bool flag0;
-	bool flag1;
-	bool flag2;
-	bool flag3;
-	u8 boost_idx;	/* Boost TCAM match index */
-	u16 alu_reg;
-	u32 next_proto;	/* next Protocol value */
+	struct_group_attr(val, __packed,
+		u16 node_id;	/* Node ID of protocol in parse graph */
+		bool flag0;
+		bool flag1;
+		bool flag2;
+		bool flag3;
+		u8 boost_idx;	/* Boost TCAM match index */
+		u16 alu_reg;
+		u32 next_proto;	/* next Protocol value (must be last) */
+	);
 };
 
 struct ice_pg_nm_cam_key {
 	bool valid;
-	u16 node_id;
-	bool flag0;
-	bool flag1;
-	bool flag2;
-	bool flag3;
-	u8 boost_idx;
-	u16 alu_reg;
+	struct_group_attr(val, __packed,
+		u16 node_id;
+		bool flag0;
+		bool flag1;
+		bool flag2;
+		bool flag3;
+		u8 boost_idx;
+		u16 alu_reg;
+	);
 };
 
 struct ice_pg_cam_action {
@@ -244,6 +248,12 @@ struct ice_pg_nm_cam_item {
 	struct ice_pg_cam_action action;
 };
 
+struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table,
+					 int size, struct ice_pg_cam_key *key);
+struct ice_pg_nm_cam_item *
+ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size,
+		    struct ice_pg_cam_key *key);
+
 /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/
 #define ICE_BST_TCAM_TABLE_SIZE		256
 #define ICE_BST_TCAM_KEY_SIZE		20
@@ -269,6 +279,9 @@ struct ice_lbl_item {
 	char label[ICE_LBL_LEN];
 };
 
+struct ice_bst_tcam_item *
+ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat);
+
 /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/
 #define ICE_PTYPE_MK_TCAM_TABLE_SIZE	1024
 #define ICE_PTYPE_MK_TCAM_KEY_SIZE	10
@@ -280,6 +293,9 @@ struct ice_ptype_mk_tcam_item {
 	u8 key_inv[ICE_PTYPE_MK_TCAM_KEY_SIZE];
 } __packed;
 
+struct ice_ptype_mk_tcam_item *
+ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table,
+			u8 *pat, int len);
 /*** ICE_SID_RXPARSER_MARKER_GRP section ***/
 #define ICE_MK_GRP_TABLE_SIZE		128
 #define ICE_MK_COUNT_PER_GRP		8
@@ -308,6 +324,7 @@ struct ice_proto_grp_item {
 
 /*** ICE_SID_RXPARSER_FLAG_REDIR section ***/
 #define ICE_FLG_RD_TABLE_SIZE	64
+#define ICE_FLG_RDT_SIZE	64
 
 /* Flags Redirection item */
 struct ice_flg_rd_item {
@@ -316,6 +333,8 @@ struct ice_flg_rd_item {
 	u8 intr_flg_id;	/* Internal Flag ID */
 };
 
+u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg);
+
 /*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL,
  * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS
  * sections ***/
@@ -341,6 +360,8 @@ struct ice_xlt_kb {
 	struct ice_xlt_kb_entry entries[ICE_XLT_KB_TBL_CNT];
 };
 
+u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag);
+
 /*** Parser API ***/
 struct ice_parser {
 	struct ice_hw *hw; /* pointer to the hardware structure */
-- 
cgit v1.3-3-g829e


From 9a4c07aaa0f54dd2ddd9e772be9b9ece27b229f0 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:01 -0600
Subject: ice: add parser execution main loop

Implement the core work of the runtime parser via:
- ice_parser_rt_execute()
- ice_parser_rt_reset()
- ice_parser_rt_pkt_buf_set()

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile        |   1 +
 drivers/net/ethernet/intel/ice/ice_parser.c    |  41 ++
 drivers/net/ethernet/intel/ice/ice_parser.h    |  91 +++
 drivers/net/ethernet/intel/ice/ice_parser_rt.c | 861 +++++++++++++++++++++++++
 4 files changed, 994 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_parser_rt.c

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 23fa3f7f36ef..b4f6fa4ba13d 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -29,6 +29,7 @@ ice-y := ice_main.o	\
 	 ice_flex_pipe.o \
 	 ice_flow.o	\
 	 ice_parser.o    \
+	 ice_parser_rt.o \
 	 ice_idc.o	\
 	 devlink/devlink.o	\
 	 devlink/devlink_port.o \
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index f44310e94150..e40dc31a5601 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -1963,6 +1963,7 @@ struct ice_parser *ice_parser_create(struct ice_hw *hw)
 		return ERR_PTR(-ENOMEM);
 
 	p->hw = hw;
+	p->rt.psr = p;
 
 	p->imem_table = ice_imem_table_get(hw);
 	if (IS_ERR(p->imem_table)) {
@@ -2091,3 +2092,43 @@ void ice_parser_destroy(struct ice_parser *psr)
 
 	kfree(psr);
 }
+
+/**
+ * ice_parser_run - parse on a packet in binary and return the result
+ * @psr: pointer to a parser instance
+ * @pkt_buf: packet data
+ * @pkt_len: packet length
+ * @rslt: input/output parameter to save parser result.
+ *
+ * Return: 0 on success or errno.
+ */
+int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf,
+		   int pkt_len, struct ice_parser_result *rslt)
+{
+	ice_parser_rt_reset(&psr->rt);
+	ice_parser_rt_pktbuf_set(&psr->rt, pkt_buf, pkt_len);
+
+	return ice_parser_rt_execute(&psr->rt, rslt);
+}
+
+/**
+ * ice_parser_result_dump - dump a parser result info
+ * @hw: pointer to the hardware structure
+ * @rslt: parser result info to dump
+ */
+void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	int i;
+
+	dev_info(dev, "ptype = %d\n", rslt->ptype);
+	for (i = 0; i < rslt->po_num; i++)
+		dev_info(dev, "proto = %d, offset = %d\n",
+			 rslt->po[i].proto_id, rslt->po[i].offset);
+
+	dev_info(dev, "flags_psr = 0x%016llx\n", rslt->flags_psr);
+	dev_info(dev, "flags_pkt = 0x%016llx\n", rslt->flags_pkt);
+	dev_info(dev, "flags_sw = 0x%04x\n", rslt->flags_sw);
+	dev_info(dev, "flags_fd = 0x%04x\n", rslt->flags_fd);
+	dev_info(dev, "flags_rss = 0x%04x\n", rslt->flags_rss);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 1d2453890d8e..ef08ccbe4874 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -363,6 +363,92 @@ struct ice_xlt_kb {
 u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag);
 
 /*** Parser API ***/
+#define ICE_GPR_HV_IDX		64
+#define ICE_GPR_HV_SIZE		32
+#define ICE_GPR_ERR_IDX		84
+#define ICE_GPR_FLG_IDX		104
+#define ICE_GPR_FLG_SIZE	16
+
+#define ICE_GPR_TSR_IDX		108	/* TSR: TCAM Search Register */
+#define ICE_GPR_NN_IDX		109	/* NN: Next Parsing Cycle Node ID */
+#define ICE_GPR_HO_IDX		110	/* HO: Next Parsing Cycle hdr Offset */
+#define ICE_GPR_NP_IDX		111	/* NP: Next Parsing Cycle */
+
+#define ICE_PARSER_MAX_PKT_LEN	504
+#define ICE_PARSER_PKT_REV	32
+#define ICE_PARSER_GPR_NUM	128
+#define ICE_PARSER_FLG_NUM	64
+#define ICE_PARSER_ERR_NUM	16
+#define ICE_BST_KEY_SIZE	10
+#define ICE_MARKER_ID_SIZE	9
+#define ICE_MARKER_MAX_SIZE	\
+		(ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1)
+#define ICE_MARKER_ID_NUM	8
+#define ICE_PO_PAIR_SIZE	256
+
+struct ice_gpr_pu {
+	/* array of flags to indicate if GRP needs to be updated */
+	bool gpr_val_upd[ICE_PARSER_GPR_NUM];
+	u16 gpr_val[ICE_PARSER_GPR_NUM];
+	u64 flg_msk;
+	u64 flg_val;
+	u16 err_msk;
+	u16 err_val;
+};
+
+enum ice_pg_prio {
+	ICE_PG_P0	= 0,
+	ICE_PG_P1	= 1,
+	ICE_PG_P2	= 2,
+	ICE_PG_P3	= 3,
+};
+
+struct ice_parser_rt {
+	struct ice_parser *psr;
+	u16 gpr[ICE_PARSER_GPR_NUM];
+	u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV];
+	u16 pkt_len;
+	u16 po;
+	u8 bst_key[ICE_BST_KEY_SIZE];
+	struct ice_pg_cam_key pg_key;
+	struct ice_alu *alu0;
+	struct ice_alu *alu1;
+	struct ice_alu *alu2;
+	struct ice_pg_cam_action *action;
+	u8 pg_prio;
+	struct ice_gpr_pu pu;
+	u8 markers[ICE_MARKER_ID_SIZE];
+	bool protocols[ICE_PO_PAIR_SIZE];
+	u16 offsets[ICE_PO_PAIR_SIZE];
+};
+
+struct ice_parser_proto_off {
+	u8 proto_id;	/* hardware protocol ID */
+	u16 offset;	/* offset from the start of the protocol header */
+};
+
+#define ICE_PARSER_PROTO_OFF_PAIR_SIZE	16
+#define ICE_PARSER_FLAG_PSR_SIZE	8
+
+struct ice_parser_result {
+	u16 ptype;	/* 16 bits hardware PTYPE */
+	/* array of protocol and header offset pairs */
+	struct ice_parser_proto_off po[ICE_PARSER_PROTO_OFF_PAIR_SIZE];
+	int po_num;	/* # of protocol-offset pairs must <= 16 */
+	u64 flags_psr;	/* parser flags */
+	u64 flags_pkt;	/* packet flags */
+	u16 flags_sw;	/* key builder flags for SW */
+	u16 flags_acl;	/* key builder flags for ACL */
+	u16 flags_fd;	/* key builder flags for FD */
+	u16 flags_rss;	/* key builder flags for RSS */
+};
+
+void ice_parser_rt_reset(struct ice_parser_rt *rt);
+void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf,
+			      int pkt_len);
+int ice_parser_rt_execute(struct ice_parser_rt *rt,
+			  struct ice_parser_result *rslt);
+
 struct ice_parser {
 	struct ice_hw *hw; /* pointer to the hardware structure */
 
@@ -385,8 +471,13 @@ struct ice_parser {
 	struct ice_xlt_kb *xlt_kb_acl;
 	struct ice_xlt_kb *xlt_kb_fd;
 	struct ice_xlt_kb *xlt_kb_rss;
+
+	struct ice_parser_rt rt;
 };
 
 struct ice_parser *ice_parser_create(struct ice_hw *hw);
 void ice_parser_destroy(struct ice_parser *psr);
+int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf,
+		   int pkt_len, struct ice_parser_result *rslt);
+void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt);
 #endif /* _ICE_PARSER_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
new file mode 100644
index 000000000000..d5bcc266b01e
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
@@ -0,0 +1,861 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "ice_common.h"
+
+static void ice_rt_tsr_set(struct ice_parser_rt *rt, u16 tsr)
+{
+	rt->gpr[ICE_GPR_TSR_IDX] = tsr;
+}
+
+static void ice_rt_ho_set(struct ice_parser_rt *rt, u16 ho)
+{
+	rt->gpr[ICE_GPR_HO_IDX] = ho;
+	memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE);
+}
+
+static void ice_rt_np_set(struct ice_parser_rt *rt, u16 pc)
+{
+	rt->gpr[ICE_GPR_NP_IDX] = pc;
+}
+
+static void ice_rt_nn_set(struct ice_parser_rt *rt, u16 node)
+{
+	rt->gpr[ICE_GPR_NN_IDX] = node;
+}
+
+static void
+ice_rt_flag_set(struct ice_parser_rt *rt, unsigned int idx, bool set)
+{
+	struct ice_hw *hw = rt->psr->hw;
+	unsigned int word, id;
+
+	word = idx / ICE_GPR_FLG_SIZE;
+	id = idx % ICE_GPR_FLG_SIZE;
+
+	if (set) {
+		rt->gpr[ICE_GPR_FLG_IDX + word] |= (u16)BIT(id);
+		ice_debug(hw, ICE_DBG_PARSER, "Set parser flag %u\n", idx);
+	} else {
+		rt->gpr[ICE_GPR_FLG_IDX + word] &= ~(u16)BIT(id);
+		ice_debug(hw, ICE_DBG_PARSER, "Clear parser flag %u\n", idx);
+	}
+}
+
+static void ice_rt_gpr_set(struct ice_parser_rt *rt, int idx, u16 val)
+{
+	struct ice_hw *hw = rt->psr->hw;
+
+	if (idx == ICE_GPR_HO_IDX)
+		ice_rt_ho_set(rt, val);
+	else
+		rt->gpr[idx] = val;
+
+	ice_debug(hw, ICE_DBG_PARSER, "Set GPR %d value %d\n", idx, val);
+}
+
+static void ice_rt_err_set(struct ice_parser_rt *rt, unsigned int idx, bool set)
+{
+	struct ice_hw *hw = rt->psr->hw;
+
+	if (set) {
+		rt->gpr[ICE_GPR_ERR_IDX] |= (u16)BIT(idx);
+		ice_debug(hw, ICE_DBG_PARSER, "Set parser error %u\n", idx);
+	} else {
+		rt->gpr[ICE_GPR_ERR_IDX] &= ~(u16)BIT(idx);
+		ice_debug(hw, ICE_DBG_PARSER, "Reset parser error %u\n", idx);
+	}
+}
+
+/**
+ * ice_parser_rt_reset - reset the parser runtime
+ * @rt: pointer to the parser runtime
+ */
+void ice_parser_rt_reset(struct ice_parser_rt *rt)
+{
+	struct ice_parser *psr = rt->psr;
+	struct ice_metainit_item *mi;
+	unsigned int i;
+
+	mi = &psr->mi_table[0];
+
+	memset(rt, 0, sizeof(*rt));
+	rt->psr = psr;
+
+	ice_rt_tsr_set(rt, mi->tsr);
+	ice_rt_ho_set(rt, mi->ho);
+	ice_rt_np_set(rt, mi->pc);
+	ice_rt_nn_set(rt, mi->pg_rn);
+
+	for (i = 0; i < ICE_PARSER_FLG_NUM; i++) {
+		if (mi->flags & BIT(i))
+			ice_rt_flag_set(rt, i, true);
+	}
+}
+
+/**
+ * ice_parser_rt_pktbuf_set - set a packet into parser runtime
+ * @rt: pointer to the parser runtime
+ * @pkt_buf: buffer with packet data
+ * @pkt_len: packet buffer length
+ */
+void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf,
+			      int pkt_len)
+{
+	int len = min(ICE_PARSER_MAX_PKT_LEN, pkt_len);
+	u16 ho = rt->gpr[ICE_GPR_HO_IDX];
+
+	memcpy(rt->pkt_buf, pkt_buf, len);
+	rt->pkt_len = pkt_len;
+
+	memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE);
+}
+
+static void ice_bst_key_init(struct ice_parser_rt *rt,
+			     struct ice_imem_item *imem)
+{
+	u8 tsr = (u8)rt->gpr[ICE_GPR_TSR_IDX];
+	u16 ho = rt->gpr[ICE_GPR_HO_IDX];
+	u8 *key = rt->bst_key;
+	int idd, i;
+
+	idd = ICE_BST_TCAM_KEY_SIZE - 1;
+	if (imem->b_kb.tsr_ctrl)
+		key[idd] = tsr;
+	else
+		key[idd] = imem->b_kb.prio;
+
+	idd = ICE_BST_KEY_TCAM_SIZE - 1;
+	for (i = idd; i >= 0; i--) {
+		int j;
+
+		j = ho + idd - i;
+		if (j < ICE_PARSER_MAX_PKT_LEN)
+			key[i] = rt->pkt_buf[ho + idd - i];
+		else
+			key[i] = 0;
+	}
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n");
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n",
+		  key[0], key[1], key[2], key[3], key[4],
+		  key[5], key[6], key[7], key[8], key[9]);
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n");
+}
+
+static u16 ice_bit_rev_u16(u16 v, int len)
+{
+	return bitrev16(v) >> (BITS_PER_TYPE(v) - len);
+}
+
+static u32 ice_bit_rev_u32(u32 v, int len)
+{
+	return bitrev32(v) >> (BITS_PER_TYPE(v) - len);
+}
+
+static u32 ice_hv_bit_sel(struct ice_parser_rt *rt, int start, int len)
+{
+	int offset;
+	u32 buf[2];
+	u64 val;
+
+	offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16));
+
+	memcpy(buf, &rt->gpr[offset], sizeof(buf));
+
+	buf[0] = bitrev8x4(buf[0]);
+	buf[1] = bitrev8x4(buf[1]);
+
+	val = *(u64 *)buf;
+	val >>= start % BITS_PER_TYPE(u16);
+
+	return ice_bit_rev_u32(val, len);
+}
+
+static u32 ice_pk_build(struct ice_parser_rt *rt,
+			struct ice_np_keybuilder *kb)
+{
+	if (kb->opc == ICE_NPKB_OPC_EXTRACT)
+		return ice_hv_bit_sel(rt, kb->start_reg0, kb->len_reg1);
+	else if (kb->opc == ICE_NPKB_OPC_BUILD)
+		return rt->gpr[kb->start_reg0] |
+		       ((u32)rt->gpr[kb->len_reg1] << BITS_PER_TYPE(u16));
+	else if (kb->opc == ICE_NPKB_OPC_BYPASS)
+		return 0;
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported OP Code %u\n",
+		  kb->opc);
+	return U32_MAX;
+}
+
+static bool ice_flag_get(struct ice_parser_rt *rt, unsigned int index)
+{
+	int word = index / ICE_GPR_FLG_SIZE;
+	int id = index % ICE_GPR_FLG_SIZE;
+
+	return !!(rt->gpr[ICE_GPR_FLG_IDX + word] & (u16)BIT(id));
+}
+
+static int ice_imem_pgk_init(struct ice_parser_rt *rt,
+			     struct ice_imem_item *imem)
+{
+	memset(&rt->pg_key, 0, sizeof(rt->pg_key));
+	rt->pg_key.next_proto = ice_pk_build(rt, &imem->np_kb);
+	if (rt->pg_key.next_proto == U32_MAX)
+		return -EINVAL;
+
+	if (imem->pg_kb.flag0_ena)
+		rt->pg_key.flag0 = ice_flag_get(rt, imem->pg_kb.flag0_idx);
+	if (imem->pg_kb.flag1_ena)
+		rt->pg_key.flag1 = ice_flag_get(rt, imem->pg_kb.flag1_idx);
+	if (imem->pg_kb.flag2_ena)
+		rt->pg_key.flag2 = ice_flag_get(rt, imem->pg_kb.flag2_idx);
+	if (imem->pg_kb.flag3_ena)
+		rt->pg_key.flag3 = ice_flag_get(rt, imem->pg_kb.flag3_idx);
+
+	rt->pg_key.alu_reg = rt->gpr[imem->pg_kb.alu_reg_idx];
+	rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX];
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n",
+		  rt->pg_key.node_id,
+		  rt->pg_key.flag0,
+		  rt->pg_key.flag1,
+		  rt->pg_key.flag2,
+		  rt->pg_key.flag3,
+		  rt->pg_key.boost_idx,
+		  rt->pg_key.alu_reg,
+		  rt->pg_key.next_proto);
+
+	return 0;
+}
+
+static void ice_imem_alu0_set(struct ice_parser_rt *rt,
+			      struct ice_imem_item *imem)
+{
+	rt->alu0 = &imem->alu0;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from imem pc %d\n",
+		  imem->idx);
+}
+
+static void ice_imem_alu1_set(struct ice_parser_rt *rt,
+			      struct ice_imem_item *imem)
+{
+	rt->alu1 = &imem->alu1;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from imem pc %d\n",
+		  imem->idx);
+}
+
+static void ice_imem_alu2_set(struct ice_parser_rt *rt,
+			      struct ice_imem_item *imem)
+{
+	rt->alu2 = &imem->alu2;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from imem pc %d\n",
+		  imem->idx);
+}
+
+static void ice_imem_pgp_set(struct ice_parser_rt *rt,
+			     struct ice_imem_item *imem)
+{
+	rt->pg_prio = imem->pg_prio;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from imem pc %d\n",
+		  rt->pg_prio, imem->idx);
+}
+
+static int ice_bst_pgk_init(struct ice_parser_rt *rt,
+			    struct ice_bst_tcam_item *bst)
+{
+	memset(&rt->pg_key, 0, sizeof(rt->pg_key));
+	rt->pg_key.boost_idx = bst->hit_idx_grp;
+	rt->pg_key.next_proto = ice_pk_build(rt, &bst->np_kb);
+	if (rt->pg_key.next_proto == U32_MAX)
+		return -EINVAL;
+
+	if (bst->pg_kb.flag0_ena)
+		rt->pg_key.flag0 = ice_flag_get(rt, bst->pg_kb.flag0_idx);
+	if (bst->pg_kb.flag1_ena)
+		rt->pg_key.flag1 = ice_flag_get(rt, bst->pg_kb.flag1_idx);
+	if (bst->pg_kb.flag2_ena)
+		rt->pg_key.flag2 = ice_flag_get(rt, bst->pg_kb.flag2_idx);
+	if (bst->pg_kb.flag3_ena)
+		rt->pg_key.flag3 = ice_flag_get(rt, bst->pg_kb.flag3_idx);
+
+	rt->pg_key.alu_reg = rt->gpr[bst->pg_kb.alu_reg_idx];
+	rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX];
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n",
+		  rt->pg_key.node_id,
+		  rt->pg_key.flag0,
+		  rt->pg_key.flag1,
+		  rt->pg_key.flag2,
+		  rt->pg_key.flag3,
+		  rt->pg_key.boost_idx,
+		  rt->pg_key.alu_reg,
+		  rt->pg_key.next_proto);
+
+	return 0;
+}
+
+static void ice_bst_alu0_set(struct ice_parser_rt *rt,
+			     struct ice_bst_tcam_item *bst)
+{
+	rt->alu0 = &bst->alu0;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from boost address %d\n",
+		  bst->addr);
+}
+
+static void ice_bst_alu1_set(struct ice_parser_rt *rt,
+			     struct ice_bst_tcam_item *bst)
+{
+	rt->alu1 = &bst->alu1;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from boost address %d\n",
+		  bst->addr);
+}
+
+static void ice_bst_alu2_set(struct ice_parser_rt *rt,
+			     struct ice_bst_tcam_item *bst)
+{
+	rt->alu2 = &bst->alu2;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from boost address %d\n",
+		  bst->addr);
+}
+
+static void ice_bst_pgp_set(struct ice_parser_rt *rt,
+			    struct ice_bst_tcam_item *bst)
+{
+	rt->pg_prio = bst->pg_prio;
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from boost address %d\n",
+		  rt->pg_prio, bst->addr);
+}
+
+static struct ice_pg_cam_item *ice_rt_pg_cam_match(struct ice_parser_rt *rt)
+{
+	struct ice_parser *psr = rt->psr;
+	struct ice_pg_cam_item *item;
+
+	item = ice_pg_cam_match(psr->pg_cam_table, ICE_PG_CAM_TABLE_SIZE,
+				&rt->pg_key);
+	if (!item)
+		item = ice_pg_cam_match(psr->pg_sp_cam_table,
+					ICE_PG_SP_CAM_TABLE_SIZE, &rt->pg_key);
+	return item;
+}
+
+static
+struct ice_pg_nm_cam_item *ice_rt_pg_nm_cam_match(struct ice_parser_rt *rt)
+{
+	struct ice_parser *psr = rt->psr;
+	struct ice_pg_nm_cam_item *item;
+
+	item = ice_pg_nm_cam_match(psr->pg_nm_cam_table,
+				   ICE_PG_NM_CAM_TABLE_SIZE, &rt->pg_key);
+
+	if (!item)
+		item = ice_pg_nm_cam_match(psr->pg_nm_sp_cam_table,
+					   ICE_PG_NM_SP_CAM_TABLE_SIZE,
+					   &rt->pg_key);
+	return item;
+}
+
+static void ice_gpr_add(struct ice_parser_rt *rt, int idx, u16 val)
+{
+	rt->pu.gpr_val_upd[idx] = true;
+	rt->pu.gpr_val[idx] = val;
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for register %d value %d\n",
+		  idx, val);
+}
+
+static void ice_pg_exe(struct ice_parser_rt *rt)
+{
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action ...\n");
+
+	ice_gpr_add(rt, ICE_GPR_NP_IDX, rt->action->next_pc);
+	ice_gpr_add(rt, ICE_GPR_NN_IDX, rt->action->next_node);
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action done.\n");
+}
+
+static void ice_flg_add(struct ice_parser_rt *rt, int idx, bool val)
+{
+	rt->pu.flg_msk |= BIT(idx);
+	if (val)
+		rt->pu.flg_val |= BIT(idx);
+	else
+		rt->pu.flg_val &= ~BIT(idx);
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for flag %d value %d\n",
+		  idx, val);
+}
+
+static void ice_flg_update(struct ice_parser_rt *rt, struct ice_alu *alu)
+{
+	u32 hv_bit_sel;
+	int i;
+
+	if (!alu->dedicate_flags_ena)
+		return;
+
+	if (alu->flags_extr_imm) {
+		for (i = 0; i < alu->dst_len; i++)
+			ice_flg_add(rt, alu->dst_start + i,
+				    !!(alu->flags_start_imm & BIT(i)));
+	} else {
+		for (i = 0; i < alu->dst_len; i++) {
+			hv_bit_sel = ice_hv_bit_sel(rt,
+						    alu->flags_start_imm + i,
+						    1);
+			ice_flg_add(rt, alu->dst_start + i, !!hv_bit_sel);
+		}
+	}
+}
+
+static void ice_po_update(struct ice_parser_rt *rt, struct ice_alu *alu)
+{
+	if (alu->proto_offset_opc == ICE_PO_OFF_HDR_ADD)
+		rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] + alu->proto_offset);
+	else if (alu->proto_offset_opc == ICE_PO_OFF_HDR_SUB)
+		rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] - alu->proto_offset);
+	else if (alu->proto_offset_opc == ICE_PO_OFF_REMAIN)
+		rt->po = rt->gpr[ICE_GPR_HO_IDX];
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Update Protocol Offset = %d\n",
+		  rt->po);
+}
+
+static u16 ice_reg_bit_sel(struct ice_parser_rt *rt, int reg_idx,
+			   int start, int len)
+{
+	int offset;
+	u32 val;
+
+	offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16));
+
+	memcpy(&val, &rt->gpr[offset], sizeof(val));
+
+	val = bitrev8x4(val);
+	val >>= start % BITS_PER_TYPE(u16);
+
+	return ice_bit_rev_u16(val, len);
+}
+
+static void ice_err_add(struct ice_parser_rt *rt, int idx, bool val)
+{
+	rt->pu.err_msk |= (u16)BIT(idx);
+	if (val)
+		rt->pu.flg_val |= (u64)BIT_ULL(idx);
+	else
+		rt->pu.flg_val &= ~(u64)BIT_ULL(idx);
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for error %d value %d\n",
+		  idx, val);
+}
+
+static void ice_dst_reg_bit_set(struct ice_parser_rt *rt, struct ice_alu *alu,
+				bool val)
+{
+	u16 flg_idx;
+
+	if (alu->dedicate_flags_ena) {
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "DedicatedFlagsEnable should not be enabled in opcode %d\n",
+			  alu->opc);
+		return;
+	}
+
+	if (alu->dst_reg_id == ICE_GPR_ERR_IDX) {
+		if (alu->dst_start >= ICE_PARSER_ERR_NUM) {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid error %d\n",
+				  alu->dst_start);
+			return;
+		}
+		ice_err_add(rt, alu->dst_start, val);
+	} else if (alu->dst_reg_id >= ICE_GPR_FLG_IDX) {
+		flg_idx = (u16)(((alu->dst_reg_id - ICE_GPR_FLG_IDX) << 4) +
+				alu->dst_start);
+
+		if (flg_idx >= ICE_PARSER_FLG_NUM) {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid flag %d\n",
+				  flg_idx);
+			return;
+		}
+		ice_flg_add(rt, flg_idx, val);
+	} else {
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unexpected Dest Register Bit set, RegisterID %d Start %d\n",
+			  alu->dst_reg_id, alu->dst_start);
+	}
+}
+
+static void ice_alu_exe(struct ice_parser_rt *rt, struct ice_alu *alu)
+{
+	u16 dst, src, shift, imm;
+
+	if (alu->shift_xlate_sel) {
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "shift_xlate_sel != 0 is not expected\n");
+		return;
+	}
+
+	ice_po_update(rt, alu);
+	ice_flg_update(rt, alu);
+
+	dst = rt->gpr[alu->dst_reg_id];
+	src = ice_reg_bit_sel(rt, alu->src_reg_id,
+			      alu->src_start, alu->src_len);
+	shift = alu->shift_xlate_key;
+	imm = alu->imm;
+
+	switch (alu->opc) {
+	case ICE_ALU_PARK:
+		break;
+	case ICE_ALU_MOV_ADD:
+		dst = (src << shift) + imm;
+		ice_gpr_add(rt, alu->dst_reg_id, dst);
+		break;
+	case ICE_ALU_ADD:
+		dst += (src << shift) + imm;
+		ice_gpr_add(rt, alu->dst_reg_id, dst);
+		break;
+	case ICE_ALU_ORLT:
+		if (src < imm)
+			ice_dst_reg_bit_set(rt, alu, true);
+		ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr);
+		break;
+	case ICE_ALU_OREQ:
+		if (src == imm)
+			ice_dst_reg_bit_set(rt, alu, true);
+		ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr);
+		break;
+	case ICE_ALU_SETEQ:
+		ice_dst_reg_bit_set(rt, alu, src == imm);
+		ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr);
+		break;
+	case ICE_ALU_MOV_XOR:
+		dst = (src << shift) ^ imm;
+		ice_gpr_add(rt, alu->dst_reg_id, dst);
+		break;
+	default:
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported ALU instruction %d\n",
+			  alu->opc);
+		break;
+	}
+}
+
+static void ice_alu0_exe(struct ice_parser_rt *rt)
+{
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 ...\n");
+	ice_alu_exe(rt, rt->alu0);
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 done.\n");
+}
+
+static void ice_alu1_exe(struct ice_parser_rt *rt)
+{
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 ...\n");
+	ice_alu_exe(rt, rt->alu1);
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 done.\n");
+}
+
+static void ice_alu2_exe(struct ice_parser_rt *rt)
+{
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 ...\n");
+	ice_alu_exe(rt, rt->alu2);
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 done.\n");
+}
+
+static void ice_pu_exe(struct ice_parser_rt *rt)
+{
+	struct ice_gpr_pu *pu = &rt->pu;
+	unsigned int i;
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers ...\n");
+
+	for (i = 0; i < ICE_PARSER_GPR_NUM; i++) {
+		if (pu->gpr_val_upd[i])
+			ice_rt_gpr_set(rt, i, pu->gpr_val[i]);
+	}
+
+	for (i = 0; i < ICE_PARSER_FLG_NUM; i++) {
+		if (pu->flg_msk & BIT(i))
+			ice_rt_flag_set(rt, i, pu->flg_val & BIT(i));
+	}
+
+	for (i = 0; i < ICE_PARSER_ERR_NUM; i++) {
+		if (pu->err_msk & BIT(i))
+			ice_rt_err_set(rt, i, pu->err_val & BIT(i));
+	}
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers done.\n");
+}
+
+static void ice_alu_pg_exe(struct ice_parser_rt *rt)
+{
+	memset(&rt->pu, 0, sizeof(rt->pu));
+
+	switch (rt->pg_prio) {
+	case (ICE_PG_P0):
+		ice_pg_exe(rt);
+		ice_alu0_exe(rt);
+		ice_alu1_exe(rt);
+		ice_alu2_exe(rt);
+		break;
+	case (ICE_PG_P1):
+		ice_alu0_exe(rt);
+		ice_pg_exe(rt);
+		ice_alu1_exe(rt);
+		ice_alu2_exe(rt);
+		break;
+	case (ICE_PG_P2):
+		ice_alu0_exe(rt);
+		ice_alu1_exe(rt);
+		ice_pg_exe(rt);
+		ice_alu2_exe(rt);
+		break;
+	case (ICE_PG_P3):
+		ice_alu0_exe(rt);
+		ice_alu1_exe(rt);
+		ice_alu2_exe(rt);
+		ice_pg_exe(rt);
+		break;
+	}
+
+	ice_pu_exe(rt);
+
+	if (rt->action->ho_inc == 0)
+		return;
+
+	if (rt->action->ho_polarity)
+		ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] + rt->action->ho_inc);
+	else
+		ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] - rt->action->ho_inc);
+}
+
+static void ice_proto_off_update(struct ice_parser_rt *rt)
+{
+	struct ice_parser *psr = rt->psr;
+
+	if (rt->action->is_pg) {
+		struct ice_proto_grp_item *proto_grp =
+			&psr->proto_grp_table[rt->action->proto_id];
+		u16 po;
+		int i;
+
+		for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) {
+			struct ice_proto_off *entry = &proto_grp->po[i];
+
+			if (entry->proto_id == U8_MAX)
+				break;
+
+			if (!entry->polarity)
+				po = rt->po + entry->offset;
+			else
+				po = rt->po - entry->offset;
+
+			rt->protocols[entry->proto_id] = true;
+			rt->offsets[entry->proto_id] = po;
+
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n",
+				  entry->proto_id, po);
+		}
+	} else {
+		rt->protocols[rt->action->proto_id] = true;
+		rt->offsets[rt->action->proto_id] = rt->po;
+
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n",
+			  rt->action->proto_id, rt->po);
+	}
+}
+
+static void ice_marker_set(struct ice_parser_rt *rt, int idx)
+{
+	unsigned int byte = idx / BITS_PER_BYTE;
+	unsigned int bit = idx % BITS_PER_BYTE;
+
+	rt->markers[byte] |= (u8)BIT(bit);
+}
+
+static void ice_marker_update(struct ice_parser_rt *rt)
+{
+	struct ice_parser *psr = rt->psr;
+
+	if (rt->action->is_mg) {
+		struct ice_mk_grp_item *mk_grp =
+			&psr->mk_grp_table[rt->action->marker_id];
+		int i;
+
+		for (i = 0; i < ICE_MARKER_ID_NUM; i++) {
+			u8 marker = mk_grp->markers[i];
+
+			if (marker == ICE_MARKER_MAX_SIZE)
+				break;
+
+			ice_marker_set(rt, marker);
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n",
+				  marker);
+		}
+	} else {
+		if (rt->action->marker_id != ICE_MARKER_MAX_SIZE)
+			ice_marker_set(rt, rt->action->marker_id);
+
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n",
+			  rt->action->marker_id);
+	}
+}
+
+static u16 ice_ptype_resolve(struct ice_parser_rt *rt)
+{
+	struct ice_ptype_mk_tcam_item *item;
+	struct ice_parser *psr = rt->psr;
+
+	item = ice_ptype_mk_tcam_match(psr->ptype_mk_tcam_table,
+				       rt->markers, ICE_MARKER_ID_SIZE);
+	if (item)
+		return item->ptype;
+
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Could not resolve PTYPE\n");
+	return U16_MAX;
+}
+
+static void ice_proto_off_resolve(struct ice_parser_rt *rt,
+				  struct ice_parser_result *rslt)
+{
+	int i;
+
+	for (i = 0; i < ICE_PO_PAIR_SIZE - 1; i++) {
+		if (rt->protocols[i]) {
+			rslt->po[rslt->po_num].proto_id = (u8)i;
+			rslt->po[rslt->po_num].offset = rt->offsets[i];
+			rslt->po_num++;
+		}
+	}
+}
+
+static void ice_result_resolve(struct ice_parser_rt *rt,
+			       struct ice_parser_result *rslt)
+{
+	struct ice_parser *psr = rt->psr;
+
+	memset(rslt, 0, sizeof(*rslt));
+
+	memcpy(&rslt->flags_psr, &rt->gpr[ICE_GPR_FLG_IDX],
+	       ICE_PARSER_FLAG_PSR_SIZE);
+	rslt->flags_pkt = ice_flg_redirect(psr->flg_rd_table, rslt->flags_psr);
+	rslt->flags_sw = ice_xlt_kb_flag_get(psr->xlt_kb_sw, rslt->flags_pkt);
+	rslt->flags_fd = ice_xlt_kb_flag_get(psr->xlt_kb_fd, rslt->flags_pkt);
+	rslt->flags_rss = ice_xlt_kb_flag_get(psr->xlt_kb_rss, rslt->flags_pkt);
+
+	ice_proto_off_resolve(rt, rslt);
+	rslt->ptype = ice_ptype_resolve(rt);
+}
+
+/**
+ * ice_parser_rt_execute - parser execution routine
+ * @rt: pointer to the parser runtime
+ * @rslt: input/output parameter to save parser result
+ *
+ * Return: 0 on success or errno.
+ */
+int ice_parser_rt_execute(struct ice_parser_rt *rt,
+			  struct ice_parser_result *rslt)
+{
+	struct ice_pg_nm_cam_item *pg_nm_cam;
+	struct ice_parser *psr = rt->psr;
+	struct ice_pg_cam_item *pg_cam;
+	int status = 0;
+	u16 node;
+	u16 pc;
+
+	node = rt->gpr[ICE_GPR_NN_IDX];
+	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Start with Node: %u\n", node);
+
+	while (true) {
+		struct ice_bst_tcam_item *bst;
+		struct ice_imem_item *imem;
+
+		pc = rt->gpr[ICE_GPR_NP_IDX];
+		imem = &psr->imem_table[pc];
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load imem at pc: %u\n",
+			  pc);
+
+		ice_bst_key_init(rt, imem);
+		bst = ice_bst_tcam_match(psr->bst_tcam_table, rt->bst_key);
+		if (!bst) {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "No Boost TCAM Match\n");
+			status = ice_imem_pgk_init(rt, imem);
+			if (status)
+				break;
+			ice_imem_alu0_set(rt, imem);
+			ice_imem_alu1_set(rt, imem);
+			ice_imem_alu2_set(rt, imem);
+			ice_imem_pgp_set(rt, imem);
+		} else {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Boost TCAM Match address: %u\n",
+				  bst->addr);
+			if (imem->b_m.pg) {
+				status = ice_bst_pgk_init(rt, bst);
+				if (status)
+					break;
+				ice_bst_pgp_set(rt, bst);
+			} else {
+				status = ice_imem_pgk_init(rt, imem);
+				if (status)
+					break;
+				ice_imem_pgp_set(rt, imem);
+			}
+
+			if (imem->b_m.alu0)
+				ice_bst_alu0_set(rt, bst);
+			else
+				ice_imem_alu0_set(rt, imem);
+
+			if (imem->b_m.alu1)
+				ice_bst_alu1_set(rt, bst);
+			else
+				ice_imem_alu1_set(rt, imem);
+
+			if (imem->b_m.alu2)
+				ice_bst_alu2_set(rt, bst);
+			else
+				ice_imem_alu2_set(rt, imem);
+		}
+
+		rt->action = NULL;
+		pg_cam = ice_rt_pg_cam_match(rt);
+		if (!pg_cam) {
+			pg_nm_cam = ice_rt_pg_nm_cam_match(rt);
+			if (pg_nm_cam) {
+				ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph Nomatch CAM Address %u\n",
+					  pg_nm_cam->idx);
+				rt->action = &pg_nm_cam->action;
+			}
+		} else {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph CAM Address %u\n",
+				  pg_cam->idx);
+			rt->action = &pg_cam->action;
+		}
+
+		if (!rt->action) {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Failed to match ParseGraph CAM, stop parsing.\n");
+			status = -EINVAL;
+			break;
+		}
+
+		ice_alu_pg_exe(rt);
+		ice_marker_update(rt);
+		ice_proto_off_update(rt);
+
+		ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Go to node %u\n",
+			  rt->action->next_node);
+
+		if (rt->action->is_last_round) {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Last Round in ParseGraph Action, stop parsing.\n");
+			break;
+		}
+
+		if (rt->gpr[ICE_GPR_HO_IDX] >= rt->pkt_len) {
+			ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Header Offset (%u) is larger than packet len (%u), stop parsing\n",
+				  rt->gpr[ICE_GPR_HO_IDX], rt->pkt_len);
+			break;
+		}
+	}
+
+	ice_result_resolve(rt, rslt);
+
+	return status;
+}
-- 
cgit v1.3-3-g829e


From b2687653fe690569d48eb60343745fe436f7d532 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:02 -0600
Subject: ice: support turning on/off the parser's double vlan mode

Add API ice_parser_dvm_set() to support turning on/off the parser's double
vlan mode.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Co-developed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_parser.c | 78 +++++++++++++++++++++++++++--
 drivers/net/ethernet/intel/ice/ice_parser.h | 18 +++++++
 2 files changed, 93 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index e40dc31a5601..f032b907ccd2 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -597,6 +597,32 @@ static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw)
 				       ice_metainit_parse_item, false);
 }
 
+/**
+ * ice_bst_tcam_search - find a TCAM item with specific type
+ * @tcam_table: the TCAM table
+ * @lbl_table: the lbl table to search
+ * @type: the type we need to match against
+ * @start: start searching from this index
+ *
+ * Return: a pointer to the matching BOOST TCAM item or NULL.
+ */
+struct ice_bst_tcam_item *
+ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table,
+		    struct ice_lbl_item *lbl_table,
+		    enum ice_lbl_type type, u16 *start)
+{
+	u16 i = *start;
+
+	for (; i < ICE_BST_TCAM_TABLE_SIZE; i++) {
+		if (lbl_table[i].type == type) {
+			*start = i;
+			return &tcam_table[lbl_table[i].idx];
+		}
+	}
+
+	return NULL;
+}
+
 /*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL,
  *    ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM
  *    sections ***/
@@ -1151,6 +1177,7 @@ static void ice_lbl_dump(struct ice_hw *hw, struct ice_lbl_item *item)
 	struct device *dev = ice_hw_to_dev(hw);
 
 	dev_info(dev, "index = %u\n", item->idx);
+	dev_info(dev, "type = %u\n", item->type);
 	dev_info(dev, "label = %s\n", item->label);
 }
 
@@ -1340,12 +1367,21 @@ static struct ice_bst_tcam_item *ice_bst_tcam_table_get(struct ice_hw *hw)
 }
 
 static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item,
-			       void *data, int size)
+			       void *data, int __maybe_unused size)
 {
-	memcpy(item, data, size);
+	struct ice_lbl_item *lbl_item = item;
+	struct ice_lbl_item *lbl_data = data;
+
+	lbl_item->idx = lbl_data->idx;
+	memcpy(lbl_item->label, lbl_data->label, sizeof(lbl_item->label));
+
+	if (strstarts(lbl_item->label, ICE_LBL_BST_DVM))
+		lbl_item->type = ICE_LBL_BST_TYPE_DVM;
+	else if (strstarts(lbl_item->label, ICE_LBL_BST_SVM))
+		lbl_item->type = ICE_LBL_BST_TYPE_SVM;
 
 	if (hw->debug_mask & ICE_DBG_PARSER)
-		ice_lbl_dump(hw, (struct ice_lbl_item *)item);
+		ice_lbl_dump(hw, lbl_item);
 }
 
 /**
@@ -2132,3 +2168,39 @@ void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt)
 	dev_info(dev, "flags_fd = 0x%04x\n", rslt->flags_fd);
 	dev_info(dev, "flags_rss = 0x%04x\n", rslt->flags_rss);
 }
+
+#define ICE_BT_VLD_KEY	0xFF
+#define ICE_BT_INV_KEY	0xFE
+
+static void ice_bst_dvm_set(struct ice_parser *psr, enum ice_lbl_type type,
+			    bool on)
+{
+	u16 i = 0;
+
+	while (true) {
+		struct ice_bst_tcam_item *item;
+		u8 key;
+
+		item = ice_bst_tcam_search(psr->bst_tcam_table,
+					   psr->bst_lbl_table,
+					   type, &i);
+		if (!item)
+			break;
+
+		key = on ? ICE_BT_VLD_KEY : ICE_BT_INV_KEY;
+		item->key[ICE_BT_VM_OFF] = key;
+		item->key_inv[ICE_BT_VM_OFF] = key;
+		i++;
+	}
+}
+
+/**
+ * ice_parser_dvm_set - configure double vlan mode for parser
+ * @psr: pointer to a parser instance
+ * @on: true to turn on; false to turn off
+ */
+void ice_parser_dvm_set(struct ice_parser *psr, bool on)
+{
+	ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_DVM, on);
+	ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_SVM, !on);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index ef08ccbe4874..92319c60b388 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -274,13 +274,29 @@ struct ice_bst_tcam_item {
 };
 
 #define ICE_LBL_LEN			64
+#define ICE_LBL_BST_DVM			"BOOST_MAC_VLAN_DVM"
+#define ICE_LBL_BST_SVM			"BOOST_MAC_VLAN_SVM"
+
+enum ice_lbl_type {
+	ICE_LBL_BST_TYPE_UNKNOWN,
+	ICE_LBL_BST_TYPE_DVM,
+	ICE_LBL_BST_TYPE_SVM,
+};
+
 struct ice_lbl_item {
 	u16 idx;
 	char label[ICE_LBL_LEN];
+
+	/* must be at the end, not part of the DDP section */
+	enum ice_lbl_type type;
 };
 
 struct ice_bst_tcam_item *
 ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat);
+struct ice_bst_tcam_item *
+ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table,
+		    struct ice_lbl_item *lbl_table,
+		    enum ice_lbl_type type, u16 *start);
 
 /*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/
 #define ICE_PTYPE_MK_TCAM_TABLE_SIZE	1024
@@ -429,6 +445,7 @@ struct ice_parser_proto_off {
 
 #define ICE_PARSER_PROTO_OFF_PAIR_SIZE	16
 #define ICE_PARSER_FLAG_PSR_SIZE	8
+#define ICE_BT_VM_OFF			0
 
 struct ice_parser_result {
 	u16 ptype;	/* 16 bits hardware PTYPE */
@@ -477,6 +494,7 @@ struct ice_parser {
 
 struct ice_parser *ice_parser_create(struct ice_hw *hw);
 void ice_parser_destroy(struct ice_parser *psr);
+void ice_parser_dvm_set(struct ice_parser *psr, bool on);
 int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf,
 		   int pkt_len, struct ice_parser_result *rslt);
 void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt);
-- 
cgit v1.3-3-g829e


From 80a480075911ec333a692e3108899a565b5f4bdc Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:03 -0600
Subject: ice: add UDP tunnels support to the parser

Add support for the vxlan, geneve, ecpri UDP tunnels through the
following APIs:
- ice_parser_vxlan_tunnel_set()
- ice_parser_geneve_tunnel_set()
- ice_parser_ecpri_tunnel_set()

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_parser.c | 98 +++++++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_parser.h | 13 ++++
 2 files changed, 111 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index f032b907ccd2..ee89208bf21d 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -1379,6 +1379,12 @@ static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item,
 		lbl_item->type = ICE_LBL_BST_TYPE_DVM;
 	else if (strstarts(lbl_item->label, ICE_LBL_BST_SVM))
 		lbl_item->type = ICE_LBL_BST_TYPE_SVM;
+	else if (strstarts(lbl_item->label, ICE_LBL_TNL_VXLAN))
+		lbl_item->type = ICE_LBL_BST_TYPE_VXLAN;
+	else if (strstarts(lbl_item->label, ICE_LBL_TNL_GENEVE))
+		lbl_item->type = ICE_LBL_BST_TYPE_GENEVE;
+	else if (strstarts(lbl_item->label, ICE_LBL_TNL_UDP_ECPRI))
+		lbl_item->type = ICE_LBL_BST_TYPE_UDP_ECPRI;
 
 	if (hw->debug_mask & ICE_DBG_PARSER)
 		ice_lbl_dump(hw, lbl_item);
@@ -2204,3 +2210,95 @@ void ice_parser_dvm_set(struct ice_parser *psr, bool on)
 	ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_DVM, on);
 	ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_SVM, !on);
 }
+
+static int ice_tunnel_port_set(struct ice_parser *psr, enum ice_lbl_type type,
+			       u16 udp_port, bool on)
+{
+	u8 *buf = (u8 *)&udp_port;
+	u16 i = 0;
+
+	while (true) {
+		struct ice_bst_tcam_item *item;
+
+		item = ice_bst_tcam_search(psr->bst_tcam_table,
+					   psr->bst_lbl_table,
+					   type, &i);
+		if (!item)
+			break;
+
+		/* found empty slot to add */
+		if (on && item->key[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY &&
+		    item->key_inv[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY) {
+			item->key_inv[ICE_BT_TUN_PORT_OFF_L] =
+						buf[ICE_UDP_PORT_OFF_L];
+			item->key_inv[ICE_BT_TUN_PORT_OFF_H] =
+						buf[ICE_UDP_PORT_OFF_H];
+
+			item->key[ICE_BT_TUN_PORT_OFF_L] =
+				ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_L];
+			item->key[ICE_BT_TUN_PORT_OFF_H] =
+				ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_H];
+
+			return 0;
+		/* found a matched slot to delete */
+		} else if (!on &&
+			   (item->key_inv[ICE_BT_TUN_PORT_OFF_L] ==
+			    buf[ICE_UDP_PORT_OFF_L] ||
+			    item->key_inv[ICE_BT_TUN_PORT_OFF_H] ==
+			    buf[ICE_UDP_PORT_OFF_H])) {
+			item->key_inv[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY;
+			item->key_inv[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY;
+
+			item->key[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY;
+			item->key[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY;
+
+			return 0;
+		}
+		i++;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * ice_parser_vxlan_tunnel_set - configure vxlan tunnel for parser
+ * @psr: pointer to a parser instance
+ * @udp_port: vxlan tunnel port in UDP header
+ * @on: true to turn on; false to turn off
+ *
+ * Return: 0 on success or errno on failure.
+ */
+int ice_parser_vxlan_tunnel_set(struct ice_parser *psr,
+				u16 udp_port, bool on)
+{
+	return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_VXLAN, udp_port, on);
+}
+
+/**
+ * ice_parser_geneve_tunnel_set - configure geneve tunnel for parser
+ * @psr: pointer to a parser instance
+ * @udp_port: geneve tunnel port in UDP header
+ * @on: true to turn on; false to turn off
+ *
+ * Return: 0 on success or errno on failure.
+ */
+int ice_parser_geneve_tunnel_set(struct ice_parser *psr,
+				 u16 udp_port, bool on)
+{
+	return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_GENEVE, udp_port, on);
+}
+
+/**
+ * ice_parser_ecpri_tunnel_set - configure ecpri tunnel for parser
+ * @psr: pointer to a parser instance
+ * @udp_port: ecpri tunnel port in UDP header
+ * @on: true to turn on; false to turn off
+ *
+ * Return: 0 on success or errno on failure.
+ */
+int ice_parser_ecpri_tunnel_set(struct ice_parser *psr,
+				u16 udp_port, bool on)
+{
+	return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_UDP_ECPRI,
+				   udp_port, on);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index 92319c60b388..f9500ddf1567 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -276,11 +276,17 @@ struct ice_bst_tcam_item {
 #define ICE_LBL_LEN			64
 #define ICE_LBL_BST_DVM			"BOOST_MAC_VLAN_DVM"
 #define ICE_LBL_BST_SVM			"BOOST_MAC_VLAN_SVM"
+#define ICE_LBL_TNL_VXLAN		"TNL_VXLAN"
+#define ICE_LBL_TNL_GENEVE		"TNL_GENEVE"
+#define ICE_LBL_TNL_UDP_ECPRI		"TNL_UDP_ECPRI"
 
 enum ice_lbl_type {
 	ICE_LBL_BST_TYPE_UNKNOWN,
 	ICE_LBL_BST_TYPE_DVM,
 	ICE_LBL_BST_TYPE_SVM,
+	ICE_LBL_BST_TYPE_VXLAN,
+	ICE_LBL_BST_TYPE_GENEVE,
+	ICE_LBL_BST_TYPE_UDP_ECPRI,
 };
 
 struct ice_lbl_item {
@@ -445,7 +451,11 @@ struct ice_parser_proto_off {
 
 #define ICE_PARSER_PROTO_OFF_PAIR_SIZE	16
 #define ICE_PARSER_FLAG_PSR_SIZE	8
+#define ICE_BT_TUN_PORT_OFF_H		16
+#define ICE_BT_TUN_PORT_OFF_L		15
 #define ICE_BT_VM_OFF			0
+#define ICE_UDP_PORT_OFF_H		1
+#define ICE_UDP_PORT_OFF_L		0
 
 struct ice_parser_result {
 	u16 ptype;	/* 16 bits hardware PTYPE */
@@ -495,6 +505,9 @@ struct ice_parser {
 struct ice_parser *ice_parser_create(struct ice_hw *hw);
 void ice_parser_destroy(struct ice_parser *psr);
 void ice_parser_dvm_set(struct ice_parser *psr, bool on);
+int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on);
+int ice_parser_geneve_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on);
+int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on);
 int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf,
 		   int pkt_len, struct ice_parser_result *rslt);
 void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt);
-- 
cgit v1.3-3-g829e


From e312b3a1e2092f612914dbc4fa5d96b4d8ff94ef Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:04 -0600
Subject: ice: add API for parser profile initialization

Add API ice_parser_profile_init() to init a parser profile based on
a parser result and a mask buffer. The ice_parser_profile struct is used
by the low level FXP engine to create HW profile/field vectors.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_parser.c | 130 +++++++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_parser.h |  26 ++++++
 2 files changed, 154 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c
index ee89208bf21d..664beb64f557 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser.c
@@ -2243,9 +2243,9 @@ static int ice_tunnel_port_set(struct ice_parser *psr, enum ice_lbl_type type,
 		/* found a matched slot to delete */
 		} else if (!on &&
 			   (item->key_inv[ICE_BT_TUN_PORT_OFF_L] ==
-			    buf[ICE_UDP_PORT_OFF_L] ||
+				buf[ICE_UDP_PORT_OFF_L] ||
 			    item->key_inv[ICE_BT_TUN_PORT_OFF_H] ==
-			    buf[ICE_UDP_PORT_OFF_H])) {
+				buf[ICE_UDP_PORT_OFF_H])) {
 			item->key_inv[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY;
 			item->key_inv[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY;
 
@@ -2302,3 +2302,129 @@ int ice_parser_ecpri_tunnel_set(struct ice_parser *psr,
 	return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_UDP_ECPRI,
 				   udp_port, on);
 }
+
+/**
+ * ice_nearest_proto_id - find nearest protocol ID
+ * @rslt: pointer to a parser result instance
+ * @offset: a min value for the protocol offset
+ * @proto_id: the protocol ID (output)
+ * @proto_off: the protocol offset (output)
+ *
+ * From the protocols in @rslt, find the nearest protocol that has offset
+ * larger than @offset.
+ *
+ * Return: if true, the protocol's ID and offset
+ */
+static bool ice_nearest_proto_id(struct ice_parser_result *rslt, u16 offset,
+				 u8 *proto_id, u16 *proto_off)
+{
+	u16 dist = U16_MAX;
+	u8 proto = 0;
+	int i;
+
+	for (i = 0; i < rslt->po_num; i++) {
+		if (offset < rslt->po[i].offset)
+			continue;
+		if (offset - rslt->po[i].offset < dist) {
+			proto = rslt->po[i].proto_id;
+			dist = offset - rslt->po[i].offset;
+		}
+	}
+
+	if (dist % 2)
+		return false;
+
+	*proto_id = proto;
+	*proto_off = dist;
+
+	return true;
+}
+
+/* default flag mask to cover GTP_EH_PDU, GTP_EH_PDU_LINK and TUN2
+ * In future, the flag masks should learn from DDP
+ */
+#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW	0x4002
+#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL	0x0000
+#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD	0x6080
+#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS	0x6010
+
+/**
+ * ice_parser_profile_init - initialize a FXP profile based on parser result
+ * @rslt: a instance of a parser result
+ * @pkt_buf: packet data buffer
+ * @msk_buf: packet mask buffer
+ * @buf_len: packet length
+ * @blk: FXP pipeline stage
+ * @prof: input/output parameter to save the profile
+ *
+ * Return: 0 on success or errno on failure.
+ */
+int ice_parser_profile_init(struct ice_parser_result *rslt,
+			    const u8 *pkt_buf, const u8 *msk_buf,
+			    int buf_len, enum ice_block blk,
+			    struct ice_parser_profile *prof)
+{
+	u8 proto_id = U8_MAX;
+	u16 proto_off = 0;
+	u16 off;
+
+	memset(prof, 0, sizeof(*prof));
+	set_bit(rslt->ptype, prof->ptypes);
+	if (blk == ICE_BLK_SW) {
+		prof->flags	= rslt->flags_sw;
+		prof->flags_msk	= ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW;
+	} else if (blk == ICE_BLK_ACL) {
+		prof->flags	= rslt->flags_acl;
+		prof->flags_msk	= ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL;
+	} else if (blk == ICE_BLK_FD) {
+		prof->flags	= rslt->flags_fd;
+		prof->flags_msk	= ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD;
+	} else if (blk == ICE_BLK_RSS) {
+		prof->flags	= rslt->flags_rss;
+		prof->flags_msk	= ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS;
+	} else {
+		return -EINVAL;
+	}
+
+	for (off = 0; off < buf_len - 1; off++) {
+		if (msk_buf[off] == 0 && msk_buf[off + 1] == 0)
+			continue;
+		if (!ice_nearest_proto_id(rslt, off, &proto_id, &proto_off))
+			continue;
+		if (prof->fv_num >= ICE_PARSER_FV_MAX)
+			return -EINVAL;
+
+		prof->fv[prof->fv_num].proto_id	= proto_id;
+		prof->fv[prof->fv_num].offset	= proto_off;
+		prof->fv[prof->fv_num].spec	= *(const u16 *)&pkt_buf[off];
+		prof->fv[prof->fv_num].msk	= *(const u16 *)&msk_buf[off];
+		prof->fv_num++;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_parser_profile_dump - dump an FXP profile info
+ * @hw: pointer to the hardware structure
+ * @prof: profile info to dump
+ */
+void ice_parser_profile_dump(struct ice_hw *hw,
+			     struct ice_parser_profile *prof)
+{
+	struct device *dev = ice_hw_to_dev(hw);
+	u16 i;
+
+	dev_info(dev, "ptypes:\n");
+	for (i = 0; i < ICE_FLOW_PTYPE_MAX; i++)
+		if (test_bit(i, prof->ptypes))
+			dev_info(dev, "\t%u\n", i);
+
+	for (i = 0; i < prof->fv_num; i++)
+		dev_info(dev, "proto = %u, offset = %2u, spec = 0x%04x, mask = 0x%04x\n",
+			 prof->fv[i].proto_id, prof->fv[i].offset,
+			 prof->fv[i].spec, prof->fv[i].msk);
+
+	dev_info(dev, "flags = 0x%04x\n", prof->flags);
+	dev_info(dev, "flags_msk = 0x%04x\n", prof->flags_msk);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h
index f9500ddf1567..6509d807627c 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser.h
+++ b/drivers/net/ethernet/intel/ice/ice_parser.h
@@ -451,6 +451,8 @@ struct ice_parser_proto_off {
 
 #define ICE_PARSER_PROTO_OFF_PAIR_SIZE	16
 #define ICE_PARSER_FLAG_PSR_SIZE	8
+#define ICE_PARSER_FV_SIZE		48
+#define ICE_PARSER_FV_MAX		24
 #define ICE_BT_TUN_PORT_OFF_H		16
 #define ICE_BT_TUN_PORT_OFF_L		15
 #define ICE_BT_VM_OFF			0
@@ -511,4 +513,28 @@ int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on);
 int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf,
 		   int pkt_len, struct ice_parser_result *rslt);
 void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt);
+
+struct ice_parser_fv {
+	u8 proto_id;	/* hardware protocol ID */
+	u16 offset;	/* offset from the start of the protocol header */
+	u16 spec;	/* pattern to match */
+	u16 msk;	/* pattern mask */
+};
+
+struct ice_parser_profile {
+	/* array of field vectors */
+	struct ice_parser_fv fv[ICE_PARSER_FV_SIZE];
+	int fv_num;		/* # of field vectors must <= 48 */
+	u16 flags;		/* key builder flags */
+	u16 flags_msk;		/* key builder flag mask */
+
+	DECLARE_BITMAP(ptypes, ICE_FLOW_PTYPE_MAX); /* PTYPE bitmap */
+};
+
+int ice_parser_profile_init(struct ice_parser_result *rslt,
+			    const u8 *pkt_buf, const u8 *msk_buf,
+			    int buf_len, enum ice_block blk,
+			    struct ice_parser_profile *prof);
+void ice_parser_profile_dump(struct ice_hw *hw,
+			     struct ice_parser_profile *prof);
 #endif /* _ICE_PARSER_H_ */
-- 
cgit v1.3-3-g829e


From fb4dae4ca315fe48f1a8a452172f29196b2a7f3d Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:05 -0600
Subject: virtchnl: support raw packet in protocol header

The patch extends existing virtchnl_proto_hdrs structure to allow VF
to pass a pair of buffers as packet data and mask that describe
a match pattern of a filter rule. Then the kernel PF driver is requested
to parse the pair of buffer and figure out low level hardware metadata
(ptype, profile, field vector.. ) to program the expected FDIR or RSS
rules.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/linux/avf/virtchnl.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 8e177b67e82f..4f78a65e33dc 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -1121,6 +1121,7 @@ enum virtchnl_vfr_states {
 };
 
 #define VIRTCHNL_MAX_NUM_PROTO_HDRS	32
+#define VIRTCHNL_MAX_SIZE_RAW_PACKET	1024
 #define PROTO_HDR_SHIFT			5
 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT)
 #define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1)
@@ -1266,13 +1267,22 @@ struct virtchnl_proto_hdrs {
 	u8 pad[3];
 	/**
 	 * specify where protocol header start from.
+	 * must be 0 when sending a raw packet request.
 	 * 0 - from the outer layer
 	 * 1 - from the first inner layer
 	 * 2 - from the second inner layer
 	 * ....
 	 **/
 	int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */
-	struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS];
+	union {
+		struct virtchnl_proto_hdr
+			proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS];
+		struct {
+			u16 pkt_len;
+			u8 spec[VIRTCHNL_MAX_SIZE_RAW_PACKET];
+			u8 mask[VIRTCHNL_MAX_SIZE_RAW_PACKET];
+		} raw;
+	};
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs);
-- 
cgit v1.3-3-g829e


From f217c187ea2eb31500fdea34f595f56433a164f1 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:06 -0600
Subject: ice: add method to disable FDIR SWAP option

The SWAP Flag in the FDIR Programming Descriptor doesn't work properly,
it is always set and cannot be unset (hardware bug). Thus, add a method
to effectively disable the FDIR SWAP option by setting the FDSWAP instead
of FDINSET registers.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c | 51 +++++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_flex_pipe.h |  4 +-
 drivers/net/ethernet/intel/ice/ice_flow.c      |  2 +-
 3 files changed, 53 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 20d5db88c99f..7f182a6f72aa 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -2981,6 +2981,50 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype,
 }
 
 /**
+ * ice_disable_fd_swap - set register appropriately to disable FD SWAP
+ * @hw: pointer to the HW struct
+ * @prof_id: profile ID
+ */
+static void
+ice_disable_fd_swap(struct ice_hw *hw, u8 prof_id)
+{
+	u16 swap_val, fvw_num;
+	unsigned int i;
+
+	swap_val = ICE_SWAP_VALID;
+	fvw_num = hw->blk[ICE_BLK_FD].es.fvw / ICE_FDIR_REG_SET_SIZE;
+
+	/* Since the SWAP Flag in the Programming Desc doesn't work,
+	 * here add method to disable the SWAP Option via setting
+	 * certain SWAP and INSET register sets.
+	 */
+	for (i = 0; i < fvw_num ; i++) {
+		u32 raw_swap, raw_in;
+		unsigned int j;
+
+		raw_swap = 0;
+		raw_in = 0;
+
+		for (j = 0; j < ICE_FDIR_REG_SET_SIZE; j++) {
+			raw_swap |= (swap_val++) << (j * BITS_PER_BYTE);
+			raw_in |= ICE_INSET_DFLT << (j * BITS_PER_BYTE);
+		}
+
+		/* write the FDIR swap register set */
+		wr32(hw, GLQF_FDSWAP(prof_id, i), raw_swap);
+
+		ice_debug(hw, ICE_DBG_INIT, "swap wr(%d, %d): 0x%x = 0x%08x\n",
+			  prof_id, i, GLQF_FDSWAP(prof_id, i), raw_swap);
+
+		/* write the FDIR inset register set */
+		wr32(hw, GLQF_FDINSET(prof_id, i), raw_in);
+
+		ice_debug(hw, ICE_DBG_INIT, "inset wr(%d, %d): 0x%x = 0x%08x\n",
+			  prof_id, i, GLQF_FDINSET(prof_id, i), raw_in);
+	}
+}
+
+/*
  * ice_add_prof - add profile
  * @hw: pointer to the HW struct
  * @blk: hardware block
@@ -2991,6 +3035,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype,
  * @es: extraction sequence (length of array is determined by the block)
  * @masks: mask for extraction sequence
  * @symm: symmetric setting for RSS profiles
+ * @fd_swap: enable/disable FDIR paired src/dst fields swap option
  *
  * This function registers a profile, which matches a set of PTYPES with a
  * particular extraction sequence. While the hardware profile is allocated
@@ -3000,7 +3045,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype,
 int
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	     const struct ice_ptype_attributes *attr, u16 attr_cnt,
-	     struct ice_fv_word *es, u16 *masks, bool symm)
+	     struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap)
 {
 	u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE);
 	DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT);
@@ -3020,7 +3065,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 		status = ice_alloc_prof_id(hw, blk, &prof_id);
 		if (status)
 			goto err_ice_add_prof;
-		if (blk == ICE_BLK_FD) {
+		if (blk == ICE_BLK_FD && fd_swap) {
 			/* For Flow Director block, the extraction sequence may
 			 * need to be altered in the case where there are paired
 			 * fields that have no match. This is necessary because
@@ -3031,6 +3076,8 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 			status = ice_update_fd_swap(hw, prof_id, es);
 			if (status)
 				goto err_ice_add_prof;
+		} else if (blk == ICE_BLK_FD) {
+			ice_disable_fd_swap(hw, prof_id);
 		}
 		status = ice_update_prof_masking(hw, blk, prof_id, masks);
 		if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index b39d7cdc381f..7c66652dadd6 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -6,6 +6,8 @@
 
 #include "ice_type.h"
 
+#define ICE_FDIR_REG_SET_SIZE	4
+
 int
 ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access);
 void ice_release_change_lock(struct ice_hw *hw);
@@ -42,7 +44,7 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype);
 int
 ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[],
 	     const struct ice_ptype_attributes *attr, u16 attr_cnt,
-	     struct ice_fv_word *es, u16 *masks, bool symm);
+	     struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap);
 struct ice_prof_map *
 ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index fc2b58f56279..79106503194b 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -1400,7 +1400,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk,
 	/* Add a HW profile for this flow profile */
 	status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes,
 			      params->attr, params->attr_cnt, params->es,
-			      params->mask, symm);
+			      params->mask, symm, true);
 	if (status) {
 		ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n");
 		goto out;
-- 
cgit v1.3-3-g829e


From 99f419df8a5c5e1a58822203989f77712d01d410 Mon Sep 17 00:00:00 2001
From: Junfeng Guo <junfeng.guo@intel.com>
Date: Thu, 25 Jul 2024 16:08:07 -0600
Subject: ice: enable FDIR filters from raw binary patterns for VFs

Enable VFs to create FDIR filters from raw binary patterns.
The corresponding processes for raw flow are added in the
Parse / Create / Destroy stages.

Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Co-developed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_flex_pipe.c     |  48 +++
 drivers/net/ethernet/intel/ice/ice_flex_pipe.h     |   3 +
 drivers/net/ethernet/intel/ice/ice_flow.c          | 107 ++++++
 drivers/net/ethernet/intel/ice/ice_flow.h          |   5 +
 drivers/net/ethernet/intel/ice/ice_vf_lib.h        |   8 +
 drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c | 403 ++++++++++++++++++++-
 6 files changed, 566 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 7f182a6f72aa..ed95072ca6e3 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -4145,6 +4145,54 @@ err_ice_add_prof_id_flow:
 	return status;
 }
 
+/**
+ * ice_flow_assoc_fdir_prof - add an FDIR profile for main/ctrl VSI
+ * @hw: pointer to the HW struct
+ * @blk: HW block
+ * @dest_vsi: dest VSI
+ * @fdir_vsi: fdir programming VSI
+ * @hdl: profile handle
+ *
+ * Update the hardware tables to enable the FDIR profile indicated by @hdl for
+ * the VSI specified by @dest_vsi. On success, the flow will be enabled.
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+int
+ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk,
+			 u16 dest_vsi, u16 fdir_vsi, u64 hdl)
+{
+	u16 vsi_num;
+	int status;
+
+	if (blk != ICE_BLK_FD)
+		return -EINVAL;
+
+	vsi_num = ice_get_hw_vsi_num(hw, dest_vsi);
+	status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl);
+	if (status) {
+		ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for main VSI flow entry: %d\n",
+			  status);
+		return status;
+	}
+
+	vsi_num = ice_get_hw_vsi_num(hw, fdir_vsi);
+	status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl);
+	if (status) {
+		ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for ctrl VSI flow entry: %d\n",
+			  status);
+		goto err;
+	}
+
+	return 0;
+
+err:
+	vsi_num = ice_get_hw_vsi_num(hw, dest_vsi);
+	ice_rem_prof_id_flow(hw, blk, vsi_num, hdl);
+
+	return status;
+}
+
 /**
  * ice_rem_prof_from_list - remove a profile from list
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
index 7c66652dadd6..90b9b0993122 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h
@@ -51,6 +51,9 @@ int
 ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl);
 int
 ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl);
+int
+ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk,
+			 u16 dest_vsi, u16 fdir_vsi, u64 hdl);
 enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len);
 enum ice_ddp_state
 ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index 79106503194b..d97b751052f2 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -409,6 +409,29 @@ static const u32 ice_ptypes_gtpc_tid[] = {
 };
 
 /* Packet types for GTPU */
+static const struct ice_ptype_attributes ice_attr_gtpu_session[] = {
+	{ ICE_MAC_IPV4_GTPU_IPV4_FRAG,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV4_PAY,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV4_TCP,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV4_ICMP,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV4_FRAG,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV4_PAY,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV4_TCP,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV4_ICMP,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV6_FRAG,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV6_PAY,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV6_TCP,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV4_GTPU_IPV6_ICMPV6,  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV6_FRAG,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV6_PAY,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV6_TCP,	  ICE_PTYPE_ATTR_GTP_SESSION },
+	{ ICE_MAC_IPV6_GTPU_IPV6_ICMPV6,  ICE_PTYPE_ATTR_GTP_SESSION },
+};
+
 static const struct ice_ptype_attributes ice_attr_gtpu_eh[] = {
 	{ ICE_MAC_IPV4_GTPU_IPV4_FRAG,	  ICE_PTYPE_ATTR_GTP_PDU_EH },
 	{ ICE_MAC_IPV4_GTPU_IPV4_PAY,	  ICE_PTYPE_ATTR_GTP_PDU_EH },
@@ -1523,6 +1546,90 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk,
 	return status;
 }
 
+#define FLAG_GTP_EH_PDU_LINK	BIT_ULL(13)
+#define FLAG_GTP_EH_PDU		BIT_ULL(14)
+
+#define HI_BYTE_IN_WORD		GENMASK(15, 8)
+#define LO_BYTE_IN_WORD		GENMASK(7, 0)
+
+#define FLAG_GTPU_MSK	\
+	(FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK)
+#define FLAG_GTPU_UP	\
+	(FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK)
+#define FLAG_GTPU_DW	FLAG_GTP_EH_PDU
+
+/**
+ * ice_flow_set_parser_prof - Set flow profile based on the parsed profile info
+ * @hw: pointer to the HW struct
+ * @dest_vsi: dest VSI
+ * @fdir_vsi: fdir programming VSI
+ * @prof: stores parsed profile info from raw flow
+ * @blk: classification blk
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+int
+ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi,
+			 struct ice_parser_profile *prof, enum ice_block blk)
+{
+	u64 id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX);
+	struct ice_flow_prof_params *params __free(kfree);
+	u8 fv_words = hw->blk[blk].es.fvw;
+	int status;
+	int i, idx;
+
+	params = kzalloc(sizeof(*params), GFP_KERNEL);
+	if (!params)
+		return -ENOMEM;
+
+	for (i = 0; i < ICE_MAX_FV_WORDS; i++) {
+		params->es[i].prot_id = ICE_PROT_INVALID;
+		params->es[i].off = ICE_FV_OFFSET_INVAL;
+	}
+
+	for (i = 0; i < prof->fv_num; i++) {
+		if (hw->blk[blk].es.reverse)
+			idx = fv_words - i - 1;
+		else
+			idx = i;
+		params->es[idx].prot_id = prof->fv[i].proto_id;
+		params->es[idx].off = prof->fv[i].offset;
+		params->mask[idx] = (((prof->fv[i].msk) << BITS_PER_BYTE) &
+				      HI_BYTE_IN_WORD) |
+				    (((prof->fv[i].msk) >> BITS_PER_BYTE) &
+				      LO_BYTE_IN_WORD);
+	}
+
+	switch (prof->flags) {
+	case FLAG_GTPU_DW:
+		params->attr = ice_attr_gtpu_down;
+		params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_down);
+		break;
+	case FLAG_GTPU_UP:
+		params->attr = ice_attr_gtpu_up;
+		params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_up);
+		break;
+	default:
+		if (prof->flags_msk & FLAG_GTPU_MSK) {
+			params->attr = ice_attr_gtpu_session;
+			params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_session);
+		}
+		break;
+	}
+
+	status = ice_add_prof(hw, blk, id, (u8 *)prof->ptypes,
+			      params->attr, params->attr_cnt,
+			      params->es, params->mask, false, false);
+	if (status)
+		return status;
+
+	status = ice_flow_assoc_fdir_prof(hw, blk, dest_vsi, fdir_vsi, id);
+	if (status)
+		ice_rem_prof(hw, blk, id);
+
+	return status;
+}
+
 /**
  * ice_flow_add_prof - Add a flow profile for packet segments and matched fields
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 2fd2e0cb483d..6cb7bb879c98 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -5,6 +5,7 @@
 #define _ICE_FLOW_H_
 
 #include "ice_flex_type.h"
+#include "ice_parser.h"
 
 #define ICE_FLOW_ENTRY_HANDLE_INVAL	0
 #define ICE_FLOW_FLD_OFF_INVAL		0xffff
@@ -326,6 +327,7 @@ enum ice_rss_cfg_hdr_type {
 	ICE_RSS_ANY_HEADERS
 };
 
+struct ice_vsi;
 struct ice_rss_hash_cfg {
 	u32 addl_hdrs; /* protocol header fields */
 	u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */
@@ -445,6 +447,9 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir,
 		  bool symm, struct ice_flow_prof **prof);
 int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id);
 int
+ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi,
+			 struct ice_parser_profile *prof, enum ice_block blk);
+int
 ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id,
 		   u64 entry_id, u16 vsi, enum ice_flow_priority prio,
 		   void *data, u64 *entry_h);
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index fec16919ec19..be4266899690 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -12,6 +12,7 @@
 #include <net/devlink.h>
 #include <linux/avf/virtchnl.h>
 #include "ice_type.h"
+#include "ice_flow.h"
 #include "ice_virtchnl_fdir.h"
 #include "ice_vsi_vlan_ops.h"
 
@@ -52,6 +53,12 @@ struct ice_mdd_vf_events {
 	u16 last_printed;
 };
 
+/* Structure to store fdir fv entry */
+struct ice_fdir_prof_info {
+	struct ice_parser_profile prof;
+	u64 fdir_active_cnt;
+};
+
 /* VF operations */
 struct ice_vf_ops {
 	enum ice_disq_rst_src reset_type;
@@ -91,6 +98,7 @@ struct ice_vf {
 	u16 lan_vsi_idx;		/* index into PF struct */
 	u16 ctrl_vsi_idx;
 	struct ice_vf_fdir fdir;
+	struct ice_fdir_prof_info fdir_prof_info[ICE_MAX_PTGS];
 	/* first vector index of this VF in the PF space */
 	int first_vector_idx;
 	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index b4feb0927687..14e3f0f89c78 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -26,6 +26,15 @@ enum ice_fdir_tunnel_type {
 	ICE_FDIR_TUNNEL_TYPE_NONE = 0,
 	ICE_FDIR_TUNNEL_TYPE_GTPU,
 	ICE_FDIR_TUNNEL_TYPE_GTPU_EH,
+	ICE_FDIR_TUNNEL_TYPE_ECPRI,
+	ICE_FDIR_TUNNEL_TYPE_GTPU_INNER,
+	ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER,
+	ICE_FDIR_TUNNEL_TYPE_GRE,
+	ICE_FDIR_TUNNEL_TYPE_GTPOGRE,
+	ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER,
+	ICE_FDIR_TUNNEL_TYPE_GRE_INNER,
+	ICE_FDIR_TUNNEL_TYPE_L2TPV2,
+	ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER,
 };
 
 struct virtchnl_fdir_fltr_conf {
@@ -33,6 +42,11 @@ struct virtchnl_fdir_fltr_conf {
 	enum ice_fdir_tunnel_type ttype;
 	u64 inset_flag;
 	u32 flow_id;
+
+	struct ice_parser_profile *prof;
+	bool parser_ena;
+	u8 *pkt_buf;
+	u8 pkt_len;
 };
 
 struct virtchnl_fdir_inset_map {
@@ -786,6 +800,107 @@ err_exit:
 	return ret;
 }
 
+/**
+ * ice_vc_fdir_is_raw_flow - check if FDIR flow is raw (binary)
+ * @proto: virtchnl protocol headers
+ *
+ * Check if the FDIR rule is raw flow (protocol agnostic flow) or not. Note
+ * that common FDIR rule must have non-zero proto->count. Thus, we choose the
+ * tunnel_level and count of proto as the indicators. If both tunnel_level and
+ * count of proto are zero, this FDIR rule will be regarded as raw flow.
+ *
+ * Returns: true if headers describe raw flow, false otherwise.
+ */
+static bool
+ice_vc_fdir_is_raw_flow(struct virtchnl_proto_hdrs *proto)
+{
+	return (proto->tunnel_level == 0 && proto->count == 0);
+}
+
+/**
+ * ice_vc_fdir_parse_raw - parse a virtchnl raw FDIR rule
+ * @vf: pointer to the VF info
+ * @proto: virtchnl protocol headers
+ * @conf: FDIR configuration for each filter
+ *
+ * Parse the virtual channel filter's raw flow and store it in @conf
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+static int
+ice_vc_fdir_parse_raw(struct ice_vf *vf,
+		      struct virtchnl_proto_hdrs *proto,
+		      struct virtchnl_fdir_fltr_conf *conf)
+{
+	u8 *pkt_buf, *msk_buf __free(kfree);
+	struct ice_parser_result rslt;
+	struct ice_pf *pf = vf->pf;
+	struct ice_parser *psr;
+	int status = -ENOMEM;
+	struct ice_hw *hw;
+	u16 udp_port = 0;
+
+	pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
+	msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
+	if (!pkt_buf || !msk_buf)
+		goto err_mem_alloc;
+
+	memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len);
+	memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len);
+
+	hw = &pf->hw;
+
+	/* Get raw profile info via Parser Lib */
+	psr = ice_parser_create(hw);
+	if (IS_ERR(psr)) {
+		status = PTR_ERR(psr);
+		goto err_mem_alloc;
+	}
+
+	ice_parser_dvm_set(psr, ice_is_dvm_ena(hw));
+
+	if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN))
+		ice_parser_vxlan_tunnel_set(psr, udp_port, true);
+
+	status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt);
+	if (status)
+		goto err_parser_destroy;
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_parser_result_dump(hw, &rslt);
+
+	conf->prof = kzalloc(sizeof(*conf->prof), GFP_KERNEL);
+	if (!conf->prof) {
+		status = -ENOMEM;
+		goto err_parser_destroy;
+	}
+
+	status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf,
+					 proto->raw.pkt_len, ICE_BLK_FD,
+					 conf->prof);
+	if (status)
+		goto err_parser_profile_init;
+
+	if (hw->debug_mask & ICE_DBG_PARSER)
+		ice_parser_profile_dump(hw, conf->prof);
+
+	/* Store raw flow info into @conf */
+	conf->pkt_len = proto->raw.pkt_len;
+	conf->pkt_buf = pkt_buf;
+	conf->parser_ena = true;
+
+	ice_parser_destroy(psr);
+	return 0;
+
+err_parser_profile_init:
+	kfree(conf->prof);
+err_parser_destroy:
+	ice_parser_destroy(psr);
+err_mem_alloc:
+	kfree(pkt_buf);
+	return status;
+}
+
 /**
  * ice_vc_fdir_parse_pattern
  * @vf: pointer to the VF info
@@ -813,6 +928,10 @@ ice_vc_fdir_parse_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr,
 		return -EINVAL;
 	}
 
+	/* For raw FDIR filters created by the parser */
+	if (ice_vc_fdir_is_raw_flow(proto))
+		return ice_vc_fdir_parse_raw(vf, proto, conf);
+
 	for (i = 0; i < proto->count; i++) {
 		struct virtchnl_proto_hdr *hdr = &proto->proto_hdr[i];
 		struct ip_esp_hdr *esph;
@@ -1101,8 +1220,10 @@ ice_vc_validate_fdir_fltr(struct ice_vf *vf, struct virtchnl_fdir_add *fltr,
 	struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs;
 	int ret;
 
-	if (!ice_vc_validate_pattern(vf, proto))
-		return -EINVAL;
+	/* For raw FDIR filters created by the parser */
+	if (!ice_vc_fdir_is_raw_flow(proto))
+		if (!ice_vc_validate_pattern(vf, proto))
+			return -EINVAL;
 
 	ret = ice_vc_fdir_parse_pattern(vf, fltr, conf);
 	if (ret)
@@ -1295,11 +1416,15 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf,
 		return -ENOMEM;
 
 	ice_fdir_get_prgm_desc(hw, input, &desc, add);
-	ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun);
-	if (ret) {
-		dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n",
-			vf->vf_id, input->flow_type);
-		goto err_free_pkt;
+	if (conf->parser_ena) {
+		memcpy(pkt, conf->pkt_buf, conf->pkt_len);
+	} else {
+		ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun);
+		if (ret) {
+			dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n",
+				vf->vf_id, input->flow_type);
+			goto err_free_pkt;
+		}
 	}
 
 	ret = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt);
@@ -1521,6 +1646,16 @@ err_exit:
 	return ret;
 }
 
+static int ice_fdir_is_tunnel(enum ice_fdir_tunnel_type ttype)
+{
+	return (ttype == ICE_FDIR_TUNNEL_TYPE_GRE_INNER ||
+		ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_INNER ||
+		ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER ||
+		ttype == ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER ||
+		ttype == ICE_FDIR_TUNNEL_TYPE_ECPRI ||
+		ttype == ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER);
+}
+
 /**
  * ice_vc_add_fdir_fltr_post
  * @vf: pointer to the VF structure
@@ -1781,6 +1916,158 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf)
 	spin_unlock_irqrestore(&vf->fdir.ctx_lock, flags);
 }
 
+/**
+ * ice_vc_parser_fv_check_diff - check two parsed FDIR profile fv context
+ * @fv_a: struct of parsed FDIR profile field vector
+ * @fv_b: struct of parsed FDIR profile field vector
+ *
+ * Check if the two parsed FDIR profile field vector context are different,
+ * including proto_id, offset and mask.
+ *
+ * Return: true on different, false on otherwise.
+ */
+static bool ice_vc_parser_fv_check_diff(struct ice_parser_fv *fv_a,
+					struct ice_parser_fv *fv_b)
+{
+	return (fv_a->proto_id	!= fv_b->proto_id ||
+		fv_a->offset	!= fv_b->offset ||
+		fv_a->msk	!= fv_b->msk);
+}
+
+/**
+ * ice_vc_parser_fv_save - save parsed FDIR profile fv context
+ * @fv: struct of parsed FDIR profile field vector
+ * @fv_src: parsed FDIR profile field vector context to save
+ *
+ * Save the parsed FDIR profile field vector context, including proto_id,
+ * offset and mask.
+ *
+ * Return: Void.
+ */
+static void ice_vc_parser_fv_save(struct ice_parser_fv *fv,
+				  struct ice_parser_fv *fv_src)
+{
+	fv->proto_id	= fv_src->proto_id;
+	fv->offset	= fv_src->offset;
+	fv->msk		= fv_src->msk;
+	fv->spec	= 0;
+}
+
+/**
+ * ice_vc_add_fdir_raw - add a raw FDIR filter for VF
+ * @vf: pointer to the VF info
+ * @conf: FDIR configuration for each filter
+ * @v_ret: the final VIRTCHNL code
+ * @stat: pointer to the VIRTCHNL_OP_ADD_FDIR_FILTER
+ * @len: length of the stat
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+static int
+ice_vc_add_fdir_raw(struct ice_vf *vf,
+		    struct virtchnl_fdir_fltr_conf *conf,
+		    enum virtchnl_status_code *v_ret,
+		    struct virtchnl_fdir_add *stat, int len)
+{
+	struct ice_vsi *vf_vsi, *ctrl_vsi;
+	struct ice_fdir_prof_info *pi;
+	struct ice_pf *pf = vf->pf;
+	int ret, ptg, id, i;
+	struct device *dev;
+	struct ice_hw *hw;
+	bool fv_found;
+
+	dev = ice_pf_to_dev(pf);
+	hw = &pf->hw;
+	*v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE;
+
+	id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX);
+	ptg = hw->blk[ICE_BLK_FD].xlt1.t[id];
+
+	vf_vsi = ice_get_vf_vsi(vf);
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %d\n", vf->vf_id);
+		return -ENODEV;
+	}
+
+	ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx];
+	if (!ctrl_vsi) {
+		dev_err(dev, "Can not get FDIR ctrl_vsi for VF %d\n",
+			vf->vf_id);
+		return -ENODEV;
+	}
+
+	fv_found = false;
+
+	/* Check if profile info already exists, then update the counter */
+	pi = &vf->fdir_prof_info[ptg];
+	if (pi->fdir_active_cnt != 0) {
+		for (i = 0; i < ICE_MAX_FV_WORDS; i++)
+			if (ice_vc_parser_fv_check_diff(&pi->prof.fv[i],
+							&conf->prof->fv[i]))
+				break;
+		if (i == ICE_MAX_FV_WORDS) {
+			fv_found = true;
+			pi->fdir_active_cnt++;
+		}
+	}
+
+	/* HW profile setting is only required for the first time */
+	if (!fv_found) {
+		ret = ice_flow_set_parser_prof(hw, vf_vsi->idx,
+					       ctrl_vsi->idx, conf->prof,
+					       ICE_BLK_FD);
+
+		if (ret) {
+			*v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+			dev_dbg(dev, "VF %d: insert hw prof failed\n",
+				vf->vf_id);
+			return ret;
+		}
+	}
+
+	ret = ice_vc_fdir_insert_entry(vf, conf, &conf->flow_id);
+	if (ret) {
+		*v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		dev_dbg(dev, "VF %d: insert FDIR list failed\n",
+			vf->vf_id);
+		return ret;
+	}
+
+	ret = ice_vc_fdir_set_irq_ctx(vf, conf,
+				      VIRTCHNL_OP_ADD_FDIR_FILTER);
+	if (ret) {
+		dev_dbg(dev, "VF %d: set FDIR context failed\n",
+			vf->vf_id);
+		goto err_rem_entry;
+	}
+
+	ret = ice_vc_fdir_write_fltr(vf, conf, true, false);
+	if (ret) {
+		dev_err(dev, "VF %d: adding FDIR raw flow rule failed, ret:%d\n",
+			vf->vf_id, ret);
+		goto err_clr_irq;
+	}
+
+	/* Save parsed profile fv info of the FDIR rule for the first time */
+	if (!fv_found) {
+		for (i = 0; i < conf->prof->fv_num; i++)
+			ice_vc_parser_fv_save(&pi->prof.fv[i],
+					      &conf->prof->fv[i]);
+		pi->prof.fv_num = conf->prof->fv_num;
+		pi->fdir_active_cnt = 1;
+	}
+
+	return 0;
+
+err_clr_irq:
+	ice_vc_fdir_clear_irq_ctx(vf);
+err_rem_entry:
+	ice_vc_fdir_remove_entry(vf, conf, conf->flow_id);
+	return ret;
+}
+
 /**
  * ice_vc_add_fdir_fltr - add a FDIR filter for VF by the msg buffer
  * @vf: pointer to the VF info
@@ -1846,7 +2133,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	len = sizeof(*stat);
 	ret = ice_vc_validate_fdir_fltr(vf, fltr, conf);
 	if (ret) {
-		v_ret = VIRTCHNL_STATUS_SUCCESS;
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		stat->status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID;
 		dev_dbg(dev, "Invalid FDIR filter from VF %d\n", vf->vf_id);
 		goto err_free_conf;
@@ -1861,6 +2148,15 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 		goto exit;
 	}
 
+	/* For raw FDIR filters created by the parser */
+	if (conf->parser_ena) {
+		ret = ice_vc_add_fdir_raw(vf, conf, &v_ret, stat, len);
+		if (ret)
+			goto err_free_conf;
+		goto exit;
+	}
+
+	is_tun = ice_fdir_is_tunnel(conf->ttype);
 	ret = ice_vc_fdir_config_input_set(vf, fltr, conf, is_tun);
 	if (ret) {
 		v_ret = VIRTCHNL_STATUS_SUCCESS;
@@ -1921,6 +2217,78 @@ err_exit:
 	return ret;
 }
 
+/**
+ * ice_vc_del_fdir_raw - delete a raw FDIR filter for VF
+ * @vf: pointer to the VF info
+ * @conf: FDIR configuration for each filter
+ * @v_ret: the final VIRTCHNL code
+ * @stat: pointer to the VIRTCHNL_OP_DEL_FDIR_FILTER
+ * @len: length of the stat
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+static int
+ice_vc_del_fdir_raw(struct ice_vf *vf,
+		    struct virtchnl_fdir_fltr_conf *conf,
+		    enum virtchnl_status_code *v_ret,
+		    struct virtchnl_fdir_del *stat, int len)
+{
+	struct ice_vsi *vf_vsi, *ctrl_vsi;
+	enum ice_block blk = ICE_BLK_FD;
+	struct ice_fdir_prof_info *pi;
+	struct ice_pf *pf = vf->pf;
+	struct device *dev;
+	struct ice_hw *hw;
+	unsigned long id;
+	u16 vsi_num;
+	int ptg;
+	int ret;
+
+	dev = ice_pf_to_dev(pf);
+	hw = &pf->hw;
+	*v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE;
+
+	id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX);
+	ptg = hw->blk[ICE_BLK_FD].xlt1.t[id];
+
+	ret = ice_vc_fdir_write_fltr(vf, conf, false, false);
+	if (ret) {
+		dev_err(dev, "VF %u: deleting FDIR raw flow rule failed: %d\n",
+			vf->vf_id, ret);
+		return ret;
+	}
+
+	vf_vsi = ice_get_vf_vsi(vf);
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+		return -ENODEV;
+	}
+
+	ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx];
+	if (!ctrl_vsi) {
+		dev_err(dev, "Can not get FDIR ctrl_vsi for VF %u\n",
+			vf->vf_id);
+		return -ENODEV;
+	}
+
+	pi = &vf->fdir_prof_info[ptg];
+	if (pi->fdir_active_cnt != 0) {
+		pi->fdir_active_cnt--;
+		/* Remove the profile id flow if no active FDIR rule left */
+		if (!pi->fdir_active_cnt) {
+			vsi_num = ice_get_hw_vsi_num(hw, ctrl_vsi->idx);
+			ice_rem_prof_id_flow(hw, blk, vsi_num, id);
+
+			vsi_num = ice_get_hw_vsi_num(hw, vf_vsi->idx);
+			ice_rem_prof_id_flow(hw, blk, vsi_num, id);
+		}
+	}
+
+	conf->parser_ena = false;
+	return 0;
+}
+
 /**
  * ice_vc_del_fdir_fltr - delete a FDIR filter for VF by the msg buffer
  * @vf: pointer to the VF info
@@ -1933,7 +2301,10 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	struct virtchnl_fdir_del *fltr = (struct virtchnl_fdir_del *)msg;
 	struct virtchnl_fdir_del *stat = NULL;
 	struct virtchnl_fdir_fltr_conf *conf;
+	struct ice_vf_fdir *fdir = &vf->fdir;
 	enum virtchnl_status_code v_ret;
+	struct ice_fdir_fltr *input;
+	enum ice_fltr_ptype flow;
 	struct device *dev;
 	struct ice_pf *pf;
 	int is_tun = 0;
@@ -1983,6 +2354,15 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg)
 		goto err_exit;
 	}
 
+	/* For raw FDIR filters created by the parser */
+	if (conf->parser_ena) {
+		ret = ice_vc_del_fdir_raw(vf, conf, &v_ret, stat, len);
+		if (ret)
+			goto err_del_tmr;
+		goto exit;
+	}
+
+	is_tun = ice_fdir_is_tunnel(conf->ttype);
 	ret = ice_vc_fdir_write_fltr(vf, conf, false, is_tun);
 	if (ret) {
 		v_ret = VIRTCHNL_STATUS_SUCCESS;
@@ -1992,6 +2372,13 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg)
 		goto err_del_tmr;
 	}
 
+	/* Remove unused profiles to avoid unexpected behaviors */
+	input = &conf->input;
+	flow = input->flow_type;
+	if (fdir->fdir_fltr_cnt[flow][is_tun] == 1)
+		ice_vc_fdir_rem_prof(vf, flow, is_tun);
+
+exit:
 	kfree(stat);
 
 	return ret;
-- 
cgit v1.3-3-g829e


From 995617dccc89643d8d8022bbec76e869643842bf Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Thu, 25 Jul 2024 16:08:08 -0600
Subject: iavf: refactor add/del FDIR filters

In preparation for a second type of FDIR filters that can be added by
tc-u32, move the add/del of the FDIR logic to be entirely contained in
iavf_fdir.c.

The iavf_find_fdir_fltr_by_loc() is renamed to iavf_find_fdir_fltr()
to be more agnostic to the filter ID parameter (for now @loc, which is
relevant only to current FDIR filters added via ethtool).

The FDIR filter deletion is moved from iavf_del_fdir_ethtool() in
ethtool.c to iavf_fdir_del_fltr(). While at it, fix a minor bug where
the "fltr" is accessed out of the fdir_fltr_lock spinlock protection.

Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h         |  5 ++
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 56 +++-----------------
 drivers/net/ethernet/intel/iavf/iavf_fdir.c    | 72 ++++++++++++++++++++++++--
 drivers/net/ethernet/intel/iavf/iavf_fdir.h    |  7 ++-
 4 files changed, 83 insertions(+), 57 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 23a6557fc3db..dfed22baebf8 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -444,6 +444,11 @@ struct iavf_adapter {
 	spinlock_t adv_rss_lock;	/* protect the RSS management list */
 };
 
+/* Must be called with fdir_fltr_lock lock held */
+static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter)
+{
+	return adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS;
+}
 
 /* Ethtool Private Flags */
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 52273f7eab2c..7ab445eeee18 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -927,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter,
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 
-	rule = iavf_find_fdir_fltr_by_loc(adapter, fsp->location);
+	rule = iavf_find_fdir_fltr(adapter, fsp->location);
 	if (!rule) {
 		ret = -EINVAL;
 		goto release_lock;
@@ -1263,15 +1263,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 		return -EINVAL;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
-	if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) {
-		spin_unlock_bh(&adapter->fdir_fltr_lock);
-		dev_err(&adapter->pdev->dev,
-			"Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n",
-			IAVF_MAX_FDIR_FILTERS);
-		return -ENOSPC;
-	}
-
-	if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) {
+	if (iavf_find_fdir_fltr(adapter, fsp->location)) {
 		dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n");
 		spin_unlock_bh(&adapter->fdir_fltr_lock);
 		return -EEXIST;
@@ -1291,23 +1283,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	}
 
 	err = iavf_add_fdir_fltr_info(adapter, fsp, fltr);
-	if (err)
-		goto ret;
-
-	spin_lock_bh(&adapter->fdir_fltr_lock);
-	iavf_fdir_list_add_fltr(adapter, fltr);
-	adapter->fdir_active_fltr++;
-
-	if (adapter->link_up)
-		fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
-	else
-		fltr->state = IAVF_FDIR_FLTR_INACTIVE;
-	spin_unlock_bh(&adapter->fdir_fltr_lock);
+	if (!err)
+		err = iavf_fdir_add_fltr(adapter, fltr);
 
-	if (adapter->link_up)
-		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER);
-ret:
-	if (err && fltr)
+	if (err)
 		kfree(fltr);
 
 	mutex_unlock(&adapter->crit_lock);
@@ -1324,34 +1303,11 @@ ret:
 static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
-	struct iavf_fdir_fltr *fltr = NULL;
-	int err = 0;
 
 	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
-	spin_lock_bh(&adapter->fdir_fltr_lock);
-	fltr = iavf_find_fdir_fltr_by_loc(adapter, fsp->location);
-	if (fltr) {
-		if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
-			fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
-		} else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
-			list_del(&fltr->list);
-			kfree(fltr);
-			adapter->fdir_active_fltr--;
-			fltr = NULL;
-		} else {
-			err = -EBUSY;
-		}
-	} else if (adapter->fdir_active_fltr) {
-		err = -EINVAL;
-	}
-	spin_unlock_bh(&adapter->fdir_fltr_lock);
-
-	if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST)
-		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER);
-
-	return err;
+	return iavf_fdir_del_fltr(adapter, fsp->location);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
index 2d47b0b4640e..1e1daf71dfa0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
@@ -815,13 +815,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *
 }
 
 /**
- * iavf_find_fdir_fltr_by_loc - find filter with location
+ * iavf_find_fdir_fltr - find FDIR filter
  * @adapter: pointer to the VF adapter structure
  * @loc: location to find.
  *
- * Returns pointer to Flow Director filter if found or null
+ * Returns: pointer to Flow Director filter if found or NULL. Lock must be held.
  */
-struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc)
+struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter,
+					   u32 loc)
 {
 	struct iavf_fdir_fltr *rule;
 
@@ -833,14 +834,26 @@ struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter,
 }
 
 /**
- * iavf_fdir_list_add_fltr - add a new node to the flow director filter list
+ * iavf_fdir_add_fltr - add a new node to the flow director filter list
  * @adapter: pointer to the VF adapter structure
  * @fltr: filter node to add to structure
+ *
+ * Return: 0 on success or negative errno on failure.
  */
-void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr)
+int iavf_fdir_add_fltr(struct iavf_adapter *adapter,
+		       struct iavf_fdir_fltr *fltr)
 {
 	struct iavf_fdir_fltr *rule, *parent = NULL;
 
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	if (iavf_fdir_max_reached(adapter)) {
+		spin_unlock_bh(&adapter->fdir_fltr_lock);
+		dev_err(&adapter->pdev->dev,
+			"Unable to add Flow Director filter (limit (%u) reached)\n",
+			IAVF_MAX_FDIR_FILTERS);
+		return -ENOSPC;
+	}
+
 	list_for_each_entry(rule, &adapter->fdir_list_head, list) {
 		if (rule->loc >= fltr->loc)
 			break;
@@ -851,4 +864,53 @@ void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr
 		list_add(&fltr->list, &parent->list);
 	else
 		list_add(&fltr->list, &adapter->fdir_list_head);
+	adapter->fdir_active_fltr++;
+
+	if (adapter->link_up)
+		fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
+	else
+		fltr->state = IAVF_FDIR_FLTR_INACTIVE;
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+
+	if (adapter->link_up)
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER);
+
+	return 0;
+}
+
+/**
+ * iavf_fdir_del_fltr - delete a flow director filter from the list
+ * @adapter: pointer to the VF adapter structure
+ * @loc: location to delete.
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc)
+{
+	struct iavf_fdir_fltr *fltr = NULL;
+	int err = 0;
+
+	spin_lock_bh(&adapter->fdir_fltr_lock);
+	fltr = iavf_find_fdir_fltr(adapter, loc);
+
+	if (fltr) {
+		if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
+			fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
+		} else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
+			list_del(&fltr->list);
+			kfree(fltr);
+			adapter->fdir_active_fltr--;
+			fltr = NULL;
+		} else {
+			err = -EBUSY;
+		}
+	} else if (adapter->fdir_active_fltr) {
+		err = -EINVAL;
+	}
+
+	if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST)
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER);
+
+	spin_unlock_bh(&adapter->fdir_fltr_lock);
+	return err;
 }
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
index d31bd923ba8c..5c85eb25fa2a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
@@ -128,6 +128,9 @@ int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter,
 int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
 void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
 bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
-void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
-struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc);
+int iavf_fdir_add_fltr(struct iavf_adapter *adapter,
+		       struct iavf_fdir_fltr *fltr);
+int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc);
+struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter,
+					   u32 loc);
 #endif /* _IAVF_FDIR_H_ */
-- 
cgit v1.3-3-g829e


From 623122ac1c4074791ea319df4676fb2875817fe4 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Thu, 25 Jul 2024 16:08:09 -0600
Subject: iavf: add support for offloading tc U32 cls filters

Add support for offloading cls U32 filters. Only "skbedit queue_mapping"
and "drop" actions are supported. Also, only "ip" and "802_3" tc
protocols are allowed. The PF must advertise the VIRTCHNL_VF_OFFLOAD_TC_U32
capability flag.

Since the filters will be enabled via the FD stage at the PF, a new type
of FDIR filters is added and the existing list and state machine are used.

The new filters can be used to configure flow directors based on raw
(binary) pattern in the rx packet.

Examples:

0. # tc qdisc add dev enp175s0v0  ingress

1. Redirect UDP from src IP 192.168.2.1 to queue 12:

    # tc filter add dev <dev> protocol ip ingress u32 \
	match u32 0x45000000 0xff000000 at 0  \
	match u32 0x00110000 0x00ff0000 at 8  \
	match u32 0xC0A80201 0xffffffff at 12 \
	match u32 0x00000000 0x00000000 at 24 \
	action skbedit queue_mapping 12 skip_sw

2. Drop all ICMP:

    # tc filter add dev <dev> protocol ip ingress u32 \
	match u32 0x45000000 0xff000000 at 0  \
	match u32 0x00010000 0x00ff0000 at 8  \
	match u32 0x00000000 0x00000000 at 24 \
	action drop skip_sw

3. Redirect ICMP traffic from MAC 3c:fd:fe:a5:47:e0 to queue 7
   (note proto: 802_3):

   # tc filter add dev <dev> protocol 802_3 ingress u32 \
	match u32 0x00003CFD 0x0000ffff at 4   \
	match u32 0xFEA547E0 0xffffffff at 8   \
	match u32 0x08004500 0xffffff00 at 12  \
	match u32 0x00000001 0x000000ff at 20  \
	match u32 0x0000 0x0000 at 40          \
	action skbedit queue_mapping 7 skip_sw

Notes on matches:
1 - All intermediate fields that are needed to parse the correct PTYPE
    must be provided (in e.g. 3: Ethernet Type 0x0800 in MAC, IP version
    and IP length: 0x45 and protocol: 0x01 (ICMP)).
2 - The last match must provide an offset that guarantees all required
    headers are accounted for, even if the last header is not matched.
    For example, in #2, the last match is 4 bytes at offset 24 starting
    from IP header, so the total is 14 (MAC) + 24 + 4 = 42, which is the
    sum of MAC+IP+ICMP headers.

Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h          |  27 +++-
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c  |   9 +-
 drivers/net/ethernet/intel/iavf/iavf_fdir.c     |  29 +++--
 drivers/net/ethernet/intel/iavf/iavf_fdir.h     |  10 +-
 drivers/net/ethernet/intel/iavf/iavf_main.c     | 160 +++++++++++++++++++++++-
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c |  25 ++--
 drivers/net/ethernet/intel/ice/ice_virtchnl.c   |   4 +
 include/linux/avf/virtchnl.h                    |   1 +
 8 files changed, 238 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index dfed22baebf8..48cd1d06761c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -33,6 +33,7 @@
 #include <net/udp.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/tc_act/tc_skbedit.h>
 
 #include "iavf_type.h"
 #include <linux/avf/virtchnl.h>
@@ -393,6 +394,8 @@ struct iavf_adapter {
 			     VIRTCHNL_VF_OFFLOAD_VLAN_V2)
 #define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
 				 VIRTCHNL_VF_OFFLOAD_CRC)
+#define TC_U32_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \
+			    VIRTCHNL_VF_OFFLOAD_TC_U32)
 #define VLAN_V2_FILTERING_ALLOWED(_a) \
 	(VLAN_V2_ALLOWED((_a)) && \
 	 ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \
@@ -437,6 +440,7 @@ struct iavf_adapter {
 
 #define IAVF_MAX_FDIR_FILTERS 128	/* max allowed Flow Director filters */
 	u16 fdir_active_fltr;
+	u16 raw_fdir_active_fltr;
 	struct list_head fdir_list_head;
 	spinlock_t fdir_fltr_lock;	/* protect the Flow Director filter list */
 
@@ -447,7 +451,28 @@ struct iavf_adapter {
 /* Must be called with fdir_fltr_lock lock held */
 static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter)
 {
-	return adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS;
+	return adapter->fdir_active_fltr + adapter->raw_fdir_active_fltr >=
+			IAVF_MAX_FDIR_FILTERS;
+}
+
+static inline void
+iavf_inc_fdir_active_fltr(struct iavf_adapter *adapter,
+			  struct iavf_fdir_fltr *fltr)
+{
+	if (iavf_is_raw_fdir(fltr))
+		adapter->raw_fdir_active_fltr++;
+	else
+		adapter->fdir_active_fltr++;
+}
+
+static inline void
+iavf_dec_fdir_active_fltr(struct iavf_adapter *adapter,
+			  struct iavf_fdir_fltr *fltr)
+{
+	if (iavf_is_raw_fdir(fltr))
+		adapter->raw_fdir_active_fltr--;
+	else
+		adapter->fdir_active_fltr--;
 }
 
 /* Ethtool Private Flags */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 7ab445eeee18..74a1e9fe1821 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -927,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter,
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 
-	rule = iavf_find_fdir_fltr(adapter, fsp->location);
+	rule = iavf_find_fdir_fltr(adapter, false, fsp->location);
 	if (!rule) {
 		ret = -EINVAL;
 		goto release_lock;
@@ -1072,6 +1072,9 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd,
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 
 	list_for_each_entry(fltr, &adapter->fdir_list_head, list) {
+		if (iavf_is_raw_fdir(fltr))
+			continue;
+
 		if (cnt == cmd->rule_cnt) {
 			val = -EMSGSIZE;
 			goto release_lock;
@@ -1263,7 +1266,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 		return -EINVAL;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
-	if (iavf_find_fdir_fltr(adapter, fsp->location)) {
+	if (iavf_find_fdir_fltr(adapter, false, fsp->location)) {
 		dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n");
 		spin_unlock_bh(&adapter->fdir_fltr_lock);
 		return -EEXIST;
@@ -1307,7 +1310,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx
 	if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED))
 		return -EOPNOTSUPP;
 
-	return iavf_fdir_del_fltr(adapter, fsp->location);
+	return iavf_fdir_del_fltr(adapter, false, fsp->location);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
index 1e1daf71dfa0..a1b3b44cc14a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c
@@ -796,6 +796,9 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
 	list_for_each_entry(tmp, &adapter->fdir_list_head, list) {
+		if (iavf_is_raw_fdir(fltr))
+			continue;
+
 		if (tmp->flow_type != fltr->flow_type)
 			continue;
 
@@ -817,18 +820,21 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *
 /**
  * iavf_find_fdir_fltr - find FDIR filter
  * @adapter: pointer to the VF adapter structure
- * @loc: location to find.
+ * @is_raw: filter type, is raw (tc u32) or not (ethtool)
+ * @data: data to ID the filter, type dependent
  *
  * Returns: pointer to Flow Director filter if found or NULL. Lock must be held.
  */
 struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter,
-					   u32 loc)
+					   bool is_raw, u32 data)
 {
 	struct iavf_fdir_fltr *rule;
 
-	list_for_each_entry(rule, &adapter->fdir_list_head, list)
-		if (rule->loc == loc)
+	list_for_each_entry(rule, &adapter->fdir_list_head, list) {
+		if ((is_raw && rule->cls_u32_handle == data) ||
+		    (!is_raw && rule->loc == data))
 			return rule;
+	}
 
 	return NULL;
 }
@@ -855,6 +861,9 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter,
 	}
 
 	list_for_each_entry(rule, &adapter->fdir_list_head, list) {
+		if (iavf_is_raw_fdir(fltr))
+			break;
+
 		if (rule->loc >= fltr->loc)
 			break;
 		parent = rule;
@@ -864,7 +873,8 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter,
 		list_add(&fltr->list, &parent->list);
 	else
 		list_add(&fltr->list, &adapter->fdir_list_head);
-	adapter->fdir_active_fltr++;
+
+	iavf_inc_fdir_active_fltr(adapter, fltr);
 
 	if (adapter->link_up)
 		fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST;
@@ -881,25 +891,26 @@ int iavf_fdir_add_fltr(struct iavf_adapter *adapter,
 /**
  * iavf_fdir_del_fltr - delete a flow director filter from the list
  * @adapter: pointer to the VF adapter structure
- * @loc: location to delete.
+ * @is_raw: filter type, is raw (tc u32) or not (ethtool)
+ * @data: data to ID the filter, type dependent
  *
  * Return: 0 on success or negative errno on failure.
  */
-int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc)
+int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data)
 {
 	struct iavf_fdir_fltr *fltr = NULL;
 	int err = 0;
 
 	spin_lock_bh(&adapter->fdir_fltr_lock);
-	fltr = iavf_find_fdir_fltr(adapter, loc);
+	fltr = iavf_find_fdir_fltr(adapter, is_raw, data);
 
 	if (fltr) {
 		if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) {
 			fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST;
 		} else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) {
 			list_del(&fltr->list);
+			iavf_dec_fdir_active_fltr(adapter, fltr);
 			kfree(fltr);
-			adapter->fdir_active_fltr--;
 			fltr = NULL;
 		} else {
 			err = -EBUSY;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
index 5c85eb25fa2a..e84a5351162f 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h
@@ -117,12 +117,18 @@ struct iavf_fdir_fltr {
 
 	u32 flow_id;
 
+	u32 cls_u32_handle; /* for FDIR added via tc u32 */
 	u32 loc;	/* Rule location inside the flow table */
 	u32 q_index;
 
 	struct virtchnl_fdir_add vc_add_msg;
 };
 
+static inline bool iavf_is_raw_fdir(struct iavf_fdir_fltr *fltr)
+{
+	return !fltr->vc_add_msg.rule_cfg.proto_hdrs.count;
+}
+
 int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter,
 				  struct iavf_fdir_fltr *fltr);
 int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
@@ -130,7 +136,7 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f
 bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr);
 int iavf_fdir_add_fltr(struct iavf_adapter *adapter,
 		       struct iavf_fdir_fltr *fltr);
-int iavf_fdir_del_fltr(struct iavf_adapter *adapter, u32 loc);
+int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data);
 struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter,
-					   u32 loc);
+					   bool is_raw, u32 data);
 #endif /* _IAVF_FDIR_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index ff11bafb3b4f..f782402cd789 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -4013,7 +4013,7 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter,
 
 /**
  * iavf_setup_tc_cls_flower - flower classifier offloads
- * @adapter: board private structure
+ * @adapter: pointer to iavf adapter structure
  * @cls_flower: pointer to flow_cls_offload struct with flow info
  */
 static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
@@ -4031,6 +4031,154 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
 	}
 }
 
+/**
+ * iavf_add_cls_u32 - Add U32 classifier offloads
+ * @adapter: pointer to iavf adapter structure
+ * @cls_u32: pointer to tc_cls_u32_offload struct with flow info
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+static int iavf_add_cls_u32(struct iavf_adapter *adapter,
+			    struct tc_cls_u32_offload *cls_u32)
+{
+	struct netlink_ext_ack *extack = cls_u32->common.extack;
+	struct virtchnl_fdir_rule *rule_cfg;
+	struct virtchnl_filter_action *vact;
+	struct virtchnl_proto_hdrs *hdrs;
+	struct ethhdr *spec_h, *mask_h;
+	const struct tc_action *act;
+	struct iavf_fdir_fltr *fltr;
+	struct tcf_exts *exts;
+	unsigned int q_index;
+	int i, status = 0;
+	int off_base = 0;
+
+	if (cls_u32->knode.link_handle) {
+		NL_SET_ERR_MSG_MOD(extack, "Linking not supported");
+		return -EOPNOTSUPP;
+	}
+
+	fltr = kzalloc(sizeof(*fltr), GFP_KERNEL);
+	if (!fltr)
+		return -ENOMEM;
+
+	rule_cfg = &fltr->vc_add_msg.rule_cfg;
+	hdrs = &rule_cfg->proto_hdrs;
+	hdrs->count = 0;
+
+	/* The parser lib at the PF expects the packet starting with MAC hdr */
+	switch (ntohs(cls_u32->common.protocol)) {
+	case ETH_P_802_3:
+		break;
+	case ETH_P_IP:
+		spec_h = (struct ethhdr *)hdrs->raw.spec;
+		mask_h = (struct ethhdr *)hdrs->raw.mask;
+		spec_h->h_proto = htons(ETH_P_IP);
+		mask_h->h_proto = htons(0xFFFF);
+		off_base += ETH_HLEN;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported");
+		status = -EOPNOTSUPP;
+		goto free_alloc;
+	}
+
+	for (i = 0; i < cls_u32->knode.sel->nkeys; i++) {
+		__be32 val, mask;
+		int off;
+
+		off = off_base + cls_u32->knode.sel->keys[i].off;
+		val = cls_u32->knode.sel->keys[i].val;
+		mask = cls_u32->knode.sel->keys[i].mask;
+
+		if (off >= sizeof(hdrs->raw.spec)) {
+			NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed.");
+			status = -EINVAL;
+			goto free_alloc;
+		}
+
+		memcpy(&hdrs->raw.spec[off], &val, sizeof(val));
+		memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask));
+		hdrs->raw.pkt_len = off + sizeof(val);
+	}
+
+	/* Only one action is allowed */
+	rule_cfg->action_set.count = 1;
+	vact = &rule_cfg->action_set.actions[0];
+	exts = cls_u32->knode.exts;
+
+	tcf_exts_for_each_action(i, act, exts) {
+		/* FDIR queue */
+		if (is_tcf_skbedit_rx_queue_mapping(act)) {
+			q_index = tcf_skbedit_rx_queue_mapping(act);
+			if (q_index >= adapter->num_active_queues) {
+				status = -EINVAL;
+				goto free_alloc;
+			}
+
+			vact->type = VIRTCHNL_ACTION_QUEUE;
+			vact->act_conf.queue.index = q_index;
+			break;
+		}
+
+		/* Drop */
+		if (is_tcf_gact_shot(act)) {
+			vact->type = VIRTCHNL_ACTION_DROP;
+			break;
+		}
+
+		/* Unsupported action */
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported action.");
+		status = -EOPNOTSUPP;
+		goto free_alloc;
+	}
+
+	fltr->vc_add_msg.vsi_id = adapter->vsi.id;
+	fltr->cls_u32_handle = cls_u32->knode.handle;
+	return iavf_fdir_add_fltr(adapter, fltr);
+
+free_alloc:
+	kfree(fltr);
+	return status;
+}
+
+/**
+ * iavf_del_cls_u32 - Delete U32 classifier offloads
+ * @adapter: pointer to iavf adapter structure
+ * @cls_u32: pointer to tc_cls_u32_offload struct with flow info
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+static int iavf_del_cls_u32(struct iavf_adapter *adapter,
+			    struct tc_cls_u32_offload *cls_u32)
+{
+	return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle);
+}
+
+/**
+ * iavf_setup_tc_cls_u32 - U32 filter offloads
+ * @adapter: pointer to iavf adapter structure
+ * @cls_u32: pointer to tc_cls_u32_offload struct with flow info
+ *
+ * Return: 0 on success or negative errno on failure.
+ */
+static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter,
+				 struct tc_cls_u32_offload *cls_u32)
+{
+	if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter))
+		return -EOPNOTSUPP;
+
+	switch (cls_u32->command) {
+	case TC_CLSU32_NEW_KNODE:
+	case TC_CLSU32_REPLACE_KNODE:
+		return iavf_add_cls_u32(adapter, cls_u32);
+	case TC_CLSU32_DELETE_KNODE:
+		return iavf_del_cls_u32(adapter, cls_u32);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 /**
  * iavf_setup_tc_block_cb - block callback for tc
  * @type: type of offload
@@ -4050,6 +4198,8 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return iavf_setup_tc_cls_flower(cb_priv, type_data);
+	case TC_SETUP_CLSU32:
+		return iavf_setup_tc_cls_u32(cb_priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -4332,8 +4482,8 @@ static void iavf_disable_fdir(struct iavf_adapter *adapter)
 		    fdir->state == IAVF_FDIR_FLTR_INACTIVE) {
 			/* Delete filters not registered in PF */
 			list_del(&fdir->list);
+			iavf_dec_fdir_active_fltr(adapter, fdir);
 			kfree(fdir);
-			adapter->fdir_active_fltr--;
 		} else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING ||
 			   fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST ||
 			   fdir->state == IAVF_FDIR_FLTR_ACTIVE) {
@@ -4843,9 +4993,11 @@ int iavf_process_config(struct iavf_adapter *adapter)
 	/* get HW VLAN features that can be toggled */
 	hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter);
 
-	/* Enable cloud filter if ADQ is supported */
-	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ)
+	/* Enable HW TC offload if ADQ or tc U32 is supported */
+	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ ||
+	    TC_U32_SUPPORT(adapter))
 		hw_features |= NETIF_F_HW_TC;
+
 	if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO)
 		hw_features |= NETIF_F_GSO_UDP_L4;
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 1e543f6a7c30..7e810b65380c 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -142,6 +142,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_WB_ON_ITR |
 	       VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP |
+	       VIRTCHNL_VF_OFFLOAD_TC_U32 |
 	       VIRTCHNL_VF_OFFLOAD_VLAN_V2 |
 	       VIRTCHNL_VF_OFFLOAD_CRC |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
@@ -1961,8 +1962,8 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
 			 * list on PF is already cleared after a reset
 			 */
 			list_del(&f->list);
+			iavf_dec_fdir_active_fltr(adapter, f);
 			kfree(f);
-			adapter->fdir_active_fltr--;
 		}
 	}
 	spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -2135,8 +2136,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 						dev_err(&adapter->pdev->dev,
 							"%s\n", msg);
 					list_del(&fdir->list);
+					iavf_dec_fdir_active_fltr(adapter, fdir);
 					kfree(fdir);
-					adapter->fdir_active_fltr--;
 				}
 			}
 			spin_unlock_bh(&adapter->fdir_fltr_lock);
@@ -2451,8 +2452,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 					 list) {
 			if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) {
 				if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) {
-					dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n",
-						 fdir->loc);
+					if (!iavf_is_raw_fdir(fdir))
+						dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n",
+							 fdir->loc);
+					else
+						dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is added\n",
+							 TC_U32_USERHTID(fdir->cls_u32_handle));
 					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
 					fdir->flow_id = add_fltr->flow_id;
 				} else {
@@ -2460,8 +2465,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 						 add_fltr->status);
 					iavf_print_fdir_fltr(adapter, fdir);
 					list_del(&fdir->list);
+					iavf_dec_fdir_active_fltr(adapter, fdir);
 					kfree(fdir);
-					adapter->fdir_active_fltr--;
 				}
 			}
 		}
@@ -2479,11 +2484,15 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 				if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS ||
 				    del_fltr->status ==
 				    VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) {
-					dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n",
-						 fdir->loc);
+					if (!iavf_is_raw_fdir(fdir))
+						dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n",
+							 fdir->loc);
+					else
+						dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is deleted\n",
+							 TC_U32_USERHTID(fdir->cls_u32_handle));
 					list_del(&fdir->list);
+					iavf_dec_fdir_active_fltr(adapter, fdir);
 					kfree(fdir);
-					adapter->fdir_active_fltr--;
 				} else {
 					fdir->state = IAVF_FDIR_FLTR_ACTIVE;
 					dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n",
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 1c6ce0c4ed4e..59f62306b9cb 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -461,6 +461,10 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF;
 
+	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_TC_U32 &&
+	    vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_FDIR_PF)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_TC_U32;
+
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
 
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 4f78a65e33dc..f41395264dca 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -247,6 +247,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 /* used to negotiate communicating link speeds in Mbps */
 #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED		BIT(7)
 #define  VIRTCHNL_VF_OFFLOAD_CRC		BIT(10)
+#define VIRTCHNL_VF_OFFLOAD_TC_U32		BIT(11)
 #define VIRTCHNL_VF_OFFLOAD_VLAN_V2		BIT(15)
 #define VIRTCHNL_VF_OFFLOAD_VLAN		BIT(16)
 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING		BIT(17)
-- 
cgit v1.3-3-g829e


From baae8b0ba8352f2b93346cc1e33ca115152cf22c Mon Sep 17 00:00:00 2001
From: Jing-Ping Jan <zoo868e@gmail.com>
Date: Tue, 13 Aug 2024 01:09:10 +0800
Subject: Documentation: networking: correct spelling

Correct spelling problems for Documentation/networking/ as reported
by ispell.

Signed-off-by: Jing-Ping Jan <zoo868e@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240812170910.5760-1-zoo868e@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ethtool-netlink.rst | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 82c5542c80ce..3f6c6880e7c4 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -934,18 +934,18 @@ Request contents:
   ====================================  ======  ===========================
 
 Kernel checks that requested ring sizes do not exceed limits reported by
-driver. Driver may impose additional constraints and may not suspport all
+driver. Driver may impose additional constraints and may not support all
 attributes.
 
 
 ``ETHTOOL_A_RINGS_CQE_SIZE`` specifies the completion queue event size.
-Completion queue events(CQE) are the events posted by NIC to indicate the
-completion status of a packet when the packet is sent(like send success or
-error) or received(like pointers to packet fragments). The CQE size parameter
+Completion queue events (CQE) are the events posted by NIC to indicate the
+completion status of a packet when the packet is sent (like send success or
+error) or received (like pointers to packet fragments). The CQE size parameter
 enables to modify the CQE size other than default size if NIC supports it.
-A bigger CQE can have more receive buffer pointers inturn NIC can transfer
-a bigger frame from wire. Based on the NIC hardware, the overall completion
-queue size can be adjusted in the driver if CQE size is modified.
+A bigger CQE can have more receive buffer pointers, and in turn the NIC can
+transfer a bigger frame from wire. Based on the NIC hardware, the overall
+completion queue size can be adjusted in the driver if CQE size is modified.
 
 CHANNELS_GET
 ============
@@ -989,7 +989,7 @@ Request contents:
   =====================================  ======  ==========================
 
 Kernel checks that requested channel counts do not exceed limits reported by
-driver. Driver may impose additional constraints and may not suspport all
+driver. Driver may impose additional constraints and may not support all
 attributes.
 
 
@@ -1935,7 +1935,7 @@ When set, the optional ``ETHTOOL_A_PLCA_VERSION`` attribute indicates which
 standard and version the PLCA management interface complies to. When not set,
 the interface is vendor-specific and (possibly) supplied by the driver.
 The OPEN Alliance SIG specifies a standard register map for 10BASE-T1S PHYs
-embedding the PLCA Reconcialiation Sublayer. See "10BASE-T1S PLCA Management
+embedding the PLCA Reconciliation Sublayer. See "10BASE-T1S PLCA Management
 Registers" at https://www.opensig.org/about/specifications/.
 
 When set, the optional ``ETHTOOL_A_PLCA_ENABLED`` attribute indicates the
@@ -1997,7 +1997,7 @@ Request contents:
   ``ETHTOOL_A_PLCA_ENABLED``              u8      PLCA Admin State
   ``ETHTOOL_A_PLCA_NODE_ID``              u8      PLCA unique local node ID
   ``ETHTOOL_A_PLCA_NODE_CNT``             u8      Number of PLCA nodes on the
-                                                  netkork, including the
+                                                  network, including the
                                                   coordinator
   ``ETHTOOL_A_PLCA_TO_TMR``               u8      Transmit Opportunity Timer
                                                   value in bit-times (BT)
-- 
cgit v1.3-3-g829e


From be034ee6c33dcd7c8dc7160266acb50c897cc2ea Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Sun, 11 Aug 2024 14:40:49 -0400
Subject: dt-bindings: net: fsl,qoriq-mc-dpmac: using unevaluatedProperties

Replace additionalProperties with unevaluatedProperties because it have
allOf: $ref: ethernet-controller.yaml#.

Remove all properties, which already defined in ethernet-controller.yaml.

Fixed below CHECK_DTBS warnings:
arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dtb:
   fsl-mc@80c000000: dpmacs:ethernet@11: 'fixed-link' does not match any of the regexes: 'pinctrl-[0-9]+'
        from schema $id: http://devicetree.org/schemas/misc/fsl,qoriq-mc.yaml#

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20240811184049.3759195-1-Frank.Li@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
index a1b71b35319e..f19c4fa66f18 100644
--- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml
@@ -24,24 +24,16 @@ properties:
     maxItems: 1
     description: The DPMAC number
 
-  phy-handle: true
-
-  phy-connection-type: true
-
-  phy-mode: true
-
   pcs-handle:
     maxItems: 1
     description:
       A reference to a node representing a PCS PHY device found on
       the internal MDIO bus.
 
-  managed: true
-
 required:
   - reg
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
-- 
cgit v1.3-3-g829e


From 92ec8b9367ab328cdd3d4409464137bc9775a2e5 Mon Sep 17 00:00:00 2001
From: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Date: Thu, 8 Aug 2024 07:59:02 +0000
Subject: selftests/bpf: Avoid subtraction after htons() in ipip tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On little-endian systems, doing subtraction after htons()
leads to interesting results:

Given:
  MAGIC_BYTES = 123 = 0x007B aka. in big endian: 0x7B00 = 31488
  sizeof(struct iphdr) = 20

Before this patch:
__bpf_constant_htons(MAGIC_BYTES) - sizeof(struct iphdr) = 0x7AEC
0x7AEC = htons(0xEC7A) = htons(60538)

So these were outer IP packets with a total length of 123 bytes,
containing an inner IP packet with a total length of 60538 bytes.

After this patch:
__bpf_constant_htons(MAGIC_BYTES - sizeof(struct iphdr)) = htons(103)

Now these packets are outer IP packets with a total length of 123 bytes,
containing an inner IP packet with a total length of 103 bytes.

Signed-off-by: Asbjørn Sloth Tønnesen <ast@fiberby.net>
Reviewed-by: Toke Høiland-Jørgensen <toke@kernel.org>
Link: https://lore.kernel.org/r/20240808075906.1849564-1-ast@fiberby.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/flow_dissector.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 9e5f38739104..6b3078dd5645 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -378,8 +378,8 @@ struct test tests[] = {
 			.iph_inner.ihl = 5,
 			.iph_inner.protocol = IPPROTO_TCP,
 			.iph_inner.tot_len =
-				__bpf_constant_htons(MAGIC_BYTES) -
-				sizeof(struct iphdr),
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
 			.tcp.doff = 5,
 			.tcp.source = 80,
 			.tcp.dest = 8080,
@@ -407,8 +407,8 @@ struct test tests[] = {
 			.iph_inner.ihl = 5,
 			.iph_inner.protocol = IPPROTO_TCP,
 			.iph_inner.tot_len =
-				__bpf_constant_htons(MAGIC_BYTES) -
-				sizeof(struct iphdr),
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
 			.tcp.doff = 5,
 			.tcp.source = 80,
 			.tcp.dest = 8080,
@@ -436,8 +436,8 @@ struct test tests[] = {
 			.iph_inner.ihl = 5,
 			.iph_inner.protocol = IPPROTO_TCP,
 			.iph_inner.tot_len =
-				__bpf_constant_htons(MAGIC_BYTES) -
-				sizeof(struct iphdr),
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
 			.tcp.doff = 5,
 			.tcp.source = 99,
 			.tcp.dest = 9090,
-- 
cgit v1.3-3-g829e


From 58c98d0cd4f8899f517ba1f0255d2aac7666a002 Mon Sep 17 00:00:00 2001
From: Ziwei Xiao <ziweixiao@google.com>
Date: Mon, 12 Aug 2024 15:20:12 -0700
Subject: gve: Add RSS device option

Add a device option to inform the driver about the hash key size and
hash table size used by the device. This information will be stored and
made available for RSS ethtool operations.

Signed-off-by: Ziwei Xiao <ziweixiao@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240812222013.1503584-2-pkaligineedi@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve.h        |  3 +++
 drivers/net/ethernet/google/gve/gve_adminq.c | 36 ++++++++++++++++++++++++++--
 drivers/net/ethernet/google/gve/gve_adminq.h | 15 +++++++++++-
 3 files changed, 51 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 84ac004d3953..6c21f3c53619 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -831,6 +831,9 @@ struct gve_priv {
 	u32 num_flow_rules;
 
 	struct gve_flow_rules_cache flow_rules_cache;
+
+	u16 rss_key_size;
+	u16 rss_lut_size;
 };
 
 enum gve_service_task_flags_bit {
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index c5bbc1b7524e..b5c801d2f8b5 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -45,6 +45,7 @@ void gve_parse_device_option(struct gve_priv *priv,
 			     struct gve_device_option_dqo_qpl **dev_op_dqo_qpl,
 			     struct gve_device_option_buffer_sizes **dev_op_buffer_sizes,
 			     struct gve_device_option_flow_steering **dev_op_flow_steering,
+			     struct gve_device_option_rss_config **dev_op_rss_config,
 			     struct gve_device_option_modify_ring **dev_op_modify_ring)
 {
 	u32 req_feat_mask = be32_to_cpu(option->required_features_mask);
@@ -207,6 +208,23 @@ void gve_parse_device_option(struct gve_priv *priv,
 				 "Flow Steering");
 		*dev_op_flow_steering = (void *)(option + 1);
 		break;
+	case GVE_DEV_OPT_ID_RSS_CONFIG:
+		if (option_length < sizeof(**dev_op_rss_config) ||
+		    req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG) {
+			dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT,
+				 "RSS config",
+				 (int)sizeof(**dev_op_rss_config),
+				 GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG,
+				 option_length, req_feat_mask);
+			break;
+		}
+
+		if (option_length > sizeof(**dev_op_rss_config))
+			dev_warn(&priv->pdev->dev,
+				 GVE_DEVICE_OPTION_TOO_BIG_FMT,
+				 "RSS config");
+		*dev_op_rss_config = (void *)(option + 1);
+		break;
 	default:
 		/* If we don't recognize the option just continue
 		 * without doing anything.
@@ -227,6 +245,7 @@ gve_process_device_options(struct gve_priv *priv,
 			   struct gve_device_option_dqo_qpl **dev_op_dqo_qpl,
 			   struct gve_device_option_buffer_sizes **dev_op_buffer_sizes,
 			   struct gve_device_option_flow_steering **dev_op_flow_steering,
+			   struct gve_device_option_rss_config **dev_op_rss_config,
 			   struct gve_device_option_modify_ring **dev_op_modify_ring)
 {
 	const int num_options = be16_to_cpu(descriptor->num_device_options);
@@ -249,7 +268,8 @@ gve_process_device_options(struct gve_priv *priv,
 					dev_op_gqi_rda, dev_op_gqi_qpl,
 					dev_op_dqo_rda, dev_op_jumbo_frames,
 					dev_op_dqo_qpl, dev_op_buffer_sizes,
-					dev_op_flow_steering, dev_op_modify_ring);
+					dev_op_flow_steering, dev_op_rss_config,
+					dev_op_modify_ring);
 		dev_opt = next_opt;
 	}
 
@@ -867,6 +887,8 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 					  *dev_op_buffer_sizes,
 					  const struct gve_device_option_flow_steering
 					  *dev_op_flow_steering,
+					  const struct gve_device_option_rss_config
+					  *dev_op_rss_config,
 					  const struct gve_device_option_modify_ring
 					  *dev_op_modify_ring)
 {
@@ -931,6 +953,14 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 				 priv->max_flow_rules);
 		}
 	}
+
+	if (dev_op_rss_config &&
+	    (supported_features_mask & GVE_SUP_RSS_CONFIG_MASK)) {
+		priv->rss_key_size =
+			be16_to_cpu(dev_op_rss_config->hash_key_size);
+		priv->rss_lut_size =
+			be16_to_cpu(dev_op_rss_config->hash_lut_size);
+	}
 }
 
 int gve_adminq_describe_device(struct gve_priv *priv)
@@ -939,6 +969,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL;
 	struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL;
 	struct gve_device_option_modify_ring *dev_op_modify_ring = NULL;
+	struct gve_device_option_rss_config *dev_op_rss_config = NULL;
 	struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL;
 	struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL;
 	struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL;
@@ -973,6 +1004,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 					 &dev_op_jumbo_frames, &dev_op_dqo_qpl,
 					 &dev_op_buffer_sizes,
 					 &dev_op_flow_steering,
+					 &dev_op_rss_config,
 					 &dev_op_modify_ring);
 	if (err)
 		goto free_device_descriptor;
@@ -1035,7 +1067,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	gve_enable_supported_features(priv, supported_features_mask,
 				      dev_op_jumbo_frames, dev_op_dqo_qpl,
 				      dev_op_buffer_sizes, dev_op_flow_steering,
-				      dev_op_modify_ring);
+				      dev_op_rss_config, dev_op_modify_ring);
 
 free_device_descriptor:
 	dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index ed1370c9b197..7d9ef9a12fef 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -164,6 +164,14 @@ struct gve_device_option_flow_steering {
 
 static_assert(sizeof(struct gve_device_option_flow_steering) == 12);
 
+struct gve_device_option_rss_config {
+	__be32 supported_features_mask;
+	__be16 hash_key_size;
+	__be16 hash_lut_size;
+};
+
+static_assert(sizeof(struct gve_device_option_rss_config) == 8);
+
 /* Terminology:
  *
  * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA
@@ -182,6 +190,7 @@ enum gve_dev_opt_id {
 	GVE_DEV_OPT_ID_JUMBO_FRAMES		= 0x8,
 	GVE_DEV_OPT_ID_BUFFER_SIZES		= 0xa,
 	GVE_DEV_OPT_ID_FLOW_STEERING		= 0xb,
+	GVE_DEV_OPT_ID_RSS_CONFIG		= 0xe,
 };
 
 enum gve_dev_opt_req_feat_mask {
@@ -194,6 +203,7 @@ enum gve_dev_opt_req_feat_mask {
 	GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES		= 0x0,
 	GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING		= 0x0,
 	GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING		= 0x0,
+	GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG		= 0x0,
 };
 
 enum gve_sup_feature_mask {
@@ -201,6 +211,7 @@ enum gve_sup_feature_mask {
 	GVE_SUP_JUMBO_FRAMES_MASK	= 1 << 2,
 	GVE_SUP_BUFFER_SIZES_MASK	= 1 << 4,
 	GVE_SUP_FLOW_STEERING_MASK	= 1 << 5,
+	GVE_SUP_RSS_CONFIG_MASK		= 1 << 7,
 };
 
 #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0
@@ -214,6 +225,7 @@ enum gve_driver_capbility {
 	gve_driver_capability_dqo_rda = 3,
 	gve_driver_capability_alt_miss_compl = 4,
 	gve_driver_capability_flexible_buffer_size = 5,
+	gve_driver_capability_flexible_rss_size = 6,
 };
 
 #define GVE_CAP1(a) BIT((int)a)
@@ -226,7 +238,8 @@ enum gve_driver_capbility {
 	 GVE_CAP1(gve_driver_capability_gqi_rda) | \
 	 GVE_CAP1(gve_driver_capability_dqo_rda) | \
 	 GVE_CAP1(gve_driver_capability_alt_miss_compl) | \
-	 GVE_CAP1(gve_driver_capability_flexible_buffer_size))
+	 GVE_CAP1(gve_driver_capability_flexible_buffer_size) | \
+	 GVE_CAP1(gve_driver_capability_flexible_rss_size))
 
 #define GVE_DRIVER_CAPABILITY_FLAGS2 0x0
 #define GVE_DRIVER_CAPABILITY_FLAGS3 0x0
-- 
cgit v1.3-3-g829e


From fa46c456fa6ecc409cec43ac534b1a156bcef7b2 Mon Sep 17 00:00:00 2001
From: Jeroen de Borst <jeroendb@google.com>
Date: Mon, 12 Aug 2024 15:20:13 -0700
Subject: gve: Add RSS adminq commands and ethtool support

Introduce adminq commands to configure and retrieve RSS settings from
the device. Implement corresponding ethtool ops for user-level
management.

Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Co-developed-by: Ziwei Xiao <ziweixiao@google.com>
Signed-off-by: Ziwei Xiao <ziweixiao@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://patch.msgid.link/20240812222013.1503584-3-pkaligineedi@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve.h         |   2 +
 drivers/net/ethernet/google/gve/gve_adminq.c  | 146 ++++++++++++++++++++++++++
 drivers/net/ethernet/google/gve/gve_adminq.h  |  44 ++++++++
 drivers/net/ethernet/google/gve/gve_ethtool.c |  44 +++++++-
 4 files changed, 235 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 6c21f3c53619..09a85ed59143 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -784,6 +784,8 @@ struct gve_priv {
 	u32 adminq_verify_driver_compatibility_cnt;
 	u32 adminq_query_flow_rules_cnt;
 	u32 adminq_cfg_flow_rule_cnt;
+	u32 adminq_cfg_rss_cnt;
+	u32 adminq_query_rss_cnt;
 
 	/* Global stats */
 	u32 interface_up_cnt; /* count of times interface turned up since last reset */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index b5c801d2f8b5..e44e8b139633 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -309,6 +309,8 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
 	priv->adminq_get_ptype_map_cnt = 0;
 	priv->adminq_query_flow_rules_cnt = 0;
 	priv->adminq_cfg_flow_rule_cnt = 0;
+	priv->adminq_cfg_rss_cnt = 0;
+	priv->adminq_query_rss_cnt = 0;
 
 	/* Setup Admin queue with the device */
 	if (priv->pdev->revision < 0x1) {
@@ -554,6 +556,12 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 	case GVE_ADMINQ_CONFIGURE_FLOW_RULE:
 		priv->adminq_cfg_flow_rule_cnt++;
 		break;
+	case GVE_ADMINQ_CONFIGURE_RSS:
+		priv->adminq_cfg_rss_cnt++;
+		break;
+	case GVE_ADMINQ_QUERY_RSS:
+		priv->adminq_query_rss_cnt++;
+		break;
 	default:
 		dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode);
 	}
@@ -1280,6 +1288,81 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv)
 	return gve_adminq_configure_flow_rule(priv, &flow_rule_cmd);
 }
 
+int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh)
+{
+	dma_addr_t lut_bus = 0, key_bus = 0;
+	u16 key_size = 0, lut_size = 0;
+	union gve_adminq_command cmd;
+	__be32 *lut = NULL;
+	u8 hash_alg = 0;
+	u8 *key = NULL;
+	int err = 0;
+	u16 i;
+
+	switch (rxfh->hfunc) {
+	case ETH_RSS_HASH_NO_CHANGE:
+		break;
+	case ETH_RSS_HASH_TOP:
+		hash_alg = ETH_RSS_HASH_TOP;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (rxfh->indir) {
+		lut_size = priv->rss_lut_size;
+		lut = dma_alloc_coherent(&priv->pdev->dev,
+					 lut_size * sizeof(*lut),
+					 &lut_bus, GFP_KERNEL);
+		if (!lut)
+			return -ENOMEM;
+
+		for (i = 0; i < priv->rss_lut_size; i++)
+			lut[i] = cpu_to_be32(rxfh->indir[i]);
+	}
+
+	if (rxfh->key) {
+		key_size = priv->rss_key_size;
+		key = dma_alloc_coherent(&priv->pdev->dev,
+					 key_size, &key_bus, GFP_KERNEL);
+		if (!key) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		memcpy(key, rxfh->key, key_size);
+	}
+
+	/* Zero-valued fields in the cmd.configure_rss instruct the device to
+	 * not update those fields.
+	 */
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CONFIGURE_RSS);
+	cmd.configure_rss = (struct gve_adminq_configure_rss) {
+		.hash_types = cpu_to_be16(BIT(GVE_RSS_HASH_TCPV4) |
+					  BIT(GVE_RSS_HASH_UDPV4) |
+					  BIT(GVE_RSS_HASH_TCPV6) |
+					  BIT(GVE_RSS_HASH_UDPV6)),
+		.hash_alg = hash_alg,
+		.hash_key_size = cpu_to_be16(key_size),
+		.hash_lut_size = cpu_to_be16(lut_size),
+		.hash_key_addr = cpu_to_be64(key_bus),
+		.hash_lut_addr = cpu_to_be64(lut_bus),
+	};
+
+	err = gve_adminq_execute_cmd(priv, &cmd);
+
+out:
+	if (lut)
+		dma_free_coherent(&priv->pdev->dev,
+				  lut_size * sizeof(*lut),
+				  lut, lut_bus);
+	if (key)
+		dma_free_coherent(&priv->pdev->dev,
+				  key_size, key, key_bus);
+	return err;
+}
+
 /* In the dma memory that the driver allocated for the device to query the flow rules, the device
  * will first write it with a struct of gve_query_flow_rules_descriptor. Next to it, the device
  * will write an array of rules or rule ids with the count that specified in the descriptor.
@@ -1357,3 +1440,66 @@ out:
 	dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
 	return err;
 }
+
+static int gve_adminq_process_rss_query(struct gve_priv *priv,
+					struct gve_query_rss_descriptor *descriptor,
+					struct ethtool_rxfh_param *rxfh)
+{
+	u32 total_memory_length;
+	u16 hash_lut_length;
+	void *rss_info_addr;
+	__be32 *lut;
+	u16 i;
+
+	total_memory_length = be32_to_cpu(descriptor->total_length);
+	hash_lut_length = priv->rss_lut_size * sizeof(*rxfh->indir);
+
+	if (sizeof(*descriptor) + priv->rss_key_size + hash_lut_length != total_memory_length) {
+		dev_err(&priv->dev->dev,
+			"rss query desc from device has invalid length parameter.\n");
+		return -EINVAL;
+	}
+
+	rxfh->hfunc = descriptor->hash_alg;
+
+	rss_info_addr = (void *)(descriptor + 1);
+	if (rxfh->key)
+		memcpy(rxfh->key, rss_info_addr, priv->rss_key_size);
+
+	rss_info_addr += priv->rss_key_size;
+	lut = (__be32 *)rss_info_addr;
+	if (rxfh->indir) {
+		for (i = 0; i < priv->rss_lut_size; i++)
+			rxfh->indir[i] = be32_to_cpu(lut[i]);
+	}
+
+	return 0;
+}
+
+int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_query_rss_descriptor *descriptor;
+	union gve_adminq_command cmd;
+	dma_addr_t descriptor_bus;
+	int err = 0;
+
+	descriptor = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL, &descriptor_bus);
+	if (!descriptor)
+		return -ENOMEM;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_QUERY_RSS);
+	cmd.query_rss = (struct gve_adminq_query_rss) {
+		.available_length = cpu_to_be64(GVE_ADMINQ_BUFFER_SIZE),
+		.rss_descriptor_addr = cpu_to_be64(descriptor_bus),
+	};
+	err = gve_adminq_execute_cmd(priv, &cmd);
+	if (err)
+		goto out;
+
+	err = gve_adminq_process_rss_query(priv, descriptor, rxfh);
+
+out:
+	dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus);
+	return err;
+}
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 7d9ef9a12fef..863683de9694 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -20,12 +20,14 @@ enum gve_adminq_opcodes {
 	GVE_ADMINQ_DESTROY_TX_QUEUE		= 0x7,
 	GVE_ADMINQ_DESTROY_RX_QUEUE		= 0x8,
 	GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES	= 0x9,
+	GVE_ADMINQ_CONFIGURE_RSS		= 0xA,
 	GVE_ADMINQ_SET_DRIVER_PARAMETER		= 0xB,
 	GVE_ADMINQ_REPORT_STATS			= 0xC,
 	GVE_ADMINQ_REPORT_LINK_SPEED		= 0xD,
 	GVE_ADMINQ_GET_PTYPE_MAP		= 0xE,
 	GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY	= 0xF,
 	GVE_ADMINQ_QUERY_FLOW_RULES		= 0x10,
+	GVE_ADMINQ_QUERY_RSS			= 0x12,
 
 	/* For commands that are larger than 56 bytes */
 	GVE_ADMINQ_EXTENDED_COMMAND		= 0xFF,
@@ -522,6 +524,44 @@ struct gve_adminq_query_flow_rules {
 
 static_assert(sizeof(struct gve_adminq_query_flow_rules) == 24);
 
+enum gve_rss_hash_type {
+	GVE_RSS_HASH_IPV4,
+	GVE_RSS_HASH_TCPV4,
+	GVE_RSS_HASH_IPV6,
+	GVE_RSS_HASH_IPV6_EX,
+	GVE_RSS_HASH_TCPV6,
+	GVE_RSS_HASH_TCPV6_EX,
+	GVE_RSS_HASH_UDPV4,
+	GVE_RSS_HASH_UDPV6,
+	GVE_RSS_HASH_UDPV6_EX,
+};
+
+struct gve_adminq_configure_rss {
+	__be16 hash_types;
+	u8 hash_alg;
+	u8 reserved;
+	__be16 hash_key_size;
+	__be16 hash_lut_size;
+	__be64 hash_key_addr;
+	__be64 hash_lut_addr;
+};
+
+static_assert(sizeof(struct gve_adminq_configure_rss) == 24);
+
+struct gve_query_rss_descriptor {
+	__be32 total_length;
+	__be16 hash_types;
+	u8 hash_alg;
+	u8 reserved;
+};
+
+struct gve_adminq_query_rss {
+	__be64 available_length;
+	__be64 rss_descriptor_addr;
+};
+
+static_assert(sizeof(struct gve_adminq_query_rss) == 16);
+
 union gve_adminq_command {
 	struct {
 		__be32 opcode;
@@ -543,6 +583,8 @@ union gve_adminq_command {
 			struct gve_adminq_verify_driver_compatibility
 						verify_driver_compatibility;
 			struct gve_adminq_query_flow_rules query_flow_rules;
+			struct gve_adminq_configure_rss configure_rss;
+			struct gve_adminq_query_rss query_rss;
 			struct gve_adminq_extended_command extended_command;
 		};
 	};
@@ -581,6 +623,8 @@ int gve_adminq_add_flow_rule(struct gve_priv *priv, struct gve_adminq_flow_rule
 int gve_adminq_del_flow_rule(struct gve_priv *priv, u32 loc);
 int gve_adminq_reset_flow_rules(struct gve_priv *priv);
 int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc);
+int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh);
+int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh);
 
 struct gve_ptype_lut;
 int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv,
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index 5a8b490ab3ad..bdfc6e77b2af 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -75,7 +75,8 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
 	"adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt",
 	"adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt",
 	"adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt",
-	"adminq_query_flow_rules", "adminq_cfg_flow_rule",
+	"adminq_query_flow_rules", "adminq_cfg_flow_rule", "adminq_cfg_rss_cnt",
+	"adminq_query_rss_cnt",
 };
 
 static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = {
@@ -453,6 +454,8 @@ gve_get_ethtool_stats(struct net_device *netdev,
 	data[i++] = priv->adminq_get_ptype_map_cnt;
 	data[i++] = priv->adminq_query_flow_rules_cnt;
 	data[i++] = priv->adminq_cfg_flow_rule_cnt;
+	data[i++] = priv->adminq_cfg_rss_cnt;
+	data[i++] = priv->adminq_query_rss_cnt;
 }
 
 static void gve_get_channels(struct net_device *netdev,
@@ -838,6 +841,41 @@ static int gve_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u
 	return err;
 }
 
+static u32 gve_get_rxfh_key_size(struct net_device *netdev)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	return priv->rss_key_size;
+}
+
+static u32 gve_get_rxfh_indir_size(struct net_device *netdev)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	return priv->rss_lut_size;
+}
+
+static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	if (!priv->rss_key_size || !priv->rss_lut_size)
+		return -EOPNOTSUPP;
+
+	return gve_adminq_query_rss_config(priv, rxfh);
+}
+
+static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
+			struct netlink_ext_ack *extack)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	if (!priv->rss_key_size || !priv->rss_lut_size)
+		return -EOPNOTSUPP;
+
+	return gve_adminq_configure_rss(priv, rxfh);
+}
+
 const struct ethtool_ops gve_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS,
 	.supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT,
@@ -851,6 +889,10 @@ const struct ethtool_ops gve_ethtool_ops = {
 	.get_channels = gve_get_channels,
 	.set_rxnfc = gve_set_rxnfc,
 	.get_rxnfc = gve_get_rxnfc,
+	.get_rxfh_indir_size = gve_get_rxfh_indir_size,
+	.get_rxfh_key_size = gve_get_rxfh_key_size,
+	.get_rxfh = gve_get_rxfh,
+	.set_rxfh = gve_set_rxfh,
 	.get_link = ethtool_op_get_link,
 	.get_coalesce = gve_get_coalesce,
 	.set_coalesce = gve_set_coalesce,
-- 
cgit v1.3-3-g829e


From ed4290f39f417793928630e85c26411db233d841 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 10 Aug 2024 23:39:04 +0200
Subject: net: netconsole: Constify struct config_item_type

'struct config_item_type' is not modified in this driver.

This structure is only used with config_group_init_type_name() which takes
a const struct config_item_type* as a 3rd argument.

This also makes things consistent with 'netconsole_target_type' witch is
already const.

Constifying this structure moves some data to a read-only section, so
increase overall security, especially when the structure holds some
function pointers.

On a x86_64, with allmodconfig:
Before:
======
   text	   data	    bss	    dec	    hex	filename
  33007	   3952	   1312	  38271	   957f	drivers/net/netconsole.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
  33071	   3888	   1312	  38271	   957f	drivers/net/netconsole.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/9c205b2b4bdb09fc9e9d2cb2f2936ec053da1b1b.1723325900.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 43c29b15adbf..72384c1ecc5c 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -825,7 +825,7 @@ static struct configfs_group_operations userdata_ops = {
 	.drop_item		= userdatum_drop,
 };
 
-static struct config_item_type userdata_type = {
+static const struct config_item_type userdata_type = {
 	.ct_item_ops	= &userdatum_ops,
 	.ct_group_ops	= &userdata_ops,
 	.ct_attrs	= userdata_attrs,
-- 
cgit v1.3-3-g829e


From 4374a1fe580a14f6152752390c678d90311df247 Mon Sep 17 00:00:00 2001
From: "Csókás, Bence" <csokas.bence@prolan.hu>
Date: Mon, 12 Aug 2024 11:47:13 +0200
Subject: net: fec: Move `fec_ptp_read()` to the top of the file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This function is used in `fec_ptp_enable_pps()` through
struct cyclecounter read(). Moving the declaration makes
it clearer, what's happening.

Suggested-by: Frank Li <Frank.li@nxp.com>
Link: https://lore.kernel.org/netdev/20240805144754.2384663-1-csokas.bence@prolan.hu/T/#ma6c21ad264016c24612048b1483769eaff8cdf20
Signed-off-by: Csókás, Bence <csokas.bence@prolan.hu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240812094713.2883476-1-csokas.bence@prolan.hu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_ptp.c | 50 ++++++++++++++++----------------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 2e4f3e1782a2..7f4ccd1ade5b 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -90,6 +90,30 @@
 #define FEC_PTP_MAX_NSEC_PERIOD		4000000000ULL
 #define FEC_PTP_MAX_NSEC_COUNTER	0x80000000ULL
 
+/**
+ * fec_ptp_read - read raw cycle counter (to be used by time counter)
+ * @cc: the cyclecounter structure
+ *
+ * this function reads the cyclecounter registers and is called by the
+ * cyclecounter structure used to construct a ns counter from the
+ * arbitrary fixed point registers
+ */
+static u64 fec_ptp_read(const struct cyclecounter *cc)
+{
+	struct fec_enet_private *fep =
+		container_of(cc, struct fec_enet_private, cc);
+	u32 tempval;
+
+	tempval = readl(fep->hwp + FEC_ATIME_CTRL);
+	tempval |= FEC_T_CTRL_CAPTURE;
+	writel(tempval, fep->hwp + FEC_ATIME_CTRL);
+
+	if (fep->quirks & FEC_QUIRK_BUG_CAPTURE)
+		udelay(1);
+
+	return readl(fep->hwp + FEC_ATIME);
+}
+
 /**
  * fec_ptp_enable_pps
  * @fep: the fec_enet_private structure handle
@@ -136,7 +160,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 		 * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds
 		 * to current timer would be next second.
 		 */
-		tempval = fep->cc.read(&fep->cc);
+		tempval = fec_ptp_read(&fep->cc);
 		/* Convert the ptp local counter to 1588 timestamp */
 		ns = timecounter_cyc2time(&fep->tc, tempval);
 		ts = ns_to_timespec64(ns);
@@ -271,30 +295,6 @@ static enum hrtimer_restart fec_ptp_pps_perout_handler(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-/**
- * fec_ptp_read - read raw cycle counter (to be used by time counter)
- * @cc: the cyclecounter structure
- *
- * this function reads the cyclecounter registers and is called by the
- * cyclecounter structure used to construct a ns counter from the
- * arbitrary fixed point registers
- */
-static u64 fec_ptp_read(const struct cyclecounter *cc)
-{
-	struct fec_enet_private *fep =
-		container_of(cc, struct fec_enet_private, cc);
-	u32 tempval;
-
-	tempval = readl(fep->hwp + FEC_ATIME_CTRL);
-	tempval |= FEC_T_CTRL_CAPTURE;
-	writel(tempval, fep->hwp + FEC_ATIME_CTRL);
-
-	if (fep->quirks & FEC_QUIRK_BUG_CAPTURE)
-		udelay(1);
-
-	return readl(fep->hwp + FEC_ATIME);
-}
-
 /**
  * fec_ptp_start_cyclecounter - create the cycle counter from hw
  * @ndev: network device
-- 
cgit v1.3-3-g829e


From 713ebaed68d88121cbaf5e74104e2290a9ea74bd Mon Sep 17 00:00:00 2001
From: "Csókás, Bence" <csokas.bence@prolan.hu>
Date: Mon, 12 Aug 2024 11:47:15 +0200
Subject: net: fec: Remove duplicated code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

`fec_ptp_pps_perout()` reimplements logic already
in `fec_ptp_read()`. Replace with function call.

Signed-off-by: Csókás, Bence <csokas.bence@prolan.hu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240812094713.2883476-2-csokas.bence@prolan.hu
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_ptp.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7f4ccd1ade5b..4cffda363a14 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -235,13 +235,7 @@ static int fec_ptp_pps_perout(struct fec_enet_private *fep)
 	timecounter_read(&fep->tc);
 
 	/* Get the current ptp hardware time counter */
-	temp_val = readl(fep->hwp + FEC_ATIME_CTRL);
-	temp_val |= FEC_T_CTRL_CAPTURE;
-	writel(temp_val, fep->hwp + FEC_ATIME_CTRL);
-	if (fep->quirks & FEC_QUIRK_BUG_CAPTURE)
-		udelay(1);
-
-	ptp_hc = readl(fep->hwp + FEC_ATIME);
+	ptp_hc = fec_ptp_read(&fep->cc);
 
 	/* Convert the ptp local counter to 1588 timestamp */
 	curr_time = timecounter_cyc2time(&fep->tc, ptp_hc);
-- 
cgit v1.3-3-g829e


From 29cabacef1024b39506d3acd18cb2e558832bbaf Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Mon, 12 Aug 2024 12:24:13 +0100
Subject: net: mvneta: Use __be16 for l3_proto parameter of
 mvneta_txq_desc_csum()

The value passed as the l3_proto argument of mvneta_txq_desc_csum()
is __be16. And mvneta_txq_desc_csum uses this parameter as a __be16
value. So use __be16 as the type for the parameter, rather than
type with host byte order.

Flagged by Sparse as:

 .../mvneta.c:1796:25: warning: restricted __be16 degrades to integer
 .../mvneta.c:1979:45: warning: incorrect type in argument 2 (different base types)
 .../mvneta.c:1979:45:    expected int l3_proto
 .../mvneta.c:1979:45:    got restricted __be16 [usertype] l3_proto

No functional change intended.
Flagged by Sparse.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Marcin Wojtas <marcin.s.wojtas@gmail.com>
Link: https://patch.msgid.link/20240812-mvneta-be16-v1-1-e1ea12234230@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/mvneta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 41894834fb53..d72b2d5f96db 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1781,7 +1781,7 @@ static int mvneta_txq_sent_desc_proc(struct mvneta_port *pp,
 }
 
 /* Set TXQ descriptors fields relevant for CSUM calculation */
-static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto,
+static u32 mvneta_txq_desc_csum(int l3_offs, __be16 l3_proto,
 				int ip_hdr_len, int l4_proto)
 {
 	u32 command;
-- 
cgit v1.3-3-g829e


From 712f585ab8b2cc2ff4e441b14a4907f764d78f2b Mon Sep 17 00:00:00 2001
From: Enguerrand de Ribaucourt <enguerrand.de-ribaucourt@savoirfairelinux.com>
Date: Mon, 12 Aug 2024 12:43:47 +0000
Subject: net: dsa: microchip: ksz9477: unwrap URL in comment

Keep the URL in a single line for easier copy-pasting.

Signed-off-by: Enguerrand de Ribaucourt <enguerrand.de-ribaucourt@savoirfairelinux.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240812124346.597702-1-enguerrand.de-ribaucourt@savoirfairelinux.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz9477.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 1e2293aa00dc..755de092b2c2 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -439,8 +439,7 @@ static int ksz9477_half_duplex_monitor(struct ksz_device *dev, int port,
 	 * half-duplex mode. The switch might not be able to communicate anymore
 	 * in these states. If you see this message, please read the
 	 * errata-sheet for more information:
-	 * https://ww1.microchip.com/downloads/aemDocuments/documents
-	 * /UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf
+	 * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf
 	 * To workaround this issue, half-duplex mode should be avoided.
 	 * A software reset could be implemented to recover from this state.
 	 */
-- 
cgit v1.3-3-g829e


From 2984e69a24affc8e5624069b7bb44593e09037e8 Mon Sep 17 00:00:00 2001
From: Moon Yeounsu <yyyynoom@gmail.com>
Date: Sat, 10 Aug 2024 23:15:02 +0900
Subject: net: ethernet: dlink: replace deprecated macro

Macro `SIMPLE_DEV_PM_OPS()` is deprecated.
This patch replaces `SIMPLE_DEV_PM_OPS()` with
`DEFINE_SIMPLE_DEV_PM_OPS()` currently used.

Expanded results are the same since remaining
member is initialized as zero (NULL):

static SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume);
Expanded to:
static const struct dev_pm_ops __attribute__((__unused__)) rio_pm_ops = {
	.suspend = ((1) ? ((rio_suspend)) : ((void *)0)),
	.resume = ((1) ? ((rio_resume)) : ((void *)0)),
	.freeze = ((1) ? ((rio_suspend)) : ((void *)0)),
	.thaw = ((1) ? ((rio_resume)) : ((void *)0)),
	.poweroff = ((1) ? ((rio_suspend)) : ((void *)0)),
	.restore = ((1) ? ((rio_resume)) : ((void *)0)),
};

static DEFINE_SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume);
Expanded to:
static const struct dev_pm_ops rio_pm_ops = {
	.suspend = ((1) ? ((rio_suspend)) : ((void *)0)),
	.resume = ((1) ? ((rio_resume)) : ((void *)0)),
	.freeze = ((1) ? ((rio_suspend)) : ((void *)0)),
	.thaw = ((1) ? ((rio_resume)) : ((void *)0)),
	.poweroff = ((1) ? ((rio_suspend)) : ((void *)0)),
	.restore = ((1) ? ((rio_resume)) : ((void *)0)),
	.runtime_suspend = ((void *)0),
	.runtime_resume = ((void *)0),
	.runtime_idle = ((void *)0),
};

Signed-off-by: Moon Yeounsu <yyyynoom@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/dlink/dl2k.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index 7bfeae04b52b..d0ea92607870 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -1842,7 +1842,7 @@ static int rio_resume(struct device *device)
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume);
 #define RIO_PM_OPS    (&rio_pm_ops)
 
 #else
-- 
cgit v1.3-3-g829e


From ffff7ee843c351ce71d6e0d52f0f20bea35e18c9 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 13 Aug 2024 15:32:55 +0100
Subject: bnxt_en: Extend maximum length of version string by 1 byte

This corrects an out-by-one error in the maximum length of the package
version string. The size argument of snprintf includes space for the
trailing '\0' byte, so there is no need to allow extra space for it by
reducing the value of the size argument by 1.

Found by inspection.
Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240813-bnxt-str-v2-1-872050a157e7@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 61d6afc3cacb..39eed5831e3a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -4161,7 +4161,7 @@ static void bnxt_get_pkgver(struct net_device *dev)
 
 	if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) {
 		len = strlen(bp->fw_ver_str);
-		snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1,
+		snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len,
 			 "/pkg %s", buf);
 	}
 }
-- 
cgit v1.3-3-g829e


From 1418e9ab3e2e2f3aad3b1f93e9e4472160132755 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 13 Aug 2024 15:32:56 +0100
Subject: bnxt_en: avoid truncation of per rx run debugfs filename

Although it seems unlikely in practice - there would need to be
rx ring indexes greater than 10^10 - it is theoretically possible
for the filename of per rx ring debugfs files to be truncated.

This is because although a 16 byte buffer is provided, the length
of the filename is restricted to 10 bytes. Remove this restriction
and allow the entire buffer to be used.

Also reduce the buffer to 12 bytes, which is sufficient.

Given that the range of rx ring indexes likely much smaller than the
maximum range of a 32-bit signed integer, a smaller buffer could be
used, with some further changes.  But this change seems simple, robust,
and has minimal stack overhead.

Flagged by gcc-14:

  .../bnxt_debugfs.c: In function 'bnxt_debug_dev_init':
  drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c:69:30: warning: '%d' directive output may be truncated writing between 1 and 11 bytes into a region of size 10 [-Wformat-truncation=]
     69 |         snprintf(qname, 10, "%d", ring_idx);
        |                              ^~
  In function 'debugfs_dim_ring_init',
      inlined from 'bnxt_debug_dev_init' at .../bnxt_debugfs.c:87:4:
  .../bnxt_debugfs.c:69:29: note: directive argument in the range [-2147483643, 2147483646]
     69 |         snprintf(qname, 10, "%d", ring_idx);
        |                             ^~~~
  .../bnxt_debugfs.c:69:9: note: 'snprintf' output between 2 and 12 bytes into a destination of size 10
     69 |         snprintf(qname, 10, "%d", ring_idx);
        |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Compile tested only

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240813-bnxt-str-v2-2-872050a157e7@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
index 156c2404854f..127b7015f676 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
@@ -64,9 +64,9 @@ static const struct file_operations debugfs_dim_fops = {
 static void debugfs_dim_ring_init(struct dim *dim, int ring_idx,
 				  struct dentry *dd)
 {
-	static char qname[16];
+	static char qname[12];
 
-	snprintf(qname, 10, "%d", ring_idx);
+	snprintf(qname, sizeof(qname), "%d", ring_idx);
 	debugfs_create_file(qname, 0600, dd, dim, &debugfs_dim_fops);
 }
 
-- 
cgit v1.3-3-g829e


From 216203bdc2280d8fc5baf60707eee2051de1426e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 13 Aug 2024 16:15:02 -0600
Subject: UAPI: net/sched: Use __struct_group() in flex struct tc_u32_sel

Use the `__struct_group()` helper to create a new tagged
`struct tc_u32_sel_hdr`. This structure groups together all the
members of the flexible `struct tc_u32_sel` except the flexible
array. As a result, the array is effectively separated from the
rest of the members without modifying the memory layout of the
flexible structure.

This new tagged struct will be used to fix problematic declarations
of middle-flex-arrays in composite structs[1].

[1] https://git.kernel.org/linus/d88cabfd9abc

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/e59fe833564ddc5b2cc83056a4c504be887d6193.1723586870.git.gustavoars@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/pkt_cls.h | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index d36d9cdf0c00..2c32080416b5 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -246,16 +246,19 @@ struct tc_u32_key {
 };
 
 struct tc_u32_sel {
-	unsigned char		flags;
-	unsigned char		offshift;
-	unsigned char		nkeys;
-
-	__be16			offmask;
-	__u16			off;
-	short			offoff;
-
-	short			hoff;
-	__be32			hmask;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(tc_u32_sel_hdr, hdr, /* no attrs */,
+		unsigned char		flags;
+		unsigned char		offshift;
+		unsigned char		nkeys;
+
+		__be16			offmask;
+		__u16			off;
+		short			offoff;
+
+		short			hoff;
+		__be32			hmask;
+	);
 	struct tc_u32_key	keys[];
 };
 
-- 
cgit v1.3-3-g829e


From 6c5cdabb3ec325f1846dad72f520814bbda79dca Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 13 Aug 2024 16:15:31 -0600
Subject: cxgb4: Avoid -Wflex-array-member-not-at-end warning

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Change the type of the middle struct member currently causing
trouble from `struct tc_u32_sel` to `struct tc_u32_sel_hdr`.

Fix the following warning:

drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h:245:27: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/97388e8a7990975aa56cf0ada211764c735c3432.1723586870.git.gustavoars@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
index 9050568a034c..64663112cad8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h
@@ -242,7 +242,7 @@ struct cxgb4_next_header {
 	 * field's value to jump to next header such as IHL field
 	 * in IPv4 header.
 	 */
-	struct tc_u32_sel sel;
+	struct tc_u32_sel_hdr sel;
 	struct tc_u32_key key;
 	/* location of jump to make */
 	const struct cxgb4_match_field *jump;
-- 
cgit v1.3-3-g829e


From 6274df2530e35193ebac311d492d276a73162b57 Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <quic_miaoqing@quicinc.com>
Date: Thu, 15 Aug 2024 19:03:22 +0300
Subject: wifi: ath12k: fix the stack frame size warning in
 ath12k_mac_op_hw_scan
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following W=1 kernel build warning:

drivers/net/wireless/ath/ath12k/mac.c: In function ‘ath12k_mac_op_hw_scan’:
drivers/net/wireless/ath/ath12k/mac.c:3806:1: warning: the frame size of 1040 bytes is larger than 1024 bytes [-Wframe-larger-than=]

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Miaoqing Pan <quic_miaoqing@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240809015841.2671448-1-quic_miaoqing@quicinc.com
---
 drivers/net/wireless/ath/ath12k/mac.c | 54 +++++++++++++++++++----------------
 1 file changed, 30 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index a7b86e6a2655..12cf2c17636b 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3663,7 +3663,7 @@ static int ath12k_mac_op_hw_scan(struct ieee80211_hw *hw,
 	struct ath12k *ar, *prev_ar;
 	struct ath12k_vif *arvif = ath12k_vif_to_arvif(vif);
 	struct cfg80211_scan_request *req = &hw_req->req;
-	struct ath12k_wmi_scan_req_arg arg = {};
+	struct ath12k_wmi_scan_req_arg *arg = NULL;
 	int ret;
 	int i;
 	bool create = true;
@@ -3745,42 +3745,47 @@ scan:
 	if (ret)
 		goto exit;
 
-	ath12k_wmi_start_scan_init(ar, &arg);
-	arg.vdev_id = arvif->vdev_id;
-	arg.scan_id = ATH12K_SCAN_ID;
+	arg = kzalloc(sizeof(*arg), GFP_KERNEL);
+	if (!arg) {
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	ath12k_wmi_start_scan_init(ar, arg);
+	arg->vdev_id = arvif->vdev_id;
+	arg->scan_id = ATH12K_SCAN_ID;
 
 	if (req->ie_len) {
-		arg.extraie.ptr = kmemdup(req->ie, req->ie_len, GFP_KERNEL);
-		if (!arg.extraie.ptr) {
+		arg->extraie.ptr = kmemdup(req->ie, req->ie_len, GFP_KERNEL);
+		if (!arg->extraie.ptr) {
 			ret = -ENOMEM;
 			goto exit;
 		}
-		arg.extraie.len = req->ie_len;
+		arg->extraie.len = req->ie_len;
 	}
 
 	if (req->n_ssids) {
-		arg.num_ssids = req->n_ssids;
-		for (i = 0; i < arg.num_ssids; i++)
-			arg.ssid[i] = req->ssids[i];
+		arg->num_ssids = req->n_ssids;
+		for (i = 0; i < arg->num_ssids; i++)
+			arg->ssid[i] = req->ssids[i];
 	} else {
-		arg.scan_f_passive = 1;
+		arg->scan_f_passive = 1;
 	}
 
 	if (req->n_channels) {
-		arg.num_chan = req->n_channels;
-		arg.chan_list = kcalloc(arg.num_chan, sizeof(*arg.chan_list),
-					GFP_KERNEL);
-
-		if (!arg.chan_list) {
+		arg->num_chan = req->n_channels;
+		arg->chan_list = kcalloc(arg->num_chan, sizeof(*arg->chan_list),
+					 GFP_KERNEL);
+		if (!arg->chan_list) {
 			ret = -ENOMEM;
 			goto exit;
 		}
 
-		for (i = 0; i < arg.num_chan; i++)
-			arg.chan_list[i] = req->channels[i]->center_freq;
+		for (i = 0; i < arg->num_chan; i++)
+			arg->chan_list[i] = req->channels[i]->center_freq;
 	}
 
-	ret = ath12k_start_scan(ar, &arg);
+	ret = ath12k_start_scan(ar, arg);
 	if (ret) {
 		ath12k_warn(ar->ab, "failed to start hw scan: %d\n", ret);
 		spin_lock_bh(&ar->data_lock);
@@ -3790,14 +3795,15 @@ scan:
 
 	/* Add a margin to account for event/command processing */
 	ieee80211_queue_delayed_work(ath12k_ar_to_hw(ar), &ar->scan.timeout,
-				     msecs_to_jiffies(arg.max_scan_time +
+				     msecs_to_jiffies(arg->max_scan_time +
 						      ATH12K_MAC_SCAN_TIMEOUT_MSECS));
 
 exit:
-	kfree(arg.chan_list);
-
-	if (req->ie_len)
-		kfree(arg.extraie.ptr);
+	if (arg) {
+		kfree(arg->chan_list);
+		kfree(arg->extraie.ptr);
+		kfree(arg);
+	}
 
 	mutex_unlock(&ar->conf_mutex);
 
-- 
cgit v1.3-3-g829e


From e7d731326ef0622f103e5ed47d3405f71cdcd7f6 Mon Sep 17 00:00:00 2001
From: Abhash Jha <abhashkumarjha123@gmail.com>
Date: Wed, 14 Aug 2024 23:01:21 +0530
Subject: selftests/net/pmtu.sh: Fix typo in error message

The word 'expected' was spelled as 'exepcted'.
Fixed the typo in this patch.

Signed-off-by: Abhash Jha <abhashkumarjha123@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240814173121.33590-1-abhashkumarjha123@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/pmtu.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 5175c0c83a23..24a50622406c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -1447,7 +1447,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
 		size=$(du -sb $tmpoutfile)
 		size=${size%%/tmp/*}
 
-		[ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1
+		[ $size -ne 1048576 ] && err "File size $size mismatches expected value in locally bridged vxlan test" && return 1
 	done
 
 	rm -f "$tmpoutfile"
-- 
cgit v1.3-3-g829e


From 7cb43579641dc437941782b473387c6f8bbc1d25 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Mon, 12 Aug 2024 11:06:55 +0200
Subject: net: macb: increase max_mtu for oversized frames

Increase max_mtu from 1500 to 1518 bytes when not configured for jumbo
frames. Use 1536 as a starting point as documented in macb.h for
oversized (big) frames, which is the configuration applied in case
jumbo frames capability is not configured; ref. macb_main.c.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Link: https://patch.msgid.link/20240812090657.583821-1-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 97b4cc5feb95..127bb3208034 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -5119,12 +5119,12 @@ static int macb_probe(struct platform_device *pdev)
 		goto err_out_free_netdev;
 	}
 
-	/* MTU range: 68 - 1500 or 10240 */
+	/* MTU range: 68 - 1518 or 10240 */
 	dev->min_mtu = GEM_MTU_MIN_SIZE;
 	if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len)
 		dev->max_mtu = bp->jumbo_max_len - ETH_HLEN - ETH_FCS_LEN;
 	else
-		dev->max_mtu = ETH_DATA_LEN;
+		dev->max_mtu = 1536 - ETH_HLEN - ETH_FCS_LEN;
 
 	if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) {
 		val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10));
-- 
cgit v1.3-3-g829e


From e3af3d3c5b26c33a7950e34e137584f6056c4319 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 9 Aug 2024 16:54:02 -0700
Subject: ipv4: Check !in_dev earlier for ioctl(SIOCSIFADDR).

dev->ip_ptr could be NULL if we set an invalid MTU.

Even then, if we issue ioctl(SIOCSIFADDR) for a new IPv4 address,
devinet_ioctl() allocates struct in_ifaddr and fails later in
inet_set_ifa() because in_dev is NULL.

Let's move the check earlier.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240809235406.50187-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/devinet.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d96f3e452fef..ddab15116454 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -574,10 +574,6 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
 
 	ASSERT_RTNL();
 
-	if (!in_dev) {
-		inet_free_ifa(ifa);
-		return -ENOBUFS;
-	}
 	ipv4_devconf_setall(in_dev);
 	neigh_parms_data_state_setall(in_dev->arp_parms);
 	if (ifa->ifa_dev != in_dev) {
@@ -1184,6 +1180,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr)
 
 		if (!ifa) {
 			ret = -ENOBUFS;
+			if (!in_dev)
+				break;
 			ifa = inet_alloc_ifa();
 			if (!ifa)
 				break;
-- 
cgit v1.3-3-g829e


From 6e701eb914124cf260a8b9a4350740f9a7407fc7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 9 Aug 2024 16:54:03 -0700
Subject: ipv4: Set ifa->ifa_dev in inet_alloc_ifa().

When a new IPv4 address is assigned via ioctl(SIOCSIFADDR),
inet_set_ifa() sets ifa->ifa_dev if it's different from in_dev
passed as an argument.

In this case, ifa is always a newly allocated object, and
ifa->ifa_dev is NULL.

inet_set_ifa() can be called for an existing reused ifa, then,
this check is always false.

Let's set ifa_dev in inet_alloc_ifa() and remove the check
in inet_set_ifa().

Now, inet_alloc_ifa() is symmetric with inet_rcu_free_ifa().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240809235406.50187-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/devinet.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ddab15116454..9f4add07e67d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -216,9 +216,18 @@ static void devinet_sysctl_unregister(struct in_device *idev)
 
 /* Locks all the inet devices. */
 
-static struct in_ifaddr *inet_alloc_ifa(void)
+static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev)
 {
-	return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT);
+	struct in_ifaddr *ifa;
+
+	ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT);
+	if (!ifa)
+		return NULL;
+
+	in_dev_hold(in_dev);
+	ifa->ifa_dev = in_dev;
+
+	return ifa;
 }
 
 static void inet_rcu_free_ifa(struct rcu_head *head)
@@ -576,11 +585,7 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
 
 	ipv4_devconf_setall(in_dev);
 	neigh_parms_data_state_setall(in_dev->arp_parms);
-	if (ifa->ifa_dev != in_dev) {
-		WARN_ON(ifa->ifa_dev);
-		in_dev_hold(in_dev);
-		ifa->ifa_dev = in_dev;
-	}
+
 	if (ipv4_is_loopback(ifa->ifa_local))
 		ifa->ifa_scope = RT_SCOPE_HOST;
 	return inet_insert_ifa(ifa);
@@ -871,7 +876,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	if (!in_dev)
 		goto errout;
 
-	ifa = inet_alloc_ifa();
+	ifa = inet_alloc_ifa(in_dev);
 	if (!ifa)
 		/*
 		 * A potential indev allocation can be left alive, it stays
@@ -881,7 +886,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 
 	ipv4_devconf_setall(in_dev);
 	neigh_parms_data_state_setall(in_dev->arp_parms);
-	in_dev_hold(in_dev);
 
 	if (!tb[IFA_ADDRESS])
 		tb[IFA_ADDRESS] = tb[IFA_LOCAL];
@@ -892,8 +896,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
 					 ifm->ifa_flags;
 	ifa->ifa_scope = ifm->ifa_scope;
-	ifa->ifa_dev = in_dev;
-
 	ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]);
 	ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]);
 
@@ -1182,7 +1184,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr)
 			ret = -ENOBUFS;
 			if (!in_dev)
 				break;
-			ifa = inet_alloc_ifa();
+			ifa = inet_alloc_ifa(in_dev);
 			if (!ifa)
 				break;
 			INIT_HLIST_NODE(&ifa->hash);
@@ -1584,7 +1586,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 		if (!inetdev_valid_mtu(dev->mtu))
 			break;
 		if (dev->flags & IFF_LOOPBACK) {
-			struct in_ifaddr *ifa = inet_alloc_ifa();
+			struct in_ifaddr *ifa = inet_alloc_ifa(in_dev);
 
 			if (ifa) {
 				INIT_HLIST_NODE(&ifa->hash);
@@ -1592,8 +1594,6 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 				  ifa->ifa_address = htonl(INADDR_LOOPBACK);
 				ifa->ifa_prefixlen = 8;
 				ifa->ifa_mask = inet_make_mask(8);
-				in_dev_hold(in_dev);
-				ifa->ifa_dev = in_dev;
 				ifa->ifa_scope = RT_SCOPE_HOST;
 				memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
 				set_ifa_lifetime(ifa, INFINITY_LIFE_TIME,
-- 
cgit v1.3-3-g829e


From ecdae5168460f7260c0f8dad069aa06f9ba0706e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 9 Aug 2024 16:54:04 -0700
Subject: ipv4: Remove redundant !ifa->ifa_dev check.

Now, ifa_dev is only set in inet_alloc_ifa() and never
NULL after ifa gets visible.

Let's remove the unneeded NULL check for ifa->ifa_dev.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240809235406.50187-4-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c | 5 ++---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c     | 2 +-
 net/ipv4/devinet.c                                   | 3 +--
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index ed24d6af7487..9cff0a8ffb2c 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -3185,8 +3185,7 @@ netxen_list_config_ip(struct netxen_adapter *adapter,
 	struct list_head *head;
 	bool ret = false;
 
-	dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL;
-
+	dev = ifa->ifa_dev->dev;
 	if (dev == NULL)
 		goto out;
 
@@ -3379,7 +3378,7 @@ netxen_inetaddr_event(struct notifier_block *this,
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 	unsigned long ip_event;
 
-	dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL;
+	dev = ifa->ifa_dev->dev;
 	ip_event = (event == NETDEV_UP) ? NX_IP_UP : NX_IP_DOWN;
 recheck:
 	if (dev == NULL)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 90df4a0909fa..b3588a1ebc25 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -4146,7 +4146,7 @@ qlcnic_inetaddr_event(struct notifier_block *this,
 
 	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
 
-	dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL;
+	dev = ifa->ifa_dev->dev;
 
 recheck:
 	if (dev == NULL)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 9f4add07e67d..baf036bfad76 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -234,8 +234,7 @@ static void inet_rcu_free_ifa(struct rcu_head *head)
 {
 	struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head);
 
-	if (ifa->ifa_dev)
-		in_dev_put(ifa->ifa_dev);
+	in_dev_put(ifa->ifa_dev);
 	kfree(ifa);
 }
 
-- 
cgit v1.3-3-g829e


From 100465a91a900699db9c64fb55063affd15c4362 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 9 Aug 2024 16:54:05 -0700
Subject: ipv4: Initialise ifa->hash in inet_alloc_ifa().

Whenever ifa is allocated, we call INIT_HLIST_NODE(&ifa->hash).

Let's move it to inet_alloc_ifa().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240809235406.50187-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/devinet.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index baf036bfad76..b5d2a9fd46c7 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -227,6 +227,8 @@ static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev)
 	in_dev_hold(in_dev);
 	ifa->ifa_dev = in_dev;
 
+	INIT_HLIST_NODE(&ifa->hash);
+
 	return ifa;
 }
 
@@ -889,7 +891,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 	if (!tb[IFA_ADDRESS])
 		tb[IFA_ADDRESS] = tb[IFA_LOCAL];
 
-	INIT_HLIST_NODE(&ifa->hash);
 	ifa->ifa_prefixlen = ifm->ifa_prefixlen;
 	ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen);
 	ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) :
@@ -1186,7 +1187,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr)
 			ifa = inet_alloc_ifa(in_dev);
 			if (!ifa)
 				break;
-			INIT_HLIST_NODE(&ifa->hash);
+
 			if (colon)
 				memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ);
 			else
@@ -1588,7 +1589,6 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
 			struct in_ifaddr *ifa = inet_alloc_ifa(in_dev);
 
 			if (ifa) {
-				INIT_HLIST_NODE(&ifa->hash);
 				ifa->ifa_local =
 				  ifa->ifa_address = htonl(INADDR_LOOPBACK);
 				ifa->ifa_prefixlen = 8;
-- 
cgit v1.3-3-g829e


From de67763cbdbba8149eeb5d45ad0c6834f7c7b352 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 9 Aug 2024 16:54:06 -0700
Subject: ip: Move INFINITY_LIFE_TIME to addrconf.h.

INFINITY_LIFE_TIME is the common value used in IPv4 and IPv6 but defined
in both .c files.

Also, 0xffffffff used in addrconf_timeout_fixup() is INFINITY_LIFE_TIME.

Let's move INFINITY_LIFE_TIME's definition to addrconf.h

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240809235406.50187-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/addrconf.h | 4 +++-
 net/ipv4/devinet.c     | 2 --
 net/ipv6/addrconf.c    | 2 --
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index b18e81f0c9e1..c8ed31828db3 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -187,10 +187,12 @@ static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev)
 	return 0;
 }
 
+#define INFINITY_LIFE_TIME 0xFFFFFFFF
+
 static inline unsigned long addrconf_timeout_fixup(u32 timeout,
 						   unsigned int unit)
 {
-	if (timeout == 0xffffffff)
+	if (timeout == INFINITY_LIFE_TIME)
 		return ~0UL;
 
 	/*
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index b5d2a9fd46c7..61be85154dd1 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -703,8 +703,6 @@ errout:
 	return err;
 }
 
-#define INFINITY_LIFE_TIME	0xFFFFFFFF
-
 static void check_lifetime(struct work_struct *work)
 {
 	unsigned long now, next, next_sec, next_sched;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c87d008aefa4..04ee75af2f6b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -92,8 +92,6 @@
 #include <linux/export.h>
 #include <linux/ioam6.h>
 
-#define	INFINITY_LIFE_TIME	0xFFFFFFFF
-
 #define IPV6_MAX_STRLEN \
 	sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255")
 
-- 
cgit v1.3-3-g829e


From e5efc2311cc437e2b565d164a3de884fa33f13e9 Mon Sep 17 00:00:00 2001
From: Erwan Velu <erwanaliasr1@gmail.com>
Date: Mon, 12 Aug 2024 10:22:42 +0200
Subject: net/mlx5: Use cpumask_local_spread() instead of custom code

Commit 2acda57736de ("net/mlx5e: Improve remote NUMA preferences used for the IRQ affinity hints")
removed the usage of cpumask_local_spread().

The issue explained in this commit was fixed by
commit 406d394abfcd ("cpumask: improve on cpumask_local_spread() locality").

Since this commit, mlx5_cpumask_default_spread() is having the same
behavior as cpumask_local_spread().

This commit is about :
- removing the specific logic and use cpumask_local_spread() instead
- passing mlx5_core_dev as argument to more flexibility

mlx5_cpumask_default_spread() is kept as it could be useful for some
future specific quirks.

Signed-off-by: Erwan Velu <e.velu@criteo.com>
Acked-by: Yury Norov <yury.norov@gmail.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240812082244.22810-1-e.velu@criteo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 27 ++++-----------------------
 1 file changed, 4 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index cb7e7e4104af..f15ecaef1331 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -835,28 +835,9 @@ static void comp_irq_release_pci(struct mlx5_core_dev *dev, u16 vecidx)
 	mlx5_irq_release_vector(irq);
 }
 
-static int mlx5_cpumask_default_spread(int numa_node, int index)
+static int mlx5_cpumask_default_spread(struct mlx5_core_dev *dev, int index)
 {
-	const struct cpumask *prev = cpu_none_mask;
-	const struct cpumask *mask;
-	int found_cpu = 0;
-	int i = 0;
-	int cpu;
-
-	rcu_read_lock();
-	for_each_numa_hop_mask(mask, numa_node) {
-		for_each_cpu_andnot(cpu, mask, prev) {
-			if (i++ == index) {
-				found_cpu = cpu;
-				goto spread_done;
-			}
-		}
-		prev = mask;
-	}
-
-spread_done:
-	rcu_read_unlock();
-	return found_cpu;
+	return cpumask_local_spread(index, dev->priv.numa_node);
 }
 
 static struct cpu_rmap *mlx5_eq_table_get_pci_rmap(struct mlx5_core_dev *dev)
@@ -880,7 +861,7 @@ static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx)
 	int cpu;
 
 	rmap = mlx5_eq_table_get_pci_rmap(dev);
-	cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vecidx);
+	cpu = mlx5_cpumask_default_spread(dev, vecidx);
 	irq = mlx5_irq_request_vector(dev, cpu, vecidx, &rmap);
 	if (IS_ERR(irq))
 		return PTR_ERR(irq);
@@ -1145,7 +1126,7 @@ int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector)
 	if (mask)
 		cpu = cpumask_first(mask);
 	else
-		cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vector);
+		cpu = mlx5_cpumask_default_spread(dev, vector);
 
 	return cpu;
 }
-- 
cgit v1.3-3-g829e


From fcb1aa5163b1ae4cf2864b688b08927aac51f51e Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 12 Aug 2024 13:17:53 -0400
Subject: openvswitch: switch to per-action label counting in conntrack

Similar to commit 70f06c115bcc ("sched: act_ct: switch to per-action
label counting"), we should also switch to per-action label counting
in openvswitch conntrack, as Florian suggested.

The difference is that nf_connlabels_get() is called unconditionally
when creating an ct action in ovs_ct_copy_action(). As with these
flows:

  table=0,ip,actions=ct(commit,table=1)
  table=1,ip,actions=ct(commit,exec(set_field:0xac->ct_label),table=2)

it needs to make sure the label ext is created in the 1st flow before
the ct is committed in ovs_ct_commit(). Otherwise, the warning in
nf_ct_ext_add() when creating the label ext in the 2nd flow will
be triggered:

   WARN_ON(nf_ct_is_confirmed(ct));

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/6b9347d5c1a0b364e88d900b29a616c3f8e5b1ca.1723483073.git.lucien.xin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/openvswitch/conntrack.c | 30 ++++++++++++------------------
 net/openvswitch/datapath.h  |  3 ---
 2 files changed, 12 insertions(+), 21 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 8eb1d644b741..a3da5ee34f92 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1368,11 +1368,8 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr)
 	    attr == OVS_KEY_ATTR_CT_MARK)
 		return true;
 	if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
-	    attr == OVS_KEY_ATTR_CT_LABELS) {
-		struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
-
-		return ovs_net->xt_label;
-	}
+	    attr == OVS_KEY_ATTR_CT_LABELS)
+		return true;
 
 	return false;
 }
@@ -1381,6 +1378,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		       const struct sw_flow_key *key,
 		       struct sw_flow_actions **sfa,  bool log)
 {
+	unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
 	struct ovs_conntrack_info ct_info;
 	const char *helper = NULL;
 	u16 family;
@@ -1409,6 +1407,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		return -ENOMEM;
 	}
 
+	if (nf_connlabels_get(net, n_bits - 1)) {
+		nf_ct_tmpl_free(ct_info.ct);
+		OVS_NLERR(log, "Failed to set connlabel length");
+		return -EOPNOTSUPP;
+	}
+
 	if (ct_info.timeout[0]) {
 		if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
 				      ct_info.timeout))
@@ -1577,6 +1581,7 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
 	if (ct_info->ct) {
 		if (ct_info->timeout[0])
 			nf_ct_destroy_timeout(ct_info->ct);
+		nf_connlabels_put(nf_ct_net(ct_info->ct));
 		nf_ct_tmpl_free(ct_info->ct);
 	}
 }
@@ -2002,17 +2007,9 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
 
 int ovs_ct_init(struct net *net)
 {
-	unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
 
-	if (nf_connlabels_get(net, n_bits - 1)) {
-		ovs_net->xt_label = false;
-		OVS_NLERR(true, "Failed to set connlabel length");
-	} else {
-		ovs_net->xt_label = true;
-	}
-
-#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	return ovs_ct_limit_init(net, ovs_net);
 #else
 	return 0;
@@ -2021,12 +2018,9 @@ int ovs_ct_init(struct net *net)
 
 void ovs_ct_exit(struct net *net)
 {
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
 
-#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	ovs_ct_limit_exit(net, ovs_net);
 #endif
-
-	if (ovs_net->xt_label)
-		nf_connlabels_put(net);
 }
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 9ca6231ea647..365b9bb7f546 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -160,9 +160,6 @@ struct ovs_net {
 #if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	struct ovs_ct_limit_info *ct_limit_info;
 #endif
-
-	/* Module reference for configuring conntrack. */
-	bool xt_label;
 };
 
 /**
-- 
cgit v1.3-3-g829e


From d440af37ba6fa301144c6fce2186fe0ab5a8f283 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Wed, 14 Aug 2024 09:06:38 +0200
Subject: netdev: Add missing __percpu qualifier to a cast

Add missing __percpu qualifier to a (void *) cast to fix

dev.c:10863:45: warning: cast removes address space '__percpu' of expression

sparse warning. Also remove now unneeded __force sparse directives.

Found by GCC's named address space checks.

There were no changes in the resulting object file.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://patch.msgid.link/20240814070748.943671-1-ubizjak@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f66e61407883..e7260889d4cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10868,7 +10868,7 @@ noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset)
 			return;
 	}
 
-	field = (__force unsigned long __percpu *)((__force void *)p + offset);
+	field = (unsigned long __percpu *)((void __percpu *)p + offset);
 	this_cpu_inc(*field);
 }
 EXPORT_SYMBOL_GPL(netdev_core_stats_inc);
-- 
cgit v1.3-3-g829e


From 0cb70ee4a6ee6b0a4b0e0f70a64a094c6fe05944 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 14 Aug 2024 13:22:25 +0800
Subject: virtio: rename virtio_config_enabled to virtio_config_core_enabled

Following patch will allow the config interrupt to be disabled by a
specific driver via another boolean. So this patch renames
virtio_config_enabled and relevant helpers to
virtio_config_core_enabled.

Cc: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Cc: Gia-Khanh Nguyen <gia-khanh.nguyen@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240814052228.4654-2-jasowang@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/virtio/virtio.c | 22 +++++++++++-----------
 include/linux/virtio.h  |  4 ++--
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index bc1f962e483b..6b692b0fa578 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -127,7 +127,7 @@ static void __virtio_config_changed(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
-	if (!dev->config_enabled)
+	if (!dev->config_core_enabled)
 		dev->config_change_pending = true;
 	else if (drv && drv->config_changed)
 		drv->config_changed(dev);
@@ -143,17 +143,17 @@ void virtio_config_changed(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_config_changed);
 
-static void virtio_config_disable(struct virtio_device *dev)
+static void virtio_config_core_disable(struct virtio_device *dev)
 {
 	spin_lock_irq(&dev->config_lock);
-	dev->config_enabled = false;
+	dev->config_core_enabled = false;
 	spin_unlock_irq(&dev->config_lock);
 }
 
-static void virtio_config_enable(struct virtio_device *dev)
+static void virtio_config_core_enable(struct virtio_device *dev)
 {
 	spin_lock_irq(&dev->config_lock);
-	dev->config_enabled = true;
+	dev->config_core_enabled = true;
 	if (dev->config_change_pending)
 		__virtio_config_changed(dev);
 	dev->config_change_pending = false;
@@ -316,7 +316,7 @@ static int virtio_dev_probe(struct device *_d)
 	if (drv->scan)
 		drv->scan(dev);
 
-	virtio_config_enable(dev);
+	virtio_config_core_enable(dev);
 
 	return 0;
 
@@ -331,7 +331,7 @@ static void virtio_dev_remove(struct device *_d)
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
-	virtio_config_disable(dev);
+	virtio_config_core_disable(dev);
 
 	drv->remove(dev);
 
@@ -443,7 +443,7 @@ int register_virtio_device(struct virtio_device *dev)
 		goto out_ida_remove;
 
 	spin_lock_init(&dev->config_lock);
-	dev->config_enabled = false;
+	dev->config_core_enabled = false;
 	dev->config_change_pending = false;
 
 	INIT_LIST_HEAD(&dev->vqs);
@@ -500,14 +500,14 @@ int virtio_device_freeze(struct virtio_device *dev)
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 	int ret;
 
-	virtio_config_disable(dev);
+	virtio_config_core_disable(dev);
 
 	dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
 
 	if (drv && drv->freeze) {
 		ret = drv->freeze(dev);
 		if (ret) {
-			virtio_config_enable(dev);
+			virtio_config_core_enable(dev);
 			return ret;
 		}
 	}
@@ -557,7 +557,7 @@ int virtio_device_restore(struct virtio_device *dev)
 	if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
 		virtio_device_ready(dev);
 
-	virtio_config_enable(dev);
+	virtio_config_core_enable(dev);
 
 	return 0;
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 4b16844c6bc2..de6d3cc176d9 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -118,7 +118,7 @@ struct virtio_admin_cmd {
  * struct virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus
  * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore)
- * @config_enabled: configuration change reporting enabled
+ * @config_core_enabled: configuration change reporting enabled by core
  * @config_change_pending: configuration change reported while disabled
  * @config_lock: protects configuration change reporting
  * @vqs_list_lock: protects @vqs.
@@ -135,7 +135,7 @@ struct virtio_admin_cmd {
 struct virtio_device {
 	int index;
 	bool failed;
-	bool config_enabled;
+	bool config_core_enabled;
 	bool config_change_pending;
 	spinlock_t config_lock;
 	spinlock_t vqs_list_lock;
-- 
cgit v1.3-3-g829e


From 224de6f886f8184fd448700a6d78f216694de948 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 14 Aug 2024 13:22:26 +0800
Subject: virtio: allow driver to disable the configure change notification

Sometime, it would be useful to disable the configure change
notification from the driver. So this patch allows this by introducing
a variable config_change_driver_disabled and only allow the configure
change notification callback to be triggered when it is allowed by
both the virtio core and the driver. It is set to false by default to
hold the current semantic so we don't need to change any drivers.

The first user for this would be virtio-net.

Cc: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Cc: Gia-Khanh Nguyen <gia-khanh.nguyen@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240814052228.4654-3-jasowang@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/virtio/virtio.c | 39 ++++++++++++++++++++++++++++++++++++---
 include/linux/virtio.h  |  7 +++++++
 2 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 6b692b0fa578..b9095751e43b 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -127,10 +127,12 @@ static void __virtio_config_changed(struct virtio_device *dev)
 {
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
 
-	if (!dev->config_core_enabled)
+	if (!dev->config_core_enabled || dev->config_driver_disabled)
 		dev->config_change_pending = true;
-	else if (drv && drv->config_changed)
+	else if (drv && drv->config_changed) {
 		drv->config_changed(dev);
+		dev->config_change_pending = false;
+	}
 }
 
 void virtio_config_changed(struct virtio_device *dev)
@@ -143,6 +145,38 @@ void virtio_config_changed(struct virtio_device *dev)
 }
 EXPORT_SYMBOL_GPL(virtio_config_changed);
 
+/**
+ * virtio_config_driver_disable - disable config change reporting by drivers
+ * @dev: the device to reset
+ *
+ * This is only allowed to be called by a driver and disabling can't
+ * be nested.
+ */
+void virtio_config_driver_disable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_driver_disabled = true;
+	spin_unlock_irq(&dev->config_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_config_driver_disable);
+
+/**
+ * virtio_config_driver_enable - enable config change reporting by drivers
+ * @dev: the device to reset
+ *
+ * This is only allowed to be called by a driver and enabling can't
+ * be nested.
+ */
+void virtio_config_driver_enable(struct virtio_device *dev)
+{
+	spin_lock_irq(&dev->config_lock);
+	dev->config_driver_disabled = false;
+	if (dev->config_change_pending)
+		__virtio_config_changed(dev);
+	spin_unlock_irq(&dev->config_lock);
+}
+EXPORT_SYMBOL_GPL(virtio_config_driver_enable);
+
 static void virtio_config_core_disable(struct virtio_device *dev)
 {
 	spin_lock_irq(&dev->config_lock);
@@ -156,7 +190,6 @@ static void virtio_config_core_enable(struct virtio_device *dev)
 	dev->config_core_enabled = true;
 	if (dev->config_change_pending)
 		__virtio_config_changed(dev);
-	dev->config_change_pending = false;
 	spin_unlock_irq(&dev->config_lock);
 }
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index de6d3cc176d9..306137a15d07 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -119,6 +119,8 @@ struct virtio_admin_cmd {
  * @index: unique position on the virtio bus
  * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore)
  * @config_core_enabled: configuration change reporting enabled by core
+ * @config_driver_disabled: configuration change reporting disabled by
+ *                          a driver
  * @config_change_pending: configuration change reported while disabled
  * @config_lock: protects configuration change reporting
  * @vqs_list_lock: protects @vqs.
@@ -136,6 +138,7 @@ struct virtio_device {
 	int index;
 	bool failed;
 	bool config_core_enabled;
+	bool config_driver_disabled;
 	bool config_change_pending;
 	spinlock_t config_lock;
 	spinlock_t vqs_list_lock;
@@ -166,6 +169,10 @@ void __virtqueue_break(struct virtqueue *_vq);
 void __virtqueue_unbreak(struct virtqueue *_vq);
 
 void virtio_config_changed(struct virtio_device *dev);
+
+void virtio_config_driver_disable(struct virtio_device *dev);
+void virtio_config_driver_enable(struct virtio_device *dev);
+
 #ifdef CONFIG_PM_SLEEP
 int virtio_device_freeze(struct virtio_device *dev);
 int virtio_device_restore(struct virtio_device *dev);
-- 
cgit v1.3-3-g829e


From df28de7b00502761eba62490f413c65c9b175ed9 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 14 Aug 2024 13:22:27 +0800
Subject: virtio-net: synchronize operstate with admin state on up/down

This patch synchronizes operstate with admin state per RFC2863.

This is done by trying to toggle the carrier upon open/close and
synchronize with the config change work. This allows to propagate
status correctly to stacked devices like:

ip link add link enp0s3 macvlan0 type macvlan
ip link set link enp0s3 down
ip link show

Before this patch:

3: enp0s3: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000
    link/ether 00:00:05:00:00:09 brd ff:ff:ff:ff:ff:ff
......
5: macvlan0@enp0s3: <BROADCAST,MULTICAST,UP,LOWER_UP,M-DOWN> mtu 1500 qdisc noqueue state UP mode DEFAULT group default qlen 1000
    link/ether b2:a9:c5:04:da:53 brd ff:ff:ff:ff:ff:ff

After this patch:

3: enp0s3: <BROADCAST,MULTICAST> mtu 1500 qdisc pfifo_fast state DOWN mode DEFAULT group default qlen 1000
    link/ether 00:00:05:00:00:09 brd ff:ff:ff:ff:ff:ff
...
5: macvlan0@enp0s3: <NO-CARRIER,BROADCAST,MULTICAST,UP,M-DOWN> mtu 1500 qdisc noqueue state LOWERLAYERDOWN mode DEFAULT group default qlen 1000
    link/ether b2:a9:c5:04:da:53 brd ff:ff:ff:ff:ff:ff

Cc: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
Cc: Gia-Khanh Nguyen <gia-khanh.nguyen@oracle.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240814052228.4654-4-jasowang@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 78 +++++++++++++++++++++++++++++++-----------------
 1 file changed, 50 insertions(+), 28 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3f10c72743e9..55b712a71e63 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2885,6 +2885,25 @@ static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim)
 	net_dim_work_cancel(dim);
 }
 
+static void virtnet_update_settings(struct virtnet_info *vi)
+{
+	u32 speed;
+	u8 duplex;
+
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
+		return;
+
+	virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed);
+
+	if (ethtool_validate_speed(speed))
+		vi->speed = speed;
+
+	virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex);
+
+	if (ethtool_validate_duplex(duplex))
+		vi->duplex = duplex;
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -2903,6 +2922,15 @@ static int virtnet_open(struct net_device *dev)
 			goto err_enable_qp;
 	}
 
+	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
+		if (vi->status & VIRTIO_NET_S_LINK_UP)
+			netif_carrier_on(vi->dev);
+		virtio_config_driver_enable(vi->vdev);
+	} else {
+		vi->status = VIRTIO_NET_S_LINK_UP;
+		netif_carrier_on(dev);
+	}
+
 	return 0;
 
 err_enable_qp:
@@ -3381,12 +3409,22 @@ static int virtnet_close(struct net_device *dev)
 	disable_delayed_refill(vi);
 	/* Make sure refill_work doesn't re-enable napi! */
 	cancel_delayed_work_sync(&vi->refill);
+	/* Prevent the config change callback from changing carrier
+	 * after close
+	 */
+	virtio_config_driver_disable(vi->vdev);
+	/* Stop getting status/speed updates: we don't care until next
+	 * open
+	 */
+	cancel_work_sync(&vi->config_work);
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		virtnet_disable_queue_pair(vi, i);
 		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
+	netif_carrier_off(dev);
+
 	return 0;
 }
 
@@ -5095,25 +5133,6 @@ static void virtnet_init_settings(struct net_device *dev)
 	vi->duplex = DUPLEX_UNKNOWN;
 }
 
-static void virtnet_update_settings(struct virtnet_info *vi)
-{
-	u32 speed;
-	u8 duplex;
-
-	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX))
-		return;
-
-	virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed);
-
-	if (ethtool_validate_speed(speed))
-		vi->speed = speed;
-
-	virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex);
-
-	if (ethtool_validate_duplex(duplex))
-		vi->duplex = duplex;
-}
-
 static u32 virtnet_get_rxfh_key_size(struct net_device *dev)
 {
 	return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size;
@@ -6524,6 +6543,9 @@ static int virtnet_probe(struct virtio_device *vdev)
 		goto free_failover;
 	}
 
+	/* Disable config change notification until ndo_open. */
+	virtio_config_driver_disable(vi->vdev);
+
 	virtio_device_ready(vdev);
 
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
@@ -6573,25 +6595,25 @@ static int virtnet_probe(struct virtio_device *vdev)
 		vi->device_stats_cap = le64_to_cpu(v);
 	}
 
-	rtnl_unlock();
-
-	err = virtnet_cpu_notif_add(vi);
-	if (err) {
-		pr_debug("virtio_net: registering cpu notifier failed\n");
-		goto free_unregister_netdev;
-	}
-
 	/* Assume link up if device can't report link status,
 	   otherwise get link status from config. */
 	netif_carrier_off(dev);
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) {
-		schedule_work(&vi->config_work);
+		virtnet_config_changed_work(&vi->config_work);
 	} else {
 		vi->status = VIRTIO_NET_S_LINK_UP;
 		virtnet_update_settings(vi);
 		netif_carrier_on(dev);
 	}
 
+	rtnl_unlock();
+
+	err = virtnet_cpu_notif_add(vi);
+	if (err) {
+		pr_debug("virtio_net: registering cpu notifier failed\n");
+		goto free_unregister_netdev;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
 		if (virtio_has_feature(vi->vdev, guest_offloads[i]))
 			set_bit(guest_offloads[i], &vi->guest_offloads);
-- 
cgit v1.3-3-g829e


From c392d6019398315526b0b508282f87c7b2318c72 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Wed, 14 Aug 2024 13:22:28 +0800
Subject: virtio-net: synchronize probe with ndo_set_features

We calculate guest offloads during probe without the protection of
rtnl_lock. This lead to race between probe and ndo_set_features. Fix
this by moving the calculation under the rtnl_lock.

Fixes: 3f93522ffab2 ("virtio-net: switch off offloads on demand if possible on XDP set")
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240814052228.4654-5-jasowang@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 55b712a71e63..6c79fc43fa31 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -6606,6 +6606,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 		netif_carrier_on(dev);
 	}
 
+	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
+		if (virtio_has_feature(vi->vdev, guest_offloads[i]))
+			set_bit(guest_offloads[i], &vi->guest_offloads);
+	vi->guest_offloads_capable = vi->guest_offloads;
+
 	rtnl_unlock();
 
 	err = virtnet_cpu_notif_add(vi);
@@ -6614,11 +6619,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 		goto free_unregister_netdev;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(guest_offloads); i++)
-		if (virtio_has_feature(vi->vdev, guest_offloads[i]))
-			set_bit(guest_offloads[i], &vi->guest_offloads);
-	vi->guest_offloads_capable = vi->guest_offloads;
-
 	pr_debug("virtnet: registered device %s with %d RX and TX vq's\n",
 		 dev->name, max_queue_pairs);
 
-- 
cgit v1.3-3-g829e


From 9b49f55838b1f42b2624216ce494f0536669e8f0 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Sun, 11 Aug 2024 11:56:42 +0300
Subject: xfrm: Remove documentation WARN_ON to limit return values for
 offloaded SA

The original idea to put WARN_ON() on return value from driver code was
to make sure that packet offload doesn't have silent fallback to
SW implementation, like crypto offload has.

In reality, this is not needed as all *swan implementations followed
this request and used explicit configuration style to make sure that
"users will get what they ask".
So instead of forcing drivers to make sure that even their internal flows
don't return -EOPNOTSUPP, let's remove this WARN_ON.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_device.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 9a44d363ba62..f123b7c9ec82 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -328,12 +328,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		/* User explicitly requested packet offload mode and configured
 		 * policy in addition to the XFRM state. So be civil to users,
 		 * and return an error instead of taking fallback path.
-		 *
-		 * This WARN_ON() can be seen as a documentation for driver
-		 * authors to do not return -EOPNOTSUPP in packet offload mode.
 		 */
-		WARN_ON(err == -EOPNOTSUPP && is_packet_offload);
-		if (err != -EOPNOTSUPP || is_packet_offload) {
+		if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) {
 			NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state");
 			return err;
 		}
-- 
cgit v1.3-3-g829e


From daaf0dd0398d5e93b7304f35184ca182ed583681 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Fri, 9 Aug 2024 11:51:48 +0200
Subject: wifi: mwifiex: keep mwifiex_cfg80211_ops constant

With host_mlme support being added mwifiex_cfg80211_ops is no longer
constant, but supplemented with the host_mlme related ops when host_mlme
support is enabled. This doesn't work with multiple adapters when only
few of then have host_mlme support. Duplicate mwifiex_cfg80211_ops
before using it and keep the original constant.

While at it mark mwifiex_cfg80211_ops const to prevent people from
changing it again during runtime.

Fixes: 36995892c271c ("wifi: mwifiex: add host mlme for client mode")
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240809-mwifiex-duplicate-mwifiex_cfg80211_ops-v1-1-23e0e6290ace@pengutronix.de
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 26 ++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 722ead51e912..e36ef075fe05 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4570,7 +4570,7 @@ mwifiex_cfg80211_probe_client(struct wiphy *wiphy,
 }
 
 /* station cfg80211 operations */
-static struct cfg80211_ops mwifiex_cfg80211_ops = {
+static const struct cfg80211_ops mwifiex_cfg80211_ops = {
 	.add_virtual_intf = mwifiex_add_virtual_intf,
 	.del_virtual_intf = mwifiex_del_virtual_intf,
 	.change_virtual_intf = mwifiex_cfg80211_change_virtual_intf,
@@ -4705,24 +4705,28 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
 	struct mwifiex_private *priv = adapter->priv[MWIFIEX_BSS_TYPE_STA];
 	u8 *country_code;
 	u32 thr, retry;
+	struct cfg80211_ops *ops;
+
+	ops = devm_kmemdup(adapter->dev, &mwifiex_cfg80211_ops,
+			   sizeof(mwifiex_cfg80211_ops), GFP_KERNEL);
+	if (!ops)
+		return -ENOMEM;
 
 	/* create a new wiphy for use with cfg80211 */
-	wiphy = wiphy_new(&mwifiex_cfg80211_ops,
-			  sizeof(struct mwifiex_adapter *));
+	wiphy = wiphy_new(ops, sizeof(struct mwifiex_adapter *));
 	if (!wiphy) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: creating new wiphy\n", __func__);
 		return -ENOMEM;
 	}
 	if (adapter->host_mlme_enabled) {
-		mwifiex_cfg80211_ops.auth = mwifiex_cfg80211_authenticate;
-		mwifiex_cfg80211_ops.assoc = mwifiex_cfg80211_associate;
-		mwifiex_cfg80211_ops.deauth = mwifiex_cfg80211_deauthenticate;
-		mwifiex_cfg80211_ops.disassoc = mwifiex_cfg80211_disassociate;
-		mwifiex_cfg80211_ops.disconnect = NULL;
-		mwifiex_cfg80211_ops.connect = NULL;
-		mwifiex_cfg80211_ops.probe_client =
-			mwifiex_cfg80211_probe_client;
+		ops->auth = mwifiex_cfg80211_authenticate;
+		ops->assoc = mwifiex_cfg80211_associate;
+		ops->deauth = mwifiex_cfg80211_deauthenticate;
+		ops->disassoc = mwifiex_cfg80211_disassociate;
+		ops->disconnect = NULL;
+		ops->connect = NULL;
+		ops->probe_client = mwifiex_cfg80211_probe_client;
 	}
 	wiphy->max_scan_ssids = MWIFIEX_MAX_SSID_LIST_LENGTH;
 	wiphy->max_scan_ie_len = MWIFIEX_MAX_VSIE_LEN;
-- 
cgit v1.3-3-g829e


From 94745807f3ebd379f23865e6dab196f220664179 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@redhat.com>
Date: Mon, 12 Aug 2024 16:24:46 +0200
Subject: wifi: ath9k_htc: Use __skb_set_length() for resetting urb before
 resubmit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Syzbot points out that skb_trim() has a sanity check on the existing length of
the skb, which can be uninitialised in some error paths. The intent here is
clearly just to reset the length to zero before resubmitting, so switch to
calling __skb_set_length(skb, 0) directly. In addition, __skb_set_length()
already contains a call to skb_reset_tail_pointer(), so remove the redundant
call.

The syzbot report came from ath9k_hif_usb_reg_in_cb(), but there's a similar
usage of skb_trim() in ath9k_hif_usb_rx_cb(), change both while we're at it.

Reported-by: syzbot+98afa303be379af6cdb2@syzkaller.appspotmail.com
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/20240812142447.12328-1-toke@toke.dk
---
 drivers/net/wireless/ath/ath9k/hif_usb.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index 0c7841f95228..a3733c9b484e 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -716,8 +716,7 @@ static void ath9k_hif_usb_rx_cb(struct urb *urb)
 	}
 
 resubmit:
-	skb_reset_tail_pointer(skb);
-	skb_trim(skb, 0);
+	__skb_set_length(skb, 0);
 
 	usb_anchor_urb(urb, &hif_dev->rx_submitted);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
@@ -754,8 +753,7 @@ static void ath9k_hif_usb_reg_in_cb(struct urb *urb)
 	case -ESHUTDOWN:
 		goto free_skb;
 	default:
-		skb_reset_tail_pointer(skb);
-		skb_trim(skb, 0);
+		__skb_set_length(skb, 0);
 
 		goto resubmit;
 	}
-- 
cgit v1.3-3-g829e


From 526929a326d177c856b61b9d9ec721553ac49390 Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Fri, 9 Aug 2024 15:20:07 +0800
Subject: wifi: rtw89: 8852c: support firmware with fw_element

Firmware from v1 will include fw_element so that the driver will loading
parameters of BB and RF, TX power related tables from firmware. For the
current flow, if fw_element is present, the driver will prioritize
loading parameters and tables from firmware; otherwise, it will
revert to the original loading method.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240809072012.84152-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c | 100 +++++++++++++++-------
 1 file changed, 67 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
index 6e199e82690b..8fee820be258 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
@@ -5,6 +5,7 @@
 #include "chan.h"
 #include "coex.h"
 #include "debug.h"
+#include "fw.h"
 #include "phy.h"
 #include "reg.h"
 #include "rtw8852c.h"
@@ -2985,8 +2986,9 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	}						\
 	__val;						\
 })
-	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	struct rtw89_fw_txpwr_track_cfg *trk = rtwdev->fw.elm_info.txpwr_trk;
+	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -3001,56 +3003,88 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	switch (subband) {
 	default:
 	case RTW89_CH_2G:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_2ga_p;
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_2ga_n;
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_2gb_p;
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_2gb_n;
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_2GA_P][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_2ga_p;
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_2GA_N][0] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_2ga_n;
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_2GB_P][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_2gb_p;
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_2GB_N][0] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_2gb_n;
 		break;
 	case RTW89_CH_5G_BAND_1:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_5ga_p[0];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_5ga_n[0];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_5gb_p[0];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_5gb_n[0];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GA_P][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5ga_p[0];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GA_N][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5ga_n[0];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GB_P][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5gb_p[0];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GB_N][0] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_5gb_n[0];
 		break;
 	case RTW89_CH_5G_BAND_3:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_5ga_p[1];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_5ga_n[1];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_5gb_p[1];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_5gb_n[1];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GA_P][1] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5ga_p[1];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GA_N][1] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_5ga_n[1];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GB_P][1] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5gb_p[1];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GB_N][1] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_5gb_n[1];
 		break;
 	case RTW89_CH_5G_BAND_4:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_5ga_p[2];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_5ga_n[2];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_5gb_p[2];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_5gb_n[2];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GA_P][2] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5ga_p[2];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GA_N][2] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_5ga_n[2];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GB_P][2] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_5gb_p[2];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_5GB_N][2] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_5gb_n[2];
 		break;
 	case RTW89_CH_6G_BAND_IDX0:
 	case RTW89_CH_6G_BAND_IDX1:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[0];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[0];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[0];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[0];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_P][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[0];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_N][0] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[0];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_P][0] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[0];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_N][0] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[0];
 		break;
 	case RTW89_CH_6G_BAND_IDX2:
 	case RTW89_CH_6G_BAND_IDX3:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[1];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[1];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[1];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[1];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_P][1] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[1];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_N][1] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[1];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_P][1] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[1];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_N][1] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[1];
 		break;
 	case RTW89_CH_6G_BAND_IDX4:
 	case RTW89_CH_6G_BAND_IDX5:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[2];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[2];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[2];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[2];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_P][2] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[2];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_N][2] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[2];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_P][2] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[2];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_N][2] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[2];
 		break;
 	case RTW89_CH_6G_BAND_IDX6:
 	case RTW89_CH_6G_BAND_IDX7:
-		thm_up_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[3];
-		thm_down_a = rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[3];
-		thm_up_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[3];
-		thm_down_b = rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[3];
+		thm_up_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_P][3] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6ga_p[3];
+		thm_down_a = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GA_N][3] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6ga_n[3];
+		thm_up_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_P][3] :
+				 rtw89_8852c_trk_cfg.delta_swingidx_6gb_p[3];
+		thm_down_b = trk ? trk->delta[RTW89_FW_TXPWR_TRK_TYPE_6GB_N][3] :
+				   rtw89_8852c_trk_cfg.delta_swingidx_6gb_n[3];
 		break;
 	}
 
-- 
cgit v1.3-3-g829e


From 82baae10d822747e7aa35cc6903f11729ec23820 Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Fri, 9 Aug 2024 15:20:08 +0800
Subject: wifi: rtw89: 8922a: add digital compensation to avoid TX EVM degrade

TX EVM will significantly decrease for long packets when
the TX idle time increases. Introduce digital compensation
based on TX idle time, to mitigate TX EVM degradation, and
TX throughput improved from 1871 to 1947 Mbps.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240809072012.84152-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h      | 11 +++++
 drivers/net/wireless/realtek/rtw89/ps.c        |  7 +--
 drivers/net/wireless/realtek/rtw89/reg.h       |  3 ++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  | 61 +++++++++++++++++++++++++-
 9 files changed, 82 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index b42a33b9868a..3edb2f4372e4 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3566,6 +3566,8 @@ struct rtw89_chip_ops {
 	void (*cfg_txrx_path)(struct rtw89_dev *rtwdev);
 	void (*set_txpwr_ul_tb_offset)(struct rtw89_dev *rtwdev,
 				       s8 pw_ofst, enum rtw89_mac_idx mac_idx);
+	void (*digital_pwr_comp)(struct rtw89_dev *rtwdev,
+				 enum rtw89_phy_idx phy_idx);
 	int (*pwr_on_func)(struct rtw89_dev *rtwdev);
 	int (*pwr_off_func)(struct rtw89_dev *rtwdev);
 	void (*query_rxdesc)(struct rtw89_dev *rtwdev,
@@ -6274,6 +6276,15 @@ void rtw89_chip_cfg_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 		chip->ops->set_txpwr_ul_tb_offset(rtwdev, 0, rtwvif->mac_idx);
 }
 
+static inline void rtw89_chip_digital_pwr_comp(struct rtw89_dev *rtwdev,
+					       enum rtw89_phy_idx phy_idx)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	if (chip->ops->digital_pwr_comp)
+		chip->ops->digital_pwr_comp(rtwdev, phy_idx);
+}
+
 static inline void rtw89_load_txpwr_table(struct rtw89_dev *rtwdev,
 					  const struct rtw89_txpwr_table *tbl)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c
index 92074b73ebeb..aebd6404f802 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.c
+++ b/drivers/net/wireless/realtek/rtw89/ps.c
@@ -98,10 +98,10 @@ static void __rtw89_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif
 	rtw89_fw_h2c_lps_ch_info(rtwdev, rtwvif);
 }
 
-static void __rtw89_leave_lps(struct rtw89_dev *rtwdev, u8 mac_id)
+static void __rtw89_leave_lps(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
 	struct rtw89_lps_parm lps_param = {
-		.macid = mac_id,
+		.macid = rtwvif->mac_id,
 		.psmode = RTW89_MAC_AX_PS_MODE_ACTIVE,
 		.lastrpwm = RTW89_LAST_RPWM_ACTIVE,
 	};
@@ -109,6 +109,7 @@ static void __rtw89_leave_lps(struct rtw89_dev *rtwdev, u8 mac_id)
 	rtw89_fw_h2c_lps_parm(rtwdev, &lps_param);
 	rtw89_fw_leave_lps_check(rtwdev, 0);
 	rtw89_btc_ntfy_radio_state(rtwdev, BTC_RFCTRL_WL_ON);
+	rtw89_chip_digital_pwr_comp(rtwdev, rtwvif->phy_idx);
 }
 
 void rtw89_leave_ps_mode(struct rtw89_dev *rtwdev)
@@ -137,7 +138,7 @@ static void rtw89_leave_lps_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwv
 	    rtwvif->wifi_role != RTW89_WIFI_ROLE_P2P_CLIENT)
 		return;
 
-	__rtw89_leave_lps(rtwdev, rtwvif->mac_id);
+	__rtw89_leave_lps(rtwdev, rtwvif);
 }
 
 void rtw89_leave_lps(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 7afec48c4056..eacf9161db2c 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -6044,6 +6044,9 @@
 #define R_BE_WP_PAGE_INFO1 0xB7AC
 #define B_BE_WP_AVAL_PG_MASK GENMASK(28, 16)
 
+#define R_BE_LTPC_T0_PATH0 0xBA28
+#define R_BE_LTPC_T0_PATH1 0xBB28
+
 #define R_BE_CMAC_SHARE_FUNC_EN 0x0E000
 #define B_BE_CMAC_SHARE_CRPRT BIT(31)
 #define B_BE_CMAC_SHARE_EN BIT(30)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index e6463035a7af..d1358b9a73f9 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2388,6 +2388,7 @@ static const struct rtw89_chip_ops rtw8851b_chip_ops = {
 	.ctrl_nbtg_bt_tx	= rtw8851b_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8851b_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8851b_set_txpwr_ul_tb_offset,
+	.digital_pwr_comp	= NULL,
 	.pwr_on_func		= rtw8851b_pwr_on_func,
 	.pwr_off_func		= rtw8851b_pwr_off_func,
 	.query_rxdesc		= rtw89_core_query_rxdesc,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 7ea388fa0657..b073e041a16b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2111,6 +2111,7 @@ static const struct rtw89_chip_ops rtw8852a_chip_ops = {
 	.ctrl_nbtg_bt_tx	= rtw8852a_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= NULL,
 	.set_txpwr_ul_tb_offset	= rtw8852a_set_txpwr_ul_tb_offset,
+	.digital_pwr_comp	= NULL,
 	.pwr_on_func		= NULL,
 	.pwr_off_func		= NULL,
 	.query_rxdesc		= rtw89_core_query_rxdesc,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index f26979b89cc9..36a81c3323f8 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -742,6 +742,7 @@ static const struct rtw89_chip_ops rtw8852b_chip_ops = {
 	.ctrl_nbtg_bt_tx	= rtw8852bx_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8852bx_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8852bx_set_txpwr_ul_tb_offset,
+	.digital_pwr_comp	= NULL,
 	.pwr_on_func		= rtw8852b_pwr_on_func,
 	.pwr_off_func		= rtw8852b_pwr_off_func,
 	.query_rxdesc		= rtw89_core_query_rxdesc,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index fb98ef9dbc54..647bc98bcc5d 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -676,6 +676,7 @@ static const struct rtw89_chip_ops rtw8852bt_chip_ops = {
 	.ctrl_nbtg_bt_tx	= rtw8852bx_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8852bx_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8852bx_set_txpwr_ul_tb_offset,
+	.digital_pwr_comp	= NULL,
 	.pwr_on_func		= rtw8852bt_pwr_on_func,
 	.pwr_off_func		= rtw8852bt_pwr_off_func,
 	.query_rxdesc		= rtw89_core_query_rxdesc,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index dc1da9ff055c..65e61a2ede27 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2891,6 +2891,7 @@ static const struct rtw89_chip_ops rtw8852c_chip_ops = {
 	.ctrl_nbtg_bt_tx	= rtw8852c_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8852c_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8852c_set_txpwr_ul_tb_offset,
+	.digital_pwr_comp	= NULL,
 	.pwr_on_func		= rtw8852c_pwr_on_func,
 	.pwr_off_func		= rtw8852c_pwr_off_func,
 	.query_rxdesc		= rtw89_core_query_rxdesc,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 6004a622d244..7f4ac8b63e48 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -1689,6 +1689,60 @@ static int rtw8922a_ctrl_rx_path_tmac(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+#define DIGITAL_PWR_COMP_REG_NUM 22
+static const u32 rtw8922a_digital_pwr_comp_val[][DIGITAL_PWR_COMP_REG_NUM] = {
+	{0x012C0096, 0x044C02BC, 0x00322710, 0x015E0096, 0x03C8028A,
+	 0x0BB80708, 0x17701194, 0x02020100, 0x03030303, 0x01000303,
+	 0x05030302, 0x06060605, 0x06050300, 0x0A090807, 0x02000B0B,
+	 0x09080604, 0x0D0D0C0B, 0x08060400, 0x110F0C0B, 0x05001111,
+	 0x0D0C0907, 0x12121210},
+	{0x012C0096, 0x044C02BC, 0x00322710, 0x015E0096, 0x03C8028A,
+	 0x0BB80708, 0x17701194, 0x04030201, 0x05050505, 0x01000505,
+	 0x07060504, 0x09090908, 0x09070400, 0x0E0D0C0B, 0x03000E0E,
+	 0x0D0B0907, 0x1010100F, 0x0B080500, 0x1512100D, 0x05001515,
+	 0x100D0B08, 0x15151512},
+};
+
+static void rtw8922a_set_digital_pwr_comp(struct rtw89_dev *rtwdev,
+					  bool enable, u8 nss,
+					  enum rtw89_rf_path path)
+{
+	static const u32 ltpc_t0[2] = {R_BE_LTPC_T0_PATH0, R_BE_LTPC_T0_PATH1};
+	const u32 *digital_pwr_comp;
+	u32 addr, val;
+	u32 i;
+
+	if (nss == 1)
+		digital_pwr_comp = rtw8922a_digital_pwr_comp_val[0];
+	else
+		digital_pwr_comp = rtw8922a_digital_pwr_comp_val[1];
+
+	addr = ltpc_t0[path];
+	for (i = 0; i < DIGITAL_PWR_COMP_REG_NUM; i++, addr += 4) {
+		val = enable ? digital_pwr_comp[i] : 0;
+		rtw89_phy_write32(rtwdev, addr, val);
+	}
+}
+
+static void rtw8922a_digital_pwr_comp(struct rtw89_dev *rtwdev,
+				      enum rtw89_phy_idx phy_idx)
+{
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	bool enable = chan->band_type != RTW89_BAND_2G;
+	u8 path;
+
+	if (rtwdev->mlo_dbcc_mode == MLO_1_PLUS_1_1RF) {
+		if (phy_idx == RTW89_PHY_0)
+			path = RF_PATH_A;
+		else
+			path = RF_PATH_B;
+		rtw8922a_set_digital_pwr_comp(rtwdev, enable, 1, path);
+	} else {
+		rtw8922a_set_digital_pwr_comp(rtwdev, enable, 2, RF_PATH_A);
+		rtw8922a_set_digital_pwr_comp(rtwdev, enable, 2, RF_PATH_B);
+	}
+}
+
 static int rtw8922a_ctrl_mlo(struct rtw89_dev *rtwdev, enum rtw89_mlo_dbcc_mode mode)
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
@@ -1810,11 +1864,13 @@ static void rtw8922a_pre_set_channel_bb(struct rtw89_dev *rtwdev,
 }
 
 static void rtw8922a_post_set_channel_bb(struct rtw89_dev *rtwdev,
-					 enum rtw89_mlo_dbcc_mode mode)
+					 enum rtw89_mlo_dbcc_mode mode,
+					 enum rtw89_phy_idx phy_idx)
 {
 	if (!rtwdev->dbcc_en)
 		return;
 
+	rtw8922a_digital_pwr_comp(rtwdev, phy_idx);
 	rtw8922a_ctrl_mlo(rtwdev, mode);
 }
 
@@ -1921,7 +1977,7 @@ static void rtw8922a_set_channel_help(struct rtw89_dev *rtwdev, bool enter,
 	rtw8922a_hal_reset(rtwdev, phy_idx, mac_idx, chan->band_type, &p->tx_en, enter);
 
 	if (!enter) {
-		rtw8922a_post_set_channel_bb(rtwdev, rtwdev->mlo_dbcc_mode);
+		rtw8922a_post_set_channel_bb(rtwdev, rtwdev->mlo_dbcc_mode, phy_idx);
 		rtw8922a_post_set_channel_rf(rtwdev, phy_idx);
 	}
 }
@@ -2494,6 +2550,7 @@ static const struct rtw89_chip_ops rtw8922a_chip_ops = {
 	.ctrl_nbtg_bt_tx	= rtw8922a_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8922a_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= NULL,
+	.digital_pwr_comp	= rtw8922a_digital_pwr_comp,
 	.pwr_on_func		= rtw8922a_pwr_on_func,
 	.pwr_off_func		= rtw8922a_pwr_off_func,
 	.query_rxdesc		= rtw89_core_query_rxdesc_v2,
-- 
cgit v1.3-3-g829e


From 56310ddb50b190b3390fdc974aec455d0a516bd2 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 9 Aug 2024 15:20:09 +0800
Subject: wifi: rtw89: remove unused C2H event ID
 RTW89_MAC_C2H_FUNC_READ_WOW_CAM to prevent out-of-bounds reading

The handler of firmware C2H event RTW89_MAC_C2H_FUNC_READ_WOW_CAM isn't
implemented, but driver expects number of handlers is
NUM_OF_RTW89_MAC_C2H_FUNC_WOW causing out-of-bounds access. Fix it by
removing ID.

Addresses-Coverity-ID: 1598775 ("Out-of-bounds read")

Fixes: ff53fce5c78b ("wifi: rtw89: wow: update latest PTK GTK info to mac80211 after resume")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240809072012.84152-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 9d3be36ffb6e..67c2a4507124 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -421,7 +421,6 @@ enum rtw89_mac_c2h_mrc_func {
 
 enum rtw89_mac_c2h_wow_func {
 	RTW89_MAC_C2H_FUNC_AOAC_REPORT,
-	RTW89_MAC_C2H_FUNC_READ_WOW_CAM,
 
 	NUM_OF_RTW89_MAC_C2H_FUNC_WOW,
 };
-- 
cgit v1.3-3-g829e


From 45742881f9eee2a4daeb6008e648a460dd3742cd Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 9 Aug 2024 15:20:10 +0800
Subject: wifi: rtw89: correct base HT rate mask for firmware

Coverity reported that u8 rx_mask << 24 will become signed 32 bits, which
casting to unsigned 64 bits will do sign extension. For example,
putting 0x80000000 (signed 32 bits) to a u64 variable will become
0xFFFFFFFF_80000000.

The real case we meet is:
  rx_mask[0...3] = ff ff 00 00
  ra_mask = 0xffffffff_ff0ff000

After this fix:
  rx_mask[0...3] = ff ff 00 00
  ra_mask = 0x00000000_ff0ff000

Fortunately driver does bitwise-AND with incorrect ra_mask and supported
rates (1ss and 2ss rate only) afterward, so the final rate mask of
original code is still correct.

Addresses-Coverity-ID: 1504762 ("Unintended sign extension")

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240809072012.84152-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/phy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index aa4fc9115995..7306fb679e95 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -356,8 +356,8 @@ static void rtw89_phy_ra_sta_update(struct rtw89_dev *rtwdev,
 		csi_mode = RTW89_RA_RPT_MODE_HT;
 		ra_mask |= ((u64)sta->deflink.ht_cap.mcs.rx_mask[3] << 48) |
 			   ((u64)sta->deflink.ht_cap.mcs.rx_mask[2] << 36) |
-			   (sta->deflink.ht_cap.mcs.rx_mask[1] << 24) |
-			   (sta->deflink.ht_cap.mcs.rx_mask[0] << 12);
+			   ((u64)sta->deflink.ht_cap.mcs.rx_mask[1] << 24) |
+			   ((u64)sta->deflink.ht_cap.mcs.rx_mask[0] << 12);
 		high_rate_masks = rtw89_ra_mask_ht_rates;
 		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)
 			stbc_en = 1;
-- 
cgit v1.3-3-g829e


From 338c9cba8d6f16c79c58c20d68561505a8170765 Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Fri, 9 Aug 2024 15:20:11 +0800
Subject: wifi: rtw89: 8852a: adjust ANA clock to 12M

To reduce the I/O time from power save mode for 8852a,
adjust ANA clock from 500k to 12M.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240809072012.84152-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852a.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index b073e041a16b..1cbea8d665a2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -337,6 +337,11 @@ static const struct rtw89_pwr_cfg rtw8852a_pwroff[] = {
 	 PWR_INTF_MSK_PCIE,
 	 PWR_BASE_MAC,
 	 PWR_CMD_WRITE, BIT(0), 0},
+	{0x0092,
+	 PWR_CV_MSK_ALL,
+	 PWR_INTF_MSK_PCIE,
+	 PWR_BASE_MAC,
+	 PWR_CMD_WRITE, BIT(4), BIT(4)},
 	{0x0005,
 	 PWR_CV_MSK_ALL,
 	 PWR_INTF_MSK_PCIE,
-- 
cgit v1.3-3-g829e


From 77c977327dfaa9ae2e154964cdb89ceb5c7b7cf1 Mon Sep 17 00:00:00 2001
From: Dmitry Kandybka <d.kandybka@gmail.com>
Date: Fri, 9 Aug 2024 11:53:10 +0300
Subject: wifi: rtw88: remove CPT execution branch never used

In 'rtw_coex_action_bt_a2dp_pan', 'wl_cpt_test' and 'bt_cpt_test' are
hardcoded to false, so corresponding 'table_case' and 'tdma_case'
assignments are never met.
Also 'rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[1])' is never
executed. Assuming that CPT was never fully implemented, remove
lookalike leftovers. Compile tested only.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 76f631cb401f ("rtw88: coex: update the mechanism for A2DP + PAN")

Signed-off-by: Dmitry Kandybka <d.kandybka@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240809085310.10512-1-d.kandybka@gmail.com
---
 drivers/net/wireless/realtek/rtw88/coex.c | 38 ++++++++-----------------------
 1 file changed, 10 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/coex.c b/drivers/net/wireless/realtek/rtw88/coex.c
index de3332eb7a22..a99776af56c2 100644
--- a/drivers/net/wireless/realtek/rtw88/coex.c
+++ b/drivers/net/wireless/realtek/rtw88/coex.c
@@ -2194,7 +2194,6 @@ static void rtw_coex_action_bt_a2dp_pan(struct rtw_dev *rtwdev)
 	struct rtw_coex_stat *coex_stat = &coex->stat;
 	struct rtw_efuse *efuse = &rtwdev->efuse;
 	u8 table_case, tdma_case;
-	bool wl_cpt_test = false, bt_cpt_test = false;
 
 	rtw_dbg(rtwdev, RTW_DBG_COEX, "[BTCoex], %s()\n", __func__);
 
@@ -2202,29 +2201,16 @@ static void rtw_coex_action_bt_a2dp_pan(struct rtw_dev *rtwdev)
 	rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]);
 	if (efuse->share_ant) {
 		/* Shared-Ant */
-		if (wl_cpt_test) {
-			if (coex_stat->wl_gl_busy) {
-				table_case = 20;
-				tdma_case = 17;
-			} else {
-				table_case = 10;
-				tdma_case = 15;
-			}
-		} else if (bt_cpt_test) {
-			table_case = 26;
-			tdma_case = 26;
-		} else {
-			if (coex_stat->wl_gl_busy &&
-			    coex_stat->wl_noisy_level == 0)
-				table_case = 14;
-			else
-				table_case = 10;
+		if (coex_stat->wl_gl_busy &&
+		    coex_stat->wl_noisy_level == 0)
+			table_case = 14;
+		else
+			table_case = 10;
 
-			if (coex_stat->wl_gl_busy)
-				tdma_case = 15;
-			else
-				tdma_case = 20;
-		}
+		if (coex_stat->wl_gl_busy)
+			tdma_case = 15;
+		else
+			tdma_case = 20;
 	} else {
 		/* Non-Shared-Ant */
 		table_case = 112;
@@ -2235,11 +2221,7 @@ static void rtw_coex_action_bt_a2dp_pan(struct rtw_dev *rtwdev)
 			tdma_case = 120;
 	}
 
-	if (wl_cpt_test)
-		rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[1]);
-	else
-		rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]);
-
+	rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]);
 	rtw_coex_table(rtwdev, false, table_case);
 	rtw_coex_tdma(rtwdev, false, tdma_case);
 }
-- 
cgit v1.3-3-g829e


From 2140e63cd87fa707acf514d594725097bed018fd Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 12 Aug 2024 09:30:44 +0200
Subject: ethtool: Add new result codes for TDR diagnostics

Add new result codes to support TDR diagnostics in preparation for
Open Alliance 1000BaseT1 TDR support:

- ETHTOOL_A_CABLE_RESULT_CODE_NOISE: TDR not possible due to high noise
  level.
- ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE: TDR resolution not
  possible / out of distance.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240812073046.1728288-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/ethtool_netlink.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 93c57525a975..9074fa309bd6 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -556,6 +556,10 @@ enum {
 	 * a regular 100 Ohm cable and a part with the abnormal impedance value
 	 */
 	ETHTOOL_A_CABLE_RESULT_CODE_IMPEDANCE_MISMATCH,
+	/* TDR not possible due to high noise level */
+	ETHTOOL_A_CABLE_RESULT_CODE_NOISE,
+	/* TDR resolution not possible / out of distance */
+	ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE,
 };
 
 enum {
-- 
cgit v1.3-3-g829e


From 9e7c1a9b90334d3c87467f0204bf2bcd9794c22c Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 12 Aug 2024 09:30:45 +0200
Subject: phy: Add Open Alliance helpers for the PHY framework

Introduce helper functions specific to Open Alliance diagnostics,
integrating them into the PHY framework. Currently, these helpers
are limited to 1000BaseT1 specific TDR functionality.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240812073046.1728288-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Kconfig                 |  3 ++
 drivers/net/phy/Makefile                |  1 +
 drivers/net/phy/open_alliance_helpers.c | 77 +++++++++++++++++++++++++++++++++
 drivers/net/phy/open_alliance_helpers.h | 47 ++++++++++++++++++++
 4 files changed, 128 insertions(+)
 create mode 100644 drivers/net/phy/open_alliance_helpers.c
 create mode 100644 drivers/net/phy/open_alliance_helpers.h

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 7fddc8306d82..874422e530ff 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -44,6 +44,9 @@ config LED_TRIGGER_PHY
 		<Speed in megabits>Mbps OR <Speed in gigabits>Gbps OR link
 		for any speed known to the PHY.
 
+config OPEN_ALLIANCE_HELPERS
+	bool
+
 config PHYLIB_LEDS
 	def_bool OF
 	depends on LEDS_CLASS=y || LEDS_CLASS=PHYLIB
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 202ed7f450da..f086a606a87e 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -22,6 +22,7 @@ endif
 obj-$(CONFIG_MDIO_DEVRES)	+= mdio_devres.o
 libphy-$(CONFIG_SWPHY)		+= swphy.o
 libphy-$(CONFIG_LED_TRIGGER_PHY)	+= phy_led_triggers.o
+libphy-$(CONFIG_OPEN_ALLIANCE_HELPERS) += open_alliance_helpers.o
 
 obj-$(CONFIG_PHYLINK)		+= phylink.o
 obj-$(CONFIG_PHYLIB)		+= libphy.o
diff --git a/drivers/net/phy/open_alliance_helpers.c b/drivers/net/phy/open_alliance_helpers.c
new file mode 100644
index 000000000000..36a70451d7da
--- /dev/null
+++ b/drivers/net/phy/open_alliance_helpers.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * open_alliance_helpers.c - OPEN Alliance specific PHY diagnostic helpers
+ *
+ * This file contains helper functions for implementing advanced diagnostic
+ * features as specified by the OPEN Alliance for automotive Ethernet PHYs.
+ * These helpers include functionality for Time Delay Reflection (TDR), dynamic
+ * channel quality assessment, and other PHY diagnostics.
+ *
+ * For more information on the specifications, refer to the OPEN Alliance
+ * documentation: https://opensig.org/automotive-ethernet-specifications/
+ * Currently following specifications are partially or fully implemented:
+ * - Advanced diagnostic features for 1000BASE-T1 automotive Ethernet PHYs.
+ *   TC12 - advanced PHY features.
+ *   https://opensig.org/wp-content/uploads/2024/03/Advanced_PHY_features_for_automotive_Ethernet_v2.0_fin.pdf
+ */
+
+#include <linux/bitfield.h>
+#include <linux/ethtool_netlink.h>
+
+#include "open_alliance_helpers.h"
+
+/**
+ * oa_1000bt1_get_ethtool_cable_result_code - Convert TDR status to ethtool
+ *					      result code
+ * @reg_value: Value read from the TDR register
+ *
+ * This function takes a register value from the HDD.TDR register and converts
+ * the TDR status to the corresponding ethtool cable test result code.
+ *
+ * Return: The appropriate ethtool result code based on the TDR status
+ */
+int oa_1000bt1_get_ethtool_cable_result_code(u16 reg_value)
+{
+	u8 tdr_status = FIELD_GET(OA_1000BT1_HDD_TDR_STATUS_MASK, reg_value);
+	u8 dist_val = FIELD_GET(OA_1000BT1_HDD_TDR_DISTANCE_MASK, reg_value);
+
+	switch (tdr_status) {
+	case OA_1000BT1_HDD_TDR_STATUS_CABLE_OK:
+		return ETHTOOL_A_CABLE_RESULT_CODE_OK;
+	case OA_1000BT1_HDD_TDR_STATUS_OPEN:
+		return ETHTOOL_A_CABLE_RESULT_CODE_OPEN;
+	case OA_1000BT1_HDD_TDR_STATUS_SHORT:
+		return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT;
+	case OA_1000BT1_HDD_TDR_STATUS_NOISE:
+		return ETHTOOL_A_CABLE_RESULT_CODE_NOISE;
+	default:
+		if (dist_val == OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE)
+			return ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE;
+		return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC;
+	}
+}
+EXPORT_SYMBOL_GPL(oa_1000bt1_get_ethtool_cable_result_code);
+
+/**
+ * oa_1000bt1_get_tdr_distance - Get distance to the main fault from TDR
+ *				 register value
+ * @reg_value: Value read from the TDR register
+ *
+ * This function takes a register value from the HDD.TDR register and extracts
+ * the distance to the main fault detected by the TDR feature. The distance is
+ * measured in centimeters and ranges from 0 to 3100 centimeters. If the
+ * distance is not available (0x3f), the function returns -ERANGE.
+ *
+ * Return: The distance to the main fault in centimeters, or -ERANGE if the
+ * resolution is not possible.
+ */
+int oa_1000bt1_get_tdr_distance(u16 reg_value)
+{
+	u8 dist_val = FIELD_GET(OA_1000BT1_HDD_TDR_DISTANCE_MASK, reg_value);
+
+	if (dist_val == OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE)
+		return -ERANGE;
+
+	return dist_val * 100;
+}
+EXPORT_SYMBOL_GPL(oa_1000bt1_get_tdr_distance);
diff --git a/drivers/net/phy/open_alliance_helpers.h b/drivers/net/phy/open_alliance_helpers.h
new file mode 100644
index 000000000000..8b7d97bc6f18
--- /dev/null
+++ b/drivers/net/phy/open_alliance_helpers.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef OPEN_ALLIANCE_HELPERS_H
+#define OPEN_ALLIANCE_HELPERS_H
+
+/*
+ * These defines reflect the TDR (Time Delay Reflection) diagnostic feature
+ * for 1000BASE-T1 automotive Ethernet PHYs as specified by the OPEN Alliance.
+ *
+ * The register values are part of the HDD.TDR register, which provides
+ * information about the cable status and faults. The exact register offset
+ * is device-specific and should be provided by the driver.
+ */
+#define OA_1000BT1_HDD_TDR_ACTIVATION_MASK		GENMASK(1, 0)
+#define OA_1000BT1_HDD_TDR_ACTIVATION_OFF		1
+#define OA_1000BT1_HDD_TDR_ACTIVATION_ON		2
+
+#define OA_1000BT1_HDD_TDR_STATUS_MASK			GENMASK(7, 4)
+#define OA_1000BT1_HDD_TDR_STATUS_SHORT			3
+#define OA_1000BT1_HDD_TDR_STATUS_OPEN			6
+#define OA_1000BT1_HDD_TDR_STATUS_NOISE			5
+#define OA_1000BT1_HDD_TDR_STATUS_CABLE_OK		7
+#define OA_1000BT1_HDD_TDR_STATUS_TEST_IN_PROGRESS	8
+#define OA_1000BT1_HDD_TDR_STATUS_TEST_NOT_POSSIBLE	13
+
+/*
+ * OA_1000BT1_HDD_TDR_DISTANCE_MASK:
+ * This mask is used to extract the distance to the first/main fault
+ * detected by the TDR feature. Each bit represents an approximate distance
+ * of 1 meter, ranging from 0 to 31 meters. The exact interpretation of the
+ * bits may vary, but generally:
+ * 000000 = no error
+ * 000001 = error about 0-1m away
+ * 000010 = error between 1-2m away
+ * ...
+ * 011111 = error about 30-31m away
+ * 111111 = resolution not possible / out of distance
+ */
+#define OA_1000BT1_HDD_TDR_DISTANCE_MASK			GENMASK(13, 8)
+#define OA_1000BT1_HDD_TDR_DISTANCE_NO_ERROR			0
+#define OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE	0x3f
+
+int oa_1000bt1_get_ethtool_cable_result_code(u16 reg_value);
+int oa_1000bt1_get_tdr_distance(u16 reg_value);
+
+#endif /* OPEN_ALLIANCE_HELPERS_H */
+
-- 
cgit v1.3-3-g829e


From 20f77dc7247138c0c1463920f6d9829593804848 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 12 Aug 2024 09:30:46 +0200
Subject: net: phy: dp83tg720: Add cable testing support

Introduce cable testing support for the DP83TG720 PHY. This implementation
is based on the "DP83TG720S-Q1: Configuring for Open Alliance Specification
Compliance (Rev. B)" application note.

The feature has been tested with cables of various lengths:
- No cable: 1m till open reported.
- 5 meter cable: reported properly.
- 20 meter cable: reported as 19m.
- 40 meter cable: reported as cable ok.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240812073046.1728288-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Kconfig     |   1 +
 drivers/net/phy/dp83tg720.c | 154 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 155 insertions(+)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 874422e530ff..f530fcd092fe 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -417,6 +417,7 @@ config DP83TD510_PHY
 
 config DP83TG720_PHY
 	tristate "Texas Instruments DP83TG720 Ethernet 1000Base-T1 PHY"
+	select OPEN_ALLIANCE_HELPERS
 	help
 	  The DP83TG720S-Q1 is an automotive Ethernet physical layer
 	  transceiver compliant with IEEE 802.3bp and Open Alliance
diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c
index c706429b225a..0ef4d7dba065 100644
--- a/drivers/net/phy/dp83tg720.c
+++ b/drivers/net/phy/dp83tg720.c
@@ -3,10 +3,13 @@
  * Copyright (c) 2023 Pengutronix, Oleksij Rempel <kernel@pengutronix.de>
  */
 #include <linux/bitfield.h>
+#include <linux/ethtool_netlink.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/phy.h>
 
+#include "open_alliance_helpers.h"
+
 #define DP83TG720S_PHY_ID			0x2000a284
 
 /* MDIO_MMD_VEND2 registers */
@@ -14,6 +17,17 @@
 #define DP83TG720S_STS_MII_INT			BIT(7)
 #define DP83TG720S_LINK_STATUS			BIT(0)
 
+/* TDR Configuration Register (0x1E) */
+#define DP83TG720S_TDR_CFG			0x1e
+/* 1b = TDR start, 0b = No TDR */
+#define DP83TG720S_TDR_START			BIT(15)
+/* 1b = TDR auto on link down, 0b = Manual TDR start */
+#define DP83TG720S_CFG_TDR_AUTO_RUN		BIT(14)
+/* 1b = TDR done, 0b = TDR in progress */
+#define DP83TG720S_TDR_DONE			BIT(1)
+/* 1b = TDR fail, 0b = TDR success */
+#define DP83TG720S_TDR_FAIL			BIT(0)
+
 #define DP83TG720S_PHY_RESET			0x1f
 #define DP83TG720S_HW_RESET			BIT(15)
 
@@ -22,18 +36,155 @@
 /* Power Mode 0 is Normal mode */
 #define DP83TG720S_LPS_CFG3_PWR_MODE_0		BIT(0)
 
+/* Open Aliance 1000BaseT1 compatible HDD.TDR Fault Status Register */
+#define DP83TG720S_TDR_FAULT_STATUS		0x30f
+
+/* Register 0x0301: TDR Configuration 2 */
+#define DP83TG720S_TDR_CFG2			0x301
+
+/* Register 0x0303: TDR Configuration 3 */
+#define DP83TG720S_TDR_CFG3			0x303
+
+/* Register 0x0304: TDR Configuration 4 */
+#define DP83TG720S_TDR_CFG4			0x304
+
+/* Register 0x0405: Unknown Register */
+#define DP83TG720S_UNKNOWN_0405			0x405
+
+/* Register 0x0576: TDR Master Link Down Control */
+#define DP83TG720S_TDR_MASTER_LINK_DOWN		0x576
+
 #define DP83TG720S_RGMII_DELAY_CTRL		0x602
 /* In RGMII mode, Enable or disable the internal delay for RXD */
 #define DP83TG720S_RGMII_RX_CLK_SEL		BIT(1)
 /* In RGMII mode, Enable or disable the internal delay for TXD */
 #define DP83TG720S_RGMII_TX_CLK_SEL		BIT(0)
 
+/* Register 0x083F: Unknown Register */
+#define DP83TG720S_UNKNOWN_083F			0x83f
+
 #define DP83TG720S_SQI_REG_1			0x871
 #define DP83TG720S_SQI_OUT_WORST		GENMASK(7, 5)
 #define DP83TG720S_SQI_OUT			GENMASK(3, 1)
 
 #define DP83TG720_SQI_MAX			7
 
+/**
+ * dp83tg720_cable_test_start - Start the cable test for the DP83TG720 PHY.
+ * @phydev: Pointer to the phy_device structure.
+ *
+ * This sequence is based on the documented procedure for the DP83TG720 PHY.
+ *
+ * Returns: 0 on success, a negative error code on failure.
+ */
+static int dp83tg720_cable_test_start(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Initialize the PHY to run the TDR test as described in the
+	 * "DP83TG720S-Q1: Configuring for Open Alliance Specification
+	 * Compliance (Rev. B)" application note.
+	 * Most of the registers are not documented. Some of register names
+	 * are guessed by comparing the register offsets with the DP83TD510E.
+	 */
+
+	/* Force master link down */
+	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2,
+			       DP83TG720S_TDR_MASTER_LINK_DOWN, 0x0400);
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG2,
+			    0xa008);
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG3,
+			    0x0928);
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG4,
+			    0x0004);
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_UNKNOWN_0405,
+			    0x6400);
+	if (ret)
+		return ret;
+
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_UNKNOWN_083F,
+			    0x3003);
+	if (ret)
+		return ret;
+
+	/* Start the TDR */
+	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG,
+			       DP83TG720S_TDR_START);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/**
+ * dp83tg720_cable_test_get_status - Get the status of the cable test for the
+ *                                   DP83TG720 PHY.
+ * @phydev: Pointer to the phy_device structure.
+ * @finished: Pointer to a boolean that indicates whether the test is finished.
+ *
+ * The function sets the @finished flag to true if the test is complete.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static int dp83tg720_cable_test_get_status(struct phy_device *phydev,
+					   bool *finished)
+{
+	int ret, stat;
+
+	*finished = false;
+
+	/* Read the TDR status */
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG);
+	if (ret < 0)
+		return ret;
+
+	/* Check if the TDR test is done */
+	if (!(ret & DP83TG720S_TDR_DONE))
+		return 0;
+
+	/* Check for TDR test failure */
+	if (!(ret & DP83TG720S_TDR_FAIL)) {
+		int location;
+
+		/* Read fault status */
+		ret = phy_read_mmd(phydev, MDIO_MMD_VEND2,
+				   DP83TG720S_TDR_FAULT_STATUS);
+		if (ret < 0)
+			return ret;
+
+		/* Get fault type */
+		stat = oa_1000bt1_get_ethtool_cable_result_code(ret);
+
+		/* Determine fault location */
+		location = oa_1000bt1_get_tdr_distance(ret);
+		if (location > 0)
+			ethnl_cable_test_fault_length(phydev,
+						      ETHTOOL_A_CABLE_PAIR_A,
+						      location);
+	} else {
+		/* Active link partner or other issues */
+		stat = ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC;
+	}
+
+	*finished = true;
+
+	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, stat);
+
+	return phy_init_hw(phydev);
+}
+
 static int dp83tg720_config_aneg(struct phy_device *phydev)
 {
 	int ret;
@@ -195,12 +346,15 @@ static struct phy_driver dp83tg720_driver[] = {
 	PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID),
 	.name		= "TI DP83TG720S",
 
+	.flags          = PHY_POLL_CABLE_TEST,
 	.config_aneg	= dp83tg720_config_aneg,
 	.read_status	= dp83tg720_read_status,
 	.get_features	= genphy_c45_pma_read_ext_abilities,
 	.config_init	= dp83tg720_config_init,
 	.get_sqi	= dp83tg720_get_sqi,
 	.get_sqi_max	= dp83tg720_get_sqi_max,
+	.cable_test_start = dp83tg720_cable_test_start,
+	.cable_test_get_status = dp83tg720_cable_test_get_status,
 
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
-- 
cgit v1.3-3-g829e


From 6a66873d820b4bd87a7c3f8e21b8bf4a76fa3223 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Tue, 13 Aug 2024 16:27:35 +0200
Subject: dt-bindings: net: dsa: microchip: add microchip,pme-active-high flag

Add microchip,pme-active-high property to set the PME (Power
Management Event) pin polarity for Wake on Lan interrupts.

Note that the polarity is active-low by default.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240813142750.772781-2-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
index 52acc15ebcbf..c589ebc2c7be 100644
--- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
@@ -51,6 +51,11 @@ properties:
       Set if the output SYNCLKO clock should be disabled. Do not mix with
       microchip,synclko-125.
 
+  microchip,pme-active-high:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description:
+      Indicates if the PME pin polarity is active-high.
+
   microchip,io-drive-strength-microamp:
     description:
       IO Pad Drive Strength
-- 
cgit v1.3-3-g829e


From f3ac6198a719857c492b04b0a8eb22c2cc81197b Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Tue, 13 Aug 2024 16:27:36 +0200
Subject: net: dsa: microchip: move KSZ9477 WoL functions to ksz_common

Move KSZ9477 WoL functions to ksz_common, in preparation for adding
KSZ87xx family support.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240813142750.772781-3-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz9477.c     | 181 --------------------------------
 drivers/net/dsa/microchip/ksz9477.h     |   5 -
 drivers/net/dsa/microchip/ksz9477_reg.h |  12 ---
 drivers/net/dsa/microchip/ksz_common.c  | 181 ++++++++++++++++++++++++++++++++
 drivers/net/dsa/microchip/ksz_common.h  |  19 ++++
 5 files changed, 200 insertions(+), 198 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 755de092b2c2..6c1540f725e5 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -56,187 +56,6 @@ int ksz9477_change_mtu(struct ksz_device *dev, int port, int mtu)
 				  REG_SW_MTU_MASK, frame_size);
 }
 
-/**
- * ksz9477_handle_wake_reason - Handle wake reason on a specified port.
- * @dev: The device structure.
- * @port: The port number.
- *
- * This function reads the PME (Power Management Event) status register of a
- * specified port to determine the wake reason. If there is no wake event, it
- * returns early. Otherwise, it logs the wake reason which could be due to a
- * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register
- * is then cleared to acknowledge the handling of the wake event.
- *
- * Return: 0 on success, or an error code on failure.
- */
-static int ksz9477_handle_wake_reason(struct ksz_device *dev, int port)
-{
-	u8 pme_status;
-	int ret;
-
-	ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status);
-	if (ret)
-		return ret;
-
-	if (!pme_status)
-		return 0;
-
-	dev_dbg(dev->dev, "Wake event on port %d due to:%s%s%s\n", port,
-		pme_status & PME_WOL_MAGICPKT ? " \"Magic Packet\"" : "",
-		pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "",
-		pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : "");
-
-	return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status);
-}
-
-/**
- * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port.
- * @dev: The device structure.
- * @port: The port number.
- * @wol: Pointer to ethtool Wake-on-LAN settings structure.
- *
- * This function checks the PME Pin Control Register to see if  PME Pin Output
- * Enable is set, indicating PME is enabled. If enabled, it sets the supported
- * and active WoL flags.
- */
-void ksz9477_get_wol(struct ksz_device *dev, int port,
-		     struct ethtool_wolinfo *wol)
-{
-	u8 pme_ctrl;
-	int ret;
-
-	if (!dev->wakeup_source)
-		return;
-
-	wol->supported = WAKE_PHY;
-
-	/* Check if the current MAC address on this port can be set
-	 * as global for WAKE_MAGIC support. The result may vary
-	 * dynamically based on other ports configurations.
-	 */
-	if (ksz_is_port_mac_global_usable(dev->ds, port))
-		wol->supported |= WAKE_MAGIC;
-
-	ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl);
-	if (ret)
-		return;
-
-	if (pme_ctrl & PME_WOL_MAGICPKT)
-		wol->wolopts |= WAKE_MAGIC;
-	if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY))
-		wol->wolopts |= WAKE_PHY;
-}
-
-/**
- * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port.
- * @dev: The device structure.
- * @port: The port number.
- * @wol: Pointer to ethtool Wake-on-LAN settings structure.
- *
- * This function configures Wake-on-LAN (WoL) settings for a specified port.
- * It validates the provided WoL options, checks if PME is enabled via the
- * switch's PME Pin Control Register, clears any previous wake reasons,
- * and sets the Magic Packet flag in the port's PME control register if
- * specified.
- *
- * Return: 0 on success, or other error codes on failure.
- */
-int ksz9477_set_wol(struct ksz_device *dev, int port,
-		    struct ethtool_wolinfo *wol)
-{
-	u8 pme_ctrl = 0, pme_ctrl_old = 0;
-	bool magic_switched_off;
-	bool magic_switched_on;
-	int ret;
-
-	if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
-		return -EINVAL;
-
-	if (!dev->wakeup_source)
-		return -EOPNOTSUPP;
-
-	ret = ksz9477_handle_wake_reason(dev, port);
-	if (ret)
-		return ret;
-
-	if (wol->wolopts & WAKE_MAGIC)
-		pme_ctrl |= PME_WOL_MAGICPKT;
-	if (wol->wolopts & WAKE_PHY)
-		pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY;
-
-	ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old);
-	if (ret)
-		return ret;
-
-	if (pme_ctrl_old == pme_ctrl)
-		return 0;
-
-	magic_switched_off = (pme_ctrl_old & PME_WOL_MAGICPKT) &&
-			    !(pme_ctrl & PME_WOL_MAGICPKT);
-	magic_switched_on = !(pme_ctrl_old & PME_WOL_MAGICPKT) &&
-			    (pme_ctrl & PME_WOL_MAGICPKT);
-
-	/* To keep reference count of MAC address, we should do this
-	 * operation only on change of WOL settings.
-	 */
-	if (magic_switched_on) {
-		ret = ksz_switch_macaddr_get(dev->ds, port, NULL);
-		if (ret)
-			return ret;
-	} else if (magic_switched_off) {
-		ksz_switch_macaddr_put(dev->ds);
-	}
-
-	ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl);
-	if (ret) {
-		if (magic_switched_on)
-			ksz_switch_macaddr_put(dev->ds);
-		return ret;
-	}
-
-	return 0;
-}
-
-/**
- * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while
- *                            considering Wake-on-LAN (WoL) settings.
- * @dev: The switch device structure.
- * @wol_enabled: Pointer to a boolean which will be set to true if WoL is
- *               enabled on any port.
- *
- * This function prepares the switch device for a safe shutdown while taking
- * into account the Wake-on-LAN (WoL) settings on the user ports. It updates
- * the wol_enabled flag accordingly to reflect whether WoL is active on any
- * port.
- */
-void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled)
-{
-	struct dsa_port *dp;
-	int ret;
-
-	*wol_enabled = false;
-
-	if (!dev->wakeup_source)
-		return;
-
-	dsa_switch_for_each_user_port(dp, dev->ds) {
-		u8 pme_ctrl = 0;
-
-		ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl);
-		if (!ret && pme_ctrl)
-			*wol_enabled = true;
-
-		/* make sure there are no pending wake events which would
-		 * prevent the device from going to sleep/shutdown.
-		 */
-		ksz9477_handle_wake_reason(dev, dp->index);
-	}
-
-	/* Now we are save to enable PME pin. */
-	if (*wol_enabled)
-		ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE);
-}
-
 static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev)
 {
 	unsigned int val;
diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h
index 239a281da10b..d2166b0d881e 100644
--- a/drivers/net/dsa/microchip/ksz9477.h
+++ b/drivers/net/dsa/microchip/ksz9477.h
@@ -60,11 +60,6 @@ void ksz9477_switch_exit(struct ksz_device *dev);
 void ksz9477_port_queue_split(struct ksz_device *dev, int port);
 void ksz9477_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr);
 void ksz9477_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr);
-void ksz9477_get_wol(struct ksz_device *dev, int port,
-		     struct ethtool_wolinfo *wol);
-int ksz9477_set_wol(struct ksz_device *dev, int port,
-		    struct ethtool_wolinfo *wol);
-void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled);
 
 int ksz9477_port_acl_init(struct ksz_device *dev, int port);
 void ksz9477_port_acl_free(struct ksz_device *dev, int port);
diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h
index d5354c600ea1..04235c22bf40 100644
--- a/drivers/net/dsa/microchip/ksz9477_reg.h
+++ b/drivers/net/dsa/microchip/ksz9477_reg.h
@@ -38,11 +38,6 @@
 #define SWITCH_REVISION_S		4
 #define SWITCH_RESET			0x01
 
-#define REG_SW_PME_CTRL			0x0006
-
-#define PME_ENABLE			BIT(1)
-#define PME_POLARITY			BIT(0)
-
 #define REG_GLOBAL_OPTIONS		0x000F
 
 #define SW_GIGABIT_ABLE			BIT(6)
@@ -807,13 +802,6 @@
 #define REG_PORT_AVB_SR_1_TYPE		0x0008
 #define REG_PORT_AVB_SR_2_TYPE		0x000A
 
-#define REG_PORT_PME_STATUS		0x0013
-#define REG_PORT_PME_CTRL		0x0017
-
-#define PME_WOL_MAGICPKT		BIT(2)
-#define PME_WOL_LINKUP			BIT(1)
-#define PME_WOL_ENERGY			BIT(0)
-
 #define REG_PORT_INT_STATUS		0x001B
 #define REG_PORT_INT_MASK		0x001F
 
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 1491099528be..7afe958d0e21 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -3751,6 +3751,77 @@ static void ksz_get_wol(struct dsa_switch *ds, int port,
 		dev->dev_ops->get_wol(dev, port, wol);
 }
 
+/**
+ * ksz9477_handle_wake_reason - Handle wake reason on a specified port.
+ * @dev: The device structure.
+ * @port: The port number.
+ *
+ * This function reads the PME (Power Management Event) status register of a
+ * specified port to determine the wake reason. If there is no wake event, it
+ * returns early. Otherwise, it logs the wake reason which could be due to a
+ * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register
+ * is then cleared to acknowledge the handling of the wake event.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+int ksz9477_handle_wake_reason(struct ksz_device *dev, int port)
+{
+	u8 pme_status;
+	int ret;
+
+	ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status);
+	if (ret)
+		return ret;
+
+	if (!pme_status)
+		return 0;
+
+	dev_dbg(dev->dev, "Wake event on port %d due to:%s%s%s\n", port,
+		pme_status & PME_WOL_MAGICPKT ? " \"Magic Packet\"" : "",
+		pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "",
+		pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : "");
+
+	return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status);
+}
+
+/**
+ * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port.
+ * @dev: The device structure.
+ * @port: The port number.
+ * @wol: Pointer to ethtool Wake-on-LAN settings structure.
+ *
+ * This function checks the PME Pin Control Register to see if  PME Pin Output
+ * Enable is set, indicating PME is enabled. If enabled, it sets the supported
+ * and active WoL flags.
+ */
+void ksz9477_get_wol(struct ksz_device *dev, int port,
+		     struct ethtool_wolinfo *wol)
+{
+	u8 pme_ctrl;
+	int ret;
+
+	if (!dev->wakeup_source)
+		return;
+
+	wol->supported = WAKE_PHY;
+
+	/* Check if the current MAC address on this port can be set
+	 * as global for WAKE_MAGIC support. The result may vary
+	 * dynamically based on other ports configurations.
+	 */
+	if (ksz_is_port_mac_global_usable(dev->ds, port))
+		wol->supported |= WAKE_MAGIC;
+
+	ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl);
+	if (ret)
+		return;
+
+	if (pme_ctrl & PME_WOL_MAGICPKT)
+		wol->wolopts |= WAKE_MAGIC;
+	if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY))
+		wol->wolopts |= WAKE_PHY;
+}
+
 static int ksz_set_wol(struct dsa_switch *ds, int port,
 		       struct ethtool_wolinfo *wol)
 {
@@ -3762,6 +3833,116 @@ static int ksz_set_wol(struct dsa_switch *ds, int port,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port.
+ * @dev: The device structure.
+ * @port: The port number.
+ * @wol: Pointer to ethtool Wake-on-LAN settings structure.
+ *
+ * This function configures Wake-on-LAN (WoL) settings for a specified port.
+ * It validates the provided WoL options, checks if PME is enabled via the
+ * switch's PME Pin Control Register, clears any previous wake reasons,
+ * and sets the Magic Packet flag in the port's PME control register if
+ * specified.
+ *
+ * Return: 0 on success, or other error codes on failure.
+ */
+int ksz9477_set_wol(struct ksz_device *dev, int port,
+		    struct ethtool_wolinfo *wol)
+{
+	u8 pme_ctrl = 0, pme_ctrl_old = 0;
+	bool magic_switched_off;
+	bool magic_switched_on;
+	int ret;
+
+	if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
+		return -EINVAL;
+
+	if (!dev->wakeup_source)
+		return -EOPNOTSUPP;
+
+	ret = ksz9477_handle_wake_reason(dev, port);
+	if (ret)
+		return ret;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		pme_ctrl |= PME_WOL_MAGICPKT;
+	if (wol->wolopts & WAKE_PHY)
+		pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY;
+
+	ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old);
+	if (ret)
+		return ret;
+
+	if (pme_ctrl_old == pme_ctrl)
+		return 0;
+
+	magic_switched_off = (pme_ctrl_old & PME_WOL_MAGICPKT) &&
+			    !(pme_ctrl & PME_WOL_MAGICPKT);
+	magic_switched_on = !(pme_ctrl_old & PME_WOL_MAGICPKT) &&
+			    (pme_ctrl & PME_WOL_MAGICPKT);
+
+	/* To keep reference count of MAC address, we should do this
+	 * operation only on change of WOL settings.
+	 */
+	if (magic_switched_on) {
+		ret = ksz_switch_macaddr_get(dev->ds, port, NULL);
+		if (ret)
+			return ret;
+	} else if (magic_switched_off) {
+		ksz_switch_macaddr_put(dev->ds);
+	}
+
+	ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl);
+	if (ret) {
+		if (magic_switched_on)
+			ksz_switch_macaddr_put(dev->ds);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while
+ *                            considering Wake-on-LAN (WoL) settings.
+ * @dev: The switch device structure.
+ * @wol_enabled: Pointer to a boolean which will be set to true if WoL is
+ *               enabled on any port.
+ *
+ * This function prepares the switch device for a safe shutdown while taking
+ * into account the Wake-on-LAN (WoL) settings on the user ports. It updates
+ * the wol_enabled flag accordingly to reflect whether WoL is active on any
+ * port.
+ */
+void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled)
+{
+	struct dsa_port *dp;
+	int ret;
+
+	*wol_enabled = false;
+
+	if (!dev->wakeup_source)
+		return;
+
+	dsa_switch_for_each_user_port(dp, dev->ds) {
+		u8 pme_ctrl = 0;
+
+		ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl);
+		if (!ret && pme_ctrl)
+			*wol_enabled = true;
+
+		/* make sure there are no pending wake events which would
+		 * prevent the device from going to sleep/shutdown.
+		 */
+		ksz9477_handle_wake_reason(dev, dp->index);
+	}
+
+	/* Now we are save to enable PME pin. */
+	if (*wol_enabled)
+		ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE);
+}
+
 static int ksz_port_set_mac_address(struct dsa_switch *ds, int port,
 				    const unsigned char *addr)
 {
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index 5f0a628b9849..e35caca96f89 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -391,6 +391,12 @@ int ksz_switch_macaddr_get(struct dsa_switch *ds, int port,
 			   struct netlink_ext_ack *extack);
 void ksz_switch_macaddr_put(struct dsa_switch *ds);
 void ksz_switch_shutdown(struct ksz_device *dev);
+int ksz9477_handle_wake_reason(struct ksz_device *dev, int port);
+void ksz9477_get_wol(struct ksz_device *dev, int port,
+		     struct ethtool_wolinfo *wol);
+int ksz9477_set_wol(struct ksz_device *dev, int port,
+		    struct ethtool_wolinfo *wol);
+void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled);
 
 /* Common register access functions */
 static inline struct regmap *ksz_regmap_8(struct ksz_device *dev)
@@ -695,6 +701,19 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define P_MII_MAC_MODE			BIT(2)
 #define P_MII_SEL_M			0x3
 
+/* KSZ9477, KSZ8795 Wake-on-LAN (WoL) masks */
+#define REG_PORT_PME_STATUS		0x0013
+#define REG_PORT_PME_CTRL		0x0017
+
+#define PME_WOL_MAGICPKT		BIT(2)
+#define PME_WOL_LINKUP			BIT(1)
+#define PME_WOL_ENERGY			BIT(0)
+
+#define REG_SW_PME_CTRL			0x0006
+
+#define PME_ENABLE			BIT(1)
+#define PME_POLARITY			BIT(0)
+
 /* Interrupt */
 #define REG_SW_PORT_INT_STATUS__1	0x001B
 #define REG_SW_PORT_INT_MASK__1		0x001F
-- 
cgit v1.3-3-g829e


From fd250fed1f8856c37caa7b9a5e6015ad6f5011e5 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Tue, 13 Aug 2024 16:27:37 +0200
Subject: net: dsa: microchip: generalize KSZ9477 WoL functions at ksz_common

Generalize KSZ9477 WoL functions at ksz_common. Move dedicated registers
and generic masks to existing structures & defines for that purpose.

Introduction of PME (port) read/write helper functions, which happen
to be the generic read/write for KSZ9477 but not for the incoming
KSZ87xx patch.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240813142750.772781-4-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz9477.c    |  16 ++---
 drivers/net/dsa/microchip/ksz_common.c | 113 +++++++++++++++++----------------
 drivers/net/dsa/microchip/ksz_common.h |  30 ++++-----
 3 files changed, 81 insertions(+), 78 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c
index 6c1540f725e5..0ba658a72d8f 100644
--- a/drivers/net/dsa/microchip/ksz9477.c
+++ b/drivers/net/dsa/microchip/ksz9477.c
@@ -1023,6 +1023,7 @@ void ksz9477_port_queue_split(struct ksz_device *dev, int port)
 
 void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 {
+	const u16 *regs = dev->info->regs;
 	struct dsa_switch *ds = dev->ds;
 	u16 data16;
 	u8 member;
@@ -1067,12 +1068,12 @@ void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	ksz9477_port_acl_init(dev, port);
 
 	/* clear pending wake flags */
-	ksz9477_handle_wake_reason(dev, port);
+	ksz_handle_wake_reason(dev, port);
 
 	/* Disable all WoL options by default. Otherwise
 	 * ksz_switch_macaddr_get/put logic will not work properly.
 	 */
-	ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, 0);
+	ksz_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0);
 }
 
 void ksz9477_config_cpu_port(struct dsa_switch *ds)
@@ -1169,6 +1170,7 @@ int ksz9477_enable_stp_addr(struct ksz_device *dev)
 int ksz9477_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
+	const u16 *regs = dev->info->regs;
 	int ret = 0;
 
 	ds->mtu_enforcement_ingress = true;
@@ -1199,13 +1201,11 @@ int ksz9477_setup(struct dsa_switch *ds)
 	/* enable global MIB counter freeze function */
 	ksz_cfg(dev, REG_SW_MAC_CTRL_6, SW_MIB_COUNTER_FREEZE, true);
 
-	/* Make sure PME (WoL) is not enabled. If requested, it will be
-	 * enabled by ksz9477_wol_pre_shutdown(). Otherwise, some PMICs do not
-	 * like PME events changes before shutdown.
+	/* Make sure PME (WoL) is not enabled. If requested, it will
+	 * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs
+	 * do not like PME events changes before shutdown.
 	 */
-	ksz_write8(dev, REG_SW_PME_CTRL, 0);
-
-	return 0;
+	return ksz_write8(dev, regs[REG_SW_PME_CTRL], 0);
 }
 
 u32 ksz9477_get_port_addr(int port, int offset)
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 7afe958d0e21..e2a9a652c41a 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -348,9 +348,9 @@ static const struct ksz_dev_ops ksz9477_dev_ops = {
 	.mdb_add = ksz9477_mdb_add,
 	.mdb_del = ksz9477_mdb_del,
 	.change_mtu = ksz9477_change_mtu,
-	.get_wol = ksz9477_get_wol,
-	.set_wol = ksz9477_set_wol,
-	.wol_pre_shutdown = ksz9477_wol_pre_shutdown,
+	.pme_write8 = ksz_write8,
+	.pme_pread8 = ksz_pread8,
+	.pme_pwrite8 = ksz_pwrite8,
 	.config_cpu_port = ksz9477_config_cpu_port,
 	.tc_cbs_set_cinc = ksz9477_tc_cbs_set_cinc,
 	.enable_stp_addr = ksz9477_enable_stp_addr,
@@ -539,6 +539,9 @@ static const u16 ksz9477_regs[] = {
 	[S_MULTICAST_CTRL]		= 0x0331,
 	[P_XMII_CTRL_0]			= 0x0300,
 	[P_XMII_CTRL_1]			= 0x0301,
+	[REG_SW_PME_CTRL]		= 0x0006,
+	[REG_PORT_PME_STATUS]		= 0x0013,
+	[REG_PORT_PME_CTRL]		= 0x0017,
 };
 
 static const u32 ksz9477_masks[] = {
@@ -3742,17 +3745,8 @@ static int ksz_setup_tc(struct dsa_switch *ds, int port,
 	}
 }
 
-static void ksz_get_wol(struct dsa_switch *ds, int port,
-			struct ethtool_wolinfo *wol)
-{
-	struct ksz_device *dev = ds->priv;
-
-	if (dev->dev_ops->get_wol)
-		dev->dev_ops->get_wol(dev, port, wol);
-}
-
 /**
- * ksz9477_handle_wake_reason - Handle wake reason on a specified port.
+ * ksz_handle_wake_reason - Handle wake reason on a specified port.
  * @dev: The device structure.
  * @port: The port number.
  *
@@ -3764,12 +3758,15 @@ static void ksz_get_wol(struct dsa_switch *ds, int port,
  *
  * Return: 0 on success, or an error code on failure.
  */
-int ksz9477_handle_wake_reason(struct ksz_device *dev, int port)
+int ksz_handle_wake_reason(struct ksz_device *dev, int port)
 {
+	const struct ksz_dev_ops *ops = dev->dev_ops;
+	const u16 *regs = dev->info->regs;
 	u8 pme_status;
 	int ret;
 
-	ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status);
+	ret = ops->pme_pread8(dev, port, regs[REG_PORT_PME_STATUS],
+			      &pme_status);
 	if (ret)
 		return ret;
 
@@ -3781,25 +3778,31 @@ int ksz9477_handle_wake_reason(struct ksz_device *dev, int port)
 		pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "",
 		pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : "");
 
-	return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status);
+	return ops->pme_pwrite8(dev, port, regs[REG_PORT_PME_STATUS],
+				pme_status);
 }
 
 /**
- * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port.
- * @dev: The device structure.
+ * ksz_get_wol - Get Wake-on-LAN settings for a specified port.
+ * @ds: The dsa_switch structure.
  * @port: The port number.
  * @wol: Pointer to ethtool Wake-on-LAN settings structure.
  *
- * This function checks the PME Pin Control Register to see if  PME Pin Output
- * Enable is set, indicating PME is enabled. If enabled, it sets the supported
- * and active WoL flags.
+ * This function checks the device PME wakeup_source flag and chip_id.
+ * If enabled and supported, it sets the supported and active WoL
+ * flags.
  */
-void ksz9477_get_wol(struct ksz_device *dev, int port,
-		     struct ethtool_wolinfo *wol)
+static void ksz_get_wol(struct dsa_switch *ds, int port,
+			struct ethtool_wolinfo *wol)
 {
+	struct ksz_device *dev = ds->priv;
+	const u16 *regs = dev->info->regs;
 	u8 pme_ctrl;
 	int ret;
 
+	if (!is_ksz9477(dev))
+		return;
+
 	if (!dev->wakeup_source)
 		return;
 
@@ -3812,7 +3815,8 @@ void ksz9477_get_wol(struct ksz_device *dev, int port,
 	if (ksz_is_port_mac_global_usable(dev->ds, port))
 		wol->supported |= WAKE_MAGIC;
 
-	ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl);
+	ret = dev->dev_ops->pme_pread8(dev, port, regs[REG_PORT_PME_CTRL],
+				       &pme_ctrl);
 	if (ret)
 		return;
 
@@ -3822,35 +3826,26 @@ void ksz9477_get_wol(struct ksz_device *dev, int port,
 		wol->wolopts |= WAKE_PHY;
 }
 
-static int ksz_set_wol(struct dsa_switch *ds, int port,
-		       struct ethtool_wolinfo *wol)
-{
-	struct ksz_device *dev = ds->priv;
-
-	if (dev->dev_ops->set_wol)
-		return dev->dev_ops->set_wol(dev, port, wol);
-
-	return -EOPNOTSUPP;
-}
-
 /**
- * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port.
- * @dev: The device structure.
+ * ksz_set_wol - Set Wake-on-LAN settings for a specified port.
+ * @ds: The dsa_switch structure.
  * @port: The port number.
  * @wol: Pointer to ethtool Wake-on-LAN settings structure.
  *
- * This function configures Wake-on-LAN (WoL) settings for a specified port.
- * It validates the provided WoL options, checks if PME is enabled via the
- * switch's PME Pin Control Register, clears any previous wake reasons,
- * and sets the Magic Packet flag in the port's PME control register if
+ * This function configures Wake-on-LAN (WoL) settings for a specified
+ * port. It validates the provided WoL options, checks if PME is
+ * enabled and supported, clears any previous wake reasons, and sets
+ * the Magic Packet flag in the port's PME control register if
  * specified.
  *
  * Return: 0 on success, or other error codes on failure.
  */
-int ksz9477_set_wol(struct ksz_device *dev, int port,
-		    struct ethtool_wolinfo *wol)
+static int ksz_set_wol(struct dsa_switch *ds, int port,
+		       struct ethtool_wolinfo *wol)
 {
 	u8 pme_ctrl = 0, pme_ctrl_old = 0;
+	struct ksz_device *dev = ds->priv;
+	const u16 *regs = dev->info->regs;
 	bool magic_switched_off;
 	bool magic_switched_on;
 	int ret;
@@ -3858,10 +3853,13 @@ int ksz9477_set_wol(struct ksz_device *dev, int port,
 	if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
 		return -EINVAL;
 
+	if (!is_ksz9477(dev))
+		return -EOPNOTSUPP;
+
 	if (!dev->wakeup_source)
 		return -EOPNOTSUPP;
 
-	ret = ksz9477_handle_wake_reason(dev, port);
+	ret = ksz_handle_wake_reason(dev, port);
 	if (ret)
 		return ret;
 
@@ -3870,7 +3868,8 @@ int ksz9477_set_wol(struct ksz_device *dev, int port,
 	if (wol->wolopts & WAKE_PHY)
 		pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY;
 
-	ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old);
+	ret = dev->dev_ops->pme_pread8(dev, port, regs[REG_PORT_PME_CTRL],
+				       &pme_ctrl_old);
 	if (ret)
 		return ret;
 
@@ -3893,7 +3892,8 @@ int ksz9477_set_wol(struct ksz_device *dev, int port,
 		ksz_switch_macaddr_put(dev->ds);
 	}
 
-	ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl);
+	ret = dev->dev_ops->pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL],
+					pme_ctrl);
 	if (ret) {
 		if (magic_switched_on)
 			ksz_switch_macaddr_put(dev->ds);
@@ -3904,8 +3904,8 @@ int ksz9477_set_wol(struct ksz_device *dev, int port,
 }
 
 /**
- * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while
- *                            considering Wake-on-LAN (WoL) settings.
+ * ksz_wol_pre_shutdown - Prepares the switch device for shutdown while
+ *                        considering Wake-on-LAN (WoL) settings.
  * @dev: The switch device structure.
  * @wol_enabled: Pointer to a boolean which will be set to true if WoL is
  *               enabled on any port.
@@ -3915,32 +3915,38 @@ int ksz9477_set_wol(struct ksz_device *dev, int port,
  * the wol_enabled flag accordingly to reflect whether WoL is active on any
  * port.
  */
-void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled)
+static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled)
 {
+	const struct ksz_dev_ops *ops = dev->dev_ops;
+	const u16 *regs = dev->info->regs;
 	struct dsa_port *dp;
 	int ret;
 
 	*wol_enabled = false;
 
+	if (!is_ksz9477(dev))
+		return;
+
 	if (!dev->wakeup_source)
 		return;
 
 	dsa_switch_for_each_user_port(dp, dev->ds) {
 		u8 pme_ctrl = 0;
 
-		ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl);
+		ret = ops->pme_pread8(dev, dp->index,
+				      regs[REG_PORT_PME_CTRL], &pme_ctrl);
 		if (!ret && pme_ctrl)
 			*wol_enabled = true;
 
 		/* make sure there are no pending wake events which would
 		 * prevent the device from going to sleep/shutdown.
 		 */
-		ksz9477_handle_wake_reason(dev, dp->index);
+		ksz_handle_wake_reason(dev, dp->index);
 	}
 
 	/* Now we are save to enable PME pin. */
 	if (*wol_enabled)
-		ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE);
+		ops->pme_write8(dev, regs[REG_SW_PME_CTRL], PME_ENABLE);
 }
 
 static int ksz_port_set_mac_address(struct dsa_switch *ds, int port,
@@ -4253,8 +4259,7 @@ void ksz_switch_shutdown(struct ksz_device *dev)
 {
 	bool wol_enabled = false;
 
-	if (dev->dev_ops->wol_pre_shutdown)
-		dev->dev_ops->wol_pre_shutdown(dev, &wol_enabled);
+	ksz_wol_pre_shutdown(dev, &wol_enabled);
 
 	if (dev->dev_ops->reset && !wol_enabled)
 		dev->dev_ops->reset(dev);
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index e35caca96f89..c60c218afa64 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -235,6 +235,9 @@ enum ksz_regs {
 	S_MULTICAST_CTRL,
 	P_XMII_CTRL_0,
 	P_XMII_CTRL_1,
+	REG_SW_PME_CTRL,
+	REG_PORT_PME_STATUS,
+	REG_PORT_PME_CTRL,
 };
 
 enum ksz_masks {
@@ -354,6 +357,11 @@ struct ksz_dev_ops {
 	void (*get_caps)(struct ksz_device *dev, int port,
 			 struct phylink_config *config);
 	int (*change_mtu)(struct ksz_device *dev, int port, int mtu);
+	int (*pme_write8)(struct ksz_device *dev, u32 reg, u8 value);
+	int (*pme_pread8)(struct ksz_device *dev, int port, int offset,
+			  u8 *data);
+	int (*pme_pwrite8)(struct ksz_device *dev, int port, int offset,
+			   u8 data);
 	void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze);
 	void (*port_init_cnt)(struct ksz_device *dev, int port);
 	void (*phylink_mac_link_up)(struct ksz_device *dev, int port,
@@ -363,11 +371,6 @@ struct ksz_dev_ops {
 				    int duplex, bool tx_pause, bool rx_pause);
 	void (*setup_rgmii_delay)(struct ksz_device *dev, int port);
 	int (*tc_cbs_set_cinc)(struct ksz_device *dev, int port, u32 val);
-	void (*get_wol)(struct ksz_device *dev, int port,
-			struct ethtool_wolinfo *wol);
-	int (*set_wol)(struct ksz_device *dev, int port,
-		       struct ethtool_wolinfo *wol);
-	void (*wol_pre_shutdown)(struct ksz_device *dev, bool *wol_enabled);
 	void (*config_cpu_port)(struct dsa_switch *ds);
 	int (*enable_stp_addr)(struct ksz_device *dev);
 	int (*reset)(struct ksz_device *dev);
@@ -391,12 +394,7 @@ int ksz_switch_macaddr_get(struct dsa_switch *ds, int port,
 			   struct netlink_ext_ack *extack);
 void ksz_switch_macaddr_put(struct dsa_switch *ds);
 void ksz_switch_shutdown(struct ksz_device *dev);
-int ksz9477_handle_wake_reason(struct ksz_device *dev, int port);
-void ksz9477_get_wol(struct ksz_device *dev, int port,
-		     struct ethtool_wolinfo *wol);
-int ksz9477_set_wol(struct ksz_device *dev, int port,
-		    struct ethtool_wolinfo *wol);
-void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled);
+int ksz_handle_wake_reason(struct ksz_device *dev, int port);
 
 /* Common register access functions */
 static inline struct regmap *ksz_regmap_8(struct ksz_device *dev)
@@ -635,6 +633,11 @@ static inline bool is_ksz8(struct ksz_device *dev)
 	return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev);
 }
 
+static inline bool is_ksz9477(struct ksz_device *dev)
+{
+	return dev->chip_id == KSZ9477_CHIP_ID;
+}
+
 static inline int is_lan937x(struct ksz_device *dev)
 {
 	return dev->chip_id == LAN9370_CHIP_ID ||
@@ -702,15 +705,10 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define P_MII_SEL_M			0x3
 
 /* KSZ9477, KSZ8795 Wake-on-LAN (WoL) masks */
-#define REG_PORT_PME_STATUS		0x0013
-#define REG_PORT_PME_CTRL		0x0017
-
 #define PME_WOL_MAGICPKT		BIT(2)
 #define PME_WOL_LINKUP			BIT(1)
 #define PME_WOL_ENERGY			BIT(0)
 
-#define REG_SW_PME_CTRL			0x0006
-
 #define PME_ENABLE			BIT(1)
 #define PME_POLARITY			BIT(0)
 
-- 
cgit v1.3-3-g829e


From 90b06ac06529b4c90af97763e57cf38d96999827 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Tue, 13 Aug 2024 16:27:38 +0200
Subject: net: dsa: microchip: add WoL support for KSZ87xx family

Add WoL support for KSZ87xx family of switches. This code was tested
with a KSZ8794 chip.

Implement ksz_common usage of the new device-tree property
'microchip,pme-active-high'.

Make use of the now generalized ksz_common WoL functions, adding an
additional interrupt register write for KSZ87xx. Add helper functions
to convert from PME (port) read/writes to indirect register
read/writes in the dedicated ksz8795 sources.  Add initial
configuration during (port) setup as per KSZ9477.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240813142750.772781-5-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz8.h       |  3 ++
 drivers/net/dsa/microchip/ksz8795.c    | 94 +++++++++++++++++++++++++++++++++-
 drivers/net/dsa/microchip/ksz_common.c | 24 +++++++--
 drivers/net/dsa/microchip/ksz_common.h |  6 ++-
 4 files changed, 119 insertions(+), 8 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h
index ae43077e76c3..e1c79ff97123 100644
--- a/drivers/net/dsa/microchip/ksz8.h
+++ b/drivers/net/dsa/microchip/ksz8.h
@@ -54,6 +54,9 @@ int ksz8_reset_switch(struct ksz_device *dev);
 int ksz8_switch_init(struct ksz_device *dev);
 void ksz8_switch_exit(struct ksz_device *dev);
 int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu);
+int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value);
+int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data);
+int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data);
 void ksz8_phylink_mac_link_up(struct phylink_config *config,
 			      struct phy_device *phydev, unsigned int mode,
 			      phy_interface_t interface, int speed, int duplex,
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index d27b9c36d73f..a01079297a8c 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -38,6 +38,20 @@ static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
 			   bits, set ? bits : 0);
 }
 
+/**
+ * ksz8_ind_write8 - EEE/ACL/PME indirect register write
+ * @dev: The device structure.
+ * @table: Function & table select, register 110.
+ * @addr: Indirect access control, register 111.
+ * @data: The data to be written.
+ *
+ * This function performs an indirect register write for EEE, ACL or
+ * PME switch functionalities. Both 8-bit registers 110 and 111 are
+ * written at once with ksz_write16, using the serial multiple write
+ * functionality.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
 static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data)
 {
 	const u16 *regs;
@@ -58,6 +72,59 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data)
 	return ret;
 }
 
+/**
+ * ksz8_ind_read8 - EEE/ACL/PME indirect register read
+ * @dev: The device structure.
+ * @table: Function & table select, register 110.
+ * @addr: Indirect access control, register 111.
+ * @val: The value read.
+ *
+ * This function performs an indirect register read for EEE, ACL or
+ * PME switch functionalities. Both 8-bit registers 110 and 111 are
+ * written at once with ksz_write16, using the serial multiple write
+ * functionality.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+static int ksz8_ind_read8(struct ksz_device *dev, u8 table, u16 addr, u8 *val)
+{
+	const u16 *regs;
+	u16 ctrl_addr;
+	int ret = 0;
+
+	regs = dev->info->regs;
+
+	mutex_lock(&dev->alu_mutex);
+
+	ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr;
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+	if (!ret)
+		ret = ksz_read8(dev, regs[REG_IND_BYTE], val);
+
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value)
+{
+	return ksz8_ind_write8(dev, (u8)(reg >> 8), (u8)(reg), value);
+}
+
+int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data)
+{
+	u8 table = (u8)(offset >> 8 | (port + 1));
+
+	return ksz8_ind_read8(dev, table, (u8)(offset), data);
+}
+
+int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data)
+{
+	u8 table = (u8)(offset >> 8 | (port + 1));
+
+	return ksz8_ind_write8(dev, table, (u8)(offset), data);
+}
+
 int ksz8_reset_switch(struct ksz_device *dev)
 {
 	if (ksz_is_ksz88x3(dev)) {
@@ -1545,6 +1612,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port)
 
 void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 {
+	const u16 *regs = dev->info->regs;
 	struct dsa_switch *ds = dev->ds;
 	const u32 *masks;
 	int queues;
@@ -1575,6 +1643,13 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 		member = BIT(dsa_upstream_port(ds, port));
 
 	ksz8_cfg_port_member(dev, port, member);
+
+	/* Disable all WoL options by default. Otherwise
+	 * ksz_switch_macaddr_get/put logic will not work properly.
+	 * CPU port 4 has no WoL functionality.
+	 */
+	if (ksz_is_ksz87xx(dev) && !cpu_port)
+		ksz8_pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0);
 }
 
 static void ksz88x3_config_rmii_clk(struct ksz_device *dev)
@@ -1790,7 +1865,8 @@ int ksz8_enable_stp_addr(struct ksz_device *dev)
 int ksz8_setup(struct dsa_switch *ds)
 {
 	struct ksz_device *dev = ds->priv;
-	int i;
+	const u16 *regs = dev->info->regs;
+	int i, ret = 0;
 
 	ds->mtu_enforcement_ingress = true;
 
@@ -1829,7 +1905,21 @@ int ksz8_setup(struct dsa_switch *ds)
 	for (i = 0; i < (dev->info->num_vlans / 4); i++)
 		ksz8_r_vlan_entries(dev, i);
 
-	return ksz8_handle_global_errata(ds);
+	/* Make sure PME (WoL) is not enabled. If requested, it will
+	 * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs
+	 * do not like PME events changes before shutdown. PME only
+	 * available on KSZ87xx family.
+	 */
+	if (ksz_is_ksz87xx(dev)) {
+		ret = ksz8_pme_write8(dev, regs[REG_SW_PME_CTRL], 0);
+		if (!ret)
+			ret = ksz_rmw8(dev, REG_INT_ENABLE, INT_PME, 0);
+	}
+
+	if (!ret)
+		return ksz8_handle_global_errata(ds);
+	else
+		return ret;
 }
 
 void ksz8_get_caps(struct ksz_device *dev, int port,
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index e2a9a652c41a..3f3230d181d8 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -307,6 +307,9 @@ static const struct ksz_dev_ops ksz8_dev_ops = {
 	.init = ksz8_switch_init,
 	.exit = ksz8_switch_exit,
 	.change_mtu = ksz8_change_mtu,
+	.pme_write8 = ksz8_pme_write8,
+	.pme_pread8 = ksz8_pme_pread8,
+	.pme_pwrite8 = ksz8_pme_pwrite8,
 };
 
 static void ksz9477_phylink_mac_link_up(struct phylink_config *config,
@@ -423,6 +426,9 @@ static const u16 ksz8795_regs[] = {
 	[S_MULTICAST_CTRL]		= 0x04,
 	[P_XMII_CTRL_0]			= 0x06,
 	[P_XMII_CTRL_1]			= 0x06,
+	[REG_SW_PME_CTRL]		= 0x8003,
+	[REG_PORT_PME_STATUS]		= 0x8003,
+	[REG_PORT_PME_CTRL]		= 0x8007,
 };
 
 static const u32 ksz8795_masks[] = {
@@ -3800,7 +3806,7 @@ static void ksz_get_wol(struct dsa_switch *ds, int port,
 	u8 pme_ctrl;
 	int ret;
 
-	if (!is_ksz9477(dev))
+	if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev))
 		return;
 
 	if (!dev->wakeup_source)
@@ -3853,7 +3859,7 @@ static int ksz_set_wol(struct dsa_switch *ds, int port,
 	if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
 		return -EINVAL;
 
-	if (!is_ksz9477(dev))
+	if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev))
 		return -EOPNOTSUPP;
 
 	if (!dev->wakeup_source)
@@ -3919,12 +3925,13 @@ static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled)
 {
 	const struct ksz_dev_ops *ops = dev->dev_ops;
 	const u16 *regs = dev->info->regs;
+	u8 pme_pin_en = PME_ENABLE;
 	struct dsa_port *dp;
 	int ret;
 
 	*wol_enabled = false;
 
-	if (!is_ksz9477(dev))
+	if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev))
 		return;
 
 	if (!dev->wakeup_source)
@@ -3945,8 +3952,13 @@ static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled)
 	}
 
 	/* Now we are save to enable PME pin. */
-	if (*wol_enabled)
-		ops->pme_write8(dev, regs[REG_SW_PME_CTRL], PME_ENABLE);
+	if (*wol_enabled) {
+		if (dev->pme_active_high)
+			pme_pin_en |= PME_POLARITY;
+		ops->pme_write8(dev, regs[REG_SW_PME_CTRL], pme_pin_en);
+		if (ksz_is_ksz87xx(dev))
+			ksz_write8(dev, KSZ87XX_REG_INT_EN, KSZ87XX_INT_PME_MASK);
+	}
 }
 
 static int ksz_port_set_mac_address(struct dsa_switch *ds, int port,
@@ -4661,6 +4673,8 @@ int ksz_switch_register(struct ksz_device *dev)
 
 		dev->wakeup_source = of_property_read_bool(dev->dev->of_node,
 							   "wakeup-source");
+		dev->pme_active_high = of_property_read_bool(dev->dev->of_node,
+							     "microchip,pme-active-high");
 	}
 
 	ret = dsa_register_switch(dev->ds);
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index c60c218afa64..8094d90d6ca4 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -174,6 +174,7 @@ struct ksz_device {
 	bool synclko_125;
 	bool synclko_disable;
 	bool wakeup_source;
+	bool pme_active_high;
 
 	struct vlan_table *vlan_cache;
 
@@ -704,7 +705,7 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define P_MII_MAC_MODE			BIT(2)
 #define P_MII_SEL_M			0x3
 
-/* KSZ9477, KSZ8795 Wake-on-LAN (WoL) masks */
+/* KSZ9477, KSZ87xx Wake-on-LAN (WoL) masks */
 #define PME_WOL_MAGICPKT		BIT(2)
 #define PME_WOL_LINKUP			BIT(1)
 #define PME_WOL_ENERGY			BIT(0)
@@ -712,6 +713,9 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define PME_ENABLE			BIT(1)
 #define PME_POLARITY			BIT(0)
 
+#define KSZ87XX_REG_INT_EN		0x7D
+#define KSZ87XX_INT_PME_MASK		BIT(4)
+
 /* Interrupt */
 #define REG_SW_PORT_INT_STATUS__1	0x001B
 #define REG_SW_PORT_INT_MASK__1		0x001F
-- 
cgit v1.3-3-g829e


From 0d3edc90c4a0ac77332a25e1e6b709a39b202de9 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Tue, 13 Aug 2024 16:27:39 +0200
Subject: net: dsa: microchip: fix KSZ87xx family structure wrt the datasheet

The KSZ87xx switches have 32 static MAC address table entries and not
8. This fixes -ENOSPC non-critical errors from ksz8_add_sta_mac when
configured as a bridge.

Add a new ksz87xx_dev_ops structure to be able to use the
ksz_r_mib_stat64 pointer for this family; this corrects a wrong
mib->counters cast to ksz88xx_stats_raw. This fixes iproute2
statistics. Rename ksz8_dev_ops structure to ksz88x3_dev_ops, in line
with ksz_is_* naming conventions from ksz_common.h.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240813142750.772781-6-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_common.c | 51 ++++++++++++++++++++++++++++------
 1 file changed, 43 insertions(+), 8 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 3f3230d181d8..cd3991792b69 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -277,7 +277,7 @@ static const struct phylink_mac_ops ksz8_phylink_mac_ops = {
 	.mac_link_up	= ksz8_phylink_mac_link_up,
 };
 
-static const struct ksz_dev_ops ksz8_dev_ops = {
+static const struct ksz_dev_ops ksz88x3_dev_ops = {
 	.setup = ksz8_setup,
 	.get_port_addr = ksz8_get_port_addr,
 	.cfg_port_member = ksz8_cfg_port_member,
@@ -312,6 +312,41 @@ static const struct ksz_dev_ops ksz8_dev_ops = {
 	.pme_pwrite8 = ksz8_pme_pwrite8,
 };
 
+static const struct ksz_dev_ops ksz87xx_dev_ops = {
+	.setup = ksz8_setup,
+	.get_port_addr = ksz8_get_port_addr,
+	.cfg_port_member = ksz8_cfg_port_member,
+	.flush_dyn_mac_table = ksz8_flush_dyn_mac_table,
+	.port_setup = ksz8_port_setup,
+	.r_phy = ksz8_r_phy,
+	.w_phy = ksz8_w_phy,
+	.r_mib_cnt = ksz8_r_mib_cnt,
+	.r_mib_pkt = ksz8_r_mib_pkt,
+	.r_mib_stat64 = ksz_r_mib_stats64,
+	.freeze_mib = ksz8_freeze_mib,
+	.port_init_cnt = ksz8_port_init_cnt,
+	.fdb_dump = ksz8_fdb_dump,
+	.fdb_add = ksz8_fdb_add,
+	.fdb_del = ksz8_fdb_del,
+	.mdb_add = ksz8_mdb_add,
+	.mdb_del = ksz8_mdb_del,
+	.vlan_filtering = ksz8_port_vlan_filtering,
+	.vlan_add = ksz8_port_vlan_add,
+	.vlan_del = ksz8_port_vlan_del,
+	.mirror_add = ksz8_port_mirror_add,
+	.mirror_del = ksz8_port_mirror_del,
+	.get_caps = ksz8_get_caps,
+	.config_cpu_port = ksz8_config_cpu_port,
+	.enable_stp_addr = ksz8_enable_stp_addr,
+	.reset = ksz8_reset_switch,
+	.init = ksz8_switch_init,
+	.exit = ksz8_switch_exit,
+	.change_mtu = ksz8_change_mtu,
+	.pme_write8 = ksz8_pme_write8,
+	.pme_pread8 = ksz8_pme_pread8,
+	.pme_pwrite8 = ksz8_pme_pwrite8,
+};
+
 static void ksz9477_phylink_mac_link_up(struct phylink_config *config,
 					struct phy_device *phydev,
 					unsigned int mode,
@@ -1262,12 +1297,12 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.dev_name = "KSZ8795",
 		.num_vlans = 4096,
 		.num_alus = 0,
-		.num_statics = 8,
+		.num_statics = 32,
 		.cpu_ports = 0x10,	/* can be configured as cpu port */
 		.port_cnt = 5,		/* total cpu and user ports */
 		.num_tx_queues = 4,
 		.num_ipms = 4,
-		.ops = &ksz8_dev_ops,
+		.ops = &ksz87xx_dev_ops,
 		.phylink_mac_ops = &ksz8_phylink_mac_ops,
 		.ksz87xx_eee_link_erratum = true,
 		.mib_names = ksz9477_mib_names,
@@ -1303,12 +1338,12 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.dev_name = "KSZ8794",
 		.num_vlans = 4096,
 		.num_alus = 0,
-		.num_statics = 8,
+		.num_statics = 32,
 		.cpu_ports = 0x10,	/* can be configured as cpu port */
 		.port_cnt = 5,		/* total cpu and user ports */
 		.num_tx_queues = 4,
 		.num_ipms = 4,
-		.ops = &ksz8_dev_ops,
+		.ops = &ksz87xx_dev_ops,
 		.phylink_mac_ops = &ksz8_phylink_mac_ops,
 		.ksz87xx_eee_link_erratum = true,
 		.mib_names = ksz9477_mib_names,
@@ -1330,12 +1365,12 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.dev_name = "KSZ8765",
 		.num_vlans = 4096,
 		.num_alus = 0,
-		.num_statics = 8,
+		.num_statics = 32,
 		.cpu_ports = 0x10,	/* can be configured as cpu port */
 		.port_cnt = 5,		/* total cpu and user ports */
 		.num_tx_queues = 4,
 		.num_ipms = 4,
-		.ops = &ksz8_dev_ops,
+		.ops = &ksz87xx_dev_ops,
 		.phylink_mac_ops = &ksz8_phylink_mac_ops,
 		.ksz87xx_eee_link_erratum = true,
 		.mib_names = ksz9477_mib_names,
@@ -1362,7 +1397,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.port_cnt = 3,
 		.num_tx_queues = 4,
 		.num_ipms = 4,
-		.ops = &ksz8_dev_ops,
+		.ops = &ksz88x3_dev_ops,
 		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
 		.mib_names = ksz88xx_mib_names,
 		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
-- 
cgit v1.3-3-g829e


From 6f2b72c04d58a40c16f3cd858776517f16226119 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Tue, 13 Aug 2024 16:27:40 +0200
Subject: net: dsa: microchip: fix tag_ksz egress mask for KSZ8795 family

Fix the tag_ksz egress mask for DSA_TAG_PROTO_KSZ8795, the port is
encoded in the two and not three LSB. This fix is for completeness,
for example the bug doesn't manifest itself on the KSZ8794 because bit
2 seems to be always zero.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240813142750.772781-7-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/tag_ksz.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index ee7b272ab715..1f46de394f2e 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -111,9 +111,10 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
  * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes)
  * ---------------------------------------------------------------------------
  * tag0 : zero-based value represents port
- *	  (eg, 0x00=port1, 0x02=port3, 0x06=port7)
+ *	  (eg, 0x0=port1, 0x2=port3, 0x3=port4)
  */
 
+#define KSZ8795_TAIL_TAG_EG_PORT_M	GENMASK(1, 0)
 #define KSZ8795_TAIL_TAG_OVERRIDE	BIT(6)
 #define KSZ8795_TAIL_TAG_LOOKUP		BIT(7)
 
@@ -141,7 +142,8 @@ static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev)
 {
 	u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
 
-	return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN);
+	return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M,
+			      KSZ_EGRESS_TAG_LEN);
 }
 
 static const struct dsa_device_ops ksz8795_netdev_ops = {
-- 
cgit v1.3-3-g829e


From f40a455d01f80c6638be382d75cb1c4e7748d8af Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 13 Aug 2024 14:33:47 +0100
Subject: ipv6: Add ipv6_addr_{cpu_to_be32,be32_to_cpu} helpers

Add helpers to convert an ipv6 addr, expressed as an array
of words, from CPU to big-endian byte order, and vice versa.

No functional change intended.
Compile tested only.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/netdev/c7684349-535c-45a4-9a74-d47479a50020@lunn.ch/
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240813-ipv6_addr-helpers-v2-1-5c974f8cca3e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ipv6.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 88a8e554f7a1..e7113855a10f 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -1365,4 +1365,16 @@ static inline void ip6_sock_set_recvpktinfo(struct sock *sk)
 	release_sock(sk);
 }
 
+#define IPV6_ADDR_WORDS 4
+
+static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src)
+{
+	cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS);
+}
+
+static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src)
+{
+	be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS);
+}
+
 #endif /* _NET_IPV6_H */
-- 
cgit v1.3-3-g829e


From b908c722133e3a158bf703b5003e7a8272e9d540 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 13 Aug 2024 14:33:48 +0100
Subject: net: ethernet: mtk_eth_soc: Use ipv6_addr_{cpu_to_be32,be32_to_cpu}
 helpers

Use ipv6_addr_cpu_to_be32 and ipv6_addr_be32_to_cpu helpers to convert
address, rather than open coding the conversion.

No functional change intended.
Compile tested only.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/netdev/c7684349-535c-45a4-9a74-d47479a50020@lunn.ch/
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240813-ipv6_addr-helpers-v2-2-5c974f8cca3e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_ppe.c         | 10 +++++-----
 drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c |  9 +++++----
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c
index 0acee405a749..ada852adc5f7 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe.c
@@ -8,8 +8,11 @@
 #include <linux/platform_device.h>
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
+
 #include <net/dst_metadata.h>
 #include <net/dsa.h>
+#include <net/ipv6.h>
+
 #include "mtk_eth_soc.h"
 #include "mtk_ppe.h"
 #include "mtk_ppe_regs.h"
@@ -338,7 +341,6 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_eth *eth,
 {
 	int type = mtk_get_ib1_pkt_type(eth, entry->ib1);
 	u32 *src, *dest;
-	int i;
 
 	switch (type) {
 	case MTK_PPE_PKT_TYPE_IPV4_DSLITE:
@@ -359,10 +361,8 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_eth *eth,
 		return -EINVAL;
 	}
 
-	for (i = 0; i < 4; i++)
-		src[i] = be32_to_cpu(src_addr[i]);
-	for (i = 0; i < 4; i++)
-		dest[i] = be32_to_cpu(dest_addr[i]);
+	ipv6_addr_be32_to_cpu(src, src_addr);
+	ipv6_addr_be32_to_cpu(dest, dest_addr);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c
index 1a97feca77f2..570ebf91f693 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c
@@ -3,6 +3,9 @@
 
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
+
+#include <net/ipv6.h>
+
 #include "mtk_eth_soc.h"
 
 struct mtk_flow_addr_info
@@ -47,16 +50,14 @@ static const char *mtk_foe_pkt_type_str(int type)
 static void
 mtk_print_addr(struct seq_file *m, u32 *addr, bool ipv6)
 {
-	__be32 n_addr[4];
-	int i;
+	__be32 n_addr[IPV6_ADDR_WORDS];
 
 	if (!ipv6) {
 		seq_printf(m, "%pI4h", addr);
 		return;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(n_addr); i++)
-		n_addr[i] = htonl(addr[i]);
+	ipv6_addr_cpu_to_be32(n_addr, addr);
 	seq_printf(m, "%pI6", n_addr);
 }
 
-- 
cgit v1.3-3-g829e


From c7be6e70d20c0f8a20b484a0c51d2a12ef8f8ec7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 13 Aug 2024 14:33:49 +0100
Subject: net: hns3: Use ipv6_addr_{cpu_to_be32,be32_to_cpu} helpers

Use new ipv6_addr_cpu_to_be32 and ipv6_addr_be32_to_cpu helpers,
and IPV6_ADDR_WORDS. This is arguably slightly nicer.

No functional change intended.
Compile tested only.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/netdev/c7684349-535c-45a4-9a74-d47479a50020@lunn.ch/
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240813-ipv6_addr-helpers-v2-3-5c974f8cca3e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 79 +++++++++++-----------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  8 ++-
 2 files changed, 44 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 6c33195a1168..bd86efd92a5a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -13,8 +13,9 @@
 #include <linux/platform_device.h>
 #include <linux/if_vlan.h>
 #include <linux/crash_dump.h>
-#include <net/ipv6.h>
+
 #include <net/rtnetlink.h>
+
 #include "hclge_cmd.h"
 #include "hclge_dcb.h"
 #include "hclge_main.h"
@@ -6290,15 +6291,15 @@ static void hclge_fd_get_ip4_tuple(struct ethtool_rx_flow_spec *fs,
 static void hclge_fd_get_tcpip6_tuple(struct ethtool_rx_flow_spec *fs,
 				      struct hclge_fd_rule *rule, u8 ip_proto)
 {
-	be32_to_cpu_array(rule->tuples.src_ip, fs->h_u.tcp_ip6_spec.ip6src,
-			  IPV6_SIZE);
-	be32_to_cpu_array(rule->tuples_mask.src_ip, fs->m_u.tcp_ip6_spec.ip6src,
-			  IPV6_SIZE);
+	ipv6_addr_be32_to_cpu(rule->tuples.src_ip,
+			      fs->h_u.tcp_ip6_spec.ip6src);
+	ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip,
+			      fs->m_u.tcp_ip6_spec.ip6src);
 
-	be32_to_cpu_array(rule->tuples.dst_ip, fs->h_u.tcp_ip6_spec.ip6dst,
-			  IPV6_SIZE);
-	be32_to_cpu_array(rule->tuples_mask.dst_ip, fs->m_u.tcp_ip6_spec.ip6dst,
-			  IPV6_SIZE);
+	ipv6_addr_be32_to_cpu(rule->tuples.dst_ip,
+			      fs->h_u.tcp_ip6_spec.ip6dst);
+	ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip,
+			      fs->m_u.tcp_ip6_spec.ip6dst);
 
 	rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip6_spec.psrc);
 	rule->tuples_mask.src_port = be16_to_cpu(fs->m_u.tcp_ip6_spec.psrc);
@@ -6319,15 +6320,15 @@ static void hclge_fd_get_tcpip6_tuple(struct ethtool_rx_flow_spec *fs,
 static void hclge_fd_get_ip6_tuple(struct ethtool_rx_flow_spec *fs,
 				   struct hclge_fd_rule *rule)
 {
-	be32_to_cpu_array(rule->tuples.src_ip, fs->h_u.usr_ip6_spec.ip6src,
-			  IPV6_SIZE);
-	be32_to_cpu_array(rule->tuples_mask.src_ip, fs->m_u.usr_ip6_spec.ip6src,
-			  IPV6_SIZE);
+	ipv6_addr_be32_to_cpu(rule->tuples.src_ip,
+			      fs->h_u.usr_ip6_spec.ip6src);
+	ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip,
+			      fs->m_u.usr_ip6_spec.ip6src);
 
-	be32_to_cpu_array(rule->tuples.dst_ip, fs->h_u.usr_ip6_spec.ip6dst,
-			  IPV6_SIZE);
-	be32_to_cpu_array(rule->tuples_mask.dst_ip, fs->m_u.usr_ip6_spec.ip6dst,
-			  IPV6_SIZE);
+	ipv6_addr_be32_to_cpu(rule->tuples.dst_ip,
+			      fs->h_u.usr_ip6_spec.ip6dst);
+	ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip,
+			      fs->m_u.usr_ip6_spec.ip6dst);
 
 	rule->tuples.ip_proto = fs->h_u.usr_ip6_spec.l4_proto;
 	rule->tuples_mask.ip_proto = fs->m_u.usr_ip6_spec.l4_proto;
@@ -6756,21 +6757,19 @@ static void hclge_fd_get_tcpip6_info(struct hclge_fd_rule *rule,
 				     struct ethtool_tcpip6_spec *spec,
 				     struct ethtool_tcpip6_spec *spec_mask)
 {
-	cpu_to_be32_array(spec->ip6src,
-			  rule->tuples.src_ip, IPV6_SIZE);
-	cpu_to_be32_array(spec->ip6dst,
-			  rule->tuples.dst_ip, IPV6_SIZE);
+	ipv6_addr_cpu_to_be32(spec->ip6src, rule->tuples.src_ip);
+	ipv6_addr_cpu_to_be32(spec->ip6dst, rule->tuples.dst_ip);
 	if (rule->unused_tuple & BIT(INNER_SRC_IP))
 		memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src));
 	else
-		cpu_to_be32_array(spec_mask->ip6src, rule->tuples_mask.src_ip,
-				  IPV6_SIZE);
+		ipv6_addr_cpu_to_be32(spec_mask->ip6src,
+				      rule->tuples_mask.src_ip);
 
 	if (rule->unused_tuple & BIT(INNER_DST_IP))
 		memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst));
 	else
-		cpu_to_be32_array(spec_mask->ip6dst, rule->tuples_mask.dst_ip,
-				  IPV6_SIZE);
+		ipv6_addr_cpu_to_be32(spec_mask->ip6dst,
+				      rule->tuples_mask.dst_ip);
 
 	spec->tclass = rule->tuples.ip_tos;
 	spec_mask->tclass = rule->unused_tuple & BIT(INNER_IP_TOS) ?
@@ -6789,19 +6788,19 @@ static void hclge_fd_get_ip6_info(struct hclge_fd_rule *rule,
 				  struct ethtool_usrip6_spec *spec,
 				  struct ethtool_usrip6_spec *spec_mask)
 {
-	cpu_to_be32_array(spec->ip6src, rule->tuples.src_ip, IPV6_SIZE);
-	cpu_to_be32_array(spec->ip6dst, rule->tuples.dst_ip, IPV6_SIZE);
+	ipv6_addr_cpu_to_be32(spec->ip6src, rule->tuples.src_ip);
+	ipv6_addr_cpu_to_be32(spec->ip6dst, rule->tuples.dst_ip);
 	if (rule->unused_tuple & BIT(INNER_SRC_IP))
 		memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src));
 	else
-		cpu_to_be32_array(spec_mask->ip6src,
-				  rule->tuples_mask.src_ip, IPV6_SIZE);
+		ipv6_addr_cpu_to_be32(spec_mask->ip6src,
+				      rule->tuples_mask.src_ip);
 
 	if (rule->unused_tuple & BIT(INNER_DST_IP))
 		memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst));
 	else
-		cpu_to_be32_array(spec_mask->ip6dst,
-				  rule->tuples_mask.dst_ip, IPV6_SIZE);
+		ipv6_addr_cpu_to_be32(spec_mask->ip6dst,
+				      rule->tuples_mask.dst_ip);
 
 	spec->tclass = rule->tuples.ip_tos;
 	spec_mask->tclass = rule->unused_tuple & BIT(INNER_IP_TOS) ?
@@ -7019,7 +7018,7 @@ static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys,
 	} else {
 		int i;
 
-		for (i = 0; i < IPV6_SIZE; i++) {
+		for (i = 0; i < IPV6_ADDR_WORDS; i++) {
 			tuples->src_ip[i] = be32_to_cpu(flow_ip6_src[i]);
 			tuples->dst_ip[i] = be32_to_cpu(flow_ip6_dst[i]);
 		}
@@ -7274,14 +7273,14 @@ static int hclge_get_cls_key_ip(const struct flow_rule *flow,
 		struct flow_match_ipv6_addrs match;
 
 		flow_rule_match_ipv6_addrs(flow, &match);
-		be32_to_cpu_array(rule->tuples.src_ip, match.key->src.s6_addr32,
-				  IPV6_SIZE);
-		be32_to_cpu_array(rule->tuples_mask.src_ip,
-				  match.mask->src.s6_addr32, IPV6_SIZE);
-		be32_to_cpu_array(rule->tuples.dst_ip, match.key->dst.s6_addr32,
-				  IPV6_SIZE);
-		be32_to_cpu_array(rule->tuples_mask.dst_ip,
-				  match.mask->dst.s6_addr32, IPV6_SIZE);
+		ipv6_addr_be32_to_cpu(rule->tuples.src_ip,
+				      match.key->src.s6_addr32);
+		ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip,
+				      match.mask->src.s6_addr32);
+		ipv6_addr_be32_to_cpu(rule->tuples.dst_ip,
+				      match.key->dst.s6_addr32);
+		ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip,
+				      match.mask->dst.s6_addr32);
 	} else {
 		rule->unused_tuple |= BIT(INNER_SRC_IP);
 		rule->unused_tuple |= BIT(INNER_DST_IP);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b5178b0f88b3..b9fc719880bb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -8,7 +8,9 @@
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/kfifo.h>
+
 #include <net/devlink.h>
+#include <net/ipv6.h>
 
 #include "hclge_cmd.h"
 #include "hclge_ptp.h"
@@ -718,15 +720,15 @@ struct hclge_fd_cfg {
 };
 
 #define IPV4_INDEX	3
-#define IPV6_SIZE	4
+
 struct hclge_fd_rule_tuples {
 	u8 src_mac[ETH_ALEN];
 	u8 dst_mac[ETH_ALEN];
 	/* Be compatible for ip address of both ipv4 and ipv6.
 	 * For ipv4 address, we store it in src/dst_ip[3].
 	 */
-	u32 src_ip[IPV6_SIZE];
-	u32 dst_ip[IPV6_SIZE];
+	u32 src_ip[IPV6_ADDR_WORDS];
+	u32 dst_ip[IPV6_ADDR_WORDS];
 	u16 src_port;
 	u16 dst_port;
 	u16 vlan_tag1;
-- 
cgit v1.3-3-g829e


From 30dcdd6a3a6caa27d75196bcc4f6ea9c7a51ad19 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 14:10:01 +0300
Subject: selftests: fib_rule_tests: Remove unused functions

The functions are unused since commit 816cda9ae531 ("selftests: net:
fib_rule_tests: add support to select a test to run"). Remove them.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20240814111005.955359-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 7c01f58a20de..c821d91b9ee8 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -56,14 +56,6 @@ log_test()
 	fi
 }
 
-log_section()
-{
-	echo
-	echo "######################################################################"
-	echo "TEST SECTION: $*"
-	echo "######################################################################"
-}
-
 check_nettest()
 {
 	if which nettest > /dev/null 2>&1; then
@@ -453,14 +445,6 @@ fib_rule4_connect_test()
 	$IP -4 rule del dsfield 0x04 table $RTABLE_PEER
 	cleanup_peer
 }
-
-run_fibrule_tests()
-{
-	log_section "IPv4 fib rule"
-	fib_rule4_test
-	log_section "IPv6 fib rule"
-	fib_rule6_test
-}
 ################################################################################
 # usage
 
-- 
cgit v1.3-3-g829e


From b1487d6abeb5ccfc23f61d600ca63d2b09964f9a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 14:10:02 +0300
Subject: selftests: fib_rule_tests: Clarify test results

Clarify the test results by grouping the output of test cases belonging
to the same test under a common title. This is consistent with the
output of fib_tests.sh.

Before:

 # ./fib_rule_tests.sh

     TEST: rule6 check: oif redirect to table                            [ OK ]

     TEST: rule6 del by pref: oif redirect to table                      [ OK ]
 [...]
     TEST: rule4 check: oif redirect to table                            [ OK ]

     TEST: rule4 del by pref: oif redirect to table                      [ OK ]
 [...]

 Tests passed: 116
 Tests failed:   0

After:

 # ./fib_rule_tests.sh

 IPv6 FIB rule tests
     TEST: rule6 check: oif redirect to table                            [ OK ]
     TEST: rule6 del by pref: oif redirect to table                      [ OK ]
 [...]

 IPv4 FIB rule tests
     TEST: rule4 check: oif redirect to table                            [ OK ]
     TEST: rule4 del by pref: oif redirect to table                      [ OK ]
 [...]

 Tests passed: 116
 Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20240814111005.955359-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index c821d91b9ee8..9100dd4d0382 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -35,18 +35,13 @@ log_test()
 	local expected=$2
 	local msg="$3"
 
-	$IP rule show | grep -q l3mdev
-	if [ $? -eq 0 ]; then
-		msg="$msg (VRF)"
-	fi
-
 	if [ ${rc} -eq ${expected} ]; then
 		nsuccess=$((nsuccess+1))
-		printf "\n    TEST: %-60s  [ OK ]\n" "${msg}"
+		printf "    TEST: %-60s  [ OK ]\n" "${msg}"
 	else
 		ret=1
 		nfail=$((nfail+1))
-		printf "\n    TEST: %-60s  [FAIL]\n" "${msg}"
+		printf "    TEST: %-60s  [FAIL]\n" "${msg}"
 		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
 			echo
 			echo "hit enter to continue, 'q' to quit"
@@ -205,10 +200,14 @@ fib_rule6_test_reject()
 
 fib_rule6_test()
 {
+	local ext_name=$1; shift
 	local getmatch
 	local match
 	local cnt
 
+	echo
+	echo "IPv6 FIB rule tests $ext_name"
+
 	# setup the fib rule redirect route
 	$IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink
 
@@ -267,7 +266,7 @@ fib_rule6_test()
 fib_rule6_vrf_test()
 {
 	setup_vrf
-	fib_rule6_test
+	fib_rule6_test "- with VRF"
 	cleanup_vrf
 }
 
@@ -277,6 +276,9 @@ fib_rule6_connect_test()
 {
 	local dsfield
 
+	echo
+	echo "IPv6 FIB rule connect tests"
+
 	if ! check_nettest; then
 		echo "SKIP: Could not run test without nettest tool"
 		return
@@ -344,10 +346,14 @@ fib_rule4_test_reject()
 
 fib_rule4_test()
 {
+	local ext_name=$1; shift
 	local getmatch
 	local match
 	local cnt
 
+	echo
+	echo "IPv4 FIB rule tests $ext_name"
+
 	# setup the fib rule redirect route
 	$IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink
 
@@ -411,7 +417,7 @@ fib_rule4_test()
 fib_rule4_vrf_test()
 {
 	setup_vrf
-	fib_rule4_test
+	fib_rule4_test "- with VRF"
 	cleanup_vrf
 }
 
@@ -421,6 +427,9 @@ fib_rule4_connect_test()
 {
 	local dsfield
 
+	echo
+	echo "IPv4 FIB rule connect tests"
+
 	if ! check_nettest; then
 		echo "SKIP: Could not run test without nettest tool"
 		return
-- 
cgit v1.3-3-g829e


From 9b6dcef32c2d8fe357592da5f6f52ef2edf1652d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 14:10:03 +0300
Subject: selftests: fib_rule_tests: Add negative match tests

The fib_rule{4,6} tests verify the behavior of a given FIB rule selector
(e.g., dport, sport) by redirecting to a routing table with a default
route using a FIB rule with the given selector and checking that a route
lookup using the selector matches this default route.

Add negative tests to verify that a FIB rule is not hit when it should
not.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20240814111005.955359-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 87 +++++++++++++++++++++------
 1 file changed, 69 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 9100dd4d0382..085e21ed9fc3 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -174,12 +174,17 @@ fib_rule6_test_match_n_redirect()
 {
 	local match="$1"
 	local getmatch="$2"
-	local description="$3"
+	local getnomatch="$3"
+	local description="$4"
+	local nomatch_description="$5"
 
 	$IP -6 rule add $match table $RTABLE
 	$IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE"
 	log_test $? 0 "rule6 check: $description"
 
+	$IP -6 route get $GW_IP6 $getnomatch 2>&1 | grep -q "table $RTABLE"
+	log_test $? 1 "rule6 check: $nomatch_description"
+
 	fib_rule6_del_by_pref "$match"
 	log_test $? 0 "rule6 del by pref: $description"
 }
@@ -201,6 +206,7 @@ fib_rule6_test_reject()
 fib_rule6_test()
 {
 	local ext_name=$1; shift
+	local getnomatch
 	local getmatch
 	local match
 	local cnt
@@ -212,10 +218,14 @@ fib_rule6_test()
 	$IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink
 
 	match="oif $DEV"
-	fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table"
+	getnomatch="oif lo"
+	fib_rule6_test_match_n_redirect "$match" "$match" "$getnomatch" \
+		"oif redirect to table" "oif no redirect to table"
 
 	match="from $SRC_IP6 iif $DEV"
-	fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table"
+	getnomatch="from $SRC_IP6 iif lo"
+	fib_rule6_test_match_n_redirect "$match" "$match" "$getnomatch" \
+		"iif redirect to table" "iif no redirect to table"
 
 	# Reject dsfield (tos) options which have ECN bits set
 	for cnt in $(seq 1 3); do
@@ -229,37 +239,52 @@ fib_rule6_test()
 		# Using option 'tos' instead of 'dsfield' as old iproute2
 		# versions don't support 'dsfield' in ip rule show.
 		getmatch="tos $cnt"
+		getnomatch="tos 0x20"
 		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
-						"$getmatch redirect to table"
+			"$getnomatch" "$getmatch redirect to table" \
+			"$getnomatch no redirect to table"
 	done
 
 	match="fwmark 0x64"
 	getmatch="mark 0x64"
-	fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table"
+	getnomatch="mark 0x63"
+	fib_rule6_test_match_n_redirect "$match" "$getmatch" "$getnomatch" \
+		"fwmark redirect to table" "fwmark no redirect to table"
 
 	fib_check_iproute_support "uidrange" "uid"
 	if [ $? -eq 0 ]; then
 		match="uidrange 100-100"
 		getmatch="uid 100"
-		fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table"
+		getnomatch="uid 101"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "uid redirect to table" \
+			"uid no redirect to table"
 	fi
 
 	fib_check_iproute_support "sport" "sport"
 	if [ $? -eq 0 ]; then
 		match="sport 666 dport 777"
-		fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table"
+		getnomatch="sport 667 dport 778"
+		fib_rule6_test_match_n_redirect "$match" "$match" \
+			"$getnomatch" "sport and dport redirect to table" \
+			"sport and dport no redirect to table"
 	fi
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
 		match="ipproto tcp"
-		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match"
+		getnomatch="ipproto udp"
+		fib_rule6_test_match_n_redirect "$match" "$match" \
+			"$getnomatch" "ipproto tcp match" "ipproto udp no match"
 	fi
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
 		match="ipproto ipv6-icmp"
-		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match"
+		getnomatch="ipproto tcp"
+		fib_rule6_test_match_n_redirect "$match" "$match" \
+			"$getnomatch" "ipproto ipv6-icmp match" \
+			"ipproto ipv6-tcp no match"
 	fi
 }
 
@@ -320,12 +345,17 @@ fib_rule4_test_match_n_redirect()
 {
 	local match="$1"
 	local getmatch="$2"
-	local description="$3"
+	local getnomatch="$3"
+	local description="$4"
+	local nomatch_description="$5"
 
 	$IP rule add $match table $RTABLE
 	$IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE"
 	log_test $? 0 "rule4 check: $description"
 
+	$IP route get $GW_IP4 $getnomatch 2>&1 | grep -q "table $RTABLE"
+	log_test $? 1 "rule4 check: $nomatch_description"
+
 	fib_rule4_del_by_pref "$match"
 	log_test $? 0 "rule4 del by pref: $description"
 }
@@ -347,6 +377,7 @@ fib_rule4_test_reject()
 fib_rule4_test()
 {
 	local ext_name=$1; shift
+	local getnomatch
 	local getmatch
 	local match
 	local cnt
@@ -358,14 +389,18 @@ fib_rule4_test()
 	$IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink
 
 	match="oif $DEV"
-	fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table"
+	getnomatch="oif lo"
+	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
+		"oif redirect to table" "oif no redirect to table"
 
 	# need enable forwarding and disable rp_filter temporarily as all the
 	# addresses are in the same subnet and egress device == ingress device.
 	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1
 	ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
 	match="from $SRC_IP iif $DEV"
-	fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table"
+	getnomatch="from $SRC_IP iif lo"
+	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
+		"iif redirect to table" "iif no redirect to table"
 	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=0
 
 	# Reject dsfield (tos) options which have ECN bits set
@@ -380,37 +415,53 @@ fib_rule4_test()
 		# Using option 'tos' instead of 'dsfield' as old iproute2
 		# versions don't support 'dsfield' in ip rule show.
 		getmatch="tos $cnt"
+		getnomatch="tos 0x20"
 		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
-						"$getmatch redirect to table"
+			"$getnomatch" "$getmatch redirect to table" \
+			"$getnomatch no redirect to table"
 	done
 
 	match="fwmark 0x64"
 	getmatch="mark 0x64"
-	fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table"
+	getnomatch="mark 0x63"
+	fib_rule4_test_match_n_redirect "$match" "$getmatch" "$getnomatch" \
+		"fwmark redirect to table" "fwmark no redirect to table"
 
 	fib_check_iproute_support "uidrange" "uid"
 	if [ $? -eq 0 ]; then
 		match="uidrange 100-100"
 		getmatch="uid 100"
-		fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table"
+		getnomatch="uid 101"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "uid redirect to table" \
+			"uid no redirect to table"
 	fi
 
 	fib_check_iproute_support "sport" "sport"
 	if [ $? -eq 0 ]; then
 		match="sport 666 dport 777"
-		fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table"
+		getnomatch="sport 667 dport 778"
+		fib_rule4_test_match_n_redirect "$match" "$match" \
+			"$getnomatch" "sport and dport redirect to table" \
+			"sport and dport no redirect to table"
 	fi
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
 		match="ipproto tcp"
-		fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match"
+		getnomatch="ipproto udp"
+		fib_rule4_test_match_n_redirect "$match" "$match" \
+			"$getnomatch" "ipproto tcp match" \
+			"ipproto udp no match"
 	fi
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
 		match="ipproto icmp"
-		fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+		getnomatch="ipproto tcp"
+		fib_rule4_test_match_n_redirect "$match" "$match" \
+			"$getnomatch" "ipproto icmp match" \
+			"ipproto tcp no match"
 	fi
 }
 
-- 
cgit v1.3-3-g829e


From 53f88ed85bdd194b8a30605a264692b28a3ee665 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 14:10:04 +0300
Subject: selftests: fib_rule_tests: Add negative connect tests

The fib_rule{4,6}_connect tests verify that locally generated traffic
from a socket that specifies a DS Field using the IP_TOS / IPV6_TCLASS
socket options is correctly redirected using a FIB rule that matches on
the given DS Field.

Add negative tests to verify that the FIB rule is not hit when the
socket specifies a DS Field that differs from the one used by the FIB
rule.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20240814111005.955359-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 085e21ed9fc3..a3b2c833f050 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -325,6 +325,16 @@ fib_rule6_connect_test()
 		log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})"
 	done
 
+	# Check that UDP and TCP connections fail when using a DS Field that
+	# does not match the previously configured FIB rule.
+	nettest -q -6 -B -t 5 -N $testns -O $peerns -U -D \
+		-Q 0x20 -l 2001:db8::1:11 -r 2001:db8::1:11
+	log_test $? 1 "rule6 dsfield udp no connect (dsfield 0x20)"
+
+	nettest -q -6 -B -t 5 -N $testns -O $peerns -Q 0x20 \
+		-l 2001:db8::1:11 -r 2001:db8::1:11
+	log_test $? 1 "rule6 dsfield tcp no connect (dsfield 0x20)"
+
 	$IP -6 rule del dsfield 0x04 table $RTABLE_PEER
 	cleanup_peer
 }
@@ -502,6 +512,16 @@ fib_rule4_connect_test()
 		log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})"
 	done
 
+	# Check that UDP and TCP connections fail when using a DS Field that
+	# does not match the previously configured FIB rule.
+	nettest -q -B -t 5 -N $testns -O $peerns -D -U -Q 0x20 \
+		-l 198.51.100.11 -r 198.51.100.11
+	log_test $? 1 "rule4 dsfield udp no connect (dsfield 0x20)"
+
+	nettest -q -B -t 5 -N $testns -O $peerns -Q 0x20 \
+		-l 198.51.100.11 -r 198.51.100.11
+	log_test $? 1 "rule4 dsfield tcp no connect (dsfield 0x20)"
+
 	$IP -4 rule del dsfield 0x04 table $RTABLE_PEER
 	cleanup_peer
 }
-- 
cgit v1.3-3-g829e


From 5f1b4f1be2d2b8d85dd07352b097cfc7064ad2e5 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 14:10:05 +0300
Subject: selftests: fib_rule_tests: Test TOS matching with input routes

The TOS value reaches the FIB rule core via different call paths when an
input route is looked up compared to an output route.

Re-test TOS matching with input routes to exercise these code paths.

Pass the 'iif' and 'from' selectors separately from the 'get{,no}match'
variables as otherwise the test name is too long to be printed without
misalignments.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20240814111005.955359-6-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 31 ++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index a3b2c833f050..89034c5b69dc 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -245,6 +245,19 @@ fib_rule6_test()
 			"$getnomatch no redirect to table"
 	done
 
+	# Re-test TOS matching, but with input routes since they are handled
+	# differently from output routes.
+	match="tos 0x10"
+	for cnt in "0x10" "0x11" "0x12" "0x13"; do
+		getmatch="tos $cnt"
+		getnomatch="tos 0x20"
+		fib_rule6_test_match_n_redirect "$match" \
+			"from $SRC_IP6 iif $DEV $getmatch" \
+			"from $SRC_IP6 iif $DEV $getnomatch" \
+			"iif $getmatch redirect to table" \
+			"iif $getnomatch no redirect to table"
+	done
+
 	match="fwmark 0x64"
 	getmatch="mark 0x64"
 	getnomatch="mark 0x63"
@@ -403,15 +416,14 @@ fib_rule4_test()
 	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
 		"oif redirect to table" "oif no redirect to table"
 
-	# need enable forwarding and disable rp_filter temporarily as all the
-	# addresses are in the same subnet and egress device == ingress device.
+	# Enable forwarding and disable rp_filter as all the addresses are in
+	# the same subnet and egress device == ingress device.
 	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1
 	ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0
 	match="from $SRC_IP iif $DEV"
 	getnomatch="from $SRC_IP iif lo"
 	fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \
 		"iif redirect to table" "iif no redirect to table"
-	ip netns exec $testns sysctl -qw net.ipv4.ip_forward=0
 
 	# Reject dsfield (tos) options which have ECN bits set
 	for cnt in $(seq 1 3); do
@@ -431,6 +443,19 @@ fib_rule4_test()
 			"$getnomatch no redirect to table"
 	done
 
+	# Re-test TOS matching, but with input routes since they are handled
+	# differently from output routes.
+	match="tos 0x10"
+	for cnt in "0x10" "0x11" "0x12" "0x13"; do
+		getmatch="tos $cnt"
+		getnomatch="tos 0x20"
+		fib_rule4_test_match_n_redirect "$match" \
+			"from $SRC_IP iif $DEV $getmatch" \
+			"from $SRC_IP iif $DEV $getnomatch" \
+			"iif $getmatch redirect to table" \
+			"iif $getnomatch no redirect to table"
+	done
+
 	match="fwmark 0x64"
 	getmatch="mark 0x64"
 	getnomatch="mark 0x63"
-- 
cgit v1.3-3-g829e


From df37fcf58f2a02eb0d49d27020e3dbd6c1115288 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 13 Aug 2024 10:04:57 -0700
Subject: net: ag71xx: devm_clk_get_enabled

Allows removal of clk_prepare_enable to simplify the code slightly.

Tested on a TP-LINK Archer C7v2.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240813170516.7301-2-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 37 +++++++----------------------------
 1 file changed, 7 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 2916fdb1970b..9cd2b1168740 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -699,29 +699,20 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	np = dev->of_node;
 	ag->mii_bus = NULL;
 
-	ag->clk_mdio = devm_clk_get(dev, "mdio");
+	ag->clk_mdio = devm_clk_get_enabled(dev, "mdio");
 	if (IS_ERR(ag->clk_mdio)) {
 		netif_err(ag, probe, ndev, "Failed to get mdio clk.\n");
 		return PTR_ERR(ag->clk_mdio);
 	}
 
-	err = clk_prepare_enable(ag->clk_mdio);
-	if (err) {
-		netif_err(ag, probe, ndev, "Failed to enable mdio clk.\n");
-		return err;
-	}
-
 	mii_bus = devm_mdiobus_alloc(dev);
-	if (!mii_bus) {
-		err = -ENOMEM;
-		goto mdio_err_put_clk;
-	}
+	if (!mii_bus)
+		return -ENOMEM;
 
 	ag->mdio_reset = of_reset_control_get_exclusive(np, "mdio");
 	if (IS_ERR(ag->mdio_reset)) {
 		netif_err(ag, probe, ndev, "Failed to get reset mdio.\n");
-		err = PTR_ERR(ag->mdio_reset);
-		goto mdio_err_put_clk;
+		return PTR_ERR(ag->mdio_reset);
 	}
 
 	mii_bus->name = "ag71xx_mdio";
@@ -743,22 +734,17 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	err = of_mdiobus_register(mii_bus, mnp);
 	of_node_put(mnp);
 	if (err)
-		goto mdio_err_put_clk;
+		return err;
 
 	ag->mii_bus = mii_bus;
 
 	return 0;
-
-mdio_err_put_clk:
-	clk_disable_unprepare(ag->clk_mdio);
-	return err;
 }
 
 static void ag71xx_mdio_remove(struct ag71xx *ag)
 {
 	if (ag->mii_bus)
 		mdiobus_unregister(ag->mii_bus);
-	clk_disable_unprepare(ag->clk_mdio);
 }
 
 static void ag71xx_hw_stop(struct ag71xx *ag)
@@ -1853,7 +1839,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	ag->clk_eth = devm_clk_get(&pdev->dev, "eth");
+	ag->clk_eth = devm_clk_get_enabled(&pdev->dev, "eth");
 	if (IS_ERR(ag->clk_eth)) {
 		netif_err(ag, probe, ndev, "Failed to get eth clk.\n");
 		return PTR_ERR(ag->clk_eth);
@@ -1933,19 +1919,13 @@ static int ag71xx_probe(struct platform_device *pdev)
 	netif_napi_add_weight(ndev, &ag->napi, ag71xx_poll,
 			      AG71XX_NAPI_WEIGHT);
 
-	err = clk_prepare_enable(ag->clk_eth);
-	if (err) {
-		netif_err(ag, probe, ndev, "Failed to enable eth clk.\n");
-		return err;
-	}
-
 	ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0);
 
 	ag71xx_hw_init(ag);
 
 	err = ag71xx_mdio_probe(ag);
 	if (err)
-		goto err_put_clk;
+		return err;
 
 	platform_set_drvdata(pdev, ndev);
 
@@ -1970,8 +1950,6 @@ static int ag71xx_probe(struct platform_device *pdev)
 
 err_mdio_remove:
 	ag71xx_mdio_remove(ag);
-err_put_clk:
-	clk_disable_unprepare(ag->clk_eth);
 	return err;
 }
 
@@ -1986,7 +1964,6 @@ static void ag71xx_remove(struct platform_device *pdev)
 	ag = netdev_priv(ndev);
 	unregister_netdev(ndev);
 	ag71xx_mdio_remove(ag);
-	clk_disable_unprepare(ag->clk_eth);
 	platform_set_drvdata(pdev, NULL);
 }
 
-- 
cgit v1.3-3-g829e


From 8ef34bea8cad381e0b5c90f9e4e539f48e8c2d7f Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 13 Aug 2024 10:04:58 -0700
Subject: net: ag71xx: use devm for of_mdiobus_register

Allows removing ag71xx_mdio_remove.

Removed ag.mii_bus variable. Local one can be used with devm. Easier to
reason about as mii_bus is only used here now. Also shrinks the struct
slightly.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240813170516.7301-3-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 23 +++--------------------
 1 file changed, 3 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 9cd2b1168740..7bc0fb33e582 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -380,7 +380,6 @@ struct ag71xx {
 	int mac_idx;
 
 	struct reset_control *mdio_reset;
-	struct mii_bus *mii_bus;
 	struct clk *clk_mdio;
 	struct clk *clk_eth;
 };
@@ -697,7 +696,6 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	int err;
 
 	np = dev->of_node;
-	ag->mii_bus = NULL;
 
 	ag->clk_mdio = devm_clk_get_enabled(dev, "mdio");
 	if (IS_ERR(ag->clk_mdio)) {
@@ -731,22 +729,14 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	}
 
 	mnp = of_get_child_by_name(np, "mdio");
-	err = of_mdiobus_register(mii_bus, mnp);
+	err = devm_of_mdiobus_register(dev, mii_bus, mnp);
 	of_node_put(mnp);
 	if (err)
 		return err;
 
-	ag->mii_bus = mii_bus;
-
 	return 0;
 }
 
-static void ag71xx_mdio_remove(struct ag71xx *ag)
-{
-	if (ag->mii_bus)
-		mdiobus_unregister(ag->mii_bus);
-}
-
 static void ag71xx_hw_stop(struct ag71xx *ag)
 {
 	/* disable all interrupts and stop the rx/tx engine */
@@ -1932,14 +1922,14 @@ static int ag71xx_probe(struct platform_device *pdev)
 	err = ag71xx_phylink_setup(ag);
 	if (err) {
 		netif_err(ag, probe, ndev, "failed to setup phylink (%d)\n", err);
-		goto err_mdio_remove;
+		return err;
 	}
 
 	err = register_netdev(ndev);
 	if (err) {
 		netif_err(ag, probe, ndev, "unable to register net device\n");
 		platform_set_drvdata(pdev, NULL);
-		goto err_mdio_remove;
+		return err;
 	}
 
 	netif_info(ag, probe, ndev, "Atheros AG71xx at 0x%08lx, irq %d, mode:%s\n",
@@ -1947,23 +1937,16 @@ static int ag71xx_probe(struct platform_device *pdev)
 		   phy_modes(ag->phy_if_mode));
 
 	return 0;
-
-err_mdio_remove:
-	ag71xx_mdio_remove(ag);
-	return err;
 }
 
 static void ag71xx_remove(struct platform_device *pdev)
 {
 	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct ag71xx *ag;
 
 	if (!ndev)
 		return;
 
-	ag = netdev_priv(ndev);
 	unregister_netdev(ndev);
-	ag71xx_mdio_remove(ag);
 	platform_set_drvdata(pdev, NULL);
 }
 
-- 
cgit v1.3-3-g829e


From cc20a4791641a1cbd1525695fac0d4725dd72509 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 13 Aug 2024 10:04:59 -0700
Subject: net: ag71xx: use devm for register_netdev

Allows completely removing the remove function. Nothing is being done
manually now.

Tested on TP-LINK Archer C7v2.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240813170516.7301-4-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 7bc0fb33e582..ee5d429abdaa 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1925,7 +1925,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = register_netdev(ndev);
+	err = devm_register_netdev(&pdev->dev, ndev);
 	if (err) {
 		netif_err(ag, probe, ndev, "unable to register net device\n");
 		platform_set_drvdata(pdev, NULL);
@@ -1939,17 +1939,6 @@ static int ag71xx_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static void ag71xx_remove(struct platform_device *pdev)
-{
-	struct net_device *ndev = platform_get_drvdata(pdev);
-
-	if (!ndev)
-		return;
-
-	unregister_netdev(ndev);
-	platform_set_drvdata(pdev, NULL);
-}
-
 static const u32 ar71xx_fifo_ar7100[] = {
 	0x0fff0000, 0x00001fff, 0x00780fff,
 };
@@ -2034,7 +2023,6 @@ static const struct of_device_id ag71xx_match[] = {
 
 static struct platform_driver ag71xx_driver = {
 	.probe		= ag71xx_probe,
-	.remove_new	= ag71xx_remove,
 	.driver = {
 		.name	= "ag71xx",
 		.of_match_table = ag71xx_match,
-- 
cgit v1.3-3-g829e


From 795b1aa8f37e38cf1a6202d274960bdd9c2ac44a Mon Sep 17 00:00:00 2001
From: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Date: Wed, 14 Aug 2024 10:59:02 -0700
Subject: idpf: remove redundant 'req_vec_chunks' NULL check

'req_vec_chunks' is used to store the vector info received
from the device control plane. The memory for it is allocated
in idpf_send_alloc_vectors_msg and returns an error if the memory
allocation fails.

'req_vec_chunks' cannot be NULL in the later code flow. So remove
the conditional check to extract the vector ids received from
the device control plane.

Smatch static checker warning:

drivers/net/ethernet/intel/idpf/idpf_lib.c:417 idpf_intr_req()
error: we previously assumed 'adapter->req_vec_chunks'
could be null (see line 360)

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/intel-wired-lan/a355ae8a-9011-4a85-a4d1-5b2793bb5f7b@stanley.mountain/
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Tested-by: Krishneil Singh <krishneil.k.singh@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20240814175903.4166390-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c | 23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 0b6c8fd5bc90..4f20343e49a9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -357,24 +357,11 @@ int idpf_intr_req(struct idpf_adapter *adapter)
 		goto free_msix;
 	}
 
-	if (adapter->req_vec_chunks) {
-		struct virtchnl2_vector_chunks *vchunks;
-		struct virtchnl2_alloc_vectors *ac;
-
-		ac = adapter->req_vec_chunks;
-		vchunks = &ac->vchunks;
-
-		num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs,
-					       vchunks);
-		if (num_vec_ids < v_actual) {
-			err = -EINVAL;
-			goto free_vecids;
-		}
-	} else {
-		int i;
-
-		for (i = 0; i < v_actual; i++)
-			vecids[i] = i;
+	num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs,
+				       &adapter->req_vec_chunks->vchunks);
+	if (num_vec_ids < v_actual) {
+		err = -EINVAL;
+		goto free_vecids;
 	}
 
 	for (vector = 0; vector < v_actual; vector++) {
-- 
cgit v1.3-3-g829e


From 02404bdb811dbea6ab523675ec98d9f815cfb3b2 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Thu, 15 Aug 2024 12:34:07 -0400
Subject: dt-bindings: net: mdio: change nodename match pattern

Change mdio.yaml nodename match pattern to
	'^mdio(-(bus|external))?(@.+|-([0-9]+))$'

Fix mdio.yaml wrong parser mdio controller's address instead phy's address
when mdio-mux exista.

For example:
mdio-mux-emi1@54 {
	compatible = "mdio-mux-mmioreg", "mdio-mux";

        mdio@20 {
		reg = <0x20>;
		       ^^^ This is mdio controller register

		ethernet-phy@2 {
			reg = <0x2>;
                              ^^^ This phy's address
		};
	};
};

Only phy's address is limited to 31 because MDIO bus definition.

But CHECK_DTBS report below warning:

arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dtb: mdio-mux-emi1@54:
	mdio@20:reg:0:0: 32 is greater than the maximum of 31

The reason is that "mdio-mux-emi1@54" match "nodename: '^mdio(@.*)?'" in
mdio.yaml.

Change to '^mdio(-(bus|external))?(@.+|-([0-9]+))?$' to avoid wrong match
mdio mux controller's node.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240815163408.4184705-1-Frank.Li@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/mdio.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml
index a266ade918ca..bed3987a8fbf 100644
--- a/Documentation/devicetree/bindings/net/mdio.yaml
+++ b/Documentation/devicetree/bindings/net/mdio.yaml
@@ -19,7 +19,7 @@ description:
 
 properties:
   $nodename:
-    pattern: "^mdio(@.*)?"
+    pattern: '^mdio(-(bus|external))?(@.+|-([0-9]+))?$'
 
   "#address-cells":
     const: 1
-- 
cgit v1.3-3-g829e


From 9480fd0cd8a4621d42a88d43b0e7864048a6b09e Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Thu, 15 Aug 2024 17:23:43 +0300
Subject: docs: networking: Align documentation with behavior change

Following commit 9f7e8fbb91f8 ("net/mlx5: offset comp irq index in name by one"),
which fixed the index in IRQ name to start once again from 0, we change
the documentation accordingly.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Link: https://patch.msgid.link/20240815142343.2254247-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/multi-pf-netdev.rst | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst
index 268819225866..2cd25d81aaa7 100644
--- a/Documentation/networking/multi-pf-netdev.rst
+++ b/Documentation/networking/multi-pf-netdev.rst
@@ -111,11 +111,11 @@ The relation between PF, irq, napi, and queue can be observed via netlink spec::
 Here you can clearly observe our channels distribution policy::
 
   $ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1
-  /proc/irq/36/mlx5_comp1@pci:0000:08:00.0
-  /proc/irq/39/mlx5_comp1@pci:0000:09:00.0
-  /proc/irq/40/mlx5_comp2@pci:0000:08:00.0
-  /proc/irq/41/mlx5_comp2@pci:0000:09:00.0
-  /proc/irq/42/mlx5_comp3@pci:0000:08:00.0
+  /proc/irq/36/mlx5_comp0@pci:0000:08:00.0
+  /proc/irq/39/mlx5_comp0@pci:0000:09:00.0
+  /proc/irq/40/mlx5_comp1@pci:0000:08:00.0
+  /proc/irq/41/mlx5_comp1@pci:0000:09:00.0
+  /proc/irq/42/mlx5_comp2@pci:0000:08:00.0
 
 Steering
 ========
-- 
cgit v1.3-3-g829e


From 1f803c95693f140bed46cd5581b97592e20b723e Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski <olek2@wp.pl>
Date: Thu, 15 Aug 2024 09:49:56 +0200
Subject: net: ethernet: lantiq_etop: remove unused variable

Remove a variable that has never been used.

Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Link: https://patch.msgid.link/20240815074956.155224-1-olek2@wp.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/lantiq_etop.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 9e6984815386..3c289bfe0a09 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -95,7 +95,6 @@ struct ltq_etop_priv {
 	struct mii_bus *mii_bus;
 
 	struct ltq_etop_chan ch[MAX_DMA_CHAN];
-	int tx_free[MAX_DMA_CHAN >> 1];
 
 	int tx_burst_len;
 	int rx_burst_len;
-- 
cgit v1.3-3-g829e


From 1c66df862561a11a8ea9b4c97ecfe91983c3bda7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 15 Aug 2024 16:19:25 +0100
Subject: net: txgbe: Remove unnecessary NULL check before free

Remove unnecessary NULL check before freeing using kvfree().
This function will ignore a NULL argument.

Flagged by Coccinelle:

  .../txgbe_hw.c:187:2-8: WARNING: NULL check before some freeing functions is not needed.

No functional change intended.
Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240815-txgbe-kvfree-v1-1-5ecf8656f555@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index d6b2b3c781b6..cd1372da92a9 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -103,8 +103,7 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum)
 		if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM)
 			*checksum += local_buffer[i];
 
-	if (eeprom_ptrs)
-		kvfree(eeprom_ptrs);
+	kvfree(eeprom_ptrs);
 
 	*checksum = TXGBE_EEPROM_SUM - *checksum;
 
-- 
cgit v1.3-3-g829e


From f4ae8420f6ebdabf97e0c4f5f99412768687985f Mon Sep 17 00:00:00 2001
From: Christoph Paasch <cpaasch@apple.com>
Date: Thu, 15 Aug 2024 09:12:01 -0700
Subject: mpls: Reduce skb re-allocations due to skb_cow()

mpls_xmit() needs to prepend the MPLS-labels to the packet. That implies
one needs to make sure there is enough space for it in the headers.

Calling skb_cow() implies however that one wants to change even the
playload part of the packet (which is not true for MPLS). Thus, call
skb_cow_head() instead, which is what other tunnelling protocols do.

Running a server with this comm it entirely removed the calls to
pskb_expand_head() from the callstack in mpls_xmit() thus having
significant CPU-reduction, especially at peak times.

Cc: Roopa Prabhu <roopa@nvidia.com>
Reported-by: Craig Taylor <cmtaylor@apple.com>
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240815161201.22021-1-cpaasch@apple.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mpls/mpls_iptunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 4385fd3b13be..6e73da94af7f 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -106,7 +106,7 @@ static int mpls_xmit(struct sk_buff *skb)
 		hh_len = 0;
 
 	/* Ensure there is enough space for the headers in the skb */
-	if (skb_cow(skb, hh_len + new_header_size))
+	if (skb_cow_head(skb, hh_len + new_header_size))
 		goto drop;
 
 	skb_set_inner_protocol(skb, skb->protocol);
-- 
cgit v1.3-3-g829e


From a99ef548bba01435f19137cf1670861be1c1ee4b Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 15 Aug 2024 16:27:46 +0100
Subject: bnx2x: Set ivi->vlan field as an integer

In bnx2x_get_vf_config():
* The vlan field of ivi is a 32-bit integer, it is used to store a vlan ID.
* The vlan field of bulletin is a 16-bit integer, it is also used to store
  a vlan ID.

In the current code, ivi->vlan is set using memset. But in the case of
setting it to the value of bulletin->vlan, this involves reading
32 bits from a 16bit source. This is likely safe, as the following
6 bytes are padding in the same structure, but none the less, it seems
undesirable.

However, it is entirely unclear to me how this scheme works on
big-endian systems.

Resolve this by simply assigning integer values to ivi->vlan.

Flagged by W=1 builds.
f.e. gcc-14 reports:

In function 'fortify_memcpy_chk',
    inlined from 'bnx2x_get_vf_config' at .../bnx2x_sriov.c:2655:4:
.../fortify-string.h:580:25: warning: call to '__read_overflow2_field' declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning]
  580 |                         __read_overflow2_field(q_size_field, size);
      |                         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240815-bnx2x-int-vlan-v1-1-5940b76e37ad@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 77d4cb4ad782..12198fc3ab22 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -2652,10 +2652,10 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 		/* vlan */
 		if (bulletin->valid_bitmap & (1 << VLAN_VALID))
 			/* vlan configured by ndo so its in bulletin board */
-			memcpy(&ivi->vlan, &bulletin->vlan, VLAN_HLEN);
+			ivi->vlan = bulletin->vlan;
 		else
 			/* function has not been loaded yet. Show vlans as 0s */
-			memset(&ivi->vlan, 0, VLAN_HLEN);
+			ivi->vlan = 0;
 
 		mutex_unlock(&bp->vfdb->bulletin_mutex);
 	}
-- 
cgit v1.3-3-g829e


From 1bf8e07c382bd4f04ede81ecc05267a8ffd60999 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 14 Aug 2024 16:46:18 -0400
Subject: dt-binding: ptp: fsl,ptp: add pci1957,ee02 compatible string for
 fsl,enetc-ptp

fsl,enetc-ptp is embedded pcie device. Add compatible string pci1957,ee02.

Fix warning:
arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-kbox-a-230-ls.dtb: ethernet@0,4:
	compatible:0: 'pci1957,ee02' is not one of ['fsl,etsec-ptp', 'fsl,fman-ptp-timer', 'fsl,dpaa2-ptp', 'fsl,enetc-ptp']

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/ptp/fsl,ptp.yaml | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml
index 3bb8615e3e91..42ca895f3c4e 100644
--- a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml
+++ b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml
@@ -11,11 +11,14 @@ maintainers:
 
 properties:
   compatible:
-    enum:
-      - fsl,etsec-ptp
-      - fsl,fman-ptp-timer
-      - fsl,dpaa2-ptp
-      - fsl,enetc-ptp
+    oneOf:
+      - enum:
+          - fsl,etsec-ptp
+          - fsl,fman-ptp-timer
+          - fsl,dpaa2-ptp
+      - items:
+          - const: pci1957,ee02
+          - const: fsl,enetc-ptp
 
   reg:
     maxItems: 1
@@ -123,6 +126,15 @@ required:
   - compatible
   - reg
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,enetc-ptp
+    then:
+      $ref: /schemas/pci/pci-device.yaml
+
 additionalProperties: false
 
 examples:
-- 
cgit v1.3-3-g829e


From 26a77d02891ab62172085a4f94af9b3c90aed387 Mon Sep 17 00:00:00 2001
From: Antonio Ojea <aojea@google.com>
Date: Thu, 27 Jun 2024 13:27:10 +0200
Subject: netfilter: nfnetlink_queue: unbreak SCTP traffic

when packet is enqueued with nfqueue and GSO is enabled, checksum
calculation has to take into account the protocol, as SCTP uses a
32 bits CRC checksum.

Enter skb_gso_segment() path in case of SCTP GSO packets because
skb_zerocopy() does not support for GSO_BY_FRAGS.

Joint work with Pablo.

Signed-off-by: Antonio Ojea <aojea@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/core/dev.c                  |  1 +
 net/netfilter/nfnetlink_queue.c | 12 ++++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index e7260889d4cb..8384282acadf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3386,6 +3386,7 @@ int skb_crc32c_csum_help(struct sk_buff *skb)
 out:
 	return ret;
 }
+EXPORT_SYMBOL(skb_crc32c_csum_help);
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index e0716da256bf..d2773ce9b585 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -540,6 +540,14 @@ nla_put_failure:
 	return -1;
 }
 
+static int nf_queue_checksum_help(struct sk_buff *entskb)
+{
+	if (skb_csum_is_sctp(entskb))
+		return skb_crc32c_csum_help(entskb);
+
+	return skb_checksum_help(entskb);
+}
+
 static struct sk_buff *
 nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 			   struct nf_queue_entry *entry,
@@ -602,7 +610,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	case NFQNL_COPY_PACKET:
 		if (!(queue->flags & NFQA_CFG_F_GSO) &&
 		    entskb->ip_summed == CHECKSUM_PARTIAL &&
-		    skb_checksum_help(entskb))
+		    nf_queue_checksum_help(entskb))
 			return NULL;
 
 		data_len = READ_ONCE(queue->copy_range);
@@ -1014,7 +1022,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
 		break;
 	}
 
-	if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(skb))
+	if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb)))
 		return __nfqnl_enqueue_packet(net, queue, entry);
 
 	nf_bridge_adjust_skb_data(skb);
-- 
cgit v1.3-3-g829e


From 4e97d521c2be094718c4c5c7c4f785e8972b4af0 Mon Sep 17 00:00:00 2001
From: Antonio Ojea <aojea@google.com>
Date: Tue, 2 Jul 2024 13:15:36 +0200
Subject: selftests: netfilter: nft_queue.sh: sctp coverage

Test that nfqueue with and without GSO process SCTP packets correctly.

Joint work with Florian and Pablo.

Signed-off-by: Antonio Ojea <aojea@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/net/netfilter/config       |  2 +
 tools/testing/selftests/net/netfilter/nft_queue.sh | 85 +++++++++++++++++++++-
 2 files changed, 86 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config
index 63ef80ef47a4..b2dd4db45215 100644
--- a/tools/testing/selftests/net/netfilter/config
+++ b/tools/testing/selftests/net/netfilter/config
@@ -87,3 +87,5 @@ CONFIG_XFRM_USER=m
 CONFIG_XFRM_STATISTICS=y
 CONFIG_NET_PKTGEN=m
 CONFIG_TUN=m
+CONFIG_INET_DIAG=m
+CONFIG_SCTP_DIAG=m
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index c61d23a8c88d..f3bdeb1271eb 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -25,6 +25,9 @@ cleanup()
 }
 
 checktool "nft --version" "test without nft tool"
+checktool "socat -h" "run test without socat"
+
+modprobe -q sctp
 
 trap cleanup EXIT
 
@@ -265,7 +268,6 @@ test_tcp_forward()
 
 test_tcp_localhost()
 {
-	dd conv=sparse status=none if=/dev/zero bs=1M count=200 of="$TMPINPUT"
 	timeout 5 ip netns exec "$nsrouter" socat -u TCP-LISTEN:12345 STDOUT >/dev/null &
 	local rpid=$!
 
@@ -375,6 +377,82 @@ EOF
 	wait 2>/dev/null
 }
 
+sctp_listener_ready()
+{
+	ss -S -N "$1" -ln -o "sport = :12345" | grep -q 12345
+}
+
+test_sctp_forward()
+{
+	ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
+flush ruleset
+table inet sctpq {
+        chain forward {
+        type filter hook forward priority 0; policy accept;
+                sctp dport 12345 queue num 10
+        }
+}
+EOF
+	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+	local rpid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
+
+	ip netns exec "$nsrouter" ./nf_queue -q 10 -G -t "$timeout" &
+	local nfqpid=$!
+
+	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
+
+	if ! ip netns exec "$nsrouter" nft delete table inet sctpq; then
+		echo "FAIL:  Could not delete sctpq table"
+		exit 1
+	fi
+
+	wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain"
+
+	if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then
+		echo "FAIL: lost packets?!" 1>&2
+		exit 1
+	fi
+}
+
+test_sctp_output()
+{
+        ip netns exec "$ns1" nft -f /dev/stdin <<EOF
+table inet sctpq {
+        chain output {
+        type filter hook output priority 0; policy accept;
+                sctp dport 12345 queue num 11
+        }
+}
+EOF
+	# reduce test file size, software segmentation causes sk wmem increase.
+	dd conv=sparse status=none if=/dev/zero bs=1M count=50 of="$TMPINPUT"
+
+	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
+	local rpid=$!
+
+	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
+
+	ip netns exec "$ns1" ./nf_queue -q 11 -t "$timeout" &
+	local nfqpid=$!
+
+	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
+
+	if ! ip netns exec "$ns1" nft delete table inet sctpq; then
+		echo "FAIL:  Could not delete sctpq table"
+		exit 1
+	fi
+
+	# must wait before checking completeness of output file.
+	wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO"
+
+	if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then
+		echo "FAIL: lost packets?!" 1>&2
+		exit 1
+	fi
+}
+
 test_queue_removal()
 {
 	read tainted_then < /proc/sys/kernel/tainted
@@ -443,11 +521,16 @@ test_queue 10
 # same.  We queue to a second program as well.
 load_ruleset "filter2" 20
 test_queue 20
+ip netns exec "$ns1" nft flush ruleset
 
 test_tcp_forward
 test_tcp_localhost
 test_tcp_localhost_connectclose
 test_tcp_localhost_requeue
+test_sctp_forward
+test_sctp_output
+
+# should be last, adds vrf device in ns1 and changes routes
 test_icmp_vrf
 test_queue_removal
 
-- 
cgit v1.3-3-g829e


From e2444c1d463995477fb447be9d0c54150a5c393b Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 28 May 2024 11:37:54 +0100
Subject: netfilter: nfnetlink: convert kfree_skb to consume_skb

Use consume_skb in the batch code path to avoid generating spurious
NOT_SPECIFIED skb drop reasons.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 932b3ddb34f1..7784ec094097 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -402,27 +402,27 @@ replay_abort:
 		{
 			nfnl_unlock(subsys_id);
 			netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
-			return kfree_skb(skb);
+			return consume_skb(skb);
 		}
 	}
 
 	if (!ss->valid_genid || !ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
 		netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
-		return kfree_skb(skb);
+		return consume_skb(skb);
 	}
 
 	if (!try_module_get(ss->owner)) {
 		nfnl_unlock(subsys_id);
 		netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
-		return kfree_skb(skb);
+		return consume_skb(skb);
 	}
 
 	if (!ss->valid_genid(net, genid)) {
 		module_put(ss->owner);
 		nfnl_unlock(subsys_id);
 		netlink_ack(oskb, nlh, -ERESTART, NULL);
-		return kfree_skb(skb);
+		return consume_skb(skb);
 	}
 
 	nfnl_unlock(subsys_id);
@@ -567,7 +567,7 @@ done:
 	if (status & NFNL_BATCH_REPLAY) {
 		ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
 		nfnl_err_reset(&err_list);
-		kfree_skb(skb);
+		consume_skb(skb);
 		module_put(ss->owner);
 		goto replay;
 	} else if (status == NFNL_BATCH_DONE) {
@@ -593,7 +593,7 @@ done:
 		err = ss->abort(net, oskb, abort_action);
 		if (err == -EAGAIN) {
 			nfnl_err_reset(&err_list);
-			kfree_skb(skb);
+			consume_skb(skb);
 			module_put(ss->owner);
 			status |= NFNL_BATCH_FAILURE;
 			goto replay_abort;
@@ -601,7 +601,7 @@ done:
 	}
 
 	nfnl_err_deliver(&err_list, oskb);
-	kfree_skb(skb);
+	consume_skb(skb);
 	module_put(ss->owner);
 }
 
-- 
cgit v1.3-3-g829e


From c1aa38866b9c58dc6cf7a5fc6a3e1ca75565169e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 10 Jul 2024 10:58:29 +0200
Subject: netfilter: nf_tables: store new sets in dedicated list

nft_set_lookup_byid() is very slow when transaction becomes large, due to
walk of the transaction list.

Add a dedicated list that contains only the new sets.

Before: nft -f ruleset 0.07s user 0.00s system 0% cpu 1:04.84 total
After: nft -f ruleset 0.07s user 0.00s system 0% cpu 30.115 total

.. where ruleset contains ~10 sets with ~100k elements.
The above number is for a combined flush+reload of the ruleset.

With previous flush, even the first NEWELEM has to walk through a few
hundred thousands of DELSET(ELEM) transactions before the first NEWSET
object. To cope with random-order-newset-newsetelem we'd need to replace
commit_set_list with a hashtable.

Expectation is that a NEWELEM operation refers to the most recently added
set, so last entry of the dedicated list should be the set we want.

NB: This is not a bug fix per se (functionality is fine), but with
larger transaction batches list search takes forever, so it would be
nice to speed this up for -stable too, hence adding a "fixes" tag.

Fixes: 958bee14d071 ("netfilter: nf_tables: use new transaction infrastructure to handle sets")
Reported-by: Nadia Pinaeva <n.m.pinaeva@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  2 ++
 net/netfilter/nf_tables_api.c     | 29 ++++++++++++++++++++---------
 2 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1bfdd16890fa..2be4738eae1c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1674,6 +1674,7 @@ struct nft_trans_rule {
 
 struct nft_trans_set {
 	struct nft_trans_binding	nft_trans_binding;
+	struct list_head		list_trans_newset;
 	struct nft_set			*set;
 	u32				set_id;
 	u32				gc_int;
@@ -1875,6 +1876,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re
 struct nftables_pernet {
 	struct list_head	tables;
 	struct list_head	commit_list;
+	struct list_head	commit_set_list;
 	struct list_head	binding_list;
 	struct list_head	module_list;
 	struct list_head	notify_list;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0a2f79346958..3ea5d0163510 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -393,6 +393,7 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
 	struct nft_trans_binding *binding;
+	struct nft_trans_set *trans_set;
 
 	list_add_tail(&trans->list, &nft_net->commit_list);
 
@@ -402,9 +403,13 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr
 
 	switch (trans->msg_type) {
 	case NFT_MSG_NEWSET:
+		trans_set = nft_trans_container_set(trans);
+
 		if (!nft_trans_set_update(trans) &&
 		    nft_set_is_anonymous(nft_trans_set(trans)))
 			list_add_tail(&binding->binding_list, &nft_net->binding_list);
+
+		list_add_tail(&trans_set->list_trans_newset, &nft_net->commit_set_list);
 		break;
 	case NFT_MSG_NEWCHAIN:
 		if (!nft_trans_chain_update(trans) &&
@@ -611,6 +616,7 @@ static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
 
 	trans_set = nft_trans_container_set(trans);
 	INIT_LIST_HEAD(&trans_set->nft_trans_binding.binding_list);
+	INIT_LIST_HEAD(&trans_set->list_trans_newset);
 
 	if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) {
 		nft_trans_set_id(trans) =
@@ -4485,17 +4491,16 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net,
 {
 	struct nftables_pernet *nft_net = nft_pernet(net);
 	u32 id = ntohl(nla_get_be32(nla));
-	struct nft_trans *trans;
+	struct nft_trans_set *trans;
 
-	list_for_each_entry(trans, &nft_net->commit_list, list) {
-		if (trans->msg_type == NFT_MSG_NEWSET) {
-			struct nft_set *set = nft_trans_set(trans);
+	/* its likely the id we need is at the tail, not at start */
+	list_for_each_entry_reverse(trans, &nft_net->commit_set_list, list_trans_newset) {
+		struct nft_set *set = trans->set;
 
-			if (id == nft_trans_set_id(trans) &&
-			    set->table == table &&
-			    nft_active_genmask(set, genmask))
-				return set;
-		}
+		if (id == trans->set_id &&
+		    set->table == table &&
+		    nft_active_genmask(set, genmask))
+			return set;
 	}
 	return ERR_PTR(-ENOENT);
 }
@@ -10447,6 +10452,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 				nft_flow_rule_destroy(nft_trans_flow_rule(trans));
 			break;
 		case NFT_MSG_NEWSET:
+			list_del(&nft_trans_container_set(trans)->list_trans_newset);
 			if (nft_trans_set_update(trans)) {
 				struct nft_set *set = nft_trans_set(trans);
 
@@ -10755,6 +10761,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSET:
+			list_del(&nft_trans_container_set(trans)->list_trans_newset);
 			if (nft_trans_set_update(trans)) {
 				nft_trans_destroy(trans);
 				break;
@@ -10850,6 +10857,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 		}
 	}
 
+	WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list));
+
 	nft_set_abort_update(&set_update_list);
 
 	synchronize_rcu();
@@ -11519,6 +11528,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 
 	INIT_LIST_HEAD(&nft_net->tables);
 	INIT_LIST_HEAD(&nft_net->commit_list);
+	INIT_LIST_HEAD(&nft_net->commit_set_list);
 	INIT_LIST_HEAD(&nft_net->binding_list);
 	INIT_LIST_HEAD(&nft_net->module_list);
 	INIT_LIST_HEAD(&nft_net->notify_list);
@@ -11549,6 +11559,7 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	gc_seq = nft_gc_seq_begin(nft_net);
 
 	WARN_ON_ONCE(!list_empty(&nft_net->commit_list));
+	WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list));
 
 	if (!list_empty(&nft_net->module_list))
 		nf_tables_module_autoload_cleanup(net);
-- 
cgit v1.3-3-g829e


From c9526aeb4998393171d85225ff540e28c7d4ab86 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 15 Jul 2024 13:32:31 +0200
Subject: netfilter: nf_tables: do not remove elements if set backend
 implements .abort

pipapo set backend maintains two copies of the datastructure, removing
the elements from the copy that is going to be discarded slows down
the abort path significantly, from several minutes to few seconds after
this patch.

This patch was previously reverted by

  f86fb94011ae ("netfilter: nf_tables: revert do not remove elements if set backend implements .abort")

but it is now possible since recent work by Florian Westphal to perform
on-demand clone from insert/remove path:

  532aec7e878b ("netfilter: nft_set_pipapo: remove dirty flag")
  3f1d886cc7c3 ("netfilter: nft_set_pipapo: move cloning of match info to insert/removal path")
  a238106703ab ("netfilter: nft_set_pipapo: prepare pipapo_get helper for on-demand clone")
  c5444786d0ea ("netfilter: nft_set_pipapo: merge deactivate helper into caller")
  6c108d9bee44 ("netfilter: nft_set_pipapo: prepare walk function for on-demand clone")
  8b8a2417558c ("netfilter: nft_set_pipapo: prepare destroy function for on-demand clone")
  80efd2997fb9 ("netfilter: nft_set_pipapo: make pipapo_clone helper return NULL")
  a590f4760922 ("netfilter: nft_set_pipapo: move prove_locking helper around")

after this series, the clone is fully released once aborted, no need to
take it back to previous state. Thus, no stale reference to elements can
occur.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3ea5d0163510..c85d037a363b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -10789,7 +10789,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 				break;
 			}
 			te = nft_trans_container_elem(trans);
-			nft_setelem_remove(net, te->set, te->elem_priv);
+			if (!te->set->ops->abort ||
+			    nft_setelem_is_catchall(te->set, te->elem_priv))
+				nft_setelem_remove(net, te->set, te->elem_priv);
+
 			if (!nft_setelem_is_catchall(te->set, te->elem_priv))
 				atomic_dec(&te->set->nelems);
 
-- 
cgit v1.3-3-g829e


From d5283b47e225e1473e1a07085b9c4e6bfd08ba51 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Wed, 17 Jul 2024 22:09:44 -0400
Subject: netfilter: move nf_ct_netns_get out of nf_conncount_init

This patch is to move nf_ct_netns_get() out of nf_conncount_init()
and let the consumers of nf_conncount decide if they want to turn
on netfilter conntrack.

It makes nf_conncount more flexible to be used in other places and
avoids netfilter conntrack turned on when using it in openvswitch
conntrack.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_count.h |  6 ++----
 net/netfilter/nf_conncount.c               | 15 +++------------
 net/netfilter/xt_connlimit.c               | 15 +++++++++++++--
 net/openvswitch/conntrack.c                |  5 ++---
 4 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index e227d997fc71..1b58b5b91ff6 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -15,10 +15,8 @@ struct nf_conncount_list {
 	unsigned int count;	/* length of list */
 };
 
-struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
-					    unsigned int keylen);
-void nf_conncount_destroy(struct net *net, unsigned int family,
-			  struct nf_conncount_data *data);
+struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen);
+void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data);
 
 unsigned int nf_conncount_count(struct net *net,
 				struct nf_conncount_data *data,
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 34ba14e59e95..4890af4dc263 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -522,11 +522,10 @@ unsigned int nf_conncount_count(struct net *net,
 }
 EXPORT_SYMBOL_GPL(nf_conncount_count);
 
-struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
-					    unsigned int keylen)
+struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen)
 {
 	struct nf_conncount_data *data;
-	int ret, i;
+	int i;
 
 	if (keylen % sizeof(u32) ||
 	    keylen / sizeof(u32) > MAX_KEYLEN ||
@@ -539,12 +538,6 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family
 	if (!data)
 		return ERR_PTR(-ENOMEM);
 
-	ret = nf_ct_netns_get(net, family);
-	if (ret < 0) {
-		kfree(data);
-		return ERR_PTR(ret);
-	}
-
 	for (i = 0; i < ARRAY_SIZE(data->root); ++i)
 		data->root[i] = RB_ROOT;
 
@@ -581,13 +574,11 @@ static void destroy_tree(struct rb_root *r)
 	}
 }
 
-void nf_conncount_destroy(struct net *net, unsigned int family,
-			  struct nf_conncount_data *data)
+void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data)
 {
 	unsigned int i;
 
 	cancel_work_sync(&data->gc_work);
-	nf_ct_netns_put(net, family);
 
 	for (i = 0; i < ARRAY_SIZE(data->root); ++i)
 		destroy_tree(&data->root[i]);
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 5d04ef80a61d..0e762277bcf8 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -86,6 +86,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
 {
 	struct xt_connlimit_info *info = par->matchinfo;
 	unsigned int keylen;
+	int ret;
 
 	keylen = sizeof(u32);
 	if (par->family == NFPROTO_IPV6)
@@ -93,8 +94,17 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
 	else
 		keylen += sizeof(struct in_addr);
 
+	ret = nf_ct_netns_get(par->net, par->family);
+	if (ret < 0) {
+		pr_info_ratelimited("cannot load conntrack support for proto=%u\n",
+				    par->family);
+		return ret;
+	}
+
 	/* init private data */
-	info->data = nf_conncount_init(par->net, par->family, keylen);
+	info->data = nf_conncount_init(par->net, keylen);
+	if (IS_ERR(info->data))
+		nf_ct_netns_put(par->net, par->family);
 
 	return PTR_ERR_OR_ZERO(info->data);
 }
@@ -103,7 +113,8 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
 {
 	const struct xt_connlimit_info *info = par->matchinfo;
 
-	nf_conncount_destroy(par->net, par->family, info->data);
+	nf_conncount_destroy(par->net, info->data);
+	nf_ct_netns_put(par->net, par->family);
 }
 
 static struct xt_match connlimit_mt_reg __read_mostly = {
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index a3da5ee34f92..3bb4810234aa 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1608,8 +1608,7 @@ static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net)
 	for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++)
 		INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]);
 
-	ovs_net->ct_limit_info->data =
-		nf_conncount_init(net, NFPROTO_INET, sizeof(u32));
+	ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32));
 
 	if (IS_ERR(ovs_net->ct_limit_info->data)) {
 		err = PTR_ERR(ovs_net->ct_limit_info->data);
@@ -1626,7 +1625,7 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
 	const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info;
 	int i;
 
-	nf_conncount_destroy(net, NFPROTO_INET, info->data);
+	nf_conncount_destroy(net, info->data);
 	for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) {
 		struct hlist_head *head = &info->limits[i];
 		struct ovs_ct_limit *ct_limit;
-- 
cgit v1.3-3-g829e


From 190de5449973056f416c855b11fdfee2fc18f550 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 31 Jul 2024 12:01:26 +0200
Subject: selftests/bpf: Support more socket types in create_pair()

Extend the function to allow creating socket pairs of SOCK_STREAM,
SOCK_DGRAM and SOCK_SEQPACKET.

Adapt direct callers and leave further cleanups for the following patch.

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20240731-selftest-sockmap-fixes-v2-1-08a0c73abed2@rbox.co
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/sockmap_basic.c       |  19 +--
 .../selftests/bpf/prog_tests/sockmap_helpers.h     | 138 ++++++++++++++-------
 2 files changed, 96 insertions(+), 61 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 1337153eb0ad..5b17d69c9ee6 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -451,11 +451,11 @@ out:
 #define MAX_EVENTS 10
 static void test_sockmap_skb_verdict_shutdown(void)
 {
+	int n, err, map, verdict, c1 = -1, p1 = -1;
 	struct epoll_event ev, events[MAX_EVENTS];
-	int n, err, map, verdict, s, c1 = -1, p1 = -1;
 	struct test_sockmap_pass_prog *skel;
-	int epollfd;
 	int zero = 0;
+	int epollfd;
 	char b;
 
 	skel = test_sockmap_pass_prog__open_and_load();
@@ -469,10 +469,7 @@ static void test_sockmap_skb_verdict_shutdown(void)
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
 		goto out;
 
-	s = socket_loopback(AF_INET, SOCK_STREAM);
-	if (s < 0)
-		goto out;
-	err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1);
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
 	if (err < 0)
 		goto out;
 
@@ -570,16 +567,12 @@ out:
 
 static void test_sockmap_skb_verdict_peek_helper(int map)
 {
-	int err, s, c1, p1, zero = 0, sent, recvd, avail;
+	int err, c1, p1, zero = 0, sent, recvd, avail;
 	char snd[256] = "0123456789";
 	char rcv[256] = "0";
 
-	s = socket_loopback(AF_INET, SOCK_STREAM);
-	if (!ASSERT_GT(s, -1, "socket_loopback(s)"))
-		return;
-
-	err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1);
-	if (!ASSERT_OK(err, "create_pairs(s)"))
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+	if (!ASSERT_OK(err, "create_pair()"))
 		return;
 
 	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index e880f97bc44d..77b73333f091 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -3,6 +3,9 @@
 
 #include <linux/vm_sockets.h>
 
+/* include/linux/net.h */
+#define SOCK_TYPE_MASK 0xf
+
 #define IO_TIMEOUT_SEC 30
 #define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
@@ -312,54 +315,6 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
 	return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
 }
 
-static inline int create_pair(int s, int family, int sotype, int *c, int *p)
-{
-	struct sockaddr_storage addr;
-	socklen_t len;
-	int err = 0;
-
-	len = sizeof(addr);
-	err = xgetsockname(s, sockaddr(&addr), &len);
-	if (err)
-		return err;
-
-	*c = xsocket(family, sotype, 0);
-	if (*c < 0)
-		return errno;
-	err = xconnect(*c, sockaddr(&addr), len);
-	if (err) {
-		err = errno;
-		goto close_cli0;
-	}
-
-	*p = xaccept_nonblock(s, NULL, NULL);
-	if (*p < 0) {
-		err = errno;
-		goto close_cli0;
-	}
-	return err;
-close_cli0:
-	close(*c);
-	return err;
-}
-
-static inline int create_socket_pairs(int s, int family, int sotype,
-				      int *c0, int *c1, int *p0, int *p1)
-{
-	int err;
-
-	err = create_pair(s, family, sotype, c0, p0);
-	if (err)
-		return err;
-
-	err = create_pair(s, family, sotype, c1, p1);
-	if (err) {
-		close(*c0);
-		close(*p0);
-	}
-	return err;
-}
-
 static inline int enable_reuseport(int s, int progfd)
 {
 	int err, one = 1;
@@ -412,5 +367,92 @@ static inline int socket_loopback(int family, int sotype)
 	return socket_loopback_reuseport(family, sotype, -1);
 }
 
+static inline int create_pair(int family, int sotype, int *p0, int *p1)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int s, c, p, err;
+
+	s = socket_loopback(family, sotype);
+	if (s < 0)
+		return s;
+
+	err = xgetsockname(s, sockaddr(&addr), &len);
+	if (err)
+		goto close_s;
+
+	c = xsocket(family, sotype, 0);
+	if (c < 0) {
+		err = c;
+		goto close_s;
+	}
+
+	err = connect(c, sockaddr(&addr), len);
+	if (err) {
+		if (errno != EINPROGRESS) {
+			FAIL_ERRNO("connect");
+			goto close_c;
+		}
+
+		err = poll_connect(c, IO_TIMEOUT_SEC);
+		if (err) {
+			FAIL_ERRNO("poll_connect");
+			goto close_c;
+		}
+	}
+
+	switch (sotype & SOCK_TYPE_MASK) {
+	case SOCK_DGRAM:
+		err = xgetsockname(c, sockaddr(&addr), &len);
+		if (err)
+			goto close_c;
+
+		err = xconnect(s, sockaddr(&addr), len);
+		if (!err) {
+			*p0 = s;
+			*p1 = c;
+			return err;
+		}
+		break;
+	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
+		p = xaccept_nonblock(s, NULL, NULL);
+		if (p >= 0) {
+			*p0 = p;
+			*p1 = c;
+			goto close_s;
+		}
+
+		err = p;
+		break;
+	default:
+		FAIL("Unsupported socket type %#x", sotype);
+		err = -EOPNOTSUPP;
+	}
+
+close_c:
+	close(c);
+close_s:
+	close(s);
+	return err;
+}
+
+static inline int create_socket_pairs(int s, int family, int sotype,
+				      int *c0, int *c1, int *p0, int *p1)
+{
+	int err;
+
+	err = create_pair(family, sotype, c0, p0);
+	if (err)
+		return err;
+
+	err = create_pair(family, sotype, c1, p1);
+	if (err) {
+		close(*c0);
+		close(*p0);
+	}
+
+	return err;
+}
 
 #endif // __SOCKMAP_HELPERS__
-- 
cgit v1.3-3-g829e


From b08f205e5b9a074ae89ad7f71002ca417a4a2700 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 31 Jul 2024 12:01:27 +0200
Subject: selftests/bpf: Socket pair creation, cleanups

Following create_pair() changes, remove unused function argument in
create_socket_pairs() and adapt its callers, i.e. drop the open-coded
loopback socket creation.

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20240731-selftest-sockmap-fixes-v2-2-08a0c73abed2@rbox.co
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/sockmap_basic.c       |  9 +++-----
 .../selftests/bpf/prog_tests/sockmap_helpers.h     |  4 ++--
 .../selftests/bpf/prog_tests/sockmap_listen.c      | 26 +++++++---------------
 3 files changed, 13 insertions(+), 26 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 5b17d69c9ee6..82bfb266741c 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -503,8 +503,8 @@ out:
 
 static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 {
+	int err, map, verdict, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
 	int expected, zero = 0, sent, recvd, avail;
-	int err, map, verdict, s, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
 	struct test_sockmap_pass_prog *pass = NULL;
 	struct test_sockmap_drop_prog *drop = NULL;
 	char buf[256] = "0123456789";
@@ -531,11 +531,8 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog)
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
 		goto out;
 
-	s = socket_loopback(AF_INET, SOCK_STREAM);
-	if (!ASSERT_GT(s, -1, "socket_loopback(s)"))
-		goto out;
-	err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1);
-	if (!ASSERT_OK(err, "create_socket_pairs(s)"))
+	err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
 		goto out;
 
 	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index 77b73333f091..ead8ea4fd0da 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -437,8 +437,8 @@ close_s:
 	return err;
 }
 
-static inline int create_socket_pairs(int s, int family, int sotype,
-				      int *c0, int *c1, int *p0, int *p1)
+static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
+				      int *p0, int *p1)
 {
 	int err;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 9ce0e0e0b7da..bfbc217637d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -677,7 +677,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 			       int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
-	int s, c0, c1, p0, p1;
+	int c0, c1, p0, p1;
 	unsigned int pass;
 	int err, n;
 	u32 key;
@@ -685,13 +685,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 
 	zero_verdict_count(verd_mapfd);
 
-	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
-	if (s < 0)
-		return;
-
-	err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1);
+	err = create_socket_pairs(family, sotype | SOCK_NONBLOCK, &c0, &c1,
+				  &p0, &p1);
 	if (err)
-		goto close_srv;
+		return;
 
 	err = add_to_sockmap(sock_mapfd, p0, p1);
 	if (err)
@@ -722,8 +719,6 @@ close:
 	xclose(c1);
 	xclose(p0);
 	xclose(c0);
-close_srv:
-	xclose(s);
 }
 
 static void test_skb_redir_to_connected(struct test_sockmap_listen *skel,
@@ -909,7 +904,7 @@ static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *sk
 
 static void redir_partial(int family, int sotype, int sock_map, int parser_map)
 {
-	int s, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
+	int c0 = -1, c1 = -1, p0 = -1, p1 = -1;
 	int err, n, key, value;
 	char buf[] = "abc";
 
@@ -919,13 +914,10 @@ static void redir_partial(int family, int sotype, int sock_map, int parser_map)
 	if (err)
 		return;
 
-	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
-	if (s < 0)
-		goto clean_parser_map;
-
-	err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1);
+	err = create_socket_pairs(family, sotype | SOCK_NONBLOCK, &c0, &c1,
+				  &p0, &p1);
 	if (err)
-		goto close_srv;
+		goto clean_parser_map;
 
 	err = add_to_sockmap(sock_map, p0, p1);
 	if (err)
@@ -944,8 +936,6 @@ close:
 	xclose(p0);
 	xclose(c1);
 	xclose(p1);
-close_srv:
-	xclose(s);
 
 clean_parser_map:
 	key = 0;
-- 
cgit v1.3-3-g829e


From 4e3dec2295b1fdf5ea5c40a8195bc13de7cffdeb Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 31 Jul 2024 12:01:28 +0200
Subject: selftests/bpf: Simplify inet_socketpair() and
 vsock_socketpair_connectible()

Replace implementation with a call to a generic function.

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20240731-selftest-sockmap-fixes-v2-3-08a0c73abed2@rbox.co
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/sockmap_listen.c      | 83 +---------------------
 1 file changed, 2 insertions(+), 81 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index bfbc217637d1..ea2faacd146d 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1490,49 +1490,7 @@ static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *ma
 /* Returns two connected loopback vsock sockets */
 static int vsock_socketpair_connectible(int sotype, int *v0, int *v1)
 {
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
-	int s, p, c;
-
-	s = socket_loopback(AF_VSOCK, sotype);
-	if (s < 0)
-		return -1;
-
-	c = xsocket(AF_VSOCK, sotype | SOCK_NONBLOCK, 0);
-	if (c == -1)
-		goto close_srv;
-
-	if (getsockname(s, sockaddr(&addr), &len) < 0)
-		goto close_cli;
-
-	if (connect(c, sockaddr(&addr), len) < 0 && errno != EINPROGRESS) {
-		FAIL_ERRNO("connect");
-		goto close_cli;
-	}
-
-	len = sizeof(addr);
-	p = accept_timeout(s, sockaddr(&addr), &len, IO_TIMEOUT_SEC);
-	if (p < 0)
-		goto close_cli;
-
-	if (poll_connect(c, IO_TIMEOUT_SEC) < 0) {
-		FAIL_ERRNO("poll_connect");
-		goto close_acc;
-	}
-
-	*v0 = p;
-	*v1 = c;
-
-	return 0;
-
-close_acc:
-	close(p);
-close_cli:
-	close(c);
-close_srv:
-	close(s);
-
-	return -1;
+	return create_pair(AF_VSOCK, sotype | SOCK_NONBLOCK, v0, v1);
 }
 
 static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd,
@@ -1681,44 +1639,7 @@ static void test_reuseport(struct test_sockmap_listen *skel,
 
 static int inet_socketpair(int family, int type, int *s, int *c)
 {
-	struct sockaddr_storage addr;
-	socklen_t len;
-	int p0, c0;
-	int err;
-
-	p0 = socket_loopback(family, type | SOCK_NONBLOCK);
-	if (p0 < 0)
-		return p0;
-
-	len = sizeof(addr);
-	err = xgetsockname(p0, sockaddr(&addr), &len);
-	if (err)
-		goto close_peer0;
-
-	c0 = xsocket(family, type | SOCK_NONBLOCK, 0);
-	if (c0 < 0) {
-		err = c0;
-		goto close_peer0;
-	}
-	err = xconnect(c0, sockaddr(&addr), len);
-	if (err)
-		goto close_cli0;
-	err = xgetsockname(c0, sockaddr(&addr), &len);
-	if (err)
-		goto close_cli0;
-	err = xconnect(p0, sockaddr(&addr), len);
-	if (err)
-		goto close_cli0;
-
-	*s = p0;
-	*c = c0;
-	return 0;
-
-close_cli0:
-	xclose(c0);
-close_peer0:
-	xclose(p0);
-	return err;
+	return create_pair(family, type | SOCK_NONBLOCK, s, c);
 }
 
 static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
-- 
cgit v1.3-3-g829e


From b3b15b7a1e8de773c82f81c97904b51d4e919faa Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 31 Jul 2024 12:01:29 +0200
Subject: selftests/bpf: Honour the sotype of af_unix redir tests

Do actually test the sotype as specified by the caller.

This picks up after commit 75e0e27db6cf ("selftest/bpf: Change udp to inet
in some function names").

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20240731-selftest-sockmap-fixes-v2-4-08a0c73abed2@rbox.co
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/sockmap_listen.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index ea2faacd146d..7ed223df5f12 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1706,11 +1706,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
 	int sfd[2];
 	int err;
 
-	if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
+	if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd))
 		return;
 	c0 = sfd[0], p0 = sfd[1];
 
-	err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1);
+	err = inet_socketpair(family, type, &p1, &c1);
 	if (err)
 		goto close;
 
@@ -1758,7 +1758,7 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
 	int sfd[2];
 	int err;
 
-	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
+	err = inet_socketpair(family, type, &p0, &c0);
 	if (err)
 		return;
 
-- 
cgit v1.3-3-g829e


From c9c70b28face7b156960f53649bec9ace5601b85 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 31 Jul 2024 12:01:30 +0200
Subject: selftests/bpf: Exercise SOCK_STREAM unix_inet_redir_to_connected()

Constants got switched reducing the test's coverage. Replace SOCK_DGRAM
with SOCK_STREAM in one of unix_inet_skb_redir_to_connected() tests.

Fixes: 51354f700d40 ("bpf, sockmap: Add af_unix test with both sockets in map")
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20240731-selftest-sockmap-fixes-v2-5-08a0c73abed2@rbox.co
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/sockmap_listen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 7ed223df5f12..da5a6fb03b69 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1793,7 +1793,7 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
 	unix_inet_redir_to_connected(family, SOCK_DGRAM,
 				     sock_map, -1, verdict_map,
 				     REDIR_EGRESS, NO_FLAGS);
-	unix_inet_redir_to_connected(family, SOCK_DGRAM,
+	unix_inet_redir_to_connected(family, SOCK_STREAM,
 				     sock_map, -1, verdict_map,
 				     REDIR_EGRESS, NO_FLAGS);
 
-- 
cgit v1.3-3-g829e


From 86149b4f5a2d535279096946b6ef8d41911a9b5a Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 31 Jul 2024 12:01:31 +0200
Subject: selftests/bpf: Introduce __attribute__((cleanup)) in create_pair()

Rewrite function to have (unneeded) socket descriptors automatically
close()d when leaving the scope. Make sure the "ownership" of fds is
correctly passed via take_fd(); i.e. descriptor returned to caller will
remain valid.

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Tested-by: Jakub Sitnicki <jakub@cloudflare.com>
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://lore.kernel.org/r/20240731-selftest-sockmap-fixes-v2-6-08a0c73abed2@rbox.co
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/prog_tests/sockmap_helpers.h     | 61 +++++++++++++---------
 1 file changed, 36 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index ead8ea4fd0da..38e35c72bdaa 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -17,6 +17,17 @@
 
 #define __always_unused	__attribute__((__unused__))
 
+/* include/linux/cleanup.h */
+#define __get_and_null(p, nullvalue)                                           \
+	({                                                                     \
+		__auto_type __ptr = &(p);                                      \
+		__auto_type __val = *__ptr;                                    \
+		*__ptr = nullvalue;                                            \
+		__val;                                                         \
+	})
+
+#define take_fd(fd) __get_and_null(fd, -EBADF)
+
 #define _FAIL(errnum, fmt...)                                                  \
 	({                                                                     \
 		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
@@ -182,6 +193,14 @@
 		__ret;                                                         \
 	})
 
+static inline void close_fd(int *fd)
+{
+	if (*fd >= 0)
+		xclose(*fd);
+}
+
+#define __close_fd __attribute__((cleanup(close_fd)))
+
 static inline int poll_connect(int fd, unsigned int timeout_sec)
 {
 	struct timeval timeout = { .tv_sec = timeout_sec };
@@ -369,9 +388,10 @@ static inline int socket_loopback(int family, int sotype)
 
 static inline int create_pair(int family, int sotype, int *p0, int *p1)
 {
+	__close_fd int s, c = -1, p = -1;
 	struct sockaddr_storage addr;
 	socklen_t len = sizeof(addr);
-	int s, c, p, err;
+	int err;
 
 	s = socket_loopback(family, sotype);
 	if (s < 0)
@@ -379,25 +399,23 @@ static inline int create_pair(int family, int sotype, int *p0, int *p1)
 
 	err = xgetsockname(s, sockaddr(&addr), &len);
 	if (err)
-		goto close_s;
+		return err;
 
 	c = xsocket(family, sotype, 0);
-	if (c < 0) {
-		err = c;
-		goto close_s;
-	}
+	if (c < 0)
+		return c;
 
 	err = connect(c, sockaddr(&addr), len);
 	if (err) {
 		if (errno != EINPROGRESS) {
 			FAIL_ERRNO("connect");
-			goto close_c;
+			return err;
 		}
 
 		err = poll_connect(c, IO_TIMEOUT_SEC);
 		if (err) {
 			FAIL_ERRNO("poll_connect");
-			goto close_c;
+			return err;
 		}
 	}
 
@@ -405,36 +423,29 @@ static inline int create_pair(int family, int sotype, int *p0, int *p1)
 	case SOCK_DGRAM:
 		err = xgetsockname(c, sockaddr(&addr), &len);
 		if (err)
-			goto close_c;
+			return err;
 
 		err = xconnect(s, sockaddr(&addr), len);
-		if (!err) {
-			*p0 = s;
-			*p1 = c;
+		if (err)
 			return err;
-		}
+
+		*p0 = take_fd(s);
 		break;
 	case SOCK_STREAM:
 	case SOCK_SEQPACKET:
 		p = xaccept_nonblock(s, NULL, NULL);
-		if (p >= 0) {
-			*p0 = p;
-			*p1 = c;
-			goto close_s;
-		}
+		if (p < 0)
+			return p;
 
-		err = p;
+		*p0 = take_fd(p);
 		break;
 	default:
 		FAIL("Unsupported socket type %#x", sotype);
-		err = -EOPNOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
-close_c:
-	close(c);
-close_s:
-	close(s);
-	return err;
+	*p1 = take_fd(c);
+	return 0;
 }
 
 static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
-- 
cgit v1.3-3-g829e


From a2901083b1490a45df0700ac0aaa0730811cbf15 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 16 Aug 2024 14:22:44 -0700
Subject: tcp_metrics: use netlink policy for IPv6 addr len validation

Use the netlink policy to validate IPv6 address length.
Destination address currently has policy for max len set,
and source has no policy validation. In both cases
the code does the real check. With correct policy
check the code can be removed.

Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240816212245.467745-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_metrics.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index b01eb6d94413..95669935494e 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -617,9 +617,13 @@ static struct genl_family tcp_metrics_nl_family;
 
 static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = {
 	[TCP_METRICS_ATTR_ADDR_IPV4]	= { .type = NLA_U32, },
-	[TCP_METRICS_ATTR_ADDR_IPV6]	= { .type = NLA_BINARY,
-					    .len = sizeof(struct in6_addr), },
+	[TCP_METRICS_ATTR_ADDR_IPV6]	=
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+
 	[TCP_METRICS_ATTR_SADDR_IPV4]	= { .type = NLA_U32, },
+	[TCP_METRICS_ATTR_SADDR_IPV6]	=
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+
 	/* Following attributes are not received for GET/DEL,
 	 * we keep them for reference
 	 */
@@ -811,8 +815,6 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
 	if (a) {
 		struct in6_addr in6;
 
-		if (nla_len(a) != sizeof(struct in6_addr))
-			return -EINVAL;
 		in6 = nla_get_in6_addr(a);
 		inetpeer_set_addr_v6(addr, &in6);
 		if (hash)
-- 
cgit v1.3-3-g829e


From 359c5eb0f7364be9a26626402cc315e5e5f0d8c7 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 16 Aug 2024 18:19:06 +0800
Subject: gve: Remove unused declaration gve_rx_alloc_rings()

Commit f13697cc7a19 ("gve: Switch to config-aware queue allocation")
convert this function to gve_rx_alloc_rings_gqi().

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240816101906.882743-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 09a85ed59143..301fa1ea4f51 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -1153,7 +1153,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 			  int idx);
 void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
 			  struct gve_rx_alloc_rings_cfg *cfg);
-int gve_rx_alloc_rings(struct gve_priv *priv);
 int gve_rx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_rx_alloc_rings_cfg *cfg);
 void gve_rx_free_rings_gqi(struct gve_priv *priv,
-- 
cgit v1.3-3-g829e


From 12906bab4414d0e9034218a2ada82c53109ffff9 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 16 Aug 2024 18:16:38 +0800
Subject: igbvf: Remove two unused declarations

There is no caller and implementations in tree.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240816101638.882072-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/igbvf/igbvf.h | 1 -
 drivers/net/ethernet/intel/igbvf/mbx.h   | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h
index 7b83678ba83a..6ad35a00a287 100644
--- a/drivers/net/ethernet/intel/igbvf/igbvf.h
+++ b/drivers/net/ethernet/intel/igbvf/igbvf.h
@@ -282,7 +282,6 @@ enum igbvf_state_t {
 
 extern char igbvf_driver_name[];
 
-void igbvf_check_options(struct igbvf_adapter *);
 void igbvf_set_ethtool_ops(struct net_device *);
 
 int igbvf_up(struct igbvf_adapter *);
diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h
index e5b31818d565..7637d21445bf 100644
--- a/drivers/net/ethernet/intel/igbvf/mbx.h
+++ b/drivers/net/ethernet/intel/igbvf/mbx.h
@@ -49,7 +49,6 @@
 
 #define E1000_PF_CONTROL_MSG	0x0100 /* PF control message */
 
-void e1000_init_mbx_ops_generic(struct e1000_hw *hw);
 s32 e1000_init_mbx_params_vf(struct e1000_hw *);
 
 #endif /* _E1000_MBX_H_ */
-- 
cgit v1.3-3-g829e


From c5e2a1b06760a2253c5e8959b49b307e9986bfae Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 16 Aug 2024 18:15:50 +0800
Subject: net/mlx5: E-Switch, Remove unused declarations

These are never implenmented since commit b691b1116e82 ("net/mlx5: Implement
devlink port function cmds to control ipsec_packet").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240816101550.881844-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 578466d69f21..f44b4c7ebcfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -887,9 +887,6 @@ int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_v
 					 bool enable);
 int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev,
 					       u16 vport_num);
-void mlx5_esw_vport_ipsec_offload_enable(struct mlx5_eswitch *esw);
-void mlx5_esw_vport_ipsec_offload_disable(struct mlx5_eswitch *esw);
-
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
-- 
cgit v1.3-3-g829e


From af3dc0ad3167985894a292968c67502f42854e6d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 16 Aug 2024 18:04:04 +0800
Subject: mptcp: Remove unused declaration mptcp_sockopt_sync()

Commit a1ab24e5fc4a ("mptcp: consolidate sockopt synchronization")
removed the implementation but leave declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240816100404.879598-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 60c6b073d65f..08387140a646 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1154,7 +1154,6 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->pm.lock);
 }
 
-void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
 
 static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb)
-- 
cgit v1.3-3-g829e


From dca9d62a0d7684a5510645ba05960529c5066457 Mon Sep 17 00:00:00 2001
From: Zhang Changzhong <zhangchangzhong@huawei.com>
Date: Thu, 15 Aug 2024 22:09:42 +0800
Subject: net: remove redundant check in skb_shift()

The check for '!to' is redundant here, since skb_can_coalesce() already
contains this check.

Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/1723730983-22912-1-git-send-email-zhangchangzhong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index de2a044cc665..1748673e1fe0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4172,8 +4172,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen)
 	/* Actual merge is delayed until the point when we know we can
 	 * commit all, so that we don't have to undo partial changes
 	 */
-	if (!to ||
-	    !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom),
+	if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom),
 			      skb_frag_off(fragfrom))) {
 		merge = -1;
 	} else {
-- 
cgit v1.3-3-g829e


From 6ad8bc92a47702f0b5d0b96b680199910b89f688 Mon Sep 17 00:00:00 2001
From: Christian Hopps <chopps@labn.net>
Date: Thu, 15 Aug 2024 13:21:14 -0400
Subject: net: add copy from skb_seq_state to buffer function

Add an skb helper function to copy a range of bytes from within
an existing skb_seq_state.

Signed-off-by: Christian Hopps <chopps@labn.net>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/linux/skbuff.h |  1 +
 net/core/skbuff.c      | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 29c3ea5b6e93..a871533b8568 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1433,6 +1433,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
 unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
 			  struct skb_seq_state *st);
 void skb_abort_seq_read(struct skb_seq_state *st);
+int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len);
 
 unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 			   unsigned int to, struct ts_config *config);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 83f8cd8aa2d1..fe4b2dc5c19b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4409,6 +4409,41 @@ void skb_abort_seq_read(struct skb_seq_state *st)
 }
 EXPORT_SYMBOL(skb_abort_seq_read);
 
+/**
+ * skb_copy_seq_read() - copy from a skb_seq_state to a buffer
+ * @st: source skb_seq_state
+ * @offset: offset in source
+ * @to: destination buffer
+ * @len: number of bytes to copy
+ *
+ * Copy @len bytes from @offset bytes into the source @st to the destination
+ * buffer @to. `offset` should increase (or be unchanged) with each subsequent
+ * call to this function. If offset needs to decrease from the previous use `st`
+ * should be reset first.
+ *
+ * Return: 0 on success or -EINVAL if the copy ended early
+ */
+int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len)
+{
+	const u8 *data;
+	u32 sqlen;
+
+	for (;;) {
+		sqlen = skb_seq_read(offset, &data, st);
+		if (sqlen == 0)
+			return -EINVAL;
+		if (sqlen >= len) {
+			memcpy(to, data, len);
+			return 0;
+		}
+		memcpy(to, data, sqlen);
+		to += sqlen;
+		offset += sqlen;
+		len -= sqlen;
+	}
+}
+EXPORT_SYMBOL(skb_copy_seq_read);
+
 #define TS_SKB_CB(state)	((struct skb_seq_state *) &((state)->cb))
 
 static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text,
-- 
cgit v1.3-3-g829e


From d386d59b7c1a39112ca875327339ed519df2b96c Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Wed, 14 Aug 2024 21:08:26 +0800
Subject: net/smc: introduce statistics for allocated ringbufs of link group

Currently we have the statistics on sndbuf/RMB sizes of all connections
that have ever been on the link group, namely smc_stats_memsize. However
these statistics are incremental and since the ringbufs of link group
are allowed to be reused, we cannot know the actual allocated buffers
through these. So here introduces the statistic on actual allocated
ringbufs of the link group, it will be incremented when a new ringbuf is
added into buf_list and decremented when it is deleted from buf_list.

Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/smc.h |  4 ++++
 net/smc/smc_core.c       | 46 ++++++++++++++++++++++++++++++++++++++++++----
 net/smc/smc_core.h       |  2 ++
 3 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h
index b531e3ef011a..9b74ef79070a 100644
--- a/include/uapi/linux/smc.h
+++ b/include/uapi/linux/smc.h
@@ -127,6 +127,8 @@ enum {
 	SMC_NLA_LGR_R_NET_COOKIE,	/* u64 */
 	SMC_NLA_LGR_R_PAD,		/* flag */
 	SMC_NLA_LGR_R_BUF_TYPE,		/* u8 */
+	SMC_NLA_LGR_R_SNDBUF_ALLOC,	/* uint */
+	SMC_NLA_LGR_R_RMB_ALLOC,	/* uint */
 	__SMC_NLA_LGR_R_MAX,
 	SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1
 };
@@ -162,6 +164,8 @@ enum {
 	SMC_NLA_LGR_D_V2_COMMON,	/* nest */
 	SMC_NLA_LGR_D_EXT_GID,		/* u64 */
 	SMC_NLA_LGR_D_PEER_EXT_GID,	/* u64 */
+	SMC_NLA_LGR_D_SNDBUF_ALLOC,	/* uint */
+	SMC_NLA_LGR_D_DMB_ALLOC,	/* uint */
 	__SMC_NLA_LGR_D_MAX,
 	SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1
 };
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 71fb334d8234..8dcf1c7f1526 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -221,6 +221,35 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
 	write_unlock_bh(&lgr->conns_lock);
 }
 
+static void smc_lgr_buf_list_add(struct smc_link_group *lgr,
+				 bool is_rmb,
+				 struct list_head *buf_list,
+				 struct smc_buf_desc *buf_desc)
+{
+	list_add(&buf_desc->list, buf_list);
+	if (is_rmb) {
+		lgr->alloc_rmbs += buf_desc->len;
+		lgr->alloc_rmbs +=
+			lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0;
+	} else {
+		lgr->alloc_sndbufs += buf_desc->len;
+	}
+}
+
+static void smc_lgr_buf_list_del(struct smc_link_group *lgr,
+				 bool is_rmb,
+				 struct smc_buf_desc *buf_desc)
+{
+	list_del(&buf_desc->list);
+	if (is_rmb) {
+		lgr->alloc_rmbs -= buf_desc->len;
+		lgr->alloc_rmbs -=
+			lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0;
+	} else {
+		lgr->alloc_sndbufs -= buf_desc->len;
+	}
+}
+
 int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
@@ -363,6 +392,10 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr,
 	smc_target[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
 		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs))
+		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs))
+		goto errattr;
 	if (lgr->smc_version > SMC_V1) {
 		v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON);
 		if (!v2_attrs)
@@ -541,6 +574,10 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
 		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs))
+		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs))
+		goto errattr;
 	memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN);
 	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
@@ -1138,7 +1175,7 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
 		lock = is_rmb ? &lgr->rmbs_lock :
 				&lgr->sndbufs_lock;
 		down_write(lock);
-		list_del(&buf_desc->list);
+		smc_lgr_buf_list_del(lgr, is_rmb, buf_desc);
 		up_write(lock);
 
 		smc_buf_free(lgr, is_rmb, buf_desc);
@@ -1377,7 +1414,7 @@ static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
 			buf_list = &lgr->sndbufs[i];
 		list_for_each_entry_safe(buf_desc, bf_desc, buf_list,
 					 list) {
-			list_del(&buf_desc->list);
+			smc_lgr_buf_list_del(lgr, is_rmb, buf_desc);
 			smc_buf_free(lgr, is_rmb, buf_desc);
 		}
 	}
@@ -2414,7 +2451,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
 		buf_desc->used = 1;
 		down_write(lock);
-		list_add(&buf_desc->list, buf_list);
+		smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc);
 		up_write(lock);
 		break; /* found */
 	}
@@ -2496,7 +2533,8 @@ create_rmb:
 	rc = __smc_buf_create(smc, is_smcd, true);
 	if (rc && smc->conn.sndbuf_desc) {
 		down_write(&smc->conn.lgr->sndbufs_lock);
-		list_del(&smc->conn.sndbuf_desc->list);
+		smc_lgr_buf_list_del(smc->conn.lgr, false,
+				     smc->conn.sndbuf_desc);
 		up_write(&smc->conn.lgr->sndbufs_lock);
 		smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
 		smc->conn.sndbuf_desc = NULL;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index d93cf51dbd7c..0db4e5f79ac4 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -281,6 +281,8 @@ struct smc_link_group {
 	struct rw_semaphore	sndbufs_lock;	/* protects tx buffers */
 	struct list_head	rmbs[SMC_RMBE_SIZES];	/* rx buffers */
 	struct rw_semaphore	rmbs_lock;	/* protects rx buffers */
+	u64			alloc_sndbufs;	/* stats of tx buffers */
+	u64			alloc_rmbs;	/* stats of rx buffers */
 
 	u8			id[SMC_LGR_ID_SIZE];	/* unique lgr id */
 	struct delayed_work	free_work;	/* delayed freeing of an lgr */
-- 
cgit v1.3-3-g829e


From e0d103542b06c36240e3887edfe49578464866eb Mon Sep 17 00:00:00 2001
From: Wen Gu <guwen@linux.alibaba.com>
Date: Wed, 14 Aug 2024 21:08:27 +0800
Subject: net/smc: introduce statistics for ringbufs usage of net namespace

The buffer size histograms in smc_stats, namely rx/tx_rmbsize, record
the sizes of ringbufs for all connections that have ever appeared in
the net namespace. They are incremental and we cannot know the actual
ringbufs usage from these. So here introduces statistics for current
ringbufs usage of existing smc connections in the net namespace into
smc_stats, it will be incremented when new connection uses a ringbuf
and decremented when the ringbuf is unused.

Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/smc.h |  2 ++
 net/smc/smc_core.c       | 22 +++++++++++++++-------
 net/smc/smc_stats.c      |  6 ++++++
 net/smc/smc_stats.h      | 28 +++++++++++++++++++---------
 4 files changed, 42 insertions(+), 16 deletions(-)

diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h
index 9b74ef79070a..1f58cb0c266b 100644
--- a/include/uapi/linux/smc.h
+++ b/include/uapi/linux/smc.h
@@ -253,6 +253,8 @@ enum {
 	SMC_NLA_STATS_T_TX_BYTES,	/* u64 */
 	SMC_NLA_STATS_T_RX_CNT,		/* u64 */
 	SMC_NLA_STATS_T_TX_CNT,		/* u64 */
+	SMC_NLA_STATS_T_RX_RMB_USAGE,	/* uint */
+	SMC_NLA_STATS_T_TX_RMB_USAGE,	/* uint */
 	__SMC_NLA_STATS_T_MAX,
 	SMC_NLA_STATS_T_MAX = __SMC_NLA_STATS_T_MAX - 1
 };
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 8dcf1c7f1526..4e694860ece4 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1203,22 +1203,30 @@ static void smcd_buf_detach(struct smc_connection *conn)
 static void smc_buf_unuse(struct smc_connection *conn,
 			  struct smc_link_group *lgr)
 {
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	bool is_smcd = lgr->is_smcd;
+	int bufsize;
+
 	if (conn->sndbuf_desc) {
-		if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) {
+		bufsize = conn->sndbuf_desc->len;
+		if (!is_smcd && conn->sndbuf_desc->is_vm) {
 			smcr_buf_unuse(conn->sndbuf_desc, false, lgr);
 		} else {
-			memzero_explicit(conn->sndbuf_desc->cpu_addr, conn->sndbuf_desc->len);
+			memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize);
 			WRITE_ONCE(conn->sndbuf_desc->used, 0);
 		}
+		SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize);
 	}
 	if (conn->rmb_desc) {
-		if (!lgr->is_smcd) {
+		bufsize = conn->rmb_desc->len;
+		if (!is_smcd) {
 			smcr_buf_unuse(conn->rmb_desc, true, lgr);
 		} else {
-			memzero_explicit(conn->rmb_desc->cpu_addr,
-					 conn->rmb_desc->len + sizeof(struct smcd_cdc_msg));
+			bufsize += sizeof(struct smcd_cdc_msg);
+			memzero_explicit(conn->rmb_desc->cpu_addr, bufsize);
 			WRITE_ONCE(conn->rmb_desc->used, 0);
 		}
+		SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize);
 	}
 }
 
@@ -2427,7 +2435,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list);
 		if (buf_desc) {
 			buf_desc->is_dma_need_sync = 0;
-			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
+			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize);
 			SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb);
 			break; /* found reusable slot */
 		}
@@ -2448,7 +2456,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		}
 
 		SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb);
-		SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
+		SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize);
 		buf_desc->used = 1;
 		down_write(lock);
 		smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc);
diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c
index ca14c0f3a07d..e71b17d1e21c 100644
--- a/net/smc/smc_stats.c
+++ b/net/smc/smc_stats.c
@@ -218,6 +218,12 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb,
 			      smc_tech->tx_bytes,
 			      SMC_NLA_STATS_PAD))
 		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_STATS_T_RX_RMB_USAGE,
+			 smc_tech->rx_rmbuse))
+		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_STATS_T_TX_RMB_USAGE,
+			 smc_tech->tx_rmbuse))
+		goto errattr;
 	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT,
 			      smc_tech->rx_cnt,
 			      SMC_NLA_STATS_PAD))
diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
index e19177ce4092..571f9d9e7814 100644
--- a/net/smc/smc_stats.h
+++ b/net/smc/smc_stats.h
@@ -79,6 +79,8 @@ struct smc_stats_tech {
 	u64			tx_bytes;
 	u64			rx_cnt;
 	u64			tx_cnt;
+	u64			rx_rmbuse;
+	u64			tx_rmbuse;
 };
 
 struct smc_stats {
@@ -135,38 +137,46 @@ do { \
 } \
 while (0)
 
-#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \
+#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _is_add, _len) \
 do { \
+	typeof(_smc_stats) stats = (_smc_stats); \
+	typeof(_is_add) is_a = (_is_add); \
 	typeof(_len) _l = (_len); \
 	typeof(_tech) t = (_tech); \
 	int _pos; \
 	int m = SMC_BUF_MAX - 1; \
 	if (_l <= 0) \
 		break; \
-	_pos = fls((_l - 1) >> 13); \
-	_pos = (_pos <= m) ? _pos : m; \
-	this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \
+	if (is_a) { \
+		_pos = fls((_l - 1) >> 13); \
+		_pos = (_pos <= m) ? _pos : m; \
+		this_cpu_inc((*stats).smc[t].k ## _rmbsize.buf[_pos]); \
+		this_cpu_add((*stats).smc[t].k ## _rmbuse, _l); \
+	} else { \
+		this_cpu_sub((*stats).smc[t].k ## _rmbuse, _l); \
+	} \
 } \
 while (0)
 
 #define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \
 	this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt)
 
-#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \
+#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _is_add, _len) \
 do { \
 	struct net *_net = sock_net(&(_smc)->sk); \
 	struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \
+	typeof(_is_add) is_add = (_is_add); \
 	typeof(_is_smcd) is_d = (_is_smcd); \
 	typeof(_is_rx) is_r = (_is_rx); \
 	typeof(_len) l = (_len); \
 	if ((is_d) && (is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, is_add, l); \
 	if ((is_d) && !(is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, is_add, l); \
 	if (!(is_d) && (is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, is_add, l); \
 	if (!(is_d) && !(is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, is_add, l); \
 } \
 while (0)
 
-- 
cgit v1.3-3-g829e


From 7ea0522ef81a335c2d3a0ab1c8a4fab9a23c4a03 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 20 Aug 2024 11:56:12 +0200
Subject: netfilter: nf_tables: pass context structure to
 nft_parse_register_load

Mechanical transformation, no logical changes intended.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h      | 3 ++-
 net/bridge/netfilter/nft_meta_bridge.c | 2 +-
 net/ipv4/netfilter/nft_dup_ipv4.c      | 4 ++--
 net/ipv6/netfilter/nft_dup_ipv6.c      | 4 ++--
 net/netfilter/nf_tables_api.c          | 3 ++-
 net/netfilter/nft_bitwise.c            | 4 ++--
 net/netfilter/nft_byteorder.c          | 2 +-
 net/netfilter/nft_cmp.c                | 6 +++---
 net/netfilter/nft_ct.c                 | 2 +-
 net/netfilter/nft_dup_netdev.c         | 2 +-
 net/netfilter/nft_dynset.c             | 4 ++--
 net/netfilter/nft_exthdr.c             | 2 +-
 net/netfilter/nft_fwd_netdev.c         | 6 +++---
 net/netfilter/nft_hash.c               | 2 +-
 net/netfilter/nft_lookup.c             | 2 +-
 net/netfilter/nft_masq.c               | 4 ++--
 net/netfilter/nft_meta.c               | 2 +-
 net/netfilter/nft_nat.c                | 8 ++++----
 net/netfilter/nft_objref.c             | 2 +-
 net/netfilter/nft_payload.c            | 2 +-
 net/netfilter/nft_queue.c              | 2 +-
 net/netfilter/nft_range.c              | 2 +-
 net/netfilter/nft_redir.c              | 4 ++--
 net/netfilter/nft_tproxy.c             | 4 ++--
 24 files changed, 40 insertions(+), 38 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2be4738eae1c..573995e7a27e 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -254,7 +254,8 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
 int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest);
 int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg);
 
-int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len);
+int nft_parse_register_load(const struct nft_ctx *ctx,
+			    const struct nlattr *attr, u8 *sreg, u32 len);
 int nft_parse_register_store(const struct nft_ctx *ctx,
 			     const struct nlattr *attr, u8 *dreg,
 			     const struct nft_data *data,
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index bd4d1b4d745f..4d8e15927217 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -142,7 +142,7 @@ static int nft_meta_bridge_set_init(const struct nft_ctx *ctx,
 	}
 
 	priv->len = len;
-	err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len);
+	err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len);
 	if (err < 0)
 		return err;
 
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index a522c3a3be52..ef5dd88107dd 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -40,13 +40,13 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_DUP_SREG_ADDR] == NULL)
 		return -EINVAL;
 
-	err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr,
+	err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr,
 				      sizeof(struct in_addr));
 	if (err < 0)
 		return err;
 
 	if (tb[NFTA_DUP_SREG_DEV])
-		err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV],
+		err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV],
 					      &priv->sreg_dev, sizeof(int));
 
 	return err;
diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c
index c82f3fdd4a65..492a811828a7 100644
--- a/net/ipv6/netfilter/nft_dup_ipv6.c
+++ b/net/ipv6/netfilter/nft_dup_ipv6.c
@@ -38,13 +38,13 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_DUP_SREG_ADDR] == NULL)
 		return -EINVAL;
 
-	err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr,
+	err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr,
 				      sizeof(struct in6_addr));
 	if (err < 0)
 		return err;
 
 	if (tb[NFTA_DUP_SREG_DEV])
-		err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV],
+		err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV],
 					      &priv->sreg_dev, sizeof(int));
 
 	return err;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c85d037a363b..d05fc17bb9b7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -11038,7 +11038,8 @@ static int nft_validate_register_load(enum nft_registers reg, unsigned int len)
 	return 0;
 }
 
-int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len)
+int nft_parse_register_load(const struct nft_ctx *ctx,
+			    const struct nlattr *attr, u8 *sreg, u32 len)
 {
 	u32 reg;
 	int err;
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index ca857afbf061..7de95674fd8c 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -171,7 +171,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
 
 	priv->len = len;
 
-	err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg,
+	err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg,
 				      priv->len);
 	if (err < 0)
 		return err;
@@ -365,7 +365,7 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx,
 	struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg,
+	err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg,
 				      sizeof(u32));
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c
index f6e791a68101..2f82a444d21b 100644
--- a/net/netfilter/nft_byteorder.c
+++ b/net/netfilter/nft_byteorder.c
@@ -139,7 +139,7 @@ static int nft_byteorder_init(const struct nft_ctx *ctx,
 
 	priv->len = len;
 
-	err = nft_parse_register_load(tb[NFTA_BYTEORDER_SREG], &priv->sreg,
+	err = nft_parse_register_load(ctx, tb[NFTA_BYTEORDER_SREG], &priv->sreg,
 				      priv->len);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index cd4652259095..2605f43737bc 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -83,7 +83,7 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	if (err < 0)
 		return err;
 
-	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
 	if (err < 0)
 		return err;
 
@@ -222,7 +222,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
-	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
 	if (err < 0)
 		return err;
 
@@ -323,7 +323,7 @@ static int nft_cmp16_fast_init(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
-	err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
+	err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 452ed94c3a4d..67a41cd2baaf 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -606,7 +606,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx,
 	}
 
 	priv->len = len;
-	err = nft_parse_register_load(tb[NFTA_CT_SREG], &priv->sreg, len);
+	err = nft_parse_register_load(ctx, tb[NFTA_CT_SREG], &priv->sreg, len);
 	if (err < 0)
 		goto err1;
 
diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c
index e5739a59ebf1..0573f96ce079 100644
--- a/net/netfilter/nft_dup_netdev.c
+++ b/net/netfilter/nft_dup_netdev.c
@@ -40,7 +40,7 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_DUP_SREG_DEV] == NULL)
 		return -EINVAL;
 
-	return nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev,
+	return nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev,
 				       sizeof(int));
 }
 
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index b4ada3ab2167..6920df754265 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -215,7 +215,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 			return err;
 	}
 
-	err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key,
+	err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key,
 				      set->klen);
 	if (err < 0)
 		return err;
@@ -226,7 +226,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 		if (set->dtype == NFT_DATA_VERDICT)
 			return -EOPNOTSUPP;
 
-		err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_DATA],
+		err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_DATA],
 					      &priv->sreg_data, set->dlen);
 		if (err < 0)
 			return err;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index 6eb571d0c3fd..6bfd33516241 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -588,7 +588,7 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx,
 	priv->flags  = flags;
 	priv->op     = op;
 
-	return nft_parse_register_load(tb[NFTA_EXTHDR_SREG], &priv->sreg,
+	return nft_parse_register_load(ctx, tb[NFTA_EXTHDR_SREG], &priv->sreg,
 				       priv->len);
 }
 
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index 358e742afad7..c83a794025f9 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -52,7 +52,7 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_FWD_SREG_DEV] == NULL)
 		return -EINVAL;
 
-	return nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev,
+	return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev,
 				       sizeof(int));
 }
 
@@ -178,12 +178,12 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx,
 		return -EOPNOTSUPP;
 	}
 
-	err = nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev,
+	err = nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev,
 				      sizeof(int));
 	if (err < 0)
 		return err;
 
-	return nft_parse_register_load(tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr,
+	return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr,
 				       addr_len);
 }
 
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 868d68302d22..5d034bbb6913 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -92,7 +92,7 @@ static int nft_jhash_init(const struct nft_ctx *ctx,
 
 	priv->len = len;
 
-	err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len);
+	err = nft_parse_register_load(ctx, tb[NFTA_HASH_SREG], &priv->sreg, len);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index f3080fa1b226..580e4b1deb9b 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -113,7 +113,7 @@ static int nft_lookup_init(const struct nft_ctx *ctx,
 	if (IS_ERR(set))
 		return PTR_ERR(set);
 
-	err = nft_parse_register_load(tb[NFTA_LOOKUP_SREG], &priv->sreg,
+	err = nft_parse_register_load(ctx, tb[NFTA_LOOKUP_SREG], &priv->sreg,
 				      set->klen);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 8a14aaca93bb..cb43c72a8c2a 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -52,13 +52,13 @@ static int nft_masq_init(const struct nft_ctx *ctx,
 		priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS]));
 
 	if (tb[NFTA_MASQ_REG_PROTO_MIN]) {
-		err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN],
+		err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MIN],
 					      &priv->sreg_proto_min, plen);
 		if (err < 0)
 			return err;
 
 		if (tb[NFTA_MASQ_REG_PROTO_MAX]) {
-			err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MAX],
+			err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MAX],
 						      &priv->sreg_proto_max,
 						      plen);
 			if (err < 0)
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 9139ce38ea7b..0214ad1ced2f 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -657,7 +657,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx,
 	}
 
 	priv->len = len;
-	err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len);
+	err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len);
 	if (err < 0)
 		return err;
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 808f5802c270..983dd937fe02 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -214,13 +214,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	priv->family = family;
 
 	if (tb[NFTA_NAT_REG_ADDR_MIN]) {
-		err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MIN],
+		err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MIN],
 					      &priv->sreg_addr_min, alen);
 		if (err < 0)
 			return err;
 
 		if (tb[NFTA_NAT_REG_ADDR_MAX]) {
-			err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MAX],
+			err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MAX],
 						      &priv->sreg_addr_max,
 						      alen);
 			if (err < 0)
@@ -234,13 +234,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	plen = sizeof_field(struct nf_nat_range, min_proto.all);
 	if (tb[NFTA_NAT_REG_PROTO_MIN]) {
-		err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN],
+		err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MIN],
 					      &priv->sreg_proto_min, plen);
 		if (err < 0)
 			return err;
 
 		if (tb[NFTA_NAT_REG_PROTO_MAX]) {
-			err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MAX],
+			err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MAX],
 						      &priv->sreg_proto_max,
 						      plen);
 			if (err < 0)
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 509011b1ef59..09da7a3f9f96 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -143,7 +143,7 @@ static int nft_objref_map_init(const struct nft_ctx *ctx,
 	if (!(set->flags & NFT_SET_OBJECT))
 		return -EINVAL;
 
-	err = nft_parse_register_load(tb[NFTA_OBJREF_SET_SREG], &priv->sreg,
+	err = nft_parse_register_load(ctx, tb[NFTA_OBJREF_SET_SREG], &priv->sreg,
 				      set->klen);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 50429cbd42da..330609a76fb2 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -981,7 +981,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 	}
 	priv->csum_type = csum_type;
 
-	return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg,
+	return nft_parse_register_load(ctx, tb[NFTA_PAYLOAD_SREG], &priv->sreg,
 				       priv->len);
 }
 
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index b2b8127c8d43..44e6817e6e29 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -136,7 +136,7 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx,
 	struct nft_queue *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_parse_register_load(tb[NFTA_QUEUE_SREG_QNUM],
+	err = nft_parse_register_load(ctx, tb[NFTA_QUEUE_SREG_QNUM],
 				      &priv->sreg_qnum, sizeof(u32));
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index 51ae64cd268f..ea382f7bbd78 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -83,7 +83,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
 		goto err2;
 	}
 
-	err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg,
+	err = nft_parse_register_load(ctx, tb[NFTA_RANGE_SREG], &priv->sreg,
 				      desc_from.len);
 	if (err < 0)
 		goto err2;
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index a58bd8d291ff..6568cc264078 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -51,13 +51,13 @@ static int nft_redir_init(const struct nft_ctx *ctx,
 
 	plen = sizeof_field(struct nf_nat_range, min_proto.all);
 	if (tb[NFTA_REDIR_REG_PROTO_MIN]) {
-		err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN],
+		err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MIN],
 					      &priv->sreg_proto_min, plen);
 		if (err < 0)
 			return err;
 
 		if (tb[NFTA_REDIR_REG_PROTO_MAX]) {
-			err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MAX],
+			err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MAX],
 						      &priv->sreg_proto_max,
 						      plen);
 			if (err < 0)
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index 71412adb73d4..1b691393d8b1 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -254,14 +254,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx,
 	}
 
 	if (tb[NFTA_TPROXY_REG_ADDR]) {
-		err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR],
+		err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_ADDR],
 					      &priv->sreg_addr, alen);
 		if (err < 0)
 			return err;
 	}
 
 	if (tb[NFTA_TPROXY_REG_PORT]) {
-		err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT],
+		err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_PORT],
 					      &priv->sreg_port, sizeof(u16));
 		if (err < 0)
 			return err;
-- 
cgit v1.3-3-g829e


From 14fb07130c7ddd257e30079b87499b3f89097b09 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 20 Aug 2024 11:56:13 +0200
Subject: netfilter: nf_tables: allow loads only when register is initialized

Reject rules where a load occurs from a register that has not seen a store
early in the same rule.

commit 4c905f6740a3 ("netfilter: nf_tables: initialize registers in
nft_do_chain()")
had to add a unconditional memset to the nftables register space to avoid
leaking stack information to userspace.

This memset shows up in benchmarks.  After this change, this commit can
be reverted again.

Note that this breaks userspace compatibility, because theoretically
you can do

  rule 1: reg2 := meta load iif, reg2  == 1 jump ...
  rule 2: reg2 == 2 jump ...   // read access with no store in this rule

... after this change this is rejected.

Neither nftables nor iptables-nft generate such rules, each rule is
always standalone.

This resuts in a small increase of nft_ctx structure by sizeof(long).

To cope with hypothetical rulesets like the example above one could emit
on-demand "reg[x] = 0" store when generating the datapath blob in
nf_tables_commit_chain_prepare().

A patch that does this is linked to below.

For now, lets disable this.  In nf_tables, a rule is the smallest
unit that can be replaced from userspace, i.e. a hypothetical ruleset
that relies on earlier initialisations of registers can't be changed
at will as register usage would need to be coordinated.

Link: https://lore.kernel.org/netfilter-devel/20240627135330.17039-4-fw@strlen.de/
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  1 +
 net/netfilter/nf_tables_api.c     | 38 ++++++++++++++++++++++++++++++++++----
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 573995e7a27e..1cc33d946d41 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -221,6 +221,7 @@ struct nft_ctx {
 	u8				family;
 	u8				level;
 	bool				report;
+	DECLARE_BITMAP(reg_inited, NFT_REG32_NUM);
 };
 
 enum nft_data_desc_flags {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d05fc17bb9b7..904f2e25b4a4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -146,6 +146,8 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 	ctx->report	= nlmsg_report(nlh);
 	ctx->flags	= nlh->nlmsg_flags;
 	ctx->seq	= nlh->nlmsg_seq;
+
+	bitmap_zero(ctx->reg_inited, NFT_REG32_NUM);
 }
 
 static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx,
@@ -11041,8 +11043,8 @@ static int nft_validate_register_load(enum nft_registers reg, unsigned int len)
 int nft_parse_register_load(const struct nft_ctx *ctx,
 			    const struct nlattr *attr, u8 *sreg, u32 len)
 {
-	u32 reg;
-	int err;
+	int err, invalid_reg;
+	u32 reg, next_register;
 
 	err = nft_parse_register(attr, &reg);
 	if (err < 0)
@@ -11052,11 +11054,36 @@ int nft_parse_register_load(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
+	next_register = DIV_ROUND_UP(len, NFT_REG32_SIZE) + reg;
+
+	/* Can't happen: nft_validate_register_load() should have failed */
+	if (WARN_ON_ONCE(next_register > NFT_REG32_NUM))
+		return -EINVAL;
+
+	/* find first register that did not see an earlier store. */
+	invalid_reg = find_next_zero_bit(ctx->reg_inited, NFT_REG32_NUM, reg);
+
+	/* invalid register within the range that we're loading from? */
+	if (invalid_reg < next_register)
+		return -ENODATA;
+
 	*sreg = reg;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nft_parse_register_load);
 
+static void nft_saw_register_store(const struct nft_ctx *__ctx,
+				   int reg, unsigned int len)
+{
+	unsigned int registers = DIV_ROUND_UP(len, NFT_REG32_SIZE);
+	struct nft_ctx *ctx = (struct nft_ctx *)__ctx;
+
+	if (WARN_ON_ONCE(len == 0 || reg < 0))
+		return;
+
+	bitmap_set(ctx->reg_inited, reg, registers);
+}
+
 static int nft_validate_register_store(const struct nft_ctx *ctx,
 				       enum nft_registers reg,
 				       const struct nft_data *data,
@@ -11078,7 +11105,7 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
 				return err;
 		}
 
-		return 0;
+		break;
 	default:
 		if (type != NFT_DATA_VALUE)
 			return -EINVAL;
@@ -11091,8 +11118,11 @@ static int nft_validate_register_store(const struct nft_ctx *ctx,
 		    sizeof_field(struct nft_regs, data))
 			return -ERANGE;
 
-		return 0;
+		break;
 	}
+
+	nft_saw_register_store(ctx, reg, len);
+	return 0;
 }
 
 int nft_parse_register_store(const struct nft_ctx *ctx,
-- 
cgit v1.3-3-g829e


From c88baabf16d1ef74ab8832de9761226406af5507 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 20 Aug 2024 11:56:14 +0200
Subject: netfilter: nf_tables: don't initialize registers in nft_do_chain()

revert commit 4c905f6740a3 ("netfilter: nf_tables: initialize registers in
nft_do_chain()").

Previous patch makes sure that loads from uninitialized registers are
detected from the control plane. in this case rule blob auto-zeroes
registers.  Thus the explicit zeroing is not needed anymore.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index a48d5f0e2f3e..75598520b0fa 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -256,7 +256,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 	const struct net *net = nft_net(pkt);
 	const struct nft_expr *expr, *last;
 	const struct nft_rule_dp *rule;
-	struct nft_regs regs = {};
+	struct nft_regs regs;
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
 	bool genbit = READ_ONCE(net->nft.gencursor);
-- 
cgit v1.3-3-g829e


From 8fed54758cd248cd311a2b5c1e180abef1866237 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 15:52:22 +0300
Subject: ipv4: Mask upper DSCP bits and ECN bits in NETLINK_FIB_LOOKUP family

The NETLINK_FIB_LOOKUP netlink family can be used to perform a FIB
lookup according to user provided parameters and communicate the result
back to user space.

However, unlike other users of the FIB lookup API, the upper DSCP bits
and the ECN bits of the DS field are not masked, which can result in the
wrong result being returned.

Solve this by masking the upper DSCP bits and the ECN bits using
IPTOS_RT_MASK.

The structure that communicates the request and the response is not
exported to user space, so it is unlikely that this netlink family is
actually in use [1].

[1] https://lore.kernel.org/netdev/ZpqpB8vJU%2FQ6LSqa@debian/

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/fib_frontend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 7ad2cafb9276..da540ddb7af6 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
 	struct flowi4           fl4 = {
 		.flowi4_mark = frn->fl_mark,
 		.daddr = frn->fl_addr,
-		.flowi4_tos = frn->fl_tos,
+		.flowi4_tos = frn->fl_tos & IPTOS_RT_MASK,
 		.flowi4_scope = frn->fl_scope,
 	};
 	struct fib_table *tb;
-- 
cgit v1.3-3-g829e


From 548a2029eb6668a47e9bc86a7ded3d33a738aa0c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 15:52:23 +0300
Subject: netfilter: nft_fib: Mask upper DSCP bits before FIB lookup

As part of its functionality, the nftables FIB expression module
performs a FIB lookup, but unlike other users of the FIB lookup API, it
does so without masking the upper DSCP bits. In particular, this differs
from the equivalent iptables match ("rpfilter") that does mask the upper
DSCP bits before the FIB lookup.

Align the module to other users of the FIB lookup API and mask the upper
DSCP bits using IPTOS_RT_MASK before the lookup.

No regressions in nft_fib.sh:

 # ./nft_fib.sh
 PASS: fib expression did not cause unwanted packet drops
 PASS: fib expression did drop packets for 1.1.1.1
 PASS: fib expression did drop packets for 1c3::c01d
 PASS: fib expression forward check with policy based routing

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/netfilter/nft_fib_ipv4.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 9eee535c64dd..df94bc28c3d7 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -22,8 +22,6 @@ static __be32 get_saddr(__be32 addr)
 	return addr;
 }
 
-#define DSCP_BITS     0xfc
-
 void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 			const struct nft_pktinfo *pkt)
 {
@@ -110,7 +108,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (priv->flags & NFTA_FIB_F_MARK)
 		fl4.flowi4_mark = pkt->skb->mark;
 
-	fl4.flowi4_tos = iph->tos & DSCP_BITS;
+	fl4.flowi4_tos = iph->tos & IPTOS_RT_MASK;
 
 	if (priv->flags & NFTA_FIB_F_DADDR) {
 		fl4.daddr = iph->daddr;
-- 
cgit v1.3-3-g829e


From 1fa3314c14c6a20d098991a0a6980f9b18b2f930 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 14 Aug 2024 15:52:24 +0300
Subject: ipv4: Centralize TOS matching

The TOS field in the IPv4 flow information structure ('flowi4_tos') is
matched by the kernel against the TOS selector in IPv4 rules and routes.
The field is initialized differently by different call sites. Some treat
it as DSCP (RFC 2474) and initialize all six DSCP bits, some treat it as
RFC 1349 TOS and initialize it using RT_TOS() and some treat it as RFC
791 TOS and initialize it using IPTOS_RT_MASK.

What is common to all these call sites is that they all initialize the
lower three DSCP bits, which fits the TOS definition in the initial IPv4
specification (RFC 791).

Therefore, the kernel only allows configuring IPv4 FIB rules that match
on the lower three DSCP bits which are always guaranteed to be
initialized by all call sites:

 # ip -4 rule add tos 0x1c table 100
 # ip -4 rule add tos 0x3c table 100
 Error: Invalid tos.

While this works, it is unlikely to be very useful. RFC 791 that
initially defined the TOS and IP precedence fields was updated by RFC
2474 over twenty five years ago where these fields were replaced by a
single six bits DSCP field.

Extending FIB rules to match on DSCP can be done by adding a new DSCP
selector while maintaining the existing semantics of the TOS selector
for applications that rely on that.

A prerequisite for allowing FIB rules to match on DSCP is to adjust all
the call sites to initialize the high order DSCP bits and remove their
masking along the path to the core where the field is matched on.

However, making this change alone will result in a behavior change. For
example, a forwarded IPv4 packet with a DS field of 0xfc will no longer
match a FIB rule that was configured with 'tos 0x1c'.

This behavior change can be avoided by masking the upper three DSCP bits
in 'flowi4_tos' before comparing it against the TOS selectors in FIB
rules and routes.

Implement the above by adding a new function that checks whether a given
DSCP value matches the one specified in the IPv4 flow information
structure and invoke it from the three places that currently match on
'flowi4_tos'.

Use RT_TOS() for the masking of 'flowi4_tos' instead of IPTOS_RT_MASK
since the latter is not uAPI and we should be able to remove it at some
point.

Include <linux/ip.h> in <linux/in_route.h> since the former defines
IPTOS_TOS_MASK which is used in the definition of RT_TOS() in
<linux/in_route.h>.

No regressions in FIB tests:

 # ./fib_tests.sh
 [...]
 Tests passed: 218
 Tests failed:   0

And FIB rule tests:

 # ./fib_rule_tests.sh
 [...]
 Tests passed: 116
 Tests failed:   0

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/ip_fib.h          | 6 ++++++
 include/uapi/linux/in_route.h | 2 ++
 net/ipv4/fib_rules.c          | 2 +-
 net/ipv4/fib_semantics.c      | 3 +--
 net/ipv4/fib_trie.c           | 3 +--
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 72af2f223e59..269ec10f63e4 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -22,6 +22,7 @@
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/refcount.h>
+#include <linux/in_route.h>
 
 struct fib_config {
 	u8			fc_dst_len;
@@ -434,6 +435,11 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net,
 
 #endif /* CONFIG_IP_MULTIPLE_TABLES */
 
+static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4)
+{
+	return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos));
+}
+
 /* Exported by fib_frontend.c */
 extern const struct nla_policy rtm_ipv4_policy[];
 void ip_fib_init(void);
diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h
index 0cc2c23b47f8..10bdd7e7107f 100644
--- a/include/uapi/linux/in_route.h
+++ b/include/uapi/linux/in_route.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_IN_ROUTE_H
 #define _LINUX_IN_ROUTE_H
 
+#include <linux/ip.h>
+
 /* IPv4 routing cache flags */
 
 #define RTCF_DEAD	RTNH_F_DEAD
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 5bdd1c016009..c26776b71e97 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -186,7 +186,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule,
 	    ((daddr ^ r->dst) & r->dstmask))
 		return 0;
 
-	if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos))
+	if (r->dscp && !fib_dscp_masked_match(r->dscp, fl4))
 		return 0;
 
 	if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2b57cd2b96e2..0f70341cb8b5 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2066,8 +2066,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 
 		if (fa->fa_slen != slen)
 			continue;
-		if (fa->fa_dscp &&
-		    fa->fa_dscp != inet_dsfield_to_dscp(flp->flowi4_tos))
+		if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp))
 			continue;
 		if (fa->tb_id != tb->tb_id)
 			continue;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 8f30e3f00b7f..09e31757e96c 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1580,8 +1580,7 @@ found:
 			if (index >= (1ul << fa->fa_slen))
 				continue;
 		}
-		if (fa->fa_dscp &&
-		    inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos)
+		if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp))
 			continue;
 		/* Paired with WRITE_ONCE() in fib_release_info() */
 		if (READ_ONCE(fi->fib_dead))
-- 
cgit v1.3-3-g829e


From 797653865b982d53ecca517dd2b0ffb8bd967022 Mon Sep 17 00:00:00 2001
From: Zhang Zekun <zhangzekun11@huawei.com>
Date: Fri, 16 Aug 2024 09:58:37 +0800
Subject: net: ethernet: ibm: Simpify code with for_each_child_of_node()

for_each_child_of_node can help to iterate through the device_node,
and we don't need to use while loop. No functional change with this
conversion.

Signed-off-by: Zhang Zekun <zhangzekun11@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240816015837.109627-1-zhangzekun11@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ibm/ehea/ehea_main.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 1e29e5c9a2df..c41c3f1cc506 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3063,14 +3063,13 @@ static void ehea_shutdown_single_port(struct ehea_port *port)
 static int ehea_setup_ports(struct ehea_adapter *adapter)
 {
 	struct device_node *lhea_dn;
-	struct device_node *eth_dn = NULL;
+	struct device_node *eth_dn;
 
 	const u32 *dn_log_port_id;
 	int i = 0;
 
 	lhea_dn = adapter->ofdev->dev.of_node;
-	while ((eth_dn = of_get_next_child(lhea_dn, eth_dn))) {
-
+	for_each_child_of_node(lhea_dn, eth_dn) {
 		dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no",
 						 NULL);
 		if (!dn_log_port_id) {
@@ -3102,12 +3101,11 @@ static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter,
 					   u32 logical_port_id)
 {
 	struct device_node *lhea_dn;
-	struct device_node *eth_dn = NULL;
+	struct device_node *eth_dn;
 	const u32 *dn_log_port_id;
 
 	lhea_dn = adapter->ofdev->dev.of_node;
-	while ((eth_dn = of_get_next_child(lhea_dn, eth_dn))) {
-
+	for_each_child_of_node(lhea_dn, eth_dn) {
 		dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no",
 						 NULL);
 		if (dn_log_port_id)
-- 
cgit v1.3-3-g829e


From 555e5531635a7c5dba663d06cea240362624dfde Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 17 Aug 2024 13:36:59 -0700
Subject: selftests: net/forwarding: spawn sh inside vrf to speed up ping loop

Looking at timestamped output of netdev CI reveals that
most of the time in forwarding tests for custom route
hashing is spent on a single case, namely the test which
uses ping (mausezahn does not support flow labels).

On a non-debug kernel we spend 714 of 730 total test
runtime (97%) on this test case. While having flow label
support in a traffic gen tool / mausezahn would be best,
we can significantly speed up the loop by putting ip vrf exec
outside of the iteration.

In a test of 1000 pings using a normal loop takes 50 seconds
to finish. While using:

  ip vrf exec $vrf sh -c "$loop-body"

takes 12 seconds (1/4 of the time).

Some of the slowness is likely due to our inefficient virtualization
setup, but even on my laptop running "ip link help" 16k times takes
25-30 seconds, so I think it's worth optimizing even for fastest
setups.

Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20240817203659.712085-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/custom_multipath_hash.sh   | 8 ++++----
 .../testing/selftests/net/forwarding/gre_custom_multipath_hash.sh | 8 ++++----
 .../selftests/net/forwarding/ip6gre_custom_multipath_hash.sh      | 8 ++++----
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
index 1783c10215e5..7d531f7091e6 100755
--- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh
@@ -224,10 +224,10 @@ send_dst_ipv6()
 send_flowlabel()
 {
 	# Generate 16384 echo requests, each with a random flow label.
-	for _ in $(seq 1 16384); do
-		ip vrf exec v$h1 \
-			$PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1
-	done
+	ip vrf exec v$h1 sh -c \
+		"for _ in {1..16384}; do \
+			$PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1; \
+		done"
 }
 
 send_src_udp6()
diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
index 9788bd0f6e8b..dda11a4a9450 100755
--- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh
@@ -319,10 +319,10 @@ send_dst_ipv6()
 send_flowlabel()
 {
 	# Generate 16384 echo requests, each with a random flow label.
-	for _ in $(seq 1 16384); do
-		ip vrf exec v$h1 \
-			$PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1
-	done
+	ip vrf exec v$h1 sh -c \
+		"for _ in {1..16384}; do \
+			$PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \
+		done"
 }
 
 send_src_udp6()
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
index 2ab9eaaa5532..e28b4a079e52 100755
--- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh
@@ -321,10 +321,10 @@ send_dst_ipv6()
 send_flowlabel()
 {
 	# Generate 16384 echo requests, each with a random flow label.
-	for _ in $(seq 1 16384); do
-		ip vrf exec v$h1 \
-			$PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1
-	done
+	ip vrf exec v$h1 sh -c \
+		"for _ in {1..16384}; do \
+			$PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \
+		done"
 }
 
 send_src_udp6()
-- 
cgit v1.3-3-g829e


From 2cbece60a4af03803634abd1e840e513db48d42e Mon Sep 17 00:00:00 2001
From: Zhang Zekun <zhangzekun11@huawei.com>
Date: Sun, 18 Aug 2024 13:25:18 +0800
Subject: net: hns3: Use ARRAY_SIZE() to improve readability

There is a helper function ARRAY_SIZE() to help calculating the
u32 array size, and we don't need to do it mannually. So, let's
use ARRAY_SIZE() to calculate the array size, and improve the code
readability.

Signed-off-by: Zhang Zekun <zhangzekun11@huawei.com>
Reviewed-by: Jijie Shao<shaojijie@huawei.com>
Link: https://patch.msgid.link/20240818052518.45489-1-zhangzekun11@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
index 65b9dcd38137..6db415d8b917 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c
@@ -134,17 +134,17 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 	reg += hclgevf_reg_get_header(reg);
 
 	/* fetching per-VF registers values from VF PCIe register space */
-	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
+	reg_um = ARRAY_SIZE(cmdq_reg_addr_list);
 	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_um, reg);
 	for (i = 0; i < reg_um; i++)
 		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
 
-	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
+	reg_um = ARRAY_SIZE(common_reg_addr_list);
 	reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_um, reg);
 	for (i = 0; i < reg_um; i++)
 		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
 
-	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
+	reg_um = ARRAY_SIZE(ring_reg_addr_list);
 	for (j = 0; j < hdev->num_tqps; j++) {
 		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg);
 		for (i = 0; i < reg_um; i++)
@@ -153,7 +153,7 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
 						  HCLGEVF_RING_REG_OFFSET * j);
 	}
 
-	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
+	reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list);
 	for (j = 0; j < hdev->num_msi_used - 1; j++) {
 		reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR, reg_um, reg);
 		for (i = 0; i < reg_um; i++)
-- 
cgit v1.3-3-g829e


From 13cfd6a6d7ac78e845768278ab745acbd19c43ce Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 18 Aug 2024 14:43:51 +0300
Subject: net: Silence false field-spanning write warning in metadata_dst
 memcpy

When metadata_dst struct is allocated (using metadata_dst_alloc()), it
reserves room for options at the end of the struct.

Change the memcpy() to unsafe_memcpy() as it is guaranteed that enough
room (md_size bytes) was allocated and the field-spanning write is
intentional.

This resolves the following warning:
	------------[ cut here ]------------
	memcpy: detected field-spanning write (size 104) of single field "&new_md->u.tun_info" at include/net/dst_metadata.h:166 (size 96)
	WARNING: CPU: 2 PID: 391470 at include/net/dst_metadata.h:166 tun_dst_unclone+0x114/0x138 [geneve]
	Modules linked in: act_tunnel_key geneve ip6_udp_tunnel udp_tunnel act_vlan act_mirred act_skbedit cls_matchall nfnetlink_cttimeout act_gact cls_flower sch_ingress sbsa_gwdt ipmi_devintf ipmi_msghandler xfrm_interface xfrm6_tunnel tunnel6 tunnel4 xfrm_user xfrm_algo nvme_fabrics overlay optee openvswitch nsh nf_conncount ib_srp scsi_transport_srp rpcrdma rdma_ucm ib_iser rdma_cm ib_umad iw_cm libiscsi ib_ipoib scsi_transport_iscsi ib_cm uio_pdrv_genirq uio mlxbf_pmc pwr_mlxbf mlxbf_bootctl bluefield_edac nft_chain_nat binfmt_misc xt_MASQUERADE nf_nat xt_tcpmss xt_NFLOG nfnetlink_log xt_recent xt_hashlimit xt_state xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_mark xt_comment ipt_REJECT nf_reject_ipv4 nft_compat nf_tables nfnetlink sch_fq_codel dm_multipath fuse efi_pstore ip_tables btrfs blake2b_generic raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor xor_neon raid6_pq raid1 raid0 nvme nvme_core mlx5_ib ib_uverbs ib_core ipv6 crc_ccitt mlx5_core crct10dif_ce mlxfw
	 psample i2c_mlxbf gpio_mlxbf2 mlxbf_gige mlxbf_tmfifo
	CPU: 2 PID: 391470 Comm: handler6 Not tainted 6.10.0-rc1 #1
	Hardware name: https://www.mellanox.com BlueField SoC/BlueField SoC, BIOS 4.5.0.12993 Dec  6 2023
	pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
	pc : tun_dst_unclone+0x114/0x138 [geneve]
	lr : tun_dst_unclone+0x114/0x138 [geneve]
	sp : ffffffc0804533f0
	x29: ffffffc0804533f0 x28: 000000000000024e x27: 0000000000000000
	x26: ffffffdcfc0e8e40 x25: ffffff8086fa6600 x24: ffffff8096a0c000
	x23: 0000000000000068 x22: 0000000000000008 x21: ffffff8092ad7000
	x20: ffffff8081e17900 x19: ffffff8092ad7900 x18: 00000000fffffffd
	x17: 0000000000000000 x16: ffffffdcfa018488 x15: 695f6e75742e753e
	x14: 2d646d5f77656e26 x13: 6d5f77656e262220 x12: 646c65696620656c
	x11: ffffffdcfbe33ae8 x10: ffffffdcfbe1baa8 x9 : ffffffdcfa0a4c10
	x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000000001
	x5 : ffffff83fdeeb010 x4 : 0000000000000000 x3 : 0000000000000027
	x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffffff80913f6780
	Call trace:
	 tun_dst_unclone+0x114/0x138 [geneve]
	 geneve_xmit+0x214/0x10e0 [geneve]
	 dev_hard_start_xmit+0xc0/0x220
	 __dev_queue_xmit+0xa14/0xd38
	 dev_queue_xmit+0x14/0x28 [openvswitch]
	 ovs_vport_send+0x98/0x1c8 [openvswitch]
	 do_output+0x80/0x1a0 [openvswitch]
	 do_execute_actions+0x172c/0x1958 [openvswitch]
	 ovs_execute_actions+0x64/0x1a8 [openvswitch]
	 ovs_packet_cmd_execute+0x258/0x2d8 [openvswitch]
	 genl_family_rcv_msg_doit+0xc8/0x138
	 genl_rcv_msg+0x1ec/0x280
	 netlink_rcv_skb+0x64/0x150
	 genl_rcv+0x40/0x60
	 netlink_unicast+0x2e4/0x348
	 netlink_sendmsg+0x1b0/0x400
	 __sock_sendmsg+0x64/0xc0
	 ____sys_sendmsg+0x284/0x308
	 ___sys_sendmsg+0x88/0xf0
	 __sys_sendmsg+0x70/0xd8
	 __arm64_sys_sendmsg+0x2c/0x40
	 invoke_syscall+0x50/0x128
	 el0_svc_common.constprop.0+0x48/0xf0
	 do_el0_svc+0x24/0x38
	 el0_svc+0x38/0x100
	 el0t_64_sync_handler+0xc0/0xc8
	 el0t_64_sync+0x1a4/0x1a8
	---[ end trace 0000000000000000 ]---

Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240818114351.3612692-1-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/dst_metadata.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 4160731dcb6e..84c15402931c 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -163,8 +163,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
 	if (!new_md)
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
-	       sizeof(struct ip_tunnel_info) + md_size);
+	unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
+		      sizeof(struct ip_tunnel_info) + md_size,
+		      /* metadata_dst_alloc() reserves room (md_size bytes) for
+		       * options right after the ip_tunnel_info struct.
+		       */);
 #ifdef CONFIG_DST_CACHE
 	/* Unclone the dst cache if there is one */
 	if (new_md->u.tun_info.dst_cache.cache) {
-- 
cgit v1.3-3-g829e


From 55da77dec1be92afafb5683cc28a60bc2cc83716 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 18 Aug 2024 19:29:02 +0200
Subject: dt-bindings: net: mediatek,net: narrow interrupts per variants

Each variable-length property like interrupts must have fixed
constraints on number of items for given variant in binding.  The
clauses in "if:then:" block should define both limits: upper and lower.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240818172905.121829-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/mediatek,net.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml
index 686b5c2fae40..8c00a6f75357 100644
--- a/Documentation/devicetree/bindings/net/mediatek,net.yaml
+++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml
@@ -127,6 +127,7 @@ allOf:
     then:
       properties:
         interrupts:
+          minItems: 3
           maxItems: 3
 
         clocks:
@@ -183,6 +184,7 @@ allOf:
     then:
       properties:
         interrupts:
+          minItems: 3
           maxItems: 3
 
         clocks:
@@ -222,6 +224,7 @@ allOf:
     then:
       properties:
         interrupts:
+          minItems: 3
           maxItems: 3
 
         clocks:
-- 
cgit v1.3-3-g829e


From 06ab21c3cb6e124bdc2da226f38bc8eb45946887 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 18 Aug 2024 19:29:03 +0200
Subject: dt-bindings: net: mediatek,net: add top-level constraints

Properties with variable number of items per each device are expected to
have widest constraints in top-level "properties:" block and further
customized (narrowed) in "if:then:".  Add missing top-level constraints
for clocks and clock-names.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240818172905.121829-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/mediatek,net.yaml | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml
index 8c00a6f75357..9e02fd80af83 100644
--- a/Documentation/devicetree/bindings/net/mediatek,net.yaml
+++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml
@@ -30,8 +30,13 @@ properties:
   reg:
     maxItems: 1
 
-  clocks: true
-  clock-names: true
+  clocks:
+    minItems: 2
+    maxItems: 24
+
+  clock-names:
+    minItems: 2
+    maxItems: 24
 
   interrupts:
     minItems: 1
-- 
cgit v1.3-3-g829e


From 70d16e13368c0526eb3e2a326ed002183a087c21 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 18 Aug 2024 19:29:04 +0200
Subject: dt-bindings: net: renesas,etheravb: add top-level constraints

Properties with variable number of items per each device are expected to
have widest constraints in top-level "properties:" block and further
customized (narrowed) in "if:then:".  Add missing top-level constraints
for reg, clocks, clock-names, interrupts and interrupt-names.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240818172905.121829-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/renesas,etheravb.yaml  | 29 ++++++++++++++--------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
index 21a92f179093..1e00ef5b3acd 100644
--- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
+++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml
@@ -62,15 +62,27 @@ properties:
               - renesas,r9a08g045-gbeth # RZ/G3S
           - const: renesas,rzg2l-gbeth  # RZ/{G2L,G2UL,V2L} family
 
-  reg: true
+  reg:
+    minItems: 1
+    items:
+      - description: MAC register block
+      - description: Stream buffer
 
-  interrupts: true
+  interrupts:
+    minItems: 1
+    maxItems: 29
 
-  interrupt-names: true
+  interrupt-names:
+    minItems: 1
+    maxItems: 29
 
-  clocks: true
+  clocks:
+    minItems: 1
+    maxItems: 3
 
-  clock-names: true
+  clock-names:
+    minItems: 1
+    maxItems: 3
 
   iommus:
     maxItems: 1
@@ -150,14 +162,11 @@ allOf:
     then:
       properties:
         reg:
-          items:
-            - description: MAC register block
-            - description: Stream buffer
+          minItems: 2
     else:
       properties:
         reg:
-          items:
-            - description: MAC register block
+          maxItems: 1
 
   - if:
       properties:
-- 
cgit v1.3-3-g829e


From 2862c9349d5d8667d897aa5cecf0f3886979ecb1 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 18 Aug 2024 19:29:05 +0200
Subject: dt-bindings: net: socionext,uniphier-ave4: add top-level constraints

Properties with variable number of items per each device are expected to
have widest constraints in top-level "properties:" block and further
customized (narrowed) in "if:then:".  Add missing top-level constraints
for clock-names and reset-names.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240818172905.121829-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/socionext,uniphier-ave4.yaml          | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
index b0ebcef6801c..4eb63b303cff 100644
--- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
+++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml
@@ -41,13 +41,17 @@ properties:
     minItems: 1
     maxItems: 4
 
-  clock-names: true
+  clock-names:
+    minItems: 1
+    maxItems: 4
 
   resets:
     minItems: 1
     maxItems: 2
 
-  reset-names: true
+  reset-names:
+    minItems: 1
+    maxItems: 2
 
   socionext,syscon-phy-mode:
     $ref: /schemas/types.yaml#/definitions/phandle-array
-- 
cgit v1.3-3-g829e


From 8594d9b85c07f05e431bd07e895c2a3ad9b85d6f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 16 Aug 2024 16:39:21 -0700
Subject: af_unix: Don't call skb_get() for OOB skb.

Since introduced, OOB skb holds an additional reference count with no
special reason and caused many issues.

Also, kfree_skb() and consume_skb() are used to decrement the count,
which is confusing.

Let's drop the unnecessary skb_get() in queue_oob() and corresponding
kfree_skb(), consume_skb(), and skb_unref().

Now unix_sk(sk)->oob_skb is just a pointer to skb in the receive queue,
so special handing is no longer needed in GC.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240816233921.57800-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 27 +++++----------------------
 net/unix/garbage.c | 16 ++--------------
 2 files changed, 7 insertions(+), 36 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0be0dcb07f7b..a1894019ebd5 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -693,10 +693,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
 	unix_state_unlock(sk);
 
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-	if (u->oob_skb) {
-		kfree_skb(u->oob_skb);
-		u->oob_skb = NULL;
-	}
+	u->oob_skb = NULL;
 #endif
 
 	wake_up_interruptible_all(&u->peer_wait);
@@ -2226,13 +2223,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	}
 
 	maybe_add_creds(skb, sock, other);
-	skb_get(skb);
-
 	scm_stat_add(other, skb);
 
 	spin_lock(&other->sk_receive_queue.lock);
-	if (ousk->oob_skb)
-		consume_skb(ousk->oob_skb);
 	WRITE_ONCE(ousk->oob_skb, skb);
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
@@ -2640,8 +2633,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	if (!(state->flags & MSG_PEEK))
 		WRITE_ONCE(u->oob_skb, NULL);
-	else
-		skb_get(oob_skb);
 
 	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
@@ -2651,8 +2642,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 	if (!(state->flags & MSG_PEEK))
 		UNIXCB(oob_skb).consumed += 1;
 
-	consume_skb(oob_skb);
-
 	mutex_unlock(&u->iolock);
 
 	if (chunk < 0)
@@ -2694,12 +2683,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 			if (copied) {
 				skb = NULL;
 			} else if (!(flags & MSG_PEEK)) {
-				if (sock_flag(sk, SOCK_URGINLINE)) {
-					WRITE_ONCE(u->oob_skb, NULL);
-					consume_skb(skb);
-				} else {
+				WRITE_ONCE(u->oob_skb, NULL);
+
+				if (!sock_flag(sk, SOCK_URGINLINE)) {
 					__skb_unlink(skb, &sk->sk_receive_queue);
-					WRITE_ONCE(u->oob_skb, NULL);
 					unlinked_skb = skb;
 					skb = skb_peek(&sk->sk_receive_queue);
 				}
@@ -2710,10 +2697,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 		spin_unlock(&sk->sk_receive_queue.lock);
 
-		if (unlinked_skb) {
-			WARN_ON_ONCE(skb_unref(unlinked_skb));
-			kfree_skb(unlinked_skb);
-		}
+		kfree_skb(unlinked_skb);
 	}
 	return skb;
 }
@@ -2756,7 +2740,6 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		unix_state_unlock(sk);
 
 		if (drop) {
-			WARN_ON_ONCE(skb_unref(skb));
 			kfree_skb(skb);
 			return -EAGAIN;
 		}
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 06d94ad999e9..0068e758be4d 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -337,18 +337,6 @@ static bool unix_vertex_dead(struct unix_vertex *vertex)
 	return true;
 }
 
-static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist)
-{
-	skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist);
-
-#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
-	if (u->oob_skb) {
-		WARN_ON_ONCE(skb_unref(u->oob_skb));
-		u->oob_skb = NULL;
-	}
-#endif
-}
-
 static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist)
 {
 	struct unix_vertex *vertex;
@@ -371,11 +359,11 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist
 				struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue;
 
 				spin_lock(&embryo_queue->lock);
-				unix_collect_queue(unix_sk(skb->sk), hitlist);
+				skb_queue_splice_init(embryo_queue, hitlist);
 				spin_unlock(&embryo_queue->lock);
 			}
 		} else {
-			unix_collect_queue(u, hitlist);
+			skb_queue_splice_init(queue, hitlist);
 		}
 
 		spin_unlock(&queue->lock);
-- 
cgit v1.3-3-g829e


From bc3dd9ed04d69cba3bb603da06fa26d888233cff Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Mon, 19 Aug 2024 15:33:33 +0100
Subject: l2tp: use skb_queue_purge in l2tp_ip_destroy_sock

Recent commit ed8ebee6def7 ("l2tp: have l2tp_ip_destroy_sock use
ip_flush_pending_frames") was incorrect in that l2tp_ip does not use
socket cork and ip_flush_pending_frames is for sockets that do. Use
__skb_queue_purge instead and remove the unnecessary lock.

Also unexport ip_flush_pending_frames since it was originally exported
in commit 4ff8863419cd ("ipv4: export ip_flush_pending_frames") for
l2tp and is not used by other modules.

Suggested-by: xiyou.wangcong@gmail.com
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240819143333.3204957-1-jchapman@katalix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_output.c | 1 -
 net/l2tp/l2tp_ip.c   | 4 +---
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 8a10a7c67834..b90d0f78ac80 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1534,7 +1534,6 @@ void ip_flush_pending_frames(struct sock *sk)
 {
 	__ip_flush_pending_frames(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
 }
-EXPORT_SYMBOL_GPL(ip_flush_pending_frames);
 
 struct sk_buff *ip_make_skb(struct sock *sk,
 			    struct flowi4 *fl4,
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 39f3f1334c4a..4bc24fddfd52 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -258,9 +258,7 @@ static void l2tp_ip_destroy_sock(struct sock *sk)
 {
 	struct l2tp_tunnel *tunnel;
 
-	lock_sock(sk);
-	ip_flush_pending_frames(sk);
-	release_sock(sk);
+	__skb_queue_purge(&sk->sk_write_queue);
 
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
-- 
cgit v1.3-3-g829e


From 4d36b2b1dea4ff528bd7d312d9c713a827656d75 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Mon, 19 Aug 2024 17:44:35 -0700
Subject: net: dsa: b53: Use dev_err_probe()

Rather than print an error even when we get -EPROBE_DEFER, use
dev_err_probe() to filter out those messages.

Link: https://github.com/openwrt/openwrt/pull/11680
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240820004436.224603-1-florian.fainelli@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_mdio.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
index 897e5e8b3d69..31d070bf161a 100644
--- a/drivers/net/dsa/b53/b53_mdio.c
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -343,10 +343,9 @@ static int b53_mdio_probe(struct mdio_device *mdiodev)
 	dev_set_drvdata(&mdiodev->dev, dev);
 
 	ret = b53_switch_register(dev);
-	if (ret) {
-		dev_err(&mdiodev->dev, "failed to register switch: %i\n", ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(&mdiodev->dev, ret,
+				     "failed to register switch\n");
 
 	return ret;
 }
-- 
cgit v1.3-3-g829e


From d785ed945de6955361aafc2d540d9bb7c6a69a65 Mon Sep 17 00:00:00 2001
From: Jinjian Song <jinjian.song@fibocom.com>
Date: Sat, 17 Aug 2024 16:33:55 +0800
Subject: net: wwan: t7xx: PCIe reset rescan

WWAN device is programmed to boot in normal mode or fastboot mode,
when triggering a device reset through ACPI call or fastboot switch
command. Maintain state machine synchronization and reprobe logic
after a device reset.

The PCIe device reset triggered by several ways.
E.g.:
 - fastboot: echo "fastboot_switching" > /sys/bus/pci/devices/${bdf}/t7xx_mode.
 - reset: echo "reset" > /sys/bus/pci/devices/${bdf}/t7xx_mode.
 - IRQ: PCIe device request driver to reset itself by an interrupt request.

Use pci_reset_function() as a generic way to reset device, save and
restore the PCIe configuration before and after reset device to ensure
the reprobe process.

Suggestion from Bjorn:
Link: https://lore.kernel.org/all/20230127133034.GA1364550@bhelgaas/

Signed-off-by: Jinjian Song <jinjian.song@fibocom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wwan/t7xx/t7xx_modem_ops.c     | 47 ++++++++++++++++++++++----
 drivers/net/wwan/t7xx/t7xx_modem_ops.h     |  9 +++--
 drivers/net/wwan/t7xx/t7xx_pci.c           | 53 ++++++++++++++++++++++++------
 drivers/net/wwan/t7xx/t7xx_pci.h           |  3 ++
 drivers/net/wwan/t7xx/t7xx_port_proxy.c    |  1 -
 drivers/net/wwan/t7xx/t7xx_port_trace.c    |  1 +
 drivers/net/wwan/t7xx/t7xx_state_monitor.c | 34 +++++++------------
 7 files changed, 105 insertions(+), 43 deletions(-)

diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c
index 8d864d4ed77f..79f17100f70b 100644
--- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c
+++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c
@@ -53,6 +53,7 @@
 
 #define RGU_RESET_DELAY_MS	10
 #define PORT_RESET_DELAY_MS	2000
+#define FASTBOOT_RESET_DELAY_MS	2000
 #define EX_HS_TIMEOUT_MS	5000
 #define EX_HS_POLL_DELAY_MS	10
 
@@ -167,19 +168,52 @@ static int t7xx_acpi_reset(struct t7xx_pci_dev *t7xx_dev, char *fn_name)
 	}
 
 	kfree(buffer.pointer);
+#else
+	struct device *dev = &t7xx_dev->pdev->dev;
+	int ret;
 
+	ret = pci_reset_function(t7xx_dev->pdev);
+	if (ret) {
+		dev_err(dev, "Failed to reset device, error:%d\n", ret);
+		return ret;
+	}
 #endif
 	return 0;
 }
 
-int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev)
+static void t7xx_host_event_notify(struct t7xx_pci_dev *t7xx_dev, unsigned int event_id)
 {
-	return t7xx_acpi_reset(t7xx_dev, "_RST");
+	u32 value;
+
+	value = ioread32(IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS);
+	value &= ~HOST_EVENT_MASK;
+	value |= FIELD_PREP(HOST_EVENT_MASK, event_id);
+	iowrite32(value, IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS);
 }
 
-int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev)
+int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type)
 {
-	return t7xx_acpi_reset(t7xx_dev, "MRST._RST");
+	int ret = 0;
+
+	pci_save_state(t7xx_dev->pdev);
+	t7xx_pci_reprobe_early(t7xx_dev);
+	t7xx_mode_update(t7xx_dev, T7XX_RESET);
+
+	if (type == FLDR) {
+		ret = t7xx_acpi_reset(t7xx_dev, "_RST");
+	} else if (type == PLDR) {
+		ret = t7xx_acpi_reset(t7xx_dev, "MRST._RST");
+	} else if (type == FASTBOOT) {
+		t7xx_host_event_notify(t7xx_dev, FASTBOOT_DL_NOTIFY);
+		t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET);
+		msleep(FASTBOOT_RESET_DELAY_MS);
+	}
+
+	pci_restore_state(t7xx_dev->pdev);
+	if (ret)
+		return ret;
+
+	return t7xx_pci_reprobe(t7xx_dev, true);
 }
 
 static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev)
@@ -188,16 +222,15 @@ static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev)
 
 	val = ioread32(IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS);
 	if (val & MISC_RESET_TYPE_PLDR)
-		t7xx_acpi_reset(t7xx_dev, "MRST._RST");
+		t7xx_reset_device(t7xx_dev, PLDR);
 	else if (val & MISC_RESET_TYPE_FLDR)
-		t7xx_acpi_fldr_func(t7xx_dev);
+		t7xx_reset_device(t7xx_dev, FLDR);
 }
 
 static irqreturn_t t7xx_rgu_isr_thread(int irq, void *data)
 {
 	struct t7xx_pci_dev *t7xx_dev = data;
 
-	t7xx_mode_update(t7xx_dev, T7XX_RESET);
 	msleep(RGU_RESET_DELAY_MS);
 	t7xx_reset_device_via_pmic(t7xx_dev);
 	return IRQ_HANDLED;
diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.h b/drivers/net/wwan/t7xx/t7xx_modem_ops.h
index b39e945a92e0..39ed0000fbba 100644
--- a/drivers/net/wwan/t7xx/t7xx_modem_ops.h
+++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.h
@@ -78,14 +78,19 @@ struct t7xx_modem {
 	spinlock_t			exp_lock; /* Protects exception events */
 };
 
+enum reset_type {
+	FLDR,
+	PLDR,
+	FASTBOOT,
+};
+
 void t7xx_md_exception_handshake(struct t7xx_modem *md);
 void t7xx_md_event_notify(struct t7xx_modem *md, enum md_event_id evt_id);
 int t7xx_md_reset(struct t7xx_pci_dev *t7xx_dev);
 int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev);
 void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev);
 void t7xx_clear_rgu_irq(struct t7xx_pci_dev *t7xx_dev);
-int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev);
-int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev);
+int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type);
 int t7xx_pci_mhccif_isr(struct t7xx_pci_dev *t7xx_dev);
 
 #endif	/* __T7XX_MODEM_OPS_H__ */
diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c
index 10a8c1080b10..e556e5bd49ab 100644
--- a/drivers/net/wwan/t7xx/t7xx_pci.c
+++ b/drivers/net/wwan/t7xx/t7xx_pci.c
@@ -69,6 +69,7 @@ static ssize_t t7xx_mode_store(struct device *dev,
 {
 	struct t7xx_pci_dev *t7xx_dev;
 	struct pci_dev *pdev;
+	enum t7xx_mode mode;
 	int index = 0;
 
 	pdev = to_pci_dev(dev);
@@ -76,12 +77,22 @@ static ssize_t t7xx_mode_store(struct device *dev,
 	if (!t7xx_dev)
 		return -ENODEV;
 
+	mode = READ_ONCE(t7xx_dev->mode);
+
 	index = sysfs_match_string(t7xx_mode_names, buf);
+	if (index == mode)
+		return -EBUSY;
+
 	if (index == T7XX_FASTBOOT_SWITCHING) {
+		if (mode == T7XX_FASTBOOT_DOWNLOAD)
+			return count;
+
 		WRITE_ONCE(t7xx_dev->mode, T7XX_FASTBOOT_SWITCHING);
+		pm_runtime_resume(dev);
+		t7xx_reset_device(t7xx_dev, FASTBOOT);
 	} else if (index == T7XX_RESET) {
-		WRITE_ONCE(t7xx_dev->mode, T7XX_RESET);
-		t7xx_acpi_pldr_func(t7xx_dev);
+		pm_runtime_resume(dev);
+		t7xx_reset_device(t7xx_dev, PLDR);
 	}
 
 	return count;
@@ -446,7 +457,7 @@ static int t7xx_pcie_reinit(struct t7xx_pci_dev *t7xx_dev, bool is_d3)
 
 	if (is_d3) {
 		t7xx_mhccif_init(t7xx_dev);
-		return t7xx_pci_pm_reinit(t7xx_dev);
+		t7xx_pci_pm_reinit(t7xx_dev);
 	}
 
 	return 0;
@@ -481,6 +492,33 @@ static int t7xx_send_fsm_command(struct t7xx_pci_dev *t7xx_dev, u32 event)
 	return ret;
 }
 
+int t7xx_pci_reprobe_early(struct t7xx_pci_dev *t7xx_dev)
+{
+	enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode);
+	int ret;
+
+	if (mode == T7XX_FASTBOOT_DOWNLOAD)
+		pm_runtime_put_noidle(&t7xx_dev->pdev->dev);
+
+	ret = t7xx_send_fsm_command(t7xx_dev, FSM_CMD_STOP);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int t7xx_pci_reprobe(struct t7xx_pci_dev *t7xx_dev, bool boot)
+{
+	int ret;
+
+	ret = t7xx_pcie_reinit(t7xx_dev, boot);
+	if (ret)
+		return ret;
+
+	t7xx_clear_rgu_irq(t7xx_dev);
+	return t7xx_send_fsm_command(t7xx_dev, FSM_CMD_START);
+}
+
 static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check)
 {
 	struct t7xx_pci_dev *t7xx_dev;
@@ -507,16 +545,11 @@ static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check)
 		if (prev_state == PM_RESUME_REG_STATE_L3 ||
 		    (prev_state == PM_RESUME_REG_STATE_INIT &&
 		     atr_reg_val == ATR_SRC_ADDR_INVALID)) {
-			ret = t7xx_send_fsm_command(t7xx_dev, FSM_CMD_STOP);
-			if (ret)
-				return ret;
-
-			ret = t7xx_pcie_reinit(t7xx_dev, true);
+			ret = t7xx_pci_reprobe_early(t7xx_dev);
 			if (ret)
 				return ret;
 
-			t7xx_clear_rgu_irq(t7xx_dev);
-			return t7xx_send_fsm_command(t7xx_dev, FSM_CMD_START);
+			return t7xx_pci_reprobe(t7xx_dev, true);
 		}
 
 		if (prev_state == PM_RESUME_REG_STATE_EXP ||
diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h
index 49a11586d8d8..cd8ea17c2644 100644
--- a/drivers/net/wwan/t7xx/t7xx_pci.h
+++ b/drivers/net/wwan/t7xx/t7xx_pci.h
@@ -133,4 +133,7 @@ int t7xx_pci_pm_entity_unregister(struct t7xx_pci_dev *t7xx_dev, struct md_pm_en
 void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev);
 void t7xx_pci_pm_exp_detected(struct t7xx_pci_dev *t7xx_dev);
 void t7xx_mode_update(struct t7xx_pci_dev *t7xx_dev, enum t7xx_mode mode);
+int t7xx_pci_reprobe(struct t7xx_pci_dev *t7xx_dev, bool boot);
+int t7xx_pci_reprobe_early(struct t7xx_pci_dev *t7xx_dev);
+
 #endif /* __T7XX_PCI_H__ */
diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.c b/drivers/net/wwan/t7xx/t7xx_port_proxy.c
index 7d6388bf1d7c..35743e7de0c3 100644
--- a/drivers/net/wwan/t7xx/t7xx_port_proxy.c
+++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.c
@@ -553,7 +553,6 @@ static int t7xx_proxy_alloc(struct t7xx_modem *md)
 
 	md->port_prox = port_prox;
 	port_prox->dev = dev;
-	t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY);
 
 	return 0;
 }
diff --git a/drivers/net/wwan/t7xx/t7xx_port_trace.c b/drivers/net/wwan/t7xx/t7xx_port_trace.c
index 6a3f36385865..4ed8b4e29bf1 100644
--- a/drivers/net/wwan/t7xx/t7xx_port_trace.c
+++ b/drivers/net/wwan/t7xx/t7xx_port_trace.c
@@ -59,6 +59,7 @@ static void t7xx_trace_port_uninit(struct t7xx_port *port)
 
 	relay_close(relaych);
 	debugfs_remove_recursive(debugfs_dir);
+	port->log.relaych = NULL;
 }
 
 static int t7xx_trace_port_recv_skb(struct t7xx_port *port, struct sk_buff *skb)
diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c
index 9889ca4621cf..3931c7a13f5a 100644
--- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c
+++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c
@@ -213,16 +213,6 @@ static void fsm_routine_exception(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comm
 		fsm_finish_command(ctl, cmd, 0);
 }
 
-static void t7xx_host_event_notify(struct t7xx_modem *md, unsigned int event_id)
-{
-	u32 value;
-
-	value = ioread32(IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS);
-	value &= ~HOST_EVENT_MASK;
-	value |= FIELD_PREP(HOST_EVENT_MASK, event_id);
-	iowrite32(value, IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS);
-}
-
 static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int status)
 {
 	struct t7xx_modem *md = ctl->md;
@@ -264,8 +254,14 @@ static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int
 
 static int fsm_stopped_handler(struct t7xx_fsm_ctl *ctl)
 {
+	enum t7xx_mode mode;
+
 	ctl->curr_state = FSM_STATE_STOPPED;
 
+	mode = READ_ONCE(ctl->md->t7xx_dev->mode);
+	if (mode == T7XX_FASTBOOT_DOWNLOAD || mode == T7XX_FASTBOOT_DUMP)
+		return 0;
+
 	t7xx_fsm_broadcast_state(ctl, MD_STATE_STOPPED);
 	return t7xx_md_reset(ctl->md->t7xx_dev);
 }
@@ -284,8 +280,6 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma
 {
 	struct cldma_ctrl *md_ctrl = ctl->md->md_ctrl[CLDMA_ID_MD];
 	struct t7xx_pci_dev *t7xx_dev = ctl->md->t7xx_dev;
-	enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode);
-	int err;
 
 	if (ctl->curr_state == FSM_STATE_STOPPED || ctl->curr_state == FSM_STATE_STOPPING) {
 		fsm_finish_command(ctl, cmd, -EINVAL);
@@ -296,21 +290,10 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma
 	t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_TO_STOP);
 	t7xx_cldma_stop(md_ctrl);
 
-	if (mode == T7XX_FASTBOOT_SWITCHING)
-		t7xx_host_event_notify(ctl->md, FASTBOOT_DL_NOTIFY);
-
 	t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DRM_DISABLE_AP);
 	/* Wait for the DRM disable to take effect */
 	msleep(FSM_DRM_DISABLE_DELAY_MS);
 
-	if (mode == T7XX_FASTBOOT_SWITCHING) {
-		t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET);
-	} else {
-		err = t7xx_acpi_fldr_func(t7xx_dev);
-		if (err)
-			t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET);
-	}
-
 	fsm_finish_command(ctl, cmd, fsm_stopped_handler(ctl));
 }
 
@@ -414,7 +397,9 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command
 
 		case T7XX_DEV_STAGE_LK:
 			dev_dbg(dev, "LK_STAGE Entered\n");
+			t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY);
 			t7xx_lk_stage_event_handling(ctl, status);
+
 			break;
 
 		case T7XX_DEV_STAGE_LINUX:
@@ -436,6 +421,9 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command
 	}
 
 finish_command:
+	if (ret)
+		t7xx_mode_update(md->t7xx_dev, T7XX_UNKNOWN);
+
 	fsm_finish_command(ctl, cmd, ret);
 }
 
-- 
cgit v1.3-3-g829e


From 488d34643ec3f4ce5ce120846fc81412534e9af1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Mon, 19 Aug 2024 19:27:11 -0600
Subject: nfc: pn533: Avoid -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Remove unnecessary flex-array member `data[]`, and with this fix
the following warnings:

drivers/nfc/pn533/usb.c:268:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/nfc/pn533/usb.c:275:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/ZsPw7+6vNoS651Cb@elsanto
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/nfc/pn533/usb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index a187f0e0b0f7..ffd7367ce119 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -254,7 +254,6 @@ struct pn533_acr122_ccid_hdr {
 	 * byte for reposnse msg
 	 */
 	u8 params[3];
-	u8 data[]; /* payload */
 } __packed;
 
 struct pn533_acr122_apdu_hdr {
-- 
cgit v1.3-3-g829e


From e58c3f3d5196952ffa29dd987a15405b7f559af9 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Tue, 20 Aug 2024 15:48:05 +0800
Subject: net: dsa: ocelot: Simplify with scoped for each OF child loop

Use scoped for_each_available_child_of_node_scoped() when iterating over
device nodes to make code a bit simpler.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://patch.msgid.link/20240820074805.680674-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/ocelot/felix.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index e554699f06d4..800711c2b6cb 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -1265,9 +1265,8 @@ static int felix_parse_ports_node(struct felix *felix,
 				  phy_interface_t *port_phy_modes)
 {
 	struct device *dev = felix->ocelot.dev;
-	struct device_node *child;
 
-	for_each_available_child_of_node(ports_node, child) {
+	for_each_available_child_of_node_scoped(ports_node, child) {
 		phy_interface_t phy_mode;
 		u32 port;
 		int err;
@@ -1276,7 +1275,6 @@ static int felix_parse_ports_node(struct felix *felix,
 		if (of_property_read_u32(child, "reg", &port) < 0) {
 			dev_err(dev, "Port number not defined in device tree "
 				"(property \"reg\")\n");
-			of_node_put(child);
 			return -ENODEV;
 		}
 
@@ -1286,7 +1284,6 @@ static int felix_parse_ports_node(struct felix *felix,
 			dev_err(dev, "Failed to read phy-mode or "
 				"phy-interface-type property for port %d\n",
 				port);
-			of_node_put(child);
 			return -ENODEV;
 		}
 
-- 
cgit v1.3-3-g829e


From 2d86ecb64b51127f0d9eac29cd4c58215246a029 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Tue, 20 Aug 2024 15:50:47 +0800
Subject: net: dsa: sja1105: Simplify with scoped for each OF child loop

Use scoped for_each_available_child_of_node_scoped() when iterating over
device nodes to make code a bit simpler.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://patch.msgid.link/20240820075047.681223-1-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index c7282ce3d11c..bc7e50dcb57c 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1188,9 +1188,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 				    struct device_node *ports_node)
 {
 	struct device *dev = &priv->spidev->dev;
-	struct device_node *child;
 
-	for_each_available_child_of_node(ports_node, child) {
+	for_each_available_child_of_node_scoped(ports_node, child) {
 		struct device_node *phy_node;
 		phy_interface_t phy_mode;
 		u32 index;
@@ -1200,7 +1199,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 		if (of_property_read_u32(child, "reg", &index) < 0) {
 			dev_err(dev, "Port number not defined in device tree "
 				"(property \"reg\")\n");
-			of_node_put(child);
 			return -ENODEV;
 		}
 
@@ -1210,7 +1208,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 			dev_err(dev, "Failed to read phy-mode or "
 				"phy-interface-type property for port %d\n",
 				index);
-			of_node_put(child);
 			return -ENODEV;
 		}
 
@@ -1219,7 +1216,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 			if (!of_phy_is_fixed_link(child)) {
 				dev_err(dev, "phy-handle or fixed-link "
 					"properties missing!\n");
-				of_node_put(child);
 				return -ENODEV;
 			}
 			/* phy-handle is missing, but fixed-link isn't.
@@ -1233,10 +1229,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv,
 		priv->phy_mode[index] = phy_mode;
 
 		err = sja1105_parse_rgmii_delays(priv, index, child);
-		if (err) {
-			of_node_put(child);
+		if (err)
 			return err;
-		}
 	}
 
 	return 0;
-- 
cgit v1.3-3-g829e


From d35a3a8f1b7f27ac1ea0f7068dcab0c08846ac44 Mon Sep 17 00:00:00 2001
From: Xi Huang <xuiagnh@gmail.com>
Date: Tue, 20 Aug 2024 19:54:42 +0800
Subject: ipv6: remove redundant check

err varibale will be set everytime,like -ENOBUFS and in if (err < 0),
 when code gets into this path. This check will just slowdown
the execution and that's all.

Signed-off-by: Xi Huang <xuiagnh@gmail.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20240820115442.49366-1-xuiagnh@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/addrconf.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 04ee75af2f6b..d680beb91b0a 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5619,8 +5619,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa)
 	rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err);
 }
 
 static void ipv6_store_devconf(const struct ipv6_devconf *cnf,
@@ -6175,8 +6174,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev)
 	rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err);
 }
 
 static inline size_t inet6_prefix_nlmsg_size(void)
@@ -6243,8 +6241,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
 	rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err);
 }
 
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
-- 
cgit v1.3-3-g829e


From 0ce054f2b891afdd102c8bcc1fc57253c8964e40 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 20 Aug 2024 16:43:46 +0300
Subject: ice: Fix a 32bit bug

BIT() is unsigned long but ->pu.flg_msk and ->pu.flg_val are u64 type.
On 32 bit systems, unsigned long is a u32 and the mismatch between u32
and u64 will break things for the high 32 bits.

Fixes: 9a4c07aaa0f5 ("ice: add parser execution main loop")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/ddc231a8-89c1-4ff4-8704-9198bcb41f8d@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_parser_rt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
index d5bcc266b01e..dedf5e854e4b 100644
--- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c
+++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c
@@ -377,11 +377,11 @@ static void ice_pg_exe(struct ice_parser_rt *rt)
 
 static void ice_flg_add(struct ice_parser_rt *rt, int idx, bool val)
 {
-	rt->pu.flg_msk |= BIT(idx);
+	rt->pu.flg_msk |= BIT_ULL(idx);
 	if (val)
-		rt->pu.flg_val |= BIT(idx);
+		rt->pu.flg_val |= BIT_ULL(idx);
 	else
-		rt->pu.flg_val &= ~BIT(idx);
+		rt->pu.flg_val &= ~BIT_ULL(idx);
 
 	ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for flag %d value %d\n",
 		  idx, val);
-- 
cgit v1.3-3-g829e


From 74b1e94e94ea369923e5656eeb10b26b16591327 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 20 Aug 2024 13:51:19 -0700
Subject: net: repack struct netdev_queue

Adding the NAPI pointer to struct netdev_queue made it grow into another
cacheline, even though there was 44 bytes of padding available.

The struct was historically grouped as follows:

    /* read-mostly stuff (align) */
    /* ... random control path fields ... */
    /* write-mostly stuff (align) */
    /* ... 40 byte hole ... */
    /* struct dql (align) */

It seems that people want to add control path fields after
the read only fields. struct dql looks pretty innocent
but it forces its own alignment and nothing indicates that
there is a lot of empty space above it.

Move dql above the xmit_lock. This shifts the empty space
to the end of the struct rather than in the middle of it.
Move two example fields there to set an example.
Hopefully people will now add new fields at the end of
the struct. A lot of the read-only stuff is also control
path-only, but if we move it all we'll have another hole
in the middle.

Before:
	/* size: 384, cachelines: 6, members: 16 */
	/* sum members: 284, holes: 3, sum holes: 100 */

After:
        /* size: 320, cachelines: 5, members: 16 */
        /* sum members: 284, holes: 1, sum holes: 8 */

Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240820205119.1321322-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0ef3eaa23f4b..614ec5d3d75b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -644,9 +644,6 @@ struct netdev_queue {
 	struct Qdisc __rcu	*qdisc_sleeping;
 #ifdef CONFIG_SYSFS
 	struct kobject		kobj;
-#endif
-#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
-	int			numa_node;
 #endif
 	unsigned long		tx_maxrate;
 	/*
@@ -660,13 +657,13 @@ struct netdev_queue {
 #ifdef CONFIG_XDP_SOCKETS
 	struct xsk_buff_pool    *pool;
 #endif
-	/* NAPI instance for the queue
-	 * Readers and writers must hold RTNL
-	 */
-	struct napi_struct      *napi;
+
 /*
  * write-mostly part
  */
+#ifdef CONFIG_BQL
+	struct dql		dql;
+#endif
 	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
 	int			xmit_lock_owner;
 	/*
@@ -676,8 +673,16 @@ struct netdev_queue {
 
 	unsigned long		state;
 
-#ifdef CONFIG_BQL
-	struct dql		dql;
+/*
+ * slow- / control-path part
+ */
+	/* NAPI instance for the queue
+	 * Readers and writers must hold RTNL
+	 */
+	struct napi_struct	*napi;
+
+#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
+	int			numa_node;
 #endif
 } ____cacheline_aligned_in_smp;
 
-- 
cgit v1.3-3-g829e


From d70e3788da1d335449ba91dd46f7c3e16b01aaae Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Tue, 20 Aug 2024 13:53:41 -0400
Subject: net: xilinx: axienet: Report RxRject as rx_dropped

The Receive Frame Rejected interrupt is asserted whenever there was a
receive error (bad FCS, bad length, etc.) or whenever the frame was
dropped due to a mismatched address. So this is really a combination of
rx_otherhost_dropped, rx_length_errors, rx_frame_errors, and
rx_crc_errors. Mismatched addresses are common and aren't really errors
at all (much like how fragments are normal on half-duplex links). To
avoid confusion, report these events as rx_dropped. This better
reflects what's going on: the packet was received by the MAC but dropped
before being processed.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Link: https://patch.msgid.link/20240820175343.760389-2-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index ca04c298daa2..b2d7c396e2e3 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1296,7 +1296,7 @@ static irqreturn_t axienet_eth_irq(int irq, void *_ndev)
 		ndev->stats.rx_missed_errors++;
 
 	if (pending & XAE_INT_RXRJECT_MASK)
-		ndev->stats.rx_frame_errors++;
+		ndev->stats.rx_dropped++;
 
 	axienet_iow(lp, XAE_IS_OFFSET, pending);
 	return IRQ_HANDLED;
-- 
cgit v1.3-3-g829e


From 76abb5d675c49baa0bc899c6ef8b49197ac914b8 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Tue, 20 Aug 2024 13:53:42 -0400
Subject: net: xilinx: axienet: Add statistics support

Add support for reading the statistics counters, if they are enabled.
The counters may be 64-bit, but we can't detect this statically as
there's no ability bit for it and the counters are read-only. Therefore,
we assume the counters are 32-bits by default. To ensure we don't miss
an overflow, we read all counters at 13-second intervals. This should be
often enough to ensure the bytes counters don't wrap at 2.5 Gbit/s.

Another complication is that the counters may be reset when the device
is reset (depending on configuration). To ensure the counters persist
across link up/down (including suspend/resume), we maintain our own
versions along with the last counter value we saw. Because we might wait
up to 100 ms for the reset to complete, we use a mutex to protect
writing hw_stats. We can't sleep in ndo_get_stats64, so we use a seqlock
to protect readers.

We don't bother disabling the refresh work when we detect 64-bit
counters. This is because the reset issue requires us to read
hw_stat_base and reset_in_progress anyway, which would still require the
seqcount. And I don't think skipping the task is worth the extra
bookkeeping.

We can't use the byte counters for either get_stats64 or
get_eth_mac_stats. This is because the byte counters include everything
in the frame (destination address to FCS, inclusive). But
rtnl_link_stats64 wants bytes excluding the FCS, and
ethtool_eth_mac_stats wants to exclude the L2 overhead (addresses and
length/type). It might be possible to calculate the byte values Linux
expects based on the frame counters, but I think it is simpler to use
the existing software counters.

get_ethtool_stats is implemented for nonstandard statistics. This
includes the aforementioned byte counters, VLAN and PFC frame
counters, and user-defined (e.g. with custom RTL) counters.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20240820175343.760389-3-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h      |  85 ++++++
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 325 +++++++++++++++++++++-
 2 files changed, 407 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index ea4103a635f9..8165f5f271ff 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -156,6 +156,7 @@
 #define XAE_TPID0_OFFSET	0x00000028 /* VLAN TPID0 register */
 #define XAE_TPID1_OFFSET	0x0000002C /* VLAN TPID1 register */
 #define XAE_PPST_OFFSET		0x00000030 /* PCS PMA Soft Temac Status Reg */
+#define XAE_STATS_OFFSET	0x00000200 /* Statistics counters */
 #define XAE_RCW0_OFFSET		0x00000400 /* Rx Configuration Word 0 */
 #define XAE_RCW1_OFFSET		0x00000404 /* Rx Configuration Word 1 */
 #define XAE_TC_OFFSET		0x00000408 /* Tx Configuration */
@@ -163,6 +164,7 @@
 #define XAE_EMMC_OFFSET		0x00000410 /* MAC speed configuration */
 #define XAE_PHYC_OFFSET		0x00000414 /* RX Max Frame Configuration */
 #define XAE_ID_OFFSET		0x000004F8 /* Identification register */
+#define XAE_ABILITY_OFFSET	0x000004FC /* Ability Register offset */
 #define XAE_MDIO_MC_OFFSET	0x00000500 /* MDIO Setup */
 #define XAE_MDIO_MCR_OFFSET	0x00000504 /* MDIO Control */
 #define XAE_MDIO_MWD_OFFSET	0x00000508 /* MDIO Write Data */
@@ -283,6 +285,16 @@
 #define XAE_PHYC_SGLINKSPD_100		0x40000000 /* SGMII link 100 Mbit */
 #define XAE_PHYC_SGLINKSPD_1000		0x80000000 /* SGMII link 1000 Mbit */
 
+/* Bit masks for Axi Ethernet ability register */
+#define XAE_ABILITY_PFC			BIT(16)
+#define XAE_ABILITY_FRAME_FILTER	BIT(10)
+#define XAE_ABILITY_HALF_DUPLEX		BIT(9)
+#define XAE_ABILITY_STATS		BIT(8)
+#define XAE_ABILITY_2_5G		BIT(3)
+#define XAE_ABILITY_1G			BIT(2)
+#define XAE_ABILITY_100M		BIT(1)
+#define XAE_ABILITY_10M			BIT(0)
+
 /* Bit masks for Axi Ethernet MDIO interface MC register */
 #define XAE_MDIO_MC_MDIOEN_MASK		0x00000040 /* MII management enable */
 #define XAE_MDIO_MC_CLOCK_DIVIDE_MAX	0x3F	   /* Maximum MDIO divisor */
@@ -331,6 +343,7 @@
 #define XAE_FEATURE_FULL_RX_CSUM	BIT(2)
 #define XAE_FEATURE_FULL_TX_CSUM	BIT(3)
 #define XAE_FEATURE_DMA_64BIT		BIT(4)
+#define XAE_FEATURE_STATS		BIT(5)
 
 #define XAE_NO_CSUM_OFFLOAD		0
 
@@ -344,6 +357,61 @@
 #define XLNX_MII_STD_SELECT_REG		0x11
 #define XLNX_MII_STD_SELECT_SGMII	BIT(0)
 
+/* enum temac_stat - TEMAC statistics counters
+ *
+ * Index of statistics counters within the TEMAC. This must match the
+ * order/offset of hardware registers exactly.
+ */
+enum temac_stat {
+	STAT_RX_BYTES = 0,
+	STAT_TX_BYTES,
+	STAT_UNDERSIZE_FRAMES,
+	STAT_FRAGMENT_FRAMES,
+	STAT_RX_64_BYTE_FRAMES,
+	STAT_RX_65_127_BYTE_FRAMES,
+	STAT_RX_128_255_BYTE_FRAMES,
+	STAT_RX_256_511_BYTE_FRAMES,
+	STAT_RX_512_1023_BYTE_FRAMES,
+	STAT_RX_1024_MAX_BYTE_FRAMES,
+	STAT_RX_OVERSIZE_FRAMES,
+	STAT_TX_64_BYTE_FRAMES,
+	STAT_TX_65_127_BYTE_FRAMES,
+	STAT_TX_128_255_BYTE_FRAMES,
+	STAT_TX_256_511_BYTE_FRAMES,
+	STAT_TX_512_1023_BYTE_FRAMES,
+	STAT_TX_1024_MAX_BYTE_FRAMES,
+	STAT_TX_OVERSIZE_FRAMES,
+	STAT_RX_GOOD_FRAMES,
+	STAT_RX_FCS_ERRORS,
+	STAT_RX_BROADCAST_FRAMES,
+	STAT_RX_MULTICAST_FRAMES,
+	STAT_RX_CONTROL_FRAMES,
+	STAT_RX_LENGTH_ERRORS,
+	STAT_RX_VLAN_FRAMES,
+	STAT_RX_PAUSE_FRAMES,
+	STAT_RX_CONTROL_OPCODE_ERRORS,
+	STAT_TX_GOOD_FRAMES,
+	STAT_TX_BROADCAST_FRAMES,
+	STAT_TX_MULTICAST_FRAMES,
+	STAT_TX_UNDERRUN_ERRORS,
+	STAT_TX_CONTROL_FRAMES,
+	STAT_TX_VLAN_FRAMES,
+	STAT_TX_PAUSE_FRAMES,
+	STAT_TX_SINGLE_COLLISION_FRAMES,
+	STAT_TX_MULTIPLE_COLLISION_FRAMES,
+	STAT_TX_DEFERRED_FRAMES,
+	STAT_TX_LATE_COLLISIONS,
+	STAT_TX_EXCESS_COLLISIONS,
+	STAT_TX_EXCESS_DEFERRAL,
+	STAT_RX_ALIGNMENT_ERRORS,
+	STAT_TX_PFC_FRAMES,
+	STAT_RX_PFC_FRAMES,
+	STAT_USER_DEFINED0,
+	STAT_USER_DEFINED1,
+	STAT_USER_DEFINED2,
+	STAT_COUNT,
+};
+
 /**
  * struct axidma_bd - Axi Dma buffer descriptor layout
  * @next:         MM2S/S2MM Next Descriptor Pointer
@@ -434,6 +502,16 @@ struct skbuf_dma_descriptor {
  * @tx_packets: TX packet count for statistics
  * @tx_bytes:	TX byte count for statistics
  * @tx_stat_sync: Synchronization object for TX stats
+ * @hw_stat_base: Base offset for statistics counters. This may be nonzero if
+ *                the statistics counteres were reset or wrapped around.
+ * @hw_last_counter: Last-seen value of each statistic counter
+ * @reset_in_progress: Set while we are performing a reset and statistics
+ *                     counters may be invalid
+ * @hw_stats_seqcount: Sequence counter for @hw_stat_base, @hw_last_counter,
+ *                     and @reset_in_progress.
+ * @stats_lock: Lock for @hw_stats_seqcount
+ * @stats_work: Work for reading the hardware statistics counters often enough
+ *              to catch overflows.
  * @dma_err_task: Work structure to process Axi DMA errors
  * @tx_irq:	Axidma TX IRQ number
  * @rx_irq:	Axidma RX IRQ number
@@ -505,6 +583,13 @@ struct axienet_local {
 	u64_stats_t tx_bytes;
 	struct u64_stats_sync tx_stat_sync;
 
+	u64 hw_stat_base[STAT_COUNT];
+	u32 hw_last_counter[STAT_COUNT];
+	seqcount_mutex_t hw_stats_seqcount;
+	struct mutex stats_lock;
+	struct delayed_work stats_work;
+	bool reset_in_progress;
+
 	struct work_struct dma_err_task;
 
 	int tx_irq;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index b2d7c396e2e3..38f7b764fe66 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -519,11 +519,55 @@ static void axienet_setoptions(struct net_device *ndev, u32 options)
 	lp->options |= options;
 }
 
+static u64 axienet_stat(struct axienet_local *lp, enum temac_stat stat)
+{
+	u32 counter;
+
+	if (lp->reset_in_progress)
+		return lp->hw_stat_base[stat];
+
+	counter = axienet_ior(lp, XAE_STATS_OFFSET + stat * 8);
+	return lp->hw_stat_base[stat] + (counter - lp->hw_last_counter[stat]);
+}
+
+static void axienet_stats_update(struct axienet_local *lp, bool reset)
+{
+	enum temac_stat stat;
+
+	write_seqcount_begin(&lp->hw_stats_seqcount);
+	lp->reset_in_progress = reset;
+	for (stat = 0; stat < STAT_COUNT; stat++) {
+		u32 counter = axienet_ior(lp, XAE_STATS_OFFSET + stat * 8);
+
+		lp->hw_stat_base[stat] += counter - lp->hw_last_counter[stat];
+		lp->hw_last_counter[stat] = counter;
+	}
+	write_seqcount_end(&lp->hw_stats_seqcount);
+}
+
+static void axienet_refresh_stats(struct work_struct *work)
+{
+	struct axienet_local *lp = container_of(work, struct axienet_local,
+						stats_work.work);
+
+	mutex_lock(&lp->stats_lock);
+	axienet_stats_update(lp, false);
+	mutex_unlock(&lp->stats_lock);
+
+	/* Just less than 2^32 bytes at 2.5 GBit/s */
+	schedule_delayed_work(&lp->stats_work, 13 * HZ);
+}
+
 static int __axienet_device_reset(struct axienet_local *lp)
 {
 	u32 value;
 	int ret;
 
+	/* Save statistics counters in case they will be reset */
+	mutex_lock(&lp->stats_lock);
+	if (lp->features & XAE_FEATURE_STATS)
+		axienet_stats_update(lp, true);
+
 	/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
 	 * process of Axi DMA takes a while to complete as all pending
 	 * commands/transfers will be flushed or completed during this
@@ -538,7 +582,7 @@ static int __axienet_device_reset(struct axienet_local *lp)
 				XAXIDMA_TX_CR_OFFSET);
 	if (ret) {
 		dev_err(lp->dev, "%s: DMA reset timeout!\n", __func__);
-		return ret;
+		goto out;
 	}
 
 	/* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */
@@ -548,10 +592,29 @@ static int __axienet_device_reset(struct axienet_local *lp)
 				XAE_IS_OFFSET);
 	if (ret) {
 		dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__);
-		return ret;
+		goto out;
 	}
 
-	return 0;
+	/* Update statistics counters with new values */
+	if (lp->features & XAE_FEATURE_STATS) {
+		enum temac_stat stat;
+
+		write_seqcount_begin(&lp->hw_stats_seqcount);
+		lp->reset_in_progress = false;
+		for (stat = 0; stat < STAT_COUNT; stat++) {
+			u32 counter =
+				axienet_ior(lp, XAE_STATS_OFFSET + stat * 8);
+
+			lp->hw_stat_base[stat] +=
+				lp->hw_last_counter[stat] - counter;
+			lp->hw_last_counter[stat] = counter;
+		}
+		write_seqcount_end(&lp->hw_stats_seqcount);
+	}
+
+out:
+	mutex_unlock(&lp->stats_lock);
+	return ret;
 }
 
 /**
@@ -1530,6 +1593,9 @@ static int axienet_open(struct net_device *ndev)
 
 	phylink_start(lp->phylink);
 
+	/* Start the statistics refresh work */
+	schedule_delayed_work(&lp->stats_work, 0);
+
 	if (lp->use_dmaengine) {
 		/* Enable interrupts for Axi Ethernet core (if defined) */
 		if (lp->eth_irq > 0) {
@@ -1554,6 +1620,7 @@ err_free_eth_irq:
 	if (lp->eth_irq > 0)
 		free_irq(lp->eth_irq, ndev);
 err_phy:
+	cancel_delayed_work_sync(&lp->stats_work);
 	phylink_stop(lp->phylink);
 	phylink_disconnect_phy(lp->phylink);
 	return ret;
@@ -1579,6 +1646,8 @@ static int axienet_stop(struct net_device *ndev)
 		napi_disable(&lp->napi_rx);
 	}
 
+	cancel_delayed_work_sync(&lp->stats_work);
+
 	phylink_stop(lp->phylink);
 	phylink_disconnect_phy(lp->phylink);
 
@@ -1692,6 +1761,35 @@ axienet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		stats->tx_packets = u64_stats_read(&lp->tx_packets);
 		stats->tx_bytes = u64_stats_read(&lp->tx_bytes);
 	} while (u64_stats_fetch_retry(&lp->tx_stat_sync, start));
+
+	if (!(lp->features & XAE_FEATURE_STATS))
+		return;
+
+	do {
+		start = read_seqcount_begin(&lp->hw_stats_seqcount);
+		stats->rx_length_errors =
+			axienet_stat(lp, STAT_RX_LENGTH_ERRORS);
+		stats->rx_crc_errors = axienet_stat(lp, STAT_RX_FCS_ERRORS);
+		stats->rx_frame_errors =
+			axienet_stat(lp, STAT_RX_ALIGNMENT_ERRORS);
+		stats->rx_errors = axienet_stat(lp, STAT_UNDERSIZE_FRAMES) +
+				   axienet_stat(lp, STAT_FRAGMENT_FRAMES) +
+				   stats->rx_length_errors +
+				   stats->rx_crc_errors +
+				   stats->rx_frame_errors;
+		stats->multicast = axienet_stat(lp, STAT_RX_MULTICAST_FRAMES);
+
+		stats->tx_aborted_errors =
+			axienet_stat(lp, STAT_TX_EXCESS_COLLISIONS);
+		stats->tx_fifo_errors =
+			axienet_stat(lp, STAT_TX_UNDERRUN_ERRORS);
+		stats->tx_window_errors =
+			axienet_stat(lp, STAT_TX_LATE_COLLISIONS);
+		stats->tx_errors = axienet_stat(lp, STAT_TX_EXCESS_DEFERRAL) +
+				   stats->tx_aborted_errors +
+				   stats->tx_fifo_errors +
+				   stats->tx_window_errors;
+	} while (read_seqcount_retry(&lp->hw_stats_seqcount, start));
 }
 
 static const struct net_device_ops axienet_netdev_ops = {
@@ -1984,6 +2082,213 @@ static int axienet_ethtools_nway_reset(struct net_device *dev)
 	return phylink_ethtool_nway_reset(lp->phylink);
 }
 
+static void axienet_ethtools_get_ethtool_stats(struct net_device *dev,
+					       struct ethtool_stats *stats,
+					       u64 *data)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+	unsigned int start;
+
+	do {
+		start = read_seqcount_begin(&lp->hw_stats_seqcount);
+		data[0] = axienet_stat(lp, STAT_RX_BYTES);
+		data[1] = axienet_stat(lp, STAT_TX_BYTES);
+		data[2] = axienet_stat(lp, STAT_RX_VLAN_FRAMES);
+		data[3] = axienet_stat(lp, STAT_TX_VLAN_FRAMES);
+		data[6] = axienet_stat(lp, STAT_TX_PFC_FRAMES);
+		data[7] = axienet_stat(lp, STAT_RX_PFC_FRAMES);
+		data[8] = axienet_stat(lp, STAT_USER_DEFINED0);
+		data[9] = axienet_stat(lp, STAT_USER_DEFINED1);
+		data[10] = axienet_stat(lp, STAT_USER_DEFINED2);
+	} while (read_seqcount_retry(&lp->hw_stats_seqcount, start));
+}
+
+static const char axienet_ethtool_stats_strings[][ETH_GSTRING_LEN] = {
+	"Received bytes",
+	"Transmitted bytes",
+	"RX Good VLAN Tagged Frames",
+	"TX Good VLAN Tagged Frames",
+	"TX Good PFC Frames",
+	"RX Good PFC Frames",
+	"User Defined Counter 0",
+	"User Defined Counter 1",
+	"User Defined Counter 2",
+};
+
+static void axienet_ethtools_get_strings(struct net_device *dev, u32 stringset, u8 *data)
+{
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(data, axienet_ethtool_stats_strings,
+		       sizeof(axienet_ethtool_stats_strings));
+		break;
+	}
+}
+
+static int axienet_ethtools_get_sset_count(struct net_device *dev, int sset)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		if (lp->features & XAE_FEATURE_STATS)
+			return ARRAY_SIZE(axienet_ethtool_stats_strings);
+		fallthrough;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void
+axienet_ethtools_get_pause_stats(struct net_device *dev,
+				 struct ethtool_pause_stats *pause_stats)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+	unsigned int start;
+
+	if (!(lp->features & XAE_FEATURE_STATS))
+		return;
+
+	do {
+		start = read_seqcount_begin(&lp->hw_stats_seqcount);
+		pause_stats->tx_pause_frames =
+			axienet_stat(lp, STAT_TX_PAUSE_FRAMES);
+		pause_stats->rx_pause_frames =
+			axienet_stat(lp, STAT_RX_PAUSE_FRAMES);
+	} while (read_seqcount_retry(&lp->hw_stats_seqcount, start));
+}
+
+static void
+axienet_ethtool_get_eth_mac_stats(struct net_device *dev,
+				  struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+	unsigned int start;
+
+	if (!(lp->features & XAE_FEATURE_STATS))
+		return;
+
+	do {
+		start = read_seqcount_begin(&lp->hw_stats_seqcount);
+		mac_stats->FramesTransmittedOK =
+			axienet_stat(lp, STAT_TX_GOOD_FRAMES);
+		mac_stats->SingleCollisionFrames =
+			axienet_stat(lp, STAT_TX_SINGLE_COLLISION_FRAMES);
+		mac_stats->MultipleCollisionFrames =
+			axienet_stat(lp, STAT_TX_MULTIPLE_COLLISION_FRAMES);
+		mac_stats->FramesReceivedOK =
+			axienet_stat(lp, STAT_RX_GOOD_FRAMES);
+		mac_stats->FrameCheckSequenceErrors =
+			axienet_stat(lp, STAT_RX_FCS_ERRORS);
+		mac_stats->AlignmentErrors =
+			axienet_stat(lp, STAT_RX_ALIGNMENT_ERRORS);
+		mac_stats->FramesWithDeferredXmissions =
+			axienet_stat(lp, STAT_TX_DEFERRED_FRAMES);
+		mac_stats->LateCollisions =
+			axienet_stat(lp, STAT_TX_LATE_COLLISIONS);
+		mac_stats->FramesAbortedDueToXSColls =
+			axienet_stat(lp, STAT_TX_EXCESS_COLLISIONS);
+		mac_stats->MulticastFramesXmittedOK =
+			axienet_stat(lp, STAT_TX_MULTICAST_FRAMES);
+		mac_stats->BroadcastFramesXmittedOK =
+			axienet_stat(lp, STAT_TX_BROADCAST_FRAMES);
+		mac_stats->FramesWithExcessiveDeferral =
+			axienet_stat(lp, STAT_TX_EXCESS_DEFERRAL);
+		mac_stats->MulticastFramesReceivedOK =
+			axienet_stat(lp, STAT_RX_MULTICAST_FRAMES);
+		mac_stats->BroadcastFramesReceivedOK =
+			axienet_stat(lp, STAT_RX_BROADCAST_FRAMES);
+		mac_stats->InRangeLengthErrors =
+			axienet_stat(lp, STAT_RX_LENGTH_ERRORS);
+	} while (read_seqcount_retry(&lp->hw_stats_seqcount, start));
+}
+
+static void
+axienet_ethtool_get_eth_ctrl_stats(struct net_device *dev,
+				   struct ethtool_eth_ctrl_stats *ctrl_stats)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+	unsigned int start;
+
+	if (!(lp->features & XAE_FEATURE_STATS))
+		return;
+
+	do {
+		start = read_seqcount_begin(&lp->hw_stats_seqcount);
+		ctrl_stats->MACControlFramesTransmitted =
+			axienet_stat(lp, STAT_TX_CONTROL_FRAMES);
+		ctrl_stats->MACControlFramesReceived =
+			axienet_stat(lp, STAT_RX_CONTROL_FRAMES);
+		ctrl_stats->UnsupportedOpcodesReceived =
+			axienet_stat(lp, STAT_RX_CONTROL_OPCODE_ERRORS);
+	} while (read_seqcount_retry(&lp->hw_stats_seqcount, start));
+}
+
+static const struct ethtool_rmon_hist_range axienet_rmon_ranges[] = {
+	{   64,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519, 16384 },
+	{ },
+};
+
+static void
+axienet_ethtool_get_rmon_stats(struct net_device *dev,
+			       struct ethtool_rmon_stats *rmon_stats,
+			       const struct ethtool_rmon_hist_range **ranges)
+{
+	struct axienet_local *lp = netdev_priv(dev);
+	unsigned int start;
+
+	if (!(lp->features & XAE_FEATURE_STATS))
+		return;
+
+	do {
+		start = read_seqcount_begin(&lp->hw_stats_seqcount);
+		rmon_stats->undersize_pkts =
+			axienet_stat(lp, STAT_UNDERSIZE_FRAMES);
+		rmon_stats->oversize_pkts =
+			axienet_stat(lp, STAT_RX_OVERSIZE_FRAMES);
+		rmon_stats->fragments =
+			axienet_stat(lp, STAT_FRAGMENT_FRAMES);
+
+		rmon_stats->hist[0] =
+			axienet_stat(lp, STAT_RX_64_BYTE_FRAMES);
+		rmon_stats->hist[1] =
+			axienet_stat(lp, STAT_RX_65_127_BYTE_FRAMES);
+		rmon_stats->hist[2] =
+			axienet_stat(lp, STAT_RX_128_255_BYTE_FRAMES);
+		rmon_stats->hist[3] =
+			axienet_stat(lp, STAT_RX_256_511_BYTE_FRAMES);
+		rmon_stats->hist[4] =
+			axienet_stat(lp, STAT_RX_512_1023_BYTE_FRAMES);
+		rmon_stats->hist[5] =
+			axienet_stat(lp, STAT_RX_1024_MAX_BYTE_FRAMES);
+		rmon_stats->hist[6] =
+			rmon_stats->oversize_pkts;
+
+		rmon_stats->hist_tx[0] =
+			axienet_stat(lp, STAT_TX_64_BYTE_FRAMES);
+		rmon_stats->hist_tx[1] =
+			axienet_stat(lp, STAT_TX_65_127_BYTE_FRAMES);
+		rmon_stats->hist_tx[2] =
+			axienet_stat(lp, STAT_TX_128_255_BYTE_FRAMES);
+		rmon_stats->hist_tx[3] =
+			axienet_stat(lp, STAT_TX_256_511_BYTE_FRAMES);
+		rmon_stats->hist_tx[4] =
+			axienet_stat(lp, STAT_TX_512_1023_BYTE_FRAMES);
+		rmon_stats->hist_tx[5] =
+			axienet_stat(lp, STAT_TX_1024_MAX_BYTE_FRAMES);
+		rmon_stats->hist_tx[6] =
+			axienet_stat(lp, STAT_TX_OVERSIZE_FRAMES);
+	} while (read_seqcount_retry(&lp->hw_stats_seqcount, start));
+
+	*ranges = axienet_rmon_ranges;
+}
+
 static const struct ethtool_ops axienet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USECS,
@@ -2000,6 +2305,13 @@ static const struct ethtool_ops axienet_ethtool_ops = {
 	.get_link_ksettings = axienet_ethtools_get_link_ksettings,
 	.set_link_ksettings = axienet_ethtools_set_link_ksettings,
 	.nway_reset	= axienet_ethtools_nway_reset,
+	.get_ethtool_stats = axienet_ethtools_get_ethtool_stats,
+	.get_strings    = axienet_ethtools_get_strings,
+	.get_sset_count = axienet_ethtools_get_sset_count,
+	.get_pause_stats = axienet_ethtools_get_pause_stats,
+	.get_eth_mac_stats = axienet_ethtool_get_eth_mac_stats,
+	.get_eth_ctrl_stats = axienet_ethtool_get_eth_ctrl_stats,
+	.get_rmon_stats = axienet_ethtool_get_rmon_stats,
 };
 
 static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs)
@@ -2268,6 +2580,10 @@ static int axienet_probe(struct platform_device *pdev)
 	u64_stats_init(&lp->rx_stat_sync);
 	u64_stats_init(&lp->tx_stat_sync);
 
+	mutex_init(&lp->stats_lock);
+	seqcount_mutex_init(&lp->hw_stats_seqcount, &lp->stats_lock);
+	INIT_DEFERRABLE_WORK(&lp->stats_work, axienet_refresh_stats);
+
 	lp->axi_clk = devm_clk_get_optional(&pdev->dev, "s_axi_lite_clk");
 	if (!lp->axi_clk) {
 		/* For backward compatibility, if named AXI clock is not present,
@@ -2308,6 +2624,9 @@ static int axienet_probe(struct platform_device *pdev)
 	/* Setup checksum offload, but default to off if not specified */
 	lp->features = 0;
 
+	if (axienet_ior(lp, XAE_ABILITY_OFFSET) & XAE_ABILITY_STATS)
+		lp->features |= XAE_FEATURE_STATS;
+
 	ret = of_property_read_u32(pdev->dev.of_node, "xlnx,txcsum", &value);
 	if (!ret) {
 		switch (value) {
-- 
cgit v1.3-3-g829e


From f32c821ae0198cf43181711efb18376b2eb6a1cb Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 20 Aug 2024 17:12:22 +0200
Subject: tools: ynl: lift an assumption about spec file name

Currently the parsing code generator assumes that the yaml
specification file name and the main 'name' attribute carried
inside correspond, that is the field is the c-name representation
of the file basename.

The above assumption held true within the current tree, but will be
hopefully broken soon by the upcoming net shaper specification.
Additionally, it makes the field 'name' itself useless.

Lift the assumption, always computing the generated include file
name from the generated c file name.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Link: https://patch.msgid.link/24da5a3596d814beeb12bd7139a6b4f89756cc19.1724165948.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/ynl-gen-c.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py
index 51529fabd517..717530bc9c52 100755
--- a/tools/net/ynl/ynl-gen-c.py
+++ b/tools/net/ynl/ynl-gen-c.py
@@ -2668,13 +2668,15 @@ def main():
         cw.p('#define ' + hdr_prot)
         cw.nl()
 
+    hdr_file=os.path.basename(args.out_file[:-2]) + ".h"
+
     if args.mode == 'kernel':
         cw.p('#include <net/netlink.h>')
         cw.p('#include <net/genetlink.h>')
         cw.nl()
         if not args.header:
             if args.out_file:
-                cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"')
+                cw.p(f'#include "{hdr_file}"')
             cw.nl()
         headers = ['uapi/' + parsed.uapi_header]
         headers += parsed.kernel_family.get('headers', [])
@@ -2686,7 +2688,7 @@ def main():
             if family_contains_bitfield32(parsed):
                 cw.p('#include <linux/netlink.h>')
         else:
-            cw.p(f'#include "{parsed.name}-user.h"')
+            cw.p(f'#include "{hdr_file}"')
             cw.p('#include "ynl.h"')
         headers = [parsed.uapi_header]
     for definition in parsed['definitions']:
-- 
cgit v1.3-3-g829e


From a3f00afc250aac2a4ed04828b9ec27278aebfe46 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 16 Aug 2024 19:57:00 +0800
Subject: wifi: rtw89: debugfs: support multiple adapters debugging

The rtw89 uses debugfs to access registers and driver states. To get
a range of registers, the range value is set and stored to a variable, and
get the set of register values by the stored range. However, the variable
is a static global variable, which multiple adapters will be a problem,
so move the variable to adapter context rtw89_dev.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240816115700.17390-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c  |   2 +
 drivers/net/wireless/realtek/rtw89/core.h  |   3 +
 drivers/net/wireless/realtek/rtw89/debug.c | 180 +++++++++++++++--------------
 drivers/net/wireless/realtek/rtw89/debug.h |   2 +
 4 files changed, 100 insertions(+), 87 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 7b28f2c2a08e..885c759e694a 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4767,6 +4767,8 @@ EXPORT_SYMBOL(rtw89_core_register);
 void rtw89_core_unregister(struct rtw89_dev *rtwdev)
 {
 	rtw89_core_unregister_hw(rtwdev);
+
+	rtw89_debugfs_deinit(rtwdev);
 }
 EXPORT_SYMBOL(rtw89_core_unregister);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 3edb2f4372e4..c4702882367e 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -21,6 +21,7 @@ struct rtw89_efuse_block_cfg;
 struct rtw89_h2c_rf_tssi;
 struct rtw89_fw_txpwr_track_cfg;
 struct rtw89_phy_rfk_log_fmt;
+struct rtw89_debugfs;
 
 extern const struct ieee80211_ops rtw89_ops;
 
@@ -5529,6 +5530,8 @@ struct rtw89_dev {
 	struct napi_struct napi;
 	int napi_budget_countdown;
 
+	struct rtw89_debugfs *debugfs;
+
 	/* HCI related data, keep last */
 	u8 priv[] __aligned(sizeof(void *));
 };
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index bb65b814585a..29f85210f919 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -52,6 +52,27 @@ struct rtw89_debugfs_priv {
 	};
 };
 
+struct rtw89_debugfs {
+	struct rtw89_debugfs_priv read_reg;
+	struct rtw89_debugfs_priv write_reg;
+	struct rtw89_debugfs_priv read_rf;
+	struct rtw89_debugfs_priv write_rf;
+	struct rtw89_debugfs_priv rf_reg_dump;
+	struct rtw89_debugfs_priv txpwr_table;
+	struct rtw89_debugfs_priv mac_reg_dump;
+	struct rtw89_debugfs_priv mac_mem_dump;
+	struct rtw89_debugfs_priv mac_dbg_port_dump;
+	struct rtw89_debugfs_priv send_h2c;
+	struct rtw89_debugfs_priv early_h2c;
+	struct rtw89_debugfs_priv fw_crash;
+	struct rtw89_debugfs_priv btc_info;
+	struct rtw89_debugfs_priv btc_manual;
+	struct rtw89_debugfs_priv fw_log_manual;
+	struct rtw89_debugfs_priv phy_info;
+	struct rtw89_debugfs_priv stations;
+	struct rtw89_debugfs_priv disable_dm;
+};
+
 static const u16 rtw89_rate_info_bw_to_mhz_map[] = {
 	[RATE_INFO_BW_20] = 20,
 	[RATE_INFO_BW_40] = 40,
@@ -3463,9 +3484,9 @@ static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp,
 	return count;
 }
 
-static ssize_t rtw89_debug_fw_log_manual_set(struct file *filp,
-					     const char __user *user_buf,
-					     size_t count, loff_t *loff)
+static ssize_t rtw89_debug_priv_fw_log_manual_set(struct file *filp,
+						  const char __user *user_buf,
+						  size_t count, loff_t *loff)
 {
 	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
@@ -3854,92 +3875,55 @@ rtw89_debug_priv_disable_dm_set(struct file *filp, const char __user *user_buf,
 	return count;
 }
 
-static struct rtw89_debugfs_priv rtw89_debug_priv_read_reg = {
-	.cb_read = rtw89_debug_priv_read_reg_get,
-	.cb_write = rtw89_debug_priv_read_reg_select,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_write_reg = {
-	.cb_write = rtw89_debug_priv_write_reg_set,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_read_rf = {
-	.cb_read = rtw89_debug_priv_read_rf_get,
-	.cb_write = rtw89_debug_priv_read_rf_select,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_write_rf = {
-	.cb_write = rtw89_debug_priv_write_rf_set,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_rf_reg_dump = {
-	.cb_read = rtw89_debug_priv_rf_reg_dump_get,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_txpwr_table = {
-	.cb_read = rtw89_debug_priv_txpwr_table_get,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_mac_reg_dump = {
-	.cb_read = rtw89_debug_priv_mac_reg_dump_get,
-	.cb_write = rtw89_debug_priv_mac_reg_dump_select,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_mac_mem_dump = {
-	.cb_read = rtw89_debug_priv_mac_mem_dump_get,
-	.cb_write = rtw89_debug_priv_mac_mem_dump_select,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_mac_dbg_port_dump = {
-	.cb_read = rtw89_debug_priv_mac_dbg_port_dump_get,
-	.cb_write = rtw89_debug_priv_mac_dbg_port_dump_select,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_send_h2c = {
-	.cb_write = rtw89_debug_priv_send_h2c_set,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_early_h2c = {
-	.cb_read = rtw89_debug_priv_early_h2c_get,
-	.cb_write = rtw89_debug_priv_early_h2c_set,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_fw_crash = {
-	.cb_read = rtw89_debug_priv_fw_crash_get,
-	.cb_write = rtw89_debug_priv_fw_crash_set,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_btc_info = {
-	.cb_read = rtw89_debug_priv_btc_info_get,
-};
-
-static struct rtw89_debugfs_priv rtw89_debug_priv_btc_manual = {
-	.cb_write = rtw89_debug_priv_btc_manual_set,
-};
+#define rtw89_debug_priv_get(name)				\
+{								\
+	.cb_read = rtw89_debug_priv_ ##name## _get,		\
+}
 
-static struct rtw89_debugfs_priv rtw89_debug_priv_fw_log_manual = {
-	.cb_write = rtw89_debug_fw_log_manual_set,
-};
+#define rtw89_debug_priv_set(name)				\
+{								\
+	.cb_write = rtw89_debug_priv_ ##name## _set,		\
+}
 
-static struct rtw89_debugfs_priv rtw89_debug_priv_phy_info = {
-	.cb_read = rtw89_debug_priv_phy_info_get,
-};
+#define rtw89_debug_priv_select_and_get(name)			\
+{								\
+	.cb_write = rtw89_debug_priv_ ##name## _select,		\
+	.cb_read = rtw89_debug_priv_ ##name## _get,		\
+}
 
-static struct rtw89_debugfs_priv rtw89_debug_priv_stations = {
-	.cb_read = rtw89_debug_priv_stations_get,
-};
+#define rtw89_debug_priv_set_and_get(name)			\
+{								\
+	.cb_write = rtw89_debug_priv_ ##name## _set,		\
+	.cb_read = rtw89_debug_priv_ ##name## _get,		\
+}
 
-static struct rtw89_debugfs_priv rtw89_debug_priv_disable_dm = {
-	.cb_read = rtw89_debug_priv_disable_dm_get,
-	.cb_write = rtw89_debug_priv_disable_dm_set,
+static const struct rtw89_debugfs rtw89_debugfs_templ = {
+	.read_reg = rtw89_debug_priv_select_and_get(read_reg),
+	.write_reg = rtw89_debug_priv_set(write_reg),
+	.read_rf = rtw89_debug_priv_select_and_get(read_rf),
+	.write_rf = rtw89_debug_priv_set(write_rf),
+	.rf_reg_dump = rtw89_debug_priv_get(rf_reg_dump),
+	.txpwr_table = rtw89_debug_priv_get(txpwr_table),
+	.mac_reg_dump = rtw89_debug_priv_select_and_get(mac_reg_dump),
+	.mac_mem_dump = rtw89_debug_priv_select_and_get(mac_mem_dump),
+	.mac_dbg_port_dump = rtw89_debug_priv_select_and_get(mac_dbg_port_dump),
+	.send_h2c = rtw89_debug_priv_set(send_h2c),
+	.early_h2c = rtw89_debug_priv_set_and_get(early_h2c),
+	.fw_crash = rtw89_debug_priv_set_and_get(fw_crash),
+	.btc_info = rtw89_debug_priv_get(btc_info),
+	.btc_manual = rtw89_debug_priv_set(btc_manual),
+	.fw_log_manual = rtw89_debug_priv_set(fw_log_manual),
+	.phy_info = rtw89_debug_priv_get(phy_info),
+	.stations = rtw89_debug_priv_get(stations),
+	.disable_dm = rtw89_debug_priv_set_and_get(disable_dm),
 };
 
 #define rtw89_debugfs_add(name, mode, fopname, parent)				\
 	do {									\
-		rtw89_debug_priv_ ##name.rtwdev = rtwdev;			\
-		if (!debugfs_create_file(#name, mode,				\
-					 parent, &rtw89_debug_priv_ ##name,	\
-					 &file_ops_ ##fopname))			\
+		struct rtw89_debugfs_priv *priv = &rtwdev->debugfs->name;	\
+		priv->rtwdev = rtwdev;						\
+		if (IS_ERR(debugfs_create_file(#name, mode, parent, priv,	\
+					       &file_ops_ ##fopname)))		\
 			pr_debug("Unable to initialize debugfs:%s\n", #name);	\
 	} while (0)
 
@@ -3950,13 +3934,9 @@ static struct rtw89_debugfs_priv rtw89_debug_priv_disable_dm = {
 #define rtw89_debugfs_add_r(name)						\
 	rtw89_debugfs_add(name, S_IFREG | 0444, single_r, debugfs_topdir)
 
-void rtw89_debugfs_init(struct rtw89_dev *rtwdev)
+static
+void rtw89_debugfs_add_sec0(struct rtw89_dev *rtwdev, struct dentry *debugfs_topdir)
 {
-	struct dentry *debugfs_topdir;
-
-	debugfs_topdir = debugfs_create_dir("rtw89",
-					    rtwdev->hw->wiphy->debugfsdir);
-
 	rtw89_debugfs_add_rw(read_reg);
 	rtw89_debugfs_add_w(write_reg);
 	rtw89_debugfs_add_rw(read_rf);
@@ -3966,6 +3946,11 @@ void rtw89_debugfs_init(struct rtw89_dev *rtwdev)
 	rtw89_debugfs_add_rw(mac_reg_dump);
 	rtw89_debugfs_add_rw(mac_mem_dump);
 	rtw89_debugfs_add_rw(mac_dbg_port_dump);
+}
+
+static
+void rtw89_debugfs_add_sec1(struct rtw89_dev *rtwdev, struct dentry *debugfs_topdir)
+{
 	rtw89_debugfs_add_w(send_h2c);
 	rtw89_debugfs_add_rw(early_h2c);
 	rtw89_debugfs_add_rw(fw_crash);
@@ -3976,6 +3961,27 @@ void rtw89_debugfs_init(struct rtw89_dev *rtwdev)
 	rtw89_debugfs_add_r(stations);
 	rtw89_debugfs_add_rw(disable_dm);
 }
+
+void rtw89_debugfs_init(struct rtw89_dev *rtwdev)
+{
+	struct dentry *debugfs_topdir;
+
+	rtwdev->debugfs = kmemdup(&rtw89_debugfs_templ,
+				  sizeof(rtw89_debugfs_templ), GFP_KERNEL);
+	if (!rtwdev->debugfs)
+		return;
+
+	debugfs_topdir = debugfs_create_dir("rtw89",
+					    rtwdev->hw->wiphy->debugfsdir);
+
+	rtw89_debugfs_add_sec0(rtwdev, debugfs_topdir);
+	rtw89_debugfs_add_sec1(rtwdev, debugfs_topdir);
+}
+
+void rtw89_debugfs_deinit(struct rtw89_dev *rtwdev)
+{
+	kfree(rtwdev->debugfs);
+}
 #endif
 
 #ifdef CONFIG_RTW89_DEBUGMSG
diff --git a/drivers/net/wireless/realtek/rtw89/debug.h b/drivers/net/wireless/realtek/rtw89/debug.h
index 800ea59873a1..fc690f7c55dc 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.h
+++ b/drivers/net/wireless/realtek/rtw89/debug.h
@@ -49,8 +49,10 @@ enum rtw89_debug_mac_reg_sel {
 
 #ifdef CONFIG_RTW89_DEBUGFS
 void rtw89_debugfs_init(struct rtw89_dev *rtwdev);
+void rtw89_debugfs_deinit(struct rtw89_dev *rtwdev);
 #else
 static inline void rtw89_debugfs_init(struct rtw89_dev *rtwdev) {}
+static inline void rtw89_debugfs_deinit(struct rtw89_dev *rtwdev) {}
 #endif
 
 #define rtw89_info(rtwdev, a...) dev_info((rtwdev)->dev, ##a)
-- 
cgit v1.3-3-g829e


From 124410976bf807e76c45e36685ed8bf959229545 Mon Sep 17 00:00:00 2001
From: Chia-Yuan Li <leo.li@realtek.com>
Date: Thu, 15 Aug 2024 21:40:54 +0800
Subject: wifi: rtw89: limit the PPDU length for VHT rate to 0x40000

If the PPDU length for VHT rate exceeds 0x40000, calculating the PSDU
length will overflow. TMAC will determine the length to be too small and
as a result, all packets will be sent as ZLD (Zero Length Delimiter).

Fixes: 5f7e92c59b8e ("wifi: rtw89: 8852b: set AMSDU limit to 5000")
Signed-off-by: Chia-Yuan Li <leo.li@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240815134054.44649-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac.c | 7 +++++++
 drivers/net/wireless/realtek/rtw89/reg.h | 4 ++++
 2 files changed, 11 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 89875f59d722..a661c176100c 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -2742,6 +2742,7 @@ bool rtw89_mac_is_qta_dbcc(struct rtw89_dev *rtwdev, enum rtw89_qta_mode mode)
 
 static int ptcl_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 {
+	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
 	u32 val, reg;
 	int ret;
 
@@ -2780,6 +2781,12 @@ static int ptcl_init_ax(struct rtw89_dev *rtwdev, u8 mac_idx)
 				  B_AX_SPE_RPT_PATH_MASK, FWD_TO_WLCPU);
 	}
 
+	if (chip_id == RTL8852A || rtw89_is_rtl885xb(rtwdev)) {
+		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_AGG_LEN_VHT_0, mac_idx);
+		rtw89_write32_mask(rtwdev, reg,
+				   B_AX_AMPDU_MAX_LEN_VHT_MASK, 0x3FF80);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index eacf9161db2c..69678eab2309 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -2506,6 +2506,10 @@
 #define B_AX_RTS_TXTIME_TH_MASK GENMASK(15, 8)
 #define B_AX_RTS_LEN_TH_MASK GENMASK(7, 0)
 
+#define R_AX_AGG_LEN_VHT_0 0xC618
+#define R_AX_AGG_LEN_VHT_0_C1 0xE618
+#define B_AX_AMPDU_MAX_LEN_VHT_MASK GENMASK(19, 0)
+
 #define S_AX_CTS2S_TH_SEC_256B 1
 #define R_AX_SIFS_SETTING 0xC624
 #define R_AX_SIFS_SETTING_C1 0xE624
-- 
cgit v1.3-3-g829e


From 2c29f70b3884fd69b5b246e78210a707354eb45e Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 16 Aug 2024 20:46:11 +0800
Subject: wifi: rtw89: coex: Update report version of Wi-Fi firmware 0.29.90.0
 for RTL8852BT

Add the firmware related version code for RTL8852BT version 0.29.90.0.
And add the version 7 report control structure format. Firmware will
collect counters like mailbox count, RF on/off count, and some Bluetooth
related counters into this structure and pass to driver periodically.
It will help to understand how the firmware mechanism working.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240816124614.25592-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 149 +++++++++++++++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/core.h |  14 +++
 2 files changed, 162 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index c1f6fcef904b..97e34287dfca 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -129,6 +129,13 @@ static const u32 cxtbl[] = {
 
 static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = {
 	/* firmware version must be in decreasing order for each chip */
+	{RTL8852BT, RTW89_FW_VER_CODE(0, 29, 90, 0),
+	 .fcxbtcrpt = 7, .fcxtdma = 7,    .fcxslots = 7, .fcxcysta = 7,
+	 .fcxstep = 7,   .fcxnullsta = 7, .fcxmreg = 7,  .fcxgpiodbg = 7,
+	 .fcxbtver = 7,  .fcxbtscan = 7,  .fcxbtafh = 7, .fcxbtdevinfo = 7,
+	 .fwlrole = 7,   .frptmap = 3,    .fcxctrl = 7,  .fcxinit = 7,
+	 .fwevntrptl = 1, .drvinfo_type = 1, .info_buf = 1800, .max_role_num = 6,
+	},
 	{RTL8922A, RTW89_FW_VER_CODE(0, 35, 8, 0),
 	 .fcxbtcrpt = 8, .fcxtdma = 7,    .fcxslots = 7, .fcxcysta = 7,
 	 .fcxstep = 7,   .fcxnullsta = 7, .fcxmreg = 7,  .fcxgpiodbg = 7,
@@ -1351,6 +1358,10 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			pfinfo = &pfwinfo->rpt_ctrl.finfo.v8;
 			pcinfo->req_len = sizeof(pfwinfo->rpt_ctrl.finfo.v8);
 			break;
+		} else if (ver->fcxbtcrpt == 7) {
+			pfinfo = &pfwinfo->rpt_ctrl.finfo.v7;
+			pcinfo->req_len = sizeof(pfwinfo->rpt_ctrl.finfo.v7);
+			break;
 		} else {
 			goto err;
 		}
@@ -1655,6 +1666,38 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 				     pfwinfo->event[BTF_EVNT_RPT]);
 
 			dm->error.map.bt_rfk_timeout = bt->rfk_info.map.timeout;
+		} else if (ver->fcxbtcrpt == 7) {
+			prpt->v7 = pfwinfo->rpt_ctrl.finfo.v7;
+			pfwinfo->rpt_en_map = le32_to_cpu(prpt->v7.rpt_info.en);
+			wl->ver_info.fw_coex = le32_to_cpu(prpt->v7.rpt_info.cx_ver);
+			wl->ver_info.fw = le32_to_cpu(prpt->v7.rpt_info.fw_ver);
+
+			for (i = RTW89_PHY_0; i < RTW89_PHY_MAX; i++)
+				memcpy(&dm->gnt.band[i], &prpt->v7.gnt_val[i][0],
+				       sizeof(dm->gnt.band[i]));
+
+			btc->cx.cnt_bt[BTC_BCNT_HIPRI_TX] =
+				le16_to_cpu(prpt->v7.bt_cnt[BTC_BCNT_HI_TX_V105]);
+			btc->cx.cnt_bt[BTC_BCNT_HIPRI_RX] =
+				le16_to_cpu(prpt->v7.bt_cnt[BTC_BCNT_HI_RX_V105]);
+			btc->cx.cnt_bt[BTC_BCNT_LOPRI_TX] =
+				le16_to_cpu(prpt->v7.bt_cnt[BTC_BCNT_LO_TX_V105]);
+			btc->cx.cnt_bt[BTC_BCNT_LOPRI_RX] =
+				le16_to_cpu(prpt->v7.bt_cnt[BTC_BCNT_LO_RX_V105]);
+
+			val1 = le16_to_cpu(prpt->v7.bt_cnt[BTC_BCNT_POLLUTED_V105]);
+			if (val1 > btc->cx.cnt_bt[BTC_BCNT_POLUT_NOW])
+				val1 -= btc->cx.cnt_bt[BTC_BCNT_POLUT_NOW]; /* diff */
+
+			btc->cx.cnt_bt[BTC_BCNT_POLUT_DIFF] = val1;
+			btc->cx.cnt_bt[BTC_BCNT_POLUT_NOW] =
+				le16_to_cpu(prpt->v7.bt_cnt[BTC_BCNT_POLLUTED_V105]);
+
+			val1 = pfwinfo->event[BTF_EVNT_RPT];
+			_chk_btc_err(rtwdev, BTC_DCNT_BTCNT_HANG, 0);
+			_chk_btc_err(rtwdev, BTC_DCNT_RPT_HANG, val1);
+			_chk_btc_err(rtwdev, BTC_DCNT_WL_FW_VER_MATCH, 0);
+			_chk_btc_err(rtwdev, BTC_DCNT_BTTX_HANG, 0);
 		} else if (ver->fcxbtcrpt == 8) {
 			prpt->v8 = pfwinfo->rpt_ctrl.finfo.v8;
 			pfwinfo->rpt_en_map = le32_to_cpu(prpt->v8.rpt_info.en);
@@ -2397,7 +2440,7 @@ static void rtw89_btc_fw_en_rpt(struct rtw89_dev *rtwdev,
 	if (val == fwinfo->rpt_en_map)
 		return;
 
-	if (btc->ver->fcxbtcrpt == 8) {
+	if (btc->ver->fcxbtcrpt == 7 || btc->ver->fcxbtcrpt == 8) {
 		r.v8.type = SET_REPORT_EN;
 		r.v8.fver = btc->ver->fcxbtcrpt;
 		r.v8.len = sizeof(r.v8.map);
@@ -10288,6 +10331,108 @@ static void _show_summary_v105(struct rtw89_dev *rtwdev, struct seq_file *m)
 		   cnt[BTC_NCNT_CUSTOMERIZE]);
 }
 
+static void _show_summary_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
+{
+	struct rtw89_btc_btf_fwinfo *pfwinfo = &rtwdev->btc.fwinfo;
+	struct rtw89_btc_fbtc_rpt_ctrl_v7 *prptctrl = NULL;
+	struct rtw89_btc_rpt_cmn_info *pcinfo = NULL;
+	struct rtw89_btc_cx *cx = &rtwdev->btc.cx;
+	struct rtw89_btc_dm *dm = &rtwdev->btc.dm;
+	struct rtw89_btc_wl_info *wl = &cx->wl;
+	u32 *cnt = rtwdev->btc.dm.cnt_notify;
+	u32 cnt_sum = 0;
+	u8 i;
+
+	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
+		return;
+
+	seq_printf(m, "%s", "\n\r========== [Statistics] ==========");
+
+	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
+	if (pcinfo->valid && wl->status.map.lps != BTC_LPS_RF_OFF &&
+	    !wl->status.map.rf_off) {
+		prptctrl = &pfwinfo->rpt_ctrl.finfo.v7;
+
+		seq_printf(m,
+			   "\n\r %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d),"
+			   "c2h_cnt=%d(fw_send:%d, len:%d, max:%d), ",
+			   "[summary]", pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
+			   le16_to_cpu(prptctrl->rpt_info.cnt_h2c), pfwinfo->cnt_c2h,
+			   le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
+			   le16_to_cpu(prptctrl->rpt_info.len_c2h),
+			   rtwdev->btc.ver->info_buf);
+
+		seq_printf(m, "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
+			   pfwinfo->event[BTF_EVNT_RPT],
+			   le16_to_cpu(prptctrl->rpt_info.cnt),
+			   le32_to_cpu(prptctrl->rpt_info.en));
+
+		if (dm->error.map.wl_fw_hang)
+			seq_puts(m, " (WL FW Hang!!)");
+
+		seq_printf(m, "\n\r %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
+			   "[mailbox]", le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
+			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
+			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
+
+		seq_printf(m, "A2DP_empty:%d(stop:%d/tx:%d/ack:%d/nack:%d)",
+			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
+			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
+			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
+			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
+			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
+
+		seq_printf(m,
+			   "\n\r %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d/time:%dms]",
+			   "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			   cx->cnt_wl[BTC_WCNT_RFK_GO],
+			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT],
+			   wl->rfk_info.proc_time);
+
+		seq_printf(m, ", bt_rfk[req:%d]",
+			   le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
+
+		seq_printf(m, ", AOAC[RF_on:%d/RF_off:%d]",
+			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
+			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
+	} else {
+		seq_printf(m,
+			   "\n\r %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d (lps=%d/rf_off=%d)",
+			   "[summary]",
+			   pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
+			   pfwinfo->cnt_c2h,
+			   wl->status.map.lps, wl->status.map.rf_off);
+	}
+
+	for (i = 0; i < BTC_NCNT_NUM; i++)
+		cnt_sum += dm->cnt_notify[i];
+
+	seq_printf(m,
+		   "\n\r %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		   "[notify_cnt]",
+		   cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+
+	seq_printf(m,
+		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
+		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		   cnt[BTC_NCNT_WL_STA]);
+
+	seq_printf(m,
+		   "\n\r %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, switch_chbw=%d, special_pkt=%d, ",
+		   "[notify_cnt]",
+		   cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
+		   cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SWITCH_CHBW],
+		   cnt[BTC_NCNT_SPECIAL_PACKET]);
+
+	seq_printf(m, "timer=%d, customerize=%d, hub_msg=%d, chg_fw=%d, send_cc=%d",
+		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CUSTOMERIZE],
+		   rtwdev->btc.hubmsg_cnt, cnt[BTC_NCNT_RESUME_DL_FW],
+		   cnt[BTC_NCNT_COUNTRYCODE]);
+}
+
 static void _show_summary_v8(struct rtw89_dev *rtwdev, struct seq_file *m)
 {
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &rtwdev->btc.fwinfo;
@@ -10440,6 +10585,8 @@ void rtw89_btc_dump_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		_show_summary_v5(rtwdev, m);
 	else if (ver->fcxbtcrpt == 105)
 		_show_summary_v105(rtwdev, m);
+	else if (ver->fcxbtcrpt == 7)
+		_show_summary_v7(rtwdev, m);
 	else if (ver->fcxbtcrpt == 8)
 		_show_summary_v8(rtwdev, m);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index c4702882367e..ebf848bad515 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -2203,6 +2203,19 @@ struct rtw89_btc_fbtc_rpt_ctrl_v105 {
 	struct rtw89_btc_fbtc_rpt_ctrl_bt_mailbox bt_mbx_info;
 } __packed;
 
+struct rtw89_btc_fbtc_rpt_ctrl_v7 {
+	u8 fver;
+	u8 rsvd0;
+	u8 rsvd1;
+	u8 rsvd2;
+
+	u8 gnt_val[RTW89_PHY_MAX][4];
+	__le16 bt_cnt[BTC_BCNT_STA_MAX_V105];
+
+	struct rtw89_btc_fbtc_rpt_ctrl_info_v8 rpt_info;
+	struct rtw89_btc_fbtc_rpt_ctrl_bt_mailbox bt_mbx_info;
+} __packed;
+
 struct rtw89_btc_fbtc_rpt_ctrl_v8 {
 	u8 fver;
 	u8 rsvd0;
@@ -2221,6 +2234,7 @@ union rtw89_btc_fbtc_rpt_ctrl_ver_info {
 	struct rtw89_btc_fbtc_rpt_ctrl_v4 v4;
 	struct rtw89_btc_fbtc_rpt_ctrl_v5 v5;
 	struct rtw89_btc_fbtc_rpt_ctrl_v105 v105;
+	struct rtw89_btc_fbtc_rpt_ctrl_v7 v7;
 	struct rtw89_btc_fbtc_rpt_ctrl_v8 v8;
 };
 
-- 
cgit v1.3-3-g829e


From e43175dc045dd9ab77fd6ad71353f39f9c6edd66 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 16 Aug 2024 20:46:12 +0800
Subject: wifi: rtw89: coex: Update Wi-Fi role info version 7

This version included new introduced Wi-Fi DBCC information related to
WiFi role.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240816124614.25592-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 251 +++++++++++++++++++++++++++---
 drivers/net/wireless/realtek/rtw89/core.h |  36 +++++
 drivers/net/wireless/realtek/rtw89/fw.c   |  49 +++++-
 drivers/net/wireless/realtek/rtw89/fw.h   |  27 +++-
 4 files changed, 339 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 97e34287dfca..0a8480644b0c 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -2610,6 +2610,10 @@ static void _fw_set_drv_info(struct rtw89_dev *rtwdev, u8 type)
 			rtw89_fw_h2c_cxdrv_role_v1(rtwdev, type);
 		else if (ver->fwlrole == 2)
 			rtw89_fw_h2c_cxdrv_role_v2(rtwdev, type);
+		else if (ver->fwlrole == 7)
+			rtw89_fw_h2c_cxdrv_role_v7(rtwdev, type);
+		else if (ver->fwlrole == 8)
+			rtw89_fw_h2c_cxdrv_role_v8(rtwdev, type);
 		break;
 	case CXDRVINFO_CTRL:
 		if (ver->drvinfo_type == 1)
@@ -2791,7 +2795,7 @@ static void _set_gnt_v1(struct rtw89_dev *rtwdev, u8 phy_map,
 	rtw89_mac_cfg_gnt_v2(rtwdev, &dm->gnt);
 }
 
-#define BTC_TDMA_WLROLE_MAX 2
+#define BTC_TDMA_WLROLE_MAX 3
 
 static void _set_bt_ignore_wlan_act(struct rtw89_dev *rtwdev, u8 enable)
 {
@@ -5610,6 +5614,14 @@ _update_rssi_state(struct rtw89_dev *rtwdev, u8 pre_state, u8 rssi, u8 thresh)
 	return next_state;
 }
 
+static void _wl_req_mac(struct rtw89_dev *rtwdev, u8 mac)
+{
+	if (mac == RTW89_MAC_0)
+		rtw89_write32_clr(rtwdev, R_AX_BTC_CFG, B_AX_WL_SRC);
+	else
+		rtw89_write32_set(rtwdev, R_AX_BTC_CFG, B_AX_WL_SRC);
+}
+
 static
 void _update_dbcc_band(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 {
@@ -6108,12 +6120,20 @@ static u8 _chk_dbcc(struct rtw89_dev *rtwdev, struct rtw89_btc_chdef *ch,
 		    u8 *phy, u8 *role, u8 *dbcc_2g_phy)
 {
 	struct rtw89_btc_wl_info *wl = &rtwdev->btc.cx.wl;
-	struct rtw89_btc_wl_role_info_v8 *wl_rinfo = &wl->role_info_v8;
+	struct rtw89_btc_wl_role_info_v7 *rinfo_v7 = &wl->role_info_v7;
+	struct rtw89_btc_wl_role_info_v8 *rinfo_v8 = &wl->role_info_v8;
 	bool is_2g_ch_exist = false, is_multi_role_in_2g_phy = false;
-	u8 j, k, dbcc_2g_cid, dbcc_2g_cid2;
+	u8 j, k, dbcc_2g_cid, dbcc_2g_cid2, connect_cnt;
+
+	if (rtwdev->btc.ver->fwlrole == 7)
+		connect_cnt = rinfo_v7->connect_cnt;
+	else if (rtwdev->btc.ver->fwlrole == 8)
+		connect_cnt = rinfo_v8->connect_cnt;
+	else
+		return BTC_WLINK_NOLINK;
 
 	/* find out the 2G-PHY by connect-id ->ch  */
-	for (j = 0; j < wl_rinfo->connect_cnt; j++) {
+	for (j = 0; j < connect_cnt; j++) {
 		if (ch[j].center_ch <= 14) {
 			is_2g_ch_exist = true;
 			break;
@@ -6128,11 +6148,11 @@ static u8 _chk_dbcc(struct rtw89_dev *rtwdev, struct rtw89_btc_chdef *ch,
 	*dbcc_2g_phy = phy[dbcc_2g_cid];
 
 	/* connect_cnt <= 2 */
-	if (wl_rinfo->connect_cnt < BTC_TDMA_WLROLE_MAX)
+	if (connect_cnt < BTC_TDMA_WLROLE_MAX)
 		return (_get_role_link_mode((role[dbcc_2g_cid])));
 
 	/* find the other-port in the 2G-PHY, ex: PHY-0:6G, PHY1: mcc/scc */
-	for (k = 0; k < wl_rinfo->connect_cnt; k++) {
+	for (k = 0; k < connect_cnt; k++) {
 		if (k == dbcc_2g_cid)
 			continue;
 
@@ -6159,29 +6179,54 @@ static u8 _chk_dbcc(struct rtw89_dev *rtwdev, struct rtw89_btc_chdef *ch,
 static void _update_role_link_mode(struct rtw89_dev *rtwdev,
 				   bool client_joined, u32 noa)
 {
-	struct rtw89_btc_wl_role_info_v8 *wl_rinfo = &rtwdev->btc.cx.wl.role_info_v8;
+	struct rtw89_btc_wl_role_info_v8 *rinfo_v8 = &rtwdev->btc.cx.wl.role_info_v8;
+	struct rtw89_btc_wl_role_info_v7 *rinfo_v7 = &rtwdev->btc.cx.wl.role_info_v7;
+	u8 role_ver = rtwdev->btc.ver->fwlrole;
 	u32 type = BTC_WLMROLE_NONE, dur = 0;
-	u32 wl_role = wl_rinfo->role_map;
+	u8 link_mode, connect_cnt;
+	u32 wl_role;
+
+	if (role_ver == 7) {
+		wl_role = rinfo_v7->role_map;
+		link_mode = rinfo_v7->link_mode;
+		connect_cnt = rinfo_v7->connect_cnt;
+	} else if (role_ver == 8) {
+		wl_role = rinfo_v8->role_map;
+		link_mode = rinfo_v8->link_mode;
+		connect_cnt = rinfo_v8->connect_cnt;
+	} else {
+		return;
+	}
 
 	/* if no client_joined, don't care P2P-GO/AP role */
 	if (((wl_role & BIT(RTW89_WIFI_ROLE_P2P_GO)) ||
 	     (wl_role & BIT(RTW89_WIFI_ROLE_AP))) && !client_joined) {
-		if (wl_rinfo->link_mode == BTC_WLINK_2G_SCC) {
-			wl_rinfo->link_mode = BTC_WLINK_2G_STA;
-			wl_rinfo->connect_cnt--;
-		} else if (wl_rinfo->link_mode == BTC_WLINK_2G_GO ||
-			wl_rinfo->link_mode == BTC_WLINK_2G_AP) {
-			wl_rinfo->link_mode = BTC_WLINK_NOLINK;
-			wl_rinfo->connect_cnt--;
+		if (link_mode == BTC_WLINK_2G_SCC) {
+			if (role_ver == 7) {
+				rinfo_v7->link_mode = BTC_WLINK_2G_STA;
+				rinfo_v7->connect_cnt--;
+			} else if (role_ver == 8) {
+				rinfo_v8->link_mode = BTC_WLINK_2G_STA;
+				rinfo_v8->connect_cnt--;
+			}
+		} else if (link_mode == BTC_WLINK_2G_GO ||
+			   link_mode == BTC_WLINK_2G_AP) {
+			if (role_ver == 7) {
+				rinfo_v7->link_mode = BTC_WLINK_NOLINK;
+				rinfo_v7->connect_cnt--;
+			} else if (role_ver == 8) {
+				rinfo_v8->link_mode = BTC_WLINK_NOLINK;
+				rinfo_v8->connect_cnt--;
+			}
 		}
 	}
 
 	/* Identify 2-Role type  */
-	if (wl_rinfo->connect_cnt >= 2 &&
-	    (wl_rinfo->link_mode == BTC_WLINK_2G_SCC ||
-	     wl_rinfo->link_mode == BTC_WLINK_2G_MCC ||
-	     wl_rinfo->link_mode == BTC_WLINK_25G_MCC ||
-	     wl_rinfo->link_mode == BTC_WLINK_5G)) {
+	if (connect_cnt >= 2 &&
+	    (link_mode == BTC_WLINK_2G_SCC ||
+	     link_mode == BTC_WLINK_2G_MCC ||
+	     link_mode == BTC_WLINK_25G_MCC ||
+	     link_mode == BTC_WLINK_5G)) {
 		if ((wl_role & BIT(RTW89_WIFI_ROLE_P2P_GO)) ||
 		    (wl_role & BIT(RTW89_WIFI_ROLE_AP)))
 			type = noa ? BTC_WLMROLE_STA_GO_NOA : BTC_WLMROLE_STA_GO;
@@ -6193,8 +6238,167 @@ static void _update_role_link_mode(struct rtw89_dev *rtwdev,
 		dur = noa;
 	}
 
-	wl_rinfo->mrole_type = type;
-	wl_rinfo->mrole_noa_duration = dur;
+	if (role_ver == 7) {
+		rinfo_v7->mrole_type = type;
+		rinfo_v7->mrole_noa_duration = dur;
+	} else if (role_ver == 8) {
+		rinfo_v8->mrole_type = type;
+		rinfo_v8->mrole_noa_duration = dur;
+	}
+}
+
+static void _update_wl_info_v7(struct rtw89_dev *rtwdev, u8 rid)
+{
+	struct rtw89_btc_chdef cid_ch[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER];
+	struct rtw89_btc *btc = &rtwdev->btc;
+	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo = &wl->role_info_v7;
+	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
+	struct rtw89_btc_wl_link_info *wl_linfo = wl->link_info;
+	struct rtw89_btc_wl_active_role_v7 *act_role = NULL;
+	u8 i, mode, cnt = 0, cnt_2g = 0, cnt_5g = 0, phy_now = RTW89_PHY_MAX, phy_dbcc;
+	bool b2g = false, b5g = false, client_joined = false, client_inc_2g = false;
+	u8 client_cnt_last[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER] = {};
+	u8 cid_role[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER] = {};
+	u8 cid_phy[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER] = {};
+	u8 mac = RTW89_MAC_0, dbcc_2g_phy = RTW89_PHY_0;
+	u32 noa_duration = 0;
+
+	memset(wl_rinfo, 0, sizeof(*wl_rinfo));
+
+	for (i = 0; i < RTW89_PORT_NUM; i++) {
+		if (!wl_linfo[i].active || wl_linfo[i].phy >= RTW89_PHY_MAX)
+			continue;
+
+		act_role = &wl_rinfo->active_role[i];
+		act_role->role = wl_linfo[i].role;
+
+		/* check if role connect? */
+		if (wl_linfo[i].connected == MLME_NO_LINK) {
+			act_role->connected = 0;
+			continue;
+		} else if (wl_linfo[i].connected == MLME_LINKING) {
+			continue;
+		}
+
+		cnt++;
+		act_role->connected = 1;
+		act_role->pid = wl_linfo[i].pid;
+		act_role->phy = wl_linfo[i].phy;
+		act_role->band = wl_linfo[i].band;
+		act_role->ch = wl_linfo[i].ch;
+		act_role->bw = wl_linfo[i].bw;
+		act_role->noa = wl_linfo[i].noa;
+		act_role->noa_dur = wl_linfo[i].noa_duration;
+		cid_ch[cnt - 1] = wl_linfo[i].chdef;
+		cid_phy[cnt - 1] = wl_linfo[i].phy;
+		cid_role[cnt - 1] = wl_linfo[i].role;
+		wl_rinfo->role_map |= BIT(wl_linfo[i].role);
+
+		if (rid == i)
+			phy_now = act_role->phy;
+
+		if (wl_linfo[i].role == RTW89_WIFI_ROLE_P2P_GO ||
+		    wl_linfo[i].role == RTW89_WIFI_ROLE_AP) {
+			if (wl_linfo[i].client_cnt > 1)
+				client_joined = true;
+			if (client_cnt_last[i] < wl_linfo[i].client_cnt &&
+			    wl_linfo[i].chdef.band == RTW89_BAND_2G)
+				client_inc_2g = true;
+			act_role->client_cnt = wl_linfo[i].client_cnt;
+		} else {
+			act_role->client_cnt = 0;
+		}
+
+		if (act_role->noa && act_role->noa_dur > 0)
+			noa_duration = act_role->noa_dur;
+
+		if (rtwdev->dbcc_en) {
+			phy_dbcc = wl_linfo[i].phy;
+			wl_dinfo->role[phy_dbcc] |= BIT(wl_linfo[i].role);
+			wl_dinfo->op_band[phy_dbcc] = wl_linfo[i].chdef.band;
+		}
+
+		if (wl_linfo[i].chdef.band != RTW89_BAND_2G) {
+			cnt_5g++;
+			b5g = true;
+		} else {
+			if (((wl_linfo[i].role == RTW89_WIFI_ROLE_P2P_GO ||
+			      wl_linfo[i].role == RTW89_WIFI_ROLE_AP) &&
+			     client_joined) ||
+			    wl_linfo[i].role == RTW89_WIFI_ROLE_P2P_CLIENT)
+				wl_rinfo->p2p_2g = 1;
+
+			if ((wl_linfo[i].mode & BIT(BTC_WL_MODE_11B)) ||
+			    (wl_linfo[i].mode & BIT(BTC_WL_MODE_11G)))
+				wl->bg_mode = 1;
+			else if (wl_linfo[i].mode & BIT(BTC_WL_MODE_HE))
+				wl->he_mode = true;
+
+			cnt_2g++;
+			b2g = true;
+		}
+
+		if (act_role->band == RTW89_BAND_5G && act_role->ch >= 100)
+			wl->is_5g_hi_channel = 1;
+		else
+			wl->is_5g_hi_channel = 0;
+	}
+
+	wl_rinfo->connect_cnt = cnt;
+	wl->client_cnt_inc_2g = client_inc_2g;
+
+	if (cnt == 0) {
+		mode = BTC_WLINK_NOLINK;
+		wl_rinfo->role_map = BIT(RTW89_WIFI_ROLE_NONE);
+	} else if (!b2g && b5g) {
+		mode = BTC_WLINK_5G;
+	} else if (wl_rinfo->role_map & BIT(RTW89_WIFI_ROLE_NAN)) {
+		mode = BTC_WLINK_2G_NAN;
+	} else if (cnt > BTC_TDMA_WLROLE_MAX) {
+		mode = BTC_WLINK_OTHER;
+	} else if (rtwdev->dbcc_en) {
+		mode = _chk_dbcc(rtwdev, cid_ch, cid_phy, cid_role, &dbcc_2g_phy);
+
+		/* correct 2G-located PHY band for gnt ctrl */
+		if (dbcc_2g_phy < RTW89_PHY_MAX)
+			wl_dinfo->op_band[dbcc_2g_phy] = RTW89_BAND_2G;
+	} else if (b2g && b5g && cnt == 2) {
+		mode = BTC_WLINK_25G_MCC;
+	} else if (!b5g && cnt == 2) { /* cnt_connect = 2 */
+		if (_chk_role_ch_group(&cid_ch[0], &cid_ch[cnt - 1]))
+			mode = BTC_WLINK_2G_SCC;
+		else
+			mode = BTC_WLINK_2G_MCC;
+	} else if (!b5g && cnt == 1) { /* cnt_connect = 1 */
+		mode = _get_role_link_mode(cid_role[0]);
+	} else {
+		mode = BTC_WLINK_NOLINK;
+	}
+
+	wl_rinfo->link_mode = mode;
+	_update_role_link_mode(rtwdev, client_joined, noa_duration);
+
+	/* todo DBCC related event */
+	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC] wl_info phy_now=%d\n", phy_now);
+
+	if (wl_rinfo->dbcc_en != rtwdev->dbcc_en) {
+		wl_rinfo->dbcc_chg = 1;
+		wl_rinfo->dbcc_en = rtwdev->dbcc_en;
+		btc->cx.cnt_wl[BTC_WCNT_DBCC_CHG]++;
+	}
+
+	if (rtwdev->dbcc_en) {
+		wl_rinfo->dbcc_2g_phy = dbcc_2g_phy;
+
+		if (dbcc_2g_phy == RTW89_PHY_1)
+			mac = RTW89_MAC_1;
+
+		_update_dbcc_band(rtwdev, RTW89_PHY_0);
+		_update_dbcc_band(rtwdev, RTW89_PHY_1);
+	}
+	_wl_req_mac(rtwdev, mac);
+	_fw_set_drv_info(rtwdev, CXDRVINFO_ROLE);
 }
 
 static void _update_wl_info_v8(struct rtw89_dev *rtwdev, u8 role_id, u8 rlink_id,
@@ -7293,6 +7497,9 @@ void rtw89_btc_ntfy_role_info(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif
 	} else if (ver->fwlrole == 2) {
 		*wlinfo = r;
 		_update_wl_info_v2(rtwdev);
+	} else if (ver->fwlrole == 7) {
+		*wlinfo = r;
+		_update_wl_info_v7(rtwdev, r.pid);
 	} else if (ver->fwlrole == 8) {
 		wlinfo = &wl->rlink_info[r.pid][rlink_id];
 		*wlinfo = r;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index ebf848bad515..0410f6d4bb65 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -1590,6 +1590,23 @@ struct rtw89_btc_wl_active_role_v2 {
 	u32 noa_duration; /* ms */
 };
 
+struct rtw89_btc_wl_active_role_v7 {
+	u8 connected;
+	u8 pid;
+	u8 phy;
+	u8 noa;
+
+	u8 band;
+	u8 client_ps;
+	u8 bw;
+	u8 role;
+
+	u8 ch;
+	u8 noa_dur;
+	u8 client_cnt;
+	u8 rsvd2;
+} __packed;
+
 struct rtw89_btc_wl_role_info_bpos {
 	u16 none: 1;
 	u16 station: 1;
@@ -1671,6 +1688,22 @@ struct rtw89_btc_wl_rlink { /* H2C info, struct size must be n*4 bytes */
 } __packed;
 
 #define RTW89_BE_BTC_WL_MAX_ROLE_NUMBER 6
+struct rtw89_btc_wl_role_info_v7 { /* struct size must be n*4 bytes */
+	u8 connect_cnt;
+	u8 link_mode;
+	u8 link_mode_chg;
+	u8 p2p_2g;
+
+	struct rtw89_btc_wl_active_role_v7 active_role[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER];
+
+	u32 role_map;
+	u32 mrole_type; /* btc_wl_mrole_type */
+	u32 mrole_noa_duration; /* ms */
+	u32 dbcc_en;
+	u32 dbcc_chg;
+	u32 dbcc_2g_phy; /* which phy operate in 2G, HW_PHY_0 or HW_PHY_1 */
+} __packed;
+
 struct rtw89_btc_wl_role_info_v8 { /* H2C info, struct size must be n*4 bytes */
 	u8 connect_cnt;
 	u8 link_mode;
@@ -1834,6 +1867,7 @@ struct rtw89_btc_wl_info {
 	struct rtw89_btc_wl_role_info role_info;
 	struct rtw89_btc_wl_role_info_v1 role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 role_info_v8;
 	struct rtw89_btc_wl_scan_info scan_info;
 	struct rtw89_btc_wl_dbcc_info dbcc_info;
@@ -1851,8 +1885,10 @@ struct rtw89_btc_wl_info {
 	bool is_5g_hi_channel;
 	bool pta_reg_mac_chg;
 	bool bg_mode;
+	bool he_mode;
 	bool scbd_change;
 	bool fw_ver_mismatch;
+	bool client_cnt_inc_2g;
 	u32 scbd;
 };
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 47aa365991c1..06b263550ef0 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -4325,6 +4325,52 @@ fail:
 	return ret;
 }
 
+int rtw89_fw_h2c_cxdrv_role_v7(struct rtw89_dev *rtwdev, u8 type)
+{
+	struct rtw89_btc *btc = &rtwdev->btc;
+	struct rtw89_btc_wl_role_info_v7 *role = &btc->cx.wl.role_info_v7;
+	struct rtw89_h2c_cxrole_v7 *h2c;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
+	int ret;
+
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
+	if (!skb) {
+		rtw89_err(rtwdev, "failed to alloc skb for h2c cxdrv_ctrl\n");
+		return -ENOMEM;
+	}
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_cxrole_v7 *)skb->data;
+
+	h2c->hdr.type = type;
+	h2c->hdr.ver = btc->ver->fwlrole;
+	h2c->hdr.len = len - H2C_LEN_CXDRVHDR_V7;
+	memcpy(&h2c->_u8, role, sizeof(h2c->_u8));
+	h2c->_u32.role_map = cpu_to_le32(role->role_map);
+	h2c->_u32.mrole_type = cpu_to_le32(role->mrole_type);
+	h2c->_u32.mrole_noa_duration = cpu_to_le32(role->mrole_noa_duration);
+	h2c->_u32.dbcc_en = cpu_to_le32(role->dbcc_en);
+	h2c->_u32.dbcc_chg = cpu_to_le32(role->dbcc_chg);
+	h2c->_u32.dbcc_2g_phy = cpu_to_le32(role->dbcc_2g_phy);
+
+	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
+			      H2C_CAT_OUTSRC, BTFC_SET,
+			      SET_DRV_INFO, 0, 0,
+			      len);
+
+	ret = rtw89_h2c_tx(rtwdev, skb, false);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to send h2c\n");
+		goto fail;
+	}
+
+	return 0;
+fail:
+	dev_kfree_skb_any(skb);
+
+	return ret;
+}
+
 int rtw89_fw_h2c_cxdrv_role_v8(struct rtw89_dev *rtwdev, u8 type)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
@@ -4343,6 +4389,7 @@ int rtw89_fw_h2c_cxdrv_role_v8(struct rtw89_dev *rtwdev, u8 type)
 	h2c = (struct rtw89_h2c_cxrole_v8 *)skb->data;
 
 	h2c->hdr.type = type;
+	h2c->hdr.ver = btc->ver->fwlrole;
 	h2c->hdr.len = len - H2C_LEN_CXDRVHDR_V7;
 	memcpy(&h2c->_u8, role, sizeof(h2c->_u8));
 	h2c->_u32.role_map = cpu_to_le32(role->role_map);
@@ -4423,7 +4470,7 @@ int rtw89_fw_h2c_cxdrv_ctrl_v7(struct rtw89_dev *rtwdev, u8 type)
 
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
-		rtw89_err(rtwdev, "failed to alloc skb for h2c cxdrv_ctrl\n");
+		rtw89_err(rtwdev, "failed to alloc skb for h2c cxdrv_ctrl_v7\n");
 		return -ENOMEM;
 	}
 	skb_put(skb, len);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 663eda5d0452..cb0ecb9b4c11 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -2147,6 +2147,30 @@ struct rtw89_h2c_cxctrl_v7 {
 #define H2C_LEN_CXDRVHDR sizeof(struct rtw89_h2c_cxhdr)
 #define H2C_LEN_CXDRVHDR_V7 sizeof(struct rtw89_h2c_cxhdr_v7)
 
+struct rtw89_btc_wl_role_info_v7_u8 {
+	u8 connect_cnt;
+	u8 link_mode;
+	u8 link_mode_chg;
+	u8 p2p_2g;
+
+	struct rtw89_btc_wl_active_role_v7 active_role[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER];
+} __packed;
+
+struct rtw89_btc_wl_role_info_v7_u32 {
+	__le32 role_map;
+	__le32 mrole_type;
+	__le32 mrole_noa_duration;
+	__le32 dbcc_en;
+	__le32 dbcc_chg;
+	__le32 dbcc_2g_phy;
+} __packed;
+
+struct rtw89_h2c_cxrole_v7 {
+	struct rtw89_h2c_cxhdr_v7 hdr;
+	struct rtw89_btc_wl_role_info_v7_u8 _u8;
+	struct rtw89_btc_wl_role_info_v7_u32 _u32;
+} __packed;
+
 struct rtw89_btc_wl_role_info_v8_u8 {
 	u8 connect_cnt;
 	u8 link_mode;
@@ -2168,7 +2192,7 @@ struct rtw89_btc_wl_role_info_v8_u32 {
 } __packed;
 
 struct rtw89_h2c_cxrole_v8 {
-	struct rtw89_h2c_cxhdr hdr;
+	struct rtw89_h2c_cxhdr_v7 hdr;
 	struct rtw89_btc_wl_role_info_v8_u8 _u8;
 	struct rtw89_btc_wl_role_info_v8_u32 _u32;
 } __packed;
@@ -4426,6 +4450,7 @@ int rtw89_fw_h2c_cxdrv_init_v7(struct rtw89_dev *rtwdev, u8 type);
 int rtw89_fw_h2c_cxdrv_role(struct rtw89_dev *rtwdev, u8 type);
 int rtw89_fw_h2c_cxdrv_role_v1(struct rtw89_dev *rtwdev, u8 type);
 int rtw89_fw_h2c_cxdrv_role_v2(struct rtw89_dev *rtwdev, u8 type);
+int rtw89_fw_h2c_cxdrv_role_v7(struct rtw89_dev *rtwdev, u8 type);
 int rtw89_fw_h2c_cxdrv_role_v8(struct rtw89_dev *rtwdev, u8 type);
 int rtw89_fw_h2c_cxdrv_ctrl(struct rtw89_dev *rtwdev, u8 type);
 int rtw89_fw_h2c_cxdrv_ctrl_v7(struct rtw89_dev *rtwdev, u8 type);
-- 
cgit v1.3-3-g829e


From b0923d48529c5e2f49492b356b3e970f0a98a649 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 16 Aug 2024 20:46:13 +0800
Subject: wifi: rtw89: coex: Bluetooth hopping map for Wi-Fi role version 7

To get Wi-Fi channel & bandwidth information from new Wi-Fi role format.
Bluetooth will negotiate which channel to do TX/RX with connected device.
And Bluetooth will maintain a hopping map, that describe the usable
channels. To avoid the interference from Wi-Fi 2.4GHz/Bluetooth each other,
Bluetooth must not to hop into Wi-Fi channel.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240816124614.25592-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 0a8480644b0c..44e066a04b97 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -3045,10 +3045,12 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	struct rtw89_btc_wl_active_role *r;
 	struct rtw89_btc_wl_active_role_v1 *r1;
 	struct rtw89_btc_wl_active_role_v2 *r2;
+	struct rtw89_btc_wl_active_role_v7 *r7;
 	struct rtw89_btc_wl_rlink *rlink;
 	u8 en = 0, i, ch = 0, bw = 0;
 	u8 mode, connect_cnt;
@@ -3065,6 +3067,9 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev)
 	} else if (ver->fwlrole == 2) {
 		mode = wl_rinfo_v2->link_mode;
 		connect_cnt = wl_rinfo_v2->connect_cnt;
+	} else if (ver->fwlrole == 7) {
+		mode = wl_rinfo_v7->link_mode;
+		connect_cnt = wl_rinfo_v7->connect_cnt;
 	} else if (ver->fwlrole == 8) {
 		mode = wl_rinfo_v8->link_mode;
 		connect_cnt = wl_rinfo_v8->connect_cnt;
@@ -3083,6 +3088,7 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev)
 			r = &wl_rinfo->active_role[i];
 			r1 = &wl_rinfo_v1->active_role_v1[i];
 			r2 = &wl_rinfo_v2->active_role_v2[i];
+			r7 = &wl_rinfo_v7->active_role[i];
 			rlink = &wl_rinfo_v8->rlink[i][0];
 
 			if (ver->fwlrole == 0 &&
@@ -3103,6 +3109,12 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev)
 				ch = r2->ch;
 				bw = r2->bw;
 				break;
+			} else if (ver->fwlrole == 7 &&
+				   (r7->role == RTW89_WIFI_ROLE_P2P_GO ||
+				    r7->role == RTW89_WIFI_ROLE_P2P_CLIENT)) {
+				ch = r7->ch;
+				bw = r7->bw;
+				break;
 			} else if (ver->fwlrole == 8 &&
 				   (rlink->role == RTW89_WIFI_ROLE_P2P_GO ||
 				    rlink->role == RTW89_WIFI_ROLE_P2P_CLIENT)) {
@@ -3118,6 +3130,7 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev)
 			r = &wl_rinfo->active_role[i];
 			r1 = &wl_rinfo_v1->active_role_v1[i];
 			r2 = &wl_rinfo_v2->active_role_v2[i];
+			r7 = &wl_rinfo_v7->active_role[i];
 			rlink = &wl_rinfo_v8->rlink[i][0];
 
 			if (ver->fwlrole == 0 &&
@@ -3135,6 +3148,11 @@ static void _set_bt_afh_info(struct rtw89_dev *rtwdev)
 				ch = r2->ch;
 				bw = r2->bw;
 				break;
+			} else if (ver->fwlrole == 7 &&
+				   r7->connected && r7->band == RTW89_BAND_2G) {
+				ch = r7->ch;
+				bw = r7->bw;
+				break;
 			} else if (ver->fwlrole == 8 &&
 				   rlink->connected && rlink->rf_band == RTW89_BAND_2G) {
 				ch = rlink->ch;
-- 
cgit v1.3-3-g829e


From 6833337585dda8cc2e00532f1e2a6ad02fbf9dea Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 16 Aug 2024 20:46:14 +0800
Subject: wifi: rtw89: coex: Add new Wi-Fi role format condition for function
 using

There are many features need the information those record at Wi-Fi role
structure. Implement the corresponding code for using.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240816124614.25592-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 90 ++++++++++++++++++++++++-------
 1 file changed, 71 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 44e066a04b97..df51b29142aa 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -3211,6 +3211,7 @@ static bool _check_freerun(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	struct rtw89_btc_bt_link_info *bt_linfo = &bt->link_info;
 	struct rtw89_btc_bt_hid_desc *hid = &bt_linfo->hid_desc;
@@ -3229,6 +3230,8 @@ static bool _check_freerun(struct rtw89_dev *rtwdev)
 		connect_cnt = wl_rinfo_v1->connect_cnt;
 	else if (ver->fwlrole == 2)
 		connect_cnt = wl_rinfo_v2->connect_cnt;
+	else if (ver->fwlrole == 7)
+		connect_cnt = wl_rinfo_v7->connect_cnt;
 	else if (ver->fwlrole == 8)
 		connect_cnt = wl_rinfo_v8->connect_cnt;
 
@@ -4147,6 +4150,8 @@ static void _set_ant_v0(struct rtw89_dev *rtwdev, bool force_exec,
 		dbcc_chg = wl->role_info_v1.dbcc_chg;
 	else if (btc->ver->fwlrole == 2)
 		dbcc_chg = wl->role_info_v2.dbcc_chg;
+	else if (btc->ver->fwlrole == 7)
+		dbcc_chg = wl->role_info_v7.dbcc_chg;
 	else if (btc->ver->fwlrole == 8)
 		dbcc_chg = wl->role_info_v8.dbcc_chg;
 
@@ -4819,6 +4824,7 @@ static void _set_btg_ctrl(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	struct rtw89_btc_wl_role_info *wl_rinfo_v0 = &wl->role_info;
 	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
@@ -4840,6 +4846,8 @@ static void _set_btg_ctrl(struct rtw89_dev *rtwdev)
 		wl_rinfo.link_mode = wl_rinfo_v1->link_mode;
 	else if (ver->fwlrole == 2)
 		wl_rinfo.link_mode = wl_rinfo_v2->link_mode;
+	else if (ver->fwlrole == 7)
+		wl_rinfo.link_mode = wl_rinfo_v7->link_mode;
 	else if (ver->fwlrole == 8)
 		wl_rinfo.link_mode = wl_rinfo_v8->link_mode;
 	else
@@ -4855,6 +4863,8 @@ static void _set_btg_ctrl(struct rtw89_dev *rtwdev)
 			wl_rinfo.dbcc_2g_phy = wl_rinfo_v1->dbcc_2g_phy;
 		} else if (ver->fwlrole == 2) {
 			wl_rinfo.dbcc_2g_phy = wl_rinfo_v2->dbcc_2g_phy;
+		} else if (ver->fwlrole == 7) {
+			wl_rinfo.dbcc_2g_phy = wl_rinfo_v7->dbcc_2g_phy;
 		} else if (ver->fwlrole == 8) {
 			wl_rinfo.dbcc_2g_phy = wl_rinfo_v8->dbcc_2g_phy;
 		} else {
@@ -4900,37 +4910,56 @@ static void _set_wl_preagc_ctrl(struct rtw89_dev *rtwdev)
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_link_info *bt_linfo = &btc->cx.bt.link_info;
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
-	struct rtw89_btc_wl_role_info_v2 *wl_rinfo = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v2 *rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *rinfo_v7 = &wl->role_info_v7;
+	struct rtw89_btc_wl_role_info_v8 *rinfo_v8 = &wl->role_info_v8;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 	struct rtw89_btc_dm *dm = &btc->dm;
-	u8 is_preagc, val;
+	u8 is_preagc, val, link_mode, dbcc_2g_phy;
+	u8 role_ver = rtwdev->btc.ver->fwlrole;
+	bool dbcc_en;
 
 	if (btc->manual_ctrl)
 		return;
 
-	if (wl_rinfo->link_mode == BTC_WLINK_25G_MCC)
+	if (role_ver == 2) {
+		dbcc_en = rinfo_v2->dbcc_en;
+		link_mode = rinfo_v2->link_mode;
+		dbcc_2g_phy = rinfo_v2->dbcc_2g_phy;
+	} else if (role_ver == 7) {
+		dbcc_en = rinfo_v7->dbcc_en;
+		link_mode = rinfo_v7->link_mode;
+		dbcc_2g_phy = rinfo_v7->dbcc_2g_phy;
+	} else if (role_ver == 8) {
+		dbcc_en = rinfo_v8->dbcc_en;
+		link_mode = rinfo_v8->link_mode;
+		dbcc_2g_phy = rinfo_v7->dbcc_2g_phy;
+	} else {
+		return;
+	}
+
+	if (link_mode == BTC_WLINK_25G_MCC) {
 		is_preagc = BTC_PREAGC_BB_FWCTRL;
-	else if (!(bt->run_patch_code && bt->enable.now))
+	} else if (!(bt->run_patch_code && bt->enable.now)) {
 		is_preagc = BTC_PREAGC_DISABLE;
-	else if (wl_rinfo->link_mode == BTC_WLINK_5G)
+	} else if (link_mode == BTC_WLINK_5G) {
 		is_preagc = BTC_PREAGC_DISABLE;
-	else if (wl_rinfo->link_mode == BTC_WLINK_NOLINK ||
-		 btc->cx.bt.link_info.profile_cnt.now == 0)
+	} else if (link_mode == BTC_WLINK_NOLINK ||
+		 btc->cx.bt.link_info.profile_cnt.now == 0) {
 		is_preagc = BTC_PREAGC_DISABLE;
-	else if (dm->tdma_now.type != CXTDMA_OFF &&
+	} else if (dm->tdma_now.type != CXTDMA_OFF &&
 		 !bt_linfo->hfp_desc.exist &&
 		 !bt_linfo->hid_desc.exist &&
-		 dm->fddt_train == BTC_FDDT_DISABLE)
+		 dm->fddt_train == BTC_FDDT_DISABLE) {
 		is_preagc = BTC_PREAGC_DISABLE;
-	else if (ver->fwlrole == 2 && wl_rinfo->dbcc_en &&
-		 wl_rinfo->dbcc_2g_phy != RTW89_PHY_1)
+	} else if (dbcc_en && (dbcc_2g_phy != RTW89_PHY_1)) {
 		is_preagc = BTC_PREAGC_DISABLE;
-	else if (btc->ant_type == BTC_ANT_SHARED)
+	} else if (btc->ant_type == BTC_ANT_SHARED) {
 		is_preagc = BTC_PREAGC_DISABLE;
-	else
+	} else {
 		is_preagc = BTC_PREAGC_ENABLE;
+	}
 
 	if (dm->wl_pre_agc_rb != dm->wl_pre_agc &&
 	    dm->wl_pre_agc_rb != BTC_PREAGC_NOTFOUND) {
@@ -5033,6 +5062,7 @@ static void _set_wl_tx_limit(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	struct rtw89_txtime_data data = {.rtwdev = rtwdev};
 	u8 mode, igno_bt, tx_retry;
@@ -5049,6 +5079,8 @@ static void _set_wl_tx_limit(struct rtw89_dev *rtwdev)
 		mode = wl_rinfo_v1->link_mode;
 	else if (ver->fwlrole == 2)
 		mode = wl_rinfo_v2->link_mode;
+	else if (ver->fwlrole == 7)
+		mode = wl_rinfo_v7->link_mode;
 	else if (ver->fwlrole == 8)
 		mode = wl_rinfo_v8->link_mode;
 	else
@@ -5108,6 +5140,7 @@ static void _set_bt_rx_agc(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 	bool bt_hi_lna_rx = false;
@@ -5119,6 +5152,8 @@ static void _set_bt_rx_agc(struct rtw89_dev *rtwdev)
 		mode = wl_rinfo_v1->link_mode;
 	else if (ver->fwlrole == 2)
 		mode = wl_rinfo_v2->link_mode;
+	else if (ver->fwlrole == 7)
+		mode = wl_rinfo_v7->link_mode;
 	else if (ver->fwlrole == 8)
 		mode = wl_rinfo_v8->link_mode;
 	else
@@ -5424,15 +5459,26 @@ static void _action_wl_2g_scc_v2(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 	struct rtw89_btc_dm *dm = &btc->dm;
-	struct rtw89_btc_wl_role_info_v2 *wl_rinfo = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v2 *rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *rinfo_v7 = &wl->role_info_v7;
+	u32 dur, mrole_type, mrole_noa_duration;
 	u16 policy_type = BTC_CXP_OFF_BT;
-	u32 dur;
+
+	if (btc->ver->fwlrole == 2) {
+		mrole_type = rinfo_v2->mrole_type;
+		mrole_noa_duration = rinfo_v2->mrole_noa_duration;
+	} else if (btc->ver->fwlrole == 7) {
+		mrole_type = rinfo_v7->mrole_type;
+		mrole_noa_duration = rinfo_v7->mrole_noa_duration;
+	} else {
+		return;
+	}
 
 	if (btc->ant_type == BTC_ANT_DEDICATED) {
 		policy_type = BTC_CXP_OFF_EQ0;
 	} else {
 		/* shared-antenna */
-		switch (wl_rinfo->mrole_type) {
+		switch (mrole_type) {
 		case BTC_WLMROLE_STA_GC:
 			dm->wl_scc.null_role1 = RTW89_WIFI_ROLE_STATION;
 			dm->wl_scc.null_role2 = RTW89_WIFI_ROLE_P2P_CLIENT;
@@ -5450,7 +5496,7 @@ static void _action_wl_2g_scc_v2(struct rtw89_dev *rtwdev)
 		case BTC_WLMROLE_STA_GO_NOA:
 			dm->wl_scc.null_role1 = RTW89_WIFI_ROLE_STATION;
 			dm->wl_scc.null_role2 = RTW89_WIFI_ROLE_NONE;
-			dur = wl_rinfo->mrole_noa_duration;
+			dur = mrole_noa_duration;
 
 			if (wl->status.map._4way) {
 				dm->wl_scc.ebt_null = 0;
@@ -6761,6 +6807,7 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	u8 mode, igno_bt, always_freerun;
 
@@ -6776,6 +6823,8 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 		mode = wl_rinfo_v1->link_mode;
 	else if (ver->fwlrole == 2)
 		mode = wl_rinfo_v2->link_mode;
+	else if (ver->fwlrole == 7)
+		mode = wl_rinfo_v7->link_mode;
 	else if (ver->fwlrole == 8)
 		mode = wl_rinfo_v8->link_mode;
 	else
@@ -6922,7 +6971,7 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 			_action_wl_2g_scc(rtwdev);
 		else if (ver->fwlrole == 1)
 			_action_wl_2g_scc_v1(rtwdev);
-		else if (ver->fwlrole == 2)
+		else if (ver->fwlrole == 2 || ver->fwlrole == 7)
 			_action_wl_2g_scc_v2(rtwdev);
 		else if (ver->fwlrole == 8)
 			_action_wl_2g_scc_v8(rtwdev);
@@ -8124,6 +8173,7 @@ static void _show_wl_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_wl_role_info *wl_rinfo = &wl->role_info;
 	struct rtw89_btc_wl_role_info_v1 *wl_rinfo_v1 = &wl->role_info_v1;
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
+	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	u8 mode;
 
@@ -8138,6 +8188,8 @@ static void _show_wl_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		mode = wl_rinfo_v1->link_mode;
 	else if (ver->fwlrole == 2)
 		mode = wl_rinfo_v2->link_mode;
+	else if (ver->fwlrole == 7)
+		mode = wl_rinfo_v7->link_mode;
 	else if (ver->fwlrole == 8)
 		mode = wl_rinfo_v8->link_mode;
 	else
-- 
cgit v1.3-3-g829e


From af8a066f1c473261881a6d8e2b55cca8eda9ce80 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 20 Aug 2024 18:34:25 -0700
Subject: selftest: bpf: Remove mssind boundary check in
 test_tcp_custom_syncookie.c.

Smatch reported a possible off-by-one in tcp_validate_cookie().

However, it's false positive because the possible range of mssind is
limited from 0 to 3 by the preceding calculation.

  mssind = (cookie & (3 << 6)) >> 6;

Now, the verifier does not complain without the boundary check.
Let's remove the checks.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/bpf/6ae12487-d3f1-488b-9514-af0dac96608f@stanley.mountain/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20240821013425.49316-1-kuniyu@amazon.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
index 44ee0d037f95..eb5cca1fce16 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
@@ -486,17 +486,10 @@ static int tcp_validate_cookie(struct tcp_syncookie *ctx)
 		goto err;
 
 	mssind = (cookie & (3 << 6)) >> 6;
-	if (ctx->ipv4) {
-		if (mssind > ARRAY_SIZE(msstab4))
-			goto err;
-
+	if (ctx->ipv4)
 		ctx->attrs.mss = msstab4[mssind];
-	} else {
-		if (mssind > ARRAY_SIZE(msstab6))
-			goto err;
-
+	else
 		ctx->attrs.mss = msstab6[mssind];
-	}
 
 	ctx->attrs.snd_wscale = cookie & BPF_SYNCOOKIE_WSCALE_MASK;
 	ctx->attrs.rcv_wscale = ctx->attrs.snd_wscale;
-- 
cgit v1.3-3-g829e


From a7e8997ae18c42d30bc7181421b5715e319c0f71 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 15 Aug 2024 00:31:32 -0600
Subject: wifi: iwlegacy: Avoid multiple -Wflex-array-member-not-at-end
 warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in order to avoid ending up with a flexible-array member in the
middle of multiple other structs, we use the `__struct_group()`
helper to create new tagged structures with the suffix `_hdr`.
These structures group together all the members of the original
flexible structures except the flexible arrays.

As a result, the arrays are effectively separated from the rest of the
members without modifying the memory layout of the flexible structures.
We then change the type of the middle struct members currently causing
trouble from the original flex struct to the newly created structs with
suffix `_hdr`.

We also want to ensure that when new members need to be added to the
flexible structures, they are always included within the newly created
tagged structs. For this, we use `static_assert()`. This ensures that the
memory layout for both the flexible structure and the new tagged struct
is the same after any changes.

This approach avoids having to implement the `_hdr` structures as
completely separate structures, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

We also use `container_of()` whenever we need to retrieve a pointer to
the flexible structure, through which we can access the flexible-array
member, if necessary.

Also, remove a couple of unused zero-length arrays and flexible-array
members.

So, with these changes, fix the following warnings:

drivers/net/wireless/intel/iwlegacy/commands.h:1196:38: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:1197:36: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:2505:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:2549:26: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:2654:31: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:2665:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:2673:26: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlegacy/commands.h:3349:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/Zr2gxERA3RL3EwRe@elsanto
---
 drivers/net/wireless/intel/iwlegacy/3945.c     |   2 +-
 drivers/net/wireless/intel/iwlegacy/3945.h     |   6 +-
 drivers/net/wireless/intel/iwlegacy/4965-mac.c |   2 +-
 drivers/net/wireless/intel/iwlegacy/commands.h | 303 +++++++++++++------------
 drivers/net/wireless/intel/iwlegacy/common.h   |   2 +-
 5 files changed, 165 insertions(+), 150 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index 1fab7849f56d..e95800b77f6b 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -527,7 +527,7 @@ il3945_hdl_rx(struct il_priv *il, struct il_rx_buf *rxb)
 	struct ieee80211_hdr *header;
 	struct ieee80211_rx_status rx_status = {};
 	struct il_rx_pkt *pkt = rxb_addr(rxb);
-	struct il3945_rx_frame_stats *rx_stats = IL_RX_STATS(pkt);
+	struct il3945_rx_frame_stats_hdr *rx_stats = IL_RX_STATS(pkt);
 	struct il3945_rx_frame_hdr *rx_hdr = IL_RX_HDR(pkt);
 	struct il3945_rx_frame_end *rx_end = IL_RX_END(pkt);
 	u16 rx_stats_sig_avg __maybe_unused = le16_to_cpu(rx_stats->sig_avg);
diff --git a/drivers/net/wireless/intel/iwlegacy/3945.h b/drivers/net/wireless/intel/iwlegacy/3945.h
index 82e4a4878bc2..ffbe11902628 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.h
+++ b/drivers/net/wireless/intel/iwlegacy/3945.h
@@ -157,8 +157,10 @@ struct il3945_ibss_seq {
 };
 
 #define IL_RX_HDR(x) ((struct il3945_rx_frame_hdr *)(\
-		       x->u.rx_frame.stats.payload + \
-		       x->u.rx_frame.stats.phy_count))
+		      container_of(&x->u.rx_frame.stats, \
+				   struct il3945_rx_frame_stats, \
+				   hdr)->payload + \
+		      x->u.rx_frame.stats.phy_count))
 #define IL_RX_END(x) ((struct il3945_rx_frame_end *)(\
 		       IL_RX_HDR(x)->payload + \
 		       le16_to_cpu(IL_RX_HDR(x)->len)))
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 1600c344edbb..fcccde7bb659 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -1769,7 +1769,7 @@ il4965_tx_skb(struct il_priv *il,
 	/* Set up first empty entry in queue's array of Tx/cmd buffers */
 	out_cmd = txq->cmd[q->write_ptr];
 	out_meta = &txq->meta[q->write_ptr];
-	tx_cmd = &out_cmd->cmd.tx;
+	tx_cmd = container_of(&out_cmd->cmd.tx, struct il_tx_cmd, __hdr);
 	memset(&out_cmd->hdr, 0, sizeof(out_cmd->hdr));
 	memset(tx_cmd, 0, sizeof(struct il_tx_cmd));
 
diff --git a/drivers/net/wireless/intel/iwlegacy/commands.h b/drivers/net/wireless/intel/iwlegacy/commands.h
index 28cf4e832152..4a9fa8b83f0f 100644
--- a/drivers/net/wireless/intel/iwlegacy/commands.h
+++ b/drivers/net/wireless/intel/iwlegacy/commands.h
@@ -201,9 +201,6 @@ struct il_cmd_header {
 	 *  15          unsolicited RX or uCode-originated notification
 	 */
 	__le16 sequence;
-
-	/* command or response/notification data follows immediately */
-	u8 data[];
 } __packed;
 
 /**
@@ -1160,23 +1157,33 @@ struct il_wep_cmd {
 #define RX_MPDU_RES_STATUS_DEC_DONE_MSK	(0x800)
 
 struct il3945_rx_frame_stats {
-	u8 phy_count;
-	u8 id;
-	u8 rssi;
-	u8 agc;
-	__le16 sig_avg;
-	__le16 noise_diff;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(il3945_rx_frame_stats_hdr, hdr, __packed,
+		u8 phy_count;
+		u8 id;
+		u8 rssi;
+		u8 agc;
+		__le16 sig_avg;
+		__le16 noise_diff;
+	);
 	u8 payload[];
 } __packed;
+static_assert(offsetof(struct il3945_rx_frame_stats, payload) == sizeof(struct il3945_rx_frame_stats_hdr),
+	      "struct member likely outside of __struct_group()");
 
 struct il3945_rx_frame_hdr {
-	__le16 channel;
-	__le16 phy_flags;
-	u8 reserved1;
-	u8 rate;
-	__le16 len;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(il3945_rx_frame_hdr_hdr, hdr, __packed,
+		__le16 channel;
+		__le16 phy_flags;
+		u8 reserved1;
+		u8 rate;
+		__le16 len;
+	);
 	u8 payload[];
 } __packed;
+static_assert(offsetof(struct il3945_rx_frame_hdr, payload) == sizeof(struct il3945_rx_frame_hdr_hdr),
+	      "struct member likely outside of __struct_group()");
 
 struct il3945_rx_frame_end {
 	__le32 status;
@@ -1193,8 +1200,8 @@ struct il3945_rx_frame_end {
  * stats.phy_count
  */
 struct il3945_rx_frame {
-	struct il3945_rx_frame_stats stats;
-	struct il3945_rx_frame_hdr hdr;
+	struct il3945_rx_frame_stats_hdr stats;
+	struct il3945_rx_frame_hdr_hdr hdr;
 	struct il3945_rx_frame_end end;
 } __packed;
 
@@ -1352,67 +1359,69 @@ struct il_rx_mpdu_res_start {
  */
 
 struct il3945_tx_cmd {
-	/*
-	 * MPDU byte count:
-	 * MAC header (24/26/30/32 bytes) + 2 bytes pad if 26/30 header size,
-	 * + 8 byte IV for CCM or TKIP (not used for WEP)
-	 * + Data payload
-	 * + 8-byte MIC (not used for CCM/WEP)
-	 * NOTE:  Does not include Tx command bytes, post-MAC pad bytes,
-	 *        MIC (CCM) 8 bytes, ICV (WEP/TKIP/CKIP) 4 bytes, CRC 4 bytes.i
-	 * Range: 14-2342 bytes.
-	 */
-	__le16 len;
-
-	/*
-	 * MPDU or MSDU byte count for next frame.
-	 * Used for fragmentation and bursting, but not 11n aggregation.
-	 * Same as "len", but for next frame.  Set to 0 if not applicable.
-	 */
-	__le16 next_frame_len;
-
-	__le32 tx_flags;	/* TX_CMD_FLG_* */
-
-	u8 rate;
-
-	/* Index of recipient station in uCode's station table */
-	u8 sta_id;
-	u8 tid_tspec;
-	u8 sec_ctl;
-	u8 key[16];
-	union {
-		u8 byte[8];
-		__le16 word[4];
-		__le32 dw[2];
-	} tkip_mic;
-	__le32 next_frame_info;
-	union {
-		__le32 life_time;
-		__le32 attempt;
-	} stop_time;
-	u8 supp_rates[2];
-	u8 rts_retry_limit;	/*byte 50 */
-	u8 data_retry_limit;	/*byte 51 */
-	union {
-		__le16 pm_frame_timeout;
-		__le16 attempt_duration;
-	} timeout;
-
-	/*
-	 * Duration of EDCA burst Tx Opportunity, in 32-usec units.
-	 * Set this if txop time is not specified by HCCA protocol (e.g. by AP).
-	 */
-	__le16 driver_txop;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(il3945_tx_cmd_hdr, __hdr, __packed,
+		/*
+		 * MPDU byte count:
+		 * MAC header (24/26/30/32 bytes) + 2 bytes pad if 26/30 header size,
+		 * + 8 byte IV for CCM or TKIP (not used for WEP)
+		 * + Data payload
+		 * + 8-byte MIC (not used for CCM/WEP)
+		 * NOTE:  Does not include Tx command bytes, post-MAC pad bytes,
+		 *        MIC (CCM) 8 bytes, ICV (WEP/TKIP/CKIP) 4 bytes, CRC 4 bytes.i
+		 * Range: 14-2342 bytes.
+		 */
+		__le16 len;
+
+		/*
+		 * MPDU or MSDU byte count for next frame.
+		 * Used for fragmentation and bursting, but not 11n aggregation.
+		 * Same as "len", but for next frame.  Set to 0 if not applicable.
+		 */
+		__le16 next_frame_len;
+
+		__le32 tx_flags;	/* TX_CMD_FLG_* */
+
+		u8 rate;
+
+		/* Index of recipient station in uCode's station table */
+		u8 sta_id;
+		u8 tid_tspec;
+		u8 sec_ctl;
+		u8 key[16];
+		union {
+			u8 byte[8];
+			__le16 word[4];
+			__le32 dw[2];
+		} tkip_mic;
+		__le32 next_frame_info;
+		union {
+			__le32 life_time;
+			__le32 attempt;
+		} stop_time;
+		u8 supp_rates[2];
+		u8 rts_retry_limit;	/*byte 50 */
+		u8 data_retry_limit;	/*byte 51 */
+		union {
+			__le16 pm_frame_timeout;
+			__le16 attempt_duration;
+		} timeout;
+
+		/*
+		 * Duration of EDCA burst Tx Opportunity, in 32-usec units.
+		 * Set this if txop time is not specified by HCCA protocol (e.g. by AP).
+		 */
+		__le16 driver_txop;
+	);
 
 	/*
 	 * MAC header goes here, followed by 2 bytes padding if MAC header
 	 * length is 26 or 30 bytes, followed by payload data
 	 */
-	union {
-		DECLARE_FLEX_ARRAY(u8, payload);
-		DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr);
-	};
+	struct ieee80211_hdr hdr[];
 } __packed;
+static_assert(offsetof(struct il3945_tx_cmd, hdr) == sizeof(struct il3945_tx_cmd_hdr),
+	      "struct member likely outside of __struct_group()");
 
 /*
  * C_TX = 0x1c (response)
@@ -1438,83 +1447,87 @@ struct il_dram_scratch {
 } __packed;
 
 struct il_tx_cmd {
-	/*
-	 * MPDU byte count:
-	 * MAC header (24/26/30/32 bytes) + 2 bytes pad if 26/30 header size,
-	 * + 8 byte IV for CCM or TKIP (not used for WEP)
-	 * + Data payload
-	 * + 8-byte MIC (not used for CCM/WEP)
-	 * NOTE:  Does not include Tx command bytes, post-MAC pad bytes,
-	 *        MIC (CCM) 8 bytes, ICV (WEP/TKIP/CKIP) 4 bytes, CRC 4 bytes.i
-	 * Range: 14-2342 bytes.
-	 */
-	__le16 len;
-
-	/*
-	 * MPDU or MSDU byte count for next frame.
-	 * Used for fragmentation and bursting, but not 11n aggregation.
-	 * Same as "len", but for next frame.  Set to 0 if not applicable.
-	 */
-	__le16 next_frame_len;
-
-	__le32 tx_flags;	/* TX_CMD_FLG_* */
-
-	/* uCode may modify this field of the Tx command (in host DRAM!).
-	 * Driver must also set dram_lsb_ptr and dram_msb_ptr in this cmd. */
-	struct il_dram_scratch scratch;
-
-	/* Rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is cleared. */
-	__le32 rate_n_flags;	/* RATE_MCS_* */
-
-	/* Index of destination station in uCode's station table */
-	u8 sta_id;
-
-	/* Type of security encryption:  CCM or TKIP */
-	u8 sec_ctl;		/* TX_CMD_SEC_* */
-
-	/*
-	 * Index into rate table (see C_TX_LINK_QUALITY_CMD) for initial
-	 * Tx attempt, if TX_CMD_FLG_STA_RATE_MSK is set.  Normally "0" for
-	 * data frames, this field may be used to selectively reduce initial
-	 * rate (via non-0 value) for special frames (e.g. management), while
-	 * still supporting rate scaling for all frames.
-	 */
-	u8 initial_rate_idx;
-	u8 reserved;
-	u8 key[16];
-	__le16 next_frame_flags;
-	__le16 reserved2;
-	union {
-		__le32 life_time;
-		__le32 attempt;
-	} stop_time;
-
-	/* Host DRAM physical address pointer to "scratch" in this command.
-	 * Must be dword aligned.  "0" in dram_lsb_ptr disables usage. */
-	__le32 dram_lsb_ptr;
-	u8 dram_msb_ptr;
-
-	u8 rts_retry_limit;	/*byte 50 */
-	u8 data_retry_limit;	/*byte 51 */
-	u8 tid_tspec;
-	union {
-		__le16 pm_frame_timeout;
-		__le16 attempt_duration;
-	} timeout;
-
-	/*
-	 * Duration of EDCA burst Tx Opportunity, in 32-usec units.
-	 * Set this if txop time is not specified by HCCA protocol (e.g. by AP).
-	 */
-	__le16 driver_txop;
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(il_tx_cmd_hdr, __hdr, __packed,
+		/*
+		 * MPDU byte count:
+		 * MAC header (24/26/30/32 bytes) + 2 bytes pad if 26/30 header size,
+		 * + 8 byte IV for CCM or TKIP (not used for WEP)
+		 * + Data payload
+		 * + 8-byte MIC (not used for CCM/WEP)
+		 * NOTE:  Does not include Tx command bytes, post-MAC pad bytes,
+		 *        MIC (CCM) 8 bytes, ICV (WEP/TKIP/CKIP) 4 bytes, CRC 4 bytes.i
+		 * Range: 14-2342 bytes.
+		 */
+		__le16 len;
+
+		/*
+		 * MPDU or MSDU byte count for next frame.
+		 * Used for fragmentation and bursting, but not 11n aggregation.
+		 * Same as "len", but for next frame.  Set to 0 if not applicable.
+		 */
+		__le16 next_frame_len;
+
+		__le32 tx_flags;	/* TX_CMD_FLG_* */
+
+		/* uCode may modify this field of the Tx command (in host DRAM!).
+		 * Driver must also set dram_lsb_ptr and dram_msb_ptr in this cmd. */
+		struct il_dram_scratch scratch;
+
+		/* Rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is cleared. */
+		__le32 rate_n_flags;	/* RATE_MCS_* */
+
+		/* Index of destination station in uCode's station table */
+		u8 sta_id;
+
+		/* Type of security encryption:  CCM or TKIP */
+		u8 sec_ctl;		/* TX_CMD_SEC_* */
+
+		/*
+		 * Index into rate table (see C_TX_LINK_QUALITY_CMD) for initial
+		 * Tx attempt, if TX_CMD_FLG_STA_RATE_MSK is set.  Normally "0" for
+		 * data frames, this field may be used to selectively reduce initial
+		 * rate (via non-0 value) for special frames (e.g. management), while
+		 * still supporting rate scaling for all frames.
+		 */
+		u8 initial_rate_idx;
+		u8 reserved;
+		u8 key[16];
+		__le16 next_frame_flags;
+		__le16 reserved2;
+		union {
+			__le32 life_time;
+			__le32 attempt;
+		} stop_time;
+
+		/* Host DRAM physical address pointer to "scratch" in this command.
+		 * Must be dword aligned.  "0" in dram_lsb_ptr disables usage. */
+		__le32 dram_lsb_ptr;
+		u8 dram_msb_ptr;
+
+		u8 rts_retry_limit;	/*byte 50 */
+		u8 data_retry_limit;	/*byte 51 */
+		u8 tid_tspec;
+		union {
+			__le16 pm_frame_timeout;
+			__le16 attempt_duration;
+		} timeout;
+
+		/*
+		 * Duration of EDCA burst Tx Opportunity, in 32-usec units.
+		 * Set this if txop time is not specified by HCCA protocol (e.g. by AP).
+		 */
+		__le16 driver_txop;
+	);
 
 	/*
 	 * MAC header goes here, followed by 2 bytes padding if MAC header
 	 * length is 26 or 30 bytes, followed by payload data
 	 */
-	u8 payload[0];
 	struct ieee80211_hdr hdr[];
 } __packed;
+static_assert(offsetof(struct il_tx_cmd, hdr) == sizeof(struct il_tx_cmd_hdr),
+	      "struct member likely outside of __struct_group()");
 
 /* TX command response is sent after *3945* transmission attempts.
  *
@@ -2502,7 +2515,7 @@ struct il3945_scan_cmd {
 
 	/* For active scans (set to all-0s for passive scans).
 	 * Does not include payload.  Must specify Tx rate; no rate scaling. */
-	struct il3945_tx_cmd tx_cmd;
+	struct il3945_tx_cmd_hdr tx_cmd;
 
 	/* For directed active scans (set to all-0s otherwise) */
 	struct il_ssid_ie direct_scan[PROBE_OPTION_MAX_3945];
@@ -2546,7 +2559,7 @@ struct il_scan_cmd {
 
 	/* For active scans (set to all-0s for passive scans).
 	 * Does not include payload.  Must specify Tx rate; no rate scaling. */
-	struct il_tx_cmd tx_cmd;
+	struct il_tx_cmd_hdr tx_cmd;
 
 	/* For directed active scans (set to all-0s otherwise) */
 	struct il_ssid_ie direct_scan[PROBE_OPTION_MAX];
@@ -2662,7 +2675,7 @@ struct il4965_beacon_notif {
  */
 
 struct il3945_tx_beacon_cmd {
-	struct il3945_tx_cmd tx;
+	struct il3945_tx_cmd_hdr tx;
 	__le16 tim_idx;
 	u8 tim_size;
 	u8 reserved1;
@@ -2670,7 +2683,7 @@ struct il3945_tx_beacon_cmd {
 } __packed;
 
 struct il_tx_beacon_cmd {
-	struct il_tx_cmd tx;
+	struct il_tx_cmd_hdr tx;
 	__le16 tim_idx;
 	u8 tim_size;
 	u8 reserved1;
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index 69687fcf963f..2147781b5fff 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -553,7 +553,7 @@ struct il_device_cmd {
 		u8 val8;
 		u16 val16;
 		u32 val32;
-		struct il_tx_cmd tx;
+		struct il_tx_cmd_hdr tx;
 		u8 payload[DEF_CMD_PAYLOAD_SIZE];
 	} __packed cmd;
 } __packed;
-- 
cgit v1.3-3-g829e


From c9f4c1ec69728310a31080c266b8529381c1a7fa Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 15 Aug 2024 14:29:27 +0300
Subject: wifi: mwifiex: Fix uninitialized variable in
 mwifiex_cfg80211_authenticate()

Smatch complains that:

    drivers/net/wireless/marvell/mwifiex/cfg80211.c:4408 mwifiex_cfg80211_authenticate()
    error: uninitialized symbol 'varptr'.

It's a check for NULL, but "varptr" is either non-NULL or uninitialized.
Initialize it to NULL.

Fixes: 36995892c271 ("wifi: mwifiex: add host mlme for client mode")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/d7d043b2-95d5-4e1d-b340-5d7330053ac6@stanley.mountain
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index e36ef075fe05..888b586da266 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4284,7 +4284,7 @@ mwifiex_cfg80211_authenticate(struct wiphy *wiphy,
 	struct mwifiex_txinfo *tx_info;
 	u32 tx_control = 0, pkt_type = PKT_TYPE_MGMT;
 	u8 trans = 1, status_code = 0;
-	u8 *varptr;
+	u8 *varptr = NULL;
 
 	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
 		mwifiex_dbg(priv->adapter, ERROR, "Interface role is AP\n");
-- 
cgit v1.3-3-g829e


From 924b8bea870b4968cec4784676e6b27597e25d01 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Sat, 17 Aug 2024 15:18:17 +0200
Subject: net: ipv6: ioam6: code alignment

This patch prepares the next one by correcting the alignment of some
lines.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ioam6_iptunnel.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index bf7120ecea1e..cd2522f04edf 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -43,7 +43,7 @@ struct ioam6_lwt {
 	atomic_t pkt_cnt;
 	u8 mode;
 	struct in6_addr tundst;
-	struct ioam6_lwt_encap	tuninfo;
+	struct ioam6_lwt_encap tuninfo;
 };
 
 static const struct netlink_range_validation freq_range = {
@@ -73,7 +73,8 @@ static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = {
 						   IOAM6_IPTUNNEL_MODE_MIN,
 						   IOAM6_IPTUNNEL_MODE_MAX),
 	[IOAM6_IPTUNNEL_DST]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
-	[IOAM6_IPTUNNEL_TRACE]	= NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)),
+	[IOAM6_IPTUNNEL_TRACE]	= NLA_POLICY_EXACT_LEN(
+					sizeof(struct ioam6_trace_hdr)),
 };
 
 static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace)
@@ -459,9 +460,9 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
 static const struct lwtunnel_encap_ops ioam6_iptun_ops = {
 	.build_state		= ioam6_build_state,
 	.destroy_state		= ioam6_destroy_state,
-	.output		= ioam6_output,
+	.output			= ioam6_output,
 	.fill_encap		= ioam6_fill_encap_info,
-	.get_encap_size	= ioam6_encap_nlsize,
+	.get_encap_size		= ioam6_encap_nlsize,
 	.cmp_encap		= ioam6_encap_cmp,
 	.owner			= THIS_MODULE,
 };
-- 
cgit v1.3-3-g829e


From 273f8c142003dfd874d45b1a60965809e95ccd50 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Sat, 17 Aug 2024 15:18:18 +0200
Subject: net: ipv6: ioam6: new feature tunsrc

This patch provides a new feature (i.e., "tunsrc") for the tunnel (i.e.,
"encap") mode of ioam6. Just like seg6 already does, except it is
attached to a route. The "tunsrc" is optional: when not provided (by
default), the automatic resolution is applied. Using "tunsrc" when
possible has a benefit: performance. See the comparison:
 - before (= "encap" mode): https://ibb.co/bNCzvf7
 - after (= "encap" mode with "tunsrc"): https://ibb.co/PT8L6yq

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/uapi/linux/ioam6_iptunnel.h |  6 ++++
 net/ipv6/ioam6_iptunnel.c           | 65 ++++++++++++++++++++++++++++++++-----
 2 files changed, 63 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h
index 38f6a8fdfd34..8aef21e4a8c1 100644
--- a/include/uapi/linux/ioam6_iptunnel.h
+++ b/include/uapi/linux/ioam6_iptunnel.h
@@ -50,6 +50,12 @@ enum {
 	IOAM6_IPTUNNEL_FREQ_K,		/* u32 */
 	IOAM6_IPTUNNEL_FREQ_N,		/* u32 */
 
+	/* Tunnel src address.
+	 * For encap,auto modes.
+	 * Optional (automatic if not provided).
+	 */
+	IOAM6_IPTUNNEL_SRC,		/* struct in6_addr */
+
 	__IOAM6_IPTUNNEL_MAX,
 };
 
diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index cd2522f04edf..e34e1ff24546 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -42,6 +42,8 @@ struct ioam6_lwt {
 	struct ioam6_lwt_freq freq;
 	atomic_t pkt_cnt;
 	u8 mode;
+	bool has_tunsrc;
+	struct in6_addr tunsrc;
 	struct in6_addr tundst;
 	struct ioam6_lwt_encap tuninfo;
 };
@@ -72,6 +74,7 @@ static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = {
 	[IOAM6_IPTUNNEL_MODE]	= NLA_POLICY_RANGE(NLA_U8,
 						   IOAM6_IPTUNNEL_MODE_MIN,
 						   IOAM6_IPTUNNEL_MODE_MAX),
+	[IOAM6_IPTUNNEL_SRC]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[IOAM6_IPTUNNEL_DST]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[IOAM6_IPTUNNEL_TRACE]	= NLA_POLICY_EXACT_LEN(
 					sizeof(struct ioam6_trace_hdr)),
@@ -144,6 +147,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 	else
 		mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]);
 
+	if (tb[IOAM6_IPTUNNEL_SRC] && mode == IOAM6_IPTUNNEL_MODE_INLINE) {
+		NL_SET_ERR_MSG(extack, "no tunnel src expected with this mode");
+		return -EINVAL;
+	}
+
 	if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) {
 		NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination");
 		return -EINVAL;
@@ -168,16 +176,29 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 
 	ilwt = ioam6_lwt_state(lwt);
 	err = dst_cache_init(&ilwt->cache, GFP_ATOMIC);
-	if (err) {
-		kfree(lwt);
-		return err;
-	}
+	if (err)
+		goto free_lwt;
 
 	atomic_set(&ilwt->pkt_cnt, 0);
 	ilwt->freq.k = freq_k;
 	ilwt->freq.n = freq_n;
 
 	ilwt->mode = mode;
+
+	if (!tb[IOAM6_IPTUNNEL_SRC]) {
+		ilwt->has_tunsrc = false;
+	} else {
+		ilwt->has_tunsrc = true;
+		ilwt->tunsrc = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_SRC]);
+
+		if (ipv6_addr_any(&ilwt->tunsrc)) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_SRC],
+					    "invalid tunnel source address");
+			err = -EINVAL;
+			goto free_cache;
+		}
+	}
+
 	if (tb[IOAM6_IPTUNNEL_DST])
 		ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]);
 
@@ -202,6 +223,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 	*ts = lwt;
 
 	return 0;
+free_cache:
+	dst_cache_destroy(&ilwt->cache);
+free_lwt:
+	kfree(lwt);
+	return err;
 }
 
 static int ioam6_do_fill(struct net *net, struct sk_buff *skb)
@@ -257,6 +283,8 @@ static int ioam6_do_inline(struct net *net, struct sk_buff *skb,
 
 static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 			  struct ioam6_lwt_encap *tuninfo,
+			  bool has_tunsrc,
+			  struct in6_addr *tunsrc,
 			  struct in6_addr *tundst)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -286,8 +314,12 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 	hdr->nexthdr = NEXTHDR_HOP;
 	hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr));
 	hdr->daddr = *tundst;
-	ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr,
-			   IPV6_PREFER_SRC_PUBLIC, &hdr->saddr);
+
+	if (has_tunsrc)
+		memcpy(&hdr->saddr, tunsrc, sizeof(*tunsrc));
+	else
+		ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr,
+				   IPV6_PREFER_SRC_PUBLIC, &hdr->saddr);
 
 	skb_postpush_rcsum(skb, hdr, len);
 
@@ -329,7 +361,9 @@ do_inline:
 	case IOAM6_IPTUNNEL_MODE_ENCAP:
 do_encap:
 		/* Encapsulation (ip6ip6) */
-		err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst);
+		err = ioam6_do_encap(net, skb, &ilwt->tuninfo,
+				     ilwt->has_tunsrc, &ilwt->tunsrc,
+				     &ilwt->tundst);
 		if (unlikely(err))
 			goto drop;
 
@@ -415,6 +449,13 @@ static int ioam6_fill_encap_info(struct sk_buff *skb,
 		goto ret;
 
 	if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) {
+		if (ilwt->has_tunsrc) {
+			err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_SRC,
+					       &ilwt->tunsrc);
+			if (err)
+				goto ret;
+		}
+
 		err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst);
 		if (err)
 			goto ret;
@@ -436,8 +477,12 @@ static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate)
 		  nla_total_size(sizeof(ilwt->mode)) +
 		  nla_total_size(sizeof(ilwt->tuninfo.traceh));
 
-	if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE)
+	if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) {
+		if (ilwt->has_tunsrc)
+			nlsize += nla_total_size(sizeof(ilwt->tunsrc));
+
 		nlsize += nla_total_size(sizeof(ilwt->tundst));
+	}
 
 	return nlsize;
 }
@@ -452,8 +497,12 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
 	return (ilwt_a->freq.k != ilwt_b->freq.k ||
 		ilwt_a->freq.n != ilwt_b->freq.n ||
 		ilwt_a->mode != ilwt_b->mode ||
+		ilwt_a->has_tunsrc != ilwt_b->has_tunsrc ||
 		(ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE &&
 		 !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) ||
+		(ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE &&
+		 ilwt_a->has_tunsrc &&
+		 !ipv6_addr_equal(&ilwt_a->tunsrc, &ilwt_b->tunsrc)) ||
 		trace_a->namespace_id != trace_b->namespace_id);
 }
 
-- 
cgit v1.3-3-g829e


From 67a72043aa2e6f60f7bbe7bfa598ba168f16d04f Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Fri, 16 Aug 2024 08:56:10 +0200
Subject: wifi: mwifiex: remove unnecessary checks for valid priv

The pointers in adapter->priv[] are allocated in mwifiex_register().
With an allocation failed the function will return an error and
driver initialization is aborted. This makes all checks for valid
priv pointers unnecessary throughout the driver. In many places
the pointers are assumed to be valid without checks, this patch
removes the remaining checks.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240816-mwifiex-remove-priv-checks-v1-1-6dd6553e8ed9@pengutronix.de
---
 drivers/net/wireless/marvell/mwifiex/11n.c         |  2 -
 drivers/net/wireless/marvell/mwifiex/11n.h         |  4 +-
 .../net/wireless/marvell/mwifiex/11n_rxreorder.c   | 23 +++-----
 drivers/net/wireless/marvell/mwifiex/cfg80211.c    |  4 +-
 drivers/net/wireless/marvell/mwifiex/cmdevt.c      |  2 +-
 drivers/net/wireless/marvell/mwifiex/init.c        | 67 +++++++++-------------
 drivers/net/wireless/marvell/mwifiex/join.c        |  3 +-
 drivers/net/wireless/marvell/mwifiex/main.c        | 14 ++---
 drivers/net/wireless/marvell/mwifiex/main.h        | 30 ++++------
 drivers/net/wireless/marvell/mwifiex/scan.c        |  2 -
 drivers/net/wireless/marvell/mwifiex/sta_ioctl.c   |  3 +-
 drivers/net/wireless/marvell/mwifiex/usb.c         |  7 +--
 drivers/net/wireless/marvell/mwifiex/wmm.c         |  7 ---
 13 files changed, 59 insertions(+), 109 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index c0c635e74bc5..66f0f5377ac1 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -881,8 +881,6 @@ void mwifiex_update_ampdu_txwinsize(struct mwifiex_adapter *adapter)
 	struct mwifiex_private *priv;
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (!adapter->priv[i])
-			continue;
 		priv = adapter->priv[i];
 		tx_win_size = priv->add_ba_param.tx_win_size;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/11n.h b/drivers/net/wireless/marvell/mwifiex/11n.h
index 7738ebe1fec1..773bd5c0f007 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.h
+++ b/drivers/net/wireless/marvell/mwifiex/11n.h
@@ -108,9 +108,7 @@ static inline u8 mwifiex_space_avail_for_new_ba_stream(
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (priv)
-			ba_stream_num += list_count_nodes(
-				&priv->tx_ba_stream_tbl_ptr);
+		ba_stream_num += list_count_nodes(&priv->tx_ba_stream_tbl_ptr);
 	}
 
 	if (adapter->fw_api_ver == MWIFIEX_FW_V15) {
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 10690e82358b..cb948ca34373 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -810,8 +810,6 @@ void mwifiex_update_rxreor_flags(struct mwifiex_adapter *adapter, u8 flags)
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (!priv)
-			continue;
 
 		spin_lock_bh(&priv->rx_reorder_tbl_lock);
 		list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list)
@@ -834,8 +832,6 @@ static void mwifiex_update_ampdu_rxwinsize(struct mwifiex_adapter *adapter,
 	dev_dbg(adapter->dev, "Update rxwinsize %d\n", coex_flag);
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (!adapter->priv[i])
-			continue;
 		priv = adapter->priv[i];
 		rx_win_size = priv->add_ba_param.rx_win_size;
 		if (coex_flag) {
@@ -882,17 +878,16 @@ void mwifiex_coex_ampdu_rxwinsize(struct mwifiex_adapter *adapter)
 	u8 count = 0;
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			priv = adapter->priv[i];
-			if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) {
-				if (priv->media_connected)
-					count++;
-			}
-			if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
-				if (priv->bss_started)
-					count++;
-			}
+		priv = adapter->priv[i];
+		if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_STA) {
+			if (priv->media_connected)
+				count++;
 		}
+		if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
+			if (priv->bss_started)
+				count++;
+		}
+
 		if (count >= MWIFIEX_BSS_COEX_COUNT)
 			break;
 	}
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 888b586da266..5697a02e6b8d 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -3508,7 +3508,7 @@ static int mwifiex_cfg80211_suspend(struct wiphy *wiphy,
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (priv && priv->netdev)
+		if (priv->netdev)
 			netif_device_detach(priv->netdev);
 	}
 
@@ -3580,7 +3580,7 @@ static int mwifiex_cfg80211_resume(struct wiphy *wiphy)
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (priv && priv->netdev)
+		if (priv->netdev)
 			netif_device_attach(priv->netdev);
 	}
 
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index ea6ebc9c23ef..7894102f03eb 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -482,7 +482,7 @@ int mwifiex_process_event(struct mwifiex_adapter *adapter)
 	if ((adapter->event_cause & EVENT_ID_MASK) == EVENT_RADAR_DETECTED) {
 		for (i = 0; i < adapter->priv_num; i++) {
 			priv = adapter->priv[i];
-			if (priv && mwifiex_is_11h_active(priv)) {
+			if (mwifiex_is_11h_active(priv)) {
 				adapter->event_cause |=
 					((priv->bss_num & 0xff) << 16) |
 					((priv->bss_type & 0xff) << 24);
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index a336d45b9677..8b61e45cd667 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -368,15 +368,13 @@ static void mwifiex_invalidate_lists(struct mwifiex_adapter *adapter)
 		list_del(&adapter->bss_prio_tbl[i].bss_prio_head);
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			priv = adapter->priv[i];
-			for (j = 0; j < MAX_NUM_TID; ++j)
-				list_del(&priv->wmm.tid_tbl_ptr[j].ra_list);
-			list_del(&priv->tx_ba_stream_tbl_ptr);
-			list_del(&priv->rx_reorder_tbl_ptr);
-			list_del(&priv->sta_list);
-			list_del(&priv->auto_tdls_list);
-		}
+		priv = adapter->priv[i];
+		for (j = 0; j < MAX_NUM_TID; ++j)
+			list_del(&priv->wmm.tid_tbl_ptr[j].ra_list);
+		list_del(&priv->tx_ba_stream_tbl_ptr);
+		list_del(&priv->rx_reorder_tbl_ptr);
+		list_del(&priv->sta_list);
+		list_del(&priv->auto_tdls_list);
 	}
 }
 
@@ -425,13 +423,11 @@ int mwifiex_init_lock_list(struct mwifiex_adapter *adapter)
 	spin_lock_init(&adapter->mwifiex_cmd_lock);
 	spin_lock_init(&adapter->queue_lock);
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			priv = adapter->priv[i];
-			spin_lock_init(&priv->wmm.ra_list_spinlock);
-			spin_lock_init(&priv->curr_bcn_buf_lock);
-			spin_lock_init(&priv->sta_list_spinlock);
-			spin_lock_init(&priv->auto_tdls_lock);
-		}
+		priv = adapter->priv[i];
+		spin_lock_init(&priv->wmm.ra_list_spinlock);
+		spin_lock_init(&priv->curr_bcn_buf_lock);
+		spin_lock_init(&priv->sta_list_spinlock);
+		spin_lock_init(&priv->auto_tdls_lock);
 	}
 
 	/* Initialize cmd_free_q */
@@ -455,8 +451,6 @@ int mwifiex_init_lock_list(struct mwifiex_adapter *adapter)
 	}
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (!adapter->priv[i])
-			continue;
 		priv = adapter->priv[i];
 		for (j = 0; j < MAX_NUM_TID; ++j)
 			INIT_LIST_HEAD(&priv->wmm.tid_tbl_ptr[j].ra_list);
@@ -506,31 +500,24 @@ int mwifiex_init_fw(struct mwifiex_adapter *adapter)
 	mwifiex_init_adapter(adapter);
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			priv = adapter->priv[i];
+		priv = adapter->priv[i];
 
-			/* Initialize private structure */
-			ret = mwifiex_init_priv(priv);
-			if (ret)
-				return -1;
-		}
+		/* Initialize private structure */
+		ret = mwifiex_init_priv(priv);
+		if (ret)
+			return -1;
 	}
 	if (adapter->mfg_mode) {
 		adapter->hw_status = MWIFIEX_HW_STATUS_READY;
 		ret = -EINPROGRESS;
 	} else {
 		for (i = 0; i < adapter->priv_num; i++) {
-			if (adapter->priv[i]) {
-				ret = mwifiex_sta_init_cmd(adapter->priv[i],
-							   first_sta, true);
-				if (ret == -1)
-					return -1;
-
-				first_sta = false;
-			}
-
-
+			ret = mwifiex_sta_init_cmd(adapter->priv[i],
+						   first_sta, true);
+			if (ret == -1)
+				return -1;
 
+			first_sta = false;
 		}
 	}
 
@@ -637,13 +624,11 @@ mwifiex_shutdown_drv(struct mwifiex_adapter *adapter)
 
 	/* Clean up Tx/Rx queues and delete BSS priority table */
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			priv = adapter->priv[i];
+		priv = adapter->priv[i];
 
-			mwifiex_clean_auto_tdls(priv);
-			mwifiex_abort_cac(priv);
-			mwifiex_free_priv(priv);
-		}
+		mwifiex_clean_auto_tdls(priv);
+		mwifiex_abort_cac(priv);
+		mwifiex_free_priv(priv);
 	}
 
 	atomic_set(&adapter->tx_queued, 0);
diff --git a/drivers/net/wireless/marvell/mwifiex/join.c b/drivers/net/wireless/marvell/mwifiex/join.c
index 249210fb2e75..6d8f1d1d7ca4 100644
--- a/drivers/net/wireless/marvell/mwifiex/join.c
+++ b/drivers/net/wireless/marvell/mwifiex/join.c
@@ -1582,8 +1582,7 @@ void mwifiex_deauthenticate_all(struct mwifiex_adapter *adapter)
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (priv)
-			mwifiex_deauthenticate(priv, NULL);
+		mwifiex_deauthenticate(priv, NULL);
 	}
 }
 EXPORT_SYMBOL_GPL(mwifiex_deauthenticate_all);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 88cd2d6a1dcb..96d1f6039fbc 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -127,10 +127,8 @@ static int mwifiex_unregister(struct mwifiex_adapter *adapter)
 
 	/* Free private structures */
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			mwifiex_free_curr_bcn(adapter->priv[i]);
-			kfree(adapter->priv[i]);
-		}
+		mwifiex_free_curr_bcn(adapter->priv[i]);
+		kfree(adapter->priv[i]);
 	}
 
 	if (adapter->nd_info) {
@@ -1171,7 +1169,7 @@ void mwifiex_drv_info_dump(struct mwifiex_adapter *adapter)
 	}
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (!adapter->priv[i] || !adapter->priv[i]->netdev)
+		if (!adapter->priv[i]->netdev)
 			continue;
 		priv = adapter->priv[i];
 		p += sprintf(p, "\n[interface  : \"%s\"]\n",
@@ -1210,7 +1208,7 @@ void mwifiex_drv_info_dump(struct mwifiex_adapter *adapter)
 	debug_info = kzalloc(sizeof(*debug_info), GFP_KERNEL);
 	if (debug_info) {
 		for (i = 0; i < adapter->priv_num; i++) {
-			if (!adapter->priv[i] || !adapter->priv[i]->netdev)
+			if (!adapter->priv[i]->netdev)
 				continue;
 			priv = adapter->priv[i];
 			mwifiex_get_debug_info(priv, debug_info);
@@ -1472,7 +1470,7 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter)
 	/* Stop data */
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (priv && priv->netdev) {
+		if (priv->netdev) {
 			mwifiex_stop_net_dev_queue(priv->netdev, adapter);
 			if (netif_carrier_ok(priv->netdev))
 				netif_carrier_off(priv->netdev);
@@ -1497,8 +1495,6 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter)
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (!priv)
-			continue;
 		rtnl_lock();
 		if (priv->netdev &&
 		    priv->wdev.iftype != NL80211_IFTYPE_UNSPECIFIED) {
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 9024bb944e6a..529863edd7a2 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1303,14 +1303,12 @@ mwifiex_get_priv_by_id(struct mwifiex_adapter *adapter,
 	int i;
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			if (adapter->priv[i]->bss_mode == NL80211_IFTYPE_UNSPECIFIED)
-				continue;
+		if (adapter->priv[i]->bss_mode == NL80211_IFTYPE_UNSPECIFIED)
+			continue;
 
-			if ((adapter->priv[i]->bss_num == bss_num) &&
-			    (adapter->priv[i]->bss_type == bss_type))
-				break;
-		}
+		if ((adapter->priv[i]->bss_num == bss_num) &&
+		    (adapter->priv[i]->bss_type == bss_type))
+			break;
 	}
 	return ((i < adapter->priv_num) ? adapter->priv[i] : NULL);
 }
@@ -1326,11 +1324,9 @@ mwifiex_get_priv(struct mwifiex_adapter *adapter,
 	int i;
 
 	for (i = 0; i < adapter->priv_num; i++) {
-		if (adapter->priv[i]) {
-			if (bss_role == MWIFIEX_BSS_ROLE_ANY ||
-			    GET_BSS_ROLE(adapter->priv[i]) == bss_role)
-				break;
-		}
+		if (bss_role == MWIFIEX_BSS_ROLE_ANY ||
+		    GET_BSS_ROLE(adapter->priv[i]) == bss_role)
+			break;
 	}
 
 	return ((i < adapter->priv_num) ? adapter->priv[i] : NULL);
@@ -1348,12 +1344,10 @@ mwifiex_get_unused_bss_num(struct mwifiex_adapter *adapter, u8 bss_type)
 
 	memset(index, 0, sizeof(index));
 	for (i = 0; i < adapter->priv_num; i++)
-		if (adapter->priv[i]) {
-			if (adapter->priv[i]->bss_type == bss_type &&
-			    !(adapter->priv[i]->bss_mode ==
-			      NL80211_IFTYPE_UNSPECIFIED)) {
-				index[adapter->priv[i]->bss_num] = 1;
-			}
+		if (adapter->priv[i]->bss_type == bss_type &&
+		    !(adapter->priv[i]->bss_mode ==
+		      NL80211_IFTYPE_UNSPECIFIED)) {
+			index[adapter->priv[i]->bss_num] = 1;
 		}
 	for (j = 0; j < MWIFIEX_MAX_BSS_NUM; j++)
 		if (!index[j])
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index e782d652cb93..010e6ff91457 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -2051,8 +2051,6 @@ void mwifiex_cancel_scan(struct mwifiex_adapter *adapter)
 		spin_unlock_bh(&adapter->mwifiex_cmd_lock);
 		for (i = 0; i < adapter->priv_num; i++) {
 			priv = adapter->priv[i];
-			if (!priv)
-				continue;
 			if (priv->scan_request) {
 				struct cfg80211_scan_info info = {
 					.aborted = true,
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index a94659988a4c..d3cba6895f8c 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -503,8 +503,7 @@ int mwifiex_enable_hs(struct mwifiex_adapter *adapter)
 	if (disconnect_on_suspend) {
 		for (i = 0; i < adapter->priv_num; i++) {
 			priv = adapter->priv[i];
-			if (priv)
-				mwifiex_deauthenticate(priv, NULL);
+			mwifiex_deauthenticate(priv, NULL);
 		}
 	}
 
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 515e6db410f2..6085cd50970d 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -745,8 +745,6 @@ static void mwifiex_usb_port_resync(struct mwifiex_adapter *adapter)
 	if (adapter->usb_mc_status) {
 		for (i = 0; i < adapter->priv_num; i++) {
 			priv = adapter->priv[i];
-			if (!priv)
-				continue;
 			if ((priv->bss_role == MWIFIEX_BSS_ROLE_UAP &&
 			     !priv->bss_started) ||
 			    (priv->bss_role == MWIFIEX_BSS_ROLE_STA &&
@@ -758,8 +756,6 @@ static void mwifiex_usb_port_resync(struct mwifiex_adapter *adapter)
 	} else {
 		for (i = 0; i < adapter->priv_num; i++) {
 			priv = adapter->priv[i];
-			if (!priv)
-				continue;
 			if ((priv->bss_role == MWIFIEX_BSS_ROLE_UAP &&
 			     priv->bss_started) ||
 			    (priv->bss_role == MWIFIEX_BSS_ROLE_STA &&
@@ -770,8 +766,7 @@ static void mwifiex_usb_port_resync(struct mwifiex_adapter *adapter)
 		}
 		for (i = 0; i < adapter->priv_num; i++) {
 			priv = adapter->priv[i];
-			if (priv)
-				priv->usb_port = active_port;
+			priv->usb_port = active_port;
 		}
 		for (i = 0; i < MWIFIEX_TX_DATA_PORT; i++) {
 			if (active_port == card->port[i].tx_data_ep)
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index 8558995e8fc7..bcb61dab7dc8 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -454,8 +454,6 @@ int mwifiex_bypass_txlist_empty(struct mwifiex_adapter *adapter)
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		priv = adapter->priv[i];
-		if (!priv)
-			continue;
 		if (adapter->if_ops.is_port_ready &&
 		    !adapter->if_ops.is_port_ready(priv))
 			continue;
@@ -477,8 +475,6 @@ mwifiex_wmm_lists_empty(struct mwifiex_adapter *adapter)
 
 	for (i = 0; i < adapter->priv_num; ++i) {
 		priv = adapter->priv[i];
-		if (!priv)
-			continue;
 		if (!priv->port_open &&
 		    (priv->bss_mode != NL80211_IFTYPE_ADHOC))
 			continue;
@@ -1491,9 +1487,6 @@ void mwifiex_process_bypass_tx(struct mwifiex_adapter *adapter)
 	for (i = 0; i < adapter->priv_num; ++i) {
 		priv = adapter->priv[i];
 
-		if (!priv)
-			continue;
-
 		if (adapter->if_ops.is_port_ready &&
 		    !adapter->if_ops.is_port_ready(priv))
 			continue;
-- 
cgit v1.3-3-g829e


From bcc3773c49af2426093645473fe02a5a8e765587 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 20 Aug 2024 18:22:27 -0700
Subject: selftests: net: add helper for checking if nettest is available

A few tests check if nettest exists in the $PATH before adding
$PWD to $PATH and re-checking. They don't discard stderr on
the first check (and nettest is built as part of selftests,
so it's pretty normal for it to not be available in system $PATH).
This leads to output noise:

  which: no nettest in (/home/virtme/tools/fs/bin:/home/virtme/tools/fs/sbin:/home/virtme/tools/fs/usr/bin:/home/virtme/tools/fs/usr/sbin:/bin:/sbin:/usr/bin:/usr/sbin:/usr/local/bin)

Add a common helper for the check which does silence stderr.

There is another small functional change hiding here, because pmtu.sh
and fib_rule_tests.sh used to return from the test case rather than
completely exit. Building nettest is not hard, there should be no need
to maintain the ability to selectively skip cases in its absence.

Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20240821012227.1398769-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/fcnal-test.sh         |  9 +-----
 tools/testing/selftests/net/fib_rule_tests.sh     | 37 ++---------------------
 tools/testing/selftests/net/lib.sh                | 15 +++++++++
 tools/testing/selftests/net/pmtu.sh               |  8 +----
 tools/testing/selftests/net/unicast_extensions.sh |  9 +-----
 tools/testing/selftests/net/vrf_route_leaking.sh  |  3 +-
 6 files changed, 22 insertions(+), 59 deletions(-)

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 386ebd829df5..899dbad0104b 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -4304,14 +4304,7 @@ elif [ "$TESTS" = "ipv6" ]; then
 	TESTS="$TESTS_IPV6"
 fi
 
-# nettest can be run from PATH or from same directory as this selftest
-if ! which nettest >/dev/null; then
-	PATH=$PWD:$PATH
-	if ! which nettest >/dev/null; then
-		echo "'nettest' command not found; skipping tests"
-		exit $ksft_skip
-	fi
-fi
+check_gen_prog "nettest"
 
 declare -i nfail=0
 declare -i nsuccess=0
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 89034c5b69dc..53c5c1ad437e 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -51,31 +51,6 @@ log_test()
 	fi
 }
 
-check_nettest()
-{
-	if which nettest > /dev/null 2>&1; then
-		return 0
-	fi
-
-	# Add the selftest directory to PATH if not already done
-	if [ "${SELFTEST_PATH}" = "" ]; then
-		SELFTEST_PATH="$(dirname $0)"
-		PATH="${PATH}:${SELFTEST_PATH}"
-
-		# Now retry with the new path
-		if which nettest > /dev/null 2>&1; then
-			return 0
-		fi
-
-		if [ "${ret}" -eq 0 ]; then
-			ret="${ksft_skip}"
-		fi
-		echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')"
-	fi
-
-	return 1
-}
-
 setup()
 {
 	set -e
@@ -317,11 +292,6 @@ fib_rule6_connect_test()
 	echo
 	echo "IPv6 FIB rule connect tests"
 
-	if ! check_nettest; then
-		echo "SKIP: Could not run test without nettest tool"
-		return
-	fi
-
 	setup_peer
 	$IP -6 rule add dsfield 0x04 table $RTABLE_PEER
 
@@ -516,11 +486,6 @@ fib_rule4_connect_test()
 	echo
 	echo "IPv4 FIB rule connect tests"
 
-	if ! check_nettest; then
-		echo "SKIP: Could not run test without nettest tool"
-		return
-	fi
-
 	setup_peer
 	$IP -4 rule add dsfield 0x04 table $RTABLE_PEER
 
@@ -584,6 +549,8 @@ if [ ! -x "$(command -v ip)" ]; then
 	exit $ksft_skip
 fi
 
+check_gen_prog "nettest"
+
 # start clean
 cleanup &> /dev/null
 setup
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 8ee4489238ca..be8707bfb46e 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -125,6 +125,21 @@ slowwait_for_counter()
 	slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@"
 }
 
+# Check for existence of tools which are built as part of selftests
+# but may also already exist in $PATH
+check_gen_prog()
+{
+	local prog_name=$1; shift
+
+	if ! which $prog_name >/dev/null 2>/dev/null; then
+		PATH=$PWD:$PATH
+		if ! which $prog_name >/dev/null; then
+			echo "'$prog_name' command not found; skipping tests"
+			exit $ksft_skip
+		fi
+	fi
+}
+
 remove_ns_list()
 {
 	local item=$1
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 24a50622406c..569bce8b6383 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -681,13 +681,7 @@ setup_xfrm() {
 }
 
 setup_nettest_xfrm() {
-	if ! which nettest >/dev/null; then
-		PATH=$PWD:$PATH
-		if ! which nettest >/dev/null; then
-			echo "'nettest' command not found; skipping tests"
-			return 1
-		fi
-	fi
+	check_gen_prog "nettest"
 
 	[ ${1} -eq 6 ] && proto="-6" || proto=""
 	port=${2}
diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh
index f52aa5f7da52..3e751234ccfe 100755
--- a/tools/testing/selftests/net/unicast_extensions.sh
+++ b/tools/testing/selftests/net/unicast_extensions.sh
@@ -30,14 +30,7 @@
 
 source lib.sh
 
-# nettest can be run from PATH or from same directory as this selftest
-if ! which nettest >/dev/null; then
-	PATH=$PWD:$PATH
-	if ! which nettest >/dev/null; then
-		echo "'nettest' command not found; skipping tests"
-		exit $ksft_skip
-	fi
-fi
+check_gen_prog "nettest"
 
 result=0
 
diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh
index 152171fb1fc8..e9c2f71da207 100755
--- a/tools/testing/selftests/net/vrf_route_leaking.sh
+++ b/tools/testing/selftests/net/vrf_route_leaking.sh
@@ -59,7 +59,6 @@
 # while it is forwarded between different vrfs.
 
 source lib.sh
-PATH=$PWD:$PWD/tools/testing/selftests/net:$PATH
 VERBOSE=0
 PAUSE_ON_FAIL=no
 DEFAULT_TTYPE=sym
@@ -636,6 +635,8 @@ EOF
 # Some systems don't have a ping6 binary anymore
 command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping)
 
+check_gen_prog "nettest"
+
 TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_local ipv4_tcp_local
 ipv4_udp_local ipv4_ping_ttl_asym ipv4_traceroute_asym"
 TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_local ipv6_tcp_local ipv6_udp_local
-- 
cgit v1.3-3-g829e


From 812a2751e827fa1eb01f3bd268b4d74c23f4226a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 21 Aug 2024 09:30:14 +0200
Subject: net: airoha: configure hw mac address according to the port id

GDM1 port on EN7581 SoC is connected to the lan dsa switch.
GDM{2,3,4} can be used as wan port connected to an external
phy module. Configure hw mac address registers according to the port id.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20240821-airoha-eth-wan-mac-addr-v2-1-8706d0cd6cd5@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 32 +++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 1fb46db0c1e9..0c012efca3b0 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -67,9 +67,11 @@
 #define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
 #define FE_RST_CORE_MASK		BIT(0)
 
+#define REG_FE_WAN_MAC_H		0x0030
 #define REG_FE_LAN_MAC_H		0x0040
-#define REG_FE_LAN_MAC_LMIN		0x0044
-#define REG_FE_LAN_MAC_LMAX		0x0048
+
+#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
+#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
 
 #define REG_FE_CDM1_OQ_MAP0		0x0050
 #define REG_FE_CDM1_OQ_MAP1		0x0054
@@ -900,16 +902,28 @@ static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index,
 	airoha_qdma_set_irqmask(qdma, index, mask, 0);
 }
 
-static void airoha_set_macaddr(struct airoha_eth *eth, const u8 *addr)
+static bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port)
 {
-	u32 val;
+	/* GDM1 port on EN7581 SoC is connected to the lan dsa switch.
+	 * GDM{2,3,4} can be used as wan port connected to an external
+	 * phy module.
+	 */
+	return port->id == 1;
+}
+
+static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 val, reg;
 
+	reg = airhoa_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H
+					   : REG_FE_WAN_MAC_H;
 	val = (addr[0] << 16) | (addr[1] << 8) | addr[2];
-	airoha_fe_wr(eth, REG_FE_LAN_MAC_H, val);
+	airoha_fe_wr(eth, reg, val);
 
 	val = (addr[3] << 16) | (addr[4] << 8) | addr[5];
-	airoha_fe_wr(eth, REG_FE_LAN_MAC_LMIN, val);
-	airoha_fe_wr(eth, REG_FE_LAN_MAC_LMAX, val);
+	airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val);
+	airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val);
 }
 
 static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
@@ -2340,7 +2354,7 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
 	if (err)
 		return err;
 
-	airoha_set_macaddr(port->qdma->eth, dev->dev_addr);
+	airoha_set_macaddr(port, dev->dev_addr);
 
 	return 0;
 }
@@ -2349,7 +2363,7 @@ static int airoha_dev_init(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
 
-	airoha_set_macaddr(port->qdma->eth, dev->dev_addr);
+	airoha_set_macaddr(port, dev->dev_addr);
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From d6f75d86aa786740ef7a7607685e9e1039e30aab Mon Sep 17 00:00:00 2001
From: Yu Jiaoliang <yujiaoliang@vivo.com>
Date: Wed, 21 Aug 2024 16:14:45 +0800
Subject: nfp: bpf: Use kmemdup_array instead of kmemdup for multiple
 allocation

Let the kememdup_array() take care about multiplication and possible
overflows.

Signed-off-by: Yu Jiaoliang <yujiaoliang@vivo.com>
Signed-off-by: Louis Peens <louis.peens@corigine.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240821081447.12430-1-yujiaoliang@vivo.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index df2ab5cbd49b..3a02eef58cc6 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -4537,8 +4537,8 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv)
 	u64 *prog;
 	int err;
 
-	prog = kmemdup(nfp_prog->prog, nfp_prog->prog_len * sizeof(u64),
-		       GFP_KERNEL);
+	prog = kmemdup_array(nfp_prog->prog, nfp_prog->prog_len, sizeof(u64),
+			     GFP_KERNEL);
 	if (!prog)
 		return ERR_PTR(-ENOMEM);
 
-- 
cgit v1.3-3-g829e


From 5874e0c9f25661c2faefe4809907166defae3d7f Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 16:58:57 +0100
Subject: net: atlantic: Avoid warning about potential string truncation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

W=1 builds with GCC 14.2.0 warn that:

.../aq_ethtool.c:278:59: warning: ‘%d’ directive output may be truncated writing between 1 and 11 bytes into a region of size 6 [-Wformat-truncation=]
  278 |                                 snprintf(tc_string, 8, "TC%d ", tc);
      |                                                           ^~
.../aq_ethtool.c:278:56: note: directive argument in the range [-2147483641, 254]
  278 |                                 snprintf(tc_string, 8, "TC%d ", tc);
      |                                                        ^~~~~~~
.../aq_ethtool.c:278:33: note: ‘snprintf’ output between 5 and 15 bytes into a destination of size 8
  278 |                                 snprintf(tc_string, 8, "TC%d ", tc);
      |                                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

tc is always in the range 0 - cfg->tcs. And as cfg->tcs is a u8,
the range is 0 - 255. Further, on inspecting the code, it seems
that cfg->tcs will never be more than AQ_CFG_TCS_MAX (8), so
the range is actually 0 - 8.

So, it seems that the condition that GCC flags will not occur.
But, nonetheless, it would be nice if it didn't emit the warning.

It seems that this can be achieved by changing the format specifier
from %d to %u, in which case I believe GCC recognises an upper bound
on the range of tc of 0 - 255. After some experimentation I think
this is due to the combination of the use of %u and the type of
cfg->tcs (u8).

Empirically, updating the type of the tc variable to unsigned int
has the same effect.

As both of these changes seem to make sense in relation to what the code
is actually doing - iterating over unsigned values - do both.

Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240821-atlantic-str-v1-1-fa2cfe38ca00@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 38f22918c699..440ff4616fec 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -266,7 +266,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 		const int rx_stat_cnt = ARRAY_SIZE(aq_ethtool_queue_rx_stat_names);
 		const int tx_stat_cnt = ARRAY_SIZE(aq_ethtool_queue_tx_stat_names);
 		char tc_string[8];
-		int tc;
+		unsigned int tc;
 
 		memset(tc_string, 0, sizeof(tc_string));
 		memcpy(p, aq_ethtool_stat_names,
@@ -275,7 +275,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 
 		for (tc = 0; tc < cfg->tcs; tc++) {
 			if (cfg->is_qos)
-				snprintf(tc_string, 8, "TC%d ", tc);
+				snprintf(tc_string, 8, "TC%u ", tc);
 
 			for (i = 0; i < cfg->vecs; i++) {
 				for (si = 0; si < rx_stat_cnt; si++) {
-- 
cgit v1.3-3-g829e


From 1820b84f3c61fbe5d9cf82a09cb9733a23cd463c Mon Sep 17 00:00:00 2001
From: Abhinav Jain <jain.abhinav177@gmail.com>
Date: Wed, 21 Aug 2024 22:49:01 +0530
Subject: selftests: net: Create veth pair for testing in networkless kernel

Check if the netdev list is empty and create veth pair to be used for
feature on/off testing.
Remove the veth pair after testing is complete.

Signed-off-by: Abhinav Jain <jain.abhinav177@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240821171903.118324-2-jain.abhinav177@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netdevice.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index e3afcb424710..999d72b6670c 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -129,6 +129,7 @@ kci_netdev_ethtool()
 
 	kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev"
 	kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev"
+
 	return 0
 }
 
@@ -196,10 +197,24 @@ if [ ! -e "$TMP_LIST_NETDEV" ];then
 fi
 
 ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\  -f2 | cut -d: -f1> "$TMP_LIST_NETDEV"
+
+if [ ! -s "$TMP_LIST_NETDEV" ]; then
+	echo "No valid network device found, creating veth pair"
+	ip link add veth0 type veth peer name veth1
+	echo "veth0" > "$TMP_LIST_NETDEV"
+	veth_created=1
+fi
+
 while read netdev
 do
 	kci_test_netdev "$netdev"
 done < "$TMP_LIST_NETDEV"
 
+#clean up veth interface pair if it was created
+if [ "$veth_created" ]; then
+	ip link delete veth0
+	echo "Removed veth pair"
+fi
+
 rm "$TMP_LIST_NETDEV"
 exit 0
-- 
cgit v1.3-3-g829e


From 6ce7bdbc0d4bde7578727e95e7d138e364512b33 Mon Sep 17 00:00:00 2001
From: Abhinav Jain <jain.abhinav177@gmail.com>
Date: Wed, 21 Aug 2024 22:49:02 +0530
Subject: selftests: net: Add on/off checks for non-fixed features of interface

Implement on/off testing for all non-fixed features via while loop.

Signed-off-by: Abhinav Jain <jain.abhinav177@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240821171903.118324-3-jain.abhinav177@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netdevice.sh | 35 +++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index 999d72b6670c..f7752e1ebe22 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -124,7 +124,40 @@ kci_netdev_ethtool()
 		return 1
 	fi
 	echo "PASS: $netdev: ethtool list features"
-	#TODO for each non fixed features, try to turn them on/off
+
+	while read -r FEATURE VALUE FIXED; do
+		[ "$FEATURE" != "Features" ] || continue # Skip "Features"
+		[ "$FIXED" != "[fixed]" ] || continue # Skip fixed features
+		feature="${FEATURE%:*}"
+
+		ethtool --offload "$netdev" "$feature" off
+		if [ $? -eq 0 ]; then
+			echo "PASS: $netdev: Turned off feature: $feature"
+		else
+			echo "FAIL: $netdev: Failed to turn off feature:" \
+				"$feature"
+		fi
+
+		ethtool --offload "$netdev" "$feature" on
+		if [ $? -eq 0 ]; then
+			echo "PASS: $netdev: Turned on feature: $feature"
+		else
+			echo "FAIL: $netdev: Failed to turn on feature:" \
+				"$feature"
+		fi
+
+		#restore the feature to its initial state
+		ethtool --offload "$netdev" "$feature" "$VALUE"
+		if [ $? -eq 0 ]; then
+			echo "PASS: $netdev: Restore feature $feature" \
+				"to initial state $VALUE"
+		else
+			echo "FAIL: $netdev: Failed to restore feature" \
+				"$feature to initial state $VALUE"
+		fi
+
+	done < "$TMP_ETHTOOL_FEATURES"
+
 	rm "$TMP_ETHTOOL_FEATURES"
 
 	kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev"
-- 
cgit v1.3-3-g829e


From 8402a158028ffe030f3a02ec57b8c94cb94b137c Mon Sep 17 00:00:00 2001
From: Abhinav Jain <jain.abhinav177@gmail.com>
Date: Wed, 21 Aug 2024 22:49:03 +0530
Subject: selftests: net: Use XFAIL for operations not supported by the driver

Check if veth pair was created and if yes, xfail on setting IP address
logging an informational message.
Use XFAIL instead of SKIP for unsupported ethtool APIs.

Signed-off-by: Abhinav Jain <jain.abhinav177@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240821171903.118324-4-jain.abhinav177@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/netdevice.sh | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index f7752e1ebe22..438f7b2acc5f 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -67,8 +67,12 @@ kci_net_setup()
 		return $ksft_skip
 	fi
 
-	# TODO what ipaddr to set ? DHCP ?
-	echo "SKIP: $netdev: set IP address"
+	if [ "$veth_created" ]; then
+		echo "XFAIL: $netdev: set IP address unsupported for veth*"
+	else
+		# TODO what ipaddr to set ? DHCP ?
+		echo "SKIP: $netdev: set IP address"
+	fi
 	return $ksft_skip
 }
 
@@ -86,7 +90,7 @@ kci_netdev_ethtool_test()
 	ret=$?
 	if [ $ret -ne 0 ];then
 		if [ $ret -eq "$1" ];then
-			echo "SKIP: $netdev: ethtool $2 not supported"
+			echo "XFAIL: $netdev: ethtool $2 not supported"
 			return $ksft_skip
 		else
 			echo "FAIL: $netdev: ethtool $2"
-- 
cgit v1.3-3-g829e


From ef434fae72287a9cd0f7b85ad1701b998cce800b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:40 +0300
Subject: bpf: Unmask upper DSCP bits in bpf_fib_lookup() helper

The helper performs a FIB lookup according to the parameters in the
'params' argument, one of which is 'tos'. According to the test in
test_tc_neigh_fib.c, it seems that BPF programs are expected to
initialize the 'tos' field to the full 8 bit DS field from the IPv4
header.

Unmask the upper DSCP bits before invoking the IPv4 FIB lookup APIs so
that in the future the lookup could be performed according to the full
DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index f3c72cf86099..89f56fac48fb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -84,6 +84,7 @@
 #include <net/netkit.h>
 #include <linux/un.h>
 #include <net/xdp_sock_drv.h>
+#include <net/inet_dscp.h>
 
 #include "dev.h"
 
@@ -5899,7 +5900,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		fl4.flowi4_iif = params->ifindex;
 		fl4.flowi4_oif = 0;
 	}
-	fl4.flowi4_tos = params->tos & IPTOS_RT_MASK;
+	fl4.flowi4_tos = params->tos & INET_DSCP_MASK;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_flags = 0;
 
-- 
cgit v1.3-3-g829e


From bc52a4eecefdd686065f8f68ba9e1c83d4ce6f14 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:41 +0300
Subject: ipv4: Unmask upper DSCP bits in NETLINK_FIB_LOOKUP family

The NETLINK_FIB_LOOKUP netlink family can be used to perform a FIB
lookup according to user provided parameters and communicate the result
back to user space.

Unmask the upper DSCP bits of the user-provided DS field before invoking
the IPv4 FIB lookup API so that in the future the lookup could be
performed according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index da540ddb7af6..8b740f575da1 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
 	struct flowi4           fl4 = {
 		.flowi4_mark = frn->fl_mark,
 		.daddr = frn->fl_addr,
-		.flowi4_tos = frn->fl_tos & IPTOS_RT_MASK,
+		.flowi4_tos = frn->fl_tos & INET_DSCP_MASK,
 		.flowi4_scope = frn->fl_scope,
 	};
 	struct fib_table *tb;
-- 
cgit v1.3-3-g829e


From be2e9089cb34dfc958d8383a755bde3681a817b2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:42 +0300
Subject: ipv4: Unmask upper DSCP bits when constructing the Record Route
 option

The Record Route IP option records the addresses of the routers that
routed the packet. In the case of forwarded packets, the kernel performs
a route lookup via fib_lookup() and fills in the preferred source
address of the matched route.

Unmask the upper DSCP bits when performing the lookup so that in the
future the lookup could be performed according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 13c0f1d455f3..9b6528b7b562 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		struct flowi4 fl4 = {
 			.daddr = iph->daddr,
 			.saddr = iph->saddr,
-			.flowi4_tos = iph->tos & IPTOS_RT_MASK,
+			.flowi4_tos = iph->tos & INET_DSCP_MASK,
 			.flowi4_oif = rt->dst.dev->ifindex,
 			.flowi4_iif = skb->dev->ifindex,
 			.flowi4_mark = skb->mark,
-- 
cgit v1.3-3-g829e


From c1ae5ca69b691a7403e85047382fc4fd6a69ee9f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:43 +0300
Subject: netfilter: rpfilter: Unmask upper DSCP bits

The rpfilter match performs a reverse path filter test on a packet by
performing a FIB lookup with the source and destination addresses
swapped.

Unmask the upper DSCP bits of the DS field of the tested packet so that
in the future the FIB lookup could be performed according to the full
DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/netfilter/ipt_rpfilter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index ded5bef02f77..1ce7a1655b97 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
+#include <net/inet_dscp.h>
 #include <linux/ip.h>
 #include <net/ip.h>
 #include <net/ip_fib.h>
@@ -75,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.daddr = iph->saddr;
 	flow.saddr = rpfilter_get_saddr(iph->daddr);
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
-	flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
+	flow.flowi4_tos = iph->tos & INET_DSCP_MASK;
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
 	flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par));
 	flow.flowi4_uid = sock_net_uid(xt_net(par), NULL);
-- 
cgit v1.3-3-g829e


From 338385e059c5d299556fa341d10601ae72c6e932 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:44 +0300
Subject: netfilter: nft_fib: Unmask upper DSCP bits

In a similar fashion to the iptables rpfilter match, unmask the upper
DSCP bits of the DS field of the currently tested packet so that in the
future the FIB lookup could be performed according to the full DSCP
value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-6-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/netfilter/nft_fib_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index df94bc28c3d7..00da1332bbf1 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -10,6 +10,7 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nft_fib.h>
 
+#include <net/inet_dscp.h>
 #include <net/ip_fib.h>
 #include <net/route.h>
 
@@ -108,7 +109,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (priv->flags & NFTA_FIB_F_MARK)
 		fl4.flowi4_mark = pkt->skb->mark;
 
-	fl4.flowi4_tos = iph->tos & IPTOS_RT_MASK;
+	fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 
 	if (priv->flags & NFTA_FIB_F_DADDR) {
 		fl4.daddr = iph->daddr;
-- 
cgit v1.3-3-g829e


From 2bc9778b6696337f1e0b38f07522319296b39d83 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:45 +0300
Subject: ipv4: ipmr: Unmask upper DSCP bits in ipmr_rt_fib_lookup()

Unmask the upper DSCP bits when calling ipmr_fib_lookup() so that in the
future it could perform the FIB lookup according to the full DSCP value.

Note that ipmr_fib_lookup() performs a FIB rule lookup (returning the
relevant routing table) and that IPv4 multicast FIB rules do not support
matching on TOS / DSCP. However, it is still worth unmasking the upper
DSCP bits in case support for DSCP matching is ever added.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-7-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ipmr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 6c750bd13dd8..d5295b69bc0a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -62,6 +62,7 @@
 #include <net/fib_rules.h>
 #include <linux/netconf.h>
 #include <net/rtnh.h>
+#include <net/inet_dscp.h>
 
 #include <linux/nospec.h>
 
@@ -2080,7 +2081,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
 	struct flowi4 fl4 = {
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
-		.flowi4_tos = RT_TOS(iph->tos),
+		.flowi4_tos = iph->tos & INET_DSCP_MASK,
 		.flowi4_oif = (rt_is_output_route(rt) ?
 			       skb->dev->ifindex : 0),
 		.flowi4_iif = (rt_is_output_route(rt) ?
-- 
cgit v1.3-3-g829e


From 39d3628f7ceabd22385dcd6811ed4c353f7c859b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:46 +0300
Subject: ipv4: Unmask upper DSCP bits in fib_compute_spec_dst()

As explained in commit 35ebf65e851c ("ipv4: Create and use
fib_compute_spec_dst() helper."), the function is used - for example -
to determine the source address for an ICMP reply. If we are responding
to a multicast or broadcast packet, the source address is set to the
source address that we would use if we were to send a packet to the
unicast source of the original packet. This address is determined by
performing a FIB lookup and using the preferred source address of the
resulting route.

Unmask the upper DSCP bits of the DS field of the packet that triggered
the reply so that in the future the FIB lookup could be performed
according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-8-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 8b740f575da1..793e6781399a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -293,7 +293,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 			.flowi4_iif = LOOPBACK_IFINDEX,
 			.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
-			.flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK,
+			.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK,
 			.flowi4_scope = scope,
 			.flowi4_mark = vmark ? skb->mark : 0,
 		};
-- 
cgit v1.3-3-g829e


From df9131c7fafdc0d4c85686f5c7711a4dd4f3ae60 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:47 +0300
Subject: ipv4: Unmask upper DSCP bits in input route lookup

Unmask the upper DSCP bits in input route lookup so that in the future
the lookup could be performed according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-9-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 9b6528b7b562..73bb61162445 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2470,7 +2470,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	struct fib_result res;
 	int err;
 
-	tos &= IPTOS_RT_MASK;
+	tos &= INET_DSCP_MASK;
 	rcu_read_lock();
 	err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res);
 	rcu_read_unlock();
-- 
cgit v1.3-3-g829e


From b1251a6f1a9b475725a097e75196ee105076cbd1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:48 +0300
Subject: ipv4: Unmask upper DSCP bits in RTM_GETROUTE input route lookup

Unmask the upper DSCP bits when looking up an input route via the
RTM_GETROUTE netlink message so that in the future the lookup could be
performed according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-10-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 73bb61162445..524b70ab77a0 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3286,7 +3286,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		skb->dev	= dev;
 		skb->mark	= mark;
 		err = ip_route_input_rcu(skb, dst, src,
-					 rtm->rtm_tos & IPTOS_RT_MASK, dev,
+					 rtm->rtm_tos & INET_DSCP_MASK, dev,
 					 &res);
 
 		rt = skb_rtable(skb);
-- 
cgit v1.3-3-g829e


From 1c6f50b37f711b831d78973dad0df1da99ad0014 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:49 +0300
Subject: ipv4: icmp: Pass full DS field to ip_route_input()

Align the ICMP code to other callers of ip_route_input() and pass the
full DS field. In the future this will allow us to perform a route
lookup according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-11-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ab6d0d98dbc3..b8f56d03fcbb 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -545,7 +545,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 		orefdst = skb_in->_skb_refdst; /* save old refdst */
 		skb_dst_set(skb_in, NULL);
 		err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr,
-				     RT_TOS(tos), rt2->dst.dev);
+				     tos, rt2->dst.dev);
 
 		dst_release(&rt2->dst);
 		rt2 = skb_rtable(skb_in);
-- 
cgit v1.3-3-g829e


From b6791ac5ea49aec7f9ef123ebc728fa6a5f9090a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:50 +0300
Subject: ipv4: udp: Unmask upper DSCP bits during early demux

Unmask the upper DSCP bits when performing source validation for
multicast packets during early demux. In the future, this will allow us
to perform the FIB lookup which is performed as part of source
validation according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-12-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ddb86baaea6c..8accbf4cb295 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -115,6 +115,7 @@
 #include <net/addrconf.h>
 #include <net/udp_tunnel.h>
 #include <net/gro.h>
+#include <net/inet_dscp.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6_stubs.h>
 #endif
@@ -2618,7 +2619,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
 		if (!inet_sk(sk)->inet_daddr && in_dev)
 			return ip_mc_validate_source(skb, iph->daddr,
 						     iph->saddr,
-						     iph->tos & IPTOS_RT_MASK,
+						     iph->tos & INET_DSCP_MASK,
 						     skb->dev, in_dev, &itag);
 	}
 	return 0;
-- 
cgit v1.3-3-g829e


From be8b8ded77996cfcd1bb2f1d97b91106d5882877 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 21 Aug 2024 15:52:51 +0300
Subject: ipv4: Unmask upper DSCP bits when using hints

Unmask the upper DSCP bits when performing source validation and routing
a packet using the same route from a previously processed packet (hint).
In the future, this will allow us to perform the FIB lookup that is
performed as part of source validation according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240821125251.1571445-13-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 524b70ab77a0..f6972b24664a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2160,7 +2160,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (rt->rt_type != RTN_LOCAL)
 		goto skip_validate_source;
 
-	tos &= IPTOS_RT_MASK;
+	tos &= INET_DSCP_MASK;
 	err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
 	if (err < 0)
 		goto martian_source;
-- 
cgit v1.3-3-g829e


From 54f2f78d6b9f1f90e91aaf5dbb34a6198f65fdfd Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 16:30:13 +0100
Subject: xfrm: Correct spelling in xfrm.h

Correct spelling in xfrm.h.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 54cef89f6c1e..f7244ac4fa08 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -79,7 +79,7 @@
    policy entry has list of up to XFRM_MAX_DEPTH transformations,
    described by templates xfrm_tmpl. Each template is resolved
    to a complete xfrm_state (see below) and we pack bundle of transformations
-   to a dst_entry returned to requestor.
+   to a dst_entry returned to requester.
 
    dst -. xfrm  .-> xfrm_state #1
     |---. child .-> dst -. xfrm .-> xfrm_state #2
@@ -1016,7 +1016,7 @@ void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);
 
 struct xfrm_if_parms {
 	int link;		/* ifindex of underlying L2 interface */
-	u32 if_id;		/* interface identifyer */
+	u32 if_id;		/* interface identifier */
 	bool collect_md;
 };
 
-- 
cgit v1.3-3-g829e


From 3849687869092094003ba009dc00e2e0237a3b8a Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:09:55 +0200
Subject: net: phy: Introduce ethernet link topology representation

Link topologies containing multiple network PHYs attached to the same
net_device can be found when using a PHY as a media converter for use
with an SFP connector, on which an SFP transceiver containing a PHY can
be used.

With the current model, the transceiver's PHY can't be used for
operations such as cable testing, timestamping, macsec offload, etc.

The reason being that most of the logic for these configuration, coming
from either ethtool netlink or ioctls tend to use netdev->phydev, which
in multi-phy systems will reference the PHY closest to the MAC.

Introduce a numbering scheme allowing to enumerate PHY devices that
belong to any netdev, which can in turn allow userspace to take more
precise decisions with regard to each PHY's configuration.

The numbering is maintained per-netdev, in a phy_device_list.
The numbering works similarly to a netdevice's ifindex, with
identifiers that are only recycled once INT_MAX has been reached.

This prevents races that could occur between PHY listing and SFP
transceiver removal/insertion.

The identifiers are assigned at phy_attach time, as the numbering
depends on the netdevice the phy is attached to. The PHY index can be
re-used for PHYs that are persistent.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                         |   1 +
 drivers/net/phy/Makefile            |   2 +-
 drivers/net/phy/phy_device.c        |   6 +++
 drivers/net/phy/phy_link_topology.c | 105 ++++++++++++++++++++++++++++++++++++
 include/linux/netdevice.h           |   4 +-
 include/linux/phy.h                 |   4 ++
 include/linux/phy_link_topology.h   |  82 ++++++++++++++++++++++++++++
 include/uapi/linux/ethtool.h        |  16 ++++++
 net/core/dev.c                      |  15 ++++++
 9 files changed, 233 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/phy/phy_link_topology.c
 create mode 100644 include/linux/phy_link_topology.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 5f45b75eba96..e4fa9010fcb6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8341,6 +8341,7 @@ F:	include/linux/mii.h
 F:	include/linux/of_net.h
 F:	include/linux/phy.h
 F:	include/linux/phy_fixed.h
+F:	include/linux/phy_link_topology.h
 F:	include/linux/phylib_stubs.h
 F:	include/linux/platform_data/mdio-bcm-unimac.h
 F:	include/linux/platform_data/mdio-gpio.h
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index f086a606a87e..33adb3df5f64 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -2,7 +2,7 @@
 # Makefile for Linux PHY drivers
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
-				   linkmode.o
+				   linkmode.o phy_link_topology.o
 mdio-bus-y			+= mdio_bus.o mdio_device.o
 
 ifdef CONFIG_MDIO_DEVICE
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 159e71c1c972..d896c799f7c2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -29,6 +29,7 @@
 #include <linux/phy.h>
 #include <linux/phylib_stubs.h>
 #include <linux/phy_led_triggers.h>
+#include <linux/phy_link_topology.h>
 #include <linux/pse-pd/pse.h>
 #include <linux/property.h>
 #include <linux/rtnetlink.h>
@@ -1526,6 +1527,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 
 		if (phydev->sfp_bus_attached)
 			dev->sfp_bus = phydev->sfp_bus;
+
+		err = phy_link_topo_add_phy(dev, phydev, PHY_UPSTREAM_MAC, dev);
+		if (err)
+			goto error;
 	}
 
 	/* Some Ethernet drivers try to connect to a PHY device before
@@ -1953,6 +1958,7 @@ void phy_detach(struct phy_device *phydev)
 	if (dev) {
 		phydev->attached_dev->phydev = NULL;
 		phydev->attached_dev = NULL;
+		phy_link_topo_del_phy(dev, phydev);
 	}
 	phydev->phylink = NULL;
 
diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c
new file mode 100644
index 000000000000..4a5d73002a1a
--- /dev/null
+++ b/drivers/net/phy/phy_link_topology.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Infrastructure to handle all PHY devices connected to a given netdev,
+ * either directly or indirectly attached.
+ *
+ * Copyright (c) 2023 Maxime Chevallier<maxime.chevallier@bootlin.com>
+ */
+
+#include <linux/phy_link_topology.h>
+#include <linux/phy.h>
+#include <linux/rtnetlink.h>
+#include <linux/xarray.h>
+
+static int netdev_alloc_phy_link_topology(struct net_device *dev)
+{
+	struct phy_link_topology *topo;
+
+	topo = kzalloc(sizeof(*topo), GFP_KERNEL);
+	if (!topo)
+		return -ENOMEM;
+
+	xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1);
+	topo->next_phy_index = 1;
+
+	dev->link_topo = topo;
+
+	return 0;
+}
+
+int phy_link_topo_add_phy(struct net_device *dev,
+			  struct phy_device *phy,
+			  enum phy_upstream upt, void *upstream)
+{
+	struct phy_link_topology *topo = dev->link_topo;
+	struct phy_device_node *pdn;
+	int ret;
+
+	if (!topo) {
+		ret = netdev_alloc_phy_link_topology(dev);
+		if (ret)
+			return ret;
+
+		topo = dev->link_topo;
+	}
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn)
+		return -ENOMEM;
+
+	pdn->phy = phy;
+	switch (upt) {
+	case PHY_UPSTREAM_MAC:
+		pdn->upstream.netdev = (struct net_device *)upstream;
+		if (phy_on_sfp(phy))
+			pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus;
+		break;
+	case PHY_UPSTREAM_PHY:
+		pdn->upstream.phydev = (struct phy_device *)upstream;
+		if (phy_on_sfp(phy))
+			pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus;
+		break;
+	default:
+		ret = -EINVAL;
+		goto err;
+	}
+	pdn->upstream_type = upt;
+
+	/* Attempt to re-use a previously allocated phy_index */
+	if (phy->phyindex)
+		ret = xa_insert(&topo->phys, phy->phyindex, pdn, GFP_KERNEL);
+	else
+		ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn,
+				      xa_limit_32b, &topo->next_phy_index,
+				      GFP_KERNEL);
+
+	if (ret)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(pdn);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_link_topo_add_phy);
+
+void phy_link_topo_del_phy(struct net_device *dev,
+			   struct phy_device *phy)
+{
+	struct phy_link_topology *topo = dev->link_topo;
+	struct phy_device_node *pdn;
+
+	if (!topo)
+		return;
+
+	pdn = xa_erase(&topo->phys, phy->phyindex);
+
+	/* We delete the PHY from the topology, however we don't re-set the
+	 * phy->phyindex field. If the PHY isn't gone, we can re-assign it the
+	 * same index next time it's added back to the topology
+	 */
+
+	kfree(pdn);
+}
+EXPORT_SYMBOL_GPL(phy_link_topo_del_phy);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 614ec5d3d75b..289a6133769c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,7 +40,6 @@
 #include <net/dcbnl.h>
 #endif
 #include <net/netprio_cgroup.h>
-
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
 #include <linux/netdevice_xmit.h>
@@ -81,6 +80,7 @@ struct xdp_frame;
 struct xdp_metadata_ops;
 struct xdp_md;
 struct ethtool_netdev_state;
+struct phy_link_topology;
 
 typedef u32 xdp_features_t;
 
@@ -1951,6 +1951,7 @@ enum netdev_reg_state {
  *	@fcoe_ddp_xid:	Max exchange id for FCoE LRO by ddp
  *
  *	@priomap:	XXX: need comments on this one
+ *	@link_topo:	Physical link topology tracking attached PHYs
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
@@ -2342,6 +2343,7 @@ struct net_device {
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 	struct netprio_map __rcu *priomap;
 #endif
+	struct phy_link_topology	*link_topo;
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6b7d40d49129..3b0f4bf80650 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -554,6 +554,9 @@ struct macsec_ops;
  * @drv: Pointer to the driver for this PHY instance
  * @devlink: Create a link between phy dev and mac dev, if the external phy
  *           used by current mac interface is managed by another mac interface.
+ * @phyindex: Unique id across the phy's parent tree of phys to address the PHY
+ *	      from userspace, similar to ifindex. A zero index means the PHY
+ *	      wasn't assigned an id yet.
  * @phy_id: UID for this device found during discovery
  * @c45_ids: 802.3-c45 Device Identifiers if is_c45.
  * @is_c45:  Set to true if this PHY uses clause 45 addressing.
@@ -656,6 +659,7 @@ struct phy_device {
 
 	struct device_link *devlink;
 
+	u32 phyindex;
 	u32 phy_id;
 
 	struct phy_c45_device_ids c45_ids;
diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h
new file mode 100644
index 000000000000..68a59e25821c
--- /dev/null
+++ b/include/linux/phy_link_topology.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PHY device list allow maintaining a list of PHY devices that are
+ * part of a netdevice's link topology. PHYs can for example be chained,
+ * as is the case when using a PHY that exposes an SFP module, on which an
+ * SFP transceiver that embeds a PHY is connected.
+ *
+ * This list can then be used by userspace to leverage individual PHY
+ * capabilities.
+ */
+#ifndef __PHY_LINK_TOPOLOGY_H
+#define __PHY_LINK_TOPOLOGY_H
+
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+
+struct xarray;
+struct phy_device;
+struct sfp_bus;
+
+struct phy_link_topology {
+	struct xarray phys;
+	u32 next_phy_index;
+};
+
+struct phy_device_node {
+	enum phy_upstream upstream_type;
+
+	union {
+		struct net_device	*netdev;
+		struct phy_device	*phydev;
+	} upstream;
+
+	struct sfp_bus *parent_sfp_bus;
+
+	struct phy_device *phy;
+};
+
+#if IS_ENABLED(CONFIG_PHYLIB)
+int phy_link_topo_add_phy(struct net_device *dev,
+			  struct phy_device *phy,
+			  enum phy_upstream upt, void *upstream);
+
+void phy_link_topo_del_phy(struct net_device *dev, struct phy_device *phy);
+
+static inline struct phy_device *
+phy_link_topo_get_phy(struct net_device *dev, u32 phyindex)
+{
+	struct phy_link_topology *topo = dev->link_topo;
+	struct phy_device_node *pdn;
+
+	if (!topo)
+		return NULL;
+
+	pdn = xa_load(&topo->phys, phyindex);
+	if (pdn)
+		return pdn->phy;
+
+	return NULL;
+}
+
+#else
+static inline int phy_link_topo_add_phy(struct net_device *dev,
+					struct phy_device *phy,
+					enum phy_upstream upt, void *upstream)
+{
+	return 0;
+}
+
+static inline void phy_link_topo_del_phy(struct net_device *dev,
+					 struct phy_device *phy)
+{
+}
+
+static inline struct phy_device *
+phy_link_topo_get_phy(struct net_device *dev, u32 phyindex)
+{
+	return NULL;
+}
+#endif
+
+#endif /* __PHY_LINK_TOPOLOGY_H */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 4a0a6e703483..c405ed63acfa 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2533,4 +2533,20 @@ struct ethtool_link_settings {
 	 * __u32 map_lp_advertising[link_mode_masks_nwords];
 	 */
 };
+
+/**
+ * enum phy_upstream - Represents the upstream component a given PHY device
+ * is connected to, as in what is on the other end of the MII bus. Most PHYs
+ * will be attached to an Ethernet MAC controller, but in some cases, there's
+ * an intermediate PHY used as a media-converter, which will driver another
+ * MII interface as its output.
+ * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port,
+ *		      or ethernet controller)
+ * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter)
+ */
+enum phy_upstream {
+	PHY_UPSTREAM_MAC,
+	PHY_UPSTREAM_PHY,
+};
+
 #endif /* _UAPI_LINUX_ETHTOOL_H */
diff --git a/net/core/dev.c b/net/core/dev.c
index e7260889d4cb..d0e7483abdcd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -158,6 +158,7 @@
 #include <net/page_pool/types.h>
 #include <net/page_pool/helpers.h>
 #include <net/rps.h>
+#include <linux/phy_link_topology.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
@@ -10321,6 +10322,17 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev)
 	}
 }
 
+static void netdev_free_phy_link_topology(struct net_device *dev)
+{
+	struct phy_link_topology *topo = dev->link_topo;
+
+	if (IS_ENABLED(CONFIG_PHYLIB) && topo) {
+		xa_destroy(&topo->phys);
+		kfree(topo);
+		dev->link_topo = NULL;
+	}
+}
+
 /**
  * register_netdevice() - register a network device
  * @dev: device to register
@@ -11099,6 +11111,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 #ifdef CONFIG_NET_SCHED
 	hash_init(dev->qdisc_hash);
 #endif
+
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
@@ -11191,6 +11204,8 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->xdp_bulkq);
 	dev->xdp_bulkq = NULL;
 
+	netdev_free_phy_link_topology(dev);
+
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED ||
 	    dev->reg_state == NETREG_DUMMY) {
-- 
cgit v1.3-3-g829e


From 4d76f115ab9121f4458330da962ae9ef5430e60b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:09:56 +0200
Subject: net: sfp: pass the phy_device when disconnecting an sfp module's PHY

Pass the phy_device as a parameter to the sfp upstream .disconnect_phy
operation. This is preparatory work to help track phy devices across
a net_device's link.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 3 ++-
 drivers/net/phy/sfp-bus.c | 4 ++--
 include/linux/sfp.h       | 2 +-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 51c526d227fa..ab4e9fc03017 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -3423,7 +3423,8 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy)
 	return ret;
 }
 
-static void phylink_sfp_disconnect_phy(void *upstream)
+static void phylink_sfp_disconnect_phy(void *upstream,
+				       struct phy_device *phydev)
 {
 	phylink_disconnect_phy(upstream);
 }
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 2f44fc51848f..56953e66bb7b 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -487,7 +487,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 			bus->socket_ops->stop(bus->sfp);
 		bus->socket_ops->detach(bus->sfp);
 		if (bus->phydev && ops && ops->disconnect_phy)
-			ops->disconnect_phy(bus->upstream);
+			ops->disconnect_phy(bus->upstream, bus->phydev);
 	}
 	bus->registered = false;
 }
@@ -743,7 +743,7 @@ void sfp_remove_phy(struct sfp_bus *bus)
 	const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus);
 
 	if (ops && ops->disconnect_phy)
-		ops->disconnect_phy(bus->upstream);
+		ops->disconnect_phy(bus->upstream, bus->phydev);
 	bus->phydev = NULL;
 }
 EXPORT_SYMBOL_GPL(sfp_remove_phy);
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index b14be59550e3..54abb4d22b2e 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -550,7 +550,7 @@ struct sfp_upstream_ops {
 	void (*link_down)(void *priv);
 	void (*link_up)(void *priv);
 	int (*connect_phy)(void *priv, struct phy_device *);
-	void (*disconnect_phy)(void *priv);
+	void (*disconnect_phy)(void *priv, struct phy_device *);
 };
 
 #if IS_ENABLED(CONFIG_SFP)
-- 
cgit v1.3-3-g829e


From b2db6f4ace72e71fa09b8d1354f8ac9854140d74 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:09:57 +0200
Subject: net: phy: add helpers to handle sfp phy connect/disconnect

There are a few PHY drivers that can handle SFP modules through their
sfp_upstream_ops. Introduce Phylib helpers to keep track of connected
SFP PHYs in a netdevice's namespace, by adding the SFP PHY to the
upstream PHY's netdev's namespace.

By doing so, these SFP PHYs can be enumerated and exposed to users,
which will be able to use their capabilities.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell-88x2222.c |  2 ++
 drivers/net/phy/marvell.c         |  2 ++
 drivers/net/phy/marvell10g.c      |  2 ++
 drivers/net/phy/phy_device.c      | 42 +++++++++++++++++++++++++++++++++++++++
 drivers/net/phy/qcom/at803x.c     |  2 ++
 drivers/net/phy/qcom/qca807x.c    |  2 ++
 include/linux/phy.h               |  2 ++
 7 files changed, 54 insertions(+)

diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c
index b88398e6872b..0b777cdd7078 100644
--- a/drivers/net/phy/marvell-88x2222.c
+++ b/drivers/net/phy/marvell-88x2222.c
@@ -553,6 +553,8 @@ static const struct sfp_upstream_ops sfp_phy_ops = {
 	.link_down = mv2222_sfp_link_down,
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int mv2222_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index b89fbffa6a93..9964bf3dea2f 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -3613,6 +3613,8 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = {
 	.module_remove = m88e1510_sfp_remove,
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int m88e1510_probe(struct phy_device *phydev)
diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index ad43e280930c..6642eb642d4b 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -503,6 +503,8 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id)
 static const struct sfp_upstream_ops mv3310_sfp_ops = {
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 	.module_insert = mv3310_sfp_insert,
 };
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index d896c799f7c2..8f5314c1fecc 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1385,6 +1385,48 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(phy_standalone);
 
+/**
+ * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY
+ * @upstream: pointer to the upstream phy device
+ * @phy: pointer to the SFP module's phy device
+ *
+ * This helper allows keeping track of PHY devices on the link. It adds the
+ * SFP module's phy to the phy namespace of the upstream phy
+ *
+ * Return: 0 on success, otherwise a negative error code.
+ */
+int phy_sfp_connect_phy(void *upstream, struct phy_device *phy)
+{
+	struct phy_device *phydev = upstream;
+	struct net_device *dev = phydev->attached_dev;
+
+	if (dev)
+		return phy_link_topo_add_phy(dev, phy, PHY_UPSTREAM_PHY, phydev);
+
+	return 0;
+}
+EXPORT_SYMBOL(phy_sfp_connect_phy);
+
+/**
+ * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY
+ * @upstream: pointer to the upstream phy device
+ * @phy: pointer to the SFP module's phy device
+ *
+ * This helper allows keeping track of PHY devices on the link. It removes the
+ * SFP module's phy to the phy namespace of the upstream phy. As the module phy
+ * will be destroyed, re-inserting the same module will add a new phy with a
+ * new index.
+ */
+void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy)
+{
+	struct phy_device *phydev = upstream;
+	struct net_device *dev = phydev->attached_dev;
+
+	if (dev)
+		phy_link_topo_del_phy(dev, phy);
+}
+EXPORT_SYMBOL(phy_sfp_disconnect_phy);
+
 /**
  * phy_sfp_attach - attach the SFP bus to the PHY upstream network device
  * @upstream: pointer to the phy device
diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c
index c8f83e5f78ab..105602581a03 100644
--- a/drivers/net/phy/qcom/at803x.c
+++ b/drivers/net/phy/qcom/at803x.c
@@ -770,6 +770,8 @@ static const struct sfp_upstream_ops at8031_sfp_ops = {
 	.attach = phy_sfp_attach,
 	.detach = phy_sfp_detach,
 	.module_insert = at8031_sfp_insert,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int at8031_parse_dt(struct phy_device *phydev)
diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index ba558486c72f..bd8a51ec0ecd 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -699,6 +699,8 @@ static const struct sfp_upstream_ops qca807x_sfp_ops = {
 	.detach = phy_sfp_detach,
 	.module_insert = qca807x_sfp_insert,
 	.module_remove = qca807x_sfp_remove,
+	.connect_phy = phy_sfp_connect_phy,
+	.disconnect_phy = phy_sfp_disconnect_phy,
 };
 
 static int qca807x_probe(struct phy_device *phydev)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3b0f4bf80650..a98bc91a0cde 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1781,6 +1781,8 @@ int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
 int __phy_resume(struct phy_device *phydev);
 int phy_loopback(struct phy_device *phydev, bool enable);
+int phy_sfp_connect_phy(void *upstream, struct phy_device *phy);
+void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy);
 void phy_sfp_attach(void *upstream, struct sfp_bus *bus);
 void phy_sfp_detach(void *upstream, struct sfp_bus *bus);
 int phy_sfp_probe(struct phy_device *phydev,
-- 
cgit v1.3-3-g829e


From 0a2f7de0f3b96c4a30e56d2c79f8d812f89599a1 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:09:58 +0200
Subject: net: sfp: Add helper to return the SFP bus name

Knowing the bus name is helpful when we want to expose the link topology
to userspace, add a helper to return the SFP bus name.

This call will always be made while holding the RTNL which ensures
that the SFP driver won't unbind from the device. The returned pointer
to the bus name will only be used while RTNL is held.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Suggested-by: "Russell King (Oracle)" <linux@armlinux.org.uk>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp-bus.c | 22 ++++++++++++++++++++++
 include/linux/sfp.h       |  6 ++++++
 2 files changed, 28 insertions(+)

diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index 56953e66bb7b..f13c00b5b449 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -722,6 +722,28 @@ void sfp_bus_del_upstream(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_bus_del_upstream);
 
+/**
+ * sfp_get_name() - Get the SFP device name
+ * @bus: a pointer to the &struct sfp_bus structure for the sfp module
+ *
+ * Gets the SFP device's name, if @bus has a registered socket. Callers must
+ * hold RTNL, and the returned name is only valid until RTNL is released.
+ *
+ * Returns:
+ *	- The name of the SFP device registered with sfp_register_socket()
+ *	- %NULL if no device was registered on @bus
+ */
+const char *sfp_get_name(struct sfp_bus *bus)
+{
+	ASSERT_RTNL();
+
+	if (bus->sfp_dev)
+		return dev_name(bus->sfp_dev);
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(sfp_get_name);
+
 /* Socket driver entry points */
 int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev)
 {
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index 54abb4d22b2e..60c65cea74f6 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -576,6 +576,7 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode);
 int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 			 const struct sfp_upstream_ops *ops);
 void sfp_bus_del_upstream(struct sfp_bus *bus);
+const char *sfp_get_name(struct sfp_bus *bus);
 #else
 static inline int sfp_parse_port(struct sfp_bus *bus,
 				 const struct sfp_eeprom_id *id,
@@ -654,6 +655,11 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream,
 static inline void sfp_bus_del_upstream(struct sfp_bus *bus)
 {
 }
+
+static inline const char *sfp_get_name(struct sfp_bus *bus)
+{
+	return NULL;
+}
 #endif
 
 #endif
-- 
cgit v1.3-3-g829e


From c15e065b46dc4e19837275b826c1960d55564abd Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:09:59 +0200
Subject: net: ethtool: Allow passing a phy index for some commands

Some netlink commands are target towards ethernet PHYs, to control some
of their features. As there's several such commands, add the ability to
pass a PHY index in the ethnl request, which will populate the generic
ethnl_req_info with the passed phy_index.

Add a helper that netlink command handlers need to use to grab the
targeted PHY from the req_info. This helper needs to hold rtnl_lock()
while interacting with the PHY, as it may be removed at any point.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst |  7 ++++
 include/uapi/linux/ethtool_netlink.h         |  1 +
 net/ethtool/netlink.c                        | 57 +++++++++++++++++++++++++++-
 net/ethtool/netlink.h                        | 28 ++++++++++++++
 4 files changed, 91 insertions(+), 2 deletions(-)

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 3f6c6880e7c4..2d14b8551348 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -57,6 +57,7 @@ Structure of this header is
   ``ETHTOOL_A_HEADER_DEV_INDEX``  u32     device ifindex
   ``ETHTOOL_A_HEADER_DEV_NAME``   string  device name
   ``ETHTOOL_A_HEADER_FLAGS``      u32     flags common for all requests
+  ``ETHTOOL_A_HEADER_PHY_INDEX``  u32     phy device index
   ==============================  ======  =============================
 
 ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the
@@ -81,6 +82,12 @@ the behaviour is backward compatible, i.e. requests from old clients not aware
 of the flag should be interpreted the way the client expects. A client must
 not set flags it does not understand.
 
+``ETHTOOL_A_HEADER_PHY_INDEX`` identifies the Ethernet PHY the message relates to.
+As there are numerous commands that are related to PHY configuration, and because
+there may be more than one PHY on the link, the PHY index can be passed in the
+request for the commands that needs it. It is, however, not mandatory, and if it
+is not passed for commands that target a PHY, the net_device.phydev pointer
+is used.
 
 Bit sets
 ========
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 9074fa309bd6..49d1f9220fde 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -134,6 +134,7 @@ enum {
 	ETHTOOL_A_HEADER_DEV_INDEX,		/* u32 */
 	ETHTOOL_A_HEADER_DEV_NAME,		/* string */
 	ETHTOOL_A_HEADER_FLAGS,			/* u32 - ETHTOOL_FLAG_* */
+	ETHTOOL_A_HEADER_PHY_INDEX,		/* u32 */
 
 	/* add new constants above here */
 	__ETHTOOL_A_HEADER_CNT,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 041548e5f5e6..b00061924e80 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -2,6 +2,7 @@
 
 #include <net/sock.h>
 #include <linux/ethtool_netlink.h>
+#include <linux/phy_link_topology.h>
 #include <linux/pm_runtime.h>
 #include "netlink.h"
 #include "module_fw.h"
@@ -31,6 +32,24 @@ const struct nla_policy ethnl_header_policy_stats[] = {
 							  ETHTOOL_FLAGS_STATS),
 };
 
+const struct nla_policy ethnl_header_policy_phy[] = {
+	[ETHTOOL_A_HEADER_DEV_INDEX]	= { .type = NLA_U32 },
+	[ETHTOOL_A_HEADER_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = ALTIFNAMSIZ - 1 },
+	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
+							  ETHTOOL_FLAGS_BASIC),
+	[ETHTOOL_A_HEADER_PHY_INDEX]		= NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+const struct nla_policy ethnl_header_policy_phy_stats[] = {
+	[ETHTOOL_A_HEADER_DEV_INDEX]	= { .type = NLA_U32 },
+	[ETHTOOL_A_HEADER_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = ALTIFNAMSIZ - 1 },
+	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
+							  ETHTOOL_FLAGS_STATS),
+	[ETHTOOL_A_HEADER_PHY_INDEX]		= NLA_POLICY_MIN(NLA_U32, 1),
+};
+
 int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid,
 			enum ethnl_sock_type type)
 {
@@ -119,7 +138,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 			       const struct nlattr *header, struct net *net,
 			       struct netlink_ext_ack *extack, bool require_dev)
 {
-	struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)];
+	struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)];
 	const struct nlattr *devname_attr;
 	struct net_device *dev = NULL;
 	u32 flags = 0;
@@ -134,7 +153,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 	/* No validation here, command policy should have a nested policy set
 	 * for the header, therefore validation should have already been done.
 	 */
-	ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header,
+	ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header,
 			       NULL, extack);
 	if (ret < 0)
 		return ret;
@@ -175,11 +194,45 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 		return -EINVAL;
 	}
 
+	if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) {
+		if (dev) {
+			req_info->phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]);
+		} else {
+			NL_SET_ERR_MSG_ATTR(extack, header,
+					    "phy_index set without a netdev");
+			return -EINVAL;
+		}
+	}
+
 	req_info->dev = dev;
 	req_info->flags = flags;
 	return 0;
 }
 
+struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
+					const struct nlattr *header,
+					struct netlink_ext_ack *extack)
+{
+	struct phy_device *phydev;
+
+	ASSERT_RTNL();
+
+	if (!req_info->dev)
+		return NULL;
+
+	if (!req_info->phy_index)
+		return req_info->dev->phydev;
+
+	phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index);
+	if (!phydev) {
+		NL_SET_ERR_MSG_ATTR(extack, header,
+				    "no phy matching phyindex");
+		return ERR_PTR(-ENODEV);
+	}
+
+	return phydev;
+}
+
 /**
  * ethnl_fill_reply_header() - Put common header into a reply message
  * @skb:      skb with the message
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 236c189fc968..e326699405be 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -251,6 +251,9 @@ static inline unsigned int ethnl_reply_header_size(void)
  * @dev:   network device the request is for (may be null)
  * @dev_tracker: refcount tracker for @dev reference
  * @flags: request flags common for all request types
+ * @phy_index: phy_device index connected to @dev this request is for. Can be
+ *	       0 if the request doesn't target a phy, or if the @dev's attached
+ *	       phy is targeted.
  *
  * This is a common base for request specific structures holding data from
  * parsed userspace request. These always embed struct ethnl_req_info at
@@ -260,6 +263,7 @@ struct ethnl_req_info {
 	struct net_device	*dev;
 	netdevice_tracker	dev_tracker;
 	u32			flags;
+	u32			phy_index;
 };
 
 static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
@@ -267,6 +271,27 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
 	netdev_put(req_info->dev, &req_info->dev_tracker);
 }
 
+/**
+ * ethnl_req_get_phydev() - Gets the phy_device targeted by this request,
+ *			    if any. Must be called under rntl_lock().
+ * @req_info:	The ethnl request to get the phy from.
+ * @header:	The netlink header, used for error reporting.
+ * @extack:	The netlink extended ACK, for error reporting.
+ *
+ * The caller must hold RTNL, until it's done interacting with the returned
+ * phy_device.
+ *
+ * Return: A phy_device pointer corresponding either to the passed phy_index
+ *	   if one is provided. If not, the phy_device attached to the
+ *	   net_device targeted by this request is returned. If there's no
+ *	   targeted net_device, or no phy_device is attached, NULL is
+ *	   returned. If the provided phy_index is invalid, an error pointer
+ *	   is returned.
+ */
+struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
+					const struct nlattr *header,
+					struct netlink_ext_ack *extack);
+
 /**
  * struct ethnl_reply_data - base type of reply data for GET requests
  * @dev:       device for current reply message; in single shot requests it is
@@ -409,9 +434,12 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops;
 extern const struct ethnl_request_ops ethnl_plca_status_request_ops;
 extern const struct ethnl_request_ops ethnl_mm_request_ops;
+extern const struct ethnl_request_ops ethnl_phy_request_ops;
 
 extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
+extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1];
+extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1];
 extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1];
 extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1];
 extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1];
-- 
cgit v1.3-3-g829e


From 9af0e89d6c2433afd3e5e7cc52c7592ef23526c0 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:00 +0200
Subject: netlink: specs: add phy-index as a header parameter

Update the spec to take the newly introduced phy-index as a generic
request parameter.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/specs/ethtool.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 1bbeaba5c644..7d6c3ace3fa2 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -54,6 +54,9 @@ attribute-sets:
         name: flags
         type: u32
         enum: header-flags
+      -
+        name: phy-index
+        type: u32
 
   -
     name: bitset-bit
-- 
cgit v1.3-3-g829e


From 17194be4c8e1e82d8b484e58cdcb495c0714d1fd Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:01 +0200
Subject: net: ethtool: Introduce a command to list PHYs on an interface

As we have the ability to track the PHYs connected to a net_device
through the link_topology, we can expose this list to userspace. This
allows userspace to use these identifiers for phy-specific commands and
take the decision of which PHY to target by knowing the link topology.

Add PHY_GET and PHY_DUMP, which can be a filtered DUMP operation to list
devices on only one interface.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst |  41 ++++
 include/uapi/linux/ethtool_netlink.h         |  19 ++
 net/ethtool/Makefile                         |   3 +-
 net/ethtool/netlink.c                        |   9 +
 net/ethtool/netlink.h                        |   5 +
 net/ethtool/phy.c                            | 308 +++++++++++++++++++++++++++
 6 files changed, 384 insertions(+), 1 deletion(-)
 create mode 100644 net/ethtool/phy.c

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 2d14b8551348..8c152871c23c 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -2191,6 +2191,46 @@ string.
 The ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` and ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL``
 attributes encode the completed and total amount of work, respectively.
 
+PHY_GET
+=======
+
+Retrieve information about a given Ethernet PHY sitting on the link. The DO
+operation returns all available information about dev->phydev. User can also
+specify a PHY_INDEX, in which case the DO request returns information about that
+specific PHY.
+As there can be more than one PHY, the DUMP operation can be used to list the PHYs
+present on a given interface, by passing an interface index or name in
+the dump request.
+
+Request contents:
+
+  ====================================  ======  ==========================
+  ``ETHTOOL_A_PHY_HEADER``              nested  request header
+  ====================================  ======  ==========================
+
+Kernel response contents:
+
+  ===================================== ======  ===============================
+  ``ETHTOOL_A_PHY_HEADER``              nested  request header
+  ``ETHTOOL_A_PHY_INDEX``               u32     the phy's unique index, that can
+                                                be used for phy-specific
+                                                requests
+  ``ETHTOOL_A_PHY_DRVNAME``             string  the phy driver name
+  ``ETHTOOL_A_PHY_NAME``                string  the phy device name
+  ``ETHTOOL_A_PHY_UPSTREAM_TYPE``       u32     the type of device this phy is
+                                                connected to
+  ``ETHTOOL_A_PHY_UPSTREAM_INDEX``      u32     the PHY index of the upstream
+                                                PHY
+  ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME``   string  if this PHY is connected to
+                                                its parent PHY through an SFP
+                                                bus, the name of this sfp bus
+  ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string  if the phy controls an sfp bus,
+                                                the name of the sfp bus
+  ===================================== ======  ===============================
+
+When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is
+another PHY.
+
 Request translation
 ===================
 
@@ -2298,4 +2338,5 @@ are netlink only.
   n/a                                 ``ETHTOOL_MSG_MM_GET``
   n/a                                 ``ETHTOOL_MSG_MM_SET``
   n/a                                 ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT``
+  n/a                                 ``ETHTOOL_MSG_PHY_GET``
   =================================== =====================================
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 49d1f9220fde..45d8bcdea056 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -58,6 +58,7 @@ enum {
 	ETHTOOL_MSG_MM_GET,
 	ETHTOOL_MSG_MM_SET,
 	ETHTOOL_MSG_MODULE_FW_FLASH_ACT,
+	ETHTOOL_MSG_PHY_GET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -111,6 +112,8 @@ enum {
 	ETHTOOL_MSG_MM_GET_REPLY,
 	ETHTOOL_MSG_MM_NTF,
 	ETHTOOL_MSG_MODULE_FW_FLASH_NTF,
+	ETHTOOL_MSG_PHY_GET_REPLY,
+	ETHTOOL_MSG_PHY_NTF,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -1055,6 +1058,22 @@ enum {
 	ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PHY_UNSPEC,
+	ETHTOOL_A_PHY_HEADER,			/* nest - _A_HEADER_* */
+	ETHTOOL_A_PHY_INDEX,			/* u32 */
+	ETHTOOL_A_PHY_DRVNAME,			/* string */
+	ETHTOOL_A_PHY_NAME,			/* string */
+	ETHTOOL_A_PHY_UPSTREAM_TYPE,		/* u32 */
+	ETHTOOL_A_PHY_UPSTREAM_INDEX,		/* u32 */
+	ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,	/* string */
+	ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,	/* string */
+
+	/* add new constants above here */
+	__ETHTOOL_A_PHY_CNT,
+	ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 9a190635fe95..9b540644ba31 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -8,4 +8,5 @@ ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
 		   tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \
-		   module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o
+		   module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o \
+		   phy.o
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index b00061924e80..e3f0ef6b851b 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -1234,6 +1234,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy	= ethnl_module_fw_flash_act_policy,
 		.maxattr = ARRAY_SIZE(ethnl_module_fw_flash_act_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_PHY_GET,
+		.doit	= ethnl_phy_doit,
+		.start	= ethnl_phy_start,
+		.dumpit	= ethnl_phy_dumpit,
+		.done	= ethnl_phy_done,
+		.policy = ethnl_phy_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index e326699405be..203b08eb6c6f 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -484,6 +484,7 @@ extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADE
 extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1];
 extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1];
 extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1];
+extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1];
 
 int ethnl_set_features(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
@@ -494,6 +495,10 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info);
 int ethnl_rss_dump_start(struct netlink_callback *cb);
 int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ethnl_phy_start(struct netlink_callback *cb);
+int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info);
+int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ethnl_phy_done(struct netlink_callback *cb);
 
 extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN];
 extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN];
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
new file mode 100644
index 000000000000..560dd039c662
--- /dev/null
+++ b/net/ethtool/phy.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2023 Bootlin
+ *
+ */
+#include "common.h"
+#include "netlink.h"
+
+#include <linux/phy.h>
+#include <linux/phy_link_topology.h>
+#include <linux/sfp.h>
+
+struct phy_req_info {
+	struct ethnl_req_info		base;
+	struct phy_device_node		*pdn;
+};
+
+#define PHY_REQINFO(__req_base) \
+	container_of(__req_base, struct phy_req_info, base)
+
+const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = {
+	[ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+/* Caller holds rtnl */
+static ssize_t
+ethnl_phy_reply_size(const struct ethnl_req_info *req_base,
+		     struct netlink_ext_ack *extack)
+{
+	struct phy_req_info *req_info = PHY_REQINFO(req_base);
+	struct phy_device_node *pdn = req_info->pdn;
+	struct phy_device *phydev = pdn->phy;
+	size_t size = 0;
+
+	ASSERT_RTNL();
+
+	/* ETHTOOL_A_PHY_INDEX */
+	size += nla_total_size(sizeof(u32));
+
+	/* ETHTOOL_A_DRVNAME */
+	if (phydev->drv)
+		size += nla_total_size(strlen(phydev->drv->name) + 1);
+
+	/* ETHTOOL_A_NAME */
+	size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1);
+
+	/* ETHTOOL_A_PHY_UPSTREAM_TYPE */
+	size += nla_total_size(sizeof(u32));
+
+	if (phy_on_sfp(phydev)) {
+		const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus);
+
+		/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
+		if (upstream_sfp_name)
+			size += nla_total_size(strlen(upstream_sfp_name) + 1);
+
+		/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
+		size += nla_total_size(sizeof(u32));
+	}
+
+	/* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */
+	if (phydev->sfp_bus) {
+		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
+
+		if (sfp_name)
+			size += nla_total_size(strlen(sfp_name) + 1);
+	}
+
+	return size;
+}
+
+static int
+ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb)
+{
+	struct phy_req_info *req_info = PHY_REQINFO(req_base);
+	struct phy_device_node *pdn = req_info->pdn;
+	struct phy_device *phydev = pdn->phy;
+	enum phy_upstream ptype;
+
+	ptype = pdn->upstream_type;
+
+	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) ||
+	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) ||
+	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype))
+		return -EMSGSIZE;
+
+	if (phydev->drv &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name))
+		return -EMSGSIZE;
+
+	if (ptype == PHY_UPSTREAM_PHY) {
+		struct phy_device *upstream = pdn->upstream.phydev;
+		const char *sfp_upstream_name;
+
+		/* Parent index */
+		if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex))
+			return -EMSGSIZE;
+
+		if (pdn->parent_sfp_bus) {
+			sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus);
+			if (sfp_upstream_name &&
+			    nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
+					   sfp_upstream_name))
+				return -EMSGSIZE;
+		}
+	}
+
+	if (phydev->sfp_bus) {
+		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
+
+		if (sfp_name &&
+		    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
+				   sfp_name))
+			return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
+static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
+				   struct nlattr **tb,
+				   struct netlink_ext_ack *extack)
+{
+	struct phy_link_topology *topo = req_base->dev->link_topo;
+	struct phy_req_info *req_info = PHY_REQINFO(req_base);
+	struct phy_device *phydev;
+
+	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER],
+				      extack);
+	if (!phydev)
+		return 0;
+
+	if (IS_ERR(phydev))
+		return PTR_ERR(phydev);
+
+	if (!topo)
+		return 0;
+
+	req_info->pdn = xa_load(&topo->phys, phydev->phyindex);
+
+	return 0;
+}
+
+int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct phy_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
+	struct sk_buff *rskb;
+	void *reply_payload;
+	int reply_len;
+	int ret;
+
+	ret = ethnl_parse_header_dev_get(&req_info.base,
+					 tb[ETHTOOL_A_PHY_HEADER],
+					 genl_info_net(info), info->extack,
+					 true);
+	if (ret < 0)
+		return ret;
+
+	rtnl_lock();
+
+	ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack);
+	if (ret < 0)
+		goto err_unlock_rtnl;
+
+	/* No PHY, return early */
+	if (!req_info.pdn->phy)
+		goto err_unlock_rtnl;
+
+	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
+	if (ret < 0)
+		goto err_unlock_rtnl;
+	reply_len = ret + ethnl_reply_header_size();
+
+	rskb = ethnl_reply_init(reply_len, req_info.base.dev,
+				ETHTOOL_MSG_PHY_GET_REPLY,
+				ETHTOOL_A_PHY_HEADER,
+				info, &reply_payload);
+	if (!rskb) {
+		ret = -ENOMEM;
+		goto err_unlock_rtnl;
+	}
+
+	ret = ethnl_phy_fill_reply(&req_info.base, rskb);
+	if (ret)
+		goto err_free_msg;
+
+	rtnl_unlock();
+	ethnl_parse_header_dev_put(&req_info.base);
+	genlmsg_end(rskb, reply_payload);
+
+	return genlmsg_reply(rskb, info);
+
+err_free_msg:
+	nlmsg_free(rskb);
+err_unlock_rtnl:
+	rtnl_unlock();
+	ethnl_parse_header_dev_put(&req_info.base);
+	return ret;
+}
+
+struct ethnl_phy_dump_ctx {
+	struct phy_req_info	*phy_req_info;
+	unsigned long ifindex;
+	unsigned long phy_index;
+};
+
+int ethnl_phy_start(struct netlink_callback *cb)
+{
+	const struct genl_info *info = genl_info_dump(cb);
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
+
+	ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL);
+	if (!ctx->phy_req_info)
+		return -ENOMEM;
+
+	ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base,
+					 info->attrs[ETHTOOL_A_PHY_HEADER],
+					 sock_net(cb->skb->sk), cb->extack,
+					 false);
+	ctx->ifindex = 0;
+	ctx->phy_index = 0;
+
+	if (ret)
+		kfree(ctx->phy_req_info);
+
+	return ret;
+}
+
+int ethnl_phy_done(struct netlink_callback *cb)
+{
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+
+	if (ctx->phy_req_info->base.dev)
+		ethnl_parse_header_dev_put(&ctx->phy_req_info->base);
+
+	kfree(ctx->phy_req_info);
+
+	return 0;
+}
+
+static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
+				  struct netlink_callback *cb)
+{
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	struct phy_req_info *pri = ctx->phy_req_info;
+	struct phy_device_node *pdn;
+	int ret = 0;
+	void *ehdr;
+
+	pri->base.dev = dev;
+
+	if (!dev->link_topo)
+		return 0;
+
+	xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) {
+		ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY);
+		if (!ehdr) {
+			ret = -EMSGSIZE;
+			break;
+		}
+
+		ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER);
+		if (ret < 0) {
+			genlmsg_cancel(skb, ehdr);
+			break;
+		}
+
+		pri->pdn = pdn;
+		ret = ethnl_phy_fill_reply(&pri->base, skb);
+		if (ret < 0) {
+			genlmsg_cancel(skb, ehdr);
+			break;
+		}
+
+		genlmsg_end(skb, ehdr);
+	}
+
+	return ret;
+}
+
+int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	int ret = 0;
+
+	rtnl_lock();
+
+	if (ctx->phy_req_info->base.dev) {
+		ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb);
+	} else {
+		for_each_netdev_dump(net, dev, ctx->ifindex) {
+			ret = ethnl_phy_dump_one_dev(skb, dev, cb);
+			if (ret)
+				break;
+
+			ctx->phy_index = 0;
+		}
+	}
+	rtnl_unlock();
+
+	return ret;
+}
-- 
cgit v1.3-3-g829e


From d3d9a3e48a63eec82082a7ef76f5d5b6d339933f Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:02 +0200
Subject: netlink: specs: add ethnl PHY_GET command set

The PHY_GET command, supporting both DUMP and GET operations, is used to
retrieve the list of PHYs connected to a netdevice, and get topology
information to know where exactly it sits on the physical link.

Add the netlink specs corresponding to that command.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/netlink/specs/ethtool.yaml | 55 ++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 7d6c3ace3fa2..37211b1e861f 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -39,6 +39,11 @@ definitions:
         - ovld-detected
         - power-not-available
         - short-detected
+  -
+    name: phy-upstream-type
+    enum-name:
+    type: enum
+    entries: [ mac, phy ]
 
 attribute-sets:
   -
@@ -1092,6 +1097,35 @@ attribute-sets:
       -
         name: total
         type: uint
+  -
+    name: phy
+    attributes:
+      -
+        name: header
+        type: nest
+        nested-attributes: header
+      -
+        name: index
+        type: u32
+      -
+        name: drvname
+        type: string
+      -
+        name: name
+        type: string
+      -
+        name: upstream-type
+        type: u32
+        enum: phy-upstream-type
+      -
+        name: upstream-index
+        type: u32
+      -
+        name: upstream-sfp-name
+        type: string
+      -
+        name: downstream-sfp-name
+        type: string
 
 operations:
   enum-model: directional
@@ -1890,3 +1924,24 @@ operations:
           - status-msg
           - done
           - total
+    -
+      name: phy-get
+      doc: Get PHY devices attached to an interface
+
+      attribute-set: phy
+
+      do: &phy-get-op
+        request:
+          attributes:
+            - header
+        reply:
+          attributes:
+            - header
+            - index
+            - drvname
+            - name
+            - upstream-type
+            - upstream-index
+            - upstream-sfp-name
+            - downstream-sfp-name
+      dump: *phy-get-op
-- 
cgit v1.3-3-g829e


From 02180fb525bac8c259c3b7271ddfa498d47c5dcc Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:03 +0200
Subject: net: ethtool: plca: Target the command to the requested PHY

PLCA is a PHY-specific command. Instead of targeting the command
towards dev->phydev, use the request to pick the targeted PHY.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/plca.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c
index b1e2e3b5027f..d95d92f173a6 100644
--- a/net/ethtool/plca.c
+++ b/net/ethtool/plca.c
@@ -25,7 +25,7 @@ struct plca_reply_data {
 
 const struct nla_policy ethnl_plca_get_cfg_policy[] = {
 	[ETHTOOL_A_PLCA_HEADER]		=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_phy),
 };
 
 static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid,
@@ -58,10 +58,14 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 	struct plca_reply_data *data = PLCA_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
 	const struct ethtool_phy_ops *ops;
+	struct nlattr **tb = info->attrs;
+	struct phy_device *phydev;
 	int ret;
 
+	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER],
+				      info->extack);
 	// check that the PHY device is available and connected
-	if (!dev->phydev) {
+	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -80,7 +84,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 	memset(&data->plca_cfg, 0xff,
 	       sizeof_field(struct plca_reply_data, plca_cfg));
 
-	ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg);
+	ret = ops->get_plca_cfg(phydev, &data->plca_cfg);
 	ethnl_ops_complete(dev);
 
 out:
@@ -129,7 +133,7 @@ static int plca_get_cfg_fill_reply(struct sk_buff *skb,
 
 const struct nla_policy ethnl_plca_set_cfg_policy[] = {
 	[ETHTOOL_A_PLCA_HEADER]		=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_phy),
 	[ETHTOOL_A_PLCA_ENABLED]	= NLA_POLICY_MAX(NLA_U8, 1),
 	[ETHTOOL_A_PLCA_NODE_ID]	= NLA_POLICY_MAX(NLA_U32, 255),
 	[ETHTOOL_A_PLCA_NODE_CNT]	= NLA_POLICY_RANGE(NLA_U32, 1, 255),
@@ -141,15 +145,17 @@ const struct nla_policy ethnl_plca_set_cfg_policy[] = {
 static int
 ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 {
-	struct net_device *dev = req_info->dev;
 	const struct ethtool_phy_ops *ops;
 	struct nlattr **tb = info->attrs;
 	struct phy_plca_cfg plca_cfg;
+	struct phy_device *phydev;
 	bool mod = false;
 	int ret;
 
+	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PLCA_HEADER],
+				      info->extack);
 	// check that the PHY device is available and connected
-	if (!dev->phydev)
+	if (IS_ERR_OR_NULL(phydev))
 		return -EOPNOTSUPP;
 
 	ops = ethtool_phy_ops;
@@ -168,7 +174,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 	if (!mod)
 		return 0;
 
-	ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack);
+	ret = ops->set_plca_cfg(phydev, &plca_cfg, info->extack);
 	return ret < 0 ? ret : 1;
 }
 
@@ -191,7 +197,7 @@ const struct ethnl_request_ops ethnl_plca_cfg_request_ops = {
 
 const struct nla_policy ethnl_plca_get_status_policy[] = {
 	[ETHTOOL_A_PLCA_HEADER]		=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_phy),
 };
 
 static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
@@ -201,10 +207,14 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 	struct plca_reply_data *data = PLCA_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
 	const struct ethtool_phy_ops *ops;
+	struct nlattr **tb = info->attrs;
+	struct phy_device *phydev;
 	int ret;
 
+	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER],
+				      info->extack);
 	// check that the PHY device is available and connected
-	if (!dev->phydev) {
+	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -223,7 +233,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 	memset(&data->plca_st, 0xff,
 	       sizeof_field(struct plca_reply_data, plca_st));
 
-	ret = ops->get_plca_status(dev->phydev, &data->plca_st);
+	ret = ops->get_plca_status(phydev, &data->plca_st);
 	ethnl_ops_complete(dev);
 out:
 	return ret;
-- 
cgit v1.3-3-g829e


From 31748765bed3fb7cebf4a32b43a6fdf91b9c23de Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:04 +0200
Subject: net: ethtool: pse-pd: Target the command to the requested PHY

PSE and PD configuration is a PHY-specific command. Instead of targeting
the command towards dev->phydev, use the request to pick the targeted
PHY device.

As we don't get the PHY directly from the netdev's attached phydev, also
adjust the error messages.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/pse-pd.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index ff81aa749784..507cb21d6bf0 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -28,17 +28,15 @@ struct pse_reply_data {
 /* PSE_GET */
 
 const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = {
-	[ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy),
 };
 
-static int pse_get_pse_attributes(struct net_device *dev,
+static int pse_get_pse_attributes(struct phy_device *phydev,
 				  struct netlink_ext_ack *extack,
 				  struct pse_reply_data *data)
 {
-	struct phy_device *phydev = dev->phydev;
-
 	if (!phydev) {
-		NL_SET_ERR_MSG(extack, "No PHY is attached");
+		NL_SET_ERR_MSG(extack, "No PHY found");
 		return -EOPNOTSUPP;
 	}
 
@@ -58,13 +56,20 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
 {
 	struct pse_reply_data *data = PSE_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
+	struct nlattr **tb = info->attrs;
+	struct phy_device *phydev;
 	int ret;
 
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		return ret;
 
-	ret = pse_get_pse_attributes(dev, info->extack, data);
+	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER],
+				      info->extack);
+	if (IS_ERR(phydev))
+		return -ENODEV;
+
+	ret = pse_get_pse_attributes(phydev, info->extack, data);
 
 	ethnl_ops_complete(dev);
 
@@ -206,7 +211,7 @@ static void pse_cleanup_data(struct ethnl_reply_data *reply_base)
 /* PSE_SET */
 
 const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = {
-	[ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy),
 	[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] =
 		NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED,
 				 ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED),
@@ -219,12 +224,12 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = {
 static int
 ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info)
 {
-	struct net_device *dev = req_info->dev;
 	struct nlattr **tb = info->attrs;
 	struct phy_device *phydev;
 
-	phydev = dev->phydev;
-	if (!phydev) {
+	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER],
+				      info->extack);
+	if (IS_ERR_OR_NULL(phydev)) {
 		NL_SET_ERR_MSG(info->extack, "No PHY is attached");
 		return -EOPNOTSUPP;
 	}
@@ -255,12 +260,14 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info)
 static int
 ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 {
-	struct net_device *dev = req_info->dev;
 	struct nlattr **tb = info->attrs;
 	struct phy_device *phydev;
 	int ret = 0;
 
-	phydev = dev->phydev;
+	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER],
+				      info->extack);
+	if (IS_ERR_OR_NULL(phydev))
+		return -ENODEV;
 
 	if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) {
 		unsigned int pw_limit;
-- 
cgit v1.3-3-g829e


From 3688ff3077d3f334cee1d4b61d8bfb6a9508c2d2 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:05 +0200
Subject: net: ethtool: cable-test: Target the command to the requested PHY

Cable testing is a PHY-specific command. Instead of targeting the command
towards dev->phydev, use the request to pick the targeted PHY.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/cabletest.c | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index f6f136ec7ddf..01db8f394869 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -13,7 +13,7 @@
 
 const struct nla_policy ethnl_cable_test_act_policy[] = {
 	[ETHTOOL_A_CABLE_TEST_HEADER]		=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_phy),
 };
 
 static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd)
@@ -58,6 +58,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	struct ethnl_req_info req_info = {};
 	const struct ethtool_phy_ops *ops;
 	struct nlattr **tb = info->attrs;
+	struct phy_device *phydev;
 	struct net_device *dev;
 	int ret;
 
@@ -69,12 +70,16 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 		return ret;
 
 	dev = req_info.dev;
-	if (!dev->phydev) {
+
+	rtnl_lock();
+	phydev = ethnl_req_get_phydev(&req_info,
+				      tb[ETHTOOL_A_CABLE_TEST_HEADER],
+				      info->extack);
+	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
 		goto out_dev_put;
 	}
 
-	rtnl_lock();
 	ops = ethtool_phy_ops;
 	if (!ops || !ops->start_cable_test) {
 		ret = -EOPNOTSUPP;
@@ -85,13 +90,12 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto out_rtnl;
 
-	ret = ops->start_cable_test(dev->phydev, info->extack);
+	ret = ops->start_cable_test(phydev, info->extack);
 
 	ethnl_ops_complete(dev);
 
 	if (!ret)
-		ethnl_cable_test_started(dev->phydev,
-					 ETHTOOL_MSG_CABLE_TEST_NTF);
+		ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_NTF);
 
 out_rtnl:
 	rtnl_unlock();
@@ -216,7 +220,7 @@ static const struct nla_policy cable_test_tdr_act_cfg_policy[] = {
 
 const struct nla_policy ethnl_cable_test_tdr_act_policy[] = {
 	[ETHTOOL_A_CABLE_TEST_TDR_HEADER]	=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_phy),
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG]		= { .type = NLA_NESTED },
 };
 
@@ -305,6 +309,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 	struct ethnl_req_info req_info = {};
 	const struct ethtool_phy_ops *ops;
 	struct nlattr **tb = info->attrs;
+	struct phy_device *phydev;
 	struct phy_tdr_config cfg;
 	struct net_device *dev;
 	int ret;
@@ -317,10 +322,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		return ret;
 
 	dev = req_info.dev;
-	if (!dev->phydev) {
-		ret = -EOPNOTSUPP;
-		goto out_dev_put;
-	}
 
 	ret = ethnl_act_cable_test_tdr_cfg(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG],
 					   info, &cfg);
@@ -328,6 +329,14 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		goto out_dev_put;
 
 	rtnl_lock();
+	phydev = ethnl_req_get_phydev(&req_info,
+				      tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER],
+				      info->extack);
+	if (!IS_ERR_OR_NULL(phydev)) {
+		ret = -EOPNOTSUPP;
+		goto out_dev_put;
+	}
+
 	ops = ethtool_phy_ops;
 	if (!ops || !ops->start_cable_test_tdr) {
 		ret = -EOPNOTSUPP;
@@ -338,12 +347,12 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto out_rtnl;
 
-	ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg);
+	ret = ops->start_cable_test_tdr(phydev, info->extack, &cfg);
 
 	ethnl_ops_complete(dev);
 
 	if (!ret)
-		ethnl_cable_test_started(dev->phydev,
+		ethnl_cable_test_started(phydev,
 					 ETHTOOL_MSG_CABLE_TEST_TDR_NTF);
 
 out_rtnl:
-- 
cgit v1.3-3-g829e


From e96c93aa4be971276f9340fa74e84ae62701f2f0 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:06 +0200
Subject: net: ethtool: strset: Allow querying phy stats by index

The ETH_SS_PHY_STATS command gets PHY statistics. Use the phydev pointer
from the ethnl request to allow query phy stats from each PHY on the
link.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ethtool/strset.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 56b99606f00b..b3382b3cf325 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -126,7 +126,7 @@ struct strset_reply_data {
 
 const struct nla_policy ethnl_strset_get_policy[] = {
 	[ETHTOOL_A_STRSET_HEADER]	=
-		NLA_POLICY_NESTED(ethnl_header_policy),
+		NLA_POLICY_NESTED(ethnl_header_policy_phy),
 	[ETHTOOL_A_STRSET_STRINGSETS]	= { .type = NLA_NESTED },
 	[ETHTOOL_A_STRSET_COUNTS_ONLY]	= { .type = NLA_FLAG },
 };
@@ -233,17 +233,18 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base)
 }
 
 static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
-			      unsigned int id, bool counts_only)
+			      struct phy_device *phydev, unsigned int id,
+			      bool counts_only)
 {
 	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	void *strings;
 	int count, ret;
 
-	if (id == ETH_SS_PHY_STATS && dev->phydev &&
+	if (id == ETH_SS_PHY_STATS && phydev &&
 	    !ops->get_ethtool_phy_stats && phy_ops &&
 	    phy_ops->get_sset_count)
-		ret = phy_ops->get_sset_count(dev->phydev);
+		ret = phy_ops->get_sset_count(phydev);
 	else if (ops->get_sset_count && ops->get_strings)
 		ret = ops->get_sset_count(dev, id);
 	else
@@ -258,10 +259,10 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev,
 		strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL);
 		if (!strings)
 			return -ENOMEM;
-		if (id == ETH_SS_PHY_STATS && dev->phydev &&
+		if (id == ETH_SS_PHY_STATS && phydev &&
 		    !ops->get_ethtool_phy_stats && phy_ops &&
 		    phy_ops->get_strings)
-			phy_ops->get_strings(dev->phydev, strings);
+			phy_ops->get_strings(phydev, strings);
 		else
 			ops->get_strings(dev, id, strings);
 		info->strings = strings;
@@ -279,6 +280,8 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 	const struct strset_req_info *req_info = STRSET_REQINFO(req_base);
 	struct strset_reply_data *data = STRSET_REPDATA(reply_base);
 	struct net_device *dev = reply_base->dev;
+	struct nlattr **tb = info->attrs;
+	struct phy_device *phydev;
 	unsigned int i;
 	int ret;
 
@@ -296,6 +299,13 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 		return 0;
 	}
 
+	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_HEADER_FLAGS],
+				      info->extack);
+
+	/* phydev can be NULL, check for errors only */
+	if (IS_ERR(phydev))
+		return PTR_ERR(phydev);
+
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		goto err_strset;
@@ -304,7 +314,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 		    !data->sets[i].per_dev)
 			continue;
 
-		ret = strset_prepare_set(&data->sets[i], dev, i,
+		ret = strset_prepare_set(&data->sets[i], dev, phydev, i,
 					 req_info->counts_only);
 		if (ret < 0)
 			goto err_ops;
-- 
cgit v1.3-3-g829e


From db31e09d517bac2ac7314d8c5749ee2cb2b50ef2 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 21 Aug 2024 17:10:07 +0200
Subject: Documentation: networking: document phy_link_topology

The newly introduced phy_link_topology tracks all ethernet PHYs that are
attached to a netdevice. Document the base principle, internal and
external APIs. As the phy_link_topology is expected to be extended, this
documentation will hold any further improvements and additions made
relative to topology handling.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Tested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ethtool-netlink.rst   |   3 +
 Documentation/networking/index.rst             |   1 +
 Documentation/networking/phy-link-topology.rst | 121 +++++++++++++++++++++++++
 3 files changed, 125 insertions(+)
 create mode 100644 Documentation/networking/phy-link-topology.rst

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 8c152871c23c..44cb9e29f325 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -2198,10 +2198,13 @@ Retrieve information about a given Ethernet PHY sitting on the link. The DO
 operation returns all available information about dev->phydev. User can also
 specify a PHY_INDEX, in which case the DO request returns information about that
 specific PHY.
+
 As there can be more than one PHY, the DUMP operation can be used to list the PHYs
 present on a given interface, by passing an interface index or name in
 the dump request.
 
+For more information, refer to :ref:`phy_link_topology`
+
 Request contents:
 
   ====================================  ======  ==========================
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index d1af04b952f8..c71b87346178 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -91,6 +91,7 @@ Contents:
    operstates
    packet_mmap
    phonet
+   phy-link-topology
    pktgen
    plip
    ppp_generic
diff --git a/Documentation/networking/phy-link-topology.rst b/Documentation/networking/phy-link-topology.rst
new file mode 100644
index 000000000000..4dec5d7d6513
--- /dev/null
+++ b/Documentation/networking/phy-link-topology.rst
@@ -0,0 +1,121 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. _phy_link_topology:
+
+=================
+PHY link topology
+=================
+
+Overview
+========
+
+The PHY link topology representation in the networking stack aims at representing
+the hardware layout for any given Ethernet link.
+
+An Ethernet interface from userspace's point of view is nothing but a
+:c:type:`struct net_device <net_device>`, which exposes configuration options
+through the legacy ioctls and the ethtool netlink commands. The base assumption
+when designing these configuration APIs were that the link looks something like ::
+
+  +-----------------------+        +----------+      +--------------+
+  | Ethernet Controller / |        | Ethernet |      | Connector /  |
+  |       MAC             | ------ |   PHY    | ---- |    Port      | ---... to LP
+  +-----------------------+        +----------+      +--------------+
+  struct net_device               struct phy_device
+
+Commands that needs to configure the PHY will go through the net_device.phydev
+field to reach the PHY and perform the relevant configuration.
+
+This assumption falls apart in more complex topologies that can arise when,
+for example, using SFP transceivers (although that's not the only specific case).
+
+Here, we have 2 basic scenarios. Either the MAC is able to output a serialized
+interface, that can directly be fed to an SFP cage, such as SGMII, 1000BaseX,
+10GBaseR, etc.
+
+The link topology then looks like this (when an SFP module is inserted) ::
+
+  +-----+  SGMII  +------------+
+  | MAC | ------- | SFP Module |
+  +-----+         +------------+
+
+Knowing that some modules embed a PHY, the actual link is more like ::
+
+  +-----+  SGMII   +--------------+
+  | MAC | -------- | PHY (on SFP) |
+  +-----+          +--------------+
+
+In this case, the SFP PHY is handled by phylib, and registered by phylink through
+its SFP upstream ops.
+
+Now some Ethernet controllers aren't able to output a serialized interface, so
+we can't directly connect them to an SFP cage. However, some PHYs can be used
+as media-converters, to translate the non-serialized MAC MII interface to a
+serialized MII interface fed to the SFP ::
+
+  +-----+  RGMII  +-----------------------+  SGMII  +--------------+
+  | MAC | ------- | PHY (media converter) | ------- | PHY (on SFP) |
+  +-----+         +-----------------------+         +--------------+
+
+This is where the model of having a single net_device.phydev pointer shows its
+limitations, as we now have 2 PHYs on the link.
+
+The phy_link topology framework aims at providing a way to keep track of every
+PHY on the link, for use by both kernel drivers and subsystems, but also to
+report the topology to userspace, allowing to target individual PHYs in configuration
+commands.
+
+API
+===
+
+The :c:type:`struct phy_link_topology <phy_link_topology>` is a per-netdevice
+resource, that gets initialized at netdevice creation. Once it's initialized,
+it is then possible to register PHYs to the topology through :
+
+:c:func:`phy_link_topo_add_phy`
+
+Besides registering the PHY to the topology, this call will also assign a unique
+index to the PHY, which can then be reported to userspace to refer to this PHY
+(akin to the ifindex). This index is a u32, ranging from 1 to U32_MAX. The value
+0 is reserved to indicate the PHY doesn't belong to any topology yet.
+
+The PHY can then be removed from the topology through
+
+:c:func:`phy_link_topo_del_phy`
+
+These function are already hooked into the phylib subsystem, so all PHYs that
+are linked to a net_device through :c:func:`phy_attach_direct` will automatically
+join the netdev's topology.
+
+PHYs that are on a SFP module will also be automatically registered IF the SFP
+upstream is phylink (so, no media-converter).
+
+PHY drivers that can be used as SFP upstream need to call :c:func:`phy_sfp_attach_phy`
+and :c:func:`phy_sfp_detach_phy`, which can be used as a
+.attach_phy / .detach_phy implementation for the
+:c:type:`struct sfp_upstream_ops <sfp_upstream_ops>`.
+
+UAPI
+====
+
+There exist a set of netlink commands to query the link topology from userspace,
+see ``Documentation/networking/ethtool-netlink.rst``.
+
+The whole point of having a topology representation is to assign the phyindex
+field in :c:type:`struct phy_device <phy_device>`. This index is reported to
+userspace using the ``ETHTOOL_MSG_PHY_GET`` ethtnl command. Performing a DUMP operation
+will result in all PHYs from all net_device being listed. The DUMP command
+accepts either a ``ETHTOOL_A_HEADER_DEV_INDEX`` or ``ETHTOOL_A_HEADER_DEV_NAME``
+to be passed in the request to filter the DUMP to a single net_device.
+
+The retrieved index can then be passed as a request parameter using the
+``ETHTOOL_A_HEADER_PHY_INDEX`` field in the following ethnl commands :
+
+* ``ETHTOOL_MSG_STRSET_GET`` to get the stats string set from a given PHY
+* ``ETHTOOL_MSG_CABLE_TEST_ACT`` and ``ETHTOOL_MSG_CABLE_TEST_ACT``, to perform
+  cable testing on a given PHY on the link (most likely the outermost PHY)
+* ``ETHTOOL_MSG_PSE_SET`` and ``ETHTOOL_MSG_PSE_GET`` for PHY-controlled PoE and PSE settings
+* ``ETHTOOL_MSG_PLCA_GET_CFG``, ``ETHTOOL_MSG_PLCA_SET_CFG`` and ``ETHTOOL_MSG_PLCA_GET_STATUS``
+  to set the PLCA (Physical Layer Collision Avoidance) parameters
+
+Note that the PHY index can be passed to other requests, which will silently
+ignore it if present and irrelevant.
-- 
cgit v1.3-3-g829e


From 6ef1ca2d14f2a78a83dfd40e34f53e8d5c1c0b4b Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:43 +0800
Subject: net: vxlan: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan/vxlan_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 8983e75e9881..34391c18bba7 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -277,8 +277,7 @@ static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
 	rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
+	rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
 static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan,
-- 
cgit v1.3-3-g829e


From 41aa426392be26865a8a774df3e5ec4c56a98b26 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:44 +0800
Subject: fib: rules: delete redundant judgment statements

The initial value of err is -ENOMEM, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 6ebffbc63236..3c76b835493d 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -1205,8 +1205,7 @@ static void notify_rule_change(int event, struct fib_rule *rule,
 	rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, ops->nlgroup, err);
+	rtnl_set_sk_err(net, ops->nlgroup, err);
 }
 
 static void attach_rules(struct list_head *rules, struct net_device *dev)
-- 
cgit v1.3-3-g829e


From c25bdd2ac8cf7da70a226f1a66cdce7af15ff86f Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:45 +0800
Subject: neighbour: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index a6fe88eca939..77b819cd995b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3530,8 +3530,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags,
 	rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
+	rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
 }
 
 void neigh_app_ns(struct neighbour *n)
-- 
cgit v1.3-3-g829e


From 2d522384fb5b8187cb7f8fe7d05c119ac38fd8f3 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:46 +0800
Subject: rtnetlink: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 73fd7f543fd0..cd9487a12d1a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4087,8 +4087,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 	}
 	return skb;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 	return NULL;
 }
 
-- 
cgit v1.3-3-g829e


From 4c180887775f3e3fb46b9e447cf3ea539286919d Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:47 +0800
Subject: ipv4: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/devinet.c       | 6 ++----
 net/ipv4/fib_semantics.c | 3 +--
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 61be85154dd1..ab76744383cf 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1943,8 +1943,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 	rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err);
 }
 
 static size_t inet_get_link_af_size(const struct net_device *dev,
@@ -2140,8 +2139,7 @@ void inet_netconf_notify_devconf(struct net *net, int event, int type,
 	rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err);
 }
 
 static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0f70341cb8b5..ba2df3d2ac15 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -543,8 +543,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
 		    info->nlh, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
+	rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
 }
 
 static int fib_detect_death(struct fib_info *fi, int order,
-- 
cgit v1.3-3-g829e


From ebe39f95bc8138eedaba9adaa5a4d7bfe98a9806 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:48 +0800
Subject: ipmr: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ipmr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index d5295b69bc0a..b0eda745e3bc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2407,8 +2407,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 
 errout:
 	kfree_skb(skb);
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err);
 }
 
 static size_t igmpmsg_netlink_msgsize(size_t payloadlen)
-- 
cgit v1.3-3-g829e


From 649c3c9b8e448f41f6249abcfe9a670a80fac7f7 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:49 +0800
Subject: net: nexthop: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/nexthop.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 9db10d409074..93aaea0006ba 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1090,8 +1090,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info)
 		    info->nlh, gfp_any());
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err);
+	rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err);
 }
 
 static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket)
@@ -1211,8 +1210,7 @@ static void nexthop_bucket_notify(struct nh_res_table *res_table,
 	rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err);
+	rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err);
 }
 
 static bool valid_group_nh(struct nexthop *nh, unsigned int npaths,
-- 
cgit v1.3-3-g829e


From aa32799c017b881a79cb1b9263419626fc9a5f66 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:50 +0800
Subject: ip6mr: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6mr.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index dd342e6ecf3f..e3ee93c562c3 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2431,8 +2431,7 @@ static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
 
 errout:
 	kfree_skb(skb);
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err);
 }
 
 static size_t mrt6msg_netlink_msgsize(size_t payloadlen)
-- 
cgit v1.3-3-g829e


From cd9ebde125bf77e22ba0c47e3ac657b993089a55 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:51 +0800
Subject: net/ipv6: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/route.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 219701caba1e..7e7de29ad05f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6193,8 +6193,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		    info->nlh, gfp_any());
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
 }
 
 void fib6_rt_update(struct net *net, struct fib6_info *rt,
@@ -6220,8 +6219,7 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
 		    info->nlh, gfp_any());
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+	rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
 }
 
 void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
-- 
cgit v1.3-3-g829e


From fb8e83cf443a98297cd15b58b5529f8d259b22f5 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 12:32:52 +0800
Subject: net: mpls: delete redundant judgment statements

The initial value of err is -ENOBUFS, and err is guaranteed to be
less than 0 before all goto errout. Therefore, on the error path
of errout, there is no need to repeatedly judge that err is less than 0,
and delete redundant judgments to make the code more concise.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/af_mpls.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 0e6c94a8c2bc..aba983531ed3 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1201,8 +1201,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int event,
 	rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL);
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err);
+	rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err);
 }
 
 static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = {
@@ -2278,8 +2277,7 @@ static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
 
 	return;
 errout:
-	if (err < 0)
-		rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err);
+	rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err);
 }
 
 static int mpls_valid_getroute_req(struct sk_buff *skb,
-- 
cgit v1.3-3-g829e


From 9c5b6d4e33dd78a0511ec34756d783b7e36028c2 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 22 Aug 2024 15:04:29 +0200
Subject: selftests: add xfrm policy insertion speed test script

Nothing special, just test how long insertion of x policies takes.
This should ideally show linear insertion speeds.

Do not run this by default, it has little value, but it can be useful to
check for insertion speed chahnges when altering the xfrm policy db
implementation.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 tools/testing/selftests/net/Makefile               |  2 +-
 .../testing/selftests/net/xfrm_policy_add_speed.sh | 83 ++++++++++++++++++++++
 2 files changed, 84 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/xfrm_policy_add_speed.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8eaffd7a641c..e127a80ff713 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -56,7 +56,7 @@ TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
 TEST_PROGS += netns-sysctl.sh
-TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh
+TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh xfrm_policy_add_speed.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
diff --git a/tools/testing/selftests/net/xfrm_policy_add_speed.sh b/tools/testing/selftests/net/xfrm_policy_add_speed.sh
new file mode 100755
index 000000000000..2fab29d3cb91
--- /dev/null
+++ b/tools/testing/selftests/net/xfrm_policy_add_speed.sh
@@ -0,0 +1,83 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+source lib.sh
+
+timeout=4m
+ret=0
+tmp=$(mktemp)
+cleanup() {
+	cleanup_all_ns
+	rm -f "$tmp"
+}
+
+trap cleanup EXIT
+
+maxpolicies=100000
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && maxpolicies=10000
+
+do_dummies4() {
+	local dir="$1"
+	local max="$2"
+
+	local policies
+	local pfx
+	pfx=30
+	policies=0
+
+	ip netns exec "$ns" ip xfrm policy flush
+
+	for i in $(seq 1 100);do
+		local s
+		local d
+		for j in $(seq 1 255);do
+			s=$((i+0))
+			d=$((i+100))
+
+			for a in $(seq 1 8 255); do
+				policies=$((policies+1))
+				[ "$policies" -gt "$max" ] && return
+				echo xfrm policy add src 10.$s.$j.0/30 dst 10.$d.$j.$a/$pfx dir $dir action block
+			done
+			for a in $(seq 1 8 255); do
+				policies=$((policies+1))
+				[ "$policies" -gt "$max" ] && return
+				echo xfrm policy add src 10.$s.$j.$a/30 dst 10.$d.$j.0/$pfx dir $dir action block
+			done
+		done
+	done
+}
+
+setup_ns ns
+
+do_bench()
+{
+	local max="$1"
+
+	start=$(date +%s%3N)
+	do_dummies4 "out" "$max" > "$tmp"
+	if ! timeout "$timeout" ip netns exec "$ns" ip -batch "$tmp";then
+		echo "WARNING: policy insertion cancelled after $timeout"
+		ret=1
+	fi
+	stop=$(date +%s%3N)
+
+	result=$((stop-start))
+
+	policies=$(wc -l < "$tmp")
+	printf "Inserted %-06s policies in $result ms\n" $policies
+
+	have=$(ip netns exec "$ns" ip xfrm policy show | grep "action block" | wc -l)
+	if [ "$have" -ne "$policies" ]; then
+		echo "WARNING: mismatch, have $have policies, expected $policies"
+		ret=1
+	fi
+}
+
+p=100
+while [ $p -le "$maxpolicies" ]; do
+	do_bench "$p"
+	p="${p}0"
+done
+
+exit $ret
-- 
cgit v1.3-3-g829e


From 33f611cf7d52ffdaebdcd6e42672ca1d06e22974 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 22 Aug 2024 15:04:30 +0200
Subject: xfrm: policy: don't iterate inexact policies twice at insert time

Since commit
6be3b0db6db8 ("xfrm: policy: add inexact policy search tree infrastructure")
policy lookup no longer walks a list but has a set of candidate lists.

This set has to be searched for the best match.
In case there are several matches, the priority wins.

If the priority is also the same, then the historic behaviour with
a single list was to return the first match (first-in-list).

With introduction of serval lists, this doesn't work and a new
'pos' member was added that reflects the xfrm_policy structs position
in the list.

This value is not exported to userspace and it does not need to be
the 'position in the list', it just needs to make sure that
a->pos < b->pos means that a was added to the lists more recently
than b.

This re-walk is expensive when many inexact policies are in use.

Speed this up: when appending the policy to the end of the walker list,
then just take the ->pos value of the last entry made and add 1.

Add a slowpath version to prevent overflow, if we'd assign UINT_MAX
then iterate the entire list and fix the ordering.

While this speeds up insertion considerably finding the insertion spot
in the inexact list still requires a partial list walk.

This is addressed in followup patches.

Before:
./xfrm_policy_add_speed.sh
Inserted 1000   policies in 72 ms
Inserted 10000  policies in 1540 ms
Inserted 100000 policies in 334780 ms

After:
Inserted 1000   policies in 68 ms
Inserted 10000  policies in 1137 ms
Inserted 100000 policies in 157307 ms

Reported-by: Noel Kuntze <noel@familie-kuntze.de>
Cc: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 59 +++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 6 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c56c61b0c12e..423d1eb24f31 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1237,6 +1237,17 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
 	return delpol;
 }
 
+static bool xfrm_policy_is_dead_or_sk(const struct xfrm_policy *policy)
+{
+	int dir;
+
+	if (policy->walk.dead)
+		return true;
+
+	dir = xfrm_policy_id2dir(policy->index);
+	return dir >= XFRM_POLICY_MAX;
+}
+
 static void xfrm_hash_rebuild(struct work_struct *work)
 {
 	struct net *net = container_of(work, struct net,
@@ -1524,7 +1535,6 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 {
 	struct xfrm_policy *pol, *delpol = NULL;
 	struct hlist_node *newpos = NULL;
-	int i = 0;
 
 	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
 		if (pol->type == policy->type &&
@@ -1548,11 +1558,6 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
 	else
 		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
-
-	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
-		pol->pos = i;
-		i++;
-	}
 }
 
 static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
@@ -2294,10 +2299,52 @@ out:
 	return pol;
 }
 
+static u32 xfrm_gen_pos_slow(struct net *net)
+{
+	struct xfrm_policy *policy;
+	u32 i = 0;
+
+	/* oldest entry is last in list */
+	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+		if (!xfrm_policy_is_dead_or_sk(policy))
+			policy->pos = ++i;
+	}
+
+	return i;
+}
+
+static u32 xfrm_gen_pos(struct net *net)
+{
+	const struct xfrm_policy *policy;
+	u32 i = 0;
+
+	/* most recently added policy is at the head of the list */
+	list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) {
+		if (xfrm_policy_is_dead_or_sk(policy))
+			continue;
+
+		if (policy->pos == UINT_MAX)
+			return xfrm_gen_pos_slow(net);
+
+		i = policy->pos + 1;
+		break;
+	}
+
+	return i;
+}
+
 static void __xfrm_policy_link(struct xfrm_policy *pol, int dir)
 {
 	struct net *net = xp_net(pol);
 
+	switch (dir) {
+	case XFRM_POLICY_IN:
+	case XFRM_POLICY_FWD:
+	case XFRM_POLICY_OUT:
+		pol->pos = xfrm_gen_pos(net);
+		break;
+	}
+
 	list_add(&pol->walk.all, &net->xfrm.policy_all);
 	net->xfrm.policy_count[dir]++;
 	xfrm_pol_hold(pol);
-- 
cgit v1.3-3-g829e


From 563d5ca93e883b9dcb4b7dc8967ac569fd91820d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 22 Aug 2024 15:04:31 +0200
Subject: xfrm: switch migrate to xfrm_policy_lookup_bytype

XFRM_MIGRATE still uses the old lookup method:
first check the bydst hash table, then search the list of all the other
policies.

Switch MIGRATE to use the same lookup function as the packetpath.

This is done to remove the last remaining users of the pernet
xfrm.policy_inexact lists with the intent of removing this list.

After this patch, policies are still added to the list on insertion
and they are rehashed as-needed but no single API makes use of these
anymore.

This change is compile tested only.

Cc: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 106 ++++++++++++++++++-------------------------------
 1 file changed, 39 insertions(+), 67 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 423d1eb24f31..d2feee60bb62 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1252,13 +1252,10 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 {
 	struct net *net = container_of(work, struct net,
 				       xfrm.policy_hthresh.work);
-	unsigned int hmask;
 	struct xfrm_policy *pol;
 	struct xfrm_policy *policy;
 	struct hlist_head *chain;
-	struct hlist_head *odst;
 	struct hlist_node *newpos;
-	int i;
 	int dir;
 	unsigned seq;
 	u8 lbits4, rbits4, lbits6, rbits6;
@@ -1322,23 +1319,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 			goto out_unlock;
 	}
 
-	/* reset the bydst and inexact table in all directions */
 	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
-		struct hlist_node *n;
-
-		hlist_for_each_entry_safe(policy, n,
-					  &net->xfrm.policy_inexact[dir],
-					  bydst_inexact_list) {
-			hlist_del_rcu(&policy->bydst);
-			hlist_del_init(&policy->bydst_inexact_list);
-		}
-
-		hmask = net->xfrm.policy_bydst[dir].hmask;
-		odst = net->xfrm.policy_bydst[dir].table;
-		for (i = hmask; i >= 0; i--) {
-			hlist_for_each_entry_safe(policy, n, odst + i, bydst)
-				hlist_del_rcu(&policy->bydst);
-		}
 		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
 			/* dir out => dst = remote, src = local */
 			net->xfrm.policy_bydst[dir].dbits4 = rbits4;
@@ -1363,6 +1344,10 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 			/* skip socket policies */
 			continue;
 		}
+
+		hlist_del_rcu(&policy->bydst);
+		hlist_del_init(&policy->bydst_inexact_list);
+
 		newpos = NULL;
 		chain = policy_hash_bysel(net, &policy->selector,
 					  policy->family, dir);
@@ -4484,63 +4469,50 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete);
 #endif
 
 #ifdef CONFIG_XFRM_MIGRATE
-static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp,
-					const struct xfrm_selector *sel_tgt)
-{
-	if (sel_cmp->proto == IPSEC_ULPROTO_ANY) {
-		if (sel_tgt->family == sel_cmp->family &&
-		    xfrm_addr_equal(&sel_tgt->daddr, &sel_cmp->daddr,
-				    sel_cmp->family) &&
-		    xfrm_addr_equal(&sel_tgt->saddr, &sel_cmp->saddr,
-				    sel_cmp->family) &&
-		    sel_tgt->prefixlen_d == sel_cmp->prefixlen_d &&
-		    sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) {
-			return true;
-		}
-	} else {
-		if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) {
-			return true;
-		}
-	}
-	return false;
-}
-
 static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
 						    u8 dir, u8 type, struct net *net, u32 if_id)
 {
 	struct xfrm_policy *pol, *ret = NULL;
-	struct hlist_head *chain;
-	u32 priority = ~0U;
+	struct flowi fl;
 
-	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir);
-	hlist_for_each_entry(pol, chain, bydst) {
-		if ((if_id == 0 || pol->if_id == if_id) &&
-		    xfrm_migrate_selector_match(sel, &pol->selector) &&
-		    pol->type == type) {
-			ret = pol;
-			priority = ret->priority;
-			break;
-		}
-	}
-	chain = &net->xfrm.policy_inexact[dir];
-	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
-		if ((pol->priority >= priority) && ret)
-			break;
+	memset(&fl, 0, sizeof(fl));
 
-		if ((if_id == 0 || pol->if_id == if_id) &&
-		    xfrm_migrate_selector_match(sel, &pol->selector) &&
-		    pol->type == type) {
-			ret = pol;
+	fl.flowi_proto = sel->proto;
+
+	switch (sel->family) {
+	case AF_INET:
+		fl.u.ip4.saddr = sel->saddr.a4;
+		fl.u.ip4.daddr = sel->daddr.a4;
+		if (sel->proto == IPSEC_ULPROTO_ANY)
 			break;
-		}
+		fl.u.flowi4_oif = sel->ifindex;
+		fl.u.ip4.fl4_sport = sel->sport;
+		fl.u.ip4.fl4_dport = sel->dport;
+		break;
+	case AF_INET6:
+		fl.u.ip6.saddr = sel->saddr.in6;
+		fl.u.ip6.daddr = sel->daddr.in6;
+		if (sel->proto == IPSEC_ULPROTO_ANY)
+			break;
+		fl.u.flowi6_oif = sel->ifindex;
+		fl.u.ip6.fl4_sport = sel->sport;
+		fl.u.ip6.fl4_dport = sel->dport;
+		break;
+	default:
+		return ERR_PTR(-EAFNOSUPPORT);
 	}
 
-	xfrm_pol_hold(ret);
+	rcu_read_lock();
 
-	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	pol = xfrm_policy_lookup_bytype(net, type, &fl, sel->family, dir, if_id);
+	if (IS_ERR_OR_NULL(pol))
+		goto out_unlock;
 
-	return ret;
+	if (!xfrm_pol_hold_rcu(ret))
+		pol = NULL;
+out_unlock:
+	rcu_read_unlock();
+	return pol;
 }
 
 static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t)
@@ -4677,9 +4649,9 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 
 	/* Stage 1 - find policy */
 	pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id);
-	if (!pol) {
+	if (IS_ERR_OR_NULL(pol)) {
 		NL_SET_ERR_MSG(extack, "Target policy not found");
-		err = -ENOENT;
+		err = IS_ERR(pol) ? PTR_ERR(pol) : -ENOENT;
 		goto out;
 	}
 
-- 
cgit v1.3-3-g829e


From a54ad727f74559f7c3dfcfd2a63d0ce7683a82e8 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 22 Aug 2024 15:04:32 +0200
Subject: xfrm: policy: remove remaining use of inexact list

No consumers anymore, remove it.  After this, insertion of policies
no longer require list walk of all inexact policies but only those
that are reachable via the candidate sets.

This gives almost linear insertion speeds provided the inserted
policies are for non-overlapping networks.

Before:
Inserted 1000   policies in 70 ms
Inserted 10000  policies in 1155 ms
Inserted 100000 policies in 216848 ms

After:
Inserted 1000   policies in 56 ms
Inserted 10000  policies in 478 ms
Inserted 100000 policies in 4580 ms

Insertion of 1m entries takes about ~40s after this change
on my test vm.

Cc: Noel Kuntze <noel@familie-kuntze.de>
Cc: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |  1 -
 net/xfrm/xfrm_policy.c | 38 --------------------------------------
 2 files changed, 39 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index f7244ac4fa08..1fa2da22a49e 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -555,7 +555,6 @@ struct xfrm_policy {
 	u16			family;
 	struct xfrm_sec_ctx	*security;
 	struct xfrm_tmpl       	xfrm_vec[XFRM_MAX_DEPTH];
-	struct hlist_node	bydst_inexact_list;
 	struct rcu_head		rcu;
 
 	struct xfrm_dev_offload xdo;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d2feee60bb62..b79ac453ea37 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -196,8 +196,6 @@ xfrm_policy_inexact_lookup_rcu(struct net *net,
 static struct xfrm_policy *
 xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy,
 			bool excl);
-static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
-					    struct xfrm_policy *policy);
 
 static bool
 xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand,
@@ -410,7 +408,6 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
 	if (policy) {
 		write_pnet(&policy->xp_net, net);
 		INIT_LIST_HEAD(&policy->walk.all);
-		INIT_HLIST_NODE(&policy->bydst_inexact_list);
 		INIT_HLIST_NODE(&policy->bydst);
 		INIT_HLIST_NODE(&policy->byidx);
 		rwlock_init(&policy->lock);
@@ -1228,9 +1225,6 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl)
 		return ERR_PTR(-EEXIST);
 	}
 
-	chain = &net->xfrm.policy_inexact[dir];
-	xfrm_policy_insert_inexact_list(chain, policy);
-
 	if (delpol)
 		__xfrm_policy_inexact_prune_bin(bin, false);
 
@@ -1346,7 +1340,6 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		}
 
 		hlist_del_rcu(&policy->bydst);
-		hlist_del_init(&policy->bydst_inexact_list);
 
 		newpos = NULL;
 		chain = policy_hash_bysel(net, &policy->selector,
@@ -1515,36 +1508,6 @@ static const struct rhashtable_params xfrm_pol_inexact_params = {
 	.automatic_shrinking	= true,
 };
 
-static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
-					    struct xfrm_policy *policy)
-{
-	struct xfrm_policy *pol, *delpol = NULL;
-	struct hlist_node *newpos = NULL;
-
-	hlist_for_each_entry(pol, chain, bydst_inexact_list) {
-		if (pol->type == policy->type &&
-		    pol->if_id == policy->if_id &&
-		    !selector_cmp(&pol->selector, &policy->selector) &&
-		    xfrm_policy_mark_match(&policy->mark, pol) &&
-		    xfrm_sec_ctx_match(pol->security, policy->security) &&
-		    !WARN_ON(delpol)) {
-			delpol = pol;
-			if (policy->priority > pol->priority)
-				continue;
-		} else if (policy->priority >= pol->priority) {
-			newpos = &pol->bydst_inexact_list;
-			continue;
-		}
-		if (delpol)
-			break;
-	}
-
-	if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
-		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
-	else
-		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
-}
-
 static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
 						   struct xfrm_policy *policy,
 						   bool excl)
@@ -2346,7 +2309,6 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol,
 	/* Socket policies are not hashed. */
 	if (!hlist_unhashed(&pol->bydst)) {
 		hlist_del_rcu(&pol->bydst);
-		hlist_del_init(&pol->bydst_inexact_list);
 		hlist_del(&pol->byidx);
 	}
 
-- 
cgit v1.3-3-g829e


From 7d3aed652d090508990d245f9d80dcc481910d02 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Thu, 22 Aug 2024 05:51:54 +0000
Subject: net: refactor ->ndo_bpf calls into dev_xdp_propagate

When net devices propagate xdp configurations to slave devices,
we will need to perform a memory provider check to ensure we're
not binding xdp to a device using unreadable netmem.

Currently the ->ndo_bpf calls in a few places. Adding checks to all
these places would not be ideal.

Refactor all the ->ndo_bpf calls into one place where we can add this
check in the future.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 8 ++++----
 drivers/net/hyperv/netvsc_bpf.c | 2 +-
 include/linux/netdevice.h       | 1 +
 net/core/dev.c                  | 9 +++++++++
 4 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 96f5470a5f55..a3b6e6c696b4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2253,7 +2253,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 			goto err_sysfs_del;
 		}
 
-		res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		res = dev_xdp_propagate(slave_dev, &xdp);
 		if (res < 0) {
 			/* ndo_bpf() sets extack error message */
 			slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res);
@@ -2389,7 +2389,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 			.prog	 = NULL,
 			.extack  = NULL,
 		};
-		if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp))
+		if (dev_xdp_propagate(slave_dev, &xdp))
 			slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n");
 	}
 
@@ -5579,7 +5579,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			goto err;
 		}
 
-		err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		err = dev_xdp_propagate(slave_dev, &xdp);
 		if (err < 0) {
 			/* ndo_bpf() sets extack error message */
 			slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err);
@@ -5611,7 +5611,7 @@ err:
 		if (slave == rollback_slave)
 			break;
 
-		err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		err_unwind = dev_xdp_propagate(slave_dev, &xdp);
 		if (err_unwind < 0)
 			slave_err(dev, slave_dev,
 				  "Error %d when unwinding XDP program change\n", err_unwind);
diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c
index 4a9522689fa4..e01c5997a551 100644
--- a/drivers/net/hyperv/netvsc_bpf.c
+++ b/drivers/net/hyperv/netvsc_bpf.c
@@ -183,7 +183,7 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog)
 	xdp.command = XDP_SETUP_PROG;
 	xdp.prog = prog;
 
-	ret = vf_netdev->netdev_ops->ndo_bpf(vf_netdev, &xdp);
+	ret = dev_xdp_propagate(vf_netdev, &xdp);
 
 	if (ret && prog)
 		bpf_prog_put(prog);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 289a6133769c..7dfa836d9dbf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3925,6 +3925,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u8 dev_xdp_prog_count(struct net_device *dev);
+int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index d0e7483abdcd..271d6aa0cfb9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9370,6 +9370,15 @@ u8 dev_xdp_prog_count(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_xdp_prog_count);
 
+int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
+{
+	if (!dev->netdev_ops->ndo_bpf)
+		return -EOPNOTSUPP;
+
+	return dev->netdev_ops->ndo_bpf(dev, bpf);
+}
+EXPORT_SYMBOL_GPL(dev_xdp_propagate);
+
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 {
 	struct bpf_prog *prog = dev_xdp_prog(dev, mode);
-- 
cgit v1.3-3-g829e


From 18aaa82bd36ae3d4eaa3f1d1d8cf643e39f151cd Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Thu, 22 Aug 2024 09:03:20 +0200
Subject: net: netlink: Remove the dump_cb_mutex field from struct netlink_sock

Commit 5fbf57a937f4 ("net: netlink: remove the cb_mutex "injection" from
netlink core") has removed the usage of the 'dump_cb_mutex' field from the
struct netlink_sock.

Remove the field itself now. It saves a few bytes in the structure.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netlink/af_netlink.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 9751e29d4bbb..5b0e4e62ab8b 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -41,7 +41,6 @@ struct netlink_sock {
 	struct netlink_callback	cb;
 	struct mutex		nl_cb_mutex;
 
-	struct mutex		*dump_cb_mutex;
 	void			(*netlink_rcv)(struct sk_buff *skb);
 	int			(*netlink_bind)(struct net *net, int group);
 	void			(*netlink_unbind)(struct net *net, int group);
-- 
cgit v1.3-3-g829e


From d4c897675a5a9f41a3f2c964d84e93bca5367f7a Mon Sep 17 00:00:00 2001
From: Divya Koppera <divya.koppera@microchip.com>
Date: Wed, 21 Aug 2024 11:29:05 +0530
Subject: net: phy: Add phy library support to check supported list when
 autoneg is enabled

Adds support in phy library to accept autoneg configuration only when
feature is enabled in supported list.

Signed-off-by: Divya Koppera <divya.koppera@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240821055906.27717-2-Divya.Koppera@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 785182fa5fe0..cba3af926429 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1089,7 +1089,10 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev,
 	if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
 		return -EINVAL;
 
-	if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
+	if (autoneg == AUTONEG_ENABLE &&
+	    (linkmode_empty(advertising) ||
+	     !linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				phydev->supported)))
 		return -EINVAL;
 
 	if (autoneg == AUTONEG_DISABLE &&
-- 
cgit v1.3-3-g829e


From 0941c83282349859e736b279908fd958f23e281a Mon Sep 17 00:00:00 2001
From: Divya Koppera <divya.koppera@microchip.com>
Date: Wed, 21 Aug 2024 11:29:06 +0530
Subject: net: phy: microchip_t1: Adds support for lan887x phy

The LAN887x is a Single-Port Ethernet Physical Layer Transceiver compliant
with the IEEE 802.3bw (100BASE-T1) and IEEE 802.3bp (1000BASE-T1)
specifications. The device provides 100/1000 Mbit/s transmit and receive
capability over a single Unshielded Twisted Pair (UTP) cable. It supports
communication with an Ethernet MAC via standard RGMII/SGMII interfaces.

LAN887x supports following features,
- Events/Interrupts
- LED/GPIO Operation
- IEEE 1588 (PTP)
- SQI
- Sleep and Wakeup (TC10)
- Cable Diagnostics

First patch only supports 100Mbps and 1000Mbps force-mode.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Divya Koppera <divya.koppera@microchip.com>
Link: https://patch.msgid.link/20240821055906.27717-3-Divya.Koppera@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/microchip_t1.c | 577 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 576 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c
index a35528497a57..5732ad65e7f9 100644
--- a/drivers/net/phy/microchip_t1.c
+++ b/drivers/net/phy/microchip_t1.c
@@ -12,6 +12,7 @@
 
 #define PHY_ID_LAN87XX				0x0007c150
 #define PHY_ID_LAN937X				0x0007c180
+#define PHY_ID_LAN887X				0x0007c1f0
 
 /* External Register Control Register */
 #define LAN87XX_EXT_REG_CTL                     (0x14)
@@ -94,8 +95,101 @@
 /* SQI defines */
 #define LAN87XX_MAX_SQI			0x07
 
+/* Chiptop registers */
+#define LAN887X_PMA_EXT_ABILITY_2		0x12
+#define LAN887X_PMA_EXT_ABILITY_2_1000T1	BIT(1)
+#define LAN887X_PMA_EXT_ABILITY_2_100T1		BIT(0)
+
+/* DSP 100M registers */
+#define LAN887x_CDR_CONFIG1_100			0x0405
+#define LAN887x_LOCK1_EQLSR_CONFIG_100		0x0411
+#define LAN887x_SLV_HD_MUFAC_CONFIG_100		0x0417
+#define LAN887x_PLOCK_MUFAC_CONFIG_100		0x041c
+#define LAN887x_PROT_DISABLE_100		0x0425
+#define LAN887x_KF_LOOP_SAT_CONFIG_100		0x0454
+
+/* DSP 1000M registers */
+#define LAN887X_LOCK1_EQLSR_CONFIG		0x0811
+#define LAN887X_LOCK3_EQLSR_CONFIG		0x0813
+#define LAN887X_PROT_DISABLE			0x0825
+#define LAN887X_FFE_GAIN6			0x0843
+#define LAN887X_FFE_GAIN7			0x0844
+#define LAN887X_FFE_GAIN8			0x0845
+#define LAN887X_FFE_GAIN9			0x0846
+#define LAN887X_ECHO_DELAY_CONFIG		0x08ec
+#define LAN887X_FFE_MAX_CONFIG			0x08ee
+
+/* PCS 1000M registers */
+#define LAN887X_SCR_CONFIG_3			0x8043
+#define LAN887X_INFO_FLD_CONFIG_5		0x8048
+
+/* T1 afe registers */
+#define LAN887X_ZQCAL_CONTROL_1			0x8080
+#define LAN887X_AFE_PORT_TESTBUS_CTRL2		0x8089
+#define LAN887X_AFE_PORT_TESTBUS_CTRL4		0x808b
+#define LAN887X_AFE_PORT_TESTBUS_CTRL6		0x808d
+#define LAN887X_TX_AMPLT_1000T1_REG		0x80b0
+#define LAN887X_INIT_COEFF_DFE1_100		0x0422
+
+/* PMA registers */
+#define LAN887X_DSP_PMA_CONTROL			0x810e
+#define LAN887X_DSP_PMA_CONTROL_LNK_SYNC	BIT(4)
+
+/* PCS 100M registers */
+#define LAN887X_IDLE_ERR_TIMER_WIN		0x8204
+#define LAN887X_IDLE_ERR_CNT_THRESH		0x8213
+
+/* Misc registers */
+#define LAN887X_REG_REG26			0x001a
+#define LAN887X_REG_REG26_HW_INIT_SEQ_EN	BIT(8)
+
+/* Mis registers */
+#define LAN887X_MIS_CFG_REG0			0xa00
+#define LAN887X_MIS_CFG_REG0_RCLKOUT_DIS	BIT(5)
+#define LAN887X_MIS_CFG_REG0_MAC_MODE_SEL	GENMASK(1, 0)
+
+#define LAN887X_MAC_MODE_RGMII			0x01
+#define LAN887X_MAC_MODE_SGMII			0x03
+
+#define LAN887X_MIS_DLL_CFG_REG0		0xa01
+#define LAN887X_MIS_DLL_CFG_REG1		0xa02
+
+#define LAN887X_MIS_DLL_DELAY_EN		BIT(15)
+#define LAN887X_MIS_DLL_EN			BIT(0)
+#define LAN887X_MIS_DLL_CONF	(LAN887X_MIS_DLL_DELAY_EN |\
+				 LAN887X_MIS_DLL_EN)
+
+#define LAN887X_MIS_CFG_REG2			0xa03
+#define LAN887X_MIS_CFG_REG2_FE_LPBK_EN		BIT(2)
+
+#define LAN887X_MIS_PKT_STAT_REG0		0xa06
+#define LAN887X_MIS_PKT_STAT_REG1		0xa07
+#define LAN887X_MIS_PKT_STAT_REG3		0xa09
+#define LAN887X_MIS_PKT_STAT_REG4		0xa0a
+#define LAN887X_MIS_PKT_STAT_REG5		0xa0b
+#define LAN887X_MIS_PKT_STAT_REG6		0xa0c
+
+/* Chiptop common registers */
+#define LAN887X_COMMON_LED3_LED2		0xc05
+#define LAN887X_COMMON_LED2_MODE_SEL_MASK	GENMASK(4, 0)
+#define LAN887X_LED_LINK_ACT_ANY_SPEED		0x0
+
+/* MX chip top registers */
+#define LAN887X_CHIP_SOFT_RST			0xf03f
+#define LAN887X_CHIP_SOFT_RST_RESET		BIT(0)
+
+#define LAN887X_SGMII_CTL			0xf01a
+#define LAN887X_SGMII_CTL_SGMII_MUX_EN		BIT(0)
+
+#define LAN887X_SGMII_PCS_CFG			0xf034
+#define LAN887X_SGMII_PCS_CFG_PCS_ENA		BIT(9)
+
+#define LAN887X_EFUSE_READ_DAT9			0xf209
+#define LAN887X_EFUSE_READ_DAT9_SGMII_DIS	BIT(9)
+#define LAN887X_EFUSE_READ_DAT9_MAC_MODE	GENMASK(1, 0)
+
 #define DRIVER_AUTHOR	"Nisar Sayed <nisar.sayed@microchip.com>"
-#define DRIVER_DESC	"Microchip LAN87XX/LAN937x T1 PHY driver"
+#define DRIVER_DESC	"Microchip LAN87XX/LAN937x/LAN887x T1 PHY driver"
 
 struct access_ereg_val {
 	u8  mode;
@@ -105,6 +199,32 @@ struct access_ereg_val {
 	u16 mask;
 };
 
+struct lan887x_hw_stat {
+	const char *string;
+	u8 mmd;
+	u16 reg;
+	u8 bits;
+};
+
+static const struct lan887x_hw_stat lan887x_hw_stats[] = {
+	{ "TX Good Count",                      MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG0, 14},
+	{ "RX Good Count",                      MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG1, 14},
+	{ "RX ERR Count detected by PCS",       MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG3, 16},
+	{ "TX CRC ERR Count",                   MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG4, 8},
+	{ "RX CRC ERR Count",                   MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG5, 8},
+	{ "RX ERR Count for SGMII MII2GMII",    MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG6, 8},
+};
+
+struct lan887x_regwr_map {
+	u8  mmd;
+	u16 reg;
+	u16 val;
+};
+
+struct lan887x_priv {
+	u64 stats[ARRAY_SIZE(lan887x_hw_stats)];
+};
+
 static int lan937x_dsp_workaround(struct phy_device *phydev, u16 ereg, u8 bank)
 {
 	u8 prev_bank;
@@ -860,6 +980,446 @@ static int lan87xx_get_sqi_max(struct phy_device *phydev)
 	return LAN87XX_MAX_SQI;
 }
 
+static int lan887x_rgmii_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* SGMII mux disable */
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 LAN887X_SGMII_CTL,
+				 LAN887X_SGMII_CTL_SGMII_MUX_EN);
+	if (ret < 0)
+		return ret;
+
+	/* Select MAC_MODE as RGMII */
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0,
+			     LAN887X_MIS_CFG_REG0_MAC_MODE_SEL,
+			     LAN887X_MAC_MODE_RGMII);
+	if (ret < 0)
+		return ret;
+
+	/* Disable PCS */
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 LAN887X_SGMII_PCS_CFG,
+				 LAN887X_SGMII_PCS_CFG_PCS_ENA);
+	if (ret < 0)
+		return ret;
+
+	/* LAN887x Errata: RGMII rx clock active in SGMII mode
+	 * Disabled it for SGMII mode
+	 * Re-enabling it for RGMII mode
+	 */
+	return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				  LAN887X_MIS_CFG_REG0,
+				  LAN887X_MIS_CFG_REG0_RCLKOUT_DIS);
+}
+
+static int lan887x_sgmii_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* SGMII mux enable */
+	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+			       LAN887X_SGMII_CTL,
+			       LAN887X_SGMII_CTL_SGMII_MUX_EN);
+	if (ret < 0)
+		return ret;
+
+	/* Select MAC_MODE as SGMII */
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0,
+			     LAN887X_MIS_CFG_REG0_MAC_MODE_SEL,
+			     LAN887X_MAC_MODE_SGMII);
+	if (ret < 0)
+		return ret;
+
+	/* LAN887x Errata: RGMII rx clock active in SGMII mode.
+	 * So disabling it for SGMII mode
+	 */
+	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0,
+			       LAN887X_MIS_CFG_REG0_RCLKOUT_DIS);
+	if (ret < 0)
+		return ret;
+
+	/* Enable PCS */
+	return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_SGMII_PCS_CFG,
+				LAN887X_SGMII_PCS_CFG_PCS_ENA);
+}
+
+static int lan887x_config_rgmii_en(struct phy_device *phydev)
+{
+	int txc;
+	int rxc;
+	int ret;
+
+	ret = lan887x_rgmii_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Control bit to enable/disable TX DLL delay line in signal path */
+	txc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG0);
+	if (txc < 0)
+		return txc;
+
+	/* Control bit to enable/disable RX DLL delay line in signal path */
+	rxc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG1);
+	if (rxc < 0)
+		return rxc;
+
+	/* Configures the phy to enable RX/TX delay
+	 * RGMII        - TX & RX delays are either added by MAC or not needed,
+	 *                phy should not add
+	 * RGMII_ID     - Configures phy to enable TX & RX delays, MAC shouldn't add
+	 * RGMII_RX_ID  - Configures the PHY to enable the RX delay.
+	 *                The MAC shouldn't add the RX delay
+	 * RGMII_TX_ID  - Configures the PHY to enable the TX delay.
+	 *                The MAC shouldn't add the TX delay in this case
+	 */
+	switch (phydev->interface) {
+	case PHY_INTERFACE_MODE_RGMII:
+		txc &= ~LAN887X_MIS_DLL_CONF;
+		rxc &= ~LAN887X_MIS_DLL_CONF;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		txc |= LAN887X_MIS_DLL_CONF;
+		rxc |= LAN887X_MIS_DLL_CONF;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		txc &= ~LAN887X_MIS_DLL_CONF;
+		rxc |= LAN887X_MIS_DLL_CONF;
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		txc |= LAN887X_MIS_DLL_CONF;
+		rxc &= ~LAN887X_MIS_DLL_CONF;
+		break;
+	default:
+		WARN_ONCE(1, "Invalid phydev interface %d\n", phydev->interface);
+		return 0;
+	}
+
+	/* Configures the PHY to enable/disable RX delay in signal path */
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG1,
+			     LAN887X_MIS_DLL_CONF, rxc);
+	if (ret < 0)
+		return ret;
+
+	/* Configures the PHY to enable/disable the TX delay in signal path */
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG0,
+			      LAN887X_MIS_DLL_CONF, txc);
+}
+
+static int lan887x_config_phy_interface(struct phy_device *phydev)
+{
+	int interface_mode;
+	int sgmii_dis;
+	int ret;
+
+	/* Read sku efuse data for interfaces supported by sku */
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_EFUSE_READ_DAT9);
+	if (ret < 0)
+		return ret;
+
+	/* If interface_mode is 1 then efuse sets RGMII operations.
+	 * If interface mode is 3 then efuse sets SGMII operations.
+	 */
+	interface_mode = ret & LAN887X_EFUSE_READ_DAT9_MAC_MODE;
+	/* SGMII disable is set for RGMII operations */
+	sgmii_dis = ret & LAN887X_EFUSE_READ_DAT9_SGMII_DIS;
+
+	switch (phydev->interface) {
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		/* Reject RGMII settings for SGMII only sku */
+		ret = -EOPNOTSUPP;
+
+		if (!((interface_mode & LAN887X_MAC_MODE_SGMII) ==
+		    LAN887X_MAC_MODE_SGMII))
+			ret = lan887x_config_rgmii_en(phydev);
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		/* Reject SGMII setting for RGMII only sku */
+		ret = -EOPNOTSUPP;
+
+		if (!sgmii_dis)
+			ret = lan887x_sgmii_init(phydev);
+		break;
+	default:
+		/* Reject setting for unsupported interfaces */
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static int lan887x_get_features(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_pma_read_abilities(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Enable twisted pair */
+	linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, phydev->supported);
+
+	/* First patch only supports 100Mbps and 1000Mbps force-mode.
+	 * T1 Auto-Negotiation (Clause 98 of IEEE 802.3) will be added later.
+	 */
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported);
+
+	return 0;
+}
+
+static int lan887x_phy_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Clear loopback */
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+				 LAN887X_MIS_CFG_REG2,
+				 LAN887X_MIS_CFG_REG2_FE_LPBK_EN);
+	if (ret < 0)
+		return ret;
+
+	/* Configure default behavior of led to link and activity for any
+	 * speed
+	 */
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+			     LAN887X_COMMON_LED3_LED2,
+			     LAN887X_COMMON_LED2_MODE_SEL_MASK,
+			     LAN887X_LED_LINK_ACT_ANY_SPEED);
+	if (ret < 0)
+		return ret;
+
+	/* PHY interface setup */
+	return lan887x_config_phy_interface(phydev);
+}
+
+static int lan887x_phy_config(struct phy_device *phydev,
+			      const struct lan887x_regwr_map *reg_map, int cnt)
+{
+	int ret;
+
+	for (int i = 0; i < cnt; i++) {
+		ret = phy_write_mmd(phydev, reg_map[i].mmd,
+				    reg_map[i].reg, reg_map[i].val);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int lan887x_phy_setup(struct phy_device *phydev)
+{
+	static const struct lan887x_regwr_map phy_cfg[] = {
+		/* PORT_AFE writes */
+		{MDIO_MMD_PMAPMD, LAN887X_ZQCAL_CONTROL_1, 0x4008},
+		{MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL2, 0x0000},
+		{MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL6, 0x0040},
+		/* 100T1_PCS_VENDOR writes */
+		{MDIO_MMD_PCS,	  LAN887X_IDLE_ERR_CNT_THRESH, 0x0008},
+		{MDIO_MMD_PCS,	  LAN887X_IDLE_ERR_TIMER_WIN, 0x800d},
+		/* 100T1 DSP writes */
+		{MDIO_MMD_VEND1,  LAN887x_CDR_CONFIG1_100, 0x0ab1},
+		{MDIO_MMD_VEND1,  LAN887x_LOCK1_EQLSR_CONFIG_100, 0x5274},
+		{MDIO_MMD_VEND1,  LAN887x_SLV_HD_MUFAC_CONFIG_100, 0x0d74},
+		{MDIO_MMD_VEND1,  LAN887x_PLOCK_MUFAC_CONFIG_100, 0x0aea},
+		{MDIO_MMD_VEND1,  LAN887x_PROT_DISABLE_100, 0x0360},
+		{MDIO_MMD_VEND1,  LAN887x_KF_LOOP_SAT_CONFIG_100, 0x0c30},
+		/* 1000T1 DSP writes */
+		{MDIO_MMD_VEND1,  LAN887X_LOCK1_EQLSR_CONFIG, 0x2a78},
+		{MDIO_MMD_VEND1,  LAN887X_LOCK3_EQLSR_CONFIG, 0x1368},
+		{MDIO_MMD_VEND1,  LAN887X_PROT_DISABLE, 0x1354},
+		{MDIO_MMD_VEND1,  LAN887X_FFE_GAIN6, 0x3C84},
+		{MDIO_MMD_VEND1,  LAN887X_FFE_GAIN7, 0x3ca5},
+		{MDIO_MMD_VEND1,  LAN887X_FFE_GAIN8, 0x3ca5},
+		{MDIO_MMD_VEND1,  LAN887X_FFE_GAIN9, 0x3ca5},
+		{MDIO_MMD_VEND1,  LAN887X_ECHO_DELAY_CONFIG, 0x0024},
+		{MDIO_MMD_VEND1,  LAN887X_FFE_MAX_CONFIG, 0x227f},
+		/* 1000T1 PCS writes */
+		{MDIO_MMD_PCS,    LAN887X_SCR_CONFIG_3, 0x1e00},
+		{MDIO_MMD_PCS,    LAN887X_INFO_FLD_CONFIG_5, 0x0fa1},
+	};
+
+	return lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg));
+}
+
+static int lan887x_100M_setup(struct phy_device *phydev)
+{
+	int ret;
+
+	/* (Re)configure the speed/mode dependent T1 settings */
+	if (phydev->master_slave_set == MASTER_SLAVE_CFG_MASTER_FORCE ||
+	    phydev->master_slave_set == MASTER_SLAVE_CFG_MASTER_PREFERRED){
+		static const struct lan887x_regwr_map phy_cfg[] = {
+			{MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x00b8},
+			{MDIO_MMD_PMAPMD, LAN887X_TX_AMPLT_1000T1_REG, 0x0038},
+			{MDIO_MMD_VEND1,  LAN887X_INIT_COEFF_DFE1_100, 0x000f},
+		};
+
+		ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg));
+	} else {
+		static const struct lan887x_regwr_map phy_cfg[] = {
+			{MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x0038},
+			{MDIO_MMD_VEND1, LAN887X_INIT_COEFF_DFE1_100, 0x0014},
+		};
+
+		ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg));
+	}
+	if (ret < 0)
+		return ret;
+
+	return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26,
+				LAN887X_REG_REG26_HW_INIT_SEQ_EN);
+}
+
+static int lan887x_1000M_setup(struct phy_device *phydev)
+{
+	static const struct lan887x_regwr_map phy_cfg[] = {
+		{MDIO_MMD_PMAPMD, LAN887X_TX_AMPLT_1000T1_REG, 0x003f},
+		{MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x00b8},
+	};
+	int ret;
+
+	/* (Re)configure the speed/mode dependent T1 settings */
+	ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg));
+	if (ret < 0)
+		return ret;
+
+	return phy_set_bits_mmd(phydev, MDIO_MMD_PMAPMD, LAN887X_DSP_PMA_CONTROL,
+				LAN887X_DSP_PMA_CONTROL_LNK_SYNC);
+}
+
+static int lan887x_link_setup(struct phy_device *phydev)
+{
+	int ret = -EINVAL;
+
+	if (phydev->speed == SPEED_1000)
+		ret = lan887x_1000M_setup(phydev);
+	else if (phydev->speed == SPEED_100)
+		ret = lan887x_100M_setup(phydev);
+
+	return ret;
+}
+
+/* LAN887x Errata: speed configuration changes require soft reset
+ * and chip soft reset
+ */
+static int lan887x_phy_reset(struct phy_device *phydev)
+{
+	int ret, val;
+
+	/* Clear 1000M link sync */
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_PMAPMD, LAN887X_DSP_PMA_CONTROL,
+				 LAN887X_DSP_PMA_CONTROL_LNK_SYNC);
+	if (ret < 0)
+		return ret;
+
+	/* Clear 100M link sync */
+	ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26,
+				 LAN887X_REG_REG26_HW_INIT_SEQ_EN);
+	if (ret < 0)
+		return ret;
+
+	/* Chiptop soft-reset to allow the speed/mode change */
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, LAN887X_CHIP_SOFT_RST,
+			    LAN887X_CHIP_SOFT_RST_RESET);
+	if (ret < 0)
+		return ret;
+
+	/* CL22 soft-reset to let the link re-train */
+	ret = phy_modify(phydev, MII_BMCR, BMCR_RESET, BMCR_RESET);
+	if (ret < 0)
+		return ret;
+
+	/* Wait for reset complete or timeout if > 10ms */
+	return phy_read_poll_timeout(phydev, MII_BMCR, val, !(val & BMCR_RESET),
+				    5000, 10000, true);
+}
+
+static int lan887x_phy_reconfig(struct phy_device *phydev)
+{
+	int ret;
+
+	linkmode_zero(phydev->advertising);
+
+	ret = genphy_c45_pma_setup_forced(phydev);
+	if (ret < 0)
+		return ret;
+
+	return lan887x_link_setup(phydev);
+}
+
+static int lan887x_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	/* LAN887x Errata: speed configuration changes require soft reset
+	 * and chip soft reset
+	 */
+	ret = lan887x_phy_reset(phydev);
+	if (ret < 0)
+		return ret;
+
+	return lan887x_phy_reconfig(phydev);
+}
+
+static int lan887x_probe(struct phy_device *phydev)
+{
+	struct lan887x_priv *priv;
+
+	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	phydev->priv = priv;
+
+	return lan887x_phy_setup(phydev);
+}
+
+static u64 lan887x_get_stat(struct phy_device *phydev, int i)
+{
+	struct lan887x_hw_stat stat = lan887x_hw_stats[i];
+	struct lan887x_priv *priv = phydev->priv;
+	int val;
+	u64 ret;
+
+	if (stat.mmd)
+		val = phy_read_mmd(phydev, stat.mmd, stat.reg);
+	else
+		val = phy_read(phydev, stat.reg);
+
+	if (val < 0) {
+		ret = U64_MAX;
+	} else {
+		val = val & ((1 << stat.bits) - 1);
+		priv->stats[i] += val;
+		ret = priv->stats[i];
+	}
+
+	return ret;
+}
+
+static void lan887x_get_stats(struct phy_device *phydev,
+			      struct ethtool_stats *stats, u64 *data)
+{
+	for (int i = 0; i < ARRAY_SIZE(lan887x_hw_stats); i++)
+		data[i] = lan887x_get_stat(phydev, i);
+}
+
+static int lan887x_get_sset_count(struct phy_device *phydev)
+{
+	return ARRAY_SIZE(lan887x_hw_stats);
+}
+
+static void lan887x_get_strings(struct phy_device *phydev, u8 *data)
+{
+	for (int i = 0; i < ARRAY_SIZE(lan887x_hw_stats); i++)
+		ethtool_puts(&data, lan887x_hw_stats[i].string);
+}
+
 static struct phy_driver microchip_t1_phy_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX),
@@ -894,6 +1454,20 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 		.get_sqi_max	= lan87xx_get_sqi_max,
 		.cable_test_start = lan87xx_cable_test_start,
 		.cable_test_get_status = lan87xx_cable_test_get_status,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_LAN887X),
+		.name		= "Microchip LAN887x T1 PHY",
+		.probe		= lan887x_probe,
+		.get_features	= lan887x_get_features,
+		.config_init    = lan887x_phy_init,
+		.config_aneg    = lan887x_config_aneg,
+		.get_stats      = lan887x_get_stats,
+		.get_sset_count = lan887x_get_sset_count,
+		.get_strings    = lan887x_get_strings,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.read_status	= genphy_c45_read_status,
 	}
 };
 
@@ -902,6 +1476,7 @@ module_phy_driver(microchip_t1_phy_driver);
 static struct mdio_device_id __maybe_unused microchip_t1_tbl[] = {
 	{ PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX) },
 	{ PHY_ID_MATCH_MODEL(PHY_ID_LAN937X) },
+	{ PHY_ID_MATCH_MODEL(PHY_ID_LAN887X) },
 	{ }
 };
 
-- 
cgit v1.3-3-g829e


From ae5a0456e0b4cfd7e61619e55251ffdf1bc7adfb Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 22 Aug 2024 04:10:47 -0700
Subject: netpoll: Ensure clean state on setup failures

Modify netpoll_setup() and __netpoll_setup() to ensure that the netpoll
structure (np) is left in a clean state if setup fails for any reason.
This prevents carrying over misconfigured fields in case of partial
setup success.

Key changes:
- np->dev is now set only after successful setup, ensuring it's always
  NULL if netpoll is not configured or if netpoll_setup() fails.
- np->local_ip is zeroed if netpoll setup doesn't complete successfully.
- Added DEBUG_NET_WARN_ON_ONCE() checks to catch unexpected states.
- Reordered some operations in __netpoll_setup() for better logical flow.

These changes improve the reliability of netpoll configuration, since it
assures that the structure is fully initialized or totally unset.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20240822111051.179850-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netpoll.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index cff1f89719b6..a1aea86cf98c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -624,12 +624,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 	const struct net_device_ops *ops;
 	int err;
 
-	np->dev = ndev;
-	strscpy(np->dev_name, ndev->name, IFNAMSIZ);
-
 	if (ndev->priv_flags & IFF_DISABLE_NETPOLL) {
 		np_err(np, "%s doesn't support polling, aborting\n",
-		       np->dev_name);
+		       ndev->name);
 		err = -ENOTSUPP;
 		goto out;
 	}
@@ -647,7 +644,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 
 		refcount_set(&npinfo->refcnt, 1);
 
-		ops = np->dev->netdev_ops;
+		ops = ndev->netdev_ops;
 		if (ops->ndo_netpoll_setup) {
 			err = ops->ndo_netpoll_setup(ndev, npinfo);
 			if (err)
@@ -658,6 +655,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 		refcount_inc(&npinfo->refcnt);
 	}
 
+	np->dev = ndev;
+	strscpy(np->dev_name, ndev->name, IFNAMSIZ);
 	npinfo->netpoll = np;
 
 	/* last thing to do is link it to the net device structure */
@@ -675,6 +674,7 @@ EXPORT_SYMBOL_GPL(__netpoll_setup);
 int netpoll_setup(struct netpoll *np)
 {
 	struct net_device *ndev = NULL;
+	bool ip_overwritten = false;
 	struct in_device *in_dev;
 	int err;
 
@@ -739,6 +739,7 @@ put_noaddr:
 			}
 
 			np->local_ip.ip = ifa->ifa_local;
+			ip_overwritten = true;
 			np_info(np, "local IP %pI4\n", &np->local_ip.ip);
 		} else {
 #if IS_ENABLED(CONFIG_IPV6)
@@ -755,6 +756,7 @@ put_noaddr:
 					    !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL))
 						continue;
 					np->local_ip.in6 = ifp->addr;
+					ip_overwritten = true;
 					err = 0;
 					break;
 				}
@@ -785,6 +787,9 @@ put_noaddr:
 	return 0;
 
 put:
+	DEBUG_NET_WARN_ON_ONCE(np->dev);
+	if (ip_overwritten)
+		memset(&np->local_ip, 0, sizeof(np->local_ip));
 	netdev_put(ndev, &np->dev_tracker);
 unlock:
 	rtnl_unlock();
-- 
cgit v1.3-3-g829e


From 908ee298c8fb3f9129a470735e8bb8037a95221e Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 22 Aug 2024 04:10:48 -0700
Subject: net: netconsole: Populate dynamic entry even if netpoll fails

Currently, netconsole discards targets that fail during initialization,
causing two issues:

1) Inconsistency between target list and configfs entries
  * user pass cmdline0, cmdline1. If cmdline0 fails, then cmdline1
    becomes cmdline0 in configfs.

2) Inability to manage failed targets from userspace
  * If user pass a target that fails with netpoll (interface not loaded at
    netcons initialization time, such as interface is a module), then
    the target will not exist in the configfs, so, user cannot re-enable
    or modify it from userspace.

Failed targets are now added to the target list and configfs, but
remain disabled until manually enabled or reconfigured. This change does
not change the behaviour if CONFIG_NETCONSOLE_DYNAMIC is not set.

CC: Aijay Adams <aijay@meta.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20240822111051.179850-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 72384c1ecc5c..01cf33fa7503 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1258,11 +1258,18 @@ static struct netconsole_target *alloc_param_target(char *target_config,
 		goto fail;
 
 	err = netpoll_setup(&nt->np);
-	if (err)
-		goto fail;
-
+	if (err) {
+		pr_err("Not enabling netconsole for %s%d. Netpoll setup failed\n",
+		       NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count);
+		if (!IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC))
+			/* only fail if dynamic reconfiguration is set,
+			 * otherwise, keep the target in the list, but disabled.
+			 */
+			goto fail;
+	} else {
+		nt->enabled = true;
+	}
 	populate_configfs_item(nt, cmdline_count);
-	nt->enabled = true;
 
 	return nt;
 
-- 
cgit v1.3-3-g829e


From b494b1673889c95ead43fb6978687fb61bb042d5 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 22 Aug 2024 02:56:39 -0700
Subject: net: netconsole: selftests: Create a new netconsole selftest

Adds a selftest that creates two virtual interfaces, assigns one to a
new namespace, and assigns IP addresses to both.

It listens on the destination interface using socat and configures a
dynamic target on netconsole, pointing to the destination IP address.

The test then checks if the message was received properly on the
destination interface.

Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240822095652.3806208-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                                        |   1 +
 tools/testing/selftests/drivers/net/Makefile       |   5 +-
 tools/testing/selftests/drivers/net/config         |   4 +
 .../testing/selftests/drivers/net/netcons_basic.sh | 234 +++++++++++++++++++++
 4 files changed, 243 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/drivers/net/netcons_basic.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index e4fa9010fcb6..30a9b9450e11 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15775,6 +15775,7 @@ M:	Breno Leitao <leitao@debian.org>
 S:	Maintained
 F:	Documentation/networking/netconsole.rst
 F:	drivers/net/netconsole.c
+F:	tools/testing/selftests/drivers/net/netcons_basic.sh
 
 NETDEVSIM
 M:	Jakub Kicinski <kuba@kernel.org>
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index e54f382bcb02..39fb97a8c1df 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -1,8 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
-TEST_INCLUDES := $(wildcard lib/py/*.py)
+TEST_INCLUDES := $(wildcard lib/py/*.py) \
+		 ../../net/net_helper.sh \
+		 ../../net/lib.sh \
 
 TEST_PROGS := \
+	netcons_basic.sh \
 	ping.py \
 	queues.py \
 	stats.py \
diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config
index f6a58ce8a230..a2d8af60876d 100644
--- a/tools/testing/selftests/drivers/net/config
+++ b/tools/testing/selftests/drivers/net/config
@@ -1,2 +1,6 @@
 CONFIG_IPV6=y
 CONFIG_NETDEVSIM=m
+CONFIG_CONFIGFS_FS=y
+CONFIG_NETCONSOLE=m
+CONFIG_NETCONSOLE_DYNAMIC=y
+CONFIG_NETCONSOLE_EXTENDED_LOG=y
diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh
new file mode 100755
index 000000000000..06021b2059b7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_basic.sh
@@ -0,0 +1,234 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test creates two netdevsim virtual interfaces, assigns one of them (the
+# "destination interface") to a new namespace, and assigns IP addresses to both
+# interfaces.
+#
+# It listens on the destination interface using socat and configures a dynamic
+# target on netconsole, pointing to the destination IP address.
+#
+# Finally, it checks whether the message was received properly on the
+# destination interface.  Note that this test may pollute the kernel log buffer
+# (dmesg) and relies on dynamic configuration and namespaces being configured.
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+# Simple script to test dynamic targets in netconsole
+SRCIF="" # to be populated later
+SRCIP=192.168.1.1
+DSTIF="" # to be populated later
+DSTIP=192.168.1.2
+
+PORT="6666"
+MSG="netconsole selftest"
+TARGET=$(mktemp -u netcons_XXXXX)
+DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk)
+NETCONS_CONFIGFS="/sys/kernel/config/netconsole"
+NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}"
+# NAMESPACE will be populated by setup_ns with a random value
+NAMESPACE=""
+
+# IDs for netdevsim
+NSIM_DEV_1_ID=$((256 + RANDOM % 256))
+NSIM_DEV_2_ID=$((512 + RANDOM % 256))
+
+# Used to create and delete namespaces
+source "${SCRIPTDIR}"/../../net/lib.sh
+source "${SCRIPTDIR}"/../../net/net_helper.sh
+
+# Create netdevsim interfaces
+create_ifaces() {
+	local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+
+	echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW"
+	echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW"
+	udevadm settle 2> /dev/null || true
+
+	local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID"
+	local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID"
+
+	# These are global variables
+	SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \
+		-path "$NSIM1"/net -exec basename {} \;)
+	DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \
+		-path "$NSIM2"/net -exec basename {} \;)
+}
+
+link_ifaces() {
+	local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device"
+	local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex)
+	local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex)
+
+	exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}"
+	exec {INITNS_FD}</proc/self/ns/net
+
+	# Bind the dst interface to namespace
+	ip link set "${DSTIF}" netns "${NAMESPACE}"
+
+	# Linking one device to the other one (on the other namespace}
+	if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX"  > $NSIM_DEV_SYS_LINK
+	then
+		echo "linking netdevsim1 with netdevsim2 should succeed"
+		cleanup
+		exit "${ksft_skip}"
+	fi
+}
+
+function configure_ip() {
+	# Configure the IPs for both interfaces
+	ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}"
+	ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up
+
+	ip addr add "${SRCIP}"/24 dev "${SRCIF}"
+	ip link set "${SRCIF}" up
+}
+
+function set_network() {
+	# setup_ns function is coming from lib.sh
+	setup_ns NAMESPACE
+
+	# Create both interfaces, and assign the destination to a different
+	# namespace
+	create_ifaces
+
+	# Link both interfaces back to back
+	link_ifaces
+
+	configure_ip
+}
+
+function create_dynamic_target() {
+	DSTMAC=$(ip netns exec "${NAMESPACE}" \
+		 ip link show "${DSTIF}" | awk '/ether/ {print $2}')
+
+	# Create a dynamic target
+	mkdir "${NETCONS_PATH}"
+
+	echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip
+	echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip
+	echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac
+	echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name
+
+	echo 1 > "${NETCONS_PATH}"/enabled
+}
+
+function cleanup() {
+	local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device"
+
+	# delete netconsole dynamic reconfiguration
+	echo 0 > "${NETCONS_PATH}"/enabled
+	# Remove the configfs entry
+	rmdir "${NETCONS_PATH}"
+
+	# Delete netdevsim devices
+	echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL"
+	echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL"
+
+	# this is coming from lib.sh
+	cleanup_all_ns
+
+	# Restoring printk configurations
+	echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk
+}
+
+function listen_port_and_save_to() {
+	local OUTPUT=${1}
+	# Just wait for 2 seconds
+	timeout 2 ip netns exec "${NAMESPACE}" \
+		socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}"
+}
+
+function validate_result() {
+	local TMPFILENAME="$1"
+
+	# Check if the file exists
+	if [ ! -f "$TMPFILENAME" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "${MSG}" "${TMPFILENAME}"; then
+		echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2
+		cat "${TMPFILENAME}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# Delete the file once it is validated, otherwise keep it
+	# for debugging purposes
+	rm "${TMPFILENAME}"
+	exit "${ksft_pass}"
+}
+
+function check_for_dependencies() {
+	if [ "$(id -u)" -ne 0 ]; then
+		echo "This test must be run as root" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ! which socat > /dev/null ; then
+		echo "SKIP: socat(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ! which ip > /dev/null ; then
+		echo "SKIP: ip(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ! which udevadm > /dev/null ; then
+		echo "SKIP: udevadm(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if [ ! -d "${NETCONS_CONFIGFS}" ]; then
+		echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ip link show "${DSTIF}" 2> /dev/null; then
+		echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then
+		echo "SKIP: IPs already in use. Skipping it" >&2
+		exit "${ksft_skip}"
+	fi
+}
+
+# ========== #
+# Start here #
+# ========== #
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# The content of kmsg will be save to the following file
+OUTPUT_FILE="/tmp/${TARGET}"
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+# Listed for netconsole port inside the namespace and destination interface
+listen_port_and_save_to "${OUTPUT_FILE}" &
+# Wait for socat to start and listen to the port.
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+# Send the message
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+# Wait until socat saves the file to disk
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+
+# Make sure the message was received in the dst part
+# and exit
+validate_result "${OUTPUT_FILE}"
-- 
cgit v1.3-3-g829e


From abcd3026dd63417692a5e80aff70e7cd9b5c14ea Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 22 Aug 2024 14:07:01 +0200
Subject: ethtool: Extend cable testing interface with result source
 information

Extend the ethtool netlink cable testing interface by adding support for
specifying the source of cable testing results. This allows users to
differentiate between results obtained through different diagnostic
methods.

For example, some TI 10BaseT1L PHYs provide two variants of cable
diagnostics: Time Domain Reflectometry (TDR) and Active Link Cable
Diagnostic (ALCD). By introducing `ETHTOOL_A_CABLE_RESULT_SRC` and
`ETHTOOL_A_CABLE_FAULT_LENGTH_SRC` attributes, this update enables
drivers to indicate whether the result was derived from TDR or ALCD,
improving the clarity and utility of diagnostic information.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240822120703.1393130-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml     |  6 ++++++
 Documentation/networking/ethtool-netlink.rst |  5 +++++
 include/uapi/linux/ethtool_netlink.h         | 11 +++++++++++
 3 files changed, 22 insertions(+)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 37211b1e861f..6a050d755b9c 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -667,6 +667,9 @@ attribute-sets:
       -
         name: code
         type: u8
+      -
+        name: src
+        type: u32
   -
     name: cable-fault-length
     attributes:
@@ -676,6 +679,9 @@ attribute-sets:
       -
         name: cm
         type: u32
+      -
+        name: src
+        type: u32
   -
     name: cable-nest
     attributes:
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 44cb9e29f325..ba90457b8b2d 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1314,12 +1314,17 @@ information.
  +-+-+-----------------------------------------+--------+---------------------+
  | | | ``ETHTOOL_A_CABLE_RESULTS_CODE``        | u8     | result code         |
  +-+-+-----------------------------------------+--------+---------------------+
+ | | | ``ETHTOOL_A_CABLE_RESULT_SRC``          | u32    | information source  |
+ +-+-+-----------------------------------------+--------+---------------------+
  | | ``ETHTOOL_A_CABLE_NEST_FAULT_LENGTH``     | nested | cable length        |
  +-+-+-----------------------------------------+--------+---------------------+
  | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR``   | u8     | pair number         |
  +-+-+-----------------------------------------+--------+---------------------+
  | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_CM``     | u32    | length in cm        |
  +-+-+-----------------------------------------+--------+---------------------+
+ | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_SRC``    | u32    | information source  |
+ +-+-+-----------------------------------------+--------+---------------------+
+
 
 CABLE_TEST TDR
 ==============
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 45d8bcdea056..283305f6b063 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -573,10 +573,20 @@ enum {
 	ETHTOOL_A_CABLE_PAIR_D,
 };
 
+/* Information source for specific results. */
+enum {
+	ETHTOOL_A_CABLE_INF_SRC_UNSPEC,
+	/* Results provided by the Time Domain Reflectometry (TDR) */
+	ETHTOOL_A_CABLE_INF_SRC_TDR,
+	/* Results provided by the Active Link Cable Diagnostic (ALCD) */
+	ETHTOOL_A_CABLE_INF_SRC_ALCD,
+};
+
 enum {
 	ETHTOOL_A_CABLE_RESULT_UNSPEC,
 	ETHTOOL_A_CABLE_RESULT_PAIR,		/* u8 ETHTOOL_A_CABLE_PAIR_ */
 	ETHTOOL_A_CABLE_RESULT_CODE,		/* u8 ETHTOOL_A_CABLE_RESULT_CODE_ */
+	ETHTOOL_A_CABLE_RESULT_SRC,		/* u32 ETHTOOL_A_CABLE_INF_SRC_ */
 
 	__ETHTOOL_A_CABLE_RESULT_CNT,
 	ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1)
@@ -586,6 +596,7 @@ enum {
 	ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC,
 	ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR,	/* u8 ETHTOOL_A_CABLE_PAIR_ */
 	ETHTOOL_A_CABLE_FAULT_LENGTH_CM,	/* u32 */
+	ETHTOOL_A_CABLE_FAULT_LENGTH_SRC,	/* u32 ETHTOOL_A_CABLE_INF_SRC_ */
 
 	__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT,
 	ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1)
-- 
cgit v1.3-3-g829e


From 4715d87e11ac805ab95a75adfbf93d67dfbdbe81 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 22 Aug 2024 14:07:02 +0200
Subject: ethtool: Add support for specifying information source in cable test
 results

Enhance the ethtool cable test interface by introducing the ability to
specify the source of the diagnostic information for cable test results.
This is particularly useful for PHYs that offer multiple diagnostic
methods, such as Time Domain Reflectometry (TDR) and Active Link Cable
Diagnostic (ALCD).

Key changes:
- Added `ethnl_cable_test_result_with_src` and
  `ethnl_cable_test_fault_length_with_src` functions to allow specifying
  the information source when reporting cable test results.
- Updated existing `ethnl_cable_test_result` and
  `ethnl_cable_test_fault_length` functions to use TDR as the default
  source, ensuring backward compatibility.
- Modified the UAPI to support these new attributes, enabling drivers to
  provide more detailed diagnostic information.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240822120703.1393130-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool_netlink.h | 29 +++++++++++++++++++++++------
 net/ethtool/cabletest.c         | 19 +++++++++++++++----
 2 files changed, 38 insertions(+), 10 deletions(-)

diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h
index fae0dfb9a9c8..aba91335273a 100644
--- a/include/linux/ethtool_netlink.h
+++ b/include/linux/ethtool_netlink.h
@@ -23,8 +23,10 @@ struct phy_device;
 int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd);
 void ethnl_cable_test_free(struct phy_device *phydev);
 void ethnl_cable_test_finished(struct phy_device *phydev);
-int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result);
-int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm);
+int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair,
+				     u8 result, u32 src);
+int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair,
+					   u32 cm, u32 src);
 int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV);
 int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV);
 int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last,
@@ -54,14 +56,14 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev)
 static inline void ethnl_cable_test_finished(struct phy_device *phydev)
 {
 }
-static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair,
-					  u8 result)
+static inline int ethnl_cable_test_result_with_src(struct phy_device *phydev,
+						   u8 pair, u8 result, u32 src)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int ethnl_cable_test_fault_length(struct phy_device *phydev,
-						u8 pair, u32 cm)
+static inline int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev,
+							 u8 pair, u32 cm, u32 src)
 {
 	return -EOPNOTSUPP;
 }
@@ -119,4 +121,19 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev)
 }
 
 #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */
+
+static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair,
+					  u8 result)
+{
+	return ethnl_cable_test_result_with_src(phydev, pair, result,
+						ETHTOOL_A_CABLE_INF_SRC_TDR);
+}
+
+static inline int ethnl_cable_test_fault_length(struct phy_device *phydev,
+						u8 pair, u32 cm)
+{
+	return ethnl_cable_test_fault_length_with_src(phydev, pair, cm,
+						      ETHTOOL_A_CABLE_INF_SRC_TDR);
+}
+
 #endif /* _LINUX_ETHTOOL_NETLINK_H_ */
diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index 01db8f394869..ff2fe3566ace 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -164,7 +164,8 @@ void ethnl_cable_test_finished(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(ethnl_cable_test_finished);
 
-int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result)
+int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair,
+				     u8 result, u32 src)
 {
 	struct nlattr *nest;
 	int ret = -EMSGSIZE;
@@ -177,6 +178,10 @@ int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result)
 		goto err;
 	if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_CODE, result))
 		goto err;
+	if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) {
+		if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_RESULT_SRC, src))
+			goto err;
+	}
 
 	nla_nest_end(phydev->skb, nest);
 	return 0;
@@ -185,9 +190,10 @@ err:
 	nla_nest_cancel(phydev->skb, nest);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(ethnl_cable_test_result);
+EXPORT_SYMBOL_GPL(ethnl_cable_test_result_with_src);
 
-int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm)
+int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair,
+					   u32 cm, u32 src)
 {
 	struct nlattr *nest;
 	int ret = -EMSGSIZE;
@@ -201,6 +207,11 @@ int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm)
 		goto err;
 	if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_CM, cm))
 		goto err;
+	if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) {
+		if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_SRC,
+				src))
+			goto err;
+	}
 
 	nla_nest_end(phydev->skb, nest);
 	return 0;
@@ -209,7 +220,7 @@ err:
 	nla_nest_cancel(phydev->skb, nest);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length);
+EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length_with_src);
 
 static const struct nla_policy cable_test_tdr_act_cfg_policy[] = {
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]	= { .type = NLA_U32 },
-- 
cgit v1.3-3-g829e


From 986a7fa4b454c9ee338a133868b8ed740cd45edd Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 22 Aug 2024 14:07:03 +0200
Subject: phy: dp83td510: Utilize ALCD for cable length measurement when link
 is active

In industrial environments where 10BaseT1L PHYs are replacing existing
field bus systems like CAN, it's often essential to retain the existing
cable infrastructure. After installation, collecting metrics such as
cable length is crucial for assessing the quality of the infrastructure.
Traditionally, TDR (Time Domain Reflectometry) is used for this purpose.
However, TDR requires interrupting the link, and if the link partner
remains active, the TDR measurement will fail.

Unlike multi-pair systems, where TDR can be attempted during the MDI-X
switching window, 10BaseT1L systems face greater challenges. The TDR
sequence on 10BaseT1L is longer and coincides with uninterrupted
autonegotiation pulses, making TDR impossible when the link partner is
active.

The DP83TD510 PHY provides an alternative through ALCD (Active Link
Cable Diagnostics), which allows for cable length measurement without
disrupting an active link. Since a live link indicates no short or open
cable states, ALCD can be used effectively to gather cable length
information.

Enhance the dp83td510 driver by:
- Leveraging ALCD to measure cable length when the link is active.
- Bypassing TDR when a link is detected, as ALCD provides the required
  information without disruption.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240822120703.1393130-4-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83td510.c | 119 +++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 113 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c
index 551e37786c2d..92aa3a2b9744 100644
--- a/drivers/net/phy/dp83td510.c
+++ b/drivers/net/phy/dp83td510.c
@@ -58,6 +58,10 @@ static const u16 dp83td510_mse_sqi_map[] = {
 	0x0000  /* 24dB =< SNR */
 };
 
+struct dp83td510_priv {
+	bool alcd_test_active;
+};
+
 /* Time Domain Reflectometry (TDR) Functionality of DP83TD510 PHY
  *
  * I assume that this PHY is using a variation of Spread Spectrum Time Domain
@@ -169,6 +173,10 @@ static const u16 dp83td510_mse_sqi_map[] = {
 #define DP83TD510E_UNKN_030E				0x30e
 #define DP83TD510E_030E_VAL				0x2520
 
+#define DP83TD510E_ALCD_STAT				0xa9f
+#define DP83TD510E_ALCD_COMPLETE			BIT(15)
+#define DP83TD510E_ALCD_CABLE_LENGTH			GENMASK(10, 0)
+
 static int dp83td510_config_intr(struct phy_device *phydev)
 {
 	int ret;
@@ -325,8 +333,23 @@ static int dp83td510_get_sqi_max(struct phy_device *phydev)
  */
 static int dp83td510_cable_test_start(struct phy_device *phydev)
 {
+	struct dp83td510_priv *priv = phydev->priv;
 	int ret;
 
+	/* If link partner is active, we won't be able to use TDR, since
+	 * we can't force link partner to be silent. The autonegotiation
+	 * pulses will be too frequent and the TDR sequence will be
+	 * too long. So, TDR will always fail. Since the link is established
+	 * we already know that the cable is working, so we can get some
+	 * extra information line the cable length using ALCD.
+	 */
+	if (phydev->link) {
+		priv->alcd_test_active = true;
+		return 0;
+	}
+
+	priv->alcd_test_active = false;
+
 	ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_CTRL,
 			       DP83TD510E_CTRL_HW_RESET);
 	if (ret)
@@ -402,8 +425,8 @@ static int dp83td510_cable_test_start(struct phy_device *phydev)
 }
 
 /**
- * dp83td510_cable_test_get_status - Get the status of the cable test for the
- *                                   DP83TD510 PHY.
+ * dp83td510_cable_test_get_tdr_status - Get the status of the TDR test for the
+ *                                       DP83TD510 PHY.
  * @phydev: Pointer to the phy_device structure.
  * @finished: Pointer to a boolean that indicates whether the test is finished.
  *
@@ -411,13 +434,11 @@ static int dp83td510_cable_test_start(struct phy_device *phydev)
  *
  * Returns: 0 on success or a negative error code on failure.
  */
-static int dp83td510_cable_test_get_status(struct phy_device *phydev,
-					   bool *finished)
+static int dp83td510_cable_test_get_tdr_status(struct phy_device *phydev,
+					       bool *finished)
 {
 	int ret, stat;
 
-	*finished = false;
-
 	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_TDR_CFG);
 	if (ret < 0)
 		return ret;
@@ -459,6 +480,77 @@ static int dp83td510_cable_test_get_status(struct phy_device *phydev,
 	return phy_init_hw(phydev);
 }
 
+/**
+ * dp83td510_cable_test_get_alcd_status - Get the status of the ALCD test for the
+ *                                        DP83TD510 PHY.
+ * @phydev: Pointer to the phy_device structure.
+ * @finished: Pointer to a boolean that indicates whether the test is finished.
+ *
+ * The function sets the @finished flag to true if the test is complete.
+ * The function reads the cable length and reports it to the user.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static int dp83td510_cable_test_get_alcd_status(struct phy_device *phydev,
+						bool *finished)
+{
+	unsigned int location;
+	int ret, phy_sts;
+
+	phy_sts = phy_read(phydev, DP83TD510E_PHY_STS);
+
+	if (!(phy_sts & DP83TD510E_LINK_STATUS)) {
+		/* If the link is down, we can't do any thing usable now */
+		ethnl_cable_test_result_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A,
+						 ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC,
+						 ETHTOOL_A_CABLE_INF_SRC_ALCD);
+		*finished = true;
+		return 0;
+	}
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_ALCD_STAT);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & DP83TD510E_ALCD_COMPLETE))
+		return 0;
+
+	location = FIELD_GET(DP83TD510E_ALCD_CABLE_LENGTH, ret) * 100;
+
+	ethnl_cable_test_fault_length_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A,
+					       location,
+					       ETHTOOL_A_CABLE_INF_SRC_ALCD);
+
+	ethnl_cable_test_result_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A,
+					 ETHTOOL_A_CABLE_RESULT_CODE_OK,
+					 ETHTOOL_A_CABLE_INF_SRC_ALCD);
+	*finished = true;
+
+	return 0;
+}
+
+/**
+ * dp83td510_cable_test_get_status - Get the status of the cable test for the
+ *                                   DP83TD510 PHY.
+ * @phydev: Pointer to the phy_device structure.
+ * @finished: Pointer to a boolean that indicates whether the test is finished.
+ *
+ * The function sets the @finished flag to true if the test is complete.
+ *
+ * Returns: 0 on success or a negative error code on failure.
+ */
+static int dp83td510_cable_test_get_status(struct phy_device *phydev,
+					   bool *finished)
+{
+	struct dp83td510_priv *priv = phydev->priv;
+	*finished = false;
+
+	if (priv->alcd_test_active)
+		return dp83td510_cable_test_get_alcd_status(phydev, finished);
+
+	return dp83td510_cable_test_get_tdr_status(phydev, finished);
+}
+
 static int dp83td510_get_features(struct phy_device *phydev)
 {
 	/* This PHY can't respond on MDIO bus if no RMII clock is enabled.
@@ -477,12 +569,27 @@ static int dp83td510_get_features(struct phy_device *phydev)
 	return 0;
 }
 
+static int dp83td510_probe(struct phy_device *phydev)
+{
+	struct device *dev = &phydev->mdio.dev;
+	struct dp83td510_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	phydev->priv = priv;
+
+	return 0;
+}
+
 static struct phy_driver dp83td510_driver[] = {
 {
 	PHY_ID_MATCH_MODEL(DP83TD510E_PHY_ID),
 	.name		= "TI DP83TD510E",
 
 	.flags          = PHY_POLL_CABLE_TEST,
+	.probe		= dp83td510_probe,
 	.config_aneg	= dp83td510_config_aneg,
 	.read_status	= dp83td510_read_status,
 	.get_features	= dp83td510_get_features,
-- 
cgit v1.3-3-g829e


From 5f6df173f92eff2d6fa09d74e47e204b0072f82e Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 6 Aug 2024 13:46:21 -0700
Subject: ice: implement and use rd32_poll_timeout for ice_sq_done timeout

The ice_sq_done function is used to check the control queue head register
and determine whether or not the control queue processing is done. This
function is called in a loop checking against jiffies for a specified
timeout.

The pattern of reading a register in a loop until a condition is true or a
timeout is reached is a relatively common pattern. In fact, the kernel
provides a read_poll_timeout function implementing this behavior in
<linux/iopoll.h>

Use of read_poll_timeout is preferred over directly coding these loops.
However, using it in the ice driver is a bit more difficult because of the
rd32 wrapper. Implement a rd32_poll_timeout wrapper based on
read_poll_timeout.

Refactor ice_sq_done to use rd32_poll_timeout, replacing the loop calling
ice_sq_done in ice_sq_send_cmd. This simplifies the logic down to a single
ice_sq_done() call.

The implementation of rd32_poll_timeout uses microseconds for its timeout
value, so update the CQ timeout macros used to be specified in microseconds
units as well instead of using HZ for jiffies.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 38 +++++++++++++--------------
 drivers/net/ethernet/intel/ice/ice_controlq.h |  2 +-
 drivers/net/ethernet/intel/ice/ice_osdep.h    |  4 +++
 3 files changed, 23 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index ffaa6511c455..1b1b68a99bb2 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -933,19 +933,29 @@ static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len)
 }
 
 /**
- * ice_sq_done - check if FW has processed the Admin Send Queue (ATQ)
+ * ice_sq_done - poll until the last send on a control queue has completed
  * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
  *
- * Returns true if the firmware has processed all descriptors on the
- * admin send queue. Returns false if there are still requests pending.
+ * Use read_poll_timeout to poll the control queue head, checking until it
+ * matches next_to_use. According to the control queue designers, this has
+ * better timing reliability than the DD bit.
+ *
+ * Return: true if all the descriptors on the send side of a control queue
+ *         are finished processing, false otherwise.
  */
 static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	/* AQ designers suggest use of head for better
-	 * timing reliability than DD bit
+	u32 head;
+
+	/* Wait a short time before the initial check, to allow hardware time
+	 * for completion.
 	 */
-	return rd32(hw, cq->sq.head) == cq->sq.next_to_use;
+	udelay(5);
+
+	return !rd32_poll_timeout(hw, cq->sq.head,
+				  head, head == cq->sq.next_to_use,
+				  20, ICE_CTL_Q_SQ_CMD_TIMEOUT);
 }
 
 /**
@@ -969,7 +979,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	struct ice_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	struct ice_sq_cd *details;
-	unsigned long timeout;
 	int status = 0;
 	u16 retval = 0;
 	u32 val = 0;
@@ -1063,20 +1072,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	wr32(hw, cq->sq.tail, cq->sq.next_to_use);
 	ice_flush(hw);
 
-	/* Wait a short time before initial ice_sq_done() check, to allow
-	 * hardware time for completion.
+	/* Wait for the command to complete. If it finishes within the
+	 * timeout, copy the descriptor back to temp.
 	 */
-	udelay(5);
-
-	timeout = jiffies + ICE_CTL_Q_SQ_CMD_TIMEOUT;
-	do {
-		if (ice_sq_done(hw, cq))
-			break;
-
-		usleep_range(100, 150);
-	} while (time_before(jiffies, timeout));
-
-	/* if ready, copy the desc back to temp */
 	if (ice_sq_done(hw, cq)) {
 		memcpy(desc, desc_on_ring, sizeof(*desc));
 		if (buf) {
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index 1d54b1cdb1c5..e5b6691436f5 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -43,7 +43,7 @@ enum ice_ctl_q {
 };
 
 /* Control Queue timeout settings - max delay 1s */
-#define ICE_CTL_Q_SQ_CMD_TIMEOUT	HZ    /* Wait max 1s */
+#define ICE_CTL_Q_SQ_CMD_TIMEOUT	USEC_PER_SEC
 #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT	10    /* Count 10 times */
 #define ICE_CTL_Q_ADMIN_INIT_MSEC	100   /* Check every 100msec */
 
diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h
index a2562f04267f..9882e6f3b26d 100644
--- a/drivers/net/ethernet/intel/ice/ice_osdep.h
+++ b/drivers/net/ethernet/intel/ice/ice_osdep.h
@@ -12,6 +12,7 @@
 #include <linux/ethtool.h>
 #include <linux/etherdevice.h>
 #include <linux/if_ether.h>
+#include <linux/iopoll.h>
 #include <linux/pci_ids.h>
 #ifndef CONFIG_64BIT
 #include <linux/io-64-nonatomic-lo-hi.h>
@@ -23,6 +24,9 @@
 #define wr64(a, reg, value)	writeq((value), ((a)->hw_addr + (reg)))
 #define rd64(a, reg)		readq((a)->hw_addr + (reg))
 
+#define rd32_poll_timeout(a, addr, val, cond, delay_us, timeout_us) \
+	read_poll_timeout(rd32, val, cond, delay_us, timeout_us, false, a, addr)
+
 #define ice_flush(a)		rd32((a), GLGEN_STAT)
 #define ICE_M(m, s)		((m ## U) << (s))
 
-- 
cgit v1.3-3-g829e


From be91edc81b09ca062e39db894561d25447235c68 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 22 Aug 2024 17:56:51 +0530
Subject: dt-bindings: soc: ti: pruss: Add documentation for PA_STATS support

Add documentation for pa-stats node which is syscon regmap for
PA_STATS registers. This will be used to dump statistics maintained by
ICSSG firmware.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Acked-by: Nishanth Menon <nm@ti.com>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20240822122652.1071801-2-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/soc/ti/ti,pruss.yaml         | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml
index c402cb2928e8..3cb1471cc6b6 100644
--- a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml
+++ b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml
@@ -278,6 +278,26 @@ patternProperties:
 
     additionalProperties: false
 
+  ^pa-stats@[a-f0-9]+$:
+    description: |
+      PA-STATS sub-module represented as a SysCon. PA_STATS is a set of
+      registers where different statistics related to ICSSG, are dumped by
+      ICSSG firmware. This syscon sub-module will help the device to
+      access/read/write those statistics.
+
+    type: object
+
+    additionalProperties: false
+
+    properties:
+      compatible:
+        items:
+          - const: ti,pruss-pa-st
+          - const: syscon
+
+      reg:
+        maxItems: 1
+
   interrupt-controller@[a-f0-9]+$:
     description: |
       PRUSS INTC Node. Each PRUSS has a single interrupt controller instance
-- 
cgit v1.3-3-g829e


From 550ee90ac61c1f0cd987c68a9ac6c4c9833925d7 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Thu, 22 Aug 2024 17:56:52 +0530
Subject: net: ti: icssg-prueth: Add support for PA Stats

Add support for dumping PA stats registers via ethtool.
Firmware maintained stats are stored at PA Stats registers.
Also modify emac_get_strings() API to use ethtool_puts().

This commit also maintains consistency between miig_stats and pa_stats by
- renaming the array icssg_all_stats to icssg_all_miig_stats
- renaming the structure icssg_stats to icssg_miig_stats
- renaming ICSSG_STATS() to ICSSG_MIIG_STATS()
- changing order of stats related data structures and arrays so that data
  structures of a certain stats type is clubbed together.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20240822122652.1071801-3-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_ethtool.c |  19 ++--
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  |   6 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |   9 +-
 drivers/net/ethernet/ti/icssg/icssg_stats.c   |  31 +++--
 drivers/net/ethernet/ti/icssg/icssg_stats.h   | 158 ++++++++++++++++----------
 5 files changed, 140 insertions(+), 83 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
index 5688f054cec5..5073ec195854 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -83,13 +83,11 @@ static void emac_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) {
-			if (!icssg_all_stats[i].standard_stats) {
-				memcpy(p, icssg_all_stats[i].name,
-				       ETH_GSTRING_LEN);
-				p += ETH_GSTRING_LEN;
-			}
-		}
+		for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++)
+			if (!icssg_all_miig_stats[i].standard_stats)
+				ethtool_puts(&p, icssg_all_miig_stats[i].name);
+		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++)
+			ethtool_puts(&p, icssg_all_pa_stats[i].name);
 		break;
 	default:
 		break;
@@ -104,9 +102,12 @@ static void emac_get_ethtool_stats(struct net_device *ndev,
 
 	emac_update_hardware_stats(emac);
 
-	for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++)
-		if (!icssg_all_stats[i].standard_stats)
+	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++)
+		if (!icssg_all_miig_stats[i].standard_stats)
 			*(data++) = emac->stats[i];
+
+	for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++)
+		*(data++) = emac->pa_stats[i];
 }
 
 static int emac_get_ts_info(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 53a3e44b99a2..f623a0f603fc 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1182,6 +1182,12 @@ static int prueth_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	prueth->pa_stats = syscon_regmap_lookup_by_phandle(np, "ti,pa-stats");
+	if (IS_ERR(prueth->pa_stats)) {
+		dev_err(dev, "couldn't get ti,pa-stats syscon regmap\n");
+		return -ENODEV;
+	}
+
 	if (eth0_node) {
 		ret = prueth_get_cores(prueth, ICSS_SLICE0, false);
 		if (ret)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index f678d656a3ed..786bd1ba34ab 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -50,8 +50,10 @@
 
 #define ICSSG_MAX_RFLOWS	8	/* per slice */
 
+#define ICSSG_NUM_PA_STATS	4
+#define ICSSG_NUM_MIIG_STATS	60
 /* Number of ICSSG related stats */
-#define ICSSG_NUM_STATS 60
+#define ICSSG_NUM_STATS (ICSSG_NUM_MIIG_STATS + ICSSG_NUM_PA_STATS)
 #define ICSSG_NUM_STANDARD_STATS 31
 #define ICSSG_NUM_ETHTOOL_STATS (ICSSG_NUM_STATS - ICSSG_NUM_STANDARD_STATS)
 
@@ -190,7 +192,8 @@ struct prueth_emac {
 	int port_vlan;
 
 	struct delayed_work stats_work;
-	u64 stats[ICSSG_NUM_STATS];
+	u64 stats[ICSSG_NUM_MIIG_STATS];
+	u64 pa_stats[ICSSG_NUM_PA_STATS];
 
 	/* RX IRQ Coalescing Related */
 	struct hrtimer rx_hrtimer;
@@ -230,6 +233,7 @@ struct icssg_firmwares {
  * @registered_netdevs: list of registered netdevs
  * @miig_rt: regmap to mii_g_rt block
  * @mii_rt: regmap to mii_rt block
+ * @pa_stats: regmap to pa_stats block
  * @pru_id: ID for each of the PRUs
  * @pdev: pointer to ICSSG platform device
  * @pdata: pointer to platform data for ICSSG driver
@@ -263,6 +267,7 @@ struct prueth {
 	struct net_device *registered_netdevs[PRUETH_NUM_MACS];
 	struct regmap *miig_rt;
 	struct regmap *mii_rt;
+	struct regmap *pa_stats;
 
 	enum pruss_pru_id pru_id[PRUSS_NUM_PRUS];
 	struct platform_device *pdev;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 2fb150c13078..06a15c0b2acc 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -11,6 +11,7 @@
 
 #define ICSSG_TX_PACKET_OFFSET	0xA0
 #define ICSSG_TX_BYTE_OFFSET	0xEC
+#define ICSSG_FW_STATS_BASE	0x0248
 
 static u32 stats_base[] = {	0x54c,	/* Slice 0 stats start */
 				0xb18,	/* Slice 1 stats start */
@@ -22,24 +23,31 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 	int slice = prueth_emac_slice(emac);
 	u32 base = stats_base[slice];
 	u32 tx_pkt_cnt = 0;
-	u32 val;
+	u32 val, reg;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) {
+	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
 		regmap_read(prueth->miig_rt,
-			    base + icssg_all_stats[i].offset,
+			    base + icssg_all_miig_stats[i].offset,
 			    &val);
 		regmap_write(prueth->miig_rt,
-			     base + icssg_all_stats[i].offset,
+			     base + icssg_all_miig_stats[i].offset,
 			     val);
 
-		if (icssg_all_stats[i].offset == ICSSG_TX_PACKET_OFFSET)
+		if (icssg_all_miig_stats[i].offset == ICSSG_TX_PACKET_OFFSET)
 			tx_pkt_cnt = val;
 
 		emac->stats[i] += val;
-		if (icssg_all_stats[i].offset == ICSSG_TX_BYTE_OFFSET)
+		if (icssg_all_miig_stats[i].offset == ICSSG_TX_BYTE_OFFSET)
 			emac->stats[i] -= tx_pkt_cnt * 8;
 	}
+
+	for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
+		reg = ICSSG_FW_STATS_BASE + icssg_all_pa_stats[i].offset *
+		      PRUETH_NUM_MACS + slice * sizeof(u32);
+		regmap_read(prueth->pa_stats, reg, &val);
+		emac->pa_stats[i] += val;
+	}
 }
 
 void icssg_stats_work_handler(struct work_struct *work)
@@ -57,9 +65,14 @@ int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) {
-		if (!strcmp(icssg_all_stats[i].name, stat_name))
-			return emac->stats[icssg_all_stats[i].offset / sizeof(u32)];
+	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
+		if (!strcmp(icssg_all_miig_stats[i].name, stat_name))
+			return emac->stats[icssg_all_miig_stats[i].offset / sizeof(u32)];
+	}
+
+	for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
+		if (!strcmp(icssg_all_pa_stats[i].name, stat_name))
+			return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)];
 	}
 
 	netdev_err(emac->ndev, "Invalid stats %s\n", stat_name);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.h b/drivers/net/ethernet/ti/icssg/icssg_stats.h
index 999a4a91276c..e88b919f532c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.h
@@ -77,82 +77,114 @@ struct miig_stats_regs {
 	u32 tx_bytes;
 };
 
-#define ICSSG_STATS(field, stats_type)			\
+#define ICSSG_MIIG_STATS(field, stats_type)			\
 {							\
 	#field,						\
 	offsetof(struct miig_stats_regs, field),	\
 	stats_type					\
 }
 
-struct icssg_stats {
+struct icssg_miig_stats {
 	char name[ETH_GSTRING_LEN];
 	u32 offset;
 	bool standard_stats;
 };
 
-static const struct icssg_stats icssg_all_stats[] = {
+static const struct icssg_miig_stats icssg_all_miig_stats[] = {
 	/* Rx */
-	ICSSG_STATS(rx_packets, true),
-	ICSSG_STATS(rx_broadcast_frames, false),
-	ICSSG_STATS(rx_multicast_frames, true),
-	ICSSG_STATS(rx_crc_errors, true),
-	ICSSG_STATS(rx_mii_error_frames, false),
-	ICSSG_STATS(rx_odd_nibble_frames, false),
-	ICSSG_STATS(rx_frame_max_size, true),
-	ICSSG_STATS(rx_max_size_error_frames, false),
-	ICSSG_STATS(rx_frame_min_size, true),
-	ICSSG_STATS(rx_min_size_error_frames, false),
-	ICSSG_STATS(rx_over_errors, true),
-	ICSSG_STATS(rx_class0_hits, false),
-	ICSSG_STATS(rx_class1_hits, false),
-	ICSSG_STATS(rx_class2_hits, false),
-	ICSSG_STATS(rx_class3_hits, false),
-	ICSSG_STATS(rx_class4_hits, false),
-	ICSSG_STATS(rx_class5_hits, false),
-	ICSSG_STATS(rx_class6_hits, false),
-	ICSSG_STATS(rx_class7_hits, false),
-	ICSSG_STATS(rx_class8_hits, false),
-	ICSSG_STATS(rx_class9_hits, false),
-	ICSSG_STATS(rx_class10_hits, false),
-	ICSSG_STATS(rx_class11_hits, false),
-	ICSSG_STATS(rx_class12_hits, false),
-	ICSSG_STATS(rx_class13_hits, false),
-	ICSSG_STATS(rx_class14_hits, false),
-	ICSSG_STATS(rx_class15_hits, false),
-	ICSSG_STATS(rx_smd_frags, false),
-	ICSSG_STATS(rx_bucket1_size, true),
-	ICSSG_STATS(rx_bucket2_size, true),
-	ICSSG_STATS(rx_bucket3_size, true),
-	ICSSG_STATS(rx_bucket4_size, true),
-	ICSSG_STATS(rx_64B_frames, true),
-	ICSSG_STATS(rx_bucket1_frames, true),
-	ICSSG_STATS(rx_bucket2_frames, true),
-	ICSSG_STATS(rx_bucket3_frames, true),
-	ICSSG_STATS(rx_bucket4_frames, true),
-	ICSSG_STATS(rx_bucket5_frames, true),
-	ICSSG_STATS(rx_bytes, true),
-	ICSSG_STATS(rx_tx_total_bytes, false),
+	ICSSG_MIIG_STATS(rx_packets, true),
+	ICSSG_MIIG_STATS(rx_broadcast_frames, false),
+	ICSSG_MIIG_STATS(rx_multicast_frames, true),
+	ICSSG_MIIG_STATS(rx_crc_errors, true),
+	ICSSG_MIIG_STATS(rx_mii_error_frames, false),
+	ICSSG_MIIG_STATS(rx_odd_nibble_frames, false),
+	ICSSG_MIIG_STATS(rx_frame_max_size, true),
+	ICSSG_MIIG_STATS(rx_max_size_error_frames, false),
+	ICSSG_MIIG_STATS(rx_frame_min_size, true),
+	ICSSG_MIIG_STATS(rx_min_size_error_frames, false),
+	ICSSG_MIIG_STATS(rx_over_errors, true),
+	ICSSG_MIIG_STATS(rx_class0_hits, false),
+	ICSSG_MIIG_STATS(rx_class1_hits, false),
+	ICSSG_MIIG_STATS(rx_class2_hits, false),
+	ICSSG_MIIG_STATS(rx_class3_hits, false),
+	ICSSG_MIIG_STATS(rx_class4_hits, false),
+	ICSSG_MIIG_STATS(rx_class5_hits, false),
+	ICSSG_MIIG_STATS(rx_class6_hits, false),
+	ICSSG_MIIG_STATS(rx_class7_hits, false),
+	ICSSG_MIIG_STATS(rx_class8_hits, false),
+	ICSSG_MIIG_STATS(rx_class9_hits, false),
+	ICSSG_MIIG_STATS(rx_class10_hits, false),
+	ICSSG_MIIG_STATS(rx_class11_hits, false),
+	ICSSG_MIIG_STATS(rx_class12_hits, false),
+	ICSSG_MIIG_STATS(rx_class13_hits, false),
+	ICSSG_MIIG_STATS(rx_class14_hits, false),
+	ICSSG_MIIG_STATS(rx_class15_hits, false),
+	ICSSG_MIIG_STATS(rx_smd_frags, false),
+	ICSSG_MIIG_STATS(rx_bucket1_size, true),
+	ICSSG_MIIG_STATS(rx_bucket2_size, true),
+	ICSSG_MIIG_STATS(rx_bucket3_size, true),
+	ICSSG_MIIG_STATS(rx_bucket4_size, true),
+	ICSSG_MIIG_STATS(rx_64B_frames, true),
+	ICSSG_MIIG_STATS(rx_bucket1_frames, true),
+	ICSSG_MIIG_STATS(rx_bucket2_frames, true),
+	ICSSG_MIIG_STATS(rx_bucket3_frames, true),
+	ICSSG_MIIG_STATS(rx_bucket4_frames, true),
+	ICSSG_MIIG_STATS(rx_bucket5_frames, true),
+	ICSSG_MIIG_STATS(rx_bytes, true),
+	ICSSG_MIIG_STATS(rx_tx_total_bytes, false),
 	/* Tx */
-	ICSSG_STATS(tx_packets, true),
-	ICSSG_STATS(tx_broadcast_frames, false),
-	ICSSG_STATS(tx_multicast_frames, false),
-	ICSSG_STATS(tx_odd_nibble_frames, false),
-	ICSSG_STATS(tx_underflow_errors, false),
-	ICSSG_STATS(tx_frame_max_size, true),
-	ICSSG_STATS(tx_max_size_error_frames, false),
-	ICSSG_STATS(tx_frame_min_size, true),
-	ICSSG_STATS(tx_min_size_error_frames, false),
-	ICSSG_STATS(tx_bucket1_size, true),
-	ICSSG_STATS(tx_bucket2_size, true),
-	ICSSG_STATS(tx_bucket3_size, true),
-	ICSSG_STATS(tx_bucket4_size, true),
-	ICSSG_STATS(tx_64B_frames, true),
-	ICSSG_STATS(tx_bucket1_frames, true),
-	ICSSG_STATS(tx_bucket2_frames, true),
-	ICSSG_STATS(tx_bucket3_frames, true),
-	ICSSG_STATS(tx_bucket4_frames, true),
-	ICSSG_STATS(tx_bucket5_frames, true),
-	ICSSG_STATS(tx_bytes, true),
+	ICSSG_MIIG_STATS(tx_packets, true),
+	ICSSG_MIIG_STATS(tx_broadcast_frames, false),
+	ICSSG_MIIG_STATS(tx_multicast_frames, false),
+	ICSSG_MIIG_STATS(tx_odd_nibble_frames, false),
+	ICSSG_MIIG_STATS(tx_underflow_errors, false),
+	ICSSG_MIIG_STATS(tx_frame_max_size, true),
+	ICSSG_MIIG_STATS(tx_max_size_error_frames, false),
+	ICSSG_MIIG_STATS(tx_frame_min_size, true),
+	ICSSG_MIIG_STATS(tx_min_size_error_frames, false),
+	ICSSG_MIIG_STATS(tx_bucket1_size, true),
+	ICSSG_MIIG_STATS(tx_bucket2_size, true),
+	ICSSG_MIIG_STATS(tx_bucket3_size, true),
+	ICSSG_MIIG_STATS(tx_bucket4_size, true),
+	ICSSG_MIIG_STATS(tx_64B_frames, true),
+	ICSSG_MIIG_STATS(tx_bucket1_frames, true),
+	ICSSG_MIIG_STATS(tx_bucket2_frames, true),
+	ICSSG_MIIG_STATS(tx_bucket3_frames, true),
+	ICSSG_MIIG_STATS(tx_bucket4_frames, true),
+	ICSSG_MIIG_STATS(tx_bucket5_frames, true),
+	ICSSG_MIIG_STATS(tx_bytes, true),
+};
+
+/**
+ * struct pa_stats_regs - ICSSG Firmware maintained PA Stats register
+ * @fw_rx_cnt: Number of valid packets sent by Rx PRU to Host on PSI
+ * @fw_tx_cnt: Number of valid packets copied by RTU0 to Tx queues
+ * @fw_tx_pre_overflow: Host Egress Q (Pre-emptible) Overflow Counter
+ * @fw_tx_exp_overflow: Host Egress Q (Express) Overflow Counter
+ */
+struct pa_stats_regs {
+	u32 fw_rx_cnt;
+	u32 fw_tx_cnt;
+	u32 fw_tx_pre_overflow;
+	u32 fw_tx_exp_overflow;
+};
+
+#define ICSSG_PA_STATS(field)			\
+{						\
+	#field,					\
+	offsetof(struct pa_stats_regs, field),	\
+}
+
+struct icssg_pa_stats {
+	char name[ETH_GSTRING_LEN];
+	u32 offset;
+};
+
+static const struct icssg_pa_stats icssg_all_pa_stats[] = {
+	ICSSG_PA_STATS(fw_rx_cnt),
+	ICSSG_PA_STATS(fw_tx_cnt),
+	ICSSG_PA_STATS(fw_tx_pre_overflow),
+	ICSSG_PA_STATS(fw_tx_exp_overflow),
 };
 
 #endif /* __NET_TI_ICSSG_STATS_H */
-- 
cgit v1.3-3-g829e


From d24dac8eb8111c401b0de40a17760a0a254bcffc Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:22 +0100
Subject: packet: Correct spelling in if_packet.h

Correct spelling in if_packet.h
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Acked-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240822-net-spell-v1-1-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/if_packet.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h
index 9efc42382fdb..1d2718dd9647 100644
--- a/include/uapi/linux/if_packet.h
+++ b/include/uapi/linux/if_packet.h
@@ -230,8 +230,8 @@ struct tpacket_hdr_v1 {
 	 * ts_first_pkt:
 	 *		Is always the time-stamp when the block was opened.
 	 *		Case a)	ZERO packets
-	 *			No packets to deal with but atleast you know the
-	 *			time-interval of this block.
+	 *			No packets to deal with but at least you know
+	 *			the time-interval of this block.
 	 *		Case b) Non-zero packets
 	 *			Use the ts of the first packet in the block.
 	 *
@@ -265,7 +265,8 @@ enum tpacket_versions {
    - struct tpacket_hdr
    - pad to TPACKET_ALIGNMENT=16
    - struct sockaddr_ll
-   - Gap, chosen so that packet data (Start+tp_net) alignes to TPACKET_ALIGNMENT=16
+   - Gap, chosen so that packet data (Start+tp_net) aligns to
+     TPACKET_ALIGNMENT=16
    - Start+tp_mac: [ Optional MAC header ]
    - Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16.
    - Pad to align to TPACKET_ALIGNMENT=16
-- 
cgit v1.3-3-g829e


From c3494460324832ba03ab8f640a0a5e52283b1b15 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:23 +0100
Subject: s390/iucv: Correct spelling in iucv.h

Correct spelling in iucv.h
As reported by codespell.

Cc: Alexandra Winter <wintera@linux.ibm.com>
Cc: Thorsten Winkler <twinkler@linux.ibm.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-2-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/iucv/iucv.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h
index 4d114e6d6d23..dd9e93c12260 100644
--- a/include/net/iucv/iucv.h
+++ b/include/net/iucv/iucv.h
@@ -15,7 +15,7 @@
  * To explore any of the IUCV functions, one must first register their
  * program using iucv_register(). Once your program has successfully
  * completed a register, it can exploit the other functions.
- * For furthur reference on all IUCV functionality, refer to the
+ * For further reference on all IUCV functionality, refer to the
  * CP Programming Services book, also available on the web thru
  * www.vm.ibm.com/pubs, manual # SC24-6084
  *
-- 
cgit v1.3-3-g829e


From d0193b167f2756de2f8be4d44186294bfacaaafc Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:24 +0100
Subject: ip_tunnel: Correct spelling in ip_tunnels.h

Correct spelling in ip_tunnels.h
As reported by codespell.

Cc: David Ahern <dsahern@kernel.org>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-3-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_tunnels.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 1db2417b8ff5..6194fbb564c6 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -573,7 +573,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
 		return 0;
 }
 
-/* Propogate ECN bits out */
+/* Propagate ECN bits out */
 static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 				     const struct sk_buff *skb)
 {
-- 
cgit v1.3-3-g829e


From 507285b7f9b2bc90f093fa335d43f2a21a2dbef9 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:25 +0100
Subject: ipv6: Correct spelling in ipv6.h

Correct spelling in ip_tunnels.h
As reported by codespell.

Cc: David Ahern <dsahern@kernel.org>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-4-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ipv6.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index e7113855a10f..248bfb26e2af 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -851,7 +851,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int
 	 *	we should *never* get to this point since that
 	 *	would mean the addrs are equal
 	 *
-	 *	However, we do get to it 8) And exacly, when
+	 *	However, we do get to it 8) And exactly, when
 	 *	addresses are equal 8)
 	 *
 	 *	ip route add 1111::/128 via ...
@@ -973,7 +973,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 	hash = skb_get_hash_flowi6(skb, fl6);
 
 	/* Since this is being sent on the wire obfuscate hash a bit
-	 * to minimize possbility that any useful information to an
+	 * to minimize possibility that any useful information to an
 	 * attacker is leaked. Only lower 20 bits are relevant.
 	 */
 	hash = rol32(hash, 16);
-- 
cgit v1.3-3-g829e


From e8ac2dba93eafb928fd9e127cdade3b2216a642c Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:26 +0100
Subject: bonding: Correct spelling in headers

Correct spelling in bond_3ad.h and bond_alb.h.
As reported by codespell.

Cc: Jay Vosburgh <jv@jvosburgh.net>
Cc: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-5-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/bond_3ad.h | 5 ++++-
 include/net/bond_alb.h | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index 9ce5ac2bfbad..2053cd8e788a 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -231,7 +231,10 @@ typedef struct port {
 	mux_states_t sm_mux_state;	/* state machine mux state */
 	u16 sm_mux_timer_counter;	/* state machine mux timer counter */
 	tx_states_t sm_tx_state;	/* state machine tx state */
-	u16 sm_tx_timer_counter;	/* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */
+	u16 sm_tx_timer_counter;	/* state machine tx timer counter
+					 * (always on - enter to transmit
+					 *  state 3 time per second)
+					 */
 	u16 sm_churn_actor_timer_counter;
 	u16 sm_churn_partner_timer_counter;
 	u32 churn_actor_count;
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index 9dc082b2d543..e5945427f38d 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -53,7 +53,7 @@ struct slave;
 
 
 struct tlb_client_info {
-	struct slave *tx_slave;	/* A pointer to slave used for transmiting
+	struct slave *tx_slave;	/* A pointer to slave used for transmitting
 				 * packets to a Client that the Hash function
 				 * gave this entry index.
 				 */
-- 
cgit v1.3-3-g829e


From 19f1f11c9a8e92a2211a3854bd2cfbd4bb6303f1 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:27 +0100
Subject: net: qualcomm: rmnet: Correct spelling in if_rmnet.h

Correct spelling in if_rmnet.h
As reported by codespell.

Cc: Sean Tranchetti <quic_stranche@quicinc.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com>
Link: https://patch.msgid.link/20240822-net-spell-v1-6-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/if_rmnet.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h
index 839d1e48b85e..c44bf6e80ecb 100644
--- a/include/linux/if_rmnet.h
+++ b/include/linux/if_rmnet.h
@@ -42,7 +42,7 @@ struct rmnet_map_ul_csum_header {
 
 /* csum_info field:
  *  OFFSET:	where (offset in bytes) to insert computed checksum
- *  UDP:	1 = UDP checksum (zero checkum means no checksum)
+ *  UDP:	1 = UDP checksum (zero checksum means no checksum)
  *  ENABLED:	1 = checksum computation requested
  */
 #define MAP_CSUM_UL_OFFSET_MASK		GENMASK(13, 0)
-- 
cgit v1.3-3-g829e


From 6899c2549cf7ca554ee2dd8574f0b70945f3ed1b Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:28 +0100
Subject: netlabel: Correct spelling in netlabel.h

Correct spelling in netlabel.h.
As reported by codespell.

Cc: Paul Moore <paul@paul-moore.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-7-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netlabel.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/netlabel.h b/include/net/netlabel.h
index 654bc777d2a7..529160f76cac 100644
--- a/include/net/netlabel.h
+++ b/include/net/netlabel.h
@@ -30,7 +30,7 @@ struct calipso_doi;
 
 /*
  * NetLabel - A management interface for maintaining network packet label
- *            mapping tables for explicit packet labling protocols.
+ *            mapping tables for explicit packet labeling protocols.
  *
  * Network protocols such as CIPSO and RIPSO require a label translation layer
  * to convert the label on the packet into something meaningful on the host
-- 
cgit v1.3-3-g829e


From 10d0749a38c3a02f308fe8c4f4ed29bd6412e5fb Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:29 +0100
Subject: NFC: Correct spelling in headers

Correct spelling in NFC headers.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-8-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/nfc/nci.h | 2 +-
 include/net/nfc/nfc.h | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h
index e82f55f543bb..dc36519d16aa 100644
--- a/include/net/nfc/nci.h
+++ b/include/net/nfc/nci.h
@@ -332,7 +332,7 @@ struct nci_core_init_rsp_1 {
 	__le32	nfcc_features;
 	__u8	num_supported_rf_interfaces;
 	__u8	supported_rf_interfaces[];	/* variable size array */
-	/* continuted in nci_core_init_rsp_2 */
+	/* continued in nci_core_init_rsp_2 */
 } __packed;
 
 struct nci_core_init_rsp_2 {
diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h
index 3d07abacf08b..3a3781838c67 100644
--- a/include/net/nfc/nfc.h
+++ b/include/net/nfc/nfc.h
@@ -80,7 +80,7 @@ struct nfc_ops {
 #define NFC_ATR_REQ_GT_OFFSET 14
 
 /**
- * struct nfc_target - NFC target descriptiom
+ * struct nfc_target - NFC target description
  *
  * @sens_res: 2 bytes describing the target SENS_RES response, if the target
  *	is a type A one. The %sens_res most significant byte must be byte 2
@@ -230,10 +230,10 @@ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev,
 }
 
 /**
- * nfc_set_drvdata - set driver specifc data
+ * nfc_set_drvdata - set driver specific data
  *
  * @dev: The nfc device
- * @data: Pointer to driver specifc data
+ * @data: Pointer to driver specific data
  */
 static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data)
 {
@@ -241,7 +241,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data)
 }
 
 /**
- * nfc_get_drvdata - get driver specifc data
+ * nfc_get_drvdata - get driver specific data
  *
  * @dev: The nfc device
  */
-- 
cgit v1.3-3-g829e


From a7a45f02a093d3b3f80a77db334703b5f53ebd44 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:30 +0100
Subject: net: sched: Correct spelling in headers

Correct spelling in pkt_cls.h and red.h.
As reported by codespell.

Cc: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-9-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/pkt_cls.h | 2 +-
 include/net/red.h     | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 41297bd38dff..4880b3a7aced 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -491,7 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *,
 			struct tcf_pkt_info *);
 
 /**
- * tcf_em_tree_match - evaulate an ematch tree
+ * tcf_em_tree_match - evaluate an ematch tree
  *
  * @skb: socket buffer of the packet in question
  * @tree: ematch tree to be used for evaluation
diff --git a/include/net/red.h b/include/net/red.h
index 802287d52c9e..159a09359fc0 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -40,7 +40,7 @@
 	max_P should be small (not 1), usually 0.01..0.02 is good value.
 
 	max_P is chosen as a number, so that max_P/(th_max-th_min)
-	is a negative power of two in order arithmetics to contain
+	is a negative power of two in order arithmetic to contain
 	only shifts.
 
 
@@ -159,7 +159,7 @@ static inline u32 red_maxp(u8 Plog)
 static inline void red_set_vars(struct red_vars *v)
 {
 	/* Reset average queue length, the value is strictly bound
-	 * to the parameters below, reseting hurts a bit but leaving
+	 * to the parameters below, resetting hurts a bit but leaving
 	 * it might result in an unreasonable qavg for a while. --TGR
 	 */
 	v->qavg		= 0;
@@ -340,7 +340,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p
 {
 	/*
 	 * NOTE: v->qavg is fixed point number with point at Wlog.
-	 * The formula below is equvalent to floating point
+	 * The formula below is equivalent to floating point
 	 * version:
 	 *
 	 * 	qavg = qavg*(1-W) + backlog*W;
@@ -375,7 +375,7 @@ static inline int red_mark_probability(const struct red_parms *p,
 	   OK. qR is random number in the interval
 		(0..1/max_P)*(qth_max-qth_min)
 	   i.e. 0..(2^Plog). If we used floating point
-	   arithmetics, it would be: (2^Plog)*rnd_num,
+	   arithmetic, it would be: (2^Plog)*rnd_num,
 	   where rnd_num is less 1.
 
 	   Taking into account, that qavg have fixed
-- 
cgit v1.3-3-g829e


From 7f47fcea8c6b4af25e72e0ebb8d492a181b7ce03 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:31 +0100
Subject: sctp: Correct spelling in headers

Correct spelling in sctp.h and structs.h.
As reported by codespell.

Cc: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Acked-by: Xin Long <lucien.xin@gmail.com>
Link: https://patch.msgid.link/20240822-net-spell-v1-10-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sctp/sctp.h    |  2 +-
 include/net/sctp/structs.h | 20 ++++++++++----------
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index a2310fa995f6..84e6b9fd5610 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -28,7 +28,7 @@
 #define __net_sctp_h__
 
 /* Header Strategy.
- *    Start getting some control over the header file depencies:
+ *    Start getting some control over the header file dependencies:
  *       includes
  *       constants
  *       structs
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index f24a1bbcb3ef..31248cfdfb23 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -521,7 +521,7 @@ struct sctp_datamsg {
 	refcount_t refcnt;
 	/* When is this message no longer interesting to the peer? */
 	unsigned long expires_at;
-	/* Did the messenge fail to send? */
+	/* Did the message fail to send? */
 	int send_error;
 	u8 send_failed:1,
 	   can_delay:1,	/* should this message be Nagle delayed */
@@ -792,7 +792,7 @@ struct sctp_transport {
 		 */
 		hb_sent:1,
 
-		/* Is the Path MTU update pending on this tranport */
+		/* Is the Path MTU update pending on this transport */
 		pmtu_pending:1,
 
 		dst_pending_confirm:1,	/* need to confirm neighbour */
@@ -1223,7 +1223,7 @@ enum sctp_endpoint_type {
 };
 
 /*
- * A common base class to bridge the implmentation view of a
+ * A common base class to bridge the implementation view of a
  * socket (usually listening) endpoint versus an association's
  * local endpoint.
  * This common structure is useful for several purposes:
@@ -1353,7 +1353,7 @@ struct sctp_endpoint {
 	struct rcu_head rcu;
 };
 
-/* Recover the outter endpoint structure. */
+/* Recover the outer endpoint structure. */
 static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base)
 {
 	struct sctp_endpoint *ep;
@@ -1906,7 +1906,7 @@ struct sctp_association {
 	__u32 rwnd_over;
 
 	/* Keeps treack of rwnd pressure.  This happens when we have
-	 * a window, but not recevie buffer (i.e small packets).  This one
+	 * a window, but not receive buffer (i.e small packets).  This one
 	 * is releases slowly (1 PMTU at a time ).
 	 */
 	__u32 rwnd_press;
@@ -1994,7 +1994,7 @@ struct sctp_association {
 
 	/* ADDIP Section 5.2 Upon reception of an ASCONF Chunk.
 	 *
-	 * This is needed to implement itmes E1 - E4 of the updated
+	 * This is needed to implement items E1 - E4 of the updated
 	 * spec.  Here is the justification:
 	 *
 	 * Since the peer may bundle multiple ASCONF chunks toward us,
@@ -2005,7 +2005,7 @@ struct sctp_association {
 
 	/* These ASCONF chunks are waiting to be sent.
 	 *
-	 * These chunaks can't be pushed to outqueue until receiving
+	 * These chunks can't be pushed to outqueue until receiving
 	 * ASCONF_ACK for the previous ASCONF indicated by
 	 * addip_last_asconf, so as to guarantee that only one ASCONF
 	 * is in flight at any time.
@@ -2059,13 +2059,13 @@ struct sctp_association {
 	struct sctp_transport *new_transport;
 
 	/* SCTP AUTH: list of the endpoint shared keys.  These
-	 * keys are provided out of band by the user applicaton
+	 * keys are provided out of band by the user application
 	 * and can't change during the lifetime of the association
 	 */
 	struct list_head endpoint_shared_keys;
 
 	/* SCTP AUTH:
-	 * The current generated assocaition shared key (secret)
+	 * The current generated association shared key (secret)
 	 */
 	struct sctp_auth_bytes *asoc_shared_key;
 	struct sctp_shared_key *shkey;
@@ -2121,7 +2121,7 @@ enum {
 	SCTP_ASSOC_EYECATCHER = 0xa550c123,
 };
 
-/* Recover the outter association structure. */
+/* Recover the outer association structure. */
 static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base)
 {
 	struct sctp_association *asoc;
-- 
cgit v1.3-3-g829e


From 01d86846a5a5f34662679dd229a0167fc9d92382 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:32 +0100
Subject: x25: Correct spelling in x25.h

Correct spelling in x25.h
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Martin Schiller <ms@dev.tdt.de>
Link: https://patch.msgid.link/20240822-net-spell-v1-11-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/x25.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/x25.h b/include/net/x25.h
index 597eb53c471e..5e833cfc864e 100644
--- a/include/net/x25.h
+++ b/include/net/x25.h
@@ -81,7 +81,7 @@ enum {
 
 #define	X25_DEFAULT_WINDOW_SIZE	2			/* Default Window Size	*/
 #define	X25_DEFAULT_PACKET_SIZE	X25_PS128		/* Default Packet Size */
-#define	X25_DEFAULT_THROUGHPUT	0x0A			/* Deafult Throughput */
+#define	X25_DEFAULT_THROUGHPUT	0x0A			/* Default Throughput */
 #define	X25_DEFAULT_REVERSE	0x00			/* Default Reverse Charging */
 
 #define X25_SMODULUS 		8
-- 
cgit v1.3-3-g829e


From 70d0bb45fae87a3b08970a318e15f317446a1956 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:33 +0100
Subject: net: Correct spelling in headers

Correct spelling in Networking headers.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-12-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/etherdevice.h    |  2 +-
 include/linux/netdevice.h      |  8 ++++----
 include/net/addrconf.h         |  2 +-
 include/net/busy_poll.h        |  2 +-
 include/net/caif/caif_layer.h  |  4 ++--
 include/net/caif/cfpkt.h       |  2 +-
 include/net/dropreason-core.h  |  6 +++---
 include/net/dst.h              |  2 +-
 include/net/dst_cache.h        |  2 +-
 include/net/erspan.h           |  4 ++--
 include/net/hwbm.h             |  4 ++--
 include/net/llc_pdu.h          |  2 +-
 include/net/netlink.h          | 16 ++++++++--------
 include/net/netns/sctp.h       |  4 ++--
 include/net/regulatory.h       |  2 +-
 include/net/sock.h             |  4 ++--
 include/net/udp.h              |  2 +-
 include/uapi/linux/in.h        |  2 +-
 include/uapi/linux/inet_diag.h |  2 +-
 19 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 0ed47d00549b..30114c25ad12 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -645,7 +645,7 @@ static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb)
 }
 
 /**
- * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame
+ * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame
  * @skb: Buffer to pad
  *
  * An Ethernet frame should have a minimum size of 60 bytes.  This function
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7dfa836d9dbf..fce70990b209 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1237,7 +1237,7 @@ struct netdev_net_notifier {
  * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
  *		      struct net_device *dev,
  *		      const unsigned char *addr, u16 vid)
- *	Deletes the FDB entry from dev coresponding to addr.
+ *	Deletes the FDB entry from dev corresponding to addr.
  * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev,
  *			   struct netlink_ext_ack *extack);
  * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
@@ -3514,7 +3514,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
 	dql_completed(&dev_queue->dql, bytes);
 
 	/*
-	 * Without the memory barrier there is a small possiblity that
+	 * Without the memory barrier there is a small possibility that
 	 * netdev_tx_sent_queue will miss the update and cause the queue to
 	 * be stopped forever
 	 */
@@ -4583,7 +4583,7 @@ void dev_uc_flush(struct net_device *dev);
 void dev_uc_init(struct net_device *dev);
 
 /**
- *  __dev_uc_sync - Synchonize device's unicast list
+ *  __dev_uc_sync - Synchronize device's unicast list
  *  @dev:  device to sync
  *  @sync: function to call if address should be added
  *  @unsync: function to call if address should be removed
@@ -4627,7 +4627,7 @@ void dev_mc_flush(struct net_device *dev);
 void dev_mc_init(struct net_device *dev);
 
 /**
- *  __dev_mc_sync - Synchonize device's multicast list
+ *  __dev_mc_sync - Synchronize device's multicast list
  *  @dev:  device to sync
  *  @sync: function to call if address should be added
  *  @unsync: function to call if address should be removed
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index c8ed31828db3..363dd63babe7 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -333,7 +333,7 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev)
 /**
  * __in6_dev_stats_get - get inet6_dev pointer for stats
  * @dev: network device
- * @skb: skb for original incoming interface if neeeded
+ * @skb: skb for original incoming interface if needed
  *
  * Caller must hold rcu_read_lock or RTNL, because this function
  * does not take a reference on the inet6_dev.
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 9b09acac538e..5e3b5703e4ab 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -131,7 +131,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
 #endif
 }
 
-/* used in the protocol hanlder to propagate the napi_id to the socket */
+/* used in the protocol handler to propagate the napi_id to the socket */
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h
index 0f45d875905f..053e7c6a6a66 100644
--- a/include/net/caif/caif_layer.h
+++ b/include/net/caif/caif_layer.h
@@ -20,7 +20,7 @@ struct caif_payload_info;
  * @assert: expression to evaluate.
  *
  * This function will print a error message and a do WARN_ON if the
- * assertion failes. Normally this will do a stack up at the current location.
+ * assertion fails. Normally this will do a stack up at the current location.
  */
 #define caif_assert(assert)					\
 do {								\
@@ -116,7 +116,7 @@ enum caif_direction {
  * @dn:		Pointer down to the layer below.
  * @node:	List node used when layer participate in a list.
  * @receive:	Packet receive function.
- * @transmit:	Packet transmit funciton.
+ * @transmit:	Packet transmit function.
  * @ctrlcmd:	Used for control signalling upwards in the stack.
  * @modemcmd:	Used for control signaling downwards in the stack.
  * @id:		The identity of this layer
diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h
index 44d914a50369..acf664227d96 100644
--- a/include/net/caif/cfpkt.h
+++ b/include/net/caif/cfpkt.h
@@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len);
 
 /*
  * Destroy a CAIF Packet.
- * pkt Packet to be destoyed.
+ * pkt Packet to be destroyed.
  */
 void cfpkt_destroy(struct cfpkt *pkt);
 
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 9707ab54fdd5..4748680e8c88 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -155,8 +155,8 @@ enum skb_drop_reason {
 	/** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */
 	SKB_DROP_REASON_SOCKET_RCVBUFF,
 	/**
-	 * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet
-	 * drop out of udp_memory_allocated.
+	 * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as
+	 * udp packet drop out of udp_memory_allocated.
 	 */
 	SKB_DROP_REASON_PROTO_MEM,
 	/**
@@ -217,7 +217,7 @@ enum skb_drop_reason {
 	 */
 	SKB_DROP_REASON_TCP_ZEROWINDOW,
 	/**
-	 * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already
+	 * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already
 	 * received before (spurious retrans may happened), see
 	 * LINUX_MIB_DELAYEDACKLOST
 	 */
diff --git a/include/net/dst.h b/include/net/dst.h
index 0aa331bd2fdb..0f303cc60252 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
 	skb->dev = dev;
 
 	/*
-	 * Clear hash so that we can recalulate the hash for the
+	 * Clear hash so that we can recalculate the hash for the
 	 * encapsulated packet, unless we have already determine the hash
 	 * over the L4 4-tuple.
 	 */
diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h
index b4a55d2d5e71..1961699598e2 100644
--- a/include/net/dst_cache.h
+++ b/include/net/dst_cache.h
@@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp);
  *	@dst_cache: the cache
  *
  *	No synchronization is enforced: it must be called only when the cache
- *	is unsed.
+ *	is unused.
  */
 void dst_cache_destroy(struct dst_cache *dst_cache);
 
diff --git a/include/net/erspan.h b/include/net/erspan.h
index 6cb4cbd6a48f..c6209e7b6c96 100644
--- a/include/net/erspan.h
+++ b/include/net/erspan.h
@@ -89,7 +89,7 @@ enum erspan_encap_type {
 	ERSPAN_ENCAP_NOVLAN = 0x0,	/* originally without VLAN tag */
 	ERSPAN_ENCAP_ISL = 0x1,		/* originally ISL encapsulated */
 	ERSPAN_ENCAP_8021Q = 0x2,	/* originally 802.1Q encapsulated */
-	ERSPAN_ENCAP_INFRAME = 0x3,	/* VLAN tag perserved in frame */
+	ERSPAN_ENCAP_INFRAME = 0x3,	/* VLAN tag preserved in frame */
 };
 
 #define ERSPAN_V1_MDSIZE	4
@@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb,
 	enc_type = ERSPAN_ENCAP_NOVLAN;
 
 	/* If mirrored packet has vlan tag, extract tci and
-	 *  perserve vlan header in the mirrored frame.
+	 * preserve vlan header in the mirrored frame.
 	 */
 	if (eth->h_proto == htons(ETH_P_8021Q)) {
 		qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN);
diff --git a/include/net/hwbm.h b/include/net/hwbm.h
index aa495decec35..bdbe91c609ff 100644
--- a/include/net/hwbm.h
+++ b/include/net/hwbm.h
@@ -11,9 +11,9 @@ struct hwbm_pool {
 	int frag_size;
 	/* Number of buffers currently used by this pool */
 	int buf_num;
-	/* constructor called during alocation */
+	/* constructor called during allocation */
 	int (*construct)(struct hwbm_pool *bm_pool, void *buf);
-	/* protect acces to the buffer counter*/
+	/* protect access to the buffer counter*/
 	struct mutex buf_lock;
 	/* private data */
 	void *priv;
diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index 1d55ba7c45be..86681f29bda7 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type,
 }
 
 /**
- *	llc_pdu_decode_sa - extracs source address (MAC) of input frame
+ *	llc_pdu_decode_sa - extracts, source address (MAC) of input frame
  *	@skb: input skb that source address must be extracted from it.
  *	@sa: pointer to source address (6 byte array).
  *
diff --git a/include/net/netlink.h b/include/net/netlink.h
index e78ce008e07c..db6af207287c 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -827,7 +827,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen,
 /**
  * nlmsg_find_attr - find a specific attribute in a netlink message
  * @nlh: netlink message header
- * @hdrlen: length of familiy specific header
+ * @hdrlen: length of family specific header
  * @attrtype: type of attribute to look for
  *
  * Returns the first attribute which matches the specified type.
@@ -849,7 +849,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh,
  *
  * Validates all attributes in the specified attribute stream against the
  * specified policy. Validation is done in liberal mode.
- * See documenation of struct nla_policy for more details.
+ * See documentation of struct nla_policy for more details.
  *
  * Returns 0 on success or a negative error code.
  */
@@ -872,7 +872,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len,
  *
  * Validates all attributes in the specified attribute stream against the
  * specified policy. Validation is done in strict mode.
- * See documenation of struct nla_policy for more details.
+ * See documentation of struct nla_policy for more details.
  *
  * Returns 0 on success or a negative error code.
  */
@@ -887,7 +887,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype,
 /**
  * nlmsg_validate_deprecated - validate a netlink message including attributes
  * @nlh: netlinket message header
- * @hdrlen: length of familiy specific header
+ * @hdrlen: length of family specific header
  * @maxtype: maximum attribute type to be expected
  * @policy: validation policy
  * @extack: extended ACK report struct
@@ -933,7 +933,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh)
  * nlmsg_for_each_attr - iterate over a stream of attributes
  * @pos: loop counter, set to current attribute
  * @nlh: netlink message header
- * @hdrlen: length of familiy specific header
+ * @hdrlen: length of family specific header
  * @rem: initialized to len, holds bytes currently remaining in stream
  */
 #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \
@@ -1034,7 +1034,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload)
  * @skb: socket buffer the message is stored in
  * @nlh: netlink message header
  *
- * Corrects the netlink message header to include the appeneded
+ * Corrects the netlink message header to include the appended
  * attributes. Only necessary if attributes have been added to
  * the message.
  */
@@ -1954,7 +1954,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype)
  * @start: container attribute
  *
  * Corrects the container attribute header to include the all
- * appeneded attributes.
+ * appended attributes.
  *
  * Returns the total data length of the skb.
  */
@@ -1987,7 +1987,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
  *
  * Validates all attributes in the nested attribute stream against the
  * specified policy. Attributes with a type exceeding maxtype will be
- * ignored. See documenation of struct nla_policy for more details.
+ * ignored. See documentation of struct nla_policy for more details.
  *
  * Returns 0 on success or a negative error code.
  */
diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h
index 7eff3d981b89..d25cd7a9c5ff 100644
--- a/include/net/netns/sctp.h
+++ b/include/net/netns/sctp.h
@@ -125,14 +125,14 @@ struct netns_sctp {
 	int pf_expose;
 
 	/*
-	 * Policy for preforming sctp/socket accounting
+	 * Policy for performing sctp/socket accounting
 	 * 0   - do socket level accounting, all assocs share sk_sndbuf
 	 * 1   - do sctp accounting, each asoc may use sk_sndbuf bytes
 	 */
 	int sndbuf_policy;
 
 	/*
-	 * Policy for preforming sctp/socket accounting
+	 * Policy for performing sctp/socket accounting
 	 * 0   - do socket level accounting, all assocs share sk_rcvbuf
 	 * 1   - do sctp accounting, each asoc may use sk_rcvbuf bytes
 	 */
diff --git a/include/net/regulatory.h b/include/net/regulatory.h
index a103f4c8cf75..6633627f6e76 100644
--- a/include/net/regulatory.h
+++ b/include/net/regulatory.h
@@ -121,7 +121,7 @@ struct regulatory_request {
  * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to
  *	ensure that passive scan flags and beaconing flags may not be lifted by
  *	cfg80211 due to regulatory beacon hints. For more information on beacon
- *	hints read the documenation for regulatory_hint_found_beacon()
+ *	hints read the documentation for regulatory_hint_found_beacon()
  * @REGULATORY_COUNTRY_IE_FOLLOW_POWER:  for devices that have a preference
  *	that even though they may have programmed their own custom power
  *	setting prior to wiphy registration, they want to ensure their channel
diff --git a/include/net/sock.h b/include/net/sock.h
index cce23ac4d514..f51d61fab059 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1624,7 +1624,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock);
  * lock_sock_fast - fast version of lock_sock
  * @sk: socket
  *
- * This version should be used for very small section, where process wont block
+ * This version should be used for very small section, where process won't block
  * return false if fast path is taken:
  *
  *   sk_lock.slock locked, owned = 0, BH disabled
@@ -2546,7 +2546,7 @@ struct sock_skb_cb {
 
 /* Store sock_skb_cb at the end of skb->cb[] so protocol families
  * using skb->cb[] would keep using it directly and utilize its
- * alignement guarantee.
+ * alignment guarantee.
  */
 #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \
 			    sizeof(struct sock_skb_cb)))
diff --git a/include/net/udp.h b/include/net/udp.h
index 5ca53b1cec67..61222545ab1c 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -232,7 +232,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
 	}
 
 	/* Since this is being sent on the wire obfuscate hash a bit
-	 * to minimize possbility that any useful information to an
+	 * to minimize possibility that any useful information to an
 	 * attacker is leaked. Only upper 16 bits are relevant in the
 	 * computation for 16 bit port value.
 	 */
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index d358add1611c..5d32d53508d9 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -141,7 +141,7 @@ struct in_addr {
  */
 #define IP_PMTUDISC_INTERFACE		4
 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
- * fragmented if they exeed the interface mtu
+ * fragmented if they exceed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
 
diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h
index 50655de04c9b..86bb2e8b17c9 100644
--- a/include/uapi/linux/inet_diag.h
+++ b/include/uapi/linux/inet_diag.h
@@ -143,7 +143,7 @@ enum {
 	INET_DIAG_SHUTDOWN,
 
 	/*
-	 * Next extenstions cannot be requested in struct inet_diag_req_v2:
+	 * Next extensions cannot be requested in struct inet_diag_req_v2:
 	 * its field idiag_ext has only 8 bits.
 	 */
 
-- 
cgit v1.3-3-g829e


From a8c924e98738f77668b022ec34107ca8b6093392 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 22 Aug 2024 13:57:34 +0100
Subject: net: Correct spelling in net/core

Correct spelling in net/core.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822-net-spell-v1-13-3a98971ce2d2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c            |  6 +++---
 net/core/dev_addr_lists.c |  6 +++---
 net/core/fib_rules.c      |  2 +-
 net/core/gro.c            |  2 +-
 net/core/netpoll.c        |  2 +-
 net/core/pktgen.c         | 10 +++++-----
 net/core/skbuff.c         |  4 ++--
 net/core/sock.c           |  6 +++---
 net/core/utils.c          |  2 +-
 9 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index f34ec921f881..63987b8b7c85 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3707,7 +3707,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d
 		next = skb->next;
 		skb_mark_not_on_list(skb);
 
-		/* in case skb wont be segmented, point to itself */
+		/* in case skb won't be segmented, point to itself */
 		skb->prev = skb;
 
 		skb = validate_xmit_skb(skb, dev, again);
@@ -11432,7 +11432,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
  *	@head: list of devices
  *
  *  Note: As most callers use a stack allocated list_head,
- *  we force a list_del() to make sure stack wont be corrupted later.
+ *  we force a list_del() to make sure stack won't be corrupted later.
  */
 void unregister_netdevice_many(struct list_head *head)
 {
@@ -11490,7 +11490,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	if (dev->features & NETIF_F_NETNS_LOCAL)
 		goto out;
 
-	/* Ensure the device has been registrered */
+	/* Ensure the device has been registered */
 	if (dev->reg_state != NETREG_REGISTERED)
 		goto out;
 
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index baa63dee2829..166e404f7c03 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -262,7 +262,7 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
 }
 
 /* This function only works where there is a strict 1-1 relationship
- * between source and destionation of they synch. If you ever need to
+ * between source and destination of they synch. If you ever need to
  * sync addresses to more then 1 destination, you need to use
  * __hw_addr_sync_multiple().
  */
@@ -299,8 +299,8 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 EXPORT_SYMBOL(__hw_addr_unsync);
 
 /**
- *  __hw_addr_sync_dev - Synchonize device's multicast list
- *  @list: address list to syncronize
+ *  __hw_addr_sync_dev - Synchronize device's multicast list
+ *  @list: address list to synchronize
  *  @dev:  device to sync
  *  @sync: function to call if address should be added
  *  @unsync: function to call if address should be removed
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 3c76b835493d..5a4eb744758c 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -72,7 +72,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->suppress_prefixlen = -1;
 	r->suppress_ifgroup = -1;
 
-	/* The lock is not required here, the list in unreacheable
+	/* The lock is not required here, the list in unreachable
 	 * at the moment this function is called */
 	list_add_tail(&r->list, &ops->rules_list);
 	return 0;
diff --git a/net/core/gro.c b/net/core/gro.c
index b3b43de1a650..3abad1b567dd 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -374,7 +374,7 @@ static void gro_list_prepare(const struct list_head *head,
 				       skb_mac_header(skb),
 				       maclen);
 
-		/* in most common scenarions 'slow_gro' is 0
+		/* in most common scenarios 'slow_gro' is 0
 		 * otherwise we are already on some slower paths
 		 * either skip all the infrequent tests altogether or
 		 * avoid trying too hard to skip each of them individually
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a1aea86cf98c..e0720ee6fa62 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -162,7 +162,7 @@ static void poll_one_napi(struct napi_struct *napi)
 	if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state))
 		return;
 
-	/* We explicilty pass the polling call a budget of 0 to
+	/* We explicitly pass the polling call a budget of 0 to
 	 * indicate that we are clearing the Tx path only.
 	 */
 	work = napi->poll(napi, 0);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index ea55a758a475..4baf02db1f6a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -69,7 +69,7 @@
  *
  * By design there should only be *one* "controlling" process. In practice
  * multiple write accesses gives unpredictable result. Understood by "write"
- * to /proc gives result code thats should be read be the "writer".
+ * to /proc gives result code that should be read be the "writer".
  * For practical use this should be no problem.
  *
  * Note when adding devices to a specific CPU there good idea to also assign
@@ -2371,11 +2371,11 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
 
 		if (pkt_dev->spi) {
 			/* We need as quick as possible to find the right SA
-			 * Searching with minimum criteria to archieve this.
+			 * Searching with minimum criteria to achieve, this.
 			 */
 			x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET);
 		} else {
-			/* slow path: we dont already have xfrm_state */
+			/* slow path: we don't already have xfrm_state */
 			x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0,
 						(xfrm_address_t *)&pkt_dev->cur_daddr,
 						(xfrm_address_t *)&pkt_dev->cur_saddr,
@@ -3838,8 +3838,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 	pkt_dev->ipsmode = XFRM_MODE_TRANSPORT;
 	pkt_dev->ipsproto = IPPROTO_ESP;
 
-	/* xfrm tunnel mode needs additional dst to extract outter
-	 * ip header protocol/ttl/id field, here creat a phony one.
+	/* xfrm tunnel mode needs additional dst to extract outer
+	 * ip header protocol/ttl/id field, here create a phony one.
 	 * instead of looking for a valid rt, which definitely hurting
 	 * performance under such circumstance.
 	 */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1748673e1fe0..6022c7359385 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5163,7 +5163,7 @@ EXPORT_SYMBOL_GPL(skb_to_sgvec);
  * 3. sg_unmark_end
  * 4. skb_to_sgvec(payload2)
  *
- * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * When mapping multiple payload conditionally, skb_to_sgvec_nomark
  * is more preferable.
  */
 int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
@@ -6021,7 +6021,7 @@ EXPORT_SYMBOL(skb_try_coalesce);
  * @skb: buffer to clean
  * @xnet: packet is crossing netns
  *
- * skb_scrub_packet can be used after encapsulating or decapsulting a packet
+ * skb_scrub_packet can be used after encapsulating or decapsulating a packet
  * into/from a tunnel. Some information have to be cleared during these
  * operations.
  * skb_scrub_packet can also be used to clean a skb before injecting it in
diff --git a/net/core/sock.c b/net/core/sock.c
index 9abc4fe25953..468b1239606c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2048,7 +2048,7 @@ static inline void sock_lock_init(struct sock *sk)
 
 /*
  * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet,
- * even temporarly, because of RCU lookups. sk_node should also be left as is.
+ * even temporarily, because of RCU lookups. sk_node should also be left as is.
  * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end
  */
 static void sock_copy(struct sock *nsk, const struct sock *osk)
@@ -2538,7 +2538,7 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
 	skb_set_hash_from_sk(skb, sk);
 	/*
 	 * We used to take a refcount on sk, but following operation
-	 * is enough to guarantee sk_free() wont free this sock until
+	 * is enough to guarantee sk_free() won't free this sock until
 	 * all in-flight packets are completed
 	 */
 	refcount_add(skb->truesize, &sk->sk_wmem_alloc);
@@ -3697,7 +3697,7 @@ EXPORT_SYMBOL(sock_recv_errqueue);
  *
  *	FIX: POSIX 1003.1g is very ambiguous here. It states that
  *	asynchronous errors should be reported by getsockopt. We assume
- *	this means if you specify SO_ERROR (otherwise whats the point of it).
+ *	this means if you specify SO_ERROR (otherwise what is the point of it).
  */
 int sock_common_getsockopt(struct socket *sock, int level, int optname,
 			   char __user *optval, int __user *optlen)
diff --git a/net/core/utils.c b/net/core/utils.c
index c994e95172ac..27f4cffaae05 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- *	Generic address resultion entity
+ *	Generic address resolution entity
  *
  *	Authors:
  *	net_random Alan Cox
-- 
cgit v1.3-3-g829e


From caf4daae871c20a3da1a822d8713c858c8a85d5c Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 6 Aug 2024 13:46:22 -0700
Subject: ice: improve debug print for control queue messages

The ice_debug_cq function is called to print debug data for a control queue
descriptor in multiple places. This includes both before we send a message
on a transmit queue, after the writeback completion of a message on the
transmit queue, and when we receive a message on a receive queue.

This function does not include data about *which* control queue the message
is on, nor whether it was what we sent to the queue or what we received
from the queue.

Modify ice_debug_cq to take two extra parameters, a pointer to the control
queue and a boolean indicating if this was a response or a command. Improve
the debug messages by replacing "CQ CMD" with a string indicating which
specific control queue (based on cq->qtype) and whether this was a command
sent by the PF or a response from the queue.

This helps make the log output easier to understand and consume when
debugging.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 36 +++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 1b1b68a99bb2..b0b38825e300 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -887,16 +887,41 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	return ICE_CTL_Q_DESC_UNUSED(sq);
 }
 
+/**
+ * ice_ctl_q_str - Convert control queue type to string
+ * @qtype: the control queue type
+ *
+ * Return: A string name for the given control queue type.
+ */
+static const char *ice_ctl_q_str(enum ice_ctl_q qtype)
+{
+	switch (qtype) {
+	case ICE_CTL_Q_UNKNOWN:
+		return "Unknown CQ";
+	case ICE_CTL_Q_ADMIN:
+		return "AQ";
+	case ICE_CTL_Q_MAILBOX:
+		return "MBXQ";
+	case ICE_CTL_Q_SB:
+		return "SBQ";
+	default:
+		return "Unrecognized CQ";
+	}
+}
+
 /**
  * ice_debug_cq
  * @hw: pointer to the hardware structure
+ * @cq: pointer to the specific Control queue
  * @desc: pointer to control queue descriptor
  * @buf: pointer to command buffer
  * @buf_len: max length of buf
+ * @response: true if this is the writeback response
  *
  * Dumps debug log about control command with descriptor contents.
  */
-static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len)
+static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
+			 void *desc, void *buf, u16 buf_len, bool response)
 {
 	struct ice_aq_desc *cq_desc = desc;
 	u16 len;
@@ -910,7 +935,8 @@ static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len)
 
 	len = le16_to_cpu(cq_desc->datalen);
 
-	ice_debug(hw, ICE_DBG_AQ_DESC, "CQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
+	ice_debug(hw, ICE_DBG_AQ_DESC, "%s %s: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
+		  ice_ctl_q_str(cq->qtype), response ? "Response" : "Command",
 		  le16_to_cpu(cq_desc->opcode),
 		  le16_to_cpu(cq_desc->flags),
 		  le16_to_cpu(cq_desc->datalen), le16_to_cpu(cq_desc->retval));
@@ -1064,7 +1090,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	/* Debug desc and buffer */
 	ice_debug(hw, ICE_DBG_AQ_DESC, "ATQ: Control Send queue desc and buffer:\n");
 
-	ice_debug_cq(hw, (void *)desc_on_ring, buf, buf_size);
+	ice_debug_cq(hw, cq, (void *)desc_on_ring, buf, buf_size, false);
 
 	(cq->sq.next_to_use)++;
 	if (cq->sq.next_to_use == cq->sq.count)
@@ -1106,7 +1132,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 
 	ice_debug(hw, ICE_DBG_AQ_MSG, "ATQ: desc and buffer writeback:\n");
 
-	ice_debug_cq(hw, (void *)desc, buf, buf_size);
+	ice_debug_cq(hw, cq, (void *)desc, buf, buf_size, true);
 
 	/* save writeback AQ if requested */
 	if (details->wb_desc)
@@ -1210,7 +1236,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 
 	ice_debug(hw, ICE_DBG_AQ_DESC, "ARQ: desc and buffer:\n");
 
-	ice_debug_cq(hw, (void *)desc, e->msg_buf, cq->rq_buf_size);
+	ice_debug_cq(hw, cq, (void *)desc, e->msg_buf, cq->rq_buf_size, true);
 
 	/* Restore the original datalen and buffer address in the desc,
 	 * FW updates datalen to indicate the event message size
-- 
cgit v1.3-3-g829e


From 6bd7cb522b1c06f826b74a40c5a0f23b1e4d00ae Mon Sep 17 00:00:00 2001
From: Bruce Allan <bruce.w.allan@intel.com>
Date: Tue, 6 Aug 2024 13:46:23 -0700
Subject: ice: do not clutter debug logs with unused data

Currently, debug logs are unnecessarily cluttered with the contents of
command data buffers even if the receiver of that command (i.e. FW or MBX)
are not told to read the buffer.  Change to only log command data buffers
when the RD flag (indicates receiver needs to read the buffer) is set.
Continue to log response data buffer when the returned datalen is non-zero.

Also, rename a local variable to reflect what is in the hardware
specification and how it is used elsewhere in the code, use local variables
instead of duplicating endian conversions unnecessarily and remove an
unnecessary assignment.

Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h |  4 ++++
 drivers/net/ethernet/intel/ice/ice_controlq.c   | 21 ++++++++++++---------
 2 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 66f02988d549..0be1a98d7cc1 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -2632,12 +2632,16 @@ struct ice_aq_desc {
 /* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
 #define ICE_AQ_LG_BUF	512
 
+#define ICE_AQ_FLAG_DD_S	0
+#define ICE_AQ_FLAG_CMP_S	1
 #define ICE_AQ_FLAG_ERR_S	2
 #define ICE_AQ_FLAG_LB_S	9
 #define ICE_AQ_FLAG_RD_S	10
 #define ICE_AQ_FLAG_BUF_S	12
 #define ICE_AQ_FLAG_SI_S	13
 
+#define ICE_AQ_FLAG_DD		BIT(ICE_AQ_FLAG_DD_S)  /* 0x1    */
+#define ICE_AQ_FLAG_CMP		BIT(ICE_AQ_FLAG_CMP_S) /* 0x2    */
 #define ICE_AQ_FLAG_ERR		BIT(ICE_AQ_FLAG_ERR_S) /* 0x4    */
 #define ICE_AQ_FLAG_LB		BIT(ICE_AQ_FLAG_LB_S)  /* 0x200  */
 #define ICE_AQ_FLAG_RD		BIT(ICE_AQ_FLAG_RD_S)  /* 0x400  */
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index b0b38825e300..ddf07b773313 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -924,7 +924,7 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			 void *desc, void *buf, u16 buf_len, bool response)
 {
 	struct ice_aq_desc *cq_desc = desc;
-	u16 len;
+	u16 datalen, flags;
 
 	if (!IS_ENABLED(CONFIG_DYNAMIC_DEBUG) &&
 	    !((ICE_DBG_AQ_DESC | ICE_DBG_AQ_DESC_BUF) & hw->debug_mask))
@@ -933,13 +933,13 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	if (!desc)
 		return;
 
-	len = le16_to_cpu(cq_desc->datalen);
+	datalen = le16_to_cpu(cq_desc->datalen);
+	flags = le16_to_cpu(cq_desc->flags);
 
 	ice_debug(hw, ICE_DBG_AQ_DESC, "%s %s: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
 		  ice_ctl_q_str(cq->qtype), response ? "Response" : "Command",
-		  le16_to_cpu(cq_desc->opcode),
-		  le16_to_cpu(cq_desc->flags),
-		  le16_to_cpu(cq_desc->datalen), le16_to_cpu(cq_desc->retval));
+		  le16_to_cpu(cq_desc->opcode), flags, datalen,
+		  le16_to_cpu(cq_desc->retval));
 	ice_debug(hw, ICE_DBG_AQ_DESC, "\tcookie (h,l) 0x%08X 0x%08X\n",
 		  le32_to_cpu(cq_desc->cookie_high),
 		  le32_to_cpu(cq_desc->cookie_low));
@@ -949,12 +949,15 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	ice_debug(hw, ICE_DBG_AQ_DESC, "\taddr (h,l)   0x%08X 0x%08X\n",
 		  le32_to_cpu(cq_desc->params.generic.addr_high),
 		  le32_to_cpu(cq_desc->params.generic.addr_low));
-	if (buf && cq_desc->datalen != 0) {
+	/* Dump buffer iff 1) one exists and 2) is either a response indicated
+	 * by the DD and/or CMP flag set or a command with the RD flag set.
+	 */
+	if (buf && cq_desc->datalen &&
+	    (flags & (ICE_AQ_FLAG_DD | ICE_AQ_FLAG_CMP | ICE_AQ_FLAG_RD))) {
 		ice_debug(hw, ICE_DBG_AQ_DESC_BUF, "Buffer:\n");
-		if (buf_len < len)
-			len = buf_len;
 
-		ice_debug_array(hw, ICE_DBG_AQ_DESC_BUF, 16, 1, buf, len);
+		ice_debug_array(hw, ICE_DBG_AQ_DESC_BUF, 16, 1, buf,
+				min_t(u16, buf_len, datalen));
 	}
 }
 
-- 
cgit v1.3-3-g829e


From 74ce564a30efbab1eccc2182f21414eae1dd085c Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Tue, 6 Aug 2024 13:46:24 -0700
Subject: ice: stop intermixing AQ commands/responses debug dumps

The ice_debug_cq() function is called to generate a debug log of control
queue messages both sent and received. It currently does this over a
potential total of 6 different printk invocations.

The main logic prints over 4 calls to ice_debug():

 1. The metadata including opcode, flags, datalength and return value.
 2. The cookie in the descriptor.
 3. The parameter values.
 4. The address for the databuffer.

In addition, if the descriptor has a data buffer, it can be logged with two
additional prints:

 5. A message indicating the start of the data buffer.
 6. The actual data buffer, printed using print_hex_dump_debug.

This can lead to trouble in the event that two different PFs are logging
messages. The messages become intermixed and it may not be possible to
determine which part of the output belongs to which control queue message.

To fix this, it needs to be possible to unambiguously determine which
messages belong together. This is trivial for the messages that comprise
the main printing. Combine them together into a single invocation of
ice_debug().

The message containing a hex-dump of the data buffer is a bit more
complicated. This is printed separately as part of print_hex_dump_debug.
This function takes a prefix, which is currently always set to
KBUILD_MODNAME. Extend this prefix to include the buffer address for the
databuffer, which is printed as part of the main print, and which is
guaranteed to be unique for each buffer.

Refactor the ice_debug_array(), introducing an ice_debug_array_w_prefix().
Build the prefix by combining KBUILD_MODNAME with the databuffer address
using snprintf().

These changes make it possible to unambiguously determine what data belongs
to what control queue message.

Reported-by: Jacek Wierzbicki <jacek.wierzbicki@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 23 ++++++++++++-----------
 drivers/net/ethernet/intel/ice/ice_osdep.h    | 24 ++++++++++++++----------
 2 files changed, 26 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index ddf07b773313..020600de9533 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -936,17 +936,14 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	datalen = le16_to_cpu(cq_desc->datalen);
 	flags = le16_to_cpu(cq_desc->flags);
 
-	ice_debug(hw, ICE_DBG_AQ_DESC, "%s %s: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n",
+	ice_debug(hw, ICE_DBG_AQ_DESC, "%s %s: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n\tcookie (h,l) 0x%08X 0x%08X\n\tparam (0,1)  0x%08X 0x%08X\n\taddr (h,l)   0x%08X 0x%08X\n",
 		  ice_ctl_q_str(cq->qtype), response ? "Response" : "Command",
 		  le16_to_cpu(cq_desc->opcode), flags, datalen,
-		  le16_to_cpu(cq_desc->retval));
-	ice_debug(hw, ICE_DBG_AQ_DESC, "\tcookie (h,l) 0x%08X 0x%08X\n",
+		  le16_to_cpu(cq_desc->retval),
 		  le32_to_cpu(cq_desc->cookie_high),
-		  le32_to_cpu(cq_desc->cookie_low));
-	ice_debug(hw, ICE_DBG_AQ_DESC, "\tparam (0,1)  0x%08X 0x%08X\n",
+		  le32_to_cpu(cq_desc->cookie_low),
 		  le32_to_cpu(cq_desc->params.generic.param0),
-		  le32_to_cpu(cq_desc->params.generic.param1));
-	ice_debug(hw, ICE_DBG_AQ_DESC, "\taddr (h,l)   0x%08X 0x%08X\n",
+		  le32_to_cpu(cq_desc->params.generic.param1),
 		  le32_to_cpu(cq_desc->params.generic.addr_high),
 		  le32_to_cpu(cq_desc->params.generic.addr_low));
 	/* Dump buffer iff 1) one exists and 2) is either a response indicated
@@ -954,10 +951,14 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	 */
 	if (buf && cq_desc->datalen &&
 	    (flags & (ICE_AQ_FLAG_DD | ICE_AQ_FLAG_CMP | ICE_AQ_FLAG_RD))) {
-		ice_debug(hw, ICE_DBG_AQ_DESC_BUF, "Buffer:\n");
-
-		ice_debug_array(hw, ICE_DBG_AQ_DESC_BUF, 16, 1, buf,
-				min_t(u16, buf_len, datalen));
+		char prefix[] = KBUILD_MODNAME " 0x12341234 0x12341234 ";
+
+		sprintf(prefix, KBUILD_MODNAME " 0x%08X 0x%08X ",
+			le32_to_cpu(cq_desc->params.generic.addr_high),
+			le32_to_cpu(cq_desc->params.generic.addr_low));
+		ice_debug_array_w_prefix(hw, ICE_DBG_AQ_DESC_BUF, prefix,
+					 buf,
+					 min_t(u16, buf_len, datalen));
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h
index 9882e6f3b26d..b9f383494b3f 100644
--- a/drivers/net/ethernet/intel/ice/ice_osdep.h
+++ b/drivers/net/ethernet/intel/ice/ice_osdep.h
@@ -43,11 +43,10 @@ struct device *ice_hw_to_dev(struct ice_hw *hw);
 #define ice_debug(hw, type, fmt, args...) \
 	dev_dbg(ice_hw_to_dev(hw), fmt, ##args)
 
-#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \
-	print_hex_dump_debug(KBUILD_MODNAME " ",		\
-			     DUMP_PREFIX_OFFSET, rowsize,	\
-			     groupsize, buf, len, false)
-#else
+#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \
+	print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET,		 \
+			     rowsize, groupsize, buf, len, false)
+#else /* CONFIG_DYNAMIC_DEBUG */
 #define ice_debug(hw, type, fmt, args...)			\
 do {								\
 	if ((type) & (hw)->debug_mask)				\
@@ -55,16 +54,15 @@ do {								\
 } while (0)
 
 #ifdef DEBUG
-#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \
+#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \
 do {								\
 	if ((type) & (hw)->debug_mask)				\
-		print_hex_dump_debug(KBUILD_MODNAME,		\
-				     DUMP_PREFIX_OFFSET,	\
+		print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET,\
 				     rowsize, groupsize, buf,	\
 				     len, false);		\
 } while (0)
-#else
-#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \
+#else /* DEBUG */
+#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \
 do {								\
 	struct ice_hw *hw_l = hw;				\
 	if ((type) & (hw_l)->debug_mask) {			\
@@ -82,4 +80,10 @@ do {								\
 #endif /* DEBUG */
 #endif /* CONFIG_DYNAMIC_DEBUG */
 
+#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \
+	_ice_debug_array(hw, type, KBUILD_MODNAME, rowsize, groupsize, buf, len)
+
+#define ice_debug_array_w_prefix(hw, type, prefix, buf, len) \
+	_ice_debug_array(hw, type, prefix, 16, 1, buf, len)
+
 #endif /* _ICE_OSDEP_H_ */
-- 
cgit v1.3-3-g829e


From 1d95d9256cfaa3e5a1a4b3cedbd3c043df229b5a Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 6 Aug 2024 13:46:25 -0700
Subject: ice: reword comments referring to control queues

Many comments in ice_controlq.c use the term "Admin queue" despite the code
being intended for arbitrary control queues, not just the Admin queue.
Reword the comments to make it clear that this code is the generic control
queue logic that is shared by all of the control queues, and is not
specific to the Admin queue.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 020600de9533..f38fd25a914a 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -188,7 +188,7 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 		if (cq->rq_buf_size > ICE_AQ_LG_BUF)
 			desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
 		desc->opcode = 0;
-		/* This is in accordance with Admin queue design, there is no
+		/* This is in accordance with control queue design, there is no
 		 * register for buffer size configuration
 		 */
 		desc->datalen = cpu_to_le16(bi->size);
@@ -405,11 +405,11 @@ init_ctrlq_exit:
 }
 
 /**
- * ice_init_rq - initialize ARQ
+ * ice_init_rq - initialize receive side of a control queue
  * @hw: pointer to the hardware structure
  * @cq: pointer to the specific Control queue
  *
- * The main initialization routine for the Admin Receive (Event) Queue.
+ * The main initialization routine for Receive side of a control queue.
  * Prior to calling this function, the driver *MUST* set the following fields
  * in the cq->structure:
  *     - cq->num_rq_entries
@@ -465,7 +465,7 @@ init_ctrlq_exit:
 }
 
 /**
- * ice_shutdown_sq - shutdown the Control ATQ
+ * ice_shutdown_sq - shutdown the transmit side of a control queue
  * @hw: pointer to the hardware structure
  * @cq: pointer to the specific Control queue
  *
@@ -482,7 +482,7 @@ static int ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 		goto shutdown_sq_out;
 	}
 
-	/* Stop firmware AdminQ processing */
+	/* Stop processing of the control queue */
 	wr32(hw, cq->sq.head, 0);
 	wr32(hw, cq->sq.tail, 0);
 	wr32(hw, cq->sq.len, 0);
@@ -855,7 +855,7 @@ void ice_destroy_all_ctrlq(struct ice_hw *hw)
 }
 
 /**
- * ice_clean_sq - cleans Admin send queue (ATQ)
+ * ice_clean_sq - cleans send side of a control queue
  * @hw: pointer to the hardware structure
  * @cq: pointer to the specific Control queue
  *
@@ -989,7 +989,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 }
 
 /**
- * ice_sq_send_cmd - send command to Control Queue (ATQ)
+ * ice_sq_send_cmd - send command to a control queue
  * @hw: pointer to the HW struct
  * @cq: pointer to the specific Control queue
  * @desc: prefilled descriptor describing the command
@@ -997,8 +997,9 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
  * @buf_size: size of buffer for indirect commands (or 0 for direct commands)
  * @cd: pointer to command details structure
  *
- * This is the main send command routine for the ATQ. It runs the queue,
- * cleans the queue, etc.
+ * Main command for the transmit side of a control queue. It puts the command
+ * on the queue, bumps the tail, waits for processing of the command, captures
+ * command status and results, etc.
  */
 int
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
@@ -1182,9 +1183,9 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
  * @e: event info from the receive descriptor, includes any buffers
  * @pending: number of events that could be left to process
  *
- * This function cleans one Admin Receive Queue element and returns
- * the contents through e. It can also return how many events are
- * left to process through 'pending'.
+ * Clean one element from the receive side of a control queue. On return 'e'
+ * contains contents of the message, and 'pending' contains the number of
+ * events left to process.
  */
 int
 ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-- 
cgit v1.3-3-g829e


From 448711c1dad080c0fc5e87d0464366f21085e98e Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 6 Aug 2024 13:46:26 -0700
Subject: ice: remove unnecessary control queue cmd_buf arrays

The driver allocates a cmd_buf array in addition to the desc_buf array.
This array stores an ice_sq_cd command details structure for each entry in
the control queue ring.

The contents of the structure are copied from the value passed in via
ice_sq_send_cmd, and include only a pointer to storage for the write back
descriptor contents.

Originally this array was intended to support asynchronous completion
including features such as a callback function. This support was never
implemented. All that exists today is needless copying and resetting of a
cmd_buf array that is otherwise functionally unused.

Since we do not plan to implement asynchronous completions, drop this
unnecessary memory and logic. This saves memory for each control queue, and
avoids the pointless copying and memset.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 29 ++-------------------------
 drivers/net/ethernet/intel/ice/ice_controlq.h |  3 ---
 2 files changed, 2 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index f38fd25a914a..b5774035e6f9 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -99,17 +99,6 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 		return -ENOMEM;
 	cq->sq.desc_buf.size = size;
 
-	cq->sq.cmd_buf = devm_kcalloc(ice_hw_to_dev(hw), cq->num_sq_entries,
-				      sizeof(struct ice_sq_cd), GFP_KERNEL);
-	if (!cq->sq.cmd_buf) {
-		dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size,
-				   cq->sq.desc_buf.va, cq->sq.desc_buf.pa);
-		cq->sq.desc_buf.va = NULL;
-		cq->sq.desc_buf.pa = 0;
-		cq->sq.desc_buf.size = 0;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
@@ -338,8 +327,6 @@ do {									\
 					(qi)->ring.r.ring##_bi[i].size = 0;\
 		}							\
 	}								\
-	/* free the buffer info list */					\
-	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);		\
 	/* free DMA head */						\
 	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
 } while (0)
@@ -865,21 +852,17 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
 	struct ice_ctl_q_ring *sq = &cq->sq;
 	u16 ntc = sq->next_to_clean;
-	struct ice_sq_cd *details;
 	struct ice_aq_desc *desc;
 
 	desc = ICE_CTL_Q_DESC(*sq, ntc);
-	details = ICE_CTL_Q_DETAILS(*sq, ntc);
 
 	while (rd32(hw, cq->sq.head) != ntc) {
 		ice_debug(hw, ICE_DBG_AQ_MSG, "ntc %d head %d.\n", ntc, rd32(hw, cq->sq.head));
 		memset(desc, 0, sizeof(*desc));
-		memset(details, 0, sizeof(*details));
 		ntc++;
 		if (ntc == sq->count)
 			ntc = 0;
 		desc = ICE_CTL_Q_DESC(*sq, ntc);
-		details = ICE_CTL_Q_DETAILS(*sq, ntc);
 	}
 
 	sq->next_to_clean = ntc;
@@ -1009,7 +992,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	struct ice_dma_mem *dma_buf = NULL;
 	struct ice_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
-	struct ice_sq_cd *details;
 	int status = 0;
 	u16 retval = 0;
 	u32 val = 0;
@@ -1053,12 +1035,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		goto sq_send_command_error;
 	}
 
-	details = ICE_CTL_Q_DETAILS(cq->sq, cq->sq.next_to_use);
-	if (cd)
-		*details = *cd;
-	else
-		memset(details, 0, sizeof(*details));
-
 	/* Call clean and check queue available function to reclaim the
 	 * descriptors that were processed by FW/MBX; the function returns the
 	 * number of desc available. The clean function called here could be
@@ -1140,9 +1116,8 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	ice_debug_cq(hw, cq, (void *)desc, buf, buf_size, true);
 
 	/* save writeback AQ if requested */
-	if (details->wb_desc)
-		memcpy(details->wb_desc, desc_on_ring,
-		       sizeof(*details->wb_desc));
+	if (cd && cd->wb_desc)
+		memcpy(cd->wb_desc, desc_on_ring, sizeof(*cd->wb_desc));
 
 	/* update the error if time out occurred */
 	if (!cmd_completed) {
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index e5b6691436f5..ca97b7365a1b 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -50,7 +50,6 @@ enum ice_ctl_q {
 struct ice_ctl_q_ring {
 	void *dma_head;			/* Virtual address to DMA head */
 	struct ice_dma_mem desc_buf;	/* descriptor ring memory */
-	void *cmd_buf;			/* command buffer memory */
 
 	union {
 		struct ice_dma_mem *sq_bi;
@@ -80,8 +79,6 @@ struct ice_sq_cd {
 	struct ice_aq_desc *wb_desc;
 };
 
-#define ICE_CTL_Q_DETAILS(R, i) (&(((struct ice_sq_cd *)((R).cmd_buf))[i]))
-
 /* rq event information */
 struct ice_rq_event_info {
 	struct ice_aq_desc desc;
-- 
cgit v1.3-3-g829e


From b1703d5f794d755e0d4ce1f22eee1215acb8ce02 Mon Sep 17 00:00:00 2001
From: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Date: Tue, 6 Aug 2024 13:46:27 -0700
Subject: ice: Report NVM version numbers on mismatch during load

Report NVM version numbers (both detected and expected) when a mismatch b/w
driver and firmware is detected. This provides more useful information
about which NVM version the driver expects, rather than requiring manual
code inspection.

Signed-off-by: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_controlq.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index b5774035e6f9..e3959ad442a2 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -488,7 +488,7 @@ shutdown_sq_out:
 }
 
 /**
- * ice_aq_ver_check - Check the reported AQ API version.
+ * ice_aq_ver_check - Check the reported AQ API version
  * @hw: pointer to the hardware structure
  *
  * Checks if the driver should load on a given AQ API version.
@@ -508,14 +508,20 @@ static bool ice_aq_ver_check(struct ice_hw *hw)
 	} else if (hw->api_maj_ver == exp_fw_api_ver_major) {
 		if (hw->api_min_ver > (exp_fw_api_ver_minor + 2))
 			dev_info(ice_hw_to_dev(hw),
-				 "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+				 "The driver for the device detected a newer version (%u.%u) of the NVM image than expected (%u.%u). Please install the most recent version of the network driver.\n",
+				 hw->api_maj_ver, hw->api_min_ver,
+				 exp_fw_api_ver_major, exp_fw_api_ver_minor);
 		else if ((hw->api_min_ver + 2) < exp_fw_api_ver_minor)
 			dev_info(ice_hw_to_dev(hw),
-				 "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+				 "The driver for the device detected an older version (%u.%u) of the NVM image than expected (%u.%u). Please update the NVM image.\n",
+				 hw->api_maj_ver, hw->api_min_ver,
+				 exp_fw_api_ver_major, exp_fw_api_ver_minor);
 	} else {
 		/* Major API version is older than expected, log a warning */
 		dev_info(ice_hw_to_dev(hw),
-			 "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+			 "The driver for the device detected an older version (%u.%u) of the NVM image than expected (%u.%u). Please update the NVM image.\n",
+			 hw->api_maj_ver, hw->api_min_ver,
+			 exp_fw_api_ver_major, exp_fw_api_ver_minor);
 	}
 	return true;
 }
-- 
cgit v1.3-3-g829e


From b4985aa8e312fd40fbbce0fe44ce677368fdee43 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 21:39:03 +0800
Subject: net: caif: use max() to simplify the code

When processing the tail append of sk buffer, the final length needs
to be determined based on expectlen and addlen. Using max() here can
increase the readability of the code.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822133908.1042240-4-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/caif/cfpkt_skbuff.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index 2ae8cfa3df88..96236d21b18e 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -298,10 +298,8 @@ struct cfpkt *cfpkt_append(struct cfpkt *dstpkt,
 	if (unlikely(is_erronous(dstpkt) || is_erronous(addpkt))) {
 		return dstpkt;
 	}
-	if (expectlen > addlen)
-		neededtailspace = expectlen;
-	else
-		neededtailspace = addlen;
+
+	neededtailspace = max(expectlen, addlen);
 
 	if (dst->tail + neededtailspace > dst->end) {
 		/* Create a dumplicate of 'dst' with more tail space */
-- 
cgit v1.3-3-g829e


From 26549dab8a4676ce549cb20bf384daf458a9ea24 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 21:39:06 +0800
Subject: ipv6: mcast: use min() to simplify the code

When coping sockaddr in ip6_mc_msfget(), the time of copies
depends on the minimum value between sl_count and gf_numsrc.
Using min() here is very semantic.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822133908.1042240-7-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/mcast.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7ba01d8cfbae..b244dbf61d5f 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -586,7 +586,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	const struct in6_addr *group;
 	struct ipv6_mc_socklist *pmc;
 	struct ip6_sf_socklist *psl;
-	int i, count, copycount;
+	unsigned int count;
+	int i, copycount;
 
 	group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr;
 
@@ -610,7 +611,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
 	psl = sock_dereference(pmc->sflist, sk);
 	count = psl ? psl->sl_count : 0;
 
-	copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
+	copycount = min(count, gsf->gf_numsrc);
 	gsf->gf_numsrc = count;
 	for (i = 0; i < copycount; i++) {
 		struct sockaddr_in6 *psin6;
-- 
cgit v1.3-3-g829e


From a18308623ce303a0f8954294f3877b3ece8c5e7b Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Thu, 22 Aug 2024 21:39:07 +0800
Subject: tipc: use min() to simplify the code

When calculating size of own domain based on number of peers, the result
should be less than MAX_MON_DOMAIN, so using min() here is very semantic.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822133908.1042240-8-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/monitor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 77a3d016cade..e2f19627e43d 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -149,7 +149,7 @@ static int dom_size(int peers)
 
 	while ((i * i) < peers)
 		i++;
-	return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN;
+	return min(i, MAX_MON_DOMAIN);
 }
 
 static void map_set(u64 *up_map, int i, unsigned int v)
-- 
cgit v1.3-3-g829e


From 62fdaf9e8056e9a9e6fe63aa9c816ec2122d60c6 Mon Sep 17 00:00:00 2001
From: Aleksandr Mishin <amishin@t-argos.ru>
Date: Wed, 10 Jul 2024 15:39:49 +0300
Subject: ice: Adjust over allocation of memory in ice_sched_add_root_node()
 and ice_sched_add_node()

In ice_sched_add_root_node() and ice_sched_add_node() there are calls to
devm_kcalloc() in order to allocate memory for array of pointers to
'ice_sched_node' structure. But incorrect types are used as sizeof()
arguments in these calls (structures instead of pointers) which leads to
over allocation of memory.

Adjust over allocation of memory by correcting types in devm_kcalloc()
sizeof() arguments.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Aleksandr Mishin <amishin@t-argos.ru>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_sched.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index ecf8f5d60292..6ca13c5dcb14 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -28,9 +28,8 @@ ice_sched_add_root_node(struct ice_port_info *pi,
 	if (!root)
 		return -ENOMEM;
 
-	/* coverity[suspicious_sizeof] */
 	root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0],
-				      sizeof(*root), GFP_KERNEL);
+				      sizeof(*root->children), GFP_KERNEL);
 	if (!root->children) {
 		devm_kfree(ice_hw_to_dev(hw), root);
 		return -ENOMEM;
@@ -186,10 +185,9 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer,
 	if (!node)
 		return -ENOMEM;
 	if (hw->max_children[layer]) {
-		/* coverity[suspicious_sizeof] */
 		node->children = devm_kcalloc(ice_hw_to_dev(hw),
 					      hw->max_children[layer],
-					      sizeof(*node), GFP_KERNEL);
+					      sizeof(*node->children), GFP_KERNEL);
 		if (!node->children) {
 			devm_kfree(ice_hw_to_dev(hw), node);
 			return -ENOMEM;
-- 
cgit v1.3-3-g829e


From cd039e6787ff6c496239c0c2f6d740e7c216d763 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 22 Aug 2024 11:40:57 -0400
Subject: net: xilinx: axienet: Don't print if we go into promiscuous mode

A message about being in promiscuous mode is printed every time each
additional multicast address beyond four is added. Suppress this message
like is done in other drivers.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822154059.1066595-4-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 88ff82c52d0c..f612adb07a25 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -447,7 +447,6 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 		reg = axienet_ior(lp, XAE_FMI_OFFSET);
 		reg |= XAE_FMI_PM_MASK;
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
-		dev_info(&ndev->dev, "Promiscuous mode enabled.\n");
 	} else if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
 
@@ -481,7 +480,6 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 		reg &= ~XAE_FMI_PM_MASK;
 
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
-		dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
 	}
 
 	for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
-- 
cgit v1.3-3-g829e


From 7a826fb3e4c68f42ffdec8361e1fb49cdfbbc991 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 22 Aug 2024 11:40:58 -0400
Subject: net: xilinx: axienet: Don't set IFF_PROMISC in ndev->flags

Contrary to the comment, we don't have to inform the net subsystem.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822154059.1066595-5-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index f612adb07a25..5c4a5949a021 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -439,11 +439,6 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 
 	if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) ||
 	    netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) {
-		/* We must make the kernel realize we had to move into
-		 * promiscuous mode. If it was a promiscuous mode request
-		 * the flag is already set. If not we set it.
-		 */
-		ndev->flags |= IFF_PROMISC;
 		reg = axienet_ior(lp, XAE_FMI_OFFSET);
 		reg |= XAE_FMI_PM_MASK;
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
-- 
cgit v1.3-3-g829e


From 749e67d5b297c01b4825315808c9f1c9e7c91d01 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 22 Aug 2024 11:40:59 -0400
Subject: net: xilinx: axienet: Support IFF_ALLMULTI

Add support for IFF_ALLMULTI by configuring a single filter to match the
multicast address bit. This allows us to keep promiscuous mode disabled,
even when we have more than four multicast addresses. An even better
solution would be to "pack" addresses into the available CAM registers,
but that can wait for a future series.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822154059.1066595-6-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h      |  2 ++
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 34 +++++++++++++----------
 2 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 5a7d6b872f5d..c301dd2ee083 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -175,6 +175,8 @@
 #define XAE_FFE_OFFSET		0x0000070C /* Frame Filter Enable */
 #define XAE_AF0_OFFSET		0x00000710 /* Address Filter 0 */
 #define XAE_AF1_OFFSET		0x00000714 /* Address Filter 1 */
+#define XAE_AM0_OFFSET		0x00000750 /* Frame Filter Mask Value Bytes 3-0 */
+#define XAE_AM1_OFFSET		0x00000754 /* Frame Filter Mask Value Bytes 7-4 */
 
 #define XAE_TX_VLAN_DATA_OFFSET 0x00004000 /* TX VLAN data table address */
 #define XAE_RX_VLAN_DATA_OFFSET 0x00008000 /* RX VLAN data table address */
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 5c4a5949a021..fe6a0e2e463f 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -437,18 +437,27 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 	u32 reg, af0reg, af1reg;
 	struct axienet_local *lp = netdev_priv(ndev);
 
-	if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) ||
-	    netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) {
-		reg = axienet_ior(lp, XAE_FMI_OFFSET);
+	reg = axienet_ior(lp, XAE_FMI_OFFSET);
+	reg &= ~XAE_FMI_PM_MASK;
+	if (ndev->flags & IFF_PROMISC)
 		reg |= XAE_FMI_PM_MASK;
+	else
+		reg &= ~XAE_FMI_PM_MASK;
+	axienet_iow(lp, XAE_FMI_OFFSET, reg);
+
+	if (ndev->flags & IFF_ALLMULTI ||
+	    netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) {
+		reg &= 0xFFFFFF00;
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
+		axienet_iow(lp, XAE_AF0_OFFSET, 1); /* Multicast bit */
+		axienet_iow(lp, XAE_AF1_OFFSET, 0);
+		axienet_iow(lp, XAE_AM0_OFFSET, 1); /* ditto */
+		axienet_iow(lp, XAE_AM1_OFFSET, 0);
+		axienet_iow(lp, XAE_FFE_OFFSET, 1);
+		i = 1;
 	} else if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
 
-		reg = axienet_ior(lp, XAE_FMI_OFFSET);
-		reg &= ~XAE_FMI_PM_MASK;
-		axienet_iow(lp, XAE_FMI_OFFSET, reg);
-
 		netdev_for_each_mc_addr(ha, ndev) {
 			if (i >= XAE_MULTICAST_CAM_TABLE_NUM)
 				break;
@@ -461,24 +470,21 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 			af1reg = (ha->addr[4]);
 			af1reg |= (ha->addr[5] << 8);
 
-			reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
+			reg &= 0xFFFFFF00;
 			reg |= i;
 
 			axienet_iow(lp, XAE_FMI_OFFSET, reg);
 			axienet_iow(lp, XAE_AF0_OFFSET, af0reg);
 			axienet_iow(lp, XAE_AF1_OFFSET, af1reg);
+			axienet_iow(lp, XAE_AM0_OFFSET, 0xffffffff);
+			axienet_iow(lp, XAE_AM1_OFFSET, 0x0000ffff);
 			axienet_iow(lp, XAE_FFE_OFFSET, 1);
 			i++;
 		}
-	} else {
-		reg = axienet_ior(lp, XAE_FMI_OFFSET);
-		reg &= ~XAE_FMI_PM_MASK;
-
-		axienet_iow(lp, XAE_FMI_OFFSET, reg);
 	}
 
 	for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
-		reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
+		reg &= 0xFFFFFF00;
 		reg |= i;
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
 		axienet_iow(lp, XAE_FFE_OFFSET, 0);
-- 
cgit v1.3-3-g829e


From 1461f5a3d810869e182f1d11caaac7dee0458ff7 Mon Sep 17 00:00:00 2001
From: Cong Wang <cong.wang@bytedance.com>
Date: Thu, 22 Aug 2024 11:25:44 -0700
Subject: l2tp: avoid overriding sk->sk_user_data

Although commit 4a4cd70369f1 ("l2tp: don't set sk_user_data in tunnel socket")
removed sk->sk_user_data usage, setup_udp_tunnel_sock() still touches
sk->sk_user_data, this conflicts with sockmap which also leverages
sk->sk_user_data to save psock.

Restore this sk->sk_user_data check to avoid such conflicts.

Fixes: 4a4cd70369f1 ("l2tp: don't set sk_user_data in tunnel socket")
Reported-by: syzbot+8dbe3133b840c470da0e@syzkaller.appspotmail.com
Cc: Tom Parkin <tparkin@katalix.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Tested-by: James Chapman <jchapman@katalix.com>
Reviewed-by: James Chapman <jchapman@katalix.com>
Link: https://patch.msgid.link/20240822182544.378169-1-xiyou.wangcong@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/l2tp/l2tp_core.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index af87c781d6a6..df73c35363cb 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1620,6 +1620,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net,
 	    (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP))
 		return -EPROTONOSUPPORT;
 
+	if (encap == L2TP_ENCAPTYPE_UDP && sk->sk_user_data)
+		return -EBUSY;
+
 	tunnel = l2tp_sk_to_tunnel(sk);
 	if (tunnel) {
 		l2tp_tunnel_put(tunnel);
-- 
cgit v1.3-3-g829e


From d2ab3bb890f6a88facf89494ce50b27ff8236d24 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 22 Aug 2024 12:27:52 -0700
Subject: net: ag71xx: move clk_eth out of struct

It's only used in one place. It doesn't need to be in the struct.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240822192758.141201-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index ee5d429abdaa..bf02bea03a7b 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -381,7 +381,6 @@ struct ag71xx {
 
 	struct reset_control *mdio_reset;
 	struct clk *clk_mdio;
-	struct clk *clk_eth;
 };
 
 static int ag71xx_desc_empty(struct ag71xx_desc *desc)
@@ -1799,6 +1798,7 @@ static int ag71xx_probe(struct platform_device *pdev)
 	const struct ag71xx_dcfg *dcfg;
 	struct net_device *ndev;
 	struct resource *res;
+	struct clk *clk_eth;
 	int tx_size, err, i;
 	struct ag71xx *ag;
 
@@ -1829,10 +1829,10 @@ static int ag71xx_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	ag->clk_eth = devm_clk_get_enabled(&pdev->dev, "eth");
-	if (IS_ERR(ag->clk_eth)) {
+	clk_eth = devm_clk_get_enabled(&pdev->dev, "eth");
+	if (IS_ERR(clk_eth)) {
 		netif_err(ag, probe, ndev, "Failed to get eth clk.\n");
-		return PTR_ERR(ag->clk_eth);
+		return PTR_ERR(clk_eth);
 	}
 
 	SET_NETDEV_DEV(ndev, &pdev->dev);
-- 
cgit v1.3-3-g829e


From ec82fa2c874f2efa55511684494949393d2789aa Mon Sep 17 00:00:00 2001
From: Kyle Swenson <kyle.swenson@est.tech>
Date: Thu, 22 Aug 2024 22:01:21 +0000
Subject: dt-bindings: pse: tps23881: add reset-gpios

The TPS23881 has an active-low reset pin that can be connected to an
SoC.  Document this with the device-tree binding.

Signed-off-by: Kyle Swenson <kyle.swenson@est.tech>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20240822220100.3030184-2-kyle.swenson@est.tech
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml
index 6992d56832bf..d08abcb01211 100644
--- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml
+++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml
@@ -23,6 +23,9 @@ properties:
   '#pse-cells':
     const: 1
 
+  reset-gpios:
+    maxItems: 1
+
   channels:
     description: each set of 8 ports can be assigned to one physical
       channels or two for PoE4. This parameter describes the configuration
-- 
cgit v1.3-3-g829e


From 69f47cad3a05f6cd345afca84f1e66740ff48a2d Mon Sep 17 00:00:00 2001
From: Kyle Swenson <kyle.swenson@est.tech>
Date: Thu, 22 Aug 2024 22:01:22 +0000
Subject: net: pse-pd: tps23881: Support reset-gpios

The TPS23880/1 has an active-low reset pin that some boards connect to
the SoC to control when the TPS23880 is pulled out of reset.

Add support for this via a reset-gpios property in the DTS.

Signed-off-by: Kyle Swenson <kyle.swenson@est.tech>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20240822220100.3030184-3-kyle.swenson@est.tech
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pse-pd/tps23881.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c
index 2ea75686a319..5c4e88be46ee 100644
--- a/drivers/net/pse-pd/tps23881.c
+++ b/drivers/net/pse-pd/tps23881.c
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/firmware.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -737,6 +738,7 @@ static int tps23881_i2c_probe(struct i2c_client *client)
 {
 	struct device *dev = &client->dev;
 	struct tps23881_priv *priv;
+	struct gpio_desc *reset;
 	int ret;
 	u8 val;
 
@@ -749,6 +751,25 @@ static int tps23881_i2c_probe(struct i2c_client *client)
 	if (!priv)
 		return -ENOMEM;
 
+	reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(reset))
+		return dev_err_probe(&client->dev, PTR_ERR(reset), "Failed to get reset GPIO\n");
+
+	if (reset) {
+		/* TPS23880 datasheet (Rev G) indicates minimum reset pulse is 5us */
+		usleep_range(5, 10);
+		gpiod_set_value_cansleep(reset, 0); /* De-assert reset */
+
+		/* TPS23880 datasheet indicates the minimum time after power on reset
+		 * should be 20ms, but the document describing how to load SRAM ("How
+		 * to Load TPS2388x SRAM and Parity Code over I2C" (Rev E))
+		 * indicates we should delay that programming by at least 50ms. So
+		 * we'll wait the entire 50ms here to ensure we're safe to go to the
+		 * SRAM loading proceedure.
+		 */
+		msleep(50);
+	}
+
 	ret = i2c_smbus_read_byte_data(client, TPS23881_REG_DEVID);
 	if (ret < 0)
 		return ret;
-- 
cgit v1.3-3-g829e


From 0d9e5df4a257afc3a471a82961ace9a22b88295a Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 23 Aug 2024 08:11:52 +0800
Subject: tcp: avoid reusing FIN_WAIT2 when trying to find port in connect()
 process

We found that one close-wait socket was reset by the other side
due to a new connection reusing the same port which is beyond our
expectation, so we have to investigate the underlying reason.

The following experiment is conducted in the test environment. We
limit the port range from 40000 to 40010 and delay the time to close()
after receiving a fin from the active close side, which can help us
easily reproduce like what happened in production.

Here are three connections captured by tcpdump:
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965525191
127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 2769915070
127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1
127.0.0.1.40002 > 127.0.0.1.9999: Flags [F.], seq 1, ack 1
// a few seconds later, within 60 seconds
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730
127.0.0.1.9999 > 127.0.0.1.40002: Flags [.], ack 2
127.0.0.1.40002 > 127.0.0.1.9999: Flags [R], seq 2965525193
// later, very quickly
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730
127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 3120990805
127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1

As we can see, the first flow is reset because:
1) client starts a new connection, I mean, the second one
2) client tries to find a suitable port which is a timewait socket
   (its state is timewait, substate is fin_wait2)
3) client occupies that timewait port to send a SYN
4) server finds a corresponding close-wait socket in ehash table,
   then replies with a challenge ack
5) client sends an RST to terminate this old close-wait socket.

I don't think the port selection algo can choose a FIN_WAIT2 socket
when we turn on tcp_tw_reuse because on the server side there
remain unread data. In some cases, if one side haven't call close() yet,
we should not consider it as expendable and treat it at will.

Even though, sometimes, the server isn't able to call close() as soon
as possible like what we expect, it can not be terminated easily,
especially due to a second unrelated connection happening.

After this patch, we can see the expected failure if we start a
connection when all the ports are occupied in fin_wait2 state:
"Ncat: Cannot assign requested address."

Reported-by: Jade Dong <jadedong@tencent.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240823001152.31004-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_ipv4.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a4e510846905..5087e12209a1 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -120,6 +120,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int ts_recent_stamp;
 
+	if (tw->tw_substate == TCP_FIN_WAIT2)
+		reuse = 0;
+
 	if (reuse == 2) {
 		/* Still does not detect *everything* that goes through
 		 * lo, since we require a loopback src or dst address
-- 
cgit v1.3-3-g829e


From 9ceebd7a264798a792a3cf515f4c331704d4c5fb Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Fri, 23 Aug 2024 15:04:53 +0800
Subject: net/ipv4: fix macro definition sk_for_each_bound_bhash

The macro sk_for_each_bound_bhash accepts a parameter
__sk, but it was not used, rather the sk2 is directly
used, so we replace the sk2 with __sk in macro.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240823070453.3327832-1-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inet_connection_sock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 64d07b842e73..ce4d77f49243 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -236,7 +236,7 @@ static bool inet_bhash2_conflict(const struct sock *sk,
 
 #define sk_for_each_bound_bhash(__sk, __tb2, __tb)			\
 	hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node)	\
-		sk_for_each_bound(sk2, &(__tb2)->owners)
+		sk_for_each_bound((__sk), &(__tb2)->owners)
 
 /* This should be called only when the tb and tb2 hashbuckets' locks are held */
 static int inet_csk_bind_conflict(const struct sock *sk,
-- 
cgit v1.3-3-g829e


From 89683b45f15ca5e0064d6dc1c1bfaa8aacc208f5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 23 Aug 2024 14:00:19 +0000
Subject: ipv6: avoid indirect calls for SOL_IP socket options

ipv6_setsockopt() can directly call ip_setsockopt()
instead of going through udp_prot.setsockopt()

ipv6_getsockopt() can directly call ip_getsockopt()
instead of going through udp_prot.getsockopt()

These indirections predate git history, not sure why they
were there.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240823140019.3727643-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ipv6_sockglue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index cd342d5015c6..1e225e6489ea 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -985,7 +985,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 	int err;
 
 	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
-		return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+		return ip_setsockopt(sk, level, optname, optval, optlen);
 
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
@@ -1475,7 +1475,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname,
 	int err;
 
 	if (level == SOL_IP && sk->sk_type != SOCK_RAW)
-		return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+		return ip_getsockopt(sk, level, optname, optval, optlen);
 
 	if (level != SOL_IPV6)
 		return -ENOPROTOOPT;
-- 
cgit v1.3-3-g829e


From 2c163922de69983e6ccedeb5c00dec85b6a17283 Mon Sep 17 00:00:00 2001
From: Xi Huang <xuiagnh@gmail.com>
Date: Thu, 22 Aug 2024 15:20:42 +0800
Subject: net: dpaa: reduce number of synchronize_net() calls

In the function dpaa_napi_del(), we execute the netif_napi_del()
for each cpu, which is actually a high overhead operation
because each call to netif_napi_del() contains a synchronize_net(),
i.e. an RCU operation. In fact, it is only necessary to call
 __netif_napi_del and use synchronize_net() once outside of the loop.
This change is similar to commit 2543a6000e593a ("gro_cells: reduce
number of synchronize_net() calls") and commit 5198d545dba8ad (" net:
remove napi_hash_del() from driver-facing API") 5198d545db.

Signed-off-by: Xi Huang <xuiagnh@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240822072042.42750-1-xuiagnh@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index cfe6b57b1da0..5d99cfb4e994 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -3156,8 +3156,9 @@ static void dpaa_napi_del(struct net_device *net_dev)
 	for_each_possible_cpu(cpu) {
 		percpu_priv = per_cpu_ptr(priv->percpu_priv, cpu);
 
-		netif_napi_del(&percpu_priv->np.napi);
+		__netif_napi_del(&percpu_priv->np.napi);
 	}
+	synchronize_net();
 }
 
 static inline void dpaa_bp_free_pf(const struct dpaa_bp *bp,
-- 
cgit v1.3-3-g829e


From cda1fba15cb2282b3c364805c9767698f11c3b0e Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 23 Aug 2024 00:25:12 +0200
Subject: dpll: add Embedded SYNC feature for a pin

Implement and document new pin attributes for providing Embedded SYNC
capabilities to the DPLL subsystem users through a netlink pin-get
do/dump messages. Allow the user to set Embedded SYNC frequency with
pin-set do netlink message.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20240822222513.255179-2-arkadiusz.kubalewski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/driver-api/dpll.rst     |  21 ++++++
 Documentation/netlink/specs/dpll.yaml |  24 +++++++
 drivers/dpll/dpll_netlink.c           | 130 ++++++++++++++++++++++++++++++++++
 drivers/dpll/dpll_nl.c                |   5 +-
 include/linux/dpll.h                  |  15 ++++
 include/uapi/linux/dpll.h             |   3 +
 6 files changed, 196 insertions(+), 2 deletions(-)

diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst
index ea8d16600e16..e6855cd37e85 100644
--- a/Documentation/driver-api/dpll.rst
+++ b/Documentation/driver-api/dpll.rst
@@ -214,6 +214,27 @@ offset values are fractional with 3-digit decimal places and shell be
 divided with ``DPLL_PIN_PHASE_OFFSET_DIVIDER`` to get integer part and
 modulo divided to get fractional part.
 
+Embedded SYNC
+=============
+
+Device may provide ability to use Embedded SYNC feature. It allows
+to embed additional SYNC signal into the base frequency of a pin - a one
+special pulse of base frequency signal every time SYNC signal pulse
+happens. The user can configure the frequency of Embedded SYNC.
+The Embedded SYNC capability is always related to a given base frequency
+and HW capabilities. The user is provided a range of Embedded SYNC
+frequencies supported, depending on current base frequency configured for
+the pin.
+
+  ========================================= =================================
+  ``DPLL_A_PIN_ESYNC_FREQUENCY``            current Embedded SYNC frequency
+  ``DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED``  nest available Embedded SYNC
+                                            frequency ranges
+    ``DPLL_A_PIN_FREQUENCY_MIN``            attr minimum value of frequency
+    ``DPLL_A_PIN_FREQUENCY_MAX``            attr maximum value of frequency
+  ``DPLL_A_PIN_ESYNC_PULSE``                pulse type of Embedded SYNC
+  ========================================= =================================
+
 Configuration commands group
 ============================
 
diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index 94132d30e0e0..f2894ca35de8 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -345,6 +345,26 @@ attribute-sets:
           Value is in PPM (parts per million).
           This may be implemented for example for pin of type
           PIN_TYPE_SYNCE_ETH_PORT.
+      -
+        name: esync-frequency
+        type: u64
+        doc: |
+          Frequency of Embedded SYNC signal. If provided, the pin is configured
+          with a SYNC signal embedded into its base clock frequency.
+      -
+        name: esync-frequency-supported
+        type: nest
+        multi-attr: true
+        nested-attributes: frequency-range
+        doc: |
+          If provided a pin is capable of embedding a SYNC signal (within given
+          range) into its base frequency signal.
+      -
+        name: esync-pulse
+        type: u32
+        doc: |
+          A ratio of high to low state of a SYNC signal pulse embedded
+          into base clock frequency. Value is in percents.
   -
     name: pin-parent-device
     subset-of: pin
@@ -510,6 +530,9 @@ operations:
             - phase-adjust-max
             - phase-adjust
             - fractional-frequency-offset
+            - esync-frequency
+            - esync-frequency-supported
+            - esync-pulse
 
       dump:
         request:
@@ -536,6 +559,7 @@ operations:
             - parent-device
             - parent-pin
             - phase-adjust
+            - esync-frequency
     -
       name: pin-create-ntf
       doc: Notification about pin appearing
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 98e6ad8528d3..fc0280dcddd1 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -342,6 +342,51 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin,
 	return 0;
 }
 
+static int
+dpll_msg_add_pin_esync(struct sk_buff *msg, struct dpll_pin *pin,
+		       struct dpll_pin_ref *ref, struct netlink_ext_ack *extack)
+{
+	const struct dpll_pin_ops *ops = dpll_pin_ops(ref);
+	struct dpll_device *dpll = ref->dpll;
+	struct dpll_pin_esync esync;
+	struct nlattr *nest;
+	int ret, i;
+
+	if (!ops->esync_get)
+		return 0;
+	ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll,
+			     dpll_priv(dpll), &esync, extack);
+	if (ret == -EOPNOTSUPP)
+		return 0;
+	else if (ret)
+		return ret;
+	if (nla_put_64bit(msg, DPLL_A_PIN_ESYNC_FREQUENCY, sizeof(esync.freq),
+			  &esync.freq, DPLL_A_PIN_PAD))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, DPLL_A_PIN_ESYNC_PULSE, esync.pulse))
+		return -EMSGSIZE;
+	for (i = 0; i < esync.range_num; i++) {
+		nest = nla_nest_start(msg,
+				      DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED);
+		if (!nest)
+			return -EMSGSIZE;
+		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN,
+				  sizeof(esync.range[i].min),
+				  &esync.range[i].min, DPLL_A_PIN_PAD))
+			goto nest_cancel;
+		if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX,
+				  sizeof(esync.range[i].max),
+				  &esync.range[i].max, DPLL_A_PIN_PAD))
+			goto nest_cancel;
+		nla_nest_end(msg, nest);
+	}
+	return 0;
+
+nest_cancel:
+	nla_nest_cancel(msg, nest);
+	return -EMSGSIZE;
+}
+
 static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq)
 {
 	int fs;
@@ -481,6 +526,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 	if (ret)
 		return ret;
 	ret = dpll_msg_add_ffo(msg, pin, ref, extack);
+	if (ret)
+		return ret;
+	ret = dpll_msg_add_pin_esync(msg, pin, ref, extack);
 	if (ret)
 		return ret;
 	if (xa_empty(&pin->parent_refs))
@@ -738,6 +786,83 @@ rollback:
 	return ret;
 }
 
+static int
+dpll_pin_esync_set(struct dpll_pin *pin, struct nlattr *a,
+		   struct netlink_ext_ack *extack)
+{
+	struct dpll_pin_ref *ref, *failed;
+	const struct dpll_pin_ops *ops;
+	struct dpll_pin_esync esync;
+	u64 freq = nla_get_u64(a);
+	struct dpll_device *dpll;
+	bool supported = false;
+	unsigned long i;
+	int ret;
+
+	xa_for_each(&pin->dpll_refs, i, ref) {
+		ops = dpll_pin_ops(ref);
+		if (!ops->esync_set || !ops->esync_get) {
+			NL_SET_ERR_MSG(extack,
+				       "embedded sync feature is not supported by this device");
+			return -EOPNOTSUPP;
+		}
+	}
+	ref = dpll_xa_ref_dpll_first(&pin->dpll_refs);
+	ops = dpll_pin_ops(ref);
+	dpll = ref->dpll;
+	ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll,
+			     dpll_priv(dpll), &esync, extack);
+	if (ret) {
+		NL_SET_ERR_MSG(extack, "unable to get current embedded sync frequency value");
+		return ret;
+	}
+	if (freq == esync.freq)
+		return 0;
+	for (i = 0; i < esync.range_num; i++)
+		if (freq <= esync.range[i].max && freq >= esync.range[i].min)
+			supported = true;
+	if (!supported) {
+		NL_SET_ERR_MSG_ATTR(extack, a,
+				    "requested embedded sync frequency value is not supported by this device");
+		return -EINVAL;
+	}
+
+	xa_for_each(&pin->dpll_refs, i, ref) {
+		void *pin_dpll_priv;
+
+		ops = dpll_pin_ops(ref);
+		dpll = ref->dpll;
+		pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin);
+		ret = ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll),
+				      freq, extack);
+		if (ret) {
+			failed = ref;
+			NL_SET_ERR_MSG_FMT(extack,
+					   "embedded sync frequency set failed for dpll_id: %u",
+					   dpll->id);
+			goto rollback;
+		}
+	}
+	__dpll_pin_change_ntf(pin);
+
+	return 0;
+
+rollback:
+	xa_for_each(&pin->dpll_refs, i, ref) {
+		void *pin_dpll_priv;
+
+		if (ref == failed)
+			break;
+		ops = dpll_pin_ops(ref);
+		dpll = ref->dpll;
+		pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin);
+		if (ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll),
+				   esync.freq, extack))
+			NL_SET_ERR_MSG(extack, "set embedded sync frequency rollback failed");
+	}
+	return ret;
+}
+
 static int
 dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx,
 			  enum dpll_pin_state state,
@@ -1039,6 +1164,11 @@ dpll_pin_set_from_nlattr(struct dpll_pin *pin, struct genl_info *info)
 			if (ret)
 				return ret;
 			break;
+		case DPLL_A_PIN_ESYNC_FREQUENCY:
+			ret = dpll_pin_esync_set(pin, a, info->extack);
+			if (ret)
+				return ret;
+			break;
 		}
 	}
 
diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c
index 1e95f5397cfc..fe9b6893d261 100644
--- a/drivers/dpll/dpll_nl.c
+++ b/drivers/dpll/dpll_nl.c
@@ -62,7 +62,7 @@ static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] =
 };
 
 /* DPLL_CMD_PIN_SET - do */
-static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + 1] = {
+static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_ESYNC_FREQUENCY + 1] = {
 	[DPLL_A_PIN_ID] = { .type = NLA_U32, },
 	[DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, },
 	[DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2),
@@ -71,6 +71,7 @@ static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST +
 	[DPLL_A_PIN_PARENT_DEVICE] = NLA_POLICY_NESTED(dpll_pin_parent_device_nl_policy),
 	[DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy),
 	[DPLL_A_PIN_PHASE_ADJUST] = { .type = NLA_S32, },
+	[DPLL_A_PIN_ESYNC_FREQUENCY] = { .type = NLA_U64, },
 };
 
 /* Ops table for dpll */
@@ -138,7 +139,7 @@ static const struct genl_split_ops dpll_nl_ops[] = {
 		.doit		= dpll_nl_pin_set_doit,
 		.post_doit	= dpll_pin_post_doit,
 		.policy		= dpll_pin_set_nl_policy,
-		.maxattr	= DPLL_A_PIN_PHASE_ADJUST,
+		.maxattr	= DPLL_A_PIN_ESYNC_FREQUENCY,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 };
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index d275736230b3..81f7b623d0ba 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -15,6 +15,7 @@
 
 struct dpll_device;
 struct dpll_pin;
+struct dpll_pin_esync;
 
 struct dpll_device_ops {
 	int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv,
@@ -83,6 +84,13 @@ struct dpll_pin_ops {
 	int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv,
 		       const struct dpll_device *dpll, void *dpll_priv,
 		       s64 *ffo, struct netlink_ext_ack *extack);
+	int (*esync_set)(const struct dpll_pin *pin, void *pin_priv,
+			 const struct dpll_device *dpll, void *dpll_priv,
+			 u64 freq, struct netlink_ext_ack *extack);
+	int (*esync_get)(const struct dpll_pin *pin, void *pin_priv,
+			 const struct dpll_device *dpll, void *dpll_priv,
+			 struct dpll_pin_esync *esync,
+			 struct netlink_ext_ack *extack);
 };
 
 struct dpll_pin_frequency {
@@ -111,6 +119,13 @@ struct dpll_pin_phase_adjust_range {
 	s32 max;
 };
 
+struct dpll_pin_esync {
+	u64 freq;
+	const struct dpll_pin_frequency *range;
+	u8 range_num;
+	u8 pulse;
+};
+
 struct dpll_pin_properties {
 	const char *board_label;
 	const char *panel_label;
diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h
index 0c13d7f1a1bc..b0654ade7b7e 100644
--- a/include/uapi/linux/dpll.h
+++ b/include/uapi/linux/dpll.h
@@ -210,6 +210,9 @@ enum dpll_a_pin {
 	DPLL_A_PIN_PHASE_ADJUST,
 	DPLL_A_PIN_PHASE_OFFSET,
 	DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET,
+	DPLL_A_PIN_ESYNC_FREQUENCY,
+	DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED,
+	DPLL_A_PIN_ESYNC_PULSE,
 
 	__DPLL_A_PIN_MAX,
 	DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1)
-- 
cgit v1.3-3-g829e


From 87abc5666ab753e8c31a2d39df3b5233f4e47b43 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Fri, 23 Aug 2024 00:25:13 +0200
Subject: ice: add callbacks for Embedded SYNC enablement on dpll pins

Allow the user to get and set configuration of Embedded SYNC feature
on the ice driver dpll pins.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20240822222513.255179-3-arkadiusz.kubalewski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_dpll.c | 223 +++++++++++++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_dpll.h |   1 +
 2 files changed, 221 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index e92be6f130a3..cd95705d1e7f 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -9,6 +9,7 @@
 #define ICE_CGU_STATE_ACQ_ERR_THRESHOLD		50
 #define ICE_DPLL_PIN_IDX_INVALID		0xff
 #define ICE_DPLL_RCLK_NUM_PER_PF		1
+#define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT	25
 
 /**
  * enum ice_dpll_pin_type - enumerate ice pin types:
@@ -30,6 +31,10 @@ static const char * const pin_type_name[] = {
 	[ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input",
 };
 
+static const struct dpll_pin_frequency ice_esync_range[] = {
+	DPLL_PIN_FREQUENCY_RANGE(0, DPLL_PIN_FREQUENCY_1_HZ),
+};
+
 /**
  * ice_dpll_is_reset - check if reset is in progress
  * @pf: private board structure
@@ -394,8 +399,8 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 
 	switch (pin_type) {
 	case ICE_DPLL_PIN_TYPE_INPUT:
-		ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL,
-					       NULL, &pin->flags[0],
+		ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, &pin->status,
+					       NULL, NULL, &pin->flags[0],
 					       &pin->freq, &pin->phase_adjust);
 		if (ret)
 			goto err;
@@ -430,7 +435,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 			goto err;
 
 		parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL;
-		if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) {
+		if (ICE_AQC_GET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) {
 			pin->state[pf->dplls.eec.dpll_idx] =
 				parent == pf->dplls.eec.dpll_idx ?
 				DPLL_PIN_STATE_CONNECTED :
@@ -1098,6 +1103,214 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv,
 	return 0;
 }
 
+/**
+ * ice_dpll_output_esync_set - callback for setting embedded sync
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @freq: requested embedded sync frequency
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting embedded sync frequency value
+ * on output pin.
+ *
+ * Context: Acquires pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_output_esync_set(const struct dpll_pin *pin, void *pin_priv,
+			  const struct dpll_device *dpll, void *dpll_priv,
+			  u64 freq, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+	u8 flags = 0;
+	int ret;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_OUT_EN)
+		flags = ICE_AQC_SET_CGU_OUT_CFG_OUT_EN;
+	if (freq == DPLL_PIN_FREQUENCY_1_HZ) {
+		if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) {
+			ret = 0;
+		} else {
+			flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN;
+			ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags,
+							0, 0, 0);
+		}
+	} else {
+		if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN)) {
+			ret = 0;
+		} else {
+			flags &= ~ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN;
+			ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags,
+							0, 0, 0);
+		}
+	}
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_output_esync_get - callback for getting embedded sync config
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @esync: on success holds embedded sync pin properties
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for getting embedded sync frequency value
+ * and capabilities on output pin.
+ *
+ * Context: Acquires pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_output_esync_get(const struct dpll_pin *pin, void *pin_priv,
+			  const struct dpll_device *dpll, void *dpll_priv,
+			  struct dpll_pin_esync *esync,
+			  struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_ABILITY) ||
+	    p->freq != DPLL_PIN_FREQUENCY_10_MHZ) {
+		mutex_unlock(&pf->dplls.lock);
+		return -EOPNOTSUPP;
+	}
+	esync->range = ice_esync_range;
+	esync->range_num = ARRAY_SIZE(ice_esync_range);
+	if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) {
+		esync->freq = DPLL_PIN_FREQUENCY_1_HZ;
+		esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT;
+	} else {
+		esync->freq = 0;
+		esync->pulse = 0;
+	}
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
+/**
+ * ice_dpll_input_esync_set - callback for setting embedded sync
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @freq: requested embedded sync frequency
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for setting embedded sync frequency value
+ * on input pin.
+ *
+ * Context: Acquires pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_input_esync_set(const struct dpll_pin *pin, void *pin_priv,
+			 const struct dpll_device *dpll, void *dpll_priv,
+			 u64 freq, struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+	u8 flags_en = 0;
+	int ret;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN)
+		flags_en = ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN;
+	if (freq == DPLL_PIN_FREQUENCY_1_HZ) {
+		if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) {
+			ret = 0;
+		} else {
+			flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN;
+			ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0,
+						       flags_en, 0, 0);
+		}
+	} else {
+		if (!(p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN)) {
+			ret = 0;
+		} else {
+			flags_en &= ~ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN;
+			ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0,
+						       flags_en, 0, 0);
+		}
+	}
+	mutex_unlock(&pf->dplls.lock);
+
+	return ret;
+}
+
+/**
+ * ice_dpll_input_esync_get - callback for getting embedded sync config
+ * @pin: pointer to a pin
+ * @pin_priv: private data pointer passed on pin registration
+ * @dpll: registered dpll pointer
+ * @dpll_priv: private data pointer passed on dpll registration
+ * @esync: on success holds embedded sync pin properties
+ * @extack: error reporting
+ *
+ * Dpll subsystem callback. Handler for getting embedded sync frequency value
+ * and capabilities on input pin.
+ *
+ * Context: Acquires pf->dplls.lock
+ * Return:
+ * * 0 - success
+ * * negative - error
+ */
+static int
+ice_dpll_input_esync_get(const struct dpll_pin *pin, void *pin_priv,
+			 const struct dpll_device *dpll, void *dpll_priv,
+			 struct dpll_pin_esync *esync,
+			 struct netlink_ext_ack *extack)
+{
+	struct ice_dpll_pin *p = pin_priv;
+	struct ice_dpll *d = dpll_priv;
+	struct ice_pf *pf = d->pf;
+
+	if (ice_dpll_is_reset(pf, extack))
+		return -EBUSY;
+	mutex_lock(&pf->dplls.lock);
+	if (!(p->status & ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_CAP) ||
+	    p->freq != DPLL_PIN_FREQUENCY_10_MHZ) {
+		mutex_unlock(&pf->dplls.lock);
+		return -EOPNOTSUPP;
+	}
+	esync->range = ice_esync_range;
+	esync->range_num = ARRAY_SIZE(ice_esync_range);
+	if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) {
+		esync->freq = DPLL_PIN_FREQUENCY_1_HZ;
+		esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT;
+	} else {
+		esync->freq = 0;
+		esync->pulse = 0;
+	}
+	mutex_unlock(&pf->dplls.lock);
+
+	return 0;
+}
+
 /**
  * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin
  * @pin: pointer to a pin
@@ -1222,6 +1435,8 @@ static const struct dpll_pin_ops ice_dpll_input_ops = {
 	.phase_adjust_get = ice_dpll_pin_phase_adjust_get,
 	.phase_adjust_set = ice_dpll_input_phase_adjust_set,
 	.phase_offset_get = ice_dpll_phase_offset_get,
+	.esync_set = ice_dpll_input_esync_set,
+	.esync_get = ice_dpll_input_esync_get,
 };
 
 static const struct dpll_pin_ops ice_dpll_output_ops = {
@@ -1232,6 +1447,8 @@ static const struct dpll_pin_ops ice_dpll_output_ops = {
 	.direction_get = ice_dpll_output_direction,
 	.phase_adjust_get = ice_dpll_pin_phase_adjust_get,
 	.phase_adjust_set = ice_dpll_output_phase_adjust_set,
+	.esync_set = ice_dpll_output_esync_set,
+	.esync_get = ice_dpll_output_esync_get,
 };
 
 static const struct dpll_device_ops ice_dpll_ops = {
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h
index 93172e93995b..c320f1bf7d6d 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.h
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.h
@@ -31,6 +31,7 @@ struct ice_dpll_pin {
 	struct dpll_pin_properties prop;
 	u32 freq;
 	s32 phase_adjust;
+	u8 status;
 };
 
 /** ice_dpll - store info required for DPLL control
-- 
cgit v1.3-3-g829e


From 7c31f102030f938a24ec7ebd321fcf5953718935 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:17 +0800
Subject: wifi: rtw89: pass chan to rfk_band_changed()

Originally, all chips have implemented rfk_band_changed() and access chan
with hard-code RTW89_CHANCTX_0 in it. But, it's problematic when the chip
supports multiple channels.

So, change the prototype of rfk_band_changed() and pass chan ahead. And,
we will refine the implementation of each chip in the following.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c      | 2 +-
 drivers/net/wireless/realtek/rtw89/core.h      | 8 +++++---
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  | 3 ++-
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  | 3 ++-
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  | 3 ++-
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 3 ++-
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  | 3 ++-
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  | 3 ++-
 8 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 885c759e694a..87e649272b2e 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -429,7 +429,7 @@ int rtw89_set_channel(struct rtw89_dev *rtwdev)
 
 	if (!entity_active || chan_rcd->band_changed) {
 		rtw89_btc_ntfy_switch_band(rtwdev, phy_idx, chan->band_type);
-		rtw89_chip_rfk_band_changed(rtwdev, phy_idx);
+		rtw89_chip_rfk_band_changed(rtwdev, phy_idx, chan);
 	}
 
 	rtw89_set_entity_state(rtwdev, true);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 0410f6d4bb65..1e83c44e05fe 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3595,7 +3595,8 @@ struct rtw89_chip_ops {
 	void (*rfk_init_late)(struct rtw89_dev *rtwdev);
 	void (*rfk_channel)(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
 	void (*rfk_band_changed)(struct rtw89_dev *rtwdev,
-				 enum rtw89_phy_idx phy_idx);
+				 enum rtw89_phy_idx phy_idx,
+				 const struct rtw89_chan *chan);
 	void (*rfk_scan)(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			 bool start);
 	void (*rfk_track)(struct rtw89_dev *rtwdev);
@@ -6227,12 +6228,13 @@ static inline void rtw89_chip_rfk_channel(struct rtw89_dev *rtwdev,
 }
 
 static inline void rtw89_chip_rfk_band_changed(struct rtw89_dev *rtwdev,
-					       enum rtw89_phy_idx phy_idx)
+					       enum rtw89_phy_idx phy_idx,
+					       const struct rtw89_chan *chan)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 
 	if (chip->ops->rfk_band_changed)
-		chip->ops->rfk_band_changed(rtwdev, phy_idx);
+		chip->ops->rfk_band_changed(rtwdev, phy_idx, chan);
 }
 
 static inline void rtw89_chip_rfk_scan(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index d1358b9a73f9..d5e42b2ad9ac 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -1601,7 +1601,8 @@ static void rtw8851b_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtw
 }
 
 static void rtw8851b_rfk_band_changed(struct rtw89_dev *rtwdev,
-				      enum rtw89_phy_idx phy_idx)
+				      enum rtw89_phy_idx phy_idx,
+				      const struct rtw89_chan *chan)
 {
 	rtw8851b_tssi_scan(rtwdev, phy_idx);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 1cbea8d665a2..365f074108d4 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -1361,7 +1361,8 @@ static void rtw8852a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtw
 }
 
 static void rtw8852a_rfk_band_changed(struct rtw89_dev *rtwdev,
-				      enum rtw89_phy_idx phy_idx)
+				      enum rtw89_phy_idx phy_idx,
+				      const struct rtw89_chan *chan)
 {
 	rtw8852a_tssi_scan(rtwdev, phy_idx);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 36a81c3323f8..d055847d2de4 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -573,7 +573,8 @@ static void rtw8852b_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtw
 }
 
 static void rtw8852b_rfk_band_changed(struct rtw89_dev *rtwdev,
-				      enum rtw89_phy_idx phy_idx)
+				      enum rtw89_phy_idx phy_idx,
+				      const struct rtw89_chan *chan)
 {
 	rtw8852b_tssi_scan(rtwdev, phy_idx);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 647bc98bcc5d..5eb38370aba4 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -546,7 +546,8 @@ static void rtw8852bt_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rt
 }
 
 static void rtw8852bt_rfk_band_changed(struct rtw89_dev *rtwdev,
-				       enum rtw89_phy_idx phy_idx)
+				       enum rtw89_phy_idx phy_idx,
+				       const struct rtw89_chan *chan)
 {
 	rtw8852bt_tssi_scan(rtwdev, phy_idx);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 65e61a2ede27..1fde8a07f73c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -1859,7 +1859,8 @@ static void rtw8852c_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtw
 }
 
 static void rtw8852c_rfk_band_changed(struct rtw89_dev *rtwdev,
-				      enum rtw89_phy_idx phy_idx)
+				      enum rtw89_phy_idx phy_idx,
+				      const struct rtw89_chan *chan)
 {
 	rtw8852c_tssi_scan(rtwdev, phy_idx);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 7f4ac8b63e48..d67bbbffb94e 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2040,7 +2040,8 @@ static void rtw8922a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtw
 }
 
 static void rtw8922a_rfk_band_changed(struct rtw89_dev *rtwdev,
-				      enum rtw89_phy_idx phy_idx)
+				      enum rtw89_phy_idx phy_idx,
+				      const struct rtw89_chan *chan)
 {
 	rtw89_phy_rfk_tssi_and_wait(rtwdev, phy_idx, RTW89_TSSI_SCAN, 6);
 }
-- 
cgit v1.3-3-g829e


From e3a2f20991feecd8ccfefcfcdb62339e6c6bb903 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:18 +0800
Subject: wifi: rtw89: 8851b: use right chanctx whenever possible in RFK flow

No longer access chan with hard-code RTW89_CHANCTX_X whenever possible.
Instead, obtain the right chanctx from somewhere and use it in RTL8851B
RFK (RF calibration) related code.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8851b.c     |  15 +--
 drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c | 138 ++++++++++++----------
 drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.h |  18 ++-
 3 files changed, 93 insertions(+), 78 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index d5e42b2ad9ac..c2fa8e270a4b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -1587,30 +1587,31 @@ static void rtw8851b_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8851b_aack(rtwdev);
 	rtw8851b_rck(rtwdev);
 	rtw8851b_dack(rtwdev);
-	rtw8851b_rx_dck(rtwdev, RTW89_PHY_0);
+	rtw8851b_rx_dck(rtwdev, RTW89_PHY_0, RTW89_CHANCTX_0);
 }
 
 static void rtw8851b_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	enum rtw89_chanctx_idx chanctx_idx = rtwvif->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
-	rtw8851b_rx_dck(rtwdev, phy_idx);
-	rtw8851b_iqk(rtwdev, phy_idx);
-	rtw8851b_tssi(rtwdev, phy_idx, true);
-	rtw8851b_dpk(rtwdev, phy_idx);
+	rtw8851b_rx_dck(rtwdev, phy_idx, chanctx_idx);
+	rtw8851b_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw8851b_tssi(rtwdev, phy_idx, true, chanctx_idx);
+	rtw8851b_dpk(rtwdev, phy_idx, chanctx_idx);
 }
 
 static void rtw8851b_rfk_band_changed(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_idx phy_idx,
 				      const struct rtw89_chan *chan)
 {
-	rtw8851b_tssi_scan(rtwdev, phy_idx);
+	rtw8851b_tssi_scan(rtwdev, phy_idx, chan);
 }
 
 static void rtw8851b_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			      bool start)
 {
-	rtw8851b_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
+	rtw8851b_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx, rtwvif->chanctx_idx);
 }
 
 static void rtw8851b_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
index 7942f334066c..364e36354225 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.c
@@ -521,9 +521,10 @@ static void _dac_cal(struct rtw89_dev *rtwdev, bool force)
 }
 
 static void _rx_dck_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			 enum rtw89_rf_path path, bool is_afe)
+			 enum rtw89_rf_path path, bool is_afe,
+			 enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[RX_DCK] ==== S%d RX DCK (%s / CH%d / %s / by %s)====\n", path,
@@ -574,7 +575,8 @@ static void _set_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_rf_path path, u8 rf
 	_rxbb_ofst_swap(rtwdev, path, rf_mode);
 }
 
-static void _rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_afe)
+static void _rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_afe,
+		    enum rtw89_chanctx_idx chanctx_idx)
 {
 	u32 rf_reg5;
 	u8 path;
@@ -584,7 +586,7 @@ static void _rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_af
 		    0x2, rtwdev->hal.cv);
 
 	for (path = 0; path < RF_PATH_NUM_8851B; path++) {
-		_rx_dck_info(rtwdev, phy, path, is_afe);
+		_rx_dck_info(rtwdev, phy, path, is_afe, chanctx_idx);
 
 		rf_reg5 = rtw89_read_rf(rtwdev, path, RR_RSV1, RFREG_MASK);
 
@@ -1481,9 +1483,9 @@ static void _rfk_restore_rf_reg(struct rtw89_dev *rtwdev,
 }
 
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     u8 path)
+			     u8 path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 idx = 0;
 
@@ -1586,10 +1588,11 @@ static void _iqk_init(struct rtw89_dev *rtwdev)
 }
 
 static void _doiqk(struct rtw89_dev *rtwdev, bool force,
-		   enum rtw89_phy_idx phy_idx, u8 path)
+		   enum rtw89_phy_idx phy_idx, u8 path,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, chanctx_idx);
 	u32 backup_rf_val[RTW8851B_IQK_SS][BACKUP_RF_REGS_NR];
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 
@@ -1602,7 +1605,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	iqk_info->version = RTW8851B_IQK_VER;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]Test Ver 0x%x\n", iqk_info->version);
-	_iqk_get_ch_info(rtwdev, phy_idx, path);
+	_iqk_get_ch_info(rtwdev, phy_idx, path, chanctx_idx);
 
 	_rfk_backup_bb_reg(rtwdev, &backup_bb_val[0]);
 	_rfk_backup_rf_reg(rtwdev, &backup_rf_val[path][0], path);
@@ -1618,9 +1621,10 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 			      BTC_WRFK_ONESHOT_STOP);
 }
 
-static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force)
+static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		 bool force, enum rtw89_chanctx_idx chanctx_idx)
 {
-	_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
+	_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
 }
 
 static void _dpk_bkup_kip(struct rtw89_dev *rtwdev, const u32 *reg,
@@ -1746,9 +1750,9 @@ static void _dpk_init(struct rtw89_dev *rtwdev, enum rtw89_rf_path path)
 }
 
 static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -2449,7 +2453,8 @@ _error:
 }
 
 static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
-			    enum rtw89_phy_idx phy, u8 kpath)
+			    enum rtw89_phy_idx phy, u8 kpath,
+			    enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u32 kip_bkup[RF_PATH_NUM_8851B][DPK_KIP_REG_NUM_8851B] = {};
@@ -2465,7 +2470,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 			continue;
 		_dpk_bkup_kip(rtwdev, dpk_kip_reg, kip_bkup, path);
 		_dpk_bkup_rf(rtwdev, dpk_rf_reg, rf_bkup, path);
-		_dpk_information(rtwdev, phy, path);
+		_dpk_information(rtwdev, phy, path, chanctx_idx);
 		_dpk_init(rtwdev, path);
 
 		if (rtwdev->is_tssi_mode[path])
@@ -2505,13 +2510,14 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 	_dpk_kip_pwr_clk_onoff(rtwdev, false);
 }
 
-static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force)
+static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[DPK] ****** 8851B DPK Start (Ver: 0x%x, Cv: %d) ******\n",
 		    DPK_VER_8851B, rtwdev->hal.cv);
 
-	_dpk_cal_select(rtwdev, force, phy, _kpath(rtwdev, phy));
+	_dpk_cal_select(rtwdev, force, phy, _kpath(rtwdev, phy), chanctx_idx);
 }
 
 static void _dpk_track(struct rtw89_dev *rtwdev)
@@ -2617,9 +2623,8 @@ static void _rck(struct rtw89_dev *rtwdev, enum rtw89_rf_path path)
 }
 
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			  enum rtw89_rf_path path)
+			  enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8851b_tssi_sys_defs_tbl);
@@ -2650,7 +2655,7 @@ static void _tssi_set_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 #define RTW8851B_TSSI_GET_VAL(ptr, idx)			\
 ({							\
@@ -2664,7 +2669,6 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -2755,9 +2759,8 @@ static void _tssi_set_dac_gain_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 }
 
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				enum rtw89_rf_path path)
+				enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser_by_cond(rtwdev, band == RTW89_BAND_2G,
@@ -2766,9 +2769,9 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 }
 
 static void _tssi_alignment_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				    enum rtw89_rf_path path, bool all)
+				    enum rtw89_rf_path path, bool all,
+				    const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser_by_cond(rtwdev, band == RTW89_BAND_2G,
@@ -2944,10 +2947,9 @@ static u32 _tssi_get_trim_group(struct rtw89_dev *rtwdev, u8 ch)
 }
 
 static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			    enum rtw89_rf_path path)
+			    enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 gidx, gidx_1st, gidx_2nd;
 	u8 ch = chan->channel;
 	s8 de_1st;
@@ -2980,10 +2982,9 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	u8 ch = chan->channel;
 	s8 tde_1st;
@@ -3017,10 +3018,10 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	return val;
 }
 
-static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+				  const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3033,7 +3034,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx p
 
 	for (i = RF_PATH_A; i < RTW8851B_TSSI_PATH_NR; i++) {
 		gidx = _tssi_get_cck_group(rtwdev, ch);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = tssi_info->tssi_cck[i][gidx] + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3049,8 +3050,8 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx p
 			    rtw89_phy_read32_mask(rtwdev, _tssi_de_cck_long[i],
 						  _TSSI_DE_MASK));
 
-		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i, chan);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = ofdm_de + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3096,10 +3097,10 @@ static void _tssi_alimentk_dump_result(struct rtw89_dev *rtwdev, enum rtw89_rf_p
 }
 
 static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
-				enum rtw89_phy_idx phy, enum rtw89_rf_path path)
+				enum rtw89_phy_idx phy, enum rtw89_rf_path path,
+				const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u8 band;
 
@@ -3255,9 +3256,10 @@ void rtw8851b_dack(struct rtw89_dev *rtwdev)
 	_dac_cal(rtwdev, false);
 }
 
-void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
@@ -3265,30 +3267,32 @@ void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
 	_iqk_init(rtwdev);
-	_iqk(rtwdev, phy_idx, false);
+	_iqk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_STOP);
 }
 
-void rtw8851b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8851b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		     enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
-	_rx_dck(rtwdev, phy_idx, false);
+	_rx_dck(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_STOP);
 }
 
-void rtw8851b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8851b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
@@ -3297,7 +3301,7 @@ void rtw8851b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 	rtwdev->dpk.is_dpk_enable = true;
 	rtwdev->dpk.is_dpk_reload_en = false;
-	_dpk(rtwdev, phy_idx, false);
+	_dpk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_STOP);
@@ -3308,9 +3312,11 @@ void rtw8851b_dpk_track(struct rtw89_dev *rtwdev)
 	_dpk_track(rtwdev);
 }
 
-void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en)
+void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   bool hwtx_en, enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_A, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_A, chanctx_idx);
 	u8 i;
 
 	rtw89_debug(rtwdev, RTW89_DBG_TSSI, "[TSSI] %s: phy=%d\n", __func__, phy);
@@ -3319,26 +3325,26 @@ void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_e
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8851B; i++) {
-		_tssi_set_sys(rtwdev, phy, i);
+		_tssi_set_sys(rtwdev, phy, i, chan);
 		_tssi_ini_txpwr_ctrl_bb(rtwdev, phy, i);
 		_tssi_ini_txpwr_ctrl_bb_he_tb(rtwdev, phy, i);
 		_tssi_set_dck(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
 		_tssi_set_dac_gain_tbl(rtwdev, phy, i);
-		_tssi_slope_cal_org(rtwdev, phy, i);
-		_tssi_alignment_default(rtwdev, phy, i, true);
+		_tssi_slope_cal_org(rtwdev, phy, i, chan);
+		_tssi_alignment_default(rtwdev, phy, i, true, chan);
 		_tssi_set_tssi_slope(rtwdev, phy, i);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u32 i;
 
@@ -3348,20 +3354,21 @@ void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8851B; i++) {
-		_tssi_set_sys(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
-		_tssi_slope_cal_org(rtwdev, phy, i);
-		_tssi_alignment_default(rtwdev, phy, i, true);
+		_tssi_set_sys(rtwdev, phy, i, chan);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
+		_tssi_slope_cal_org(rtwdev, phy, i, chan);
+		_tssi_alignment_default(rtwdev, phy, i, true, chan);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 }
 
 static void rtw8851b_tssi_default_txagc(struct rtw89_dev *rtwdev,
-					enum rtw89_phy_idx phy, bool enable)
+					enum rtw89_phy_idx phy, bool enable,
+					enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 channel = chan->channel;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "======> %s   ch=%d\n",
@@ -3379,7 +3386,7 @@ static void rtw8851b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 	rtw89_phy_write32_mask(rtwdev, R_P0_TSSI_TRK, B_P0_TSSI_OFT_EN, 0x0);
 	rtw89_phy_write32_mask(rtwdev, R_P0_TSSI_TRK, B_P0_TSSI_OFT_EN, 0x1);
 
-	_tssi_alimentk_done(rtwdev, phy, RF_PATH_A);
+	_tssi_alimentk_done(rtwdev, phy, RF_PATH_A, chan);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "======>%s 2 SCAN_END Set 0x5818[7:0]=0x%x\n",
@@ -3391,12 +3398,13 @@ static void rtw8851b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 }
 
 void rtw8851b_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
-			       enum rtw89_phy_idx phy_idx)
+			       enum rtw89_phy_idx phy_idx,
+			       enum rtw89_chanctx_idx chanctx_idx)
 {
 	if (scan_start)
-		rtw8851b_tssi_default_txagc(rtwdev, phy_idx, true);
+		rtw8851b_tssi_default_txagc(rtwdev, phy_idx, true, chanctx_idx);
 	else
-		rtw8851b_tssi_default_txagc(rtwdev, phy_idx, false);
+		rtw8851b_tssi_default_txagc(rtwdev, phy_idx, false, chanctx_idx);
 }
 
 static void _bw_setting(struct rtw89_dev *rtwdev, enum rtw89_rf_path path,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.h
index b66a23d6d367..ea7df628256b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b_rfk.h
@@ -12,15 +12,21 @@ void rtw8851b_lck_init(struct rtw89_dev *rtwdev);
 void rtw8851b_lck_track(struct rtw89_dev *rtwdev);
 void rtw8851b_rck(struct rtw89_dev *rtwdev);
 void rtw8851b_dack(struct rtw89_dev *rtwdev);
-void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-void rtw8851b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
+void rtw8851b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
+void rtw8851b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		     enum rtw89_chanctx_idx chanctx_idx);
 void rtw8851b_dpk_init(struct rtw89_dev *rtwdev);
-void rtw8851b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8851b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
 void rtw8851b_dpk_track(struct rtw89_dev *rtwdev);
-void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en);
-void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8851b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   bool hwtx_en, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8851b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan);
 void rtw8851b_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
-			       enum rtw89_phy_idx phy_idx);
+			       enum rtw89_phy_idx phy_idx,
+			       enum rtw89_chanctx_idx chanctx_idx);
 void rtw8851b_set_channel_rf(struct rtw89_dev *rtwdev,
 			     const struct rtw89_chan *chan,
 			     enum rtw89_phy_idx phy_idx);
-- 
cgit v1.3-3-g829e


From fcad7da7d3fc3dd3559c2db46c0fa6ad35097032 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:19 +0800
Subject: wifi: rtw89: 8852a: use right chanctx whenever possible in RFK flow

No longer access chan with hard-code RTW89_CHANCTX_X whenever possible.
Instead, obtain the right chanctx from somewhere and use it in RTL8852A
RFK (RF calibration) related code.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852a.c     |  23 +-
 drivers/net/wireless/realtek/rtw89/rtw8852a.h     |   4 +-
 drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c | 292 ++++++++++++----------
 drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.h |  17 +-
 4 files changed, 185 insertions(+), 151 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 365f074108d4..1034d8b29f5d 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -1346,25 +1346,26 @@ static void rtw8852a_rfk_init(struct rtw89_dev *rtwdev)
 	rtwdev->is_tssi_mode[RF_PATH_B] = false;
 
 	rtw8852a_rck(rtwdev);
-	rtw8852a_dack(rtwdev);
-	rtw8852a_rx_dck(rtwdev, RTW89_PHY_0, true);
+	rtw8852a_dack(rtwdev, RTW89_CHANCTX_0);
+	rtw8852a_rx_dck(rtwdev, RTW89_PHY_0, true, RTW89_CHANCTX_0);
 }
 
 static void rtw8852a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	enum rtw89_chanctx_idx chanctx_idx = rtwvif->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
-	rtw8852a_rx_dck(rtwdev, phy_idx, true);
-	rtw8852a_iqk(rtwdev, phy_idx);
-	rtw8852a_tssi(rtwdev, phy_idx);
-	rtw8852a_dpk(rtwdev, phy_idx);
+	rtw8852a_rx_dck(rtwdev, phy_idx, true, chanctx_idx);
+	rtw8852a_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw8852a_tssi(rtwdev, phy_idx, chanctx_idx);
+	rtw8852a_dpk(rtwdev, phy_idx, chanctx_idx);
 }
 
 static void rtw8852a_rfk_band_changed(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_idx phy_idx,
 				      const struct rtw89_chan *chan)
 {
-	rtw8852a_tssi_scan(rtwdev, phy_idx);
+	rtw8852a_tssi_scan(rtwdev, phy_idx, chan);
 }
 
 static void rtw8852a_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
@@ -1550,10 +1551,8 @@ static void rtw8852a_start_pmac_tx(struct rtw89_dev *rtwdev,
 
 void rtw8852a_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 			     struct rtw8852a_bb_pmac_info *tx_info,
-			     enum rtw89_phy_idx idx)
+			     enum rtw89_phy_idx idx, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
-
 	if (!tx_info->en_pmac_tx) {
 		rtw8852a_stop_pmac_tx(rtwdev, tx_info, idx);
 		rtw89_phy_write32_idx(rtwdev, R_PD_CTRL, B_PD_HIT_DIS, 0, idx);
@@ -1575,7 +1574,7 @@ void rtw8852a_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 
 void rtw8852a_bb_set_pmac_pkt_tx(struct rtw89_dev *rtwdev, u8 enable,
 				 u16 tx_cnt, u16 period, u16 tx_time,
-				 enum rtw89_phy_idx idx)
+				 enum rtw89_phy_idx idx, const struct rtw89_chan *chan)
 {
 	struct rtw8852a_bb_pmac_info tx_info = {0};
 
@@ -1585,7 +1584,7 @@ void rtw8852a_bb_set_pmac_pkt_tx(struct rtw89_dev *rtwdev, u8 enable,
 	tx_info.tx_cnt = tx_cnt;
 	tx_info.period = period;
 	tx_info.tx_time = tx_time;
-	rtw8852a_bb_set_pmac_tx(rtwdev, &tx_info, idx);
+	rtw8852a_bb_set_pmac_tx(rtwdev, &tx_info, idx, chan);
 }
 
 void rtw8852a_bb_set_power(struct rtw89_dev *rtwdev, s16 pwr_dbm,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.h b/drivers/net/wireless/realtek/rtw89/rtw8852a.h
index ea82fed7b7be..d6c1acd09238 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.h
@@ -97,10 +97,10 @@ extern const struct rtw89_chip_info rtw8852a_chip_info;
 void rtw8852a_bb_set_plcp_tx(struct rtw89_dev *rtwdev);
 void rtw8852a_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 			     struct rtw8852a_bb_pmac_info *tx_info,
-			     enum rtw89_phy_idx idx);
+			     enum rtw89_phy_idx idx, const struct rtw89_chan *chan);
 void rtw8852a_bb_set_pmac_pkt_tx(struct rtw89_dev *rtwdev, u8 enable,
 				 u16 tx_cnt, u16 period, u16 tx_time,
-				 enum rtw89_phy_idx idx);
+				 enum rtw89_phy_idx idx, const struct rtw89_chan *chan);
 void rtw8852a_bb_set_power(struct rtw89_dev *rtwdev, s16 pwr_dbm,
 			   enum rtw89_phy_idx idx);
 void rtw8852a_bb_cfg_tx_path(struct rtw89_dev *rtwdev, u8 tx_path);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
index 6bae8bc07e93..9db8713ac99b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.c
@@ -493,11 +493,12 @@ static void _dack(struct rtw89_dev *rtwdev)
 	_dack_s1(rtwdev);
 }
 
-static void _dac_cal(struct rtw89_dev *rtwdev, bool force)
+static void _dac_cal(struct rtw89_dev *rtwdev, bool force,
+		     enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dack_info *dack = &rtwdev->dack;
 	u32 rf0_0, rf1_0;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB, chanctx_idx);
 
 	dack->dack_done = false;
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]DACK b\n");
@@ -799,12 +800,13 @@ static bool _iqk_check_cal(struct rtw89_dev *rtwdev, u8 path, u8 ktype)
 }
 
 static bool _iqk_one_shot(struct rtw89_dev *rtwdev,
-			  enum rtw89_phy_idx phy_idx, u8 path, u8 ktype)
+			  enum rtw89_phy_idx phy_idx, u8 path, u8 ktype,
+			  enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	bool fail = false;
 	u32 iqk_cmd = 0x0;
-	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy_idx, path, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy_idx, path, chanctx_idx);
 	u32 addr_rfc_ctl = 0x0;
 
 	if (path == RF_PATH_A)
@@ -888,7 +890,8 @@ static bool _iqk_one_shot(struct rtw89_dev *rtwdev,
 }
 
 static bool _rxk_group_sel(struct rtw89_dev *rtwdev,
-			   enum rtw89_phy_idx phy_idx, u8 path)
+			   enum rtw89_phy_idx phy_idx, u8 path,
+			   enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	static const u32 rxgn_a[4] = {0x18C, 0x1A0, 0x28C, 0x2A0};
@@ -927,7 +930,7 @@ static bool _rxk_group_sel(struct rtw89_dev *rtwdev,
 		rtw89_phy_write32_mask(rtwdev, R_CFIR_LUT + (path << 8), B_CFIR_LUT_GP, gp);
 		rtw89_phy_write32_mask(rtwdev, R_IOQ_IQK_DPK, B_IOQ_IQK_DPK_EN, 0x1);
 		rtw89_phy_write32_clr(rtwdev, R_NCTL_N1, B_NCTL_N1_CIP);
-		fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_RXK);
+		fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_RXK, chanctx_idx);
 		rtw89_phy_write32_mask(rtwdev, R_IQKINF, BIT(16 + gp + path * 4), fail);
 	}
 
@@ -952,7 +955,8 @@ static bool _rxk_group_sel(struct rtw89_dev *rtwdev,
 }
 
 static bool _iqk_nbrxk(struct rtw89_dev *rtwdev,
-		       enum rtw89_phy_idx phy_idx, u8 path)
+		       enum rtw89_phy_idx phy_idx, u8 path,
+		       enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 group = 0x0;
@@ -991,7 +995,7 @@ static bool _iqk_nbrxk(struct rtw89_dev *rtwdev,
 			       B_CFIR_LUT_GP, group);
 	rtw89_phy_write32_set(rtwdev, R_IOQ_IQK_DPK, B_IOQ_IQK_DPK_EN);
 	rtw89_phy_write32_clr(rtwdev, R_NCTL_N1, B_NCTL_N1_CIP);
-	fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_NBRXK);
+	fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_NBRXK, chanctx_idx);
 
 	switch (iqk_info->iqk_band[path]) {
 	case RTW89_BAND_2G:
@@ -1040,7 +1044,8 @@ static void _iqk_rxclk_setting(struct rtw89_dev *rtwdev, u8 path)
 }
 
 static bool _txk_group_sel(struct rtw89_dev *rtwdev,
-			   enum rtw89_phy_idx phy_idx, u8 path)
+			   enum rtw89_phy_idx phy_idx, u8 path,
+			   enum rtw89_chanctx_idx chanctx_idx)
 {
 	static const u32 a_txgain[4] = {0xE466, 0x646D, 0xE4E2, 0x64ED};
 	static const u32 g_txgain[4] = {0x60e8, 0x60f0, 0x61e8, 0x61ED};
@@ -1083,7 +1088,7 @@ static bool _txk_group_sel(struct rtw89_dev *rtwdev,
 		rtw89_phy_write32_mask(rtwdev, R_CFIR_LUT + (path << 8),
 				       B_CFIR_LUT_GP, gp);
 		rtw89_phy_write32_clr(rtwdev, R_NCTL_N1, B_NCTL_N1_CIP);
-		fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_TXK);
+		fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_TXK, chanctx_idx);
 		rtw89_phy_write32_mask(rtwdev, R_IQKINF, BIT(8 + gp + path * 4), fail);
 	}
 
@@ -1098,7 +1103,8 @@ static bool _txk_group_sel(struct rtw89_dev *rtwdev,
 }
 
 static bool _iqk_nbtxk(struct rtw89_dev *rtwdev,
-		       enum rtw89_phy_idx phy_idx, u8 path)
+		       enum rtw89_phy_idx phy_idx, u8 path,
+		       enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 group = 0x2;
@@ -1131,7 +1137,7 @@ static bool _iqk_nbtxk(struct rtw89_dev *rtwdev,
 	rtw89_phy_write32_mask(rtwdev, R_CFIR_LUT + (path << 8), B_CFIR_LUT_GP, group);
 	rtw89_phy_write32_mask(rtwdev, R_KIP_IQP + (path << 8), MASKDWORD, itqt);
 	rtw89_phy_write32_clr(rtwdev, R_NCTL_N1, B_NCTL_N1_CIP);
-	fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_NBTXK);
+	fail = _iqk_one_shot(rtwdev, phy_idx, path, ID_NBTXK, chanctx_idx);
 	if (!fail) {
 		tmp = rtw89_phy_read32_mask(rtwdev, R_TXIQC + (path << 8), MASKDWORD);
 		iqk_info->nb_txcfir[path] = tmp | 0x2;
@@ -1179,7 +1185,8 @@ static bool _lok_finetune_check(struct rtw89_dev *rtwdev, u8 path)
 }
 
 static bool _iqk_lok(struct rtw89_dev *rtwdev,
-		     enum rtw89_phy_idx phy_idx, u8 path)
+		     enum rtw89_phy_idx phy_idx, u8 path,
+		     enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 rf0 = 0x0;
@@ -1210,11 +1217,11 @@ static bool _iqk_lok(struct rtw89_dev *rtwdev,
 	rtw89_phy_write32_set(rtwdev, R_IOQ_IQK_DPK, B_IOQ_IQK_DPK_EN);
 	rtw89_phy_write32_clr(rtwdev, R_NCTL_N1, B_NCTL_N1_CIP);
 	rtw89_phy_write32_mask(rtwdev, R_KIP_IQP + (path << 8), MASKDWORD, itqt);
-	tmp = _iqk_one_shot(rtwdev, phy_idx, path, ID_FLOK_COARSE);
+	tmp = _iqk_one_shot(rtwdev, phy_idx, path, ID_FLOK_COARSE, chanctx_idx);
 	iqk_info->lok_cor_fail[0][path] = tmp;
 	fsleep(10);
 	rtw89_phy_write32_mask(rtwdev, R_KIP_IQP + (path << 8), MASKDWORD, itqt);
-	tmp = _iqk_one_shot(rtwdev, phy_idx, path, ID_FLOK_FINE);
+	tmp = _iqk_one_shot(rtwdev, phy_idx, path, ID_FLOK_FINE, chanctx_idx);
 	iqk_info->lok_fin_fail[0][path] = tmp;
 	fail = _lok_finetune_check(rtwdev, path);
 	return fail;
@@ -1321,7 +1328,8 @@ static void _iqk_info_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
 }
 
 static
-void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u8 path)
+void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u8 path,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	bool lok_is_fail = false;
@@ -1333,30 +1341,35 @@ void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u8 path)
 	for (i = 0; i < 3; i++) {
 		_lok_res_table(rtwdev, path, ibias++);
 		_iqk_txk_setting(rtwdev, path);
-		lok_is_fail = _iqk_lok(rtwdev, phy_idx, path);
+		lok_is_fail = _iqk_lok(rtwdev, phy_idx, path, chanctx_idx);
 		if (!lok_is_fail)
 			break;
 	}
 	if (iqk_info->is_nbiqk)
-		iqk_info->iqk_tx_fail[0][path] = _iqk_nbtxk(rtwdev, phy_idx, path);
+		iqk_info->iqk_tx_fail[0][path] = _iqk_nbtxk(rtwdev, phy_idx, path,
+							    chanctx_idx);
 	else
-		iqk_info->iqk_tx_fail[0][path] = _txk_group_sel(rtwdev, phy_idx, path);
+		iqk_info->iqk_tx_fail[0][path] = _txk_group_sel(rtwdev, phy_idx, path,
+								chanctx_idx);
 
 	_iqk_rxclk_setting(rtwdev, path);
 	_iqk_rxk_setting(rtwdev, path);
 	if (iqk_info->is_nbiqk || rtwdev->dbcc_en || iqk_info->iqk_band[path] == RTW89_BAND_2G)
-		iqk_info->iqk_rx_fail[0][path] = _iqk_nbrxk(rtwdev, phy_idx, path);
+		iqk_info->iqk_rx_fail[0][path] = _iqk_nbrxk(rtwdev, phy_idx, path,
+							    chanctx_idx);
 	else
-		iqk_info->iqk_rx_fail[0][path] = _rxk_group_sel(rtwdev, phy_idx, path);
+		iqk_info->iqk_rx_fail[0][path] = _rxk_group_sel(rtwdev, phy_idx, path,
+								chanctx_idx);
 
 	_iqk_info_iqk(rtwdev, phy_idx, path);
 }
 
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev,
-			     enum rtw89_phy_idx phy, u8 path)
+			     enum rtw89_phy_idx phy, u8 path,
+			     enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u32 reg_rf18 = 0x0, reg_35c = 0x0;
 	u8 idx = 0;
 	u8 get_empty_table = false;
@@ -1413,9 +1426,9 @@ static void _iqk_get_ch_info(struct rtw89_dev *rtwdev,
 }
 
 static void _iqk_start_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
-			   u8 path)
+			   u8 path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	_iqk_by_path(rtwdev, phy_idx, path);
+	_iqk_by_path(rtwdev, phy_idx, path, chanctx_idx);
 }
 
 static void _iqk_restore(struct rtw89_dev *rtwdev, u8 path)
@@ -1513,7 +1526,8 @@ static void _iqk_macbb_setting(struct rtw89_dev *rtwdev,
 	rtw89_rfk_parser(rtwdev, tbl);
 }
 
-static void _iqk_dbcc(struct rtw89_dev *rtwdev, u8 path)
+static void _iqk_dbcc(struct rtw89_dev *rtwdev, u8 path,
+		      enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 phy_idx = 0x0;
@@ -1525,10 +1539,10 @@ static void _iqk_dbcc(struct rtw89_dev *rtwdev, u8 path)
 	else
 		phy_idx = RTW89_PHY_1;
 
-	_iqk_get_ch_info(rtwdev, phy_idx, path);
+	_iqk_get_ch_info(rtwdev, phy_idx, path, chanctx_idx);
 	_iqk_macbb_setting(rtwdev, phy_idx, path);
 	_iqk_preset(rtwdev, path);
-	_iqk_start_iqk(rtwdev, phy_idx, path);
+	_iqk_start_iqk(rtwdev, phy_idx, path, chanctx_idx);
 	_iqk_restore(rtwdev, path);
 	_iqk_afebb_restore(rtwdev, phy_idx, path);
 }
@@ -1607,12 +1621,13 @@ static void _iqk_init(struct rtw89_dev *rtwdev)
 }
 
 static void _doiqk(struct rtw89_dev *rtwdev, bool force,
-		   enum rtw89_phy_idx phy_idx, u8 path)
+		   enum rtw89_phy_idx phy_idx, u8 path,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852A_IQK_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -1622,12 +1637,12 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	iqk_info->version = RTW8852A_IQK_VER;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]Test Ver 0x%x\n", iqk_info->version);
-	_iqk_get_ch_info(rtwdev, phy_idx, path);
+	_iqk_get_ch_info(rtwdev, phy_idx, path, chanctx_idx);
 	_rfk_backup_bb_reg(rtwdev, &backup_bb_val[0]);
 	_rfk_backup_rf_reg(rtwdev, &backup_rf_val[path][0], path);
 	_iqk_macbb_setting(rtwdev, phy_idx, path);
 	_iqk_preset(rtwdev, path);
-	_iqk_start_iqk(rtwdev, phy_idx, path);
+	_iqk_start_iqk(rtwdev, phy_idx, path, chanctx_idx);
 	_iqk_restore(rtwdev, path);
 	_iqk_afebb_restore(rtwdev, phy_idx, path);
 	_rfk_restore_bb_reg(rtwdev, &backup_bb_val[0]);
@@ -1635,18 +1650,19 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force)
+static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	switch (_kpath(rtwdev, phy_idx)) {
 	case RF_A:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
 		break;
 	case RF_B:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	case RF_AB:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	default:
 		break;
@@ -1656,9 +1672,10 @@ static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool forc
 #define RXDCK_VER_8852A 0xe
 
 static void _set_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			enum rtw89_rf_path path, bool is_afe)
+			enum rtw89_rf_path path, bool is_afe,
+			enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy, path, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_path_phymap(rtwdev, phy, path, chanctx_idx);
 	u32 ori_val;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
@@ -1704,7 +1721,7 @@ static void _set_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-		    bool is_afe)
+		    bool is_afe, enum rtw89_chanctx_idx chanctx_idx)
 {
 	u8 path, kpath, dck_tune;
 	u32 rf_reg5;
@@ -1732,7 +1749,7 @@ static void _rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		rtw89_write_rf(rtwdev, path, RR_RSV1, RR_RSV1_RST, 0x0);
 		rtw89_write_rf(rtwdev, path, RR_DCK, RR_DCK_FINE, 0x0);
 		rtw89_write_rf(rtwdev, path, RR_MOD, RR_MOD_MASK, RR_MOD_V_RX);
-		_set_rx_dck(rtwdev, phy, path, is_afe);
+		_set_rx_dck(rtwdev, phy, path, is_afe, chanctx_idx);
 		rtw89_write_rf(rtwdev, path, RR_DCK, RR_DCK_FINE, dck_tune);
 		rtw89_write_rf(rtwdev, path, RR_RSV1, RFREG_MASK, rf_reg5);
 
@@ -1800,9 +1817,10 @@ static void _dpk_reload_kip(struct rtw89_dev *rtwdev, u32 *reg,
 }
 
 static u8 _dpk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			enum rtw89_rf_path path, enum rtw8852a_dpk_id id)
+			enum rtw89_rf_path path, enum rtw8852a_dpk_id id,
+			enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map  = rtw89_btc_path_phymap(rtwdev, phy, path, RTW89_CHANCTX_0);
+	u8 phy_map  = rtw89_btc_path_phymap(rtwdev, phy, path, chanctx_idx);
 	u16 dpk_cmd = 0x0;
 	u32 val;
 	int ret;
@@ -1841,18 +1859,19 @@ static u8 _dpk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 
 static void _dpk_rx_dck(struct rtw89_dev *rtwdev,
 			enum rtw89_phy_idx phy,
-			enum rtw89_rf_path path)
+			enum rtw89_rf_path path,
+			enum rtw89_chanctx_idx chanctx_idx)
 {
 	rtw89_write_rf(rtwdev, path, RR_RXBB2, RR_EN_TIA_IDA, 0x3);
-	_set_rx_dck(rtwdev, phy, path, false);
+	_set_rx_dck(rtwdev, phy, path, false, chanctx_idx);
 }
 
 static void _dpk_information(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 kidx = dpk->cur_idx[path];
 
 	dpk->bp[path][kidx].band = chan->band_type;
@@ -1967,7 +1986,8 @@ static void _dpk_kip_restore(struct rtw89_dev *rtwdev,
 
 static void _dpk_lbk_rxiqk(struct rtw89_dev *rtwdev,
 			   enum rtw89_phy_idx phy,
-			   enum rtw89_rf_path path)
+			   enum rtw89_rf_path path,
+			   enum rtw89_chanctx_idx chanctx_idx)
 {
 	u8 cur_rxbb;
 
@@ -1997,7 +2017,7 @@ static void _dpk_lbk_rxiqk(struct rtw89_dev *rtwdev,
 
 	rtw89_phy_write32_mask(rtwdev, R_IQK_DIF4, B_IQK_DIF4_RXT, 0x11);
 
-	_dpk_one_shot(rtwdev, phy, path, LBK_RXIQK);
+	_dpk_one_shot(rtwdev, phy, path, LBK_RXIQK, chanctx_idx);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DPK] S%d LBK RXIQC = 0x%x\n", path,
 		    rtw89_phy_read32_mask(rtwdev, R_RXIQC, MASKDWORD));
@@ -2186,10 +2206,11 @@ static bool _dpk_sync_check(struct rtw89_dev *rtwdev,
 }
 
 static bool _dpk_sync(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-		      enum rtw89_rf_path path, u8 kidx)
+		      enum rtw89_rf_path path, u8 kidx,
+		      enum rtw89_chanctx_idx chanctx_idx)
 {
 	_dpk_tpg_sel(rtwdev, path, kidx);
-	_dpk_one_shot(rtwdev, phy, path, SYNC);
+	_dpk_one_shot(rtwdev, phy, path, SYNC, chanctx_idx);
 	return _dpk_sync_check(rtwdev, path); /*1= fail*/
 }
 
@@ -2242,10 +2263,10 @@ static u8 _dpk_gainloss_read(struct rtw89_dev *rtwdev)
 
 static void _dpk_gainloss(struct rtw89_dev *rtwdev,
 			  enum rtw89_phy_idx phy, enum rtw89_rf_path path,
-			  u8 kidx)
+			  u8 kidx, enum rtw89_chanctx_idx chanctx_idx)
 {
 	_dpk_table_select(rtwdev, path, kidx, 1);
-	_dpk_one_shot(rtwdev, phy, path, GAIN_LOSS);
+	_dpk_one_shot(rtwdev, phy, path, GAIN_LOSS, chanctx_idx);
 }
 
 #define DPK_TXAGC_LOWER 0x2e
@@ -2322,7 +2343,7 @@ static u8 _dpk_pas_read(struct rtw89_dev *rtwdev, bool is_check)
 
 static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		   enum rtw89_rf_path path, u8 kidx, u8 init_txagc,
-		   bool loss_only)
+		   bool loss_only, enum rtw89_chanctx_idx chanctx_idx)
 {
 #define DPK_AGC_ADJ_LMT 6
 #define DPK_DGAIN_UPPER 1922
@@ -2330,7 +2351,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 #define DPK_RXBB_UPPER 0x1f
 #define DPK_RXBB_LOWER 0
 #define DPK_GL_CRIT 7
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 tmp_txagc, tmp_rxbb = 0, tmp_gl_idx = 0;
 	u8 agc_cnt = 0;
 	bool limited_rxbb = false;
@@ -2344,7 +2365,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	do {
 		switch (step) {
 		case DPK_AGC_STEP_SYNC_DGAIN:
-			if (_dpk_sync(rtwdev, phy, path, kidx)) {
+			if (_dpk_sync(rtwdev, phy, path, kidx, chanctx_idx)) {
 				tmp_txagc = DPK_TXAGC_INVAL;
 				goout = true;
 				break;
@@ -2380,7 +2401,8 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				if (chan->band_width < RTW89_CHANNEL_WIDTH_80)
 					_dpk_bypass_rxcfir(rtwdev, path, true);
 				else
-					_dpk_lbk_rxiqk(rtwdev, phy, path);
+					_dpk_lbk_rxiqk(rtwdev, phy, path,
+						       chanctx_idx);
 			}
 			if (dgain > DPK_DGAIN_UPPER || dgain < DPK_DGAIN_LOWER)
 				step = DPK_AGC_STEP_SYNC_DGAIN;
@@ -2391,7 +2413,7 @@ static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			break;
 
 		case DPK_AGC_STEP_GAIN_LOSS_IDX:
-			_dpk_gainloss(rtwdev, phy, path, kidx);
+			_dpk_gainloss(rtwdev, phy, path, kidx, chanctx_idx);
 			tmp_gl_idx = _dpk_gainloss_read(rtwdev);
 
 			if ((tmp_gl_idx == 0 && _dpk_pas_read(rtwdev, true)) ||
@@ -2475,11 +2497,12 @@ static void _dpk_set_mdpd_para(struct rtw89_dev *rtwdev, u8 order)
 }
 
 static void _dpk_idl_mpa(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			 enum rtw89_rf_path path, u8 kidx, u8 gain)
+			 enum rtw89_rf_path path, u8 kidx, u8 gain,
+			 enum rtw89_chanctx_idx chanctx_idx)
 {
 	_dpk_set_mdpd_para(rtwdev, 0x0);
 	_dpk_table_select(rtwdev, path, kidx, 1);
-	_dpk_one_shot(rtwdev, phy, path, MDPK_IDL);
+	_dpk_one_shot(rtwdev, phy, path, MDPK_IDL, chanctx_idx);
 }
 
 static void _dpk_fill_result(struct rtw89_dev *rtwdev,
@@ -2518,10 +2541,10 @@ static void _dpk_fill_result(struct rtw89_dev *rtwdev,
 }
 
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			      enum rtw89_rf_path path)
+			      enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	bool is_reload = false;
 	u8 idx, cur_band, cur_ch;
 
@@ -2545,7 +2568,8 @@ static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-		      enum rtw89_rf_path path, u8 gain)
+		      enum rtw89_rf_path path, u8 gain,
+		      enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 txagc = 0, kidx = dpk->cur_idx[path];
@@ -2558,16 +2582,16 @@ static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	_rf_direct_cntrl(rtwdev, path, false);
 	txagc = _dpk_set_tx_pwr(rtwdev, gain, path);
 	_dpk_rf_setting(rtwdev, gain, path, kidx);
-	_dpk_rx_dck(rtwdev, phy, path);
+	_dpk_rx_dck(rtwdev, phy, path, chanctx_idx);
 
 	_dpk_kip_setting(rtwdev, path, kidx);
 	_dpk_manual_txcfir(rtwdev, path, true);
-	txagc = _dpk_agc(rtwdev, phy, path, kidx, txagc, false);
+	txagc = _dpk_agc(rtwdev, phy, path, kidx, txagc, false, chanctx_idx);
 	if (txagc == DPK_TXAGC_INVAL)
 		is_fail = true;
 	_dpk_get_thermal(rtwdev, kidx, path);
 
-	_dpk_idl_mpa(rtwdev, phy, path, kidx, gain);
+	_dpk_idl_mpa(rtwdev, phy, path, kidx, gain, chanctx_idx);
 	rtw89_write_rf(rtwdev, path, RR_MOD, RR_MOD_MASK, RR_MOD_V_RX);
 	_dpk_fill_result(rtwdev, path, kidx, gain, txagc);
 	_dpk_manual_txcfir(rtwdev, path, false);
@@ -2584,7 +2608,8 @@ static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
-			    enum rtw89_phy_idx phy, u8 kpath)
+			    enum rtw89_phy_idx phy, u8 kpath,
+			    enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
@@ -2599,7 +2624,8 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 			if (!(kpath & BIT(path)))
 				continue;
 
-			reloaded[path] = _dpk_reload_check(rtwdev, phy, path);
+			reloaded[path] = _dpk_reload_check(rtwdev, phy, path,
+							   chanctx_idx);
 			if (!reloaded[path] && dpk->bp[path][0].ch != 0)
 				dpk->cur_idx[path] = !dpk->cur_idx[path];
 			else
@@ -2624,7 +2650,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 			_dpk_tssi_pause(rtwdev, path, true);
 		_dpk_bkup_kip(rtwdev, kip_reg, kip_bkup, path);
 		_rfk_backup_rf_reg(rtwdev, &backup_rf_val[path][0], path);
-		_dpk_information(rtwdev, phy, path);
+		_dpk_information(rtwdev, phy, path, chanctx_idx);
 	}
 
 	_dpk_bb_afe_setting(rtwdev, phy, path, kpath);
@@ -2633,7 +2659,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 		if (!(kpath & BIT(path)) || reloaded[path])
 			continue;
 
-		is_fail = _dpk_main(rtwdev, phy, path, 1);
+		is_fail = _dpk_main(rtwdev, phy, path, 1, chanctx_idx);
 		_dpk_onoff(rtwdev, path, is_fail);
 	}
 
@@ -2652,10 +2678,11 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 	}
 }
 
-static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			      enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_fem_info *fem = &rtwdev->fem;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 
 	if (fem->epa_2g && chan->band_type == RTW89_BAND_2G) {
 		rtw89_debug(rtwdev, RTW89_DBG_RFK,
@@ -2682,17 +2709,19 @@ static void _dpk_force_bypass(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	}
 }
 
-static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force)
+static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		 bool force, enum rtw89_chanctx_idx chanctx_idx)
 {
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[DPK] ****** DPK Start (Ver: 0x%x, Cv: %d, RF_para: %d) ******\n",
 		    RTW8852A_DPK_VER, rtwdev->hal.cv,
 		    RTW8852A_RF_REL_VERSION);
 
-	if (_dpk_bypass_check(rtwdev, phy))
+	if (_dpk_bypass_check(rtwdev, phy, chanctx_idx))
 		_dpk_force_bypass(rtwdev, phy);
 	else
-		_dpk_cal_select(rtwdev, force, phy, _kpath(rtwdev, phy));
+		_dpk_cal_select(rtwdev, force, phy, _kpath(rtwdev, phy),
+				chanctx_idx);
 }
 
 static void _dpk_onoff(struct rtw89_dev *rtwdev,
@@ -2815,9 +2844,8 @@ static void _dpk_track(struct rtw89_dev *rtwdev)
 }
 
 static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (band == RTW89_BAND_2G)
@@ -2826,9 +2854,9 @@ static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		rtw89_write_rf(rtwdev, path, RR_TXPOW, RR_TXPOW_TXA, 0x1);
 }
 
-static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			  const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8852a_tssi_sys_defs_tbl);
@@ -2838,9 +2866,9 @@ static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 }
 
 static void _tssi_ini_txpwr_ctrl_bb(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				    enum rtw89_rf_path path)
+				    enum rtw89_rf_path path,
+				    const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser_by_cond(rtwdev, path == RF_PATH_A,
@@ -2869,7 +2897,7 @@ static void _tssi_set_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 #define __get_val(ptr, idx)				\
 ({							\
@@ -2883,7 +2911,6 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -3076,9 +3103,8 @@ static void _tssi_set_txagc_offset_mv_avg(struct rtw89_dev *rtwdev,
 }
 
 static void _tssi_pak(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-		      enum rtw89_rf_path path)
+		      enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 subband = chan->subband_type;
 
 	switch (subband) {
@@ -3252,10 +3278,9 @@ static u32 _tssi_get_trim_group(struct rtw89_dev *rtwdev, u8 ch)
 }
 
 static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			    enum rtw89_rf_path path)
+			    enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
 	s8 de_1st = 0;
@@ -3290,10 +3315,9 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 
 static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev,
 				 enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	s8 tde_1st = 0;
@@ -3328,11 +3352,10 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev,
 }
 
 static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
-				  enum rtw89_phy_idx phy)
+				  enum rtw89_phy_idx phy, const struct rtw89_chan *chan)
 {
 #define __DE_MASK 0x003ff000
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	static const u32 r_cck_long[RF_PATH_NUM_8852A] = {0x5858, 0x7858};
 	static const u32 r_cck_short[RF_PATH_NUM_8852A] = {0x5860, 0x7860};
 	static const u32 r_mcs_20m[RF_PATH_NUM_8852A] = {0x5838, 0x7838};
@@ -3352,7 +3375,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 
 	for (i = 0; i < RF_PATH_NUM_8852A; i++) {
 		gidx = _tssi_get_cck_group(rtwdev, ch);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = tssi_info->tssi_cck[i][gidx] + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3368,8 +3391,8 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 			    rtw89_phy_read32_mask(rtwdev, r_cck_long[i],
 						  __DE_MASK));
 
-		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i, chan);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = ofdm_de + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3458,10 +3481,10 @@ static void _tssi_track(struct rtw89_dev *rtwdev)
 	}
 }
 
-static void _tssi_high_power(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static void _tssi_high_power(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			     const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel, ch_tmp;
 	u8 bw = chan->band_width;
 	u8 band = chan->band_type;
@@ -3497,24 +3520,25 @@ static void _tssi_high_power(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 }
 
 static void _tssi_hw_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			u8 path, s16 pwr_dbm, u8 enable)
+			u8 path, s16 pwr_dbm, u8 enable, const struct rtw89_chan *chan)
 {
 	rtw8852a_bb_set_plcp_tx(rtwdev);
 	rtw8852a_bb_cfg_tx_path(rtwdev, path);
 	rtw8852a_bb_set_power(rtwdev, pwr_dbm, phy);
-	rtw8852a_bb_set_pmac_pkt_tx(rtwdev, enable, 20, 5000, 0, phy);
+	rtw8852a_bb_set_pmac_pkt_tx(rtwdev, enable, 20, 5000, 0, phy, chan);
 }
 
-static void _tssi_pre_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static void _tssi_pre_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			 enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	const struct rtw89_chip_info *mac_reg = rtwdev->chip;
 	u8 ch = chan->channel, ch_tmp;
 	u8 bw = chan->band_width;
 	u8 band = chan->band_type;
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, 0, chanctx_idx);
 	s8 power;
 	s16 xdbm;
 	u32 i, tx_counter = 0;
@@ -3546,9 +3570,9 @@ static void _tssi_pre_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy));
 	tx_counter = rtw89_phy_read32_mask(rtwdev, R_TX_COUNTER, MASKLWORD);
 
-	_tssi_hw_tx(rtwdev, phy, RF_PATH_AB, xdbm, true);
+	_tssi_hw_tx(rtwdev, phy, RF_PATH_AB, xdbm, true, chan);
 	mdelay(15);
-	_tssi_hw_tx(rtwdev, phy, RF_PATH_AB, xdbm, false);
+	_tssi_hw_tx(rtwdev, phy, RF_PATH_AB, xdbm, false, chan);
 
 	tx_counter = rtw89_phy_read32_mask(rtwdev, R_TX_COUNTER, MASKLWORD) -
 		    tx_counter;
@@ -3600,19 +3624,21 @@ void rtw8852a_rck(struct rtw89_dev *rtwdev)
 		_rck(rtwdev, path);
 }
 
-void rtw8852a_dack(struct rtw89_dev *rtwdev)
+void rtw8852a_dack(struct rtw89_dev *rtwdev,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
-	_dac_cal(rtwdev, false);
+	_dac_cal(rtwdev, false, chanctx_idx);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_STOP);
 }
 
-void rtw8852a_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852a_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
@@ -3620,34 +3646,35 @@ void rtw8852a_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 	_iqk_init(rtwdev);
 	if (rtwdev->dbcc_en)
-		_iqk_dbcc(rtwdev, phy_idx);
+		_iqk_dbcc(rtwdev, phy_idx, chanctx_idx);
 	else
-		_iqk(rtwdev, phy_idx, false);
+		_iqk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_STOP);
 }
 
 void rtw8852a_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
-		     bool is_afe)
+		     bool is_afe, enum rtw89_chanctx_idx chanctx_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
-	_rx_dck(rtwdev, phy_idx, is_afe);
+	_rx_dck(rtwdev, phy_idx, is_afe, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_STOP);
 }
 
-void rtw8852a_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852a_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
@@ -3655,7 +3682,7 @@ void rtw8852a_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 	rtwdev->dpk.is_dpk_enable = true;
 	rtwdev->dpk.is_dpk_reload_en = false;
-	_dpk(rtwdev, phy_idx, false);
+	_dpk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_STOP);
@@ -3666,8 +3693,10 @@ void rtw8852a_dpk_track(struct rtw89_dev *rtwdev)
 	_dpk_track(rtwdev);
 }
 
-void rtw8852a_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8852a_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 i;
 
 	rtw89_debug(rtwdev, RTW89_DBG_TSSI, "[TSSI] %s: phy=%d\n",
@@ -3676,26 +3705,27 @@ void rtw8852a_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8852A; i++) {
-		_tssi_rf_setting(rtwdev, phy, i);
-		_tssi_set_sys(rtwdev, phy);
-		_tssi_ini_txpwr_ctrl_bb(rtwdev, phy, i);
+		_tssi_rf_setting(rtwdev, phy, i, chan);
+		_tssi_set_sys(rtwdev, phy, chan);
+		_tssi_ini_txpwr_ctrl_bb(rtwdev, phy, i, chan);
 		_tssi_ini_txpwr_ctrl_bb_he_tb(rtwdev, phy, i);
 		_tssi_set_dck(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
 		_tssi_set_dac_gain_tbl(rtwdev, phy, i);
 		_tssi_slope_cal_org(rtwdev, phy, i);
 		_tssi_set_rf_gap_tbl(rtwdev, phy, i);
 		_tssi_set_slope(rtwdev, phy, i);
-		_tssi_pak(rtwdev, phy, i);
+		_tssi_pak(rtwdev, phy, i, chan);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
-	_tssi_high_power(rtwdev, phy);
-	_tssi_pre_tx(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
+	_tssi_high_power(rtwdev, phy, chan);
+	_tssi_pre_tx(rtwdev, phy, chanctx_idx);
 }
 
-void rtw8852a_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8852a_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan)
 {
 	u8 i;
 
@@ -3710,14 +3740,14 @@ void rtw8852a_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8852A; i++) {
-		_tssi_rf_setting(rtwdev, phy, i);
-		_tssi_set_sys(rtwdev, phy);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
-		_tssi_pak(rtwdev, phy, i);
+		_tssi_rf_setting(rtwdev, phy, i, chan);
+		_tssi_set_sys(rtwdev, phy, chan);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
+		_tssi_pak(rtwdev, phy, i, chan);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 }
 
 void rtw8852a_tssi_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.h
index fa058ccc8616..8761f2cc9359 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a_rfk.h
@@ -8,14 +8,19 @@
 #include "core.h"
 
 void rtw8852a_rck(struct rtw89_dev *rtwdev);
-void rtw8852a_dack(struct rtw89_dev *rtwdev);
-void rtw8852a_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
+void rtw8852a_dack(struct rtw89_dev *rtwdev,
+		   enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852a_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852a_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
-		     bool is_afe);
-void rtw8852a_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+		     bool is_afe, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852a_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852a_dpk_track(struct rtw89_dev *rtwdev);
-void rtw8852a_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
-void rtw8852a_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8852a_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852a_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan);
 void rtw8852a_tssi_track(struct rtw89_dev *rtwdev);
 void rtw8852a_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
 			       enum rtw89_phy_idx phy_idx);
-- 
cgit v1.3-3-g829e


From 50b3da25abc6a40c8766125c47d00990765b6555 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:20 +0800
Subject: wifi: rtw89: 8852bx: use right chanctx whenever possible in RFK flow

No longer access chan with hard-code RTW89_CHANCTX_X whenever possible.
Instead, obtain the right chanctx from somewhere and use it in RTL8852BX
RFK (RF calibration) related code.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852b.c      |  17 +-
 .../net/wireless/realtek/rtw89/rtw8852b_common.c   |  15 +-
 .../net/wireless/realtek/rtw89/rtw8852b_common.h   |  15 +-
 drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c  | 211 +++++++++++----------
 drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.h  |  20 +-
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c     |  25 +--
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c | 188 +++++++++---------
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h |  20 +-
 8 files changed, 273 insertions(+), 238 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index d055847d2de4..4a4e825302ea 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -558,31 +558,32 @@ static void rtw8852b_rfk_init(struct rtw89_dev *rtwdev)
 
 	rtw8852b_dpk_init(rtwdev);
 	rtw8852b_rck(rtwdev);
-	rtw8852b_dack(rtwdev);
-	rtw8852b_rx_dck(rtwdev, RTW89_PHY_0);
+	rtw8852b_dack(rtwdev, RTW89_CHANCTX_0);
+	rtw8852b_rx_dck(rtwdev, RTW89_PHY_0, RTW89_CHANCTX_0);
 }
 
 static void rtw8852b_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	enum rtw89_chanctx_idx chanctx_idx = rtwvif->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
-	rtw8852b_rx_dck(rtwdev, phy_idx);
-	rtw8852b_iqk(rtwdev, phy_idx);
-	rtw8852b_tssi(rtwdev, phy_idx, true);
-	rtw8852b_dpk(rtwdev, phy_idx);
+	rtw8852b_rx_dck(rtwdev, phy_idx, chanctx_idx);
+	rtw8852b_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw8852b_tssi(rtwdev, phy_idx, true, chanctx_idx);
+	rtw8852b_dpk(rtwdev, phy_idx, chanctx_idx);
 }
 
 static void rtw8852b_rfk_band_changed(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_idx phy_idx,
 				      const struct rtw89_chan *chan)
 {
-	rtw8852b_tssi_scan(rtwdev, phy_idx);
+	rtw8852b_tssi_scan(rtwdev, phy_idx, chan);
 }
 
 static void rtw8852b_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			      bool start)
 {
-	rtw8852b_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
+	rtw8852b_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx, rtwvif->chanctx_idx);
 }
 
 static void rtw8852b_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
index f364e76e2b34..bd05880cfe8f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
@@ -1445,10 +1445,8 @@ static void rtw8852bx_start_pmac_tx(struct rtw89_dev *rtwdev,
 static
 void rtw8852bx_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 			      struct rtw8852bx_bb_pmac_info *tx_info,
-			      enum rtw89_phy_idx idx)
+			      enum rtw89_phy_idx idx, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
-
 	if (!tx_info->en_pmac_tx) {
 		rtw8852bx_stop_pmac_tx(rtwdev, tx_info, idx);
 		rtw89_phy_write32_idx(rtwdev, R_PD_CTRL, B_PD_HIT_DIS, 0, idx);
@@ -1473,7 +1471,7 @@ void rtw8852bx_bb_set_pmac_tx(struct rtw89_dev *rtwdev,
 static
 void __rtw8852bx_bb_set_pmac_pkt_tx(struct rtw89_dev *rtwdev, u8 enable,
 				    u16 tx_cnt, u16 period, u16 tx_time,
-				    enum rtw89_phy_idx idx)
+				    enum rtw89_phy_idx idx, const struct rtw89_chan *chan)
 {
 	struct rtw8852bx_bb_pmac_info tx_info = {0};
 
@@ -1484,7 +1482,7 @@ void __rtw8852bx_bb_set_pmac_pkt_tx(struct rtw89_dev *rtwdev, u8 enable,
 	tx_info.period = period;
 	tx_info.tx_time = tx_time;
 
-	rtw8852bx_bb_set_pmac_tx(rtwdev, &tx_info, idx);
+	rtw8852bx_bb_set_pmac_tx(rtwdev, &tx_info, idx, chan);
 }
 
 static
@@ -1623,9 +1621,9 @@ static void __rtw8852bx_ctrl_btg_bt_rx(struct rtw89_dev *rtwdev, bool en,
 
 static
 void __rtw8852bx_bb_ctrl_rx_path(struct rtw89_dev *rtwdev,
-				 enum rtw89_rf_path_bit rx_path)
+				 enum rtw89_rf_path_bit rx_path,
+				 const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u32 rst_mask0;
 	u32 rst_mask1;
 
@@ -1713,9 +1711,10 @@ static void rtw8852bx_bb_ctrl_rf_mode_rx_path(struct rtw89_dev *rtwdev,
 static void __rtw8852bx_bb_cfg_txrx_path(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_rf_path_bit rx_path = hal->antenna_rx ? hal->antenna_rx : RF_AB;
 
-	rtw8852bx_bb_ctrl_rx_path(rtwdev, rx_path);
+	rtw8852bx_bb_ctrl_rx_path(rtwdev, rx_path, chan);
 	rtw8852bx_bb_ctrl_rf_mode_rx_path(rtwdev, rx_path);
 
 	if (rtwdev->hal.rx_nss == 1) {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h
index 801e7ab9f4fa..a916e38c76c1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h
@@ -121,13 +121,14 @@ struct rtw8852bx_info {
 	void (*bb_cfg_txrx_path)(struct rtw89_dev *rtwdev);
 	void (*bb_cfg_tx_path)(struct rtw89_dev *rtwdev, u8 tx_path);
 	void (*bb_ctrl_rx_path)(struct rtw89_dev *rtwdev,
-				enum rtw89_rf_path_bit rx_path);
+				enum rtw89_rf_path_bit rx_path,
+				const struct rtw89_chan *chan);
 	void (*bb_set_plcp_tx)(struct rtw89_dev *rtwdev);
 	void (*bb_set_power)(struct rtw89_dev *rtwdev, s16 pwr_dbm,
 			     enum rtw89_phy_idx idx);
 	void (*bb_set_pmac_pkt_tx)(struct rtw89_dev *rtwdev, u8 enable,
 				   u16 tx_cnt, u16 period, u16 tx_time,
-				   enum rtw89_phy_idx idx);
+				   enum rtw89_phy_idx idx, const struct rtw89_chan *chan);
 	void (*bb_backup_tssi)(struct rtw89_dev *rtwdev, enum rtw89_phy_idx idx,
 			       struct rtw8852bx_bb_tssi_bak *bak);
 	void (*bb_restore_tssi)(struct rtw89_dev *rtwdev, enum rtw89_phy_idx idx,
@@ -207,9 +208,10 @@ void rtw8852bx_bb_cfg_tx_path(struct rtw89_dev *rtwdev, u8 tx_path)
 
 static inline
 void rtw8852bx_bb_ctrl_rx_path(struct rtw89_dev *rtwdev,
-			       enum rtw89_rf_path_bit rx_path)
+			       enum rtw89_rf_path_bit rx_path,
+			       const struct rtw89_chan *chan)
 {
-	rtw8852bx_info.bb_ctrl_rx_path(rtwdev, rx_path);
+	rtw8852bx_info.bb_ctrl_rx_path(rtwdev, rx_path, chan);
 }
 
 static inline
@@ -228,9 +230,10 @@ void rtw8852bx_bb_set_power(struct rtw89_dev *rtwdev, s16 pwr_dbm,
 static inline
 void rtw8852bx_bb_set_pmac_pkt_tx(struct rtw89_dev *rtwdev, u8 enable,
 				  u16 tx_cnt, u16 period, u16 tx_time,
-				  enum rtw89_phy_idx idx)
+				  enum rtw89_phy_idx idx, const struct rtw89_chan *chan)
 {
-	rtw8852bx_info.bb_set_pmac_pkt_tx(rtwdev, enable, tx_cnt, period, tx_time, idx);
+	rtw8852bx_info.bb_set_pmac_pkt_tx(rtwdev, enable, tx_cnt, period, tx_time, idx,
+					  chan);
 }
 
 static inline
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
index 776a45d1fe33..ef47a5facc83 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
@@ -1382,9 +1382,10 @@ static void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u
 	_iqk_info_iqk(rtwdev, phy_idx, path);
 }
 
-static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, u8 path)
+static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, u8 path,
+			     enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 reg_rf18;
 	u32 reg_35c;
@@ -1608,12 +1609,13 @@ static void _tmac_tx_pause(struct rtw89_dev *rtwdev, enum rtw89_phy_idx band_idx
 }
 
 static void _doiqk(struct rtw89_dev *rtwdev, bool force,
-		   enum rtw89_phy_idx phy_idx, u8 path)
+		   enum rtw89_phy_idx phy_idx, u8 path,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852B_IQK_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -1623,7 +1625,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	iqk_info->version = RTW8852B_IQK_VER;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]Test Ver 0x%x\n", iqk_info->version);
-	_iqk_get_ch_info(rtwdev, phy_idx, path);
+	_iqk_get_ch_info(rtwdev, phy_idx, path, chanctx_idx);
 
 	_rfk_backup_bb_reg(rtwdev, &backup_bb_val[0]);
 	_rfk_backup_rf_reg(rtwdev, &backup_rf_val[path][0], path);
@@ -1638,20 +1640,21 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force)
+static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	u8 kpath = _kpath(rtwdev, phy_idx);
 
 	switch (kpath) {
 	case RF_A:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
 		break;
 	case RF_B:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	case RF_AB:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	default:
 		break;
@@ -1761,9 +1764,9 @@ static void _dpk_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -1786,9 +1789,10 @@ static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 
 static void _dpk_bb_afe_setting(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy,
-				enum rtw89_rf_path path, u8 kpath)
+				enum rtw89_rf_path path, u8 kpath,
+				enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 
 	rtw89_rfk_parser(rtwdev, &rtw8852b_dpk_afe_defs_tbl);
 
@@ -1803,9 +1807,10 @@ static void _dpk_bb_afe_setting(struct rtw89_dev *rtwdev,
 
 static void _dpk_bb_afe_restore(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy,
-				enum rtw89_rf_path path, u8 kpath)
+				enum rtw89_rf_path path, u8 kpath,
+				enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 
 	rtw89_rfk_parser(rtwdev, &rtw8852b_dpk_afe_restore_defs_tbl);
 
@@ -2217,9 +2222,9 @@ static bool _dpk_pas_read(struct rtw89_dev *rtwdev, bool is_check)
 
 static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		   enum rtw89_rf_path path, u8 kidx, u8 init_txagc,
-		   bool loss_only)
+		   bool loss_only, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 step = DPK_AGC_STEP_SYNC_DGAIN;
 	u8 tmp_txagc, tmp_rxbb = 0, tmp_gl_idx = 0;
 	u8 goout = 0, agc_cnt = 0, limited_rxbb = 0;
@@ -2416,9 +2421,9 @@ static void _dpk_fill_result(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			      enum rtw89_rf_path path)
+			      enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	bool is_reload = false;
 	u8 idx, cur_band, cur_ch;
@@ -2443,7 +2448,8 @@ static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-		      enum rtw89_rf_path path, u8 gain)
+		      enum rtw89_rf_path path, u8 gain,
+		      enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 txagc = 0x38, kidx = dpk->cur_idx[path];
@@ -2464,7 +2470,7 @@ static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	_dpk_kip_set_rxagc(rtwdev, phy, path);
 	_dpk_table_select(rtwdev, path, kidx, gain);
 
-	txagc = _dpk_agc(rtwdev, phy, path, kidx, txagc, false);
+	txagc = _dpk_agc(rtwdev, phy, path, kidx, txagc, false, chanctx_idx);
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DPK] Adjust txagc = 0x%x\n", txagc);
 
 	if (txagc == 0xff) {
@@ -2491,7 +2497,8 @@ static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
-			    enum rtw89_phy_idx phy, u8 kpath)
+			    enum rtw89_phy_idx phy, u8 kpath,
+			    enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	static const u32 kip_reg[] = {0x813c, 0x8124, 0x8120};
@@ -2503,7 +2510,8 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 
 	if (dpk->is_dpk_reload_en) {
 		for (path = 0; path < RTW8852B_DPK_RF_PATH; path++) {
-			reloaded[path] = _dpk_reload_check(rtwdev, phy, path);
+			reloaded[path] = _dpk_reload_check(rtwdev, phy, path,
+							   chanctx_idx);
 			if (!reloaded[path] && dpk->bp[path][0].ch)
 				dpk->cur_idx[path] = !dpk->cur_idx[path];
 			else
@@ -2519,19 +2527,19 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 	for (path = 0; path < RTW8852B_DPK_RF_PATH; path++) {
 		_dpk_bkup_kip(rtwdev, kip_reg, kip_bkup, path);
 		_rfk_backup_rf_reg(rtwdev, &backup_rf_val[path][0], path);
-		_dpk_information(rtwdev, phy, path);
+		_dpk_information(rtwdev, phy, path, chanctx_idx);
 		if (rtwdev->is_tssi_mode[path])
 			_dpk_tssi_pause(rtwdev, path, true);
 	}
 
-	_dpk_bb_afe_setting(rtwdev, phy, path, kpath);
+	_dpk_bb_afe_setting(rtwdev, phy, path, kpath, chanctx_idx);
 
 	for (path = 0; path < RTW8852B_DPK_RF_PATH; path++) {
-		is_fail = _dpk_main(rtwdev, phy, path, 1);
+		is_fail = _dpk_main(rtwdev, phy, path, 1, chanctx_idx);
 		_dpk_onoff(rtwdev, path, is_fail);
 	}
 
-	_dpk_bb_afe_restore(rtwdev, phy, path, kpath);
+	_dpk_bb_afe_restore(rtwdev, phy, path, kpath, chanctx_idx);
 	_rfk_restore_bb_reg(rtwdev, &backup_bb_val[0]);
 
 	for (path = 0; path < RTW8852B_DPK_RF_PATH; path++) {
@@ -2543,9 +2551,10 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 	}
 }
 
-static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			      enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_fem_info *fem = &rtwdev->fem;
 
 	if (fem->epa_2g && chan->band_type == RTW89_BAND_2G) {
@@ -2577,17 +2586,18 @@ static void _dpk_force_bypass(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	}
 }
 
-static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force)
+static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[DPK] ****** DPK Start (Ver: 0x%x, Cv: %d, RF_para: %d) ******\n",
 		    RTW8852B_DPK_VER, rtwdev->hal.cv,
 		    RTW8852B_RF_REL_VERSION);
 
-	if (_dpk_bypass_check(rtwdev, phy))
+	if (_dpk_bypass_check(rtwdev, phy, chanctx_idx))
 		_dpk_force_bypass(rtwdev, phy);
 	else
-		_dpk_cal_select(rtwdev, force, phy, RF_AB);
+		_dpk_cal_select(rtwdev, force, phy, RF_AB, chanctx_idx);
 }
 
 static void _dpk_track(struct rtw89_dev *rtwdev)
@@ -2722,9 +2732,8 @@ static void _set_dpd_backoff(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 }
 
 static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (band == RTW89_BAND_2G)
@@ -2734,9 +2743,8 @@ static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			  enum rtw89_rf_path path)
+			  enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8852b_tssi_sys_defs_tbl);
@@ -2778,7 +2786,7 @@ static void _tssi_set_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 #define RTW8852B_TSSI_GET_VAL(ptr, idx)			\
 ({							\
@@ -2792,7 +2800,6 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	__val;						\
 })
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -2944,9 +2951,8 @@ static void _tssi_set_dac_gain_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 }
 
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				enum rtw89_rf_path path)
+				enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A)
@@ -2960,9 +2966,9 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 }
 
 static void _tssi_alignment_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				    enum rtw89_rf_path path, bool all)
+				    enum rtw89_rf_path path, bool all,
+				    const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	const struct rtw89_rfk_tbl *tbl = NULL;
 	u8 ch = chan->channel;
@@ -3231,10 +3237,9 @@ static u32 _tssi_get_trim_group(struct rtw89_dev *rtwdev, u8 ch)
 }
 
 static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			    enum rtw89_rf_path path)
+			    enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
 	s8 de_1st;
@@ -3267,10 +3272,9 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	s8 tde_1st;
@@ -3304,10 +3308,10 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	return val;
 }
 
-static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+				  const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3320,7 +3324,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx p
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8852B; i++) {
 		gidx = _tssi_get_cck_group(rtwdev, ch);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = tssi_info->tssi_cck[i][gidx] + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3336,8 +3340,8 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx p
 			    rtw89_phy_read32_mask(rtwdev, _tssi_de_cck_long[i],
 						  _TSSI_DE_MASK));
 
-		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i, chan);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = ofdm_de + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3383,10 +3387,10 @@ static void _tssi_alimentk_dump_result(struct rtw89_dev *rtwdev, enum rtw89_rf_p
 }
 
 static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
-				enum rtw89_phy_idx phy, enum rtw89_rf_path path)
+				enum rtw89_phy_idx phy, enum rtw89_rf_path path,
+				const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u8 band;
 
@@ -3420,7 +3424,7 @@ static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
 
 static void _tssi_hw_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			enum rtw89_rf_path path, u16 cnt, u16 period, s16 pwr_dbm,
-			u8 enable)
+			u8 enable, const struct rtw89_chan *chan)
 {
 	enum rtw89_rf_path_bit rx_path;
 
@@ -3436,11 +3440,11 @@ static void _tssi_hw_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	if (enable) {
 		rtw8852bx_bb_set_plcp_tx(rtwdev);
 		rtw8852bx_bb_cfg_tx_path(rtwdev, path);
-		rtw8852bx_bb_ctrl_rx_path(rtwdev, rx_path);
+		rtw8852bx_bb_ctrl_rx_path(rtwdev, rx_path, chan);
 		rtw8852bx_bb_set_power(rtwdev, pwr_dbm, phy);
 	}
 
-	rtw8852bx_bb_set_pmac_pkt_tx(rtwdev, enable, cnt, period, 20, phy);
+	rtw8852bx_bb_set_pmac_pkt_tx(rtwdev, enable, cnt, period, 20, phy, chan);
 }
 
 static void _tssi_backup_bb_registers(struct rtw89_dev *rtwdev,
@@ -3494,7 +3498,7 @@ static u8 _tssi_ch_to_idx(struct rtw89_dev *rtwdev, u8 channel)
 
 static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path, const s16 *power,
-				u32 *tssi_cw_rpt)
+				u32 *tssi_cw_rpt, const struct rtw89_chan *chan)
 {
 	u32 tx_counter, tx_counter_tmp;
 	const int retry = 100;
@@ -3513,9 +3517,10 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 			    _tssi_trigger[path], tmp, path);
 
 		if (j == 0)
-			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], true);
+			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], true, chan);
 		else
-			_tssi_hw_tx(rtwdev, phy, RF_PATH_ABCD, 100, 5000, power[j], true);
+			_tssi_hw_tx(rtwdev, phy, RF_PATH_ABCD, 100, 5000, power[j], true,
+				    chan);
 
 		tx_counter_tmp = rtw89_phy_read32_mask(rtwdev, R_TX_COUNTER, MASKLWORD);
 		tx_counter_tmp -= tx_counter;
@@ -3546,14 +3551,14 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 				    "[TSSI PA K] TSSI finish bit k > %d mp:100ms normal:30us path=%d\n",
 				    k, path);
 
-			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false);
+			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false, chan);
 			return false;
 		}
 
 		tssi_cw_rpt[j] =
 			rtw89_phy_read32_mask(rtwdev, _tssi_cw_rpt_addr[path], B_TSSI_CWRPT);
 
-		_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false);
+		_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false, chan);
 
 		tx_counter_tmp = rtw89_phy_read32_mask(rtwdev, R_TX_COUNTER, MASKLWORD);
 		tx_counter_tmp -= tx_counter;
@@ -3567,14 +3572,13 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 }
 
 static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			   enum rtw89_rf_path path)
+			   enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	static const u32 bb_reg[8] = {0x5820, 0x7820, 0x4978, 0x58e4,
 				      0x78e4, 0x49c0, 0x0d18, 0x0d80};
 	static const s16 power_2g[4] = {48, 20, 4, 4};
 	static const s16 power_5g[4] = {48, 20, 4, 4};
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	s32 tssi_alim_offset_1, tssi_alim_offset_2, tssi_alim_offset_3;
 	u32 tssi_cw_rpt[RTW8852B_TSSI_PATH_NR] = {0};
 	u8 channel = chan->channel;
@@ -3635,7 +3639,7 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	rtw89_phy_write32_mask(rtwdev, R_P0_TSSI_MV_AVG, B_P0_TSSI_MV_AVG, 0x2);
 	rtw89_phy_write32_mask(rtwdev, R_P1_TSSI_MV_AVG, B_P1_TSSI_MV_AVG, 0x2);
 
-	ok = _tssi_get_cw_report(rtwdev, phy, path, power, tssi_cw_rpt);
+	ok = _tssi_get_cw_report(rtwdev, phy, path, power, tssi_cw_rpt, chan);
 	if (!ok)
 		goto out;
 
@@ -3755,18 +3759,19 @@ void rtw8852b_rck(struct rtw89_dev *rtwdev)
 		_rck(rtwdev, path);
 }
 
-void rtw8852b_dack(struct rtw89_dev *rtwdev)
+void rtw8852b_dack(struct rtw89_dev *rtwdev, enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
 	_dac_cal(rtwdev, false);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_STOP);
 }
 
-void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
@@ -3774,15 +3779,16 @@ void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
 	_iqk_init(rtwdev);
-	_iqk(rtwdev, phy_idx, false);
+	_iqk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_STOP);
 }
 
-void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		     enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
@@ -3795,9 +3801,10 @@ void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_STOP);
 }
 
-void rtw8852b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
@@ -3806,7 +3813,7 @@ void rtw8852b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 
 	rtwdev->dpk.is_dpk_enable = true;
 	rtwdev->dpk.is_dpk_reload_en = false;
-	_dpk(rtwdev, phy_idx, false);
+	_dpk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_STOP);
@@ -3817,9 +3824,11 @@ void rtw8852b_dpk_track(struct rtw89_dev *rtwdev)
 	_dpk_track(rtwdev);
 }
 
-void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en)
+void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   bool hwtx_en, enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB, chanctx_idx);
 	u32 tx_en;
 	u8 i;
 
@@ -3829,34 +3838,34 @@ void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_e
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8852B; i++) {
-		_tssi_rf_setting(rtwdev, phy, i);
-		_tssi_set_sys(rtwdev, phy, i);
+		_tssi_rf_setting(rtwdev, phy, i, chan);
+		_tssi_set_sys(rtwdev, phy, i, chan);
 		_tssi_ini_txpwr_ctrl_bb(rtwdev, phy, i);
 		_tssi_ini_txpwr_ctrl_bb_he_tb(rtwdev, phy, i);
 		_tssi_set_dck(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
 		_tssi_set_dac_gain_tbl(rtwdev, phy, i);
-		_tssi_slope_cal_org(rtwdev, phy, i);
-		_tssi_alignment_default(rtwdev, phy, i, true);
+		_tssi_slope_cal_org(rtwdev, phy, i, chan);
+		_tssi_alignment_default(rtwdev, phy, i, true, chan);
 		_tssi_set_tssi_slope(rtwdev, phy, i);
 
 		rtw89_chip_stop_sch_tx(rtwdev, phy, &tx_en, RTW89_SCH_TX_SEL_ALL);
 		_tmac_tx_pause(rtwdev, phy, true);
 		if (hwtx_en)
-			_tssi_alimentk(rtwdev, phy, i);
+			_tssi_alimentk(rtwdev, phy, i, chan);
 		_tmac_tx_pause(rtwdev, phy, false);
 		rtw89_chip_resume_sch_tx(rtwdev, phy, tx_en);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	u8 channel = chan->channel;
 	u8 band;
@@ -3879,24 +3888,25 @@ void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RTW8852B_TSSI_PATH_NR; i++) {
-		_tssi_rf_setting(rtwdev, phy, i);
-		_tssi_set_sys(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
+		_tssi_rf_setting(rtwdev, phy, i, chan);
+		_tssi_set_sys(rtwdev, phy, i, chan);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
 
 		if (tssi_info->alignment_done[i][band])
-			_tssi_alimentk_done(rtwdev, phy, i);
+			_tssi_alimentk_done(rtwdev, phy, i, chan);
 		else
-			_tssi_alignment_default(rtwdev, phy, i, true);
+			_tssi_alignment_default(rtwdev, phy, i, true, chan);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 }
 
 static void rtw8852b_tssi_default_txagc(struct rtw89_dev *rtwdev,
-					enum rtw89_phy_idx phy, bool enable)
+					enum rtw89_phy_idx phy, bool enable,
+					enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 channel = chan->channel;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "======> %s   ch=%d\n",
@@ -3904,7 +3914,7 @@ static void rtw8852b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 
 	if (enable) {
 		if (!rtwdev->is_tssi_mode[RF_PATH_A] && !rtwdev->is_tssi_mode[RF_PATH_B])
-			rtw8852b_tssi(rtwdev, phy, true);
+			rtw8852b_tssi(rtwdev, phy, true, chanctx_idx);
 		return;
 	}
 
@@ -3921,8 +3931,8 @@ static void rtw8852b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 	rtw89_phy_write32_mask(rtwdev, R_P1_TSSI_TRK, B_P1_TSSI_OFT_EN, 0x0);
 	rtw89_phy_write32_mask(rtwdev, R_P1_TSSI_TRK, B_P1_TSSI_OFT_EN, 0x1);
 
-	_tssi_alimentk_done(rtwdev, phy, RF_PATH_A);
-	_tssi_alimentk_done(rtwdev, phy, RF_PATH_B);
+	_tssi_alimentk_done(rtwdev, phy, RF_PATH_A, chan);
+	_tssi_alimentk_done(rtwdev, phy, RF_PATH_B, chan);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "======>%s 2 SCAN_END Set 0x5818[7:0]=0x%x 0x7818[7:0]=0x%x\n",
@@ -3935,12 +3945,13 @@ static void rtw8852b_tssi_default_txagc(struct rtw89_dev *rtwdev,
 }
 
 void rtw8852b_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
-			       enum rtw89_phy_idx phy_idx)
+			       enum rtw89_phy_idx phy_idx,
+			       enum rtw89_chanctx_idx chanctx_idx)
 {
 	if (scan_start)
-		rtw8852b_tssi_default_txagc(rtwdev, phy_idx, true);
+		rtw8852b_tssi_default_txagc(rtwdev, phy_idx, true, chanctx_idx);
 	else
-		rtw8852b_tssi_default_txagc(rtwdev, phy_idx, false);
+		rtw8852b_tssi_default_txagc(rtwdev, phy_idx, false, chanctx_idx);
 }
 
 static void _bw_setting(struct rtw89_dev *rtwdev, enum rtw89_rf_path path,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.h
index f52832065600..c31ba446e6e0 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.h
@@ -8,16 +8,22 @@
 #include "core.h"
 
 void rtw8852b_rck(struct rtw89_dev *rtwdev);
-void rtw8852b_dack(struct rtw89_dev *rtwdev);
-void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
+void rtw8852b_dack(struct rtw89_dev *rtwdev, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852b_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852b_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		     enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852b_dpk_init(struct rtw89_dev *rtwdev);
-void rtw8852b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8852b_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852b_dpk_track(struct rtw89_dev *rtwdev);
-void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en);
-void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8852b_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   bool hwtx_en, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852b_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan);
 void rtw8852b_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
-			       enum rtw89_phy_idx phy_idx);
+			       enum rtw89_phy_idx phy_idx,
+			       enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852b_set_channel_rf(struct rtw89_dev *rtwdev,
 			     const struct rtw89_chan *chan,
 			     enum rtw89_phy_idx phy_idx);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 5eb38370aba4..f7d133ac34de 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -480,12 +480,12 @@ static void rtw8852bt_tssi_cont_en(struct rtw89_dev *rtwdev, bool en,
 }
 
 static void rtw8852bt_tssi_cont_en_phyidx(struct rtw89_dev *rtwdev, bool en,
-					  u8 phy_idx)
+					  u8 phy_idx, const struct rtw89_chan *chan)
 {
 	if (!rtwdev->dbcc_en) {
 		rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_A);
 		rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_B);
-		rtw8852bt_tssi_scan(rtwdev, phy_idx);
+		rtw8852bt_tssi_scan(rtwdev, phy_idx, chan);
 	} else {
 		if (phy_idx == RTW89_PHY_0)
 			rtw8852bt_tssi_cont_en(rtwdev, en, RF_PATH_A);
@@ -511,14 +511,14 @@ static void rtw8852bt_set_channel_help(struct rtw89_dev *rtwdev, bool enter,
 	if (enter) {
 		rtw89_chip_stop_sch_tx(rtwdev, RTW89_MAC_0, &p->tx_en, RTW89_SCH_TX_SEL_ALL);
 		rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, false);
-		rtw8852bt_tssi_cont_en_phyidx(rtwdev, false, RTW89_PHY_0);
+		rtw8852bt_tssi_cont_en_phyidx(rtwdev, false, RTW89_PHY_0, chan);
 		rtw8852bt_adc_en(rtwdev, false);
 		fsleep(40);
 		rtw8852bt_bb_reset_en(rtwdev, chan->band_type, phy_idx, false);
 	} else {
 		rtw89_mac_cfg_ppdu_status(rtwdev, RTW89_MAC_0, true);
 		rtw8852bt_adc_en(rtwdev, true);
-		rtw8852bt_tssi_cont_en_phyidx(rtwdev, true, RTW89_PHY_0);
+		rtw8852bt_tssi_cont_en_phyidx(rtwdev, true, RTW89_PHY_0, chan);
 		rtw8852bt_bb_reset_en(rtwdev, chan->band_type, phy_idx, true);
 		rtw89_chip_resume_sch_tx(rtwdev, RTW89_MAC_0, p->tx_en);
 	}
@@ -531,31 +531,32 @@ static void rtw8852bt_rfk_init(struct rtw89_dev *rtwdev)
 
 	rtw8852bt_dpk_init(rtwdev);
 	rtw8852bt_rck(rtwdev);
-	rtw8852bt_dack(rtwdev);
-	rtw8852bt_rx_dck(rtwdev, RTW89_PHY_0);
+	rtw8852bt_dack(rtwdev, RTW89_CHANCTX_0);
+	rtw8852bt_rx_dck(rtwdev, RTW89_PHY_0, RTW89_CHANCTX_0);
 }
 
 static void rtw8852bt_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	enum rtw89_chanctx_idx chanctx_idx = rtwvif->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
-	rtw8852bt_rx_dck(rtwdev, phy_idx);
-	rtw8852bt_iqk(rtwdev, phy_idx);
-	rtw8852bt_tssi(rtwdev, phy_idx, true);
-	rtw8852bt_dpk(rtwdev, phy_idx);
+	rtw8852bt_rx_dck(rtwdev, phy_idx, chanctx_idx);
+	rtw8852bt_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw8852bt_tssi(rtwdev, phy_idx, true, chanctx_idx);
+	rtw8852bt_dpk(rtwdev, phy_idx, chanctx_idx);
 }
 
 static void rtw8852bt_rfk_band_changed(struct rtw89_dev *rtwdev,
 				       enum rtw89_phy_idx phy_idx,
 				       const struct rtw89_chan *chan)
 {
-	rtw8852bt_tssi_scan(rtwdev, phy_idx);
+	rtw8852bt_tssi_scan(rtwdev, phy_idx, chan);
 }
 
 static void rtw8852bt_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			       bool start)
 {
-	rtw8852bt_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx);
+	rtw8852bt_wifi_scan_notify(rtwdev, start, rtwvif->phy_idx, rtwvif->chanctx_idx);
 }
 
 static void rtw8852bt_rfk_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index 278f907fd895..336a83e1d46b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -1525,9 +1525,10 @@ static void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u
 		    lok_result, txk_result, rxk_result);
 }
 
-static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, u8 path)
+static void _iqk_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, u8 path,
+			     enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u8 get_empty_table = false;
 	u32 reg_rf18;
@@ -1755,12 +1756,13 @@ static void _tmac_tx_pause(struct rtw89_dev *rtwdev, enum rtw89_phy_idx band_idx
 }
 
 static void _doiqk(struct rtw89_dev *rtwdev, bool force,
-		   enum rtw89_phy_idx phy_idx, u8 path)
+		   enum rtw89_phy_idx phy_idx, u8 path,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852BT_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -1770,7 +1772,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	iqk_info->version = RTW8852BT_IQK_VER;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]Test Ver 0x%x\n", iqk_info->version);
-	_iqk_get_ch_info(rtwdev, phy_idx, path);
+	_iqk_get_ch_info(rtwdev, phy_idx, path, chanctx_idx);
 
 	_rfk_backup_bb_reg(rtwdev, backup_bb_val);
 	_rfk_backup_rf_reg(rtwdev, backup_rf_val[path], path);
@@ -1785,20 +1787,21 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force)
+static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	u8 kpath = _kpath(rtwdev, phy_idx);
 
 	switch (kpath) {
 	case RF_A:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
 		break;
 	case RF_B:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	case RF_AB:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	default:
 		break;
@@ -1879,9 +1882,9 @@ static void _dpk_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _dpk_information(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -2277,9 +2280,9 @@ static bool _dpk_pas_read(struct rtw89_dev *rtwdev, enum rtw89_rf_path path,
 
 static u8 _dpk_agc(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		   enum rtw89_rf_path path, u8 kidx, u8 init_txagc,
-		   bool loss_only)
+		   bool loss_only, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 goout = 0, agc_cnt = 0, limited_rxbb = 0, gl_cnt = 0;
 	u8 tmp_txagc, tmp_rxbb, tmp_gl_idx = 0;
@@ -2504,9 +2507,9 @@ static void _dpk_fill_result(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			      enum rtw89_rf_path path)
+			      enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 idx, cur_band, cur_ch;
 	bool is_reload = false;
@@ -2549,7 +2552,8 @@ void _drf_direct_cntrl(struct rtw89_dev *rtwdev, enum rtw89_rf_path path, bool i
 }
 
 static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-		      enum rtw89_rf_path path, u8 gain)
+		      enum rtw89_rf_path path, u8 gain,
+		      enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u8 txagc = 0x38, kidx = dpk->cur_idx[path];
@@ -2569,7 +2573,7 @@ static bool _dpk_main(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	_dpk_kip_set_rxagc(rtwdev, phy, path);
 	_dpk_table_select(rtwdev, path, kidx, gain);
 
-	txagc = _dpk_agc(rtwdev, phy, path, kidx, txagc, false);
+	txagc = _dpk_agc(rtwdev, phy, path, kidx, txagc, false, chanctx_idx);
 
 	_rfk_get_thermal(rtwdev, kidx, path);
 
@@ -2601,7 +2605,8 @@ _error:
 }
 
 static void _dpk_cal_select(struct rtw89_dev *rtwdev,
-			    enum rtw89_phy_idx phy, u8 kpath)
+			    enum rtw89_phy_idx phy, u8 kpath,
+			    enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	u32 backup_kip_val[BACKUP_KIP_REGS_NR];
@@ -2611,7 +2616,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev,
 	u8 path;
 
 	for (path = 0; path < DPK_RF_PATH_MAX_8852BT; path++) {
-		reloaded[path] = _dpk_reload_check(rtwdev, phy, path);
+		reloaded[path] = _dpk_reload_check(rtwdev, phy, path, chanctx_idx);
 		if (!reloaded[path] && dpk->bp[path][0].ch != 0)
 			dpk->cur_idx[path] = !dpk->cur_idx[path];
 		else
@@ -2623,7 +2628,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev,
 
 	for (path = 0; path < DPK_RF_PATH_MAX_8852BT; path++) {
 		_rfk_backup_rf_reg(rtwdev, backup_rf_val[path], path);
-		_dpk_information(rtwdev, phy, path);
+		_dpk_information(rtwdev, phy, path, chanctx_idx);
 		if (rtwdev->is_tssi_mode[path])
 			_dpk_tssi_pause(rtwdev, path, true);
 	}
@@ -2631,7 +2636,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev,
 	_rfk_bb_afe_setting(rtwdev, phy, path, kpath);
 
 	for (path = 0; path < DPK_RF_PATH_MAX_8852BT; path++)
-		_dpk_main(rtwdev, phy, path, 1);
+		_dpk_main(rtwdev, phy, path, 1, chanctx_idx);
 
 	_rfk_bb_afe_restore(rtwdev, phy, path, kpath);
 
@@ -2646,9 +2651,10 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev,
 	}
 }
 
-static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			      enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_fem_info *fem = &rtwdev->fem;
 
 	if (fem->epa_2g && chan->band_type == RTW89_BAND_2G) {
@@ -2817,9 +2823,8 @@ static void _tssi_dpk_off(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 }
 
 static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (band == RTW89_BAND_2G)
@@ -2829,9 +2834,8 @@ static void _tssi_rf_setting(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			  enum rtw89_rf_path path)
+			  enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	rtw89_rfk_parser(rtwdev, &rtw8852bt_tssi_sys_defs_tbl);
@@ -2878,7 +2882,7 @@ static void _tssi_set_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 #define RTW8852BT_TSSI_GET_VAL(ptr, idx)			\
 ({							\
@@ -2893,7 +2897,6 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 })
 	struct rtw89_fw_txpwr_track_cfg *trk = rtwdev->fw.elm_info.txpwr_trk;
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 subband = chan->subband_type;
 	const s8 *thm_up_a = NULL;
@@ -3047,9 +3050,8 @@ static void _tssi_set_dac_gain_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 }
 
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				enum rtw89_rf_path path)
+				enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A)
@@ -3063,9 +3065,9 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 }
 
 static void _tssi_alignment_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				    enum rtw89_rf_path path, bool all)
+				    enum rtw89_rf_path path, bool all,
+				    const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	const struct rtw89_rfk_tbl *tbl = NULL;
 	u8 ch = chan->channel;
@@ -3310,10 +3312,9 @@ static u32 _tssi_get_trim_group(struct rtw89_dev *rtwdev, u8 ch)
 }
 
 static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			    enum rtw89_rf_path path)
+			    enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
 	s8 de_1st;
@@ -3346,10 +3347,9 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
 	s8 tde_1st;
@@ -3383,10 +3383,10 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	return val;
 }
 
-static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+				  const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3399,7 +3399,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx p
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8852BT; i++) {
 		gidx = _tssi_get_cck_group(rtwdev, ch);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = tssi_info->tssi_cck[i][gidx] + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3415,8 +3415,8 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx p
 			    rtw89_phy_read32_mask(rtwdev, _tssi_de_cck_long[i],
 						  _TSSI_DE_MASK));
 
-		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i, chan);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = ofdm_de + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3463,10 +3463,10 @@ static void _tssi_alimentk_dump_result(struct rtw89_dev *rtwdev, enum rtw89_rf_p
 }
 
 static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
-				enum rtw89_phy_idx phy, enum rtw89_rf_path path)
+				enum rtw89_phy_idx phy, enum rtw89_rf_path path,
+				const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 channel = chan->channel;
 	u8 band;
 
@@ -3500,7 +3500,7 @@ static void _tssi_alimentk_done(struct rtw89_dev *rtwdev,
 
 static void _tssi_hw_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 			enum rtw89_rf_path path, u16 cnt, u16 period, s16 pwr_dbm,
-			u8 enable)
+			u8 enable, const struct rtw89_chan *chan)
 {
 	enum rtw89_rf_path_bit rx_path;
 
@@ -3516,11 +3516,11 @@ static void _tssi_hw_tx(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	if (enable) {
 		rtw8852bx_bb_set_plcp_tx(rtwdev);
 		rtw8852bx_bb_cfg_tx_path(rtwdev, path);
-		rtw8852bx_bb_ctrl_rx_path(rtwdev, rx_path);
+		rtw8852bx_bb_ctrl_rx_path(rtwdev, rx_path, chan);
 		rtw8852bx_bb_set_power(rtwdev, pwr_dbm, phy);
 	}
 
-	rtw8852bx_bb_set_pmac_pkt_tx(rtwdev, enable, cnt, period, 20, phy);
+	rtw8852bx_bb_set_pmac_pkt_tx(rtwdev, enable, cnt, period, 20, phy, chan);
 }
 
 static void _tssi_backup_bb_registers(struct rtw89_dev *rtwdev,
@@ -3574,7 +3574,7 @@ static u8 _tssi_ch_to_idx(struct rtw89_dev *rtwdev, u8 channel)
 
 static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 				enum rtw89_rf_path path, const s16 *power,
-				u32 *tssi_cw_rpt)
+				u32 *tssi_cw_rpt, const struct rtw89_chan *chan)
 {
 	u32 tx_counter, tx_counter_tmp;
 	const int retry = 100;
@@ -3593,9 +3593,11 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 			    _tssi_trigger[path], tmp, path);
 
 		if (j == 0)
-			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], true);
+			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], true,
+				    chan);
 		else
-			_tssi_hw_tx(rtwdev, phy, RF_PATH_ABCD, 100, 5000, power[j], true);
+			_tssi_hw_tx(rtwdev, phy, RF_PATH_ABCD, 100, 5000, power[j], true,
+				    chan);
 
 		tx_counter_tmp = rtw89_phy_read32_mask(rtwdev, R_TX_COUNTER, MASKLWORD);
 		tx_counter_tmp -= tx_counter;
@@ -3626,7 +3628,7 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 				    "[TSSI PA K] TSSI finish bit k > %d mp:100ms normal:30us path=%d\n",
 				    k, path);
 
-			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false);
+			_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false, chan);
 			return false;
 		}
 
@@ -3634,7 +3636,7 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 			rtw89_phy_read32_mask(rtwdev, _tssi_cw_rpt_addr[path],
 					      B_TSSI_CWRPT);
 
-		_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false);
+		_tssi_hw_tx(rtwdev, phy, path, 100, 5000, power[j], false, chan);
 
 		tx_counter_tmp = rtw89_phy_read32_mask(rtwdev, R_TX_COUNTER, MASKLWORD);
 		tx_counter_tmp -= tx_counter;
@@ -3648,14 +3650,13 @@ static bool _tssi_get_cw_report(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 }
 
 static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			   enum rtw89_rf_path path)
+			   enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	static const u32 bb_reg[8] = {0x5820, 0x7820, 0x4978, 0x58e4,
 				      0x78e4, 0x49c0, 0x0d18, 0x0d80};
 	static const s16 power_2g[4] = {48, 20, 4, -8};
 	static const s16 power_5g[4] = {48, 20, 4, 4};
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	s32 tssi_alim_offset_1, tssi_alim_offset_2, tssi_alim_offset_3;
 	u32 tssi_cw_rpt[RTW8852BT_TSSI_PATH_NR] = {};
 	u8 channel = chan->channel;
@@ -3701,7 +3702,7 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	rtw89_phy_write32_mask(rtwdev, R_P0_TSSI_MV_AVG, B_P0_TSSI_MV_AVG, 0x2);
 	rtw89_phy_write32_mask(rtwdev, R_P1_TSSI_MV_AVG, B_P1_TSSI_MV_AVG, 0x2);
 
-	ok = _tssi_get_cw_report(rtwdev, phy, path, power, tssi_cw_rpt);
+	ok = _tssi_get_cw_report(rtwdev, phy, path, power, tssi_cw_rpt, chan);
 	if (!ok)
 		goto out;
 
@@ -3833,18 +3834,19 @@ void rtw8852bt_rck(struct rtw89_dev *rtwdev)
 		_rck(rtwdev, path);
 }
 
-void rtw8852bt_dack(struct rtw89_dev *rtwdev)
+void rtw8852bt_dack(struct rtw89_dev *rtwdev, enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
 	_dac_cal(rtwdev, false);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_STOP);
 }
 
-void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
@@ -3852,15 +3854,16 @@ void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
 	_iqk_init(rtwdev);
-	_iqk(rtwdev, phy_idx, false);
+	_iqk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_STOP);
 }
 
-void rtw8852bt_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852bt_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		      enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_START);
@@ -3873,15 +3876,16 @@ void rtw8852bt_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_RXDCK, BTC_WRFK_STOP);
 }
 
-void rtw8852bt_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852bt_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[DPK] ****** DPK Start (Ver: 0x%x) ******\n", RTW8852BT_DPK_VER);
 
-	if (_dpk_bypass_check(rtwdev, phy_idx))
+	if (_dpk_bypass_check(rtwdev, phy_idx, chanctx_idx))
 		_dpk_force_bypass(rtwdev, phy_idx);
 	else
-		_dpk_cal_select(rtwdev, phy_idx, RF_AB);
+		_dpk_cal_select(rtwdev, phy_idx, RF_AB, chanctx_idx);
 }
 
 void rtw8852bt_dpk_track(struct rtw89_dev *rtwdev)
@@ -3889,10 +3893,12 @@ void rtw8852bt_dpk_track(struct rtw89_dev *rtwdev)
 	_dpk_track(rtwdev);
 }
 
-void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en)
+void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		    bool hwtx_en, enum rtw89_chanctx_idx chanctx_idx)
 {
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	static const u32 reg[2] = {R_DPD_CH0A, R_DPD_CH0B};
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy, RF_AB, chanctx_idx);
 	u32 reg_backup[2] = {};
 	u32 tx_en;
 	u8 i;
@@ -3905,36 +3911,36 @@ void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RF_PATH_NUM_8852BT; i++) {
-		_tssi_rf_setting(rtwdev, phy, i);
-		_tssi_set_sys(rtwdev, phy, i);
+		_tssi_rf_setting(rtwdev, phy, i, chan);
+		_tssi_set_sys(rtwdev, phy, i, chan);
 		_tssi_ini_txpwr_ctrl_bb(rtwdev, phy, i);
 		_tssi_ini_txpwr_ctrl_bb_he_tb(rtwdev, phy, i);
 		_tssi_set_dck(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
 		_tssi_set_dac_gain_tbl(rtwdev, phy, i);
-		_tssi_slope_cal_org(rtwdev, phy, i);
-		_tssi_alignment_default(rtwdev, phy, i, true);
+		_tssi_slope_cal_org(rtwdev, phy, i, chan);
+		_tssi_alignment_default(rtwdev, phy, i, true, chan);
 		_tssi_set_tssi_slope(rtwdev, phy, i);
 
 		rtw89_chip_stop_sch_tx(rtwdev, phy, &tx_en, RTW89_SCH_TX_SEL_ALL);
 		_tmac_tx_pause(rtwdev, phy, true);
 		if (hwtx_en)
-			_tssi_alimentk(rtwdev, phy, i);
+			_tssi_alimentk(rtwdev, phy, i, chan);
 		_tmac_tx_pause(rtwdev, phy, false);
 		rtw89_chip_resume_sch_tx(rtwdev, phy, tx_en);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 
 	_tssi_reload_bb_registers(rtwdev, phy, reg, reg_backup, 2);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			 const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	u8 channel = chan->channel;
 	u8 band;
@@ -3957,24 +3963,25 @@ void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = RF_PATH_A; i < RTW8852BT_TSSI_PATH_NR; i++) {
-		_tssi_rf_setting(rtwdev, phy, i);
-		_tssi_set_sys(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
+		_tssi_rf_setting(rtwdev, phy, i, chan);
+		_tssi_set_sys(rtwdev, phy, i, chan);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
 
 		if (tssi_info->alignment_done[i][band])
-			_tssi_alimentk_done(rtwdev, phy, i);
+			_tssi_alimentk_done(rtwdev, phy, i, chan);
 		else
-			_tssi_alignment_default(rtwdev, phy, i, true);
+			_tssi_alignment_default(rtwdev, phy, i, true, chan);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 }
 
 static void rtw8852bt_tssi_default_txagc(struct rtw89_dev *rtwdev,
-					 enum rtw89_phy_idx phy, bool enable)
+					 enum rtw89_phy_idx phy, bool enable,
+					 enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 channel = chan->channel;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "======> %s   ch=%d\n",
@@ -3996,8 +4003,8 @@ static void rtw8852bt_tssi_default_txagc(struct rtw89_dev *rtwdev,
 	rtw89_phy_write32_mask(rtwdev, R_P1_TSSI_TRK, B_P1_TSSI_OFT_EN, 0x0);
 	rtw89_phy_write32_mask(rtwdev, R_P1_TSSI_TRK, B_P1_TSSI_OFT_EN, 0x1);
 
-	_tssi_alimentk_done(rtwdev, phy, RF_PATH_A);
-	_tssi_alimentk_done(rtwdev, phy, RF_PATH_B);
+	_tssi_alimentk_done(rtwdev, phy, RF_PATH_A, chan);
+	_tssi_alimentk_done(rtwdev, phy, RF_PATH_B, chan);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "======>%s 2 SCAN_END Set 0x5818[7:0]=0x%x 0x7818[7:0]=0x%x\n",
@@ -4010,12 +4017,13 @@ static void rtw8852bt_tssi_default_txagc(struct rtw89_dev *rtwdev,
 }
 
 void rtw8852bt_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
-				enum rtw89_phy_idx phy_idx)
+				enum rtw89_phy_idx phy_idx,
+				enum rtw89_chanctx_idx chanctx_idx)
 {
 	if (scan_start)
-		rtw8852bt_tssi_default_txagc(rtwdev, phy_idx, true);
+		rtw8852bt_tssi_default_txagc(rtwdev, phy_idx, true, chanctx_idx);
 	else
-		rtw8852bt_tssi_default_txagc(rtwdev, phy_idx, false);
+		rtw8852bt_tssi_default_txagc(rtwdev, phy_idx, false, chanctx_idx);
 }
 
 static void _bw_setting(struct rtw89_dev *rtwdev, enum rtw89_rf_path path,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h
index ef3d98f80400..e34560b4905f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.h
@@ -8,16 +8,22 @@
 #include "core.h"
 
 void rtw8852bt_rck(struct rtw89_dev *rtwdev);
-void rtw8852bt_dack(struct rtw89_dev *rtwdev);
-void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-void rtw8852bt_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
+void rtw8852bt_dack(struct rtw89_dev *rtwdev, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852bt_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		   enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852bt_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		      enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852bt_dpk_init(struct rtw89_dev *rtwdev);
-void rtw8852bt_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8852bt_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		   enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852bt_dpk_track(struct rtw89_dev *rtwdev);
-void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool hwtx_en);
-void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8852bt_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		    bool hwtx_en, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852bt_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			 const struct rtw89_chan *chan);
 void rtw8852bt_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
-				enum rtw89_phy_idx phy_idx);
+				enum rtw89_phy_idx phy_idx,
+				enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852bt_set_channel_rf(struct rtw89_dev *rtwdev,
 			      const struct rtw89_chan *chan,
 			      enum rtw89_phy_idx phy_idx);
-- 
cgit v1.3-3-g829e


From 395bd59c95fdcc6a3305d5ac3132f029ad61ca98 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:21 +0800
Subject: wifi: rtw89: 8852c: use right chanctx whenever possible in RFK flow

No longer access chan with hard-code RTW89_CHANCTX_X whenever possible.
Instead, obtain the right chanctx from somewhere and use it in RTL8852C
RFK (RF calibration) related code.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8852c.c     |  15 +-
 drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c | 162 ++++++++++++----------
 drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h |  17 ++-
 3 files changed, 104 insertions(+), 90 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 1fde8a07f73c..d4adab43f4f2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -1817,7 +1817,7 @@ static void rtw8852c_set_channel_help(struct rtw89_dev *rtwdev, bool enter,
 				       RTW89_SCH_TX_SEL_ALL);
 		rtw89_mac_cfg_ppdu_status(rtwdev, mac_idx, false);
 		rtw8852c_dfs_en(rtwdev, false);
-		rtw8852c_tssi_cont_en_phyidx(rtwdev, false, phy_idx);
+		rtw8852c_tssi_cont_en_phyidx(rtwdev, false, phy_idx, chan);
 		rtw8852c_adc_en(rtwdev, false);
 		fsleep(40);
 		rtw8852c_bb_reset_en(rtwdev, chan->band_type, phy_idx, false);
@@ -1825,7 +1825,7 @@ static void rtw8852c_set_channel_help(struct rtw89_dev *rtwdev, bool enter,
 		rtw89_mac_cfg_ppdu_status(rtwdev, mac_idx, true);
 		rtw8852c_adc_en(rtwdev, true);
 		rtw8852c_dfs_en(rtwdev, true);
-		rtw8852c_tssi_cont_en_phyidx(rtwdev, true, phy_idx);
+		rtw8852c_tssi_cont_en_phyidx(rtwdev, true, phy_idx, chan);
 		rtw8852c_bb_reset_en(rtwdev, chan->band_type, phy_idx, true);
 		rtw89_chip_resume_sch_tx(rtwdev, mac_idx, p->tx_en);
 	}
@@ -1842,19 +1842,20 @@ static void rtw8852c_rfk_init(struct rtw89_dev *rtwdev)
 	rtw8852c_dpk_init(rtwdev);
 
 	rtw8852c_rck(rtwdev);
-	rtw8852c_dack(rtwdev);
+	rtw8852c_dack(rtwdev, RTW89_CHANCTX_0);
 	rtw8852c_rx_dck(rtwdev, RTW89_PHY_0, false);
 }
 
 static void rtw8852c_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	enum rtw89_chanctx_idx chanctx_idx = rtwvif->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
 
 	rtw8852c_mcc_get_ch_info(rtwdev, phy_idx);
 	rtw8852c_rx_dck(rtwdev, phy_idx, false);
-	rtw8852c_iqk(rtwdev, phy_idx);
-	rtw8852c_tssi(rtwdev, phy_idx);
-	rtw8852c_dpk(rtwdev, phy_idx);
+	rtw8852c_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw8852c_tssi(rtwdev, phy_idx, chanctx_idx);
+	rtw8852c_dpk(rtwdev, phy_idx, chanctx_idx);
 	rtw89_fw_h2c_rf_ntfy_mcc(rtwdev);
 }
 
@@ -1862,7 +1863,7 @@ static void rtw8852c_rfk_band_changed(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_idx phy_idx,
 				      const struct rtw89_chan *chan)
 {
-	rtw8852c_tssi_scan(rtwdev, phy_idx);
+	rtw8852c_tssi_scan(rtwdev, phy_idx, chan);
 }
 
 static void rtw8852c_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
index 8fee820be258..211c051c2967 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c
@@ -585,11 +585,12 @@ static void _drck(struct rtw89_dev *rtwdev)
 		    rtw89_phy_read32_mask(rtwdev, R_DRCK, MASKDWORD));
 }
 
-static void _dac_cal(struct rtw89_dev *rtwdev, bool force)
+static void _dac_cal(struct rtw89_dev *rtwdev, bool force,
+		     enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dack_info *dack = &rtwdev->dack;
 	u32 rf0_0, rf1_0;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, RF_AB, chanctx_idx);
 
 	dack->dack_done = false;
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[DACK]DACK b\n");
@@ -1322,9 +1323,10 @@ static void _iqk_by_path(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, u
 }
 
 static void _iqk_get_ch_info(struct rtw89_dev *rtwdev,
-			     enum rtw89_phy_idx phy, u8 path)
+			     enum rtw89_phy_idx phy, u8 path,
+			     enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]===>%s\n", __func__);
@@ -1517,12 +1519,13 @@ static void _iqk_init(struct rtw89_dev *rtwdev)
 }
 
 static void _doiqk(struct rtw89_dev *rtwdev, bool force,
-		   enum rtw89_phy_idx phy_idx, u8 path)
+		   enum rtw89_phy_idx phy_idx, u8 path,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_iqk_info *iqk_info = &rtwdev->iqk;
 	u32 backup_bb_val[BACKUP_BB_REGS_NR];
 	u32 backup_rf_val[RTW8852C_IQK_SS][BACKUP_RF_REGS_NR];
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_START);
 
@@ -1532,7 +1535,7 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	iqk_info->version = RTW8852C_IQK_VER;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK, "[IQK]Test Ver 0x%x\n", iqk_info->version);
-	_iqk_get_ch_info(rtwdev, phy_idx, path);
+	_iqk_get_ch_info(rtwdev, phy_idx, path, chanctx_idx);
 	_rfk_backup_bb_reg(rtwdev, backup_bb_val);
 	_rfk_backup_rf_reg(rtwdev, backup_rf_val[path], path);
 	_iqk_macbb_setting(rtwdev, phy_idx, path);
@@ -1545,18 +1548,19 @@ static void _doiqk(struct rtw89_dev *rtwdev, bool force,
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_ONESHOT_STOP);
 }
 
-static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force)
+static void _iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	switch (_kpath(rtwdev, phy_idx)) {
 	case RF_A:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
 		break;
 	case RF_B:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	case RF_AB:
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_A);
-		_doiqk(rtwdev, force, phy_idx, RF_PATH_B);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_A, chanctx_idx);
+		_doiqk(rtwdev, force, phy_idx, RF_PATH_B, chanctx_idx);
 		break;
 	default:
 		break;
@@ -1902,9 +1906,9 @@ static u8 _dpk_one_shot(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 
 static void _dpk_information(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy,
-			     enum rtw89_rf_path path)
+			     enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 
 	u8 kidx = dpk->cur_idx[path];
@@ -2496,9 +2500,9 @@ static void _dpk_idl_mpa(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 }
 
 static bool _dpk_reload_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			      enum rtw89_rf_path path)
+			      enum rtw89_rf_path path, enum rtw89_chanctx_idx chanctx_idx)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	bool is_reload = false;
 	u8 idx, cur_band, cur_ch;
@@ -2690,7 +2694,8 @@ static void _dpk_drf_direct_cntrl(struct rtw89_dev *rtwdev, u8 path, bool is_byb
 }
 
 static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
-			    enum rtw89_phy_idx phy, u8 kpath)
+			    enum rtw89_phy_idx phy, u8 kpath,
+			    enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_dpk_info *dpk = &rtwdev->dpk;
 	static const u32 kip_reg[] = {0x813c, 0x8124, 0x8120, 0xc0c4, 0xc0e8, 0xc0d4, 0xc0d8};
@@ -2706,7 +2711,8 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 			if (!(kpath & BIT(path)))
 				continue;
 
-			reloaded[path] = _dpk_reload_check(rtwdev, phy, path);
+			reloaded[path] = _dpk_reload_check(rtwdev, phy, path,
+							   chanctx_idx);
 			if (!reloaded[path] && dpk->bp[path][0].ch != 0)
 				dpk->cur_idx[path] = !dpk->cur_idx[path];
 			else
@@ -2723,7 +2729,7 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 			    path, dpk->cur_idx[path]);
 		_dpk_bkup_kip(rtwdev, kip_reg, kip_bkup, path);
 		_rfk_backup_rf_reg(rtwdev, backup_rf_val[path], path);
-		_dpk_information(rtwdev, phy, path);
+		_dpk_information(rtwdev, phy, path, chanctx_idx);
 		_dpk_init(rtwdev, path);
 		if (rtwdev->is_tssi_mode[path])
 			_dpk_tssi_pause(rtwdev, path, true);
@@ -2756,10 +2762,11 @@ static void _dpk_cal_select(struct rtw89_dev *rtwdev, bool force,
 	_dpk_kip_pwr_clk_onoff(rtwdev, false);
 }
 
-static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+static bool _dpk_bypass_check(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			      enum rtw89_chanctx_idx chanctx_idx)
 {
 	struct rtw89_fem_info *fem = &rtwdev->fem;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u8 band = chan->band_type;
 
 	if (rtwdev->hal.cv == CHIP_CAV && band != RTW89_BAND_2G) {
@@ -2791,17 +2798,18 @@ static void _dpk_force_bypass(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	}
 }
 
-static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force)
+static void _dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool force,
+		 enum rtw89_chanctx_idx chanctx_idx)
 {
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
 		    "[DPK] ****** DPK Start (Ver: 0x%x, Cv: %d, RF_para: %d) ******\n",
 		    RTW8852C_DPK_VER, rtwdev->hal.cv,
 		    RTW8852C_RF_REL_VERSION);
 
-	if (_dpk_bypass_check(rtwdev, phy))
+	if (_dpk_bypass_check(rtwdev, phy, chanctx_idx))
 		_dpk_force_bypass(rtwdev, phy);
 	else
-		_dpk_cal_select(rtwdev, force, phy, _kpath(rtwdev, phy));
+		_dpk_cal_select(rtwdev, force, phy, _kpath(rtwdev, phy), chanctx_idx);
 
 	if (rtw89_read_rf(rtwdev, RF_PATH_A, RR_DCKC, RR_DCKC_CHK) == 0x1)
 		rtw8852c_rx_dck(rtwdev, phy, false);
@@ -2892,9 +2900,8 @@ static void _dpk_track(struct rtw89_dev *rtwdev)
 }
 
 static void _tssi_set_sys(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			  enum rtw89_rf_path path)
+			  enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_bandwidth bw = chan->band_width;
 	enum rtw89_band band = chan->band_type;
 	u32 clk = 0x0;
@@ -2946,9 +2953,8 @@ static void _tssi_ini_txpwr_ctrl_bb_he_tb(struct rtw89_dev *rtwdev,
 }
 
 static void _tssi_set_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			  enum rtw89_rf_path path)
+			  enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A) {
@@ -2973,7 +2979,7 @@ static void _tssi_set_bbgain_split(struct rtw89_dev *rtwdev, enum rtw89_phy_idx
 }
 
 static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 #define RTW8852C_TSSI_GET_VAL(ptr, idx)			\
 ({							\
@@ -2986,7 +2992,6 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 	}						\
 	__val;						\
 })
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_fw_txpwr_track_cfg *trk = rtwdev->fw.elm_info.txpwr_trk;
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
 	u8 ch = chan->channel;
@@ -3192,9 +3197,8 @@ static void _tssi_set_tmeter_tbl(struct rtw89_dev *rtwdev, enum rtw89_phy_idx ph
 }
 
 static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				enum rtw89_rf_path path)
+				enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 
 	if (path == RF_PATH_A) {
@@ -3209,9 +3213,9 @@ static void _tssi_slope_cal_org(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy
 }
 
 static void _tssi_set_aligk_default(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-				    enum rtw89_rf_path path)
+				    enum rtw89_rf_path path,
+				    const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	const struct rtw89_rfk_tbl *tbl;
 
@@ -3620,10 +3624,9 @@ static u32 _tssi_get_6g_trim_group(struct rtw89_dev *rtwdev, u8 ch)
 }
 
 static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
-			    enum rtw89_rf_path path)
+			    enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	u8 ch = chan->channel;
 	u32 gidx, gidx_1st, gidx_2nd;
@@ -3684,10 +3687,9 @@ static s8 _tssi_get_ofdm_de(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 
 static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev,
 				 enum rtw89_phy_idx phy,
-				 enum rtw89_rf_path path)
+				 enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	enum rtw89_band band = chan->band_type;
 	u8 ch = chan->channel;
 	u32 tgidx, tgidx_1st, tgidx_2nd;
@@ -3749,10 +3751,9 @@ static s8 _tssi_get_ofdm_trim_de(struct rtw89_dev *rtwdev,
 }
 
 static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
-				  enum rtw89_phy_idx phy)
+				  enum rtw89_phy_idx phy, const struct rtw89_chan *chan)
 {
 	struct rtw89_tssi_info *tssi_info = &rtwdev->tssi;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	u8 ch = chan->channel;
 	u8 gidx;
 	s8 ofdm_de;
@@ -3775,7 +3776,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 
 	for (i = path; i < path_max; i++) {
 		gidx = _tssi_get_cck_group(rtwdev, ch);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = tssi_info->tssi_cck[i][gidx] + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3791,8 +3792,8 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 			    rtw89_phy_read32_mask(rtwdev, _tssi_de_cck_long[i],
 						  _TSSI_DE_MASK));
 
-		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i);
-		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i);
+		ofdm_de = _tssi_get_ofdm_de(rtwdev, phy, i, chan);
+		trim_de = _tssi_get_ofdm_trim_de(rtwdev, phy, i, chan);
 		val = ofdm_de + trim_de;
 
 		rtw89_debug(rtwdev, RTW89_DBG_TSSI,
@@ -3815,7 +3816,7 @@ static void _tssi_set_efuse_to_de(struct rtw89_dev *rtwdev,
 }
 
 static void rtw8852c_tssi_cont_en(struct rtw89_dev *rtwdev, bool en,
-				  enum rtw89_rf_path path)
+				  enum rtw89_rf_path path, const struct rtw89_chan *chan)
 {
 	static const u32 tssi_trk[2] = {0x5818, 0x7818};
 	static const u32 tssi_en[2] = {0x5820, 0x7820};
@@ -3824,25 +3825,26 @@ static void rtw8852c_tssi_cont_en(struct rtw89_dev *rtwdev, bool en,
 		rtw89_phy_write32_mask(rtwdev, tssi_trk[path], BIT(30), 0x0);
 		rtw89_phy_write32_mask(rtwdev, tssi_en[path], BIT(31), 0x0);
 		if (rtwdev->dbcc_en && path == RF_PATH_B)
-			_tssi_set_efuse_to_de(rtwdev, RTW89_PHY_1);
+			_tssi_set_efuse_to_de(rtwdev, RTW89_PHY_1, chan);
 		else
-			_tssi_set_efuse_to_de(rtwdev, RTW89_PHY_0);
+			_tssi_set_efuse_to_de(rtwdev, RTW89_PHY_0, chan);
 	} else {
 		rtw89_phy_write32_mask(rtwdev, tssi_trk[path], BIT(30), 0x1);
 		rtw89_phy_write32_mask(rtwdev, tssi_en[path], BIT(31), 0x1);
 	}
 }
 
-void rtw8852c_tssi_cont_en_phyidx(struct rtw89_dev *rtwdev, bool en, u8 phy_idx)
+void rtw8852c_tssi_cont_en_phyidx(struct rtw89_dev *rtwdev, bool en, u8 phy_idx,
+				  const struct rtw89_chan *chan)
 {
 	if (!rtwdev->dbcc_en) {
-		rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_A);
-		rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_B);
+		rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_A, chan);
+		rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_B, chan);
 	} else {
 		if (phy_idx == RTW89_PHY_0)
-			rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_A);
+			rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_A, chan);
 		else
-			rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_B);
+			rtw8852c_tssi_cont_en(rtwdev, en, RF_PATH_B, chan);
 	}
 }
 
@@ -4146,26 +4148,27 @@ void rtw8852c_rck(struct rtw89_dev *rtwdev)
 		_rck(rtwdev, path);
 }
 
-void rtw8852c_dack(struct rtw89_dev *rtwdev)
+void rtw8852c_dack(struct rtw89_dev *rtwdev, enum rtw89_chanctx_idx chanctx_idx)
 {
-	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, RTW89_PHY_0, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_START);
-	_dac_cal(rtwdev, false);
+	_dac_cal(rtwdev, false, chanctx_idx);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DACK, BTC_WRFK_STOP);
 }
 
-void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
 	_iqk_init(rtwdev);
-	_iqk(rtwdev, phy_idx, false);
+	_iqk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_IQK, BTC_WRFK_STOP);
@@ -4236,10 +4239,11 @@ void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_a
 
 void rtw8852c_rx_dck_track(struct rtw89_dev *rtwdev)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	enum rtw89_chanctx_idx chanctx_idx = RTW89_CHANCTX_0;
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	struct rtw89_rx_dck_info *rx_dck = &rtwdev->rx_dck;
 	enum rtw89_phy_idx phy_idx = RTW89_PHY_0;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 	u8 dck_channel;
 	u8 cur_thermal;
 	u32 tx_en;
@@ -4293,16 +4297,17 @@ void rtw8852c_dpk_init(struct rtw89_dev *rtwdev)
 	dpk->is_dpk_reload_en = false;
 }
 
-void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx)
 {
 	u32 tx_en;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, 0, chanctx_idx);
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_START);
 	rtw89_chip_stop_sch_tx(rtwdev, phy_idx, &tx_en, RTW89_SCH_TX_SEL_ALL);
 	_wait_rx_mode(rtwdev, _kpath(rtwdev, phy_idx));
 
-	_dpk(rtwdev, phy_idx, false);
+	_dpk(rtwdev, phy_idx, false, chanctx_idx);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_DPK, BTC_WRFK_STOP);
@@ -4313,8 +4318,10 @@ void rtw8852c_dpk_track(struct rtw89_dev *rtwdev)
 	_dpk_track(rtwdev);
 }
 
-void rtw8852c_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8852c_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   enum rtw89_chanctx_idx chanctx_idx)
 {
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	u32 i, path = RF_PATH_A, path_max = RF_PATH_NUM_8852C;
 
 	rtw89_debug(rtwdev, RTW89_DBG_TSSI, "[TSSI] %s: phy=%d\n", __func__, phy);
@@ -4332,23 +4339,24 @@ void rtw8852c_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = path; i < path_max; i++) {
-		_tssi_set_sys(rtwdev, phy, i);
+		_tssi_set_sys(rtwdev, phy, i, chan);
 		_tssi_ini_txpwr_ctrl_bb(rtwdev, phy, i);
 		_tssi_ini_txpwr_ctrl_bb_he_tb(rtwdev, phy, i);
-		_tssi_set_dck(rtwdev, phy, i);
+		_tssi_set_dck(rtwdev, phy, i, chan);
 		_tssi_set_bbgain_split(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
-		_tssi_slope_cal_org(rtwdev, phy, i);
-		_tssi_set_aligk_default(rtwdev, phy, i);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
+		_tssi_slope_cal_org(rtwdev, phy, i, chan);
+		_tssi_set_aligk_default(rtwdev, phy, i, chan);
 		_tssi_set_slope(rtwdev, phy, i);
 		_tssi_run_slope(rtwdev, phy, i);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 }
 
-void rtw8852c_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
+void rtw8852c_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan)
 {
 	u32 i, path = RF_PATH_A, path_max = RF_PATH_NUM_8852C;
 
@@ -4373,15 +4381,15 @@ void rtw8852c_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy)
 	_tssi_disable(rtwdev, phy);
 
 	for (i = path; i < path_max; i++) {
-		_tssi_set_sys(rtwdev, phy, i);
-		_tssi_set_dck(rtwdev, phy, i);
-		_tssi_set_tmeter_tbl(rtwdev, phy, i);
-		_tssi_slope_cal_org(rtwdev, phy, i);
-		_tssi_set_aligk_default(rtwdev, phy, i);
+		_tssi_set_sys(rtwdev, phy, i, chan);
+		_tssi_set_dck(rtwdev, phy, i, chan);
+		_tssi_set_tmeter_tbl(rtwdev, phy, i, chan);
+		_tssi_slope_cal_org(rtwdev, phy, i, chan);
+		_tssi_set_aligk_default(rtwdev, phy, i, chan);
 	}
 
 	_tssi_enable(rtwdev, phy);
-	_tssi_set_efuse_to_de(rtwdev, phy);
+	_tssi_set_efuse_to_de(rtwdev, phy, chan);
 }
 
 static void rtw8852c_tssi_default_txagc(struct rtw89_dev *rtwdev,
@@ -4456,7 +4464,7 @@ void rtw8852c_rfk_chanctx_cb(struct rtw89_dev *rtwdev,
 		dpk->is_dpk_enable = true;
 		for (path = 0; path < RTW8852C_DPK_RF_PATH; path++)
 			_dpk_onoff(rtwdev, path, false);
-		rtw8852c_dpk(rtwdev, RTW89_PHY_0);
+		rtw8852c_dpk(rtwdev, RTW89_PHY_0, RTW89_CHANCTX_0);
 		break;
 	default:
 		break;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h
index 6605137e61aa..306dd0a0be73 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h
@@ -9,16 +9,21 @@
 
 void rtw8852c_mcc_get_ch_info(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
 void rtw8852c_rck(struct rtw89_dev *rtwdev);
-void rtw8852c_dack(struct rtw89_dev *rtwdev);
-void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
+void rtw8852c_dack(struct rtw89_dev *rtwdev, enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool is_afe);
 void rtw8852c_rx_dck_track(struct rtw89_dev *rtwdev);
 void rtw8852c_dpk_init(struct rtw89_dev *rtwdev);
-void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
+void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+		  enum rtw89_chanctx_idx chanctx_idx);
 void rtw8852c_dpk_track(struct rtw89_dev *rtwdev);
-void rtw8852c_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
-void rtw8852c_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy);
-void rtw8852c_tssi_cont_en_phyidx(struct rtw89_dev *rtwdev, bool en, u8 phy_idx);
+void rtw8852c_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+		   enum rtw89_chanctx_idx chanctx_idx);
+void rtw8852c_tssi_scan(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
+			const struct rtw89_chan *chan);
+void rtw8852c_tssi_cont_en_phyidx(struct rtw89_dev *rtwdev, bool en, u8 phy_idx,
+				  const struct rtw89_chan *chan);
 void rtw8852c_wifi_scan_notify(struct rtw89_dev *rtwdev, bool scan_start,
 			       enum rtw89_phy_idx phy_idx);
 void rtw8852c_set_channel_rf(struct rtw89_dev *rtwdev,
-- 
cgit v1.3-3-g829e


From abc1296768977f2478a1a686e8b20c2a97c58065 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:22 +0800
Subject: wifi: rtw89: 8922a: use right chanctx whenever possible in RFK flow

No longer access chan with hard-code RTW89_CHANCTX_X whenever possible.
Instead, obtain the right chanctx from somewhere and use it in RTL8922A
RFK (RF calibration) related code.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c       | 25 +++++++++++--------------
 drivers/net/wireless/realtek/rtw89/fw.h       | 17 +++++++++++------
 drivers/net/wireless/realtek/rtw89/phy.c      | 18 ++++++++++++------
 drivers/net/wireless/realtek/rtw89/phy.h      |  6 ++++++
 drivers/net/wireless/realtek/rtw89/rtw8922a.c | 22 +++++++++++++---------
 5 files changed, 53 insertions(+), 35 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 06b263550ef0..023dd3456783 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -5314,10 +5314,8 @@ fail:
 }
 
 int rtw89_fw_h2c_rf_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
-			 enum rtw89_tssi_mode tssi_mode)
+			 const struct rtw89_chan *chan, enum rtw89_tssi_mode tssi_mode)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_CHANCTX_0);
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_h2c_rf_tssi *h2c;
 	u32 len = sizeof(*h2c);
@@ -5361,7 +5359,8 @@ fail:
 	return ret;
 }
 
-int rtw89_fw_h2c_rf_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+int rtw89_fw_h2c_rf_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			const struct rtw89_chan *chan)
 {
 	struct rtw89_h2c_rf_iqk *h2c;
 	u32 len = sizeof(*h2c);
@@ -5396,10 +5395,9 @@ fail:
 	return ret;
 }
 
-int rtw89_fw_h2c_rf_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+int rtw89_fw_h2c_rf_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_CHANCTX_0);
 	struct rtw89_h2c_rf_dpk *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
@@ -5439,10 +5437,9 @@ fail:
 	return ret;
 }
 
-int rtw89_fw_h2c_rf_txgapk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+int rtw89_fw_h2c_rf_txgapk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			   const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_CHANCTX_0);
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_h2c_rf_txgapk *h2c;
 	u32 len = sizeof(*h2c);
@@ -5483,7 +5480,8 @@ fail:
 	return ret;
 }
 
-int rtw89_fw_h2c_rf_dack(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+int rtw89_fw_h2c_rf_dack(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			 const struct rtw89_chan *chan)
 {
 	struct rtw89_h2c_rf_dack *h2c;
 	u32 len = sizeof(*h2c);
@@ -5519,10 +5517,9 @@ fail:
 	return ret;
 }
 
-int rtw89_fw_h2c_rf_rxdck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx)
+int rtw89_fw_h2c_rf_rxdck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			  const struct rtw89_chan *chan)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
-						       RTW89_CHANCTX_0);
 	struct rtw89_h2c_rf_rxdck *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index cb0ecb9b4c11..6e43cbc9559c 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4478,12 +4478,17 @@ int rtw89_fw_h2c_rf_ntfy_mcc(struct rtw89_dev *rtwdev);
 int rtw89_fw_h2c_rf_pre_ntfy(struct rtw89_dev *rtwdev,
 			     enum rtw89_phy_idx phy_idx);
 int rtw89_fw_h2c_rf_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
-			 enum rtw89_tssi_mode tssi_mode);
-int rtw89_fw_h2c_rf_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-int rtw89_fw_h2c_rf_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-int rtw89_fw_h2c_rf_txgapk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-int rtw89_fw_h2c_rf_dack(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
-int rtw89_fw_h2c_rf_rxdck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx);
+			 const struct rtw89_chan *chan, enum rtw89_tssi_mode tssi_mode);
+int rtw89_fw_h2c_rf_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			const struct rtw89_chan *chan);
+int rtw89_fw_h2c_rf_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			const struct rtw89_chan *chan);
+int rtw89_fw_h2c_rf_txgapk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			   const struct rtw89_chan *chan);
+int rtw89_fw_h2c_rf_dack(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			 const struct rtw89_chan *chan);
+int rtw89_fw_h2c_rf_rxdck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx,
+			  const struct rtw89_chan *chan);
 int rtw89_fw_h2c_raw_with_hdr(struct rtw89_dev *rtwdev,
 			      u8 h2c_class, u8 h2c_func, u8 *buf, u16 len,
 			      bool rack, bool dack);
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 7306fb679e95..59b98aa876dd 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -3084,6 +3084,7 @@ EXPORT_SYMBOL(rtw89_phy_rfk_pre_ntfy_and_wait);
 
 int rtw89_phy_rfk_tssi_and_wait(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy_idx,
+				const struct rtw89_chan *chan,
 				enum rtw89_tssi_mode tssi_mode,
 				unsigned int ms)
 {
@@ -3091,7 +3092,7 @@ int rtw89_phy_rfk_tssi_and_wait(struct rtw89_dev *rtwdev,
 
 	rtw89_phy_rfk_report_prep(rtwdev);
 
-	ret = rtw89_fw_h2c_rf_tssi(rtwdev, phy_idx, tssi_mode);
+	ret = rtw89_fw_h2c_rf_tssi(rtwdev, phy_idx, chan, tssi_mode);
 	if (ret)
 		return ret;
 
@@ -3101,13 +3102,14 @@ EXPORT_SYMBOL(rtw89_phy_rfk_tssi_and_wait);
 
 int rtw89_phy_rfk_iqk_and_wait(struct rtw89_dev *rtwdev,
 			       enum rtw89_phy_idx phy_idx,
+			       const struct rtw89_chan *chan,
 			       unsigned int ms)
 {
 	int ret;
 
 	rtw89_phy_rfk_report_prep(rtwdev);
 
-	ret = rtw89_fw_h2c_rf_iqk(rtwdev, phy_idx);
+	ret = rtw89_fw_h2c_rf_iqk(rtwdev, phy_idx, chan);
 	if (ret)
 		return ret;
 
@@ -3117,13 +3119,14 @@ EXPORT_SYMBOL(rtw89_phy_rfk_iqk_and_wait);
 
 int rtw89_phy_rfk_dpk_and_wait(struct rtw89_dev *rtwdev,
 			       enum rtw89_phy_idx phy_idx,
+			       const struct rtw89_chan *chan,
 			       unsigned int ms)
 {
 	int ret;
 
 	rtw89_phy_rfk_report_prep(rtwdev);
 
-	ret = rtw89_fw_h2c_rf_dpk(rtwdev, phy_idx);
+	ret = rtw89_fw_h2c_rf_dpk(rtwdev, phy_idx, chan);
 	if (ret)
 		return ret;
 
@@ -3133,13 +3136,14 @@ EXPORT_SYMBOL(rtw89_phy_rfk_dpk_and_wait);
 
 int rtw89_phy_rfk_txgapk_and_wait(struct rtw89_dev *rtwdev,
 				  enum rtw89_phy_idx phy_idx,
+				  const struct rtw89_chan *chan,
 				  unsigned int ms)
 {
 	int ret;
 
 	rtw89_phy_rfk_report_prep(rtwdev);
 
-	ret = rtw89_fw_h2c_rf_txgapk(rtwdev, phy_idx);
+	ret = rtw89_fw_h2c_rf_txgapk(rtwdev, phy_idx, chan);
 	if (ret)
 		return ret;
 
@@ -3149,13 +3153,14 @@ EXPORT_SYMBOL(rtw89_phy_rfk_txgapk_and_wait);
 
 int rtw89_phy_rfk_dack_and_wait(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy_idx,
+				const struct rtw89_chan *chan,
 				unsigned int ms)
 {
 	int ret;
 
 	rtw89_phy_rfk_report_prep(rtwdev);
 
-	ret = rtw89_fw_h2c_rf_dack(rtwdev, phy_idx);
+	ret = rtw89_fw_h2c_rf_dack(rtwdev, phy_idx, chan);
 	if (ret)
 		return ret;
 
@@ -3165,13 +3170,14 @@ EXPORT_SYMBOL(rtw89_phy_rfk_dack_and_wait);
 
 int rtw89_phy_rfk_rxdck_and_wait(struct rtw89_dev *rtwdev,
 				 enum rtw89_phy_idx phy_idx,
+				 const struct rtw89_chan *chan,
 				 unsigned int ms)
 {
 	int ret;
 
 	rtw89_phy_rfk_report_prep(rtwdev);
 
-	ret = rtw89_fw_h2c_rf_rxdck(rtwdev, phy_idx);
+	ret = rtw89_fw_h2c_rf_rxdck(rtwdev, phy_idx, chan);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 512f17d808fe..6dd8ec46939a 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -907,22 +907,28 @@ int rtw89_phy_rfk_pre_ntfy_and_wait(struct rtw89_dev *rtwdev,
 				    unsigned int ms);
 int rtw89_phy_rfk_tssi_and_wait(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy_idx,
+				const struct rtw89_chan *chan,
 				enum rtw89_tssi_mode tssi_mode,
 				unsigned int ms);
 int rtw89_phy_rfk_iqk_and_wait(struct rtw89_dev *rtwdev,
 			       enum rtw89_phy_idx phy_idx,
+			       const struct rtw89_chan *chan,
 			       unsigned int ms);
 int rtw89_phy_rfk_dpk_and_wait(struct rtw89_dev *rtwdev,
 			       enum rtw89_phy_idx phy_idx,
+			       const struct rtw89_chan *chan,
 			       unsigned int ms);
 int rtw89_phy_rfk_txgapk_and_wait(struct rtw89_dev *rtwdev,
 				  enum rtw89_phy_idx phy_idx,
+				  const struct rtw89_chan *chan,
 				  unsigned int ms);
 int rtw89_phy_rfk_dack_and_wait(struct rtw89_dev *rtwdev,
 				enum rtw89_phy_idx phy_idx,
+				const struct rtw89_chan *chan,
 				unsigned int ms);
 int rtw89_phy_rfk_rxdck_and_wait(struct rtw89_dev *rtwdev,
 				 enum rtw89_phy_idx phy_idx,
+				 const struct rtw89_chan *chan,
 				 unsigned int ms);
 void rtw89_phy_rfk_tssi_fill_fwcmd_efuse_to_de(struct rtw89_dev *rtwdev,
 					       enum rtw89_phy_idx phy,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index d67bbbffb94e..85bdeeda95de 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -1993,10 +1993,12 @@ static void rtw8922a_rfk_init(struct rtw89_dev *rtwdev)
 
 static void rtw8922a_rfk_init_late(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+
 	rtw89_phy_rfk_pre_ntfy_and_wait(rtwdev, RTW89_PHY_0, 5);
 
-	rtw89_phy_rfk_dack_and_wait(rtwdev, RTW89_PHY_0, 58);
-	rtw89_phy_rfk_rxdck_and_wait(rtwdev, RTW89_PHY_0, 32);
+	rtw89_phy_rfk_dack_and_wait(rtwdev, RTW89_PHY_0, chan, 58);
+	rtw89_phy_rfk_rxdck_and_wait(rtwdev, RTW89_PHY_0, chan, 32);
 }
 
 static void _wait_rx_mode(struct rtw89_dev *rtwdev, u8 kpath)
@@ -2020,8 +2022,10 @@ static void _wait_rx_mode(struct rtw89_dev *rtwdev, u8 kpath)
 
 static void rtw8922a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 {
+	enum rtw89_chanctx_idx chanctx_idx = rtwvif->chanctx_idx;
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, chanctx_idx);
 	enum rtw89_phy_idx phy_idx = rtwvif->phy_idx;
-	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, RTW89_CHANCTX_0);
+	u8 phy_map = rtw89_btc_phymap(rtwdev, phy_idx, RF_AB, chanctx_idx);
 	u32 tx_en;
 
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_CHLK, BTC_WRFK_START);
@@ -2029,11 +2033,11 @@ static void rtw8922a_rfk_channel(struct rtw89_dev *rtwdev, struct rtw89_vif *rtw
 	_wait_rx_mode(rtwdev, RF_AB);
 
 	rtw89_phy_rfk_pre_ntfy_and_wait(rtwdev, phy_idx, 5);
-	rtw89_phy_rfk_txgapk_and_wait(rtwdev, phy_idx, 54);
-	rtw89_phy_rfk_iqk_and_wait(rtwdev, phy_idx, 84);
-	rtw89_phy_rfk_tssi_and_wait(rtwdev, phy_idx, RTW89_TSSI_NORMAL, 6);
-	rtw89_phy_rfk_dpk_and_wait(rtwdev, phy_idx, 34);
-	rtw89_phy_rfk_rxdck_and_wait(rtwdev, RTW89_PHY_0, 32);
+	rtw89_phy_rfk_txgapk_and_wait(rtwdev, phy_idx, chan, 54);
+	rtw89_phy_rfk_iqk_and_wait(rtwdev, phy_idx, chan, 84);
+	rtw89_phy_rfk_tssi_and_wait(rtwdev, phy_idx, chan, RTW89_TSSI_NORMAL, 6);
+	rtw89_phy_rfk_dpk_and_wait(rtwdev, phy_idx, chan, 34);
+	rtw89_phy_rfk_rxdck_and_wait(rtwdev, RTW89_PHY_0, chan, 32);
 
 	rtw89_chip_resume_sch_tx(rtwdev, phy_idx, tx_en);
 	rtw89_btc_ntfy_wl_rfk(rtwdev, phy_map, BTC_WRFKT_CHLK, BTC_WRFK_STOP);
@@ -2043,7 +2047,7 @@ static void rtw8922a_rfk_band_changed(struct rtw89_dev *rtwdev,
 				      enum rtw89_phy_idx phy_idx,
 				      const struct rtw89_chan *chan)
 {
-	rtw89_phy_rfk_tssi_and_wait(rtwdev, phy_idx, RTW89_TSSI_SCAN, 6);
+	rtw89_phy_rfk_tssi_and_wait(rtwdev, phy_idx, chan, RTW89_TSSI_SCAN, 6);
 }
 
 static void rtw8922a_rfk_scan(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
-- 
cgit v1.3-3-g829e


From d03b3d7493f5a3908c86bac443631e144e4ffb7d Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:23 +0800
Subject: wifi: rtw89: rename roc_entity_idx to roc_chanctx_idx

The target enum has been renamed to rtw89_"chanctx"_idx. So for
readability, rename roc_entity_idx to roc_"chanctx"_idx to align.

No logic is changed.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c | 12 ++++++------
 drivers/net/wireless/realtek/rtw89/core.c |  4 ++--
 drivers/net/wireless/realtek/rtw89/core.h |  4 ++--
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index a67e16ded91d..7070c85e2c28 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -191,7 +191,7 @@ void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
 	enum rtw89_chanctx_idx cur;
 
 	if (chandef) {
-		cur = atomic_cmpxchg(&hal->roc_entity_idx,
+		cur = atomic_cmpxchg(&hal->roc_chanctx_idx,
 				     RTW89_CHANCTX_IDLE, idx);
 		if (cur != RTW89_CHANCTX_IDLE) {
 			rtw89_debug(rtwdev, RTW89_DBG_TXRX,
@@ -201,7 +201,7 @@ void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
 
 		hal->roc_chandef = *chandef;
 	} else {
-		cur = atomic_cmpxchg(&hal->roc_entity_idx, idx,
+		cur = atomic_cmpxchg(&hal->roc_chanctx_idx, idx,
 				     RTW89_CHANCTX_IDLE);
 		if (cur == idx)
 			return;
@@ -230,7 +230,7 @@ void rtw89_entity_init(struct rtw89_dev *rtwdev)
 	hal->entity_pause = false;
 	bitmap_zero(hal->entity_map, NUM_OF_RTW89_CHANCTX);
 	bitmap_zero(hal->changes, NUM_OF_RTW89_CHANCTX_CHANGES);
-	atomic_set(&hal->roc_entity_idx, RTW89_CHANCTX_IDLE);
+	atomic_set(&hal->roc_chanctx_idx, RTW89_CHANCTX_IDLE);
 	rtw89_config_default_chandef(rtwdev);
 }
 
@@ -2395,11 +2395,11 @@ static void rtw89_swap_chanctx(struct rtw89_dev *rtwdev,
 			rtwvif->chanctx_idx = idx1;
 	}
 
-	cur = atomic_read(&hal->roc_entity_idx);
+	cur = atomic_read(&hal->roc_chanctx_idx);
 	if (cur == idx1)
-		atomic_set(&hal->roc_entity_idx, idx2);
+		atomic_set(&hal->roc_chanctx_idx, idx2);
 	else if (cur == idx2)
-		atomic_set(&hal->roc_entity_idx, idx1);
+		atomic_set(&hal->roc_chanctx_idx, idx1);
 }
 
 int rtw89_chanctx_ops_add(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 87e649272b2e..c3680353bcf1 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -370,7 +370,7 @@ void rtw89_core_set_chip_txpwr(struct rtw89_dev *rtwdev)
 		return;
 	}
 
-	roc_idx = atomic_read(&hal->roc_entity_idx);
+	roc_idx = atomic_read(&hal->roc_chanctx_idx);
 	if (roc_idx != RTW89_CHANCTX_IDLE)
 		chanctx_idx = roc_idx;
 
@@ -409,7 +409,7 @@ int rtw89_set_channel(struct rtw89_dev *rtwdev)
 		return -EINVAL;
 	}
 
-	roc_idx = atomic_read(&hal->roc_entity_idx);
+	roc_idx = atomic_read(&hal->roc_chanctx_idx);
 	if (roc_idx != RTW89_CHANCTX_IDLE)
 		chanctx_idx = roc_idx;
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 1e83c44e05fe..b24c2e5ecc64 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4648,7 +4648,7 @@ struct rtw89_hal {
 	bool ant_diversity_fixed;
 	bool support_cckpd;
 	bool support_igi;
-	atomic_t roc_entity_idx;
+	atomic_t roc_chanctx_idx;
 
 	DECLARE_BITMAP(changes, NUM_OF_RTW89_CHANCTX_CHANGES);
 	DECLARE_BITMAP(entity_map, NUM_OF_RTW89_CHANCTX);
@@ -6109,7 +6109,7 @@ const struct cfg80211_chan_def *rtw89_chandef_get(struct rtw89_dev *rtwdev,
 						  enum rtw89_chanctx_idx idx)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
-	enum rtw89_chanctx_idx roc_idx = atomic_read(&hal->roc_entity_idx);
+	enum rtw89_chanctx_idx roc_idx = atomic_read(&hal->roc_chanctx_idx);
 
 	if (roc_idx == idx)
 		return &hal->roc_chandef;
-- 
cgit v1.3-3-g829e


From fef63150940c2aaa50721dde33d48f00ab510591 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 19 Aug 2024 17:17:24 +0800
Subject: wifi: rtw89: introduce chip support link number and driver MLO
 capability

Configure supported link number by chip. And, introduce driver capability
flag for MLO. Driver should depend on runtime FW features and chip info to
determine whether to set the MLO capability flag or not. Once the MLO flag
is set, driver will consider/register/initialize things for MLO usages.

However, we just add the driver MLO capability flag ahead and don't really
set it. Then, we can start to tweak driver architecture for MLO. Some code
should depend on this flag. And after tweaking driver architecture is done,
we will set it based on runtime conditions as mentioned above.

Besides, MLD number supported by HW should be
	chip supported mac_id number / chip supported link number
Without driver MLO capability flag, we allocate stations based on supported
mac_id number. With driver MLO capability flag, we allocate stations based
on supported MLD number.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819091724.33730-9-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c      | 24 ++++++++++++++++++++++--
 drivers/net/wireless/realtek/rtw89/core.h      |  2 ++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  |  1 +
 8 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index c3680353bcf1..dc642697d74a 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4263,9 +4263,14 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 u8 rtw89_acquire_mac_id(struct rtw89_dev *rtwdev)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	u8 mac_id_num = chip->support_macid_num;
+	u8 mac_id_num;
 	u8 mac_id;
 
+	if (rtwdev->support_mlo)
+		mac_id_num = chip->support_macid_num / chip->support_link_num;
+	else
+		mac_id_num = chip->support_macid_num;
+
 	mac_id = find_first_zero_bit(rtwdev->mac_id_map, mac_id_num);
 	if (mac_id == mac_id_num)
 		return RTW89_MAX_MAC_ID_NUM;
@@ -4681,6 +4686,9 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 	if (chip->chip_gen == RTW89_CHIP_BE)
 		hw->wiphy->flags |= WIPHY_FLAG_DISABLE_WEXT;
 
+	if (rtwdev->support_mlo)
+		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
+
 	hw->wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
 
 	hw->wiphy->max_scan_ssids = RTW89_SCANOFLD_MAX_SSID;
@@ -4783,6 +4791,7 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device,
 	struct ieee80211_ops *ops;
 	u32 driver_data_size;
 	int fw_format = -1;
+	bool support_mlo;
 	bool no_chanctx;
 
 	firmware = rtw89_early_fw_feature_recognize(device, chip, &early_fw, &fw_format);
@@ -4811,6 +4820,14 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device,
 	if (!hw)
 		goto err;
 
+	/* TODO: When driver MLO arch. is done, determine whether to support MLO
+	 * according to the following conditions.
+	 * 1. run with chanctx_ops
+	 * 2. chip->support_link_num != 0
+	 * 3. FW feature supports AP_LINK_PS
+	 */
+	support_mlo = false;
+
 	hw->wiphy->iface_combinations = rtw89_iface_combs;
 
 	if (no_chanctx || chip->support_chanctx_num == 1)
@@ -4825,9 +4842,12 @@ struct rtw89_dev *rtw89_alloc_ieee80211_hw(struct device *device,
 	rtwdev->chip = chip;
 	rtwdev->fw.req.firmware = firmware;
 	rtwdev->fw.fw_format = fw_format;
+	rtwdev->support_mlo = support_mlo;
 
-	rtw89_debug(rtwdev, RTW89_DBG_FW, "probe driver %s chanctx\n",
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "probe driver %s chanctx\n",
 		    no_chanctx ? "without" : "with");
+	rtw89_debug(rtwdev, RTW89_DBG_CHAN, "probe driver %s MLO cap\n",
+		    support_mlo ? "with" : "without");
 
 	return rtwdev;
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index b24c2e5ecc64..34dbe7f132f8 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4232,6 +4232,7 @@ struct rtw89_chip_info {
 	u8 wde_qempty_mgq_grpsel;
 	u32 rf_base_addr[2];
 	u8 support_macid_num;
+	u8 support_link_num;
 	u8 support_chanctx_num;
 	u8 support_bands;
 	u16 support_bandwidths;
@@ -5475,6 +5476,7 @@ struct rtw89_dev {
 	const struct ieee80211_ops *ops;
 
 	bool dbcc_en;
+	bool support_mlo;
 	enum rtw89_mlo_dbcc_mode mlo_dbcc_mode;
 	struct rtw89_hw_scan_info scan_info;
 	const struct rtw89_chip_info *chip;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index c2fa8e270a4b..6dc07edd18a2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2465,6 +2465,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.dig_regs		= &rtw8851b_dig_regs,
 	.tssi_dbw_table		= NULL,
 	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
+	.support_link_num	= 0,
 	.support_chanctx_num	= 0,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 1034d8b29f5d..5eadb0cba29c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2183,6 +2183,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.dig_regs		= &rtw8852a_dig_regs,
 	.tssi_dbw_table		= NULL,
 	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
+	.support_link_num	= 0,
 	.support_chanctx_num	= 1,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 4a4e825302ea..b7e92ce9256b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -820,6 +820,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.dig_regs		= &rtw8852b_dig_regs,
 	.tssi_dbw_table		= NULL,
 	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
+	.support_link_num	= 0,
 	.support_chanctx_num	= 0,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index f7d133ac34de..52a76d2646e9 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -753,6 +753,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.dig_regs		= &rtw8852bt_dig_regs,
 	.tssi_dbw_table		= NULL,
 	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
+	.support_link_num       = 0,
 	.support_chanctx_num	= 1,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index d4adab43f4f2..4a7eaebcdddc 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2961,6 +2961,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.dig_regs		= &rtw8852c_dig_regs,
 	.tssi_dbw_table		= &rtw89_8852c_tssi_dbw_table,
 	.support_macid_num	= RTW89_MAX_MAC_ID_NUM,
+	.support_link_num	= 0,
 	.support_chanctx_num	= 2,
 	.support_rnr		= false,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 85bdeeda95de..3387989299c9 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2621,6 +2621,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.dig_regs		= &rtw8922a_dig_regs,
 	.tssi_dbw_table		= NULL,
 	.support_macid_num	= 32,
+	.support_link_num	= 2,
 	.support_chanctx_num	= 2,
 	.support_rnr		= true,
 	.support_bands		= BIT(NL80211_BAND_2GHZ) |
-- 
cgit v1.3-3-g829e


From 7c24c5bdf489c8f3a9c701a950126da871ebdaca Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Fri, 12 Jul 2024 15:49:38 +0800
Subject: wifi: mac80211_hwsim: correct MODULE_PARM_DESC of multi_radio

Correct the name field in multi_radio's MODULE_PARM_DESC.

Fixes: d2601e34a102 ("wifi: mac80211_hwsim: add support for multi-radio wiphy")
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Acked-by: Felix Fietkau <nbd@nbd.name>
Link: https://patch.msgid.link/20240712074938.26437-1-kevin_yang@realtek.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index d86e6ff4523d..5fe9e4e26142 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -71,7 +71,7 @@ MODULE_PARM_DESC(mlo, "Support MLO");
 
 static bool multi_radio;
 module_param(multi_radio, bool, 0444);
-MODULE_PARM_DESC(mlo, "Support Multiple Radios per wiphy");
+MODULE_PARM_DESC(multi_radio, "Support Multiple Radios per wiphy");
 
 /**
  * enum hwsim_regtest - the type of regulatory tests we offer
-- 
cgit v1.3-3-g829e


From ea63fb71993c56628f323b8268d36f4bbd836a7f Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 25 Jul 2024 12:09:25 +0300
Subject: wifi: mac80211: refactor block ack management code

Introduce 'ieee80211_mgmt_ba()' to avoid code duplication between
'ieee80211_send_addba_resp()', 'ieee80211_send_addba_request()',
and 'ieee80211_send_delba()', ensure that all related addresses
are '__aligned(2)', and prefer convenient 'ether_addr_copy()'
over generic 'memcpy()'. No functional changes expected.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://patch.msgid.link/20240725090925.6022-1-dmantipov@yandex.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  2 +-
 net/mac80211/agg-rx.c      | 15 +--------------
 net/mac80211/agg-tx.c      | 15 +--------------
 net/mac80211/ht.c          | 15 +--------------
 net/mac80211/ieee80211_i.h | 23 +++++++++++++++++++++++
 5 files changed, 27 insertions(+), 43 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 0a04eaf5343c..9406f687cffb 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2487,7 +2487,7 @@ struct ieee80211_link_sta {
  * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not.
  */
 struct ieee80211_sta {
-	u8 addr[ETH_ALEN];
+	u8 addr[ETH_ALEN] __aligned(2);
 	u16 aid;
 	u16 max_rx_aggregation_subframes;
 	bool wme;
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 9bffac7a4974..fe7eab4b681b 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -207,20 +207,7 @@ static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid,
 		return;
 
 	skb_reserve(skb, local->hw.extra_tx_headroom);
-	mgmt = skb_put_zero(skb, 24);
-	memcpy(mgmt->da, da, ETH_ALEN);
-	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
-	if (sdata->vif.type == NL80211_IFTYPE_AP ||
-	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-	    sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
-		memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN);
-	else if (sdata->vif.type == NL80211_IFTYPE_STATION)
-		memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN);
-	else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
-		memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN);
-
-	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-					  IEEE80211_STYPE_ACTION);
+	mgmt = ieee80211_mgmt_ba(skb, da, sdata);
 
 	skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_resp));
 	mgmt->u.action.category = WLAN_CATEGORY_BACK;
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 677bbbac9f16..1c18b862ef8c 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -74,20 +74,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
 		return;
 
 	skb_reserve(skb, local->hw.extra_tx_headroom);
-	mgmt = skb_put_zero(skb, 24);
-	memcpy(mgmt->da, da, ETH_ALEN);
-	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
-	if (sdata->vif.type == NL80211_IFTYPE_AP ||
-	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-	    sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
-		memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN);
-	else if (sdata->vif.type == NL80211_IFTYPE_STATION)
-		memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN);
-	else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
-		memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN);
-
-	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-					  IEEE80211_STYPE_ACTION);
+	mgmt = ieee80211_mgmt_ba(skb, da, sdata);
 
 	skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_req));
 
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 79caeb485fd5..1c2b7dd8976a 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -467,20 +467,7 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata,
 		return;
 
 	skb_reserve(skb, local->hw.extra_tx_headroom);
-	mgmt = skb_put_zero(skb, 24);
-	memcpy(mgmt->da, da, ETH_ALEN);
-	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
-	if (sdata->vif.type == NL80211_IFTYPE_AP ||
-	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-	    sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
-		memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN);
-	else if (sdata->vif.type == NL80211_IFTYPE_STATION)
-		memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN);
-	else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
-		memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN);
-
-	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
-					  IEEE80211_STYPE_ACTION);
+	mgmt = ieee80211_mgmt_ba(skb, da, sdata);
 
 	skb_put(skb, 1 + sizeof(mgmt->u.action.u.delba));
 
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index a3485e4c6132..fdd2bad15076 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2136,6 +2136,29 @@ void ieee80211_process_addba_request(struct ieee80211_local *local,
 				     struct ieee80211_mgmt *mgmt,
 				     size_t len);
 
+static inline struct ieee80211_mgmt *
+ieee80211_mgmt_ba(struct sk_buff *skb, const u8 *da,
+		  struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_mgmt *mgmt = skb_put_zero(skb, 24);
+
+	ether_addr_copy(mgmt->da, da);
+	ether_addr_copy(mgmt->sa, sdata->vif.addr);
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP ||
+	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+	    sdata->vif.type == NL80211_IFTYPE_MESH_POINT)
+		ether_addr_copy(mgmt->bssid, sdata->vif.addr);
+	else if (sdata->vif.type == NL80211_IFTYPE_STATION)
+		ether_addr_copy(mgmt->bssid, sdata->vif.cfg.ap_addr);
+	else if (sdata->vif.type == NL80211_IFTYPE_ADHOC)
+		ether_addr_copy(mgmt->bssid, sdata->u.ibss.bssid);
+
+	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+					  IEEE80211_STYPE_ACTION);
+	return mgmt;
+}
+
 int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid,
 				   enum ieee80211_agg_stop_reason reason);
 void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid,
-- 
cgit v1.3-3-g829e


From e7a7ef9a0742dbd0818d5b15fba2c5313ace765b Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 29 Jul 2024 15:48:16 +0800
Subject: wifi: mac80211: don't use rate mask for offchannel TX either

Like the commit ab9177d83c04 ("wifi: mac80211: don't use rate mask for
scanning"), ignore incorrect settings to avoid no supported rate warning
reported by syzbot.

The syzbot did bisect and found cause is commit 9df66d5b9f45 ("cfg80211:
fix default HE tx bitrate mask in 2G band"), which however corrects
bitmask of HE MCS and recognizes correctly settings of empty legacy rate
plus HE MCS rate instead of returning -EINVAL.

As suggestions [1], follow the change of SCAN TX to consider this case of
offchannel TX as well.

[1] https://lore.kernel.org/linux-wireless/6ab2dc9c3afe753ca6fdcdd1421e7a1f47e87b84.camel@sipsolutions.net/T/#m2ac2a6d2be06a37c9c47a3d8a44b4f647ed4f024

Reported-by: syzbot+8dd98a9e98ee28dc484a@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-wireless/000000000000fdef8706191a3f7b@google.com/
Fixes: 9df66d5b9f45 ("cfg80211: fix default HE tx bitrate mask in 2G band")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240729074816.20323-1-pkshih@realtek.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    | 7 ++++---
 net/mac80211/offchannel.c | 1 +
 net/mac80211/rate.c       | 2 +-
 net/mac80211/scan.c       | 2 +-
 net/mac80211/tx.c         | 2 +-
 5 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 9406f687cffb..de50dc8712c0 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -994,8 +994,9 @@ enum mac80211_tx_info_flags {
  *	of their QoS TID or other priority field values.
  * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally
  *	for sequence number assignment
- * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted
- *	due to scanning, not in normal operation on the interface.
+ * @IEEE80211_TX_CTRL_DONT_USE_RATE_MASK: Don't use rate mask for this frame
+ *	which is transmitted due to scanning or offchannel TX, not in normal
+ *	operation on the interface.
  * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this
  *	frame should be transmitted on the specific link. This really is
  *	only relevant for frames that do not have data present, and is
@@ -1016,7 +1017,7 @@ enum mac80211_tx_control_flags {
 	IEEE80211_TX_CTRL_NO_SEQNO		= BIT(7),
 	IEEE80211_TX_CTRL_DONT_REORDER		= BIT(8),
 	IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX	= BIT(9),
-	IEEE80211_TX_CTRL_SCAN_TX		= BIT(10),
+	IEEE80211_TX_CTRL_DONT_USE_RATE_MASK	= BIT(10),
 	IEEE80211_TX_CTRL_MLO_LINK		= 0xf0000000,
 };
 
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 28d03196ef75..29fab7ae47b4 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -997,6 +997,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	}
 
 	IEEE80211_SKB_CB(skb)->flags = flags;
+	IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK;
 
 	skb->dev = sdata->dev;
 
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 4dc1def69548..3dc9752188d5 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -890,7 +890,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif,
 	if (ieee80211_is_tx_data(skb))
 		rate_control_apply_mask(sdata, sta, sband, dest, max_rates);
 
-	if (!(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX))
+	if (!(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK))
 		mask = sdata->rc_rateidx_mask[info->band];
 
 	if (dest[0].idx < 0)
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index b5f2df61c7f6..1c5d99975ad0 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -649,7 +649,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata,
 				cpu_to_le16(IEEE80211_SN_TO_SEQ(sn));
 		}
 		IEEE80211_SKB_CB(skb)->flags |= tx_flags;
-		IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_SCAN_TX;
+		IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK;
 		ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
 	}
 }
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 72a9ba8bc5fd..0c79584922cc 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -699,7 +699,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
 	txrc.skb = tx->skb;
 	txrc.reported_rate.idx = -1;
 
-	if (unlikely(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) {
+	if (unlikely(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) {
 		txrc.rate_idx_mask = ~0;
 	} else {
 		txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band];
-- 
cgit v1.3-3-g829e


From cfc13542aa693f248b5b67828a9231c849554dc3 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:02 +0300
Subject: wifi: iwlwifi: mvm: prepare the introduction of V9 of
 REDUCED_TX_POWER

* Rename iwl_dev_tx_power_cmd to iwl_dev_tx_power_cmd_v3_v8
* struct iwl_dev_tx_power_common needs to be packed. It was always the
  case, but now that its size is not a multiple of 4, it becomes
  meaningful.
* Move per_band data out of the common structure since it won't be
  present in the new versions of the command.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.8da29a66984f.I922bdef4740d990f98cb452e858c4157bbc491c5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/power.h | 25 +++++++++++++++--------
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c       |  7 +++++--
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c |  7 +++++--
 3 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
index 6e6a92d173cc..4c9d28327efc 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
@@ -285,18 +285,12 @@ enum iwl_dev_tx_power_cmd_mode {
  * @set_mode: see &enum iwl_dev_tx_power_cmd_mode
  * @mac_context_id: id of the mac ctx for which we are reducing TX power.
  * @pwr_restriction: TX power restriction in 1/8 dBms.
- * @dev_24: device TX power restriction in 1/8 dBms
- * @dev_52_low: device TX power restriction upper band - low
- * @dev_52_high: device TX power restriction upper band - high
  */
 struct iwl_dev_tx_power_common {
 	__le32 set_mode;
 	__le32 mac_context_id;
 	__le16 pwr_restriction;
-	__le16 dev_24;
-	__le16 dev_52_low;
-	__le16 dev_52_high;
-};
+} __packed;
 
 /**
  * struct iwl_dev_tx_power_cmd_v3 - TX power reduction command version 3
@@ -412,8 +406,20 @@ struct iwl_dev_tx_power_cmd_v8 {
 	__le32 tpc_vlp_backoff_level;
 } __packed; /* TX_REDUCED_POWER_API_S_VER_8 */
 
+/*
+ * @dev_24: device TX power restriction in 1/8 dBms
+ * @dev_52_low: device TX power restriction upper band - low
+ * @dev_52_high: device TX power restriction upper band - high
+ */
+struct iwl_dev_tx_power_cmd_per_band {
+	__le16 dev_24;
+	__le16 dev_52_low;
+	__le16 dev_52_high;
+} __packed;
+
 /**
- * struct iwl_dev_tx_power_cmd - TX power reduction command (multiversion)
+ * struct iwl_dev_tx_power_cmd_v3_v8 - TX power reduction command (multiversion)
+ * @per_band: per band restrictions
  * @common: common part of the command
  * @v3: version 3 part of the command
  * @v4: version 4 part of the command
@@ -422,8 +428,9 @@ struct iwl_dev_tx_power_cmd_v8 {
  * @v7: version 7 part of the command
  * @v8: version 8 part of the command
  */
-struct iwl_dev_tx_power_cmd {
+struct iwl_dev_tx_power_cmd_v3_v8 {
 	struct iwl_dev_tx_power_common common;
+	struct iwl_dev_tx_power_cmd_per_band per_band;
 	union {
 		struct iwl_dev_tx_power_cmd_v3 v3;
 		struct iwl_dev_tx_power_cmd_v4 v4;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 08c4898c8f1a..4c0847446e22 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -863,7 +863,7 @@ static int iwl_mvm_config_ltr(struct iwl_mvm *mvm)
 int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 {
 	u32 cmd_id = REDUCE_TX_POWER_CMD;
-	struct iwl_dev_tx_power_cmd cmd = {
+	struct iwl_dev_tx_power_cmd_v3_v8 cmd = {
 		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
 	};
 	__le16 *per_chain;
@@ -899,9 +899,12 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 		per_chain = cmd.v3.per_chain[0][0];
 	}
 
-	/* all structs have the same common part, add it */
+	/* all structs have the same common part, add its length */
 	len += sizeof(cmd.common);
 
+	/* all structs have the same per_band part, add its length */
+	len += sizeof(cmd.per_band);
+
 	ret = iwl_sar_fill_profile(&mvm->fwrt, per_chain,
 				   IWL_NUM_CHAIN_TABLES,
 				   n_subbands, prof_a, prof_b);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 835a05b91833..f0b290aa6bec 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1480,7 +1480,7 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 {
 	u32 cmd_id = REDUCE_TX_POWER_CMD;
 	int len;
-	struct iwl_dev_tx_power_cmd cmd = {
+	struct iwl_dev_tx_power_cmd_v3_v8 cmd = {
 		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC),
 		.common.mac_context_id =
 			cpu_to_le32(iwl_mvm_vif_from_mac80211(vif)->id),
@@ -1507,9 +1507,12 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	else
 		len = sizeof(cmd.v3);
 
-	/* all structs have the same common part, add it */
+	/* all structs have the same common part, add its length */
 	len += sizeof(cmd.common);
 
+	/* all structs have the same per_band part, add its length */
+	len += sizeof(cmd.per_band);
+
 	return iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, len, &cmd);
 }
 
-- 
cgit v1.3-3-g829e


From 535f01905afac5a5ad420bb94970d410f5e6fec6 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:03 +0300
Subject: wifi: iwlwifi: mvm: add support for new REDUCE_TXPOWER_CMD versions

New API versions are coming up for this command.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.7ec1527be98c.I52dede6532bc61041c441caee5273734f14a1d78@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/power.h | 54 +++++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c       | 24 ++++++++--
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 37 +++++++++++-----
 3 files changed, 100 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
index 4c9d28327efc..df0680eae30c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h
@@ -441,6 +441,60 @@ struct iwl_dev_tx_power_cmd_v3_v8 {
 	};
 };
 
+/**
+ * struct iwl_dev_tx_power_cmd_v9 - TX power reduction cmd
+ * @reserved: reserved (padding)
+ * @per_chain: per chain restrictions
+ * @per_chain_restriction_changed: is per_chain_restriction has changed
+ *	from last command. used if set_mode is
+ *	IWL_TX_POWER_MODE_SET_SAR_TIMER.
+ *	note: if not changed, the command is used for keep alive only.
+ * @reserved1: reserved (padding)
+ * @timer_period: timer in milliseconds. if expires FW will change to default
+ *	BIOS values. relevant if setMode is IWL_TX_POWER_MODE_SET_SAR_TIMER
+ */
+struct iwl_dev_tx_power_cmd_v9 {
+	__le16 reserved;
+	__le16 per_chain[IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V1];
+	u8 per_chain_restriction_changed;
+	u8 reserved1[3];
+	__le32 timer_period;
+} __packed; /* TX_REDUCED_POWER_API_S_VER_9 */
+
+/**
+ * struct iwl_dev_tx_power_cmd_v10 - TX power reduction cmd
+ * @per_chain: per chain restrictions
+ * @per_chain_restriction_changed: is per_chain_restriction has changed
+ *	from last command. used if set_mode is
+ *	IWL_TX_POWER_MODE_SET_SAR_TIMER.
+ *	note: if not changed, the command is used for keep alive only.
+ * @reserved: reserved (padding)
+ * @timer_period: timer in milliseconds. if expires FW will change to default
+ *	BIOS values. relevant if setMode is IWL_TX_POWER_MODE_SET_SAR_TIMER
+ * @flags: reduce power flags.
+ */
+struct iwl_dev_tx_power_cmd_v10 {
+	__le16 per_chain[IWL_NUM_CHAIN_TABLES_V2][IWL_NUM_CHAIN_LIMITS][IWL_NUM_SUB_BANDS_V2];
+	u8 per_chain_restriction_changed;
+	u8 reserved;
+	__le32 timer_period;
+	__le32 flags;
+} __packed; /* TX_REDUCED_POWER_API_S_VER_10 */
+
+/*
+ * struct iwl_dev_tx_power_cmd - TX power reduction command (multiversion)
+ * @common: common part of the command
+ * @v9: version 9 part of the command
+ * @v10: version 10 part of the command
+ */
+struct iwl_dev_tx_power_cmd {
+	struct iwl_dev_tx_power_common common;
+	union {
+		struct iwl_dev_tx_power_cmd_v9 v9;
+		struct iwl_dev_tx_power_cmd_v10 v10;
+	};
+} __packed; /* TX_REDUCED_POWER_API_S_VER_9_VER10 */
+
 #define IWL_NUM_GEO_PROFILES		3
 #define IWL_NUM_GEO_PROFILES_V3		8
 #define IWL_NUM_BANDS_PER_CHAIN_V1	2
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 4c0847446e22..e279fd409b6f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -866,13 +866,27 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 	struct iwl_dev_tx_power_cmd_v3_v8 cmd = {
 		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
 	};
+	struct iwl_dev_tx_power_cmd cmd_v9_v10 = {
+		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
+	};
 	__le16 *per_chain;
 	int ret;
 	u16 len = 0;
 	u32 n_subbands;
 	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 3);
+	void *cmd_data = &cmd;
 
-	if (cmd_ver >= 7) {
+	if (cmd_ver == 10) {
+		len = sizeof(cmd_v9_v10.v10);
+		n_subbands = IWL_NUM_SUB_BANDS_V2;
+		per_chain = &cmd_v9_v10.v10.per_chain[0][0][0];
+		cmd_v9_v10.v10.flags =
+			cpu_to_le32(mvm->fwrt.reduced_power_flags);
+	} else if (cmd_ver == 9) {
+		len = sizeof(cmd_v9_v10.v9);
+		n_subbands = IWL_NUM_SUB_BANDS_V1;
+		per_chain = &cmd_v9_v10.v9.per_chain[0][0];
+	} else if (cmd_ver >= 7) {
 		len = sizeof(cmd.v7);
 		n_subbands = IWL_NUM_SUB_BANDS_V2;
 		per_chain = cmd.v7.per_chain[0][0];
@@ -902,8 +916,10 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 	/* all structs have the same common part, add its length */
 	len += sizeof(cmd.common);
 
-	/* all structs have the same per_band part, add its length */
-	len += sizeof(cmd.per_band);
+	if (cmd_ver < 9)
+		len += sizeof(cmd.per_band);
+	else
+		cmd_data = &cmd_v9_v10;
 
 	ret = iwl_sar_fill_profile(&mvm->fwrt, per_chain,
 				   IWL_NUM_CHAIN_TABLES,
@@ -916,7 +932,7 @@ int iwl_mvm_sar_select_profile(struct iwl_mvm *mvm, int prof_a, int prof_b)
 	iwl_mei_set_power_limit(per_chain);
 
 	IWL_DEBUG_RADIO(mvm, "Sending REDUCE_TX_POWER_CMD per chain\n");
-	return iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, len, &cmd);
+	return iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, len, cmd_data);
 }
 
 int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index f0b290aa6bec..f48f445e006c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1484,15 +1484,29 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC),
 		.common.mac_context_id =
 			cpu_to_le32(iwl_mvm_vif_from_mac80211(vif)->id),
-		.common.pwr_restriction = cpu_to_le16(8 * tx_power),
 	};
-	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id,
-					   IWL_FW_CMD_VER_UNKNOWN);
-
-	if (tx_power == IWL_DEFAULT_MAX_TX_POWER)
-		cmd.common.pwr_restriction = cpu_to_le16(IWL_DEV_MAX_TX_POWER);
-
-	if (cmd_ver == 8)
+	struct iwl_dev_tx_power_cmd cmd_v9_v10;
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, cmd_id, 3);
+	u16 u_tx_power = tx_power == IWL_DEFAULT_MAX_TX_POWER ?
+		IWL_DEV_MAX_TX_POWER : 8 * tx_power;
+	void *cmd_data = &cmd;
+
+	cmd.common.pwr_restriction = cpu_to_le16(u_tx_power);
+
+	if (cmd_ver > 8) {
+		/* Those fields sit on the same place for v9 and v10 */
+		cmd_v9_v10.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_MAC);
+		cmd_v9_v10.common.mac_context_id =
+			cpu_to_le32(iwl_mvm_vif_from_mac80211(vif)->id);
+		cmd_v9_v10.common.pwr_restriction = cpu_to_le16(u_tx_power);
+		cmd_data = &cmd_v9_v10;
+	}
+
+	if (cmd_ver == 10)
+		len = sizeof(cmd_v9_v10.v10);
+	else if (cmd_ver == 9)
+		len = sizeof(cmd_v9_v10.v9);
+	else if (cmd_ver == 8)
 		len = sizeof(cmd.v8);
 	else if (cmd_ver == 7)
 		len = sizeof(cmd.v7);
@@ -1510,10 +1524,11 @@ int iwl_mvm_set_tx_power(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	/* all structs have the same common part, add its length */
 	len += sizeof(cmd.common);
 
-	/* all structs have the same per_band part, add its length */
-	len += sizeof(cmd.per_band);
+	if (cmd_ver < 9)
+		len += sizeof(cmd.per_band);
+
+	return iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, len, cmd_data);
 
-	return iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, len, &cmd);
 }
 
 static void iwl_mvm_post_csa_tx(void *data, struct ieee80211_sta *sta)
-- 
cgit v1.3-3-g829e


From cb2b6ce8b2e9289b95d6b997eecdf3083107acad Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 29 Jul 2024 20:20:04 +0300
Subject: wifi: iwlwifi: remove MVM prefix from FW macros

These are not mvm specific.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240729201718.939b32f84f46.I293957bf172680871eba24448d9d1870e49100b6@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h | 4 ++--
 drivers/net/wireless/intel/iwlwifi/fw/api/stats.h   | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c         | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h        | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/rx.c         | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c        | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h        | 2 +-
 7 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index ca6fa66d1917..b9ed42faa63e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -524,8 +524,8 @@ struct iwl_link_config_cmd {
 /* Currently FW supports link ids in the range 0-3 and can have
  * at most two active links for each vif.
  */
-#define IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM 2
-#define IWL_MVM_FW_MAX_LINK_ID 3
+#define IWL_FW_MAX_ACTIVE_LINKS_NUM 2
+#define IWL_FW_MAX_LINK_ID 3
 
 /**
  * enum iwl_fw_sta_type - FW station types
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
index 2271b19213fa..659cb40ecfb4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018, 2020 - 2021, 2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018, 2020 - 2021, 2023 - 2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -594,7 +594,7 @@ struct iwl_stats_ntfy_per_sta {
 } __packed; /* STATISTICS_NTFY_PER_STA_API_S_VER_1 */
 
 #define IWL_STATS_MAX_PHY_OPERATIONAL 3
-#define IWL_STATS_MAX_FW_LINKS	(IWL_MVM_FW_MAX_LINK_ID + 1)
+#define IWL_STATS_MAX_FW_LINKS	(IWL_FW_MAX_LINK_ID + 1)
 
 /**
  * struct iwl_system_statistics_notif_oper
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index e279fd409b6f..08546e673cf5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1483,7 +1483,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 		RCU_INIT_POINTER(mvm->fw_id_to_link_sta[i], NULL);
 	}
 
-	for (i = 0; i < IWL_MVM_FW_MAX_LINK_ID + 1; i++)
+	for (i = 0; i < IWL_FW_MAX_LINK_ID + 1; i++)
 		RCU_INIT_POINTER(mvm->link_id_to_link_conf[i], NULL);
 
 	mvm->tdls_cs.peer.sta_id = IWL_MVM_INVALID_STA;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 22f48b66d79c..e2cc378d6d91 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1164,7 +1164,7 @@ struct iwl_mvm {
 
 	struct ieee80211_vif __rcu *vif_id_to_mac[NUM_MAC_INDEX_DRIVER];
 
-	struct ieee80211_bss_conf __rcu *link_id_to_link_conf[IWL_MVM_FW_MAX_LINK_ID + 1];
+	struct ieee80211_bss_conf __rcu *link_id_to_link_conf[IWL_FW_MAX_LINK_ID + 1];
 
 	/* -1 for always, 0 for never, >0 for that many times */
 	s8 fw_restart;
@@ -1745,7 +1745,7 @@ static inline int iwl_mvm_max_active_links(struct iwl_mvm *mvm,
 	if (iwl_mvm_is_esr_supported(trans) ||
 	    (CSR_HW_RFID_TYPE(trans->hw_rf_id) == IWL_CFG_RF_TYPE_FM &&
 	     CSR_HW_RFID_IS_CDB(trans->hw_rf_id)))
-		return IWL_MVM_FW_MAX_ACTIVE_LINKS_NUM;
+		return IWL_FW_MAX_ACTIVE_LINKS_NUM;
 
 	return 1;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 151289e13308..bc8078875c5a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -991,7 +991,7 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm)
 		spin_lock_bh(&mvmsta->mpdu_counters[q].lock);
 
 		/* The link IDs that doesn't exist will contain 0 */
-		for (int link = 0; link < IWL_MVM_FW_MAX_LINK_ID; link++) {
+		for (int link = 0; link < IWL_FW_MAX_LINK_ID; link++) {
 			total_tx += mvmsta->mpdu_counters[q].per_link[link].tx;
 			total_rx += mvmsta->mpdu_counters[q].per_link[link].rx;
 		}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 15e64d94d6ea..550c97a014b9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -4458,7 +4458,7 @@ void iwl_mvm_count_mpdu(struct iwl_mvm_sta *mvm_sta, u8 fw_sta_id, u32 count,
 		IWL_DEBUG_STATS(mvm, "MPDU counters are cleared\n");
 	}
 
-	for (int i = 0; i < IWL_MVM_FW_MAX_LINK_ID; i++)
+	for (int i = 0; i < IWL_FW_MAX_LINK_ID; i++)
 		total_mpdus += tx ? queue_counter->per_link[i].tx :
 				    queue_counter->per_link[i].rx;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 0dc83d6afb3c..193a1edc38d2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -361,7 +361,7 @@ struct iwl_mvm_mpdu_counter {
  */
 struct iwl_mvm_tpt_counter {
 	spinlock_t lock;
-	struct iwl_mvm_mpdu_counter per_link[IWL_MVM_FW_MAX_LINK_ID];
+	struct iwl_mvm_mpdu_counter per_link[IWL_FW_MAX_LINK_ID];
 	unsigned long window_start;
 } ____cacheline_aligned_in_smp;
 
-- 
cgit v1.3-3-g829e


From 4f1591d292277eec51d027405a92f0d4ef5e299e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jul 2024 20:20:05 +0300
Subject: wifi: iwlwifi: mvm: use correct key iteration

In the cases changed here, key iteration isn't done from
an RCU critical section, but rather using the wiphy lock
as protection. Therefore, just use ieee80211_iter_keys().
The link switch case can therefore also use sync commands.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.69a2d18580c1.I2148e04d4b467d0b100beac8f7e449bfaaf775a5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c
index 8a38fc4b0b0f..455f5f417506 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-key.c
@@ -144,7 +144,7 @@ static void iwl_mvm_mld_update_sta_key(struct ieee80211_hw *hw,
 	if (sta != data->sta || key->link_id >= 0)
 		return;
 
-	err = iwl_mvm_send_cmd_pdu(mvm, cmd_id, CMD_ASYNC, sizeof(cmd), &cmd);
+	err = iwl_mvm_send_cmd_pdu(mvm, cmd_id, 0, sizeof(cmd), &cmd);
 
 	if (err)
 		data->err = err;
@@ -162,8 +162,8 @@ int iwl_mvm_mld_update_sta_keys(struct iwl_mvm *mvm,
 		.new_sta_mask = new_sta_mask,
 	};
 
-	ieee80211_iter_keys_rcu(mvm->hw, vif, iwl_mvm_mld_update_sta_key,
-				&data);
+	ieee80211_iter_keys(mvm->hw, vif, iwl_mvm_mld_update_sta_key,
+			    &data);
 	return data.err;
 }
 
@@ -402,7 +402,7 @@ void iwl_mvm_sec_key_remove_ap(struct iwl_mvm *mvm,
 	if (!sec_key_ver)
 		return;
 
-	ieee80211_iter_keys_rcu(mvm->hw, vif,
-				iwl_mvm_sec_key_remove_ap_iter,
-				(void *)(uintptr_t)link_id);
+	ieee80211_iter_keys(mvm->hw, vif,
+			    iwl_mvm_sec_key_remove_ap_iter,
+			    (void *)(uintptr_t)link_id);
 }
-- 
cgit v1.3-3-g829e


From 70d400ba7fa71d19481faf81db9483432ed1e084 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jul 2024 20:20:06 +0300
Subject: wifi: iwlwifi: pcie: print function scratch before writing

We may want to know the value of this register for certain
debug scenarios before we overwrite it, it indicates which
parts of the chip have recently been reset.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.737e5f8bb8df.Ia3f3637ac4a0fb4b35ffd652f92eb75de652ee12@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 18dda89b7985..8903a5692dfb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -526,6 +526,8 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 	keep_ram_busy = !iwl_pcie_set_ltr(trans);
 
 	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		IWL_DEBUG_POWER(trans, "function scratch register value is 0x%08x\n",
+				iwl_read32(trans, CSR_FUNC_SCRATCH));
 		iwl_write32(trans, CSR_FUNC_SCRATCH, CSR_FUNC_SCRATCH_INIT_VALUE);
 		iwl_set_bit(trans, CSR_GP_CNTRL,
 			    CSR_GP_CNTRL_REG_FLAG_ROM_START);
-- 
cgit v1.3-3-g829e


From 8131dd52810dfcdb49fcdc78f5e18e1538b6c441 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 29 Jul 2024 20:20:07 +0300
Subject: wifi: iwlwifi: config: label 'gl' devices as discrete

The 'gl' devices are in the bz family, but they're not,
integrated, so should have their own trans config struct.
Fix that, also necessitating the removal of LTR config,
and while at it remove 0x2727 and 0x272D IDs that were
only used for test chips.

Fixes: c30a2a64788b ("wifi: iwlwifi: add a new PCI device ID for BZ device")ticket=none
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.95aed0620080.Ib9129512c95aa57acc9876bdff8b99dd41e1562c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c     | 11 +++++++++++
 drivers/net/wireless/intel/iwlwifi/iwl-config.h |  1 +
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c   |  4 +---
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index 3b6b8b410be5..b230441abc16 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -148,6 +148,17 @@ const struct iwl_cfg_trans_params iwl_bz_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
+const struct iwl_cfg_trans_params iwl_gl_trans_cfg = {
+	.device_family = IWL_DEVICE_FAMILY_BZ,
+	.base_params = &iwl_bz_base_params,
+	.mq_rx_supported = true,
+	.rf_id = true,
+	.gen2 = true,
+	.umac_prph_offset = 0x300000,
+	.xtal_latency = 12000,
+	.low_latency_xtal = true,
+};
+
 const char iwl_bz_name[] = "Intel(R) TBD Bz device";
 const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz";
 const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz";
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index b2abd4fd1944..34c91deca57b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -504,6 +504,7 @@ extern const struct iwl_cfg_trans_params iwl_so_long_latency_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_so_long_latency_imr_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_ma_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_bz_trans_cfg;
+extern const struct iwl_cfg_trans_params iwl_gl_trans_cfg;
 extern const struct iwl_cfg_trans_params iwl_sc_trans_cfg;
 extern const char iwl9162_name[];
 extern const char iwl9260_name[];
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 9ad43464b702..887fe56ad98b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -500,9 +500,7 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x7E40, PCI_ANY_ID, iwl_ma_trans_cfg)},
 
 /* Bz devices */
-	{IWL_PCI_DEVICE(0x2727, PCI_ANY_ID, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0x272D, PCI_ANY_ID, iwl_bz_trans_cfg)},
-	{IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_bz_trans_cfg)},
+	{IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_gl_trans_cfg)},
 	{IWL_PCI_DEVICE(0xA840, 0x0000, iwl_bz_trans_cfg)},
 	{IWL_PCI_DEVICE(0xA840, 0x0090, iwl_bz_trans_cfg)},
 	{IWL_PCI_DEVICE(0xA840, 0x0094, iwl_bz_trans_cfg)},
-- 
cgit v1.3-3-g829e


From 27c8f12e972d3647e9d759d7cafd4c34fa513432 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 29 Jul 2024 20:20:08 +0300
Subject: wifi: iwlwifi: mei: add support for SAP version 4

SAP version 4 uses larger Host to MEI notification queue.
Since it is unknown which SAP version is used by the CSME firmware
when the driver loads, try version 4 first. In case the CSME firmware
uses version 3, the memory allocation will fail. In this case the
driver will try again to allocate the memory for version 3.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.8372e040282f.Ia0085784e08a35159c9293f986c3d2774038f4c4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h | 10 ++++
 drivers/net/wireless/intel/iwlwifi/mei/main.c    | 58 ++++++++++++++++++------
 2 files changed, 53 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h b/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h
index 4900de3cc0d3..2081775e0ec9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h
+++ b/drivers/net/wireless/intel/iwlwifi/mei/iwl-mei.h
@@ -283,6 +283,16 @@ struct iwl_mei_colloc_info {
 	u8 bssid[ETH_ALEN];
 };
 
+/**
+ * enum iwl_mei_sap_version - SAP version
+ * @IWL_MEI_SAP_VERSION_3: SAP version 3
+ * @IWL_MEI_SAP_VERSION_4: SAP version 4
+ */
+enum iwl_mei_sap_version {
+	IWL_MEI_SAP_VERSION_3 = 3,
+	IWL_MEI_SAP_VERSION_4 = 4,
+};
+
 /*
  * struct iwl_mei_ops - driver's operations called by iwlmei
  * Operations will not be called more than once concurrently.
diff --git a/drivers/net/wireless/intel/iwlwifi/mei/main.c b/drivers/net/wireless/intel/iwlwifi/mei/main.c
index 1dd9106c6513..dce0b7cf7b26 100644
--- a/drivers/net/wireless/intel/iwlwifi/mei/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/mei/main.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2021-2023 Intel Corporation
+ * Copyright (C) 2021-2024 Intel Corporation
  */
 
 #include <linux/etherdevice.h>
@@ -58,7 +58,6 @@ bool iwl_mei_is_connected(void)
 }
 EXPORT_SYMBOL_GPL(iwl_mei_is_connected);
 
-#define SAP_VERSION	3
 #define SAP_CONTROL_BLOCK_ID 0x21504153 /* SAP! in ASCII */
 
 struct iwl_sap_q_ctrl_blk {
@@ -110,16 +109,19 @@ struct iwl_sap_shared_mem_ctrl_blk {
 
 #define SAP_H2M_DATA_Q_SZ	48256
 #define SAP_M2H_DATA_Q_SZ	24128
-#define SAP_H2M_NOTIF_Q_SZ	2240
+#define SAP_H2M_NOTIF_Q_SZ_VER3	2240
+#define SAP_H2M_NOTIF_Q_SZ_VER4	32768
 #define SAP_M2H_NOTIF_Q_SZ	62720
 
-#define _IWL_MEI_SAP_SHARED_MEM_SZ \
+#define _IWL_MEI_SAP_SHARED_MEM_SZ_VER3 \
 	(sizeof(struct iwl_sap_shared_mem_ctrl_blk) + \
-	 SAP_H2M_DATA_Q_SZ + SAP_H2M_NOTIF_Q_SZ + \
+	 SAP_H2M_DATA_Q_SZ + SAP_H2M_NOTIF_Q_SZ_VER3 + \
 	 SAP_M2H_DATA_Q_SZ + SAP_M2H_NOTIF_Q_SZ + 4)
 
-#define IWL_MEI_SAP_SHARED_MEM_SZ \
-	(roundup(_IWL_MEI_SAP_SHARED_MEM_SZ, PAGE_SIZE))
+#define _IWL_MEI_SAP_SHARED_MEM_SZ_VER4 \
+	(sizeof(struct iwl_sap_shared_mem_ctrl_blk) + \
+	 SAP_H2M_DATA_Q_SZ + SAP_H2M_NOTIF_Q_SZ_VER4 + \
+	 SAP_M2H_DATA_Q_SZ + SAP_M2H_NOTIF_Q_SZ + 4)
 
 struct iwl_mei_shared_mem_ptrs {
 	struct iwl_sap_shared_mem_ctrl_blk *ctrl;
@@ -206,6 +208,7 @@ struct iwl_mei {
  * @mac_address: interface MAC address.
  * @nvm_address: NVM MAC address.
  * @priv: A pointer to iwlwifi.
+ * @sap_version: The SAP version to use. enum iwl_mei_sap_version.
  *
  * This used to cache the configurations coming from iwlwifi's way. The data
  * is cached here so that we can buffer the configuration even if we don't have
@@ -220,6 +223,7 @@ struct iwl_mei_cache {
 	u16 mcc;
 	u8 mac_address[6];
 	u8 nvm_address[6];
+	enum iwl_mei_sap_version sap_version;
 	void *priv;
 };
 
@@ -238,14 +242,17 @@ static void iwl_mei_free_shared_mem(struct mei_cl_device *cldev)
 
 #define HBM_DMA_BUF_ID_WLAN 1
 
-static int iwl_mei_alloc_shared_mem(struct mei_cl_device *cldev)
+static int iwl_mei_alloc_mem_for_version(struct mei_cl_device *cldev,
+					 enum iwl_mei_sap_version version)
 {
 	struct iwl_mei *mei = mei_cldev_get_drvdata(cldev);
 	struct iwl_mei_shared_mem_ptrs *mem = &mei->shared_mem;
+	u32 mem_size = roundup(version == IWL_MEI_SAP_VERSION_4 ?
+			       _IWL_MEI_SAP_SHARED_MEM_SZ_VER4 :
+			       _IWL_MEI_SAP_SHARED_MEM_SZ_VER3, PAGE_SIZE);
 
-	mem->ctrl = mei_cldev_dma_map(cldev, HBM_DMA_BUF_ID_WLAN,
-				       IWL_MEI_SAP_SHARED_MEM_SZ);
-
+	iwl_mei_cache.sap_version = version;
+	mem->ctrl = mei_cldev_dma_map(cldev, HBM_DMA_BUF_ID_WLAN, mem_size);
 	if (IS_ERR(mem->ctrl)) {
 		int ret = PTR_ERR(mem->ctrl);
 
@@ -254,11 +261,30 @@ static int iwl_mei_alloc_shared_mem(struct mei_cl_device *cldev)
 		return ret;
 	}
 
-	memset(mem->ctrl, 0, IWL_MEI_SAP_SHARED_MEM_SZ);
+	memset(mem->ctrl, 0, mem_size);
 
 	return 0;
 }
 
+static int iwl_mei_alloc_shared_mem(struct mei_cl_device *cldev)
+{
+	int ret;
+
+	/*
+	 * SAP version 4 uses a larger Host to MEI notif queue.
+	 * Since it is unknown at this stage which SAP version is used by the
+	 * CSME firmware on this platform, try to allocate the version 4 first.
+	 * If the CSME firmware uses version 3, this allocation is expected to
+	 * fail because the CSME firmware allocated less memory for our driver.
+	 */
+	ret = iwl_mei_alloc_mem_for_version(cldev, IWL_MEI_SAP_VERSION_4);
+	if (ret)
+		ret = iwl_mei_alloc_mem_for_version(cldev,
+						    IWL_MEI_SAP_VERSION_3);
+
+	return ret;
+}
+
 static void iwl_mei_init_shared_mem(struct iwl_mei *mei)
 {
 	struct iwl_mei_shared_mem_ptrs *mem = &mei->shared_mem;
@@ -277,7 +303,9 @@ static void iwl_mei_init_shared_mem(struct iwl_mei *mei)
 	h2m->q_ctrl_blk[SAP_QUEUE_IDX_DATA].size =
 		cpu_to_le32(SAP_H2M_DATA_Q_SZ);
 	h2m->q_ctrl_blk[SAP_QUEUE_IDX_NOTIF].size =
-		cpu_to_le32(SAP_H2M_NOTIF_Q_SZ);
+		iwl_mei_cache.sap_version == IWL_MEI_SAP_VERSION_3 ?
+		cpu_to_le32(SAP_H2M_NOTIF_Q_SZ_VER3) :
+		cpu_to_le32(SAP_H2M_NOTIF_Q_SZ_VER4);
 	m2h->q_ctrl_blk[SAP_QUEUE_IDX_DATA].size =
 		cpu_to_le32(SAP_M2H_DATA_Q_SZ);
 	m2h->q_ctrl_blk[SAP_QUEUE_IDX_NOTIF].size =
@@ -647,7 +675,7 @@ iwl_mei_handle_rx_start_ok(struct mei_cl_device *cldev,
 		return;
 	}
 
-	if (rsp->supported_version != SAP_VERSION) {
+	if (rsp->supported_version != iwl_mei_cache.sap_version) {
 		dev_err(&cldev->dev,
 			"didn't get the expected version: got %d\n",
 			rsp->supported_version);
@@ -1281,7 +1309,7 @@ static int iwl_mei_send_start(struct mei_cl_device *cldev)
 		.hdr.type = cpu_to_le32(SAP_ME_MSG_START),
 		.hdr.seq_num = cpu_to_le32(atomic_inc_return(&mei->seq_no)),
 		.hdr.len = cpu_to_le32(sizeof(msg)),
-		.supported_versions[0] = SAP_VERSION,
+		.supported_versions[0] = iwl_mei_cache.sap_version,
 		.init_data_seq_num = cpu_to_le16(0x100),
 		.init_notif_seq_num = cpu_to_le16(0x800),
 	};
-- 
cgit v1.3-3-g829e


From 6d1b52cc9af56b773238516030b82310cb1f1ba2 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:09 +0300
Subject: wifi: iwlwifi: mvm: set ul_mu_data_disable when needed

The firmware needs to know what we had in the HE CAP, propagate that
setting to the firmware through the LINK command.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.fef270d2995b.I328237837df30e1cb98764987eaaf8e8993e058c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h |  8 +++++---
 drivers/net/wireless/intel/iwlwifi/mvm/link.c       | 11 +++++++++++
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index b9ed42faa63e..56b880e68870 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -472,7 +472,9 @@ enum iwl_link_ctx_flags {
  * @bssid_index: index of the associated VAP
  * @bss_color: 11ax AP ID that is used in the HE SIG-A to mark inter BSS frame
  * @spec_link_id: link_id as the AP knows it
- * @reserved2: alignment
+ * @ul_mu_data_disable: OM Control UL MU Data Disable RX Support (bit 44) in
+ *	HE MAC Capabilities information field as defined in figure 9-897 in
+ *	IEEE802.11REVme-D5.0
  * @ibss_bssid_addr: bssid for ibss
  * @reserved_for_ibss_bssid_addr: reserved
  * @reserved3: reserved for future use
@@ -515,11 +517,11 @@ struct iwl_link_config_cmd {
 	u8 bssid_index;
 	u8 bss_color;
 	u8 spec_link_id;
-	u8 reserved2;
+	u8 ul_mu_data_disable;
 	u8 ibss_bssid_addr[6];
 	__le16 reserved_for_ibss_bssid_addr;
 	__le32 reserved3[8];
-} __packed; /* LINK_CONTEXT_CONFIG_CMD_API_S_VER_1, _VER_2, _VER_3 */
+} __packed; /* LINK_CONTEXT_CONFIG_CMD_API_S_VER_1, _VER_2, _VER_3, _VER_4 */
 
 /* Currently FW supports link ids in the range 0-3 and can have
  * at most two active links for each vif.
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index a9929aa49913..3a6e0a90a3ef 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -293,6 +293,17 @@ int iwl_mvm_link_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			(link_conf->uora_ocw_range >> 3) & 0x7;
 	}
 
+	/* ap_sta may be NULL if we're disconnecting */
+	if (changes & LINK_CONTEXT_MODIFY_HE_PARAMS && mvmvif->ap_sta) {
+		struct ieee80211_link_sta *link_sta =
+			link_sta_dereference_check(mvmvif->ap_sta, link_id);
+
+		if (!WARN_ON(!link_sta) && link_sta->he_cap.has_he &&
+		    link_sta->he_cap.he_cap_elem.mac_cap_info[5] &
+		    IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX)
+			cmd.ul_mu_data_disable = 1;
+	}
+
 	/* TODO  how to set ndp_fdbk_buff_th_exp? */
 
 	if (iwl_mvm_set_fw_mu_edca_params(mvm, mvmvif->link[link_id],
-- 
cgit v1.3-3-g829e


From 87c1c28a9aa149489e1667f5754fc24f4973d2d0 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 25 Aug 2024 08:56:37 +0300
Subject: wifi: iwlwifi: mvm: Fix a race in scan abort flow

When the upper layer requests to cancel an ongoing scan, a race
is possible in which by the time the driver starts to handle the
upper layers scan cancel flow, the FW already completed handling
the scan request and the driver received the scan complete
notification but still did not handle the notification. In such a
case the FW will simply ignore the scan abort request coming from
the driver, no notification would arrive from the FW and the entire
abort flow would be considered a failure.

To better handle this, check the status code returned by the FW for
the scan abort command. In case the status indicates that
no scan was aborted, complete the scan abort flow with success, i.e.,
the scan was aborted, as the flow is expected to consume the scan
complete notification.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240825085558.483989d3baef.I3340556a222388504c6330b333360bf77d10f9e2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/scan.h | 13 ++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c    | 42 +++++++++++++++++++-----
 2 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index 8598031567bb..0aefdf353b21 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -1132,6 +1132,19 @@ struct iwl_umac_scan_abort {
 	__le32 flags;
 } __packed; /* SCAN_ABORT_CMD_UMAC_API_S_VER_1 */
 
+/**
+ * enum iwl_umac_scan_abort_status
+ *
+ * @IWL_UMAC_SCAN_ABORT_STATUS_SUCCESS: scan was successfully aborted
+ * @IWL_UMAC_SCAN_ABORT_STATUS_IN_PROGRESS: scan abort is in progress
+ * @IWL_UMAC_SCAN_ABORT_STATUS_NOT_FOUND: nothing to abort
+ */
+enum iwl_umac_scan_abort_status {
+	IWL_UMAC_SCAN_ABORT_STATUS_SUCCESS = 0,
+	IWL_UMAC_SCAN_ABORT_STATUS_IN_PROGRESS,
+	IWL_UMAC_SCAN_ABORT_STATUS_NOT_FOUND,
+};
+
 /**
  * struct iwl_umac_scan_complete
  * @uid: scan id, &enum iwl_umac_scan_uid_offsets
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 8e0df31f1b3e..4ae6339f87c7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -3301,13 +3301,23 @@ void iwl_mvm_rx_umac_scan_iter_complete_notif(struct iwl_mvm *mvm,
 		       mvm->scan_start);
 }
 
-static int iwl_mvm_umac_scan_abort(struct iwl_mvm *mvm, int type)
+static int iwl_mvm_umac_scan_abort(struct iwl_mvm *mvm, int type, bool *wait)
 {
-	struct iwl_umac_scan_abort cmd = {};
+	struct iwl_umac_scan_abort abort_cmd = {};
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(IWL_ALWAYS_LONG_GROUP, SCAN_ABORT_UMAC),
+		.len = { sizeof(abort_cmd), },
+		.data = { &abort_cmd, },
+		.flags = CMD_SEND_IN_RFKILL,
+	};
+
 	int uid, ret;
+	u32 status = IWL_UMAC_SCAN_ABORT_STATUS_NOT_FOUND;
 
 	lockdep_assert_held(&mvm->mutex);
 
+	*wait = true;
+
 	/* We should always get a valid index here, because we already
 	 * checked that this type of scan was running in the generic
 	 * code.
@@ -3316,17 +3326,28 @@ static int iwl_mvm_umac_scan_abort(struct iwl_mvm *mvm, int type)
 	if (WARN_ON_ONCE(uid < 0))
 		return uid;
 
-	cmd.uid = cpu_to_le32(uid);
+	abort_cmd.uid = cpu_to_le32(uid);
 
 	IWL_DEBUG_SCAN(mvm, "Sending scan abort, uid %u\n", uid);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm,
-				   WIDE_ID(IWL_ALWAYS_LONG_GROUP, SCAN_ABORT_UMAC),
-				   CMD_SEND_IN_RFKILL, sizeof(cmd), &cmd);
+	ret = iwl_mvm_send_cmd_status(mvm, &cmd, &status);
+
+	IWL_DEBUG_SCAN(mvm, "Scan abort: ret=%d, status=%u\n", ret, status);
 	if (!ret)
 		mvm->scan_uid_status[uid] = type << IWL_MVM_SCAN_STOPPING_SHIFT;
 
-	IWL_DEBUG_SCAN(mvm, "Scan abort: ret=%d\n", ret);
+	/* Handle the case that the FW is no longer familiar with the scan that
+	 * is to be stopped. In such a case, it is expected that the scan
+	 * complete notification was already received but not yet processed.
+	 * In such a case, there is no need to wait for a scan complete
+	 * notification and the flow should continue similar to the case that
+	 * the scan was really aborted.
+	 */
+	if (status == IWL_UMAC_SCAN_ABORT_STATUS_NOT_FOUND) {
+		mvm->scan_uid_status[uid] = type << IWL_MVM_SCAN_STOPPING_SHIFT;
+		*wait = false;
+	}
+
 	return ret;
 }
 
@@ -3336,6 +3357,7 @@ static int iwl_mvm_scan_stop_wait(struct iwl_mvm *mvm, int type)
 	static const u16 scan_done_notif[] = { SCAN_COMPLETE_UMAC,
 					      SCAN_OFFLOAD_COMPLETE, };
 	int ret;
+	bool wait = true;
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -3347,7 +3369,7 @@ static int iwl_mvm_scan_stop_wait(struct iwl_mvm *mvm, int type)
 	IWL_DEBUG_SCAN(mvm, "Preparing to stop scan, type %x\n", type);
 
 	if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_UMAC_SCAN))
-		ret = iwl_mvm_umac_scan_abort(mvm, type);
+		ret = iwl_mvm_umac_scan_abort(mvm, type, &wait);
 	else
 		ret = iwl_mvm_lmac_scan_abort(mvm);
 
@@ -3355,6 +3377,10 @@ static int iwl_mvm_scan_stop_wait(struct iwl_mvm *mvm, int type)
 		IWL_DEBUG_SCAN(mvm, "couldn't stop scan type %d\n", type);
 		iwl_remove_notification(&mvm->notif_wait, &wait_scan_done);
 		return ret;
+	} else if (!wait) {
+		IWL_DEBUG_SCAN(mvm, "no need to wait for scan type %d\n", type);
+		iwl_remove_notification(&mvm->notif_wait, &wait_scan_done);
+		return 0;
 	}
 
 	return iwl_wait_notification(&mvm->notif_wait, &wait_scan_done,
-- 
cgit v1.3-3-g829e


From a949075d4bbf1ca83ccdeaa6ef4ac2ce7526c5f4 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 29 Jul 2024 20:20:11 +0300
Subject: wifi: iwlwifi: mvm: set the cipher for secured NDP ranging

The cipher pointer is not set, but is derefereced trying to set its
content, which leads to a NULL pointer dereference.
Fix it by pointing to the cipher parameter before dereferencing.

Fixes: 626be4bf99f6 ("wifi: iwlwifi: mvm: modify iwl_mvm_ftm_set_secured_ranging() parameters")
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.24e83369f136.I80501ddcb82920561f450d00020d860e7a3f90c6@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index afd90a52d4ec..55245f913286 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -772,6 +772,7 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			struct iwl_mvm_ftm_iter_data target;
 
 			target.bssid = bssid;
+			target.cipher = cipher;
 			ieee80211_iter_keys(mvm->hw, vif, iter, &target);
 		} else {
 			memcpy(tk, entry->tk, sizeof(entry->tk));
-- 
cgit v1.3-3-g829e


From 3a7ee94559dfd640604d0265739e86dec73b64e8 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Mon, 29 Jul 2024 20:20:12 +0300
Subject: wifi: iwlwifi: mvm: increase the time between ranging measurements

The algo running in fw may take a little longer than 5 milliseconds,
(e.g. measurement on 80MHz while associated). Increase the minimum
time between measurements to 7 milliseconds.

Fixes: 830aa3e7d1ca ("iwlwifi: mvm: add support for range request command version 13")
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.d3f3c26e00d9.I09e951290e8a3d73f147b88166fd9a678d1d69ed@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/constants.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index c4c1e67b9ac7..8f63cbe9e50d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -109,7 +109,7 @@
 #define IWL_MVM_FTM_INITIATOR_SECURE_LTF	false
 #define IWL_MVM_FTM_RESP_NDP_SUPPORT		true
 #define IWL_MVM_FTM_RESP_LMR_FEEDBACK_SUPPORT	true
-#define IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR	5
+#define IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR	7
 #define IWL_MVM_FTM_NON_TB_MAX_TIME_BETWEEN_MSR	1000
 #define IWL_MVM_D3_DEBUG			false
 #define IWL_MVM_USE_TWT				true
-- 
cgit v1.3-3-g829e


From 1c9c5aebb5db162515ebb719e0f6cf1292e9c40e Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:13 +0300
Subject: wifi: iwlwifi: mvm:
 s/iwl_bt_coex_profile_notif/iwl_bt_coex_prof_old_notif

The iwl_bt_coex_profile_notif is now being obsoleted. It'll be replaced
by a new notification coming with a non-legacy group. Rename it to avoid
confusion.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.dc29fd0d7817.I5881fce86ec8b76ae98d2948265434b8e7d860c1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/coex.h     | 4 ++--
 drivers/net/wireless/intel/iwlwifi/fw/api/commands.h | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/coex.c        | 8 ++++----
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h         | 6 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c         | 4 ++--
 5 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
index b97a43353779..433bda61c32e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
@@ -95,7 +95,7 @@ enum iwl_bt_ci_compliance {
 }; /* BT_COEX_CI_COMPLIENCE_E_VER_1 */
 
 /**
- * struct iwl_bt_coex_profile_notif - notification about BT coex
+ * struct iwl_bt_coex_prof_old_notif - notification about BT coex
  * @mbox_msg: message from BT to WiFi
  * @msg_idx: the index of the message
  * @bt_ci_compliance: enum %iwl_bt_ci_compliance
@@ -110,7 +110,7 @@ enum iwl_bt_ci_compliance {
  * @wifi_loss_mid_high_rssi: The predicted lost WiFi rate (% of air time that
  *	BT is utilizing) when the RSSI is mid/high (>= -65 dBm)
  */
-struct iwl_bt_coex_profile_notif {
+struct iwl_bt_coex_prof_old_notif {
 	__le32 mbox_msg[4];
 	__le32 msg_idx;
 	__le32 bt_ci_compliance;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 7544c4cb1a30..548eeca09881 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2022 Intel Corporation
+ * Copyright (C) 2018-2022, 2024 Intel Corporation
  */
 #ifndef __iwl_fw_api_commands_h__
 #define __iwl_fw_api_commands_h__
@@ -467,7 +467,7 @@ enum iwl_legacy_cmds {
 	MARKER_CMD = 0xcb,
 
 	/**
-	 * @BT_PROFILE_NOTIFICATION: &struct iwl_bt_coex_profile_notif
+	 * @BT_PROFILE_NOTIFICATION: &struct iwl_bt_coex_prof_old_notif
 	 */
 	BT_PROFILE_NOTIFICATION = 0xce,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index ad3e14a0d043..f2912105c7b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -208,7 +208,7 @@ static int iwl_mvm_bt_coex_reduced_txp(struct iwl_mvm *mvm, u8 sta_id,
 }
 
 struct iwl_bt_iterator_data {
-	struct iwl_bt_coex_profile_notif *notif;
+	struct iwl_bt_coex_prof_old_notif *notif;
 	struct iwl_mvm *mvm;
 	struct ieee80211_chanctx_conf *primary;
 	struct ieee80211_chanctx_conf *secondary;
@@ -591,11 +591,11 @@ static void iwl_mvm_bt_coex_notif_handle(struct iwl_mvm *mvm)
 	}
 }
 
-void iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
-			      struct iwl_rx_cmd_buffer *rxb)
+void iwl_mvm_rx_bt_coex_old_notif(struct iwl_mvm *mvm,
+				  struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_bt_coex_profile_notif *notif = (void *)pkt->data;
+	struct iwl_bt_coex_prof_old_notif *notif = (void *)pkt->data;
 
 	IWL_DEBUG_COEX(mvm, "BT Coex Notification received\n");
 	IWL_DEBUG_COEX(mvm, "\tBT ci compliance %d\n", notif->bt_ci_compliance);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index e2cc378d6d91..b968ca0c6a40 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1201,7 +1201,7 @@ struct iwl_mvm {
 	wait_queue_head_t rx_sync_waitq;
 
 	/* BT-Coex */
-	struct iwl_bt_coex_profile_notif last_bt_notif;
+	struct iwl_bt_coex_prof_old_notif last_bt_notif;
 	struct iwl_bt_coex_ci_cmd last_bt_ci_cmd;
 
 	u8 bt_tx_prio;
@@ -2322,8 +2322,8 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm,
 
 /* BT Coex */
 int iwl_mvm_send_bt_init_conf(struct iwl_mvm *mvm);
-void iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
-			      struct iwl_rx_cmd_buffer *rxb);
+void iwl_mvm_rx_bt_coex_old_notif(struct iwl_mvm *mvm,
+				  struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			   enum ieee80211_rssi_event_data);
 void iwl_mvm_bt_coex_vif_change(struct iwl_mvm *mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index b7dcae76a05d..cb123852fe94 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -333,9 +333,9 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 		       iwl_mvm_tlc_update_notif, RX_HANDLER_SYNC,
 		       struct iwl_tlc_update_notif),
 
-	RX_HANDLER(BT_PROFILE_NOTIFICATION, iwl_mvm_rx_bt_coex_notif,
+	RX_HANDLER(BT_PROFILE_NOTIFICATION, iwl_mvm_rx_bt_coex_old_notif,
 		   RX_HANDLER_ASYNC_LOCKED_WIPHY,
-		   struct iwl_bt_coex_profile_notif),
+		   struct iwl_bt_coex_prof_old_notif),
 	RX_HANDLER_NO_SIZE(BEACON_NOTIFICATION, iwl_mvm_rx_beacon_notif,
 			   RX_HANDLER_ASYNC_LOCKED),
 	RX_HANDLER_NO_SIZE(STATISTICS_NOTIFICATION, iwl_mvm_rx_statistics,
-- 
cgit v1.3-3-g829e


From b85b397a9ece4cdde2e18424b822702220094c83 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:14 +0300
Subject: wifi: iwlwifi: mvm: start to support the new BT profile notification

We have a new notification the BT profile. It contains almost nothing,
only the wifi loss information. Copy this into mvm. We still need to
iterate over the vifs / links to use this data.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.637499f3a85a.I8bf654cf5d8aa038100273876c936845ecc338f7@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/coex.h   | 25 +++++++++++++
 .../net/wireless/intel/iwlwifi/fw/api/commands.h   |  3 ++
 drivers/net/wireless/intel/iwlwifi/mvm/coex.c      | 41 ++++++++++++++++++----
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |  9 +++--
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       | 11 ++++++
 5 files changed, 80 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
index 433bda61c32e..ddc84430d895 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h
@@ -126,4 +126,29 @@ struct iwl_bt_coex_prof_old_notif {
 	     * BT_COEX_PROFILE_NTFY_API_S_VER_5
 	     */
 
+/**
+ * enum iwl_bt_coex_subcmd_ids - coex configuration command IDs
+ */
+enum iwl_bt_coex_subcmd_ids {
+       /**
+	*@PROFILE_NOTIF: &struct iwl_bt_coex_profile_notif
+	*/
+	PROFILE_NOTIF = 0xFF,
+};
+
+#define COEX_NUM_BAND	3
+#define COEX_NUM_CHAINS	2
+
+/**
+ * struct iwl_bt_coex_profile_notif - notification about BT coex
+ * @wifi_loss_low_rssi: The predicted lost WiFi rate (% of air time that BT is
+ *	utilizing) when the RSSI is low (<= -65 dBm)
+ * @wifi_loss_mid_high_rssi: The predicted lost WiFi rate (% of air time that
+ *	BT is utilizing) when the RSSI is mid/high (>= -65 dBm)
+ */
+struct iwl_bt_coex_profile_notif {
+	u8 wifi_loss_low_rssi[COEX_NUM_BAND][COEX_NUM_CHAINS];
+	u8 wifi_loss_mid_high_rssi[COEX_NUM_BAND][COEX_NUM_CHAINS];
+} __packed; /* BT_COEX_BT_PROFILE_NTF_API_S_VER_1 */
+
 #endif /* __iwl_fw_api_coex_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 548eeca09881..377fac278511 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -25,6 +25,8 @@
  * @NAN_GROUP: NAN group, uses command IDs from &enum iwl_nan_subcmd_ids
  * @LOCATION_GROUP: location group, uses command IDs from
  *	&enum iwl_location_subcmd_ids
+ * @BT_COEX_GROUP: bt coex group, uses command IDs from
+ *	&enum iwl_bt_coex_subcmd_ids
  * @PROT_OFFLOAD_GROUP: protocol offload group, uses command IDs from
  *	&enum iwl_prot_offload_subcmd_ids
  * @REGULATORY_AND_NVM_GROUP: regulatory/NVM group, uses command IDs from
@@ -43,6 +45,7 @@ enum iwl_mvm_command_groups {
 	SCAN_GROUP = 0x6,
 	NAN_GROUP = 0x7,
 	LOCATION_GROUP = 0x8,
+	BT_COEX_GROUP = 0x9,
 	PROT_OFFLOAD_GROUP = 0xb,
 	REGULATORY_AND_NVM_GROUP = 0xc,
 	DEBUG_GROUP = 0xf,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index f2912105c7b5..0bfe250c3bc8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -266,10 +266,26 @@ iwl_mvm_bt_coex_calculate_esr_mode(struct iwl_mvm *mvm,
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	bool have_wifi_loss_rate =
 		iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
-					BT_PROFILE_NOTIFICATION, 0) > 4;
+					BT_PROFILE_NOTIFICATION, 0) > 4 ||
+		iwl_fw_lookup_notif_ver(mvm->fw, BT_COEX_GROUP,
+					PROFILE_NOTIF, 0) >= 1;
+	u8 wifi_loss_mid_high_rssi;
+	u8 wifi_loss_low_rssi;
 	u8 wifi_loss_rate;
 
-	if (mvm->last_bt_notif.wifi_loss_low_rssi == BT_OFF)
+	if (iwl_fw_lookup_notif_ver(mvm->fw, BT_COEX_GROUP,
+				    PROFILE_NOTIF, 0) >= 1) {
+		/* For now, we consider 2.4 GHz band / ANT_A only */
+		wifi_loss_mid_high_rssi =
+			mvm->last_bt_wifi_loss.wifi_loss_mid_high_rssi[PHY_BAND_24][0];
+		wifi_loss_low_rssi =
+			mvm->last_bt_wifi_loss.wifi_loss_low_rssi[PHY_BAND_24][0];
+	} else {
+		wifi_loss_mid_high_rssi = mvm->last_bt_notif.wifi_loss_mid_high_rssi;
+		wifi_loss_low_rssi = mvm->last_bt_notif.wifi_loss_low_rssi;
+	}
+
+	if (wifi_loss_low_rssi == BT_OFF)
 		return true;
 
 	if (primary)
@@ -286,20 +302,20 @@ iwl_mvm_bt_coex_calculate_esr_mode(struct iwl_mvm *mvm,
 	 * we will get an update on this and exit eSR.
 	 */
 	if (!link_rssi)
-		wifi_loss_rate = mvm->last_bt_notif.wifi_loss_mid_high_rssi;
+		wifi_loss_rate = wifi_loss_mid_high_rssi;
 
 	else if (mvmvif->esr_active)
 		 /* RSSI needs to get really low to disable eSR... */
 		wifi_loss_rate =
 			link_rssi <= -IWL_MVM_BT_COEX_DISABLE_ESR_THRESH ?
-				mvm->last_bt_notif.wifi_loss_low_rssi :
-				mvm->last_bt_notif.wifi_loss_mid_high_rssi;
+				wifi_loss_low_rssi :
+				wifi_loss_mid_high_rssi;
 	else
 		/* ...And really high before we enable it back */
 		wifi_loss_rate =
 			link_rssi <= -IWL_MVM_BT_COEX_ENABLE_ESR_THRESH ?
-				mvm->last_bt_notif.wifi_loss_low_rssi :
-				mvm->last_bt_notif.wifi_loss_mid_high_rssi;
+				wifi_loss_low_rssi :
+				wifi_loss_mid_high_rssi;
 
 	return wifi_loss_rate <= IWL_MVM_BT_COEX_WIFI_LOSS_THRESH;
 }
@@ -612,6 +628,17 @@ void iwl_mvm_rx_bt_coex_old_notif(struct iwl_mvm *mvm,
 	iwl_mvm_bt_coex_notif_handle(mvm);
 }
 
+void iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
+			      struct iwl_rx_cmd_buffer *rxb)
+{
+	const struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	const struct iwl_bt_coex_profile_notif *notif = (const void *)pkt->data;
+
+	mvm->last_bt_wifi_loss = *notif;
+
+	/* TODO: Iterate over vifs / links to take that into account */
+}
+
 void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			   enum ieee80211_rssi_event_data rssi_event)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index b968ca0c6a40..9cb7045cc0ba 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1200,8 +1200,11 @@ struct iwl_mvm {
 
 	wait_queue_head_t rx_sync_waitq;
 
-	/* BT-Coex */
-	struct iwl_bt_coex_prof_old_notif last_bt_notif;
+	/* BT-Coex - only one of those will be used */
+	union {
+		struct iwl_bt_coex_prof_old_notif last_bt_notif;
+		struct iwl_bt_coex_profile_notif last_bt_wifi_loss;
+	};
 	struct iwl_bt_coex_ci_cmd last_bt_ci_cmd;
 
 	u8 bt_tx_prio;
@@ -2324,6 +2327,8 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm,
 int iwl_mvm_send_bt_init_conf(struct iwl_mvm *mvm);
 void iwl_mvm_rx_bt_coex_old_notif(struct iwl_mvm *mvm,
 				  struct iwl_rx_cmd_buffer *rxb);
+void iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
+			      struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			   enum ieee80211_rssi_event_data);
 void iwl_mvm_bt_coex_vif_change(struct iwl_mvm *mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index cb123852fe94..279c92307420 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -336,6 +336,9 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 	RX_HANDLER(BT_PROFILE_NOTIFICATION, iwl_mvm_rx_bt_coex_old_notif,
 		   RX_HANDLER_ASYNC_LOCKED_WIPHY,
 		   struct iwl_bt_coex_prof_old_notif),
+	RX_HANDLER_GRP(BT_COEX_GROUP, PROFILE_NOTIF, iwl_mvm_rx_bt_coex_notif,
+		       RX_HANDLER_ASYNC_LOCKED_WIPHY,
+		       struct iwl_bt_coex_profile_notif),
 	RX_HANDLER_NO_SIZE(BEACON_NOTIFICATION, iwl_mvm_rx_beacon_notif,
 			   RX_HANDLER_ASYNC_LOCKED),
 	RX_HANDLER_NO_SIZE(STATISTICS_NOTIFICATION, iwl_mvm_rx_statistics,
@@ -713,6 +716,13 @@ static const struct iwl_hcmd_names iwl_mvm_regulatory_and_nvm_names[] = {
 	HCMD_NAME(TAS_CONFIG),
 };
 
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mvm_bt_coex_names[] = {
+	HCMD_NAME(PROFILE_NOTIF),
+};
+
 static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 	[LEGACY_GROUP] = HCMD_ARR(iwl_mvm_legacy_names),
 	[LONG_GROUP] = HCMD_ARR(iwl_mvm_legacy_names),
@@ -722,6 +732,7 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = {
 	[DATA_PATH_GROUP] = HCMD_ARR(iwl_mvm_data_path_names),
 	[SCAN_GROUP] = HCMD_ARR(iwl_mvm_scan_names),
 	[LOCATION_GROUP] = HCMD_ARR(iwl_mvm_location_names),
+	[BT_COEX_GROUP] = HCMD_ARR(iwl_mvm_bt_coex_names),
 	[PROT_OFFLOAD_GROUP] = HCMD_ARR(iwl_mvm_prot_offload_names),
 	[REGULATORY_AND_NVM_GROUP] =
 		HCMD_ARR(iwl_mvm_regulatory_and_nvm_names),
-- 
cgit v1.3-3-g829e


From 2b7ee1a10a72ef8f3df621133ac04e80e8214037 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:15 +0300
Subject: wifi: iwlwiif: mvm: handle the new BT notif

Iterate all the links and check if any action must be taken.
The new notification impacts only the esr decision.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.00cfc07879c6.I8491483fda3b5888ea6ffa10fbd17807e443f943@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/coex.c | 36 ++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
index 0bfe250c3bc8..b607961970e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/coex.c
@@ -525,6 +525,35 @@ static void iwl_mvm_bt_notif_iterator(void *_data, u8 *mac,
 		iwl_mvm_bt_notif_per_link(mvm, vif, data, link_id);
 }
 
+/* must be called under rcu_read_lock */
+static void iwl_mvm_bt_coex_notif_iterator(void *_data, u8 *mac,
+					   struct ieee80211_vif *vif)
+{
+	struct iwl_mvm *mvm = _data;
+
+	lockdep_assert_held(&mvm->mutex);
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	for (int link_id = 0;
+	     link_id < IEEE80211_MLD_MAX_NUM_LINKS;
+	     link_id++) {
+		struct ieee80211_bss_conf *link_conf =
+			rcu_dereference_check(vif->link_conf[link_id],
+					      lockdep_is_held(&mvm->mutex));
+		struct ieee80211_chanctx_conf *chanctx_conf =
+			rcu_dereference_check(link_conf->chanctx_conf,
+					      lockdep_is_held(&mvm->mutex));
+
+		if ((!chanctx_conf ||
+		     chanctx_conf->def.chan->band != NL80211_BAND_2GHZ))
+			continue;
+
+		iwl_mvm_bt_coex_update_link_esr(mvm, vif, link_id);
+	}
+}
+
 static void iwl_mvm_bt_coex_notif_handle(struct iwl_mvm *mvm)
 {
 	struct iwl_bt_iterator_data data = {
@@ -634,9 +663,14 @@ void iwl_mvm_rx_bt_coex_notif(struct iwl_mvm *mvm,
 	const struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	const struct iwl_bt_coex_profile_notif *notif = (const void *)pkt->data;
 
+	lockdep_assert_held(&mvm->mutex);
+
 	mvm->last_bt_wifi_loss = *notif;
 
-	/* TODO: Iterate over vifs / links to take that into account */
+	ieee80211_iterate_active_interfaces(mvm->hw,
+					    IEEE80211_IFACE_ITER_NORMAL,
+					    iwl_mvm_bt_coex_notif_iterator,
+					    mvm);
 }
 
 void iwl_mvm_bt_rssi_event(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-- 
cgit v1.3-3-g829e


From db9979d5aae8496233a8551320a69a2f9b1b0ac3 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Mon, 29 Jul 2024 20:20:16 +0300
Subject: wifi: iwlwifi: mvm: add firmware debug points for EMLSR entry / exit

This will help to dump the firmware logs at the right spot if needed.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.3a91e89e32f8.Ieb28d7756c47dee52c912a71abe82fa0b08b19da@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h   | 4 ++++
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 6 ++++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 855cd13a181e..550de6db1834 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -476,6 +476,8 @@ enum iwl_fw_ini_region_device_memory_subtype {
  * @IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_START: start handling override preset
  *	request
  * @IWL_FW_INI_TIME_SCAN_FAILURE: failed scan channel list
+ * @IWL_FW_INI_TIME_ESR_LINK_UP: EMLSR is active (several links are activated)
+ * @IWL_FW_INI_TIME_ESR_LINK_DOWN: EMLSR is inactive (only one active link left)
  * @IWL_FW_INI_TIME_POINT_NUM: number of time points
  */
 enum iwl_fw_ini_time_point {
@@ -509,6 +511,8 @@ enum iwl_fw_ini_time_point {
 	IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_EXT_REQ,
 	IWL_FW_INI_TIME_POINT_PRESET_OVERRIDE_START,
 	IWL_FW_INI_TIME_SCAN_FAILURE,
+	IWL_FW_INI_TIME_ESR_LINK_UP,
+	IWL_FW_INI_TIME_ESR_LINK_DOWN,
 	IWL_FW_INI_TIME_POINT_NUM,
 }; /* FW_TLV_DEBUG_TIME_POINT_API_E */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 3c99396ad369..ed30247de407 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -269,6 +269,9 @@ static int iwl_mvm_esr_mode_active(struct iwl_mvm *mvm,
 	 */
 	iwl_mvm_restart_mpdu_count(mvm, mvmvif);
 
+	iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_ESR_LINK_UP,
+			       NULL);
+
 	return ret;
 }
 
@@ -456,6 +459,9 @@ static int iwl_mvm_esr_mode_inactive(struct iwl_mvm *mvm,
 	/* Start a new counting window */
 	iwl_mvm_restart_mpdu_count(mvm, mvmvif);
 
+	iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_ESR_LINK_DOWN,
+			       NULL);
+
 	return ret;
 }
 
-- 
cgit v1.3-3-g829e


From b312e357207c53270bd9b99e0bfd5dd9bf183078 Mon Sep 17 00:00:00 2001
From: "Somashekhar(Som)" <somashekhar.puttagangaiah@intel.com>
Date: Mon, 29 Jul 2024 20:20:17 +0300
Subject: wifi: iwlwifi: Enable channel puncturing for US/CAN from bios

Add support for enabling channel puncturing for US/CAN based
on BIOS configuration through UEFI

Signed-off-by: Somashekhar(Som) <somashekhar.puttagangaiah@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240729201718.828f3ecf5118.I5561ab8c7cd48ad4e5d6daf21b037bf88c619a4a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/regulatory.c | 16 ++++++++++++
 drivers/net/wireless/intel/iwlwifi/fw/regulatory.h |  2 ++
 drivers/net/wireless/intel/iwlwifi/fw/uefi.c       | 29 ++++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/fw/uefi.h       | 28 +++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  |  8 ++----
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |  1 +
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       |  1 +
 7 files changed, 79 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
index 560a91998cc4..4d9a1f83ef8c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
@@ -634,3 +634,19 @@ int iwl_bios_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func,
 	GET_BIOS_TABLE(dsm, fwrt, func, value);
 }
 IWL_EXPORT_SYMBOL(iwl_bios_get_dsm);
+
+bool iwl_puncturing_is_allowed_in_bios(u32 puncturing, u16 mcc)
+{
+	/* Some kind of regulatory mess means we need to currently disallow
+	 * puncturing in the US and Canada unless enabled in BIOS.
+	 */
+	switch (mcc) {
+	case IWL_MCC_US:
+		return puncturing & IWL_UEFI_CNV_PUNCTURING_USA_EN_MSK;
+	case IWL_MCC_CANADA:
+		return puncturing & IWL_UEFI_CNV_PUNCTURING_CANADA_EN_MSK;
+	default:
+		return true;
+	}
+}
+IWL_EXPORT_SYMBOL(iwl_puncturing_is_allowed_in_bios);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index e2c056f483c1..c2209948b4c0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -217,4 +217,6 @@ static inline u32 iwl_bios_get_ppag_flags(const u32 ppag_modes,
 	return ppag_modes & (ppag_ver < 3 ? IWL_PPAG_ETSI_CHINA_MASK :
 					    IWL_PPAG_REV3_MASK);
 }
+
+bool iwl_puncturing_is_allowed_in_bios(u32 puncturing, u16 mcc);
 #endif /* __fw_regulatory_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index fb982d4fe851..754fc5014fbf 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -729,3 +729,32 @@ out:
 	kfree(data);
 	return ret;
 }
+
+int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt)
+{
+	struct uefi_cnv_var_puncturing_data *data;
+	/* default value is not enabled if there is any issue in reading
+	 * uefi variable or revision is not supported
+	 */
+	int puncturing = 0;
+
+	data = iwl_uefi_get_verified_variable(fwrt->trans,
+					      IWL_UEFI_PUNCTURING_NAME,
+					      "UefiCnvWlanPuncturing",
+					      sizeof(*data), NULL);
+	if (IS_ERR(data))
+		return puncturing;
+
+	if (data->revision != IWL_UEFI_PUNCTURING_REVISION) {
+		IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI PUNCTURING rev:%d\n",
+				data->revision);
+	} else {
+		puncturing = data->puncturing & IWL_UEFI_PUNCTURING_REV0_MASK;
+		IWL_DEBUG_RADIO(fwrt, "Loaded puncturing bits from UEFI: %d\n",
+				puncturing);
+	}
+
+	kfree(data);
+	return puncturing;
+}
+IWL_EXPORT_SYMBOL(iwl_uefi_get_puncturing);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
index 1f8884ca8997..0b2477190070 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
@@ -22,6 +22,7 @@
 #define IWL_UEFI_ECKV_NAME		L"UefiCnvWlanECKV"
 #define IWL_UEFI_DSM_NAME		L"UefiCnvWlanGeneralCfg"
 #define IWL_UEFI_WBEM_NAME		L"UefiCnvWlanWBEM"
+#define IWL_UEFI_PUNCTURING_NAME	L"UefiCnvWlanPuncturing"
 
 
 #define IWL_SGOM_MAP_SIZE		339
@@ -38,6 +39,7 @@
 #define IWL_UEFI_ECKV_REVISION		0
 #define IWL_UEFI_WBEM_REVISION		0
 #define IWL_UEFI_DSM_REVISION		4
+#define IWL_UEFI_PUNCTURING_REVISION	0
 
 struct pnvm_sku_package {
 	u8 rev;
@@ -194,6 +196,25 @@ struct uefi_cnv_wlan_wbem_data {
 	u32 wbem_320mhz_per_mcc;
 } __packed;
 
+enum iwl_uefi_cnv_puncturing_flags {
+	IWL_UEFI_CNV_PUNCTURING_USA_EN_MSK	= BIT(0),
+	IWL_UEFI_CNV_PUNCTURING_CANADA_EN_MSK	= BIT(1),
+};
+
+#define IWL_UEFI_PUNCTURING_REV0_MASK (IWL_UEFI_CNV_PUNCTURING_USA_EN_MSK | \
+				       IWL_UEFI_CNV_PUNCTURING_CANADA_EN_MSK)
+/**
+ * struct uefi_cnv_var_puncturing_data - controlling channel
+ *	puncturing for few countries.
+ * @revision: the revision of the table
+ * @puncturing: enablement of channel puncturing per mcc
+ *	see &enum iwl_uefi_cnv_puncturing_flags.
+ */
+struct uefi_cnv_var_puncturing_data {
+	u8 revision;
+	u32 puncturing;
+} __packed;
+
 /*
  * This is known to be broken on v4.19 and to work on v5.4.  Until we
  * figure out why this is the case and how to make it work, simply
@@ -224,6 +245,7 @@ int iwl_uefi_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func,
 void iwl_uefi_get_sgom_table(struct iwl_trans *trans, struct iwl_fw_runtime *fwrt);
 int iwl_uefi_get_uats_table(struct iwl_trans *trans,
 			    struct iwl_fw_runtime *fwrt);
+int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt);
 #else /* CONFIG_EFI */
 static inline void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len)
 {
@@ -320,5 +342,11 @@ int iwl_uefi_get_uats_table(struct iwl_trans *trans,
 {
 	return 0;
 }
+
+static inline
+int iwl_uefi_get_puncturing(struct iwl_fw_runtime *fwrt)
+{
+	return 0;
+}
 #endif /* CONFIG_EFI */
 #endif /* __iwl_fw_uefi__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index f48f445e006c..d6f4caa939bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -165,12 +165,8 @@ struct ieee80211_regdomain *iwl_mvm_get_regdomain(struct wiphy *wiphy,
 	mvm->lar_regdom_set = true;
 	mvm->mcc_src = src_id;
 
-	/* Some kind of regulatory mess means we need to currently disallow
-	 * puncturing in the US and Canada. Do that here, at least until we
-	 * figure out the new chanctx APIs for puncturing.
-	 */
-	if (resp->mcc == cpu_to_le16(IWL_MCC_US) ||
-	    resp->mcc == cpu_to_le16(IWL_MCC_CANADA))
+	if (!iwl_puncturing_is_allowed_in_bios(mvm->bios_enable_puncturing,
+					       le16_to_cpu(resp->mcc)))
 		ieee80211_hw_set(mvm->hw, DISALLOW_PUNCTURING);
 	else
 		__clear_bit(IEEE80211_HW_DISALLOW_PUNCTURING, mvm->hw->flags);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 9cb7045cc0ba..bd754b8a71fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1368,6 +1368,7 @@ struct iwl_mvm {
 	struct iwl_mvm_acs_survey *acs_survey;
 
 	bool statistics_clear;
+	u32 bios_enable_puncturing;
 };
 
 /* Extract MVM priv from op_mode and _hw */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 279c92307420..8896d9792feb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1296,6 +1296,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	}
 
 	mvm->fw_restart = iwlwifi_mod_params.fw_restart ? -1 : 0;
+	mvm->bios_enable_puncturing = iwl_uefi_get_puncturing(&mvm->fwrt);
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
 		/*
-- 
cgit v1.3-3-g829e


From 36a95e9c51684bbc0983219cc1d86a8428e4d65f Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Mon, 29 Jul 2024 20:20:18 +0300
Subject: wifi: iwlwifi: mvm: add and improve EMLSR debug info

Add prints of the per-link MPDU counters, and change the other MPDU
counters related prints to use DL_INFO, which is already used for all
EMLSR tests anyway, instead of DL_STATS which pollutes the logs with all
the RX signal info.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Daniel Gabay <daniel.gabay@intel.com>
Link: https://patch.msgid.link/20240729201718.02bd85837c87.I85480c9c4fab0f7a574dd69cbeafd82674146921@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/rx.c           | 7 +++++--
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c          | 2 +-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index ed30247de407..72bb6865dd63 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -223,7 +223,7 @@ static void iwl_mvm_restart_mpdu_count(struct iwl_mvm *mvm,
 		spin_unlock_bh(&mvmsta->mpdu_counters[q].lock);
 	}
 
-	IWL_DEBUG_STATS(mvm, "MPDU counters are cleared\n");
+	IWL_DEBUG_INFO(mvm, "MPDU counters are cleared\n");
 }
 
 static int iwl_mvm_esr_mode_active(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index bc8078875c5a..3b5bbece63f6 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -1009,8 +1009,8 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm)
 		spin_unlock_bh(&mvmsta->mpdu_counters[q].lock);
 	}
 
-	IWL_DEBUG_STATS(mvm, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n",
-			total_tx, total_rx);
+	IWL_DEBUG_INFO(mvm, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n",
+		       total_tx, total_rx);
 
 	/* If we don't have enough MPDUs - exit EMLSR */
 	if (total_tx < IWL_MVM_ENTER_ESR_TPT_THRESH &&
@@ -1020,6 +1020,9 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm)
 		return;
 	}
 
+	IWL_DEBUG_INFO(mvm, "Secondary Link %d: Tx MPDUs: %ld. Rx MPDUs: %ld\n",
+		       sec_link, sec_link_tx, sec_link_rx);
+
 	/* Calculate the percentage of the secondary link TX/RX */
 	sec_link_tx_perc = total_tx ? sec_link_tx * 100 / total_tx : 0;
 	sec_link_rx_perc = total_rx ? sec_link_rx * 100 / total_rx : 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 550c97a014b9..cf4d6425f634 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -4455,7 +4455,7 @@ void iwl_mvm_count_mpdu(struct iwl_mvm_sta *mvm_sta, u8 fw_sta_id, u32 count,
 		       sizeof(queue_counter->per_link));
 		queue_counter->window_start = jiffies;
 
-		IWL_DEBUG_STATS(mvm, "MPDU counters are cleared\n");
+		IWL_DEBUG_INFO(mvm, "MPDU counters are cleared\n");
 	}
 
 	for (int i = 0; i < IWL_FW_MAX_LINK_ID; i++)
-- 
cgit v1.3-3-g829e


From 3a3d1afd25ea2e142c78b67fb769df5be7d308c3 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 5 Aug 2024 08:40:37 +0200
Subject: wifi: lib80211: Handle const struct lib80211_crypto_ops in lib80211

lib80211_register_crypto_ops() and lib80211_unregister_crypto_ops() don't
modify their "struct lib80211_crypto_ops *ops" argument. So, it can be
declared as const.

Doing so, some adjustments are needed to also constify some date in
"struct lib80211_crypt_data", "struct lib80211_crypto_alg" and the
return value of lib80211_get_crypto_ops().

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/c74085e02f33a11327582b19c9f51c3236e85ae2.1722839425.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/ipw2x00/libipw_wx.c | 2 +-
 drivers/staging/rtl8192e/rtllib_wx.c           | 2 +-
 include/net/lib80211.h                         | 8 ++++----
 net/wireless/lib80211.c                        | 8 ++++----
 4 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_wx.c b/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
index 903de34028ef..dbc7153d0a3d 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
@@ -509,7 +509,7 @@ int libipw_wx_set_encodeext(struct libipw_device *ieee,
 	int i, idx, ret = 0;
 	int group_key = 0;
 	const char *alg, *module;
-	struct lib80211_crypto_ops *ops;
+	const struct lib80211_crypto_ops *ops;
 	struct lib80211_crypt_data **crypt;
 
 	struct libipw_security sec = {
diff --git a/drivers/staging/rtl8192e/rtllib_wx.c b/drivers/staging/rtl8192e/rtllib_wx.c
index fbd4ec824084..c730d921463d 100644
--- a/drivers/staging/rtl8192e/rtllib_wx.c
+++ b/drivers/staging/rtl8192e/rtllib_wx.c
@@ -474,7 +474,7 @@ int rtllib_wx_set_encode_ext(struct rtllib_device *ieee,
 	int i, idx;
 	int group_key = 0;
 	const char *alg, *module;
-	struct lib80211_crypto_ops *ops;
+	const struct lib80211_crypto_ops *ops;
 	struct lib80211_crypt_data **crypt;
 
 	struct rtllib_security sec = {
diff --git a/include/net/lib80211.h b/include/net/lib80211.h
index 8b47d3a51cf8..fd0f15d87d80 100644
--- a/include/net/lib80211.h
+++ b/include/net/lib80211.h
@@ -92,7 +92,7 @@ struct lib80211_crypto_ops {
 
 struct lib80211_crypt_data {
 	struct list_head list;	/* delayed deletion list */
-	struct lib80211_crypto_ops *ops;
+	const struct lib80211_crypto_ops *ops;
 	void *priv;
 	atomic_t refcnt;
 };
@@ -113,9 +113,9 @@ struct lib80211_crypt_info {
 int lib80211_crypt_info_init(struct lib80211_crypt_info *info, char *name,
                                 spinlock_t *lock);
 void lib80211_crypt_info_free(struct lib80211_crypt_info *info);
-int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops);
-int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops);
-struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name);
+int lib80211_register_crypto_ops(const struct lib80211_crypto_ops *ops);
+int lib80211_unregister_crypto_ops(const struct lib80211_crypto_ops *ops);
+const struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name);
 void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info,
 				    struct lib80211_crypt_data **crypt);
 
diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c
index d66a913027e0..51e31316bcb8 100644
--- a/net/wireless/lib80211.c
+++ b/net/wireless/lib80211.c
@@ -34,7 +34,7 @@ MODULE_LICENSE("GPL");
 
 struct lib80211_crypto_alg {
 	struct list_head list;
-	struct lib80211_crypto_ops *ops;
+	const struct lib80211_crypto_ops *ops;
 };
 
 static LIST_HEAD(lib80211_crypto_algs);
@@ -161,7 +161,7 @@ void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info,
 }
 EXPORT_SYMBOL(lib80211_crypt_delayed_deinit);
 
-int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops)
+int lib80211_register_crypto_ops(const struct lib80211_crypto_ops *ops)
 {
 	unsigned long flags;
 	struct lib80211_crypto_alg *alg;
@@ -183,7 +183,7 @@ int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops)
 }
 EXPORT_SYMBOL(lib80211_register_crypto_ops);
 
-int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops)
+int lib80211_unregister_crypto_ops(const struct lib80211_crypto_ops *ops)
 {
 	struct lib80211_crypto_alg *alg;
 	unsigned long flags;
@@ -206,7 +206,7 @@ int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops)
 }
 EXPORT_SYMBOL(lib80211_unregister_crypto_ops);
 
-struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name)
+const struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name)
 {
 	struct lib80211_crypto_alg *alg;
 	unsigned long flags;
-- 
cgit v1.3-3-g829e


From 1842442007cded42decd8c27ce84cfc570b8f5f4 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 5 Aug 2024 08:40:38 +0200
Subject: wifi: lib80211: Constify struct lib80211_crypto_ops

Now that functions in lib80211 handle "const struct lib80211_crypto_ops",
some structure can be constified as well.

Constifying these structures moves some data to a read-only section, so
increase overall security.

Before:
   text	   data	    bss	    dec	    hex	filename
   7273	    604	     16	   7893	   1ed5	net/wireless/lib80211.o

After:
   text	   data	    bss	    dec	    hex	filename
   7429	    444	     16	   7889	   1ed1	net/wireless/lib80211.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/0cc3741c15f2c502cc85bddda9d6582b5977c8f9.1722839425.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/lib80211.c            | 2 +-
 net/wireless/lib80211_crypt_ccmp.c | 2 +-
 net/wireless/lib80211_crypt_tkip.c | 2 +-
 net/wireless/lib80211_crypt_wep.c  | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c
index 51e31316bcb8..64c447040786 100644
--- a/net/wireless/lib80211.c
+++ b/net/wireless/lib80211.c
@@ -234,7 +234,7 @@ static void lib80211_crypt_null_deinit(void *priv)
 {
 }
 
-static struct lib80211_crypto_ops lib80211_crypt_null = {
+static const struct lib80211_crypto_ops lib80211_crypt_null = {
 	.name = "NULL",
 	.init = lib80211_crypt_null_init,
 	.deinit = lib80211_crypt_null_deinit,
diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c
index cca5e1cf089e..5aad139130e1 100644
--- a/net/wireless/lib80211_crypt_ccmp.c
+++ b/net/wireless/lib80211_crypt_ccmp.c
@@ -418,7 +418,7 @@ static void lib80211_ccmp_print_stats(struct seq_file *m, void *priv)
 		   ccmp->dot11RSNAStatsCCMPDecryptErrors);
 }
 
-static struct lib80211_crypto_ops lib80211_crypt_ccmp = {
+static const struct lib80211_crypto_ops lib80211_crypt_ccmp = {
 	.name = "CCMP",
 	.init = lib80211_ccmp_init,
 	.deinit = lib80211_ccmp_deinit,
diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c
index 5c8cdf7681e3..63e68e5e121e 100644
--- a/net/wireless/lib80211_crypt_tkip.c
+++ b/net/wireless/lib80211_crypt_tkip.c
@@ -705,7 +705,7 @@ static void lib80211_tkip_print_stats(struct seq_file *m, void *priv)
 		   tkip->dot11RSNAStatsTKIPLocalMICFailures);
 }
 
-static struct lib80211_crypto_ops lib80211_crypt_tkip = {
+static const struct lib80211_crypto_ops lib80211_crypt_tkip = {
 	.name = "TKIP",
 	.init = lib80211_tkip_init,
 	.deinit = lib80211_tkip_deinit,
diff --git a/net/wireless/lib80211_crypt_wep.c b/net/wireless/lib80211_crypt_wep.c
index 6ab9957b8f96..3b148c7bef85 100644
--- a/net/wireless/lib80211_crypt_wep.c
+++ b/net/wireless/lib80211_crypt_wep.c
@@ -226,7 +226,7 @@ static void lib80211_wep_print_stats(struct seq_file *m, void *priv)
 	seq_printf(m, "key[%d] alg=WEP len=%d\n", wep->key_idx, wep->key_len);
 }
 
-static struct lib80211_crypto_ops lib80211_crypt_wep = {
+static const struct lib80211_crypto_ops lib80211_crypt_wep = {
 	.name = "WEP",
 	.init = lib80211_wep_init,
 	.deinit = lib80211_wep_deinit,
-- 
cgit v1.3-3-g829e


From 6a1a6f2dba35cfb5f81100c375a0c87eda90f2c7 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 5 Aug 2024 08:40:39 +0200
Subject: staging: rtl8192e: Constify struct lib80211_crypto_ops

Now that functions in lib80211 handle "const struct lib80211_crypto_ops",
some structure can be constified as well.

Constifying these structures moves some data to a read-only section, so
increase overall security.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Philipp Hortmann <philipp.g.hortmann@gmail.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/dfda6343781ae3d50cd2ec7bbdcf76a489b6922a.1722839425.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/staging/rtl8192e/rtllib_crypt_ccmp.c | 2 +-
 drivers/staging/rtl8192e/rtllib_crypt_tkip.c | 2 +-
 drivers/staging/rtl8192e/rtllib_crypt_wep.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c
index 639877069fad..138733cb00e2 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_ccmp.c
@@ -378,7 +378,7 @@ static void rtllib_ccmp_print_stats(struct seq_file *m, void *priv)
 		   ccmp->dot11rsna_stats_ccmp_decrypt_errors);
 }
 
-static struct lib80211_crypto_ops rtllib_crypt_ccmp = {
+static const struct lib80211_crypto_ops rtllib_crypt_ccmp = {
 	.name			= "R-CCMP",
 	.init			= rtllib_ccmp_init,
 	.deinit			= rtllib_ccmp_deinit,
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
index dc0917b03511..74dc8326c886 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
@@ -678,7 +678,7 @@ static void rtllib_tkip_print_stats(struct seq_file *m, void *priv)
 		   tkip->dot11RSNAStatsTKIPLocalMICFailures);
 }
 
-static struct lib80211_crypto_ops rtllib_crypt_tkip = {
+static const struct lib80211_crypto_ops rtllib_crypt_tkip = {
 	.name			= "R-TKIP",
 	.init			= rtllib_tkip_init,
 	.deinit			= rtllib_tkip_deinit,
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_wep.c b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
index 10092f6884ff..aa18c060d727 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_wep.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_wep.c
@@ -209,7 +209,7 @@ static void prism2_wep_print_stats(struct seq_file *m, void *priv)
 	seq_printf(m, "key[%d] alg=WEP len=%d\n", wep->key_idx, wep->key_len);
 }
 
-static struct lib80211_crypto_ops rtllib_crypt_wep = {
+static const struct lib80211_crypto_ops rtllib_crypt_wep = {
 	.name			= "R-WEP",
 	.init			= prism2_wep_init,
 	.deinit			= prism2_wep_deinit,
-- 
cgit v1.3-3-g829e


From 7c3b69eadea9e57c28bf914b0fd70f268f3682e1 Mon Sep 17 00:00:00 2001
From: Rory Little <rory@candelatech.com>
Date: Mon, 5 Aug 2024 17:40:23 -0700
Subject: wifi: mac80211: Add non-atomic station iterator

Drivers may at times want to iterate their stations with a function
which requires some non-atomic operations.

ieee80211_iterate_stations_mtx() introduces an API to iterate stations
while holding that wiphy's mutex. This allows the iterating function to
do non-atomic operations safely.

Signed-off-by: Rory Little <rory@candelatech.com>
Link: https://patch.msgid.link/20240806004024.2014080-2-rory@candelatech.com
[unify internal list iteration functions]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 18 ++++++++++++++++++
 net/mac80211/util.c    | 16 +++++++++++++++-
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index de50dc8712c0..cfd64acdc039 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6243,6 +6243,24 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw,
 				       void (*iterator)(void *data,
 						struct ieee80211_sta *sta),
 				       void *data);
+
+/**
+ * ieee80211_iterate_stations_mtx - iterate stations
+ *
+ * This function iterates over all stations associated with a given
+ * hardware that are currently uploaded to the driver and calls the callback
+ * function for them. This version can only be used while holding the wiphy
+ * mutex.
+ *
+ * @hw: the hardware struct of which the interfaces should be iterated over
+ * @iterator: the iterator function to call
+ * @data: first argument of the iterator function
+ */
+void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw,
+				    void (*iterator)(void *data,
+						     struct ieee80211_sta *sta),
+				    void *data);
+
 /**
  * ieee80211_queue_work - add work onto the mac80211 workqueue
  *
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ced19ce7c51a..830f736f9c13 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -833,7 +833,8 @@ static void __iterate_stations(struct ieee80211_local *local,
 {
 	struct sta_info *sta;
 
-	list_for_each_entry_rcu(sta, &local->sta_list, list) {
+	list_for_each_entry_rcu(sta, &local->sta_list, list,
+				lockdep_is_held(&local->hw.wiphy->mtx)) {
 		if (!sta->uploaded)
 			continue;
 
@@ -854,6 +855,19 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw,
 }
 EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_atomic);
 
+void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw,
+				    void (*iterator)(void *data,
+						     struct ieee80211_sta *sta),
+				    void *data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+
+	lockdep_assert_wiphy(local->hw.wiphy);
+
+	__iterate_stations(local, iterator, data);
+}
+EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_mtx);
+
 struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
-- 
cgit v1.3-3-g829e


From a68b22e2905b04f376e2fa116be5e48b948f81c8 Mon Sep 17 00:00:00 2001
From: hhorace <hhoracehsu@gmail.com>
Date: Wed, 7 Aug 2024 16:22:05 +0800
Subject: wifi: cfg80211: fix bug of mapping AF3x to incorrect User Priority

According to RFC8325 4.3, Multimedia Streaming: AF31(011010, 26),
AF32(011100, 28), AF33(011110, 30) maps to User Priority = 4
and AC_VI (Video).

However, the original code remain the default three Most Significant
Bits (MSBs) of the DSCP, which makes AF3x map to User Priority = 3
and AC_BE (Best Effort).

Fixes: 6fdb8b8781d5 ("wifi: cfg80211: Update the default DSCP-to-UP mapping")
Signed-off-by: hhorace <hhoracehsu@gmail.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20240807082205.1369-1-hhoracehsu@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/util.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index 9a7c3adc8a3b..edeeb056fe4d 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -998,10 +998,10 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
 	 * Diffserv Service Classes no update is needed:
 	 * - Standard: DF
 	 * - Low Priority Data: CS1
-	 * - Multimedia Streaming: AF31, AF32, AF33
 	 * - Multimedia Conferencing: AF41, AF42, AF43
 	 * - Network Control Traffic: CS7
 	 * - Real-Time Interactive: CS4
+	 * - Signaling: CS5
 	 */
 	switch (dscp >> 2) {
 	case 10:
@@ -1026,9 +1026,11 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
 		/* Broadcasting video: CS3 */
 		ret = 4;
 		break;
-	case 40:
-		/* Signaling: CS5 */
-		ret = 5;
+	case 26:
+	case 28:
+	case 30:
+		/* Multimedia Streaming: AF31, AF32, AF33 */
+		ret = 4;
 		break;
 	case 44:
 		/* Voice Admit: VA */
-- 
cgit v1.3-3-g829e


From 1524173a3745899612c71d9e83ff8fe29dbb2cfb Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 8 Aug 2024 11:59:16 +0300
Subject: wifi: mac80211: fix the comeback long retry times

When we had a comeback, we will never use the default timeout values
again because comeback is never cleared.
Clear comeback if we send another association request which will allow
to start a default timer after Tx status.

The problem was seen with iwlwifi where the tx_status on the association
request is handled before the association response frame (which is the
usual case).

1) Tx assoc request 1/3
2) Rx assoc response (comeback, timeout = 1 second)
3) wait 1 second
4) Tx assoc request 2/3
5) Set timer to IEEE80211_ASSOC_TIMEOUT_LONG = 500ms (1 second after
   round_up)
6) tx_status on frame sent in 4) is ignored because comeback is still
   true
7) AP does not reply with assoc response
8) wait 1s <= This is where the bug is felt
9) Tx assoc request 3/3

With this fix, in step 6 we will reset the timer to
IEEE80211_ASSOC_TIMEOUT_SHORT = 100ms and we will wait only 100ms in
step 8.

Fixes: b133fdf07db8 ("wifi: mac80211: Skip association timeout update after comeback rejection")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240808085916.23519-1-emmanuel.grumbach@intel.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4779a18ab75d..0285924269cf 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7660,6 +7660,7 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata)
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
 	assoc_data->tries++;
+	assoc_data->comeback = false;
 	if (assoc_data->tries > IEEE80211_ASSOC_MAX_TRIES) {
 		sdata_info(sdata, "association with %pM timed out\n",
 			   assoc_data->ap_addr);
-- 
cgit v1.3-3-g829e


From b2a7c91bf93865a34e04707ef600c1c363d79125 Mon Sep 17 00:00:00 2001
From: Daniel Gabay <daniel.gabay@intel.com>
Date: Thu, 8 Aug 2024 23:22:37 +0300
Subject: wifi: iwlwifi: mvm: Offload RLC/SMPS functionality to firmware

Currently, the driver handles SMPS decisions by tracking AP
capabilities, BT coexistence changes, sending necessary SMPS
frames to the AP, and updating firmware with RX chain info
using the RLC_CONFIG_CMD.

Starting with version 3 of the RLC_CONFIG_CMD, the firmware
takes over this responsibility. It now tracks SMPS, sends
frames, and configures the RLC.

In this patch:
1. Stop sending RLC_CONFIG_CMD when firmware supports RLC
   offload (version 3), as rlc.rx_chain_info is not needed by
   firmware, and no other field in the cmd is used.
2. Prevent the driver from forwarding any SMPS requests to
   mac80211, i.e., the driver should not transmit SMPS frames
   to the AP as firmware handles that.
3. Set NL80211_FEATURE_DYNAMIC_SMPS and NL80211_FEATURE_STATIC_SMPS
   conditionally based on RLC version.

Signed-off-by: Daniel Gabay <daniel.gabay@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.45da23be1f65.I0d46db82dd990a82e8a66876fe2f5310bc9513be@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 9 +++++++--
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      | 7 +++++++
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c      | 6 ++++++
 drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c | 6 +++++-
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c    | 4 ++++
 5 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index d6f4caa939bd..af892c8291d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -635,10 +635,15 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 			       NL80211_FEATURE_LOW_PRIORITY_SCAN |
 			       NL80211_FEATURE_P2P_GO_OPPPS |
 			       NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
-			       NL80211_FEATURE_DYNAMIC_SMPS |
-			       NL80211_FEATURE_STATIC_SMPS |
 			       NL80211_FEATURE_SUPPORTS_WMM_ADMISSION;
 
+	/* when firmware supports RLC/SMPS offload, do not set these
+	 * driver features, since it's no longer supported by driver.
+	 */
+	if (!iwl_mvm_has_rlc_offload(mvm))
+		hw->wiphy->features |= NL80211_FEATURE_STATIC_SMPS |
+				       NL80211_FEATURE_DYNAMIC_SMPS;
+
 	if (fw_has_capa(&mvm->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_TXPOWER_INSERTION_SUPPORT))
 		hw->wiphy->features |= NL80211_FEATURE_TX_POWER_INSERTION;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index bd754b8a71fc..4cacaa7b398e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1768,6 +1768,13 @@ static inline u8 iwl_mvm_mac_ac_to_tx_fifo(struct iwl_mvm *mvm,
 	return iwl_mvm_ac_to_tx_fifo[ac];
 }
 
+static inline bool iwl_mvm_has_rlc_offload(struct iwl_mvm *mvm)
+{
+	return iwl_fw_lookup_cmd_ver(mvm->fw,
+				     WIDE_ID(DATA_PATH_GROUP, RLC_CONFIG_CMD),
+				     0) >= 3;
+}
+
 struct iwl_rate_info {
 	u8 plcp;	/* uCode API:  IWL_RATE_6M_PLCP, etc. */
 	u8 plcp_siso;	/* uCode API:  IWL_RATE_SISO_6M_PLCP, etc. */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 8896d9792feb..be20c8e3a389 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -261,6 +261,12 @@ static void iwl_mvm_rx_thermal_dual_chain_req(struct iwl_mvm *mvm,
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_thermal_dual_chain_request *req = (void *)pkt->data;
 
+	/* firmware is expected to handle that in RLC offload mode */
+	if (IWL_FW_CHECK(mvm, iwl_mvm_has_rlc_offload(mvm),
+			 "Got THERMAL_DUAL_CHAIN_REQUEST (0x%x) in RLC offload mode\n",
+			 req->event))
+		return;
+
 	/*
 	 * We could pass it to the iterator data, but also need to remember
 	 * it for new interfaces that are added while in this state.
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
index ce264b386029..7cab5373c8ae 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c
@@ -159,7 +159,11 @@ int iwl_mvm_phy_send_rlc(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 		.phy_id = cpu_to_le32(ctxt->id),
 	};
 
-	if (ctxt->rlc_disabled)
+	/* From version 3, RLC is offloaded to firmware, so the driver no
+	 * longer needs to send cmd.rlc, note that we are not using any
+	 * other fields in the command - don't send it.
+	 */
+	if (iwl_mvm_has_rlc_offload(mvm) || ctxt->rlc_disabled)
 		return 0;
 
 	if (iwl_fw_lookup_cmd_ver(mvm->fw, WIDE_ID(DATA_PATH_GROUP,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 0e5fa8374103..edcc6e2cb76a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -297,6 +297,10 @@ void iwl_mvm_update_smps(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (vif->type != NL80211_IFTYPE_STATION)
 		return;
 
+	/* SMPS is handled by firmware */
+	if (iwl_mvm_has_rlc_offload(mvm))
+		return;
+
 	mvmvif = iwl_mvm_vif_from_mac80211(vif);
 
 	if (WARN_ON_ONCE(!mvmvif->link[link_id]))
-- 
cgit v1.3-3-g829e


From 658b8b56c1296322a9a064c8e8cb73ea8a44f635 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 8 Aug 2024 23:22:38 +0300
Subject: wifi: iwlwifi: mvm: rename iwl_missed_beacons_notif

A new version is coming up. Rename the current struct to include the
current version.

s/iwl_missed_beacons_notif/iwl_missed_beacons_notif_v4

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.b5c3a83a05ef.I698611582b5ca8395f42a535c51f7230307e2c6f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/commands.h | 2 +-
 drivers/net/wireless/intel/iwlwifi/fw/api/mac.h      | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c    | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c         | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 377fac278511..852ea5d14051 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -401,7 +401,7 @@ enum iwl_legacy_cmds {
 	REDUCE_TX_POWER_CMD = 0x9f,
 
 	/**
-	 * @MISSED_BEACONS_NOTIFICATION: &struct iwl_missed_beacons_notif
+	 * @MISSED_BEACONS_NOTIFICATION: &struct iwl_missed_beacons_notif_v4
 	 */
 	MISSED_BEACONS_NOTIFICATION = 0xa2,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index bcbbf8c4a297..490215e71e5d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -378,7 +378,7 @@ struct iwl_missed_beacons_notif_ver_3 {
 } __packed; /* MISSED_BEACON_NTFY_API_S_VER_3 */
 
 /**
- * struct iwl_missed_beacons_notif - information on missed beacons
+ * struct iwl_missed_beacons_notif_v4 - information on missed beacons
  * ( MISSED_BEACONS_NOTIFICATION = 0xa2 )
  * @link_id: fw link ID
  * @consec_missed_beacons_since_last_rx: number of consecutive missed
@@ -387,7 +387,7 @@ struct iwl_missed_beacons_notif_ver_3 {
  * @num_expected_beacons: number of expected beacons
  * @num_recvd_beacons: number of received beacons
  */
-struct iwl_missed_beacons_notif {
+struct iwl_missed_beacons_notif_v4 {
 	__le32 link_id;
 	__le32 consec_missed_beacons_since_last_rx;
 	__le32 consec_missed_beacons;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index dfcc96f18b4f..9209814b465c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1590,7 +1590,7 @@ void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
 				     struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_missed_beacons_notif *mb = (void *)pkt->data;
+	struct iwl_missed_beacons_notif_v4 *mb = (void *)pkt->data;
 	struct iwl_fw_dbg_trigger_missed_bcon *bcon_trig;
 	struct iwl_fw_dbg_trigger_tlv *trigger;
 	u32 stop_trig_missed_bcon, stop_trig_missed_bcon_since_rx;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index be20c8e3a389..dd2631ff452d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -396,7 +396,7 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 
 	RX_HANDLER(MISSED_BEACONS_NOTIFICATION, iwl_mvm_rx_missed_beacons_notif,
 		   RX_HANDLER_ASYNC_LOCKED_WIPHY,
-		   struct iwl_missed_beacons_notif),
+		   struct iwl_missed_beacons_notif_v4),
 
 	RX_HANDLER(REPLY_ERROR, iwl_mvm_rx_fw_error, RX_HANDLER_SYNC,
 		   struct iwl_error_resp),
-- 
cgit v1.3-3-g829e


From ec6ba5367eaab4d81b14f19380b14852a49dd80a Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 8 Aug 2024 23:22:39 +0300
Subject: wifi: iwlwifi: mvm: add the new API for the missed beacons
 notification

Note that the new API does not have the same notification ID as the
previous notification: the new notification belongs to the group 0x3.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.4ea52360b32e.Ibc25dcabd8aeadda906549482a6c77bc42fb55bb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/mac-cfg.h    | 25 ++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 56b880e68870..5fc7967df6c5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -61,6 +61,10 @@ enum iwl_mac_conf_subcmd_ids {
 	 * @ROC_CMD: &struct iwl_roc_req
 	 */
 	ROC_CMD = 0xE,
+	/**
+	 * @MISSED_BEACONS_NOTIF: &struct iwl_missed_beacons_notif
+	 */
+	MISSED_BEACONS_NOTIF = 0xF6,
 	/**
 	 * @ROC_NOTIF: &struct iwl_roc_notif
 	 */
@@ -665,4 +669,25 @@ struct iwl_mvm_esr_mode_notif {
 	__le32 action;
 } __packed; /* ESR_MODE_RECOMMENDATION_NTFY_API_S_VER_1 */
 
+/**
+ * struct iwl_missed_beacons_notif - sent when by the firmware upon beacon loss
+ *  ( MISSED_BEACONS_NOTIF = 0xF6 )
+ * @link_id: fw link ID
+ * @consec_missed_beacons_since_last_rx: number of consecutive missed
+ *	beacons since last RX.
+ * @consec_missed_beacons: number of consecutive missed beacons
+ * @other_link_id: used in EMLSR only. The fw link ID for
+ *	&consec_missed_beacons_other_link. IWL_MVM_FW_LINK_ID_INVALID (0xff) if
+ *	invalid.
+ * @consec_missed_beacons_other_link: number of consecutive missed beacons on
+ *	&other_link_id.
+ */
+struct iwl_missed_beacons_notif {
+	__le32 link_id;
+	__le32 consec_missed_beacons_since_last_rx;
+	__le32 consec_missed_beacons;
+	__le32 other_link_id;
+	__le32 consec_missed_beacons_other_link;
+} __packed; /* MISSED_BEACON_NTFY_API_S_VER_5 */
+
 #endif /* __iwl_fw_api_mac_cfg_h__ */
-- 
cgit v1.3-3-g829e


From 313e32f60d5439a19b0684d3be1fe50c77ef382d Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 8 Aug 2024 23:22:40 +0300
Subject: wifi: iwlwifi: mvm: handle the new missed beacons notification

Use the same handler for both types and just convert the old version to
the new. Drop the unused fields from the old one and fake the new
fields.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.a64ffc998569.I7d181052b1a69c331d07263f20c1e00cbc0bc891@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 49 +++++++++++++++++++----
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      |  2 +
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c      |  7 +++-
 3 files changed, 49 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 9209814b465c..4a8f50f8bb79 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1586,11 +1586,11 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
 	}
 }
 
-void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
-				     struct iwl_rx_cmd_buffer *rxb)
+static void
+iwl_mvm_handle_missed_beacons_notif(struct iwl_mvm *mvm,
+				    const struct iwl_missed_beacons_notif *mb,
+				    struct iwl_rx_packet *pkt)
 {
-	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_missed_beacons_notif_v4 *mb = (void *)pkt->data;
 	struct iwl_fw_dbg_trigger_missed_bcon *bcon_trig;
 	struct iwl_fw_dbg_trigger_tlv *trigger;
 	u32 stop_trig_missed_bcon, stop_trig_missed_bcon_since_rx;
@@ -1604,6 +1604,16 @@ void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
 	u8 notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP,
 					       MISSED_BEACONS_NOTIFICATION,
 					       0);
+	u8 new_notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, MAC_CONF_GROUP,
+						   MISSED_BEACONS_NOTIF, 0);
+
+	/* If the firmware uses the new notification (from MAC_CONF_GROUP),
+	 * refer to that notification's version.
+	 * Note that the new notification from MAC_CONF_GROUP starts from
+	 * version 5.
+	 */
+	if (new_notif_ver)
+		notif_ver = new_notif_ver;
 
 	/* before version four the ID in the notification refers to mac ID */
 	if (notif_ver < 4) {
@@ -1620,13 +1630,11 @@ void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
 	}
 
 	IWL_DEBUG_INFO(mvm,
-		       "missed bcn %s_id=%u, consecutive=%u (%u, %u, %u)\n",
+		       "missed bcn %s_id=%u, consecutive=%u (%u)\n",
 		       notif_ver < 4 ? "mac" : "link",
 		       id,
 		       le32_to_cpu(mb->consec_missed_beacons),
-		       le32_to_cpu(mb->consec_missed_beacons_since_last_rx),
-		       le32_to_cpu(mb->num_recvd_beacons),
-		       le32_to_cpu(mb->num_expected_beacons));
+		       le32_to_cpu(mb->consec_missed_beacons_since_last_rx));
 
 	if (!vif)
 		return;
@@ -1687,6 +1695,31 @@ void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
 		iwl_fw_dbg_collect_trig(&mvm->fwrt, trigger, NULL);
 }
 
+void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
+				     struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+
+	iwl_mvm_handle_missed_beacons_notif(mvm, (const void *)pkt->data, pkt);
+}
+
+void iwl_mvm_rx_missed_beacons_notif_legacy(struct iwl_mvm *mvm,
+					    struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	const struct iwl_missed_beacons_notif_v4 *mb_v4 =
+		(const void *)pkt->data;
+	struct iwl_missed_beacons_notif mb = {
+		.link_id = mb_v4->link_id,
+		.consec_missed_beacons = mb_v4->consec_missed_beacons,
+		.consec_missed_beacons_since_last_rx =
+			mb_v4->consec_missed_beacons_since_last_rx,
+		.other_link_id = cpu_to_le32(IWL_MVM_FW_LINK_ID_INVALID),
+	};
+
+	iwl_mvm_handle_missed_beacons_notif(mvm, &mb, pkt);
+}
+
 void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm,
 				    struct iwl_rx_cmd_buffer *rxb)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 4cacaa7b398e..f9e676374daa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2073,6 +2073,8 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
 			     struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm,
 				     struct iwl_rx_cmd_buffer *rxb);
+void iwl_mvm_rx_missed_beacons_notif_legacy(struct iwl_mvm *mvm,
+					    struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm,
 				    struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_mu_mimo_grp_notif(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index dd2631ff452d..0b91877592a8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -394,10 +394,15 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 		   iwl_mvm_rx_umac_scan_iter_complete_notif, RX_HANDLER_SYNC,
 		   struct iwl_umac_scan_iter_complete_notif),
 
-	RX_HANDLER(MISSED_BEACONS_NOTIFICATION, iwl_mvm_rx_missed_beacons_notif,
+	RX_HANDLER(MISSED_BEACONS_NOTIFICATION,
+		   iwl_mvm_rx_missed_beacons_notif_legacy,
 		   RX_HANDLER_ASYNC_LOCKED_WIPHY,
 		   struct iwl_missed_beacons_notif_v4),
 
+	RX_HANDLER_GRP(MAC_CONF_GROUP, MISSED_BEACONS_NOTIF,
+		       iwl_mvm_rx_missed_beacons_notif,
+		       RX_HANDLER_ASYNC_LOCKED_WIPHY,
+		       struct iwl_missed_beacons_notif),
 	RX_HANDLER(REPLY_ERROR, iwl_mvm_rx_fw_error, RX_HANDLER_SYNC,
 		   struct iwl_error_resp),
 	RX_HANDLER(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION,
-- 
cgit v1.3-3-g829e


From cdade208214af34b18635747cb18d3693593c0c2 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 8 Aug 2024 23:22:41 +0300
Subject: wifi: iwlwifi: mvm: exit EMLSR if both links are missing beacons

If both links are missing 5 beacons, we need to exit EMLSR, if only one
link misses beacons, we need to wait until 11 beacons are missed.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.b7785943a4fe.I70a459c5e7db85f398d5795ba83bb15f65d6bf9d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/constants.h |  3 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c  | 25 ++++++++++++++++++----
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
index 8f63cbe9e50d..ddf484027d4f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
@@ -16,6 +16,8 @@
 #define IWL_MVM_BT_COEX_WIFI_LOSS_THRESH	0
 #define IWL_MVM_TRIGGER_LINK_SEL_TIME_SEC	30
 #define IWL_MVM_TPT_COUNT_WINDOW_SEC		5
+#define IWL_MVM_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS	5
+#define IWL_MVM_BCN_LOSS_EXIT_ESR_THRESH	11
 
 #define IWL_MVM_DEFAULT_PS_TX_DATA_TIMEOUT	(100 * USEC_PER_MSEC)
 #define IWL_MVM_DEFAULT_PS_RX_DATA_TIMEOUT	(100 * USEC_PER_MSEC)
@@ -125,7 +127,6 @@
 #define IWL_MVM_6GHZ_PASSIVE_SCAN_ASSOC_TIMEOUT 60   /* in seconds */
 #define IWL_MVM_MIN_BEACON_INTERVAL_TU		16
 #define IWL_MVM_AUTO_EML_ENABLE                 true
-#define IWL_MVM_MISSED_BEACONS_EXIT_ESR_THRESH	7
 
 #define IWL_MVM_HIGH_RSSI_THRESH_20MHZ		-67
 #define IWL_MVM_LOW_RSSI_THRESH_20MHZ		-71
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 4a8f50f8bb79..bb864ec2e22a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1664,10 +1664,27 @@ iwl_mvm_handle_missed_beacons_notif(struct iwl_mvm *mvm,
 				 "missed_beacons:%d, missed_beacons_since_rx:%d\n",
 				 rx_missed_bcon, rx_missed_bcon_since_rx);
 		}
-	} else if (rx_missed_bcon >= IWL_MVM_MISSED_BEACONS_EXIT_ESR_THRESH &&
-		   link_id >= 0 && hweight16(vif->active_links) > 1) {
-		iwl_mvm_exit_esr(mvm, vif, IWL_MVM_ESR_EXIT_MISSED_BEACON,
-				 iwl_mvm_get_other_link(vif, link_id));
+	} else if (link_id >= 0 && hweight16(vif->active_links) > 1) {
+		u32 scnd_lnk_bcn_lost = 0;
+
+		if (notif_ver >= 5 &&
+		    !IWL_FW_CHECK(mvm,
+				  le32_to_cpu(mb->other_link_id) == IWL_MVM_FW_LINK_ID_INVALID,
+				  "No data for other link id but we are in EMLSR active_links: 0x%x\n",
+				  vif->active_links))
+			scnd_lnk_bcn_lost =
+				le32_to_cpu(mb->consec_missed_beacons_other_link);
+
+		/* Exit EMLSR if we lost more than
+		 * IWL_MVM_MISSED_BEACONS_EXIT_ESR_THRESH beacons on boths links
+		 * OR more than IWL_MVM_BCN_LOSS_EXIT_ESR_THRESH on any link.
+		 */
+		if ((rx_missed_bcon >= IWL_MVM_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS &&
+		     scnd_lnk_bcn_lost >= IWL_MVM_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS) ||
+		    rx_missed_bcon >= IWL_MVM_BCN_LOSS_EXIT_ESR_THRESH)
+			iwl_mvm_exit_esr(mvm, vif,
+					 IWL_MVM_ESR_EXIT_MISSED_BEACON,
+					 iwl_mvm_get_primary_link(vif));
 	} else if (rx_missed_bcon_since_rx > IWL_MVM_MISSED_BEACONS_THRESHOLD) {
 		if (!iwl_mvm_has_new_tx_api(mvm))
 			ieee80211_beacon_loss(vif);
-- 
cgit v1.3-3-g829e


From 4d8ff1f7df43ee8560818b0b6cdec6e9ce703748 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 8 Aug 2024 23:22:42 +0300
Subject: wifi: iwlwifi: mvm: add API for EML OMN frame failure

When the firmware fails to send EML OMN frames, it notifies the host and
the host need to take proper action.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.0c6bc216ef8c.Ida85d2062734a569e1af35f47d14cc5bb4bf893e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/mac-cfg.h    | 30 ++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 5fc7967df6c5..6a2c5bed357e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -65,6 +65,10 @@ enum iwl_mac_conf_subcmd_ids {
 	 * @MISSED_BEACONS_NOTIF: &struct iwl_missed_beacons_notif
 	 */
 	MISSED_BEACONS_NOTIF = 0xF6,
+	/**
+	 * @EMLSR_TRANS_FAIL_NOTIF: &struct iwl_esr_trans_fail_notif
+	 */
+	EMLSR_TRANS_FAIL_NOTIF = 0xF7,
 	/**
 	 * @ROC_NOTIF: &struct iwl_roc_notif
 	 */
@@ -690,4 +694,30 @@ struct iwl_missed_beacons_notif {
 	__le32 consec_missed_beacons_other_link;
 } __packed; /* MISSED_BEACON_NTFY_API_S_VER_5 */
 
+/*
+ * enum iwl_esr_trans_fail_code: to be used to parse the notif below
+ *
+ * @ESR_TRANS_FAILED_TX_STATUS_ERROR: failed to TX EML OMN frame
+ * @ESR_TRANSITION_FAILED_TX_TIMEOUT: timeout on the EML OMN frame
+ * @ESR_TRANSITION_FAILED_BEACONS_NOT_HEARD: can't get a beacon on the new link
+ */
+enum iwl_esr_trans_fail_code {
+	ESR_TRANS_FAILED_TX_STATUS_ERROR,
+	ESR_TRANSITION_FAILED_TX_TIMEOUT,
+	ESR_TRANSITION_FAILED_BEACONS_NOT_HEARD,
+};
+
+/**
+ * struct iwl_esr_trans_fail_notif - FW reports a failure in EMLSR transition
+ *
+ * @link_id: the link_id that was activated / de-activated
+ * @activation: true if the link was activated, false otherwise
+ * @err_code: see &enum iwl_esr_trans_fail_code
+ */
+struct iwl_esr_trans_fail_notif {
+	__le32 link_id;
+	__le32 activation;
+	__le32 err_code;
+} __packed; /* ESR_TRANSITION_FAILED_NTFY_API_S_VER_1 */
+
 #endif /* __iwl_fw_api_mac_cfg_h__ */
-- 
cgit v1.3-3-g829e


From 1987bf29f891d30c7d85d7da179a67628c3fe8e6 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Thu, 8 Aug 2024 23:22:44 +0300
Subject: wifi: iwlwifi: mvm: Stop processing MCC update if there was no change

When processing a MCC update notification from the firmware, if
the firmware indicates that the regulatory configuration didn't
change, abort the flow and do not notify higher layers.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.60dd273d00e0.I985b3bc61ca4a6cac7c1d1365b5c0afba04f3031@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/nvm.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
index 836ca22597bc..80ec59c58ae4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c
@@ -611,6 +611,7 @@ void iwl_mvm_rx_chub_update_mcc(struct iwl_mvm *mvm,
 	char mcc[3];
 	struct ieee80211_regdomain *regd;
 	int wgds_tbl_idx;
+	bool changed = false;
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -630,10 +631,15 @@ void iwl_mvm_rx_chub_update_mcc(struct iwl_mvm *mvm,
 	IWL_DEBUG_LAR(mvm,
 		      "RX: received chub update mcc cmd (mcc '%s' src %d)\n",
 		      mcc, src);
-	regd = iwl_mvm_get_regdomain(mvm->hw->wiphy, mcc, src, NULL);
+	regd = iwl_mvm_get_regdomain(mvm->hw->wiphy, mcc, src, &changed);
 	if (IS_ERR_OR_NULL(regd))
 		return;
 
+	if (!changed) {
+		IWL_DEBUG_LAR(mvm, "RX: No change in the regulatory data\n");
+		goto out;
+	}
+
 	wgds_tbl_idx = iwl_mvm_get_sar_geo_profile(mvm);
 	if (wgds_tbl_idx < 1)
 		IWL_DEBUG_INFO(mvm,
@@ -644,5 +650,7 @@ void iwl_mvm_rx_chub_update_mcc(struct iwl_mvm *mvm,
 			       wgds_tbl_idx);
 
 	regulatory_set_wiphy_regd(mvm->hw->wiphy, regd);
+
+out:
 	kfree(regd);
 }
-- 
cgit v1.3-3-g829e


From a08cf01905dfd7884d41db782667420500bdd90e Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 25 Aug 2024 09:00:54 +0300
Subject: wifi: iwlwifi: mvm: handle the new EML OMN failure notification

Take the proper action upon EML OMN frame failure.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240825090005.01ff45fa69db.I9f2d3ea851050f6031ac07bbe69eb38000fd5683@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/mac-cfg.h    |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/link.c      |  3 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |  2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       | 42 ++++++++++++++++++++++
 4 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 6a2c5bed357e..7af580d1c99c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -710,7 +710,7 @@ enum iwl_esr_trans_fail_code {
 /**
  * struct iwl_esr_trans_fail_notif - FW reports a failure in EMLSR transition
  *
- * @link_id: the link_id that was activated / de-activated
+ * @link_id: the link_id that still works after the failure
  * @activation: true if the link was activated, false otherwise
  * @err_code: see &enum iwl_esr_trans_fail_code
  */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index 3a6e0a90a3ef..d151d935e12a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -17,7 +17,8 @@
 	HOW(EXIT_COEX)			\
 	HOW(EXIT_BANDWIDTH)		\
 	HOW(EXIT_CSA)			\
-	HOW(EXIT_LINK_USAGE)
+	HOW(EXIT_LINK_USAGE)		\
+	HOW(EXIT_FAIL_ENTRY)
 
 static const char *const iwl_mvm_esr_states_names[] = {
 #define NAME_ENTRY(x) [ilog2(IWL_MVM_ESR_##x)] = #x,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index f9e676374daa..65b66f01bef9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -368,6 +368,7 @@ struct iwl_mvm_vif_link_info {
  *	preventing the enablement of EMLSR
  * @IWL_MVM_ESR_EXIT_CSA: CSA happened, so exit EMLSR
  * @IWL_MVM_ESR_EXIT_LINK_USAGE: Exit EMLSR due to low tpt on secondary link
+ * @IWL_MVM_ESR_EXIT_FAIL_ENTRY: Exit EMLSR due to entry failure
  */
 enum iwl_mvm_esr_state {
 	IWL_MVM_ESR_BLOCKED_PREVENTION	= 0x1,
@@ -382,6 +383,7 @@ enum iwl_mvm_esr_state {
 	IWL_MVM_ESR_EXIT_BANDWIDTH	= 0x80000,
 	IWL_MVM_ESR_EXIT_CSA		= 0x100000,
 	IWL_MVM_ESR_EXIT_LINK_USAGE	= 0x200000,
+	IWL_MVM_ESR_EXIT_FAIL_ENTRY	= 0x400000,
 };
 
 #define IWL_MVM_BLOCK_ESR_REASONS 0xffff
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 0b91877592a8..f207ac46b8ec 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -159,6 +159,43 @@ static void iwl_mvm_rx_esr_mode_notif(struct iwl_mvm *mvm,
 				  iwl_mvm_get_primary_link(vif));
 }
 
+static void iwl_mvm_rx_esr_trans_fail_notif(struct iwl_mvm *mvm,
+					    struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_esr_trans_fail_notif *notif = (void *)pkt->data;
+	struct ieee80211_vif *vif = iwl_mvm_get_bss_vif(mvm);
+	u8 fw_link_id = le32_to_cpu(notif->link_id);
+	struct ieee80211_bss_conf *bss_conf;
+
+	if (IS_ERR_OR_NULL(vif))
+		return;
+
+	IWL_DEBUG_INFO(mvm, "Failed to %s eSR on link %d, reason %d\n",
+		       le32_to_cpu(notif->activation) ? "enter" : "exit",
+		       le32_to_cpu(notif->link_id),
+		       le32_to_cpu(notif->err_code));
+
+	/* we couldn't go back to single link, disconnect */
+	if (!le32_to_cpu(notif->activation)) {
+		iwl_mvm_connection_loss(mvm, vif, "emlsr exit failed");
+		return;
+	}
+
+	bss_conf = iwl_mvm_rcu_fw_link_id_to_link_conf(mvm, fw_link_id, false);
+	if (IWL_FW_CHECK(mvm, !bss_conf,
+			 "FW reported failure to activate EMLSR on a non-existing link: %d\n",
+			 fw_link_id))
+		return;
+
+	/*
+	 * We failed to activate the second link and enter EMLSR, we need to go
+	 * back to single link.
+	 */
+	iwl_mvm_exit_esr(mvm, vif, IWL_MVM_ESR_EXIT_FAIL_ENTRY,
+			 bss_conf->link_id);
+}
+
 static void iwl_mvm_rx_monitor_notif(struct iwl_mvm *mvm,
 				     struct iwl_rx_cmd_buffer *rxb)
 {
@@ -486,6 +523,10 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 	RX_HANDLER_GRP(SCAN_GROUP, CHANNEL_SURVEY_NOTIF,
 		       iwl_mvm_rx_channel_survey_notif, RX_HANDLER_ASYNC_LOCKED,
 		       struct iwl_umac_scan_channel_survey_notif),
+	RX_HANDLER_GRP(MAC_CONF_GROUP, EMLSR_TRANS_FAIL_NOTIF,
+		       iwl_mvm_rx_esr_trans_fail_notif,
+		       RX_HANDLER_ASYNC_LOCKED_WIPHY,
+		       struct iwl_esr_trans_fail_notif),
 };
 #undef RX_HANDLER
 #undef RX_HANDLER_GRP
@@ -616,6 +657,7 @@ static const struct iwl_hcmd_names iwl_mvm_mac_conf_names[] = {
 	HCMD_NAME(STA_REMOVE_CMD),
 	HCMD_NAME(STA_DISABLE_TX_CMD),
 	HCMD_NAME(ROC_CMD),
+	HCMD_NAME(EMLSR_TRANS_FAIL_NOTIF),
 	HCMD_NAME(ROC_NOTIF),
 	HCMD_NAME(CHANNEL_SWITCH_ERROR_NOTIF),
 	HCMD_NAME(MISSED_VAP_NOTIF),
-- 
cgit v1.3-3-g829e


From 7921c411490ca8b091068a41de873d79d065aab1 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 8 Aug 2024 23:22:45 +0300
Subject: wifi: iwlwifi: use default command queue watchdog timeout

We used to have the opmode configuring it to the trans according to the
debug tlv value (FW_DBG_TRIGGER_TXQ_TIMERS).
But this debug is not used, so trans can just have the default value
hardcoded.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.87af3f063025.I2222981ead13f6a917f2d4b116c5b94200dc9e51@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c   | 2 --
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h  | 2 --
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c    | 4 ----
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 4 +++-
 4 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index 65b7c68e5ca7..e0b14be25b02 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1325,8 +1325,6 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 		       iwlwifi_mod_params.amsdu_size);
 	}
 
-	trans_cfg.cmd_q_wdg_timeout = IWL_WATCHDOG_DISABLED;
-
 	trans_cfg.command_groups = iwl_dvm_groups;
 	trans_cfg.command_groups_size = ARRAY_SIZE(iwl_dvm_groups);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 6148acbac6af..c6f51e3bc3c6 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -386,7 +386,6 @@ struct iwl_dump_sanitize_ops {
  * @cmd_queue: the index of the command queue.
  *	Must be set before start_fw.
  * @cmd_fifo: the fifo for host commands
- * @cmd_q_wdg_timeout: the timeout of the watchdog timer for the command queue.
  * @no_reclaim_cmds: Some devices erroneously don't set the
  *	SEQ_RX_FRAME bit on some notifications, this is the
  *	list of such notifications to filter. Max length is
@@ -412,7 +411,6 @@ struct iwl_trans_config {
 
 	u8 cmd_queue;
 	u8 cmd_fifo;
-	unsigned int cmd_q_wdg_timeout;
 	const u8 *no_reclaim_cmds;
 	unsigned int n_no_reclaim_cmds;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index f207ac46b8ec..273767b074b8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1449,10 +1449,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	trans_cfg.cb_data_offs = offsetof(struct ieee80211_tx_info,
 					  driver_data[2]);
 
-	/* Set a short watchdog for the command queue */
-	trans_cfg.cmd_q_wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, NULL, false, true);
-
 	snprintf(mvm->hw->wiphy->fw_version,
 		 sizeof(mvm->hw->wiphy->fw_version),
 		 "%.31s", fw->fw_version);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 719ddc4b72c5..3b9943eb6934 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1967,7 +1967,6 @@ void iwl_trans_pcie_configure(struct iwl_trans *trans,
 
 	trans_pcie->txqs.cmd.q_id = trans_cfg->cmd_queue;
 	trans_pcie->txqs.cmd.fifo = trans_cfg->cmd_fifo;
-	trans_pcie->txqs.cmd.wdg_timeout = trans_cfg->cmd_q_wdg_timeout;
 	trans_pcie->txqs.page_offs = trans_cfg->cb_data_offs;
 	trans_pcie->txqs.dev_cmd_offs = trans_cfg->cb_data_offs + sizeof(void *);
 	trans_pcie->txqs.queue_alloc_cmd_ver = trans_cfg->queue_alloc_cmd_ver;
@@ -3567,6 +3566,9 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	}
 	trans->max_skb_frags = IWL_TRANS_PCIE_MAX_FRAGS(trans_pcie);
 
+	/* Set a short watchdog for the command queue */
+	trans_pcie->txqs.cmd.wdg_timeout = IWL_DEF_WD_TIMEOUT;
+
 	trans_pcie->txqs.tso_hdr_page = alloc_percpu(struct iwl_tso_hdr_page);
 	if (!trans_pcie->txqs.tso_hdr_page) {
 		ret = -ENOMEM;
-- 
cgit v1.3-3-g829e


From 7dd22dad8dc335dd7650d03ba1c08cae5afdefcc Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 8 Aug 2024 23:22:46 +0300
Subject: wifi: iwlwifi: mvm: cleanup iwl_mvm_get_wd_timeout

This used to extract the timeout from the debug TLV
(FW_DBG_TRIGGER_TXQ_TIMERS), which is not in use.
Cleanup iwl_mvm_get_wd_timeout to not consider the debug TLV.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240808232017.7a6944bc2e38.I532b4b5487c6be9203ff4db9742d7cc5b148d502@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c |  4 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h     |  3 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c     | 16 +++----
 drivers/net/wireless/intel/iwlwifi/mvm/utils.c   | 60 +++++-------------------
 4 files changed, 22 insertions(+), 61 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index d5a204e52076..071de9372843 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -216,7 +216,7 @@ int iwl_mvm_mld_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	static const u8 _baddr[] = {0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
 	const u8 *baddr = _baddr;
 	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+		iwl_mvm_get_wd_timeout(mvm, vif);
 	u16 *queue;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -254,7 +254,7 @@ int iwl_mvm_mld_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	struct iwl_mvm_int_sta *msta = &mvm_link->mcast_sta;
 	static const u8 _maddr[] = {0x03, 0x00, 0x00, 0x00, 0x00, 0x00};
 	const u8 *maddr = _maddr;
-	unsigned int timeout = iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+	unsigned int timeout = iwl_mvm_get_wd_timeout(mvm, vif);
 
 	lockdep_assert_held(&mvm->mutex);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 65b66f01bef9..68464f892e85 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2587,8 +2587,7 @@ u8 iwl_mvm_tcm_load_percentage(u32 airtime, u32 elapsed);
 
 void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error);
 unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm,
-				    struct ieee80211_vif *vif,
-				    bool tdls, bool cmd_q);
+				    struct ieee80211_vif *vif);
 void iwl_mvm_connection_loss(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			     const char *errmsg);
 void iwl_mvm_event_frame_timeout_callback(struct iwl_mvm *mvm,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index cf4d6425f634..74bbeebe69d5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -900,7 +900,7 @@ static int iwl_mvm_sta_alloc_queue_tvqm(struct iwl_mvm *mvm,
 	struct iwl_mvm_txq *mvmtxq =
 		iwl_mvm_txq_from_tid(sta, tid);
 	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false);
+		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif);
 	int queue = -1;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -1080,7 +1080,7 @@ static void iwl_mvm_unshare_queue(struct iwl_mvm *mvm, int queue)
 		return;
 
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
-	wdg_timeout = iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false);
+	wdg_timeout = iwl_mvm_get_wd_timeout(mvm, mvmsta->vif);
 
 	ssn = IEEE80211_SEQ_TO_SN(mvmsta->tid_data[tid].seq_number);
 
@@ -1330,7 +1330,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 		.frame_limit = IWL_FRAME_LIMIT,
 	};
 	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false);
+		iwl_mvm_get_wd_timeout(mvm, mvmsta->vif);
 	int queue = -1;
 	u16 queue_tmp;
 	unsigned long disable_agg_tids = 0;
@@ -1622,7 +1622,7 @@ void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm,
 {
 	struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
 	unsigned int wdg =
-		iwl_mvm_get_wd_timeout(mvm, mvm_sta->vif, false, false);
+		iwl_mvm_get_wd_timeout(mvm, mvm_sta->vif);
 	int i;
 	struct iwl_trans_txq_scd_cfg cfg = {
 		.sta_id = mvm_sta->deflink.sta_id,
@@ -2359,7 +2359,7 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	int queue;
 	int ret;
 	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+		iwl_mvm_get_wd_timeout(mvm, vif);
 	struct iwl_trans_txq_scd_cfg cfg = {
 		.fifo = IWL_MVM_TX_FIFO_VO,
 		.sta_id = mvmvif->deflink.bcast_sta.sta_id,
@@ -2568,7 +2568,7 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		.aggregate = false,
 		.frame_limit = IWL_FRAME_LIMIT,
 	};
-	unsigned int timeout = iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+	unsigned int timeout = iwl_mvm_get_wd_timeout(mvm, vif);
 	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -3207,7 +3207,7 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid];
 	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, vif, sta->tdls, false);
+		iwl_mvm_get_wd_timeout(mvm, vif);
 	int queue, ret;
 	bool alloc_queue = true;
 	enum iwl_mvm_queue_status queue_status;
@@ -4326,7 +4326,7 @@ int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	u16 queue;
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
 	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, vif, false, false);
+		iwl_mvm_get_wd_timeout(mvm, vif);
 	bool mld = iwl_mvm_has_mld_api(mvm->fw);
 	u32 type = mld ? STATION_TYPE_PEER : IWL_STA_LINK;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index edcc6e2cb76a..1d1364d03f02 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -747,58 +747,20 @@ bool iwl_mvm_is_vif_assoc(struct iwl_mvm *mvm)
 }
 
 unsigned int iwl_mvm_get_wd_timeout(struct iwl_mvm *mvm,
-				    struct ieee80211_vif *vif,
-				    bool tdls, bool cmd_q)
+				    struct ieee80211_vif *vif)
 {
-	struct iwl_fw_dbg_trigger_tlv *trigger;
-	struct iwl_fw_dbg_trigger_txq_timer *txq_timer;
-	unsigned int default_timeout = cmd_q ?
-		IWL_DEF_WD_TIMEOUT :
+	unsigned int default_timeout =
 		mvm->trans->trans_cfg->base_params->wd_timeout;
 
-	if (!iwl_fw_dbg_trigger_enabled(mvm->fw, FW_DBG_TRIGGER_TXQ_TIMERS)) {
-		/*
-		 * We can't know when the station is asleep or awake, so we
-		 * must disable the queue hang detection.
-		 */
-		if (fw_has_capa(&mvm->fw->ucode_capa,
-				IWL_UCODE_TLV_CAPA_STA_PM_NOTIF) &&
-		    vif && vif->type == NL80211_IFTYPE_AP)
-			return IWL_WATCHDOG_DISABLED;
-		return default_timeout;
-	}
-
-	trigger = iwl_fw_dbg_get_trigger(mvm->fw, FW_DBG_TRIGGER_TXQ_TIMERS);
-	txq_timer = (void *)trigger->data;
-
-	if (tdls)
-		return le32_to_cpu(txq_timer->tdls);
-
-	if (cmd_q)
-		return le32_to_cpu(txq_timer->command_queue);
-
-	if (WARN_ON(!vif))
-		return default_timeout;
-
-	switch (ieee80211_vif_type_p2p(vif)) {
-	case NL80211_IFTYPE_ADHOC:
-		return le32_to_cpu(txq_timer->ibss);
-	case NL80211_IFTYPE_STATION:
-		return le32_to_cpu(txq_timer->bss);
-	case NL80211_IFTYPE_AP:
-		return le32_to_cpu(txq_timer->softap);
-	case NL80211_IFTYPE_P2P_CLIENT:
-		return le32_to_cpu(txq_timer->p2p_client);
-	case NL80211_IFTYPE_P2P_GO:
-		return le32_to_cpu(txq_timer->p2p_go);
-	case NL80211_IFTYPE_P2P_DEVICE:
-		return le32_to_cpu(txq_timer->p2p_device);
-	case NL80211_IFTYPE_MONITOR:
-		return default_timeout;
-	default:
-		WARN_ON(1);
-		return mvm->trans->trans_cfg->base_params->wd_timeout;
-	}
+	/*
+	 * We can't know when the station is asleep or awake, so we
+	 * must disable the queue hang detection.
+	 */
+	if (fw_has_capa(&mvm->fw->ucode_capa,
+			IWL_UCODE_TLV_CAPA_STA_PM_NOTIF) &&
+	    vif->type == NL80211_IFTYPE_AP)
+		return IWL_WATCHDOG_DISABLED;
+	return default_timeout;
 }
 
 void iwl_mvm_connection_loss(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-- 
cgit v1.3-3-g829e


From fa21770fe4f36d3a42297e74c9e02e019b436b07 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 8 Aug 2024 23:22:47 +0300
Subject: wifi: iwlwifi: bump FW API to 93 for BZ/SC devices

Start supporting API version 93 for new devices.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20240808232017.5c9846f4c2c3.I6c825bc93aa23db302f24db5617f9b9b06042ec8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index b230441abc16..fa1be8c54d3c 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -10,7 +10,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_BZ_UCODE_API_MAX	92
+#define IWL_BZ_UCODE_API_MAX	93
 
 /* Lowest firmware API version supported */
 #define IWL_BZ_UCODE_API_MIN	90
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 4ccb0b7bdc20..f1dd1c29f305 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -10,7 +10,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_SC_UCODE_API_MAX	92
+#define IWL_SC_UCODE_API_MAX	93
 
 /* Lowest firmware API version supported */
 #define IWL_SC_UCODE_API_MIN	90
-- 
cgit v1.3-3-g829e


From 1c7e1068a7c9c39ed27636db93e71911e0045419 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 8 Aug 2024 23:22:48 +0300
Subject: wifi: iwlwifi: mvm: drop wrong STA selection in TX

This shouldn't happen at all, since in station mode all MMPDUs
go through the TXQ for the STA, and not this function. There
may or may not be a race in mac80211 through which this might
happen for some frames while a station is being added, but in
that case we can also just drop the frame and pretend the STA
didn't exist yet.

Also, the code is simply wrong since it uses deflink, and it's
not easy to fix it since the mvmvif->ap_sta pointer cannot be
used without the mutex, and perhaps the right link might not
even be known.

Just drop the frame at that point instead of trying to fix it
up.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.45ad105dc7fe.I6d45c82e5758395d9afb8854057ded03c7dc81d7@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index af892c8291d4..f3f5cfd3baaa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -839,20 +839,10 @@ void iwl_mvm_mac_tx(struct ieee80211_hw *hw,
 	if (ieee80211_is_mgmt(hdr->frame_control))
 		sta = NULL;
 
-	/* If there is no sta, and it's not offchannel - send through AP */
+	/* this shouldn't even happen: just drop */
 	if (!sta && info->control.vif->type == NL80211_IFTYPE_STATION &&
-	    !offchannel) {
-		struct iwl_mvm_vif *mvmvif =
-			iwl_mvm_vif_from_mac80211(info->control.vif);
-		u8 ap_sta_id = READ_ONCE(mvmvif->deflink.ap_sta_id);
-
-		if (ap_sta_id < mvm->fw->ucode_capa.num_stations) {
-			/* mac80211 holds rcu read lock */
-			sta = rcu_dereference(mvm->fw_id_to_mac_id[ap_sta_id]);
-			if (IS_ERR_OR_NULL(sta))
-				goto drop;
-		}
-	}
+	    !offchannel)
+		goto drop;
 
 	if (tmp_sta && !sta && link_id != IEEE80211_LINK_UNSPECIFIED &&
 	    !ieee80211_is_probe_resp(hdr->frame_control)) {
-- 
cgit v1.3-3-g829e


From ff5aabe7c2a4a4b089a9ced0cb3d0e284963a7dd Mon Sep 17 00:00:00 2001
From: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Thu, 8 Aug 2024 23:22:49 +0300
Subject: wifi: iwlwifi: allow only CN mcc from WRDD

Block other mcc expect CN from WRDD ACPI.

Signed-off-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240808232017.fe6ea7aa4b39.I86004687a2963fe26f990770aca103e2f5cb1628@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/acpi.c       | 5 +++++
 drivers/net/wireless/intel/iwlwifi/fw/regulatory.h | 2 ++
 drivers/net/wireless/intel/iwlwifi/fw/uefi.c       | 2 +-
 drivers/net/wireless/intel/iwlwifi/fw/uefi.h       | 2 --
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 79774c8c7ff4..d20cd49773c9 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -357,6 +357,11 @@ int iwl_acpi_get_mcc(struct iwl_fw_runtime *fwrt, char *mcc)
 	}
 
 	mcc_val = wifi_pkg->package.elements[1].integer.value;
+	if (mcc_val != BIOS_MCC_CHINA) {
+		ret = -EINVAL;
+		IWL_DEBUG_RADIO(fwrt, "ACPI WRDD is supported only for CN\n");
+		goto out_free;
+	}
 
 	mcc[0] = (mcc_val >> 8) & 0xff;
 	mcc[1] = mcc_val & 0xff;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index c2209948b4c0..81787501d4a4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -45,6 +45,8 @@
 #define IWL_WTAS_ENABLE_IEC_MSK	0x4
 #define IWL_WTAS_USA_UHB_MSK		BIT(16)
 
+#define BIOS_MCC_CHINA 0x434e
+
 /*
  * The profile for revision 2 is a superset of revision 1, which is in
  * turn a superset of revision 0.  So we can store all revisions
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index 754fc5014fbf..091fb6fd7c78 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -638,7 +638,7 @@ int iwl_uefi_get_mcc(struct iwl_fw_runtime *fwrt, char *mcc)
 		goto out;
 	}
 
-	if (data->mcc != UEFI_MCC_CHINA) {
+	if (data->mcc != BIOS_MCC_CHINA) {
 		ret = -EINVAL;
 		IWL_DEBUG_RADIO(fwrt, "UEFI WRDD is supported only for CN\n");
 		goto out;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
index 0b2477190070..e525d449e656 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
@@ -151,8 +151,6 @@ struct uefi_cnv_var_splc {
 	u32 default_pwr_limit;
 } __packed;
 
-#define UEFI_MCC_CHINA 0x434e
-
 /* struct uefi_cnv_var_wrdd - WRDD table as defined in UEFI
  * @revision: the revision of the table
  * @mcc: country identifier as defined in ISO/IEC 3166-1 Alpha 2 code
-- 
cgit v1.3-3-g829e


From 0f31a7effa5b7bd9cd9698ac43c443b7075f497c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 25 Aug 2024 15:19:16 +0200
Subject: net: rfkill: gpio: Do not load on Lenovo Yoga Tab 3 Pro YT3-X90

The Lenovo Yoga Tab 3 Pro YT3-X90 has a non functional "BCM4752" ACPI
device, which uses GPIO resources which are actually necessary / used
for the sound (codec, speaker amplifier) on the Lenovo Yoga Tab 3 Pro.

If the rfkill-gpio driver loads before the sound drivers do the sound
drivers fail to load because the GPIOs are already claimed.

Add a DMI based deny list with the Lenovo Yoga Tab 3 Pro on there and
make rfkill_gpio_probe() exit with -ENODEV for devices on the DMI based
deny list.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Link: https://patch.msgid.link/20240825131916.6388-1-hdegoede@redhat.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/rfkill/rfkill-gpio.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 84529886c2e6..c268c2b011f4 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -3,6 +3,7 @@
  * Copyright (c) 2011, NVIDIA Corporation.
  */
 
+#include <linux/dmi.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -72,6 +73,20 @@ static int rfkill_gpio_acpi_probe(struct device *dev,
 	return devm_acpi_dev_add_driver_gpios(dev, acpi_rfkill_default_gpios);
 }
 
+/* List of DMI matches for devices on which rfkill-gpio should not load,
+ * to avoid firmware bugs.
+ */
+static const struct dmi_system_id rfkill_gpio_deny_table[] = {
+	{
+		/* Lenovo Yoga Tab 3 Pro YT3-X90, bogus "BCM4752" device in DSDT */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
+		},
+	},
+	{ }
+};
+
 static int rfkill_gpio_probe(struct platform_device *pdev)
 {
 	struct rfkill_gpio_data *rfkill;
@@ -81,6 +96,9 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 	const char *type_name;
 	int ret;
 
+	if (dmi_check_system(rfkill_gpio_deny_table))
+		return -ENODEV;
+
 	rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL);
 	if (!rfkill)
 		return -ENOMEM;
-- 
cgit v1.3-3-g829e


From a0ee9dcce60027258a53ee85b9153ab268dcb55a Mon Sep 17 00:00:00 2001
From: Zhang Changzhong <zhangchangzhong@huawei.com>
Date: Sat, 24 Aug 2024 16:26:43 +0800
Subject: wifi: mac80211: remove redundant unlikely() around IS_ERR()

IS_ERR() already calls unlikely(), so unlikely() is redundant here.

Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Link: https://patch.msgid.link/1724488003-45388-1-git-send-email-zhangchangzhong@huawei.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh_pathtbl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index c0a5c75cddcb..30c0d89203af 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -580,7 +580,7 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata,
 	prev = rhashtable_lookup_get_insert_fast(&cache->rht,
 						 &entry->rhash,
 						 fast_tx_rht_params);
-	if (unlikely(IS_ERR(prev))) {
+	if (IS_ERR(prev)) {
 		kfree(entry);
 		goto unlock_cache;
 	}
-- 
cgit v1.3-3-g829e


From 373d3f8dcbb1c0d764123653ca4574be636b8d86 Mon Sep 17 00:00:00 2001
From: Zijun Hu <quic_zijuhu@quicinc.com>
Date: Sun, 11 Aug 2024 12:47:26 +0800
Subject: wifi: rfkill: Correct parameter type for rfkill_set_hw_state_reason()

Change type of parameter @reason to enum rfkill_hard_block_reasons
for API rfkill_set_hw_state_reason() according to its comments, and
all kernel callers have invoked the API with enum type actually.

Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Link: https://patch.msgid.link/20240811-rfkill_fix-v2-1-9050760336f4@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/rfkill.h | 5 +++--
 net/rfkill/core.c      | 8 ++------
 2 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index 373003ace639..997b34197385 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -147,7 +147,8 @@ void rfkill_destroy(struct rfkill *rfkill);
  * Prefer to use rfkill_set_hw_state if you don't need any special reason.
  */
 bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
-				bool blocked, unsigned long reason);
+				bool blocked,
+				enum rfkill_hard_block_reasons reason);
 /**
  * rfkill_set_hw_state - Set the internal rfkill hardware block state
  * @rfkill: pointer to the rfkill class to modify.
@@ -280,7 +281,7 @@ static inline void rfkill_destroy(struct rfkill *rfkill)
 
 static inline bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
 					      bool blocked,
-					      unsigned long reason)
+					      enum rfkill_hard_block_reasons reason)
 {
 	return blocked;
 }
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 7a5367628c05..13a5126bc36e 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -539,18 +539,14 @@ bool rfkill_get_global_sw_state(const enum rfkill_type type)
 #endif
 
 bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
-				bool blocked, unsigned long reason)
+				bool blocked,
+				enum rfkill_hard_block_reasons reason)
 {
 	unsigned long flags;
 	bool ret, prev;
 
 	BUG_ON(!rfkill);
 
-	if (WARN(reason & ~(RFKILL_HARD_BLOCK_SIGNAL |
-			    RFKILL_HARD_BLOCK_NOT_OWNER),
-		 "hw_state reason not supported: 0x%lx", reason))
-		return rfkill_blocked(rfkill);
-
 	spin_lock_irqsave(&rfkill->lock, flags);
 	prev = !!(rfkill->hard_block_reasons & reason);
 	if (blocked) {
-- 
cgit v1.3-3-g829e


From 53bc1b73b67836ac9867f93dee7a443986b4a94f Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Thu, 22 Aug 2024 09:42:54 +0800
Subject: wifi: mac80211: export ieee80211_purge_tx_queue() for drivers

Drivers need to purge TX SKB when stopping. Using skb_queue_purge() can't
report TX status to mac80211, causing ieee80211_free_ack_frame() warns
"Have pending ack frames!". Export ieee80211_purge_tx_queue() for drivers
to not have to reimplement it.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240822014255.10211-1-pkshih@realtek.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     | 13 +++++++++++++
 net/mac80211/ieee80211_i.h |  2 --
 net/mac80211/status.c      |  1 +
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index cfd64acdc039..adfec877f392 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3181,6 +3181,19 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw,
  */
 void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
 
+/**
+ * ieee80211_purge_tx_queue - purge TX skb queue
+ * @hw: the hardware
+ * @skbs: the skbs
+ *
+ * Free a set of transmit skbs. Use this function when device is going to stop
+ * but some transmit skbs without TX status are still queued.
+ * This function does not take the list lock and the caller must hold the
+ * relevant locks to use it.
+ */
+void ieee80211_purge_tx_queue(struct ieee80211_hw *hw,
+			      struct sk_buff_head *skbs);
+
 /**
  * DOC: Hardware crypto acceleration
  *
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index fdd2bad15076..6305c4e9cca1 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2072,8 +2072,6 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 				  u32 info_flags,
 				  u32 ctrl_flags,
 				  u64 *cookie);
-void ieee80211_purge_tx_queue(struct ieee80211_hw *hw,
-			      struct sk_buff_head *skbs);
 struct sk_buff *
 ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
 			      struct sk_buff *skb, u32 info_flags);
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index dd8f857a1fbc..d1cf987de13b 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -1301,3 +1301,4 @@ void ieee80211_purge_tx_queue(struct ieee80211_hw *hw,
 	while ((skb = __skb_dequeue(skbs)))
 		ieee80211_free_txskb(hw, skb);
 }
+EXPORT_SYMBOL(ieee80211_purge_tx_queue);
-- 
cgit v1.3-3-g829e


From 557a6cd847645e667f3b362560bd7e7c09aac284 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 25 Aug 2024 19:17:09 +0300
Subject: wifi: iwlwifi: mvm: avoid NULL pointer dereference

iwl_mvm_tx_skb_sta() and iwl_mvm_tx_mpdu() verify that the mvmvsta
pointer is not NULL.
It retrieves this pointer using iwl_mvm_sta_from_mac80211, which is
dereferencing the ieee80211_sta pointer.
If sta is NULL, iwl_mvm_sta_from_mac80211 will dereference a NULL
pointer.
Fix this by checking the sta pointer before retrieving the mvmsta
from it. If sta is not NULL, then mvmsta isn't either.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20240825191257.880921ce23b7.I340052d70ab6d3410724ce955eb00da10e08188f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 7ff5ea5e7aca..db926b2f4d8d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1203,6 +1203,9 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	bool is_ampdu = false;
 	int hdrlen;
 
+	if (WARN_ON_ONCE(!sta))
+		return -1;
+
 	mvmsta = iwl_mvm_sta_from_mac80211(sta);
 	fc = hdr->frame_control;
 	hdrlen = ieee80211_hdrlen(fc);
@@ -1210,9 +1213,6 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb,
 	if (IWL_MVM_NON_TRANSMITTING_AP && ieee80211_is_probe_resp(fc))
 		return -1;
 
-	if (WARN_ON_ONCE(!mvmsta))
-		return -1;
-
 	if (WARN_ON_ONCE(mvmsta->deflink.sta_id == IWL_MVM_INVALID_STA))
 		return -1;
 
@@ -1343,7 +1343,7 @@ drop:
 int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 		       struct ieee80211_sta *sta)
 {
-	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+	struct iwl_mvm_sta *mvmsta;
 	struct ieee80211_tx_info info;
 	struct sk_buff_head mpdus_skbs;
 	struct ieee80211_vif *vif;
@@ -1352,9 +1352,11 @@ int iwl_mvm_tx_skb_sta(struct iwl_mvm *mvm, struct sk_buff *skb,
 	struct sk_buff *orig_skb = skb;
 	const u8 *addr3;
 
-	if (WARN_ON_ONCE(!mvmsta))
+	if (WARN_ON_ONCE(!sta))
 		return -1;
 
+	mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
 	if (WARN_ON_ONCE(mvmsta->deflink.sta_id == IWL_MVM_INVALID_STA))
 		return -1;
 
-- 
cgit v1.3-3-g829e


From 76364f3edfde60aa2fa20b578ba9b96797d7bff5 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 25 Aug 2024 19:17:11 +0300
Subject: wifi: iwlwifi: mvm: allow ESR when we the ROC expires

We forgot to release the ROC reason for ESR prevention when the remain
on channel expires.
Add this.

Fixes: a1efeb823084 ("wifi: iwlwifi: mvm: Block EMLSR when a p2p/softAP vif is active")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240825191257.8f8765f359cc.I16fcd6198072d422ff36dce68070aafaf011f4c1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index a8c42ce3b630..72fa7ac86516 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -114,16 +114,14 @@ static void iwl_mvm_cleanup_roc(struct iwl_mvm *mvm)
 		iwl_mvm_flush_sta(mvm, mvm->aux_sta.sta_id,
 				  mvm->aux_sta.tfd_queue_msk);
 
-		if (mvm->mld_api_is_used) {
-			iwl_mvm_mld_rm_aux_sta(mvm);
-			mutex_unlock(&mvm->mutex);
-			return;
-		}
-
 		/* In newer version of this command an aux station is added only
 		 * in cases of dedicated tx queue and need to be removed in end
-		 * of use */
-		if (iwl_mvm_has_new_station_api(mvm->fw))
+		 * of use. For the even newer mld api, use the appropriate
+		 * function.
+		 */
+		if (mvm->mld_api_is_used)
+			iwl_mvm_mld_rm_aux_sta(mvm);
+		else if (iwl_mvm_has_new_station_api(mvm->fw))
 			iwl_mvm_rm_aux_sta(mvm);
 	}
 
-- 
cgit v1.3-3-g829e


From 32bf7729d2e67aed4a6c537bf21d2023e3f39c45 Mon Sep 17 00:00:00 2001
From: Yu Jiaoliang <yujiaoliang@vivo.com>
Date: Thu, 22 Aug 2024 15:47:43 +0800
Subject: wifi: cfg80211: Use kmemdup_array instead of kmemdup for multiple
 allocation

Let the kememdup_array() take care about multiplication and possible
overflows.

Signed-off-by: Yu Jiaoliang <yujiaoliang@vivo.com>
Reviewed-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://patch.msgid.link/20240822074743.1366561-1-yujiaoliang@vivo.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/util.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index edeeb056fe4d..f49b55724f83 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -2437,8 +2437,8 @@ int cfg80211_iter_combinations(struct wiphy *wiphy,
 		if (params->num_different_channels > c->num_different_channels)
 			continue;
 
-		limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits,
-				 GFP_KERNEL);
+		limits = kmemdup_array(c->limits, c->n_limits, sizeof(*limits),
+				       GFP_KERNEL);
 		if (!limits)
 			return -ENOMEM;
 
-- 
cgit v1.3-3-g829e


From d07e1f5c745058d1805e7d8042b9a326b120cb6e Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Tue, 27 Aug 2024 15:21:15 +0800
Subject: wifi: mac80211: use kmemdup_array instead of kmemdup for multiple
 allocation

Let the kmemdup_array() take care about multiplication
and possible overflows.

Using kmemdup_array() is more appropriate and makes the code
easier to audit.

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20240827072115.42680-1-shenlichuan@vivo.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index a3104b6ea6f0..89084690350f 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1051,9 +1051,9 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local)
 			return 0;
 
 		/* Driver provides cipher suites, but we need to exclude WEP */
-		suites = kmemdup(local->hw.wiphy->cipher_suites,
-				 sizeof(u32) * local->hw.wiphy->n_cipher_suites,
-				 GFP_KERNEL);
+		suites = kmemdup_array(local->hw.wiphy->cipher_suites,
+				       local->hw.wiphy->n_cipher_suites,
+				       sizeof(u32), GFP_KERNEL);
 		if (!suites)
 			return -ENOMEM;
 
-- 
cgit v1.3-3-g829e


From e7cd191f83fd899c233dfbe7dc6d96ef703dcbbd Mon Sep 17 00:00:00 2001
From: wangfe <wangfe@google.com>
Date: Thu, 22 Aug 2024 13:02:52 -0700
Subject: xfrm: add SA information to the offloaded packet

In packet offload mode, append Security Association (SA) information
to each packet, replicating the crypto offload implementation.
The XFRM_XMIT flag is set to enable packet to be returned immediately
from the validate_xmit_xfrm function, thus aligning with the existing
code path for packet offload mode.

This SA info helps HW offload match packets to their correct security
policies. The XFRM interface ID is included, which is crucial in setups
with multiple XFRM interfaces where source/destination addresses alone
can't pinpoint the right policy.

Signed-off-by: wangfe <wangfe@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_output.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index e5722c95b8bb..a12588e7b060 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -706,6 +706,8 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
 	int family;
 	int err;
+	struct xfrm_offload *xo;
+	struct sec_path *sp;
 
 	family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family
 		: skb_dst(skb)->ops->family;
@@ -728,6 +730,25 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 			kfree_skb(skb);
 			return -EHOSTUNREACH;
 		}
+		sp = secpath_set(skb);
+		if (!sp) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+
+		sp->olen++;
+		sp->xvec[sp->len++] = x;
+		xfrm_state_hold(x);
+
+		xo = xfrm_offload(skb);
+		if (!xo) {
+			secpath_reset(skb);
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return -EINVAL;
+		}
+		xo->flags |= XFRM_XMIT;
 
 		return xfrm_output_resume(sk, skb, 0);
 	}
-- 
cgit v1.3-3-g829e


From 938863727076f684abb39d1d0f9dce1924e9028e Mon Sep 17 00:00:00 2001
From: Boris Sukholitko <boris.sukholitko@broadcom.com>
Date: Thu, 22 Aug 2024 13:35:08 +0300
Subject: tc: adjust network header after 2nd vlan push

<tldr>
skb network header of the single-tagged vlan packet continues to point the
vlan payload (e.g. IP) after second vlan tag is pushed by tc act_vlan. This
causes problem at the dissector which expects double-tagged packet network
header to point to the inner vlan.

The fix is to adjust network header in tcf_act_vlan.c but requires
refactoring of skb_vlan_push function.
</tldr>

Consider the following shell script snippet configuring TC rules on the
veth interface:

ip link add veth0 type veth peer veth1
ip link set veth0 up
ip link set veth1 up

tc qdisc add dev veth0 clsact

tc filter add dev veth0 ingress pref 10 chain 0 flower \
	num_of_vlans 2 cvlan_ethtype 0x800 action goto chain 5
tc filter add dev veth0 ingress pref 20 chain 0 flower \
	num_of_vlans 1 action vlan push id 100 \
	protocol 0x8100 action goto chain 5
tc filter add dev veth0 ingress pref 30 chain 5 flower \
	num_of_vlans 2 cvlan_ethtype 0x800 action simple sdata "success"

Sending double-tagged vlan packet with the IP payload inside:

cat <<ENDS | text2pcap - - | tcpreplay -i veth1 -
0000  00 00 00 00 00 11 00 00 00 00 00 22 81 00 00 64   ..........."...d
0010  81 00 00 14 08 00 45 04 00 26 04 d2 00 00 7f 11   ......E..&......
0020  18 ef 0a 00 00 01 14 00 00 02 00 00 00 00 00 12   ................
0030  e1 c7 00 00 00 00 00 00 00 00 00 00               ............
ENDS

will match rule 10, goto rule 30 in chain 5 and correctly emit "success" to
the dmesg.

OTOH, sending single-tagged vlan packet:

cat <<ENDS | text2pcap - - | tcpreplay -i veth1 -
0000  00 00 00 00 00 11 00 00 00 00 00 22 81 00 00 14   ..........."....
0010  08 00 45 04 00 2a 04 d2 00 00 7f 11 18 eb 0a 00   ..E..*..........
0020  00 01 14 00 00 02 00 00 00 00 00 16 e1 bf 00 00   ................
0030  00 00 00 00 00 00 00 00 00 00 00 00               ............
ENDS

will match rule 20, will push the second vlan tag but will *not* match
rule 30. IOW, the match at rule 30 fails if the second vlan was freshly
pushed by the kernel.

Lets look at  __skb_flow_dissect working on the double-tagged vlan packet.
Here is the relevant code from around net/core/flow_dissector.c:1277
copy-pasted here for convenience:

	if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX &&
	    skb && skb_vlan_tag_present(skb)) {
		proto = skb->protocol;
	} else {
		vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
					    data, hlen, &_vlan);
		if (!vlan) {
			fdret = FLOW_DISSECT_RET_OUT_BAD;
			break;
		}

		proto = vlan->h_vlan_encapsulated_proto;
		nhoff += sizeof(*vlan);
	}

The "else" clause above gets the protocol of the encapsulated packet from
the skb data at the network header location. printk debugging has showed
that in the good double-tagged packet case proto is
htons(0x800 == ETH_P_IP) as expected. However in the single-tagged packet
case proto is garbage leading to the failure to match tc filter 30.

proto is being set from the skb header pointed by nhoff parameter which is
defined at the beginning of __skb_flow_dissect
(net/core/flow_dissector.c:1055 in the current version):

		nhoff = skb_network_offset(skb);

Therefore the culprit seems to be that the skb network offset is different
between double-tagged packet received from the interface and single-tagged
packet having its vlan tag pushed by TC.

Lets look at the interesting points of the lifetime of the single/double
tagged packets as they traverse our packet flow.

Both of them will start at __netif_receive_skb_core where the first vlan
tag will be stripped:

	if (eth_type_vlan(skb->protocol)) {
		skb = skb_vlan_untag(skb);
		if (unlikely(!skb))
			goto out;
	}

At this stage in double-tagged case skb->data points to the second vlan tag
while in single-tagged case skb->data points to the network (eg. IP)
header.

Looking at TC vlan push action (net/sched/act_vlan.c) we have the following
code at tcf_vlan_act (interesting points are in square brackets):

	if (skb_at_tc_ingress(skb))
[1]		skb_push_rcsum(skb, skb->mac_len);

	....

	case TCA_VLAN_ACT_PUSH:
		err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid |
				    (p->tcfv_push_prio << VLAN_PRIO_SHIFT),
				    0);
		if (err)
			goto drop;
		break;

	....

out:
	if (skb_at_tc_ingress(skb))
[3]		skb_pull_rcsum(skb, skb->mac_len);

And skb_vlan_push (net/core/skbuff.c:6204) function does:

		err = __vlan_insert_tag(skb, skb->vlan_proto,
					skb_vlan_tag_get(skb));
		if (err)
			return err;

		skb->protocol = skb->vlan_proto;
[2]		skb->mac_len += VLAN_HLEN;

in the case of pushing the second tag. Lets look at what happens with
skb->data of the single-tagged packet at each of the above points:

1. As a result of the skb_push_rcsum, skb->data is moved back to the start
   of the packet.

2. First VLAN tag is moved from the skb into packet buffer, skb->mac_len is
   incremented, skb->data still points to the start of the packet.

3. As a result of the skb_pull_rcsum, skb->data is moved forward by the
   modified skb->mac_len, thus pointing to the network header again.

Then __skb_flow_dissect will get confused by having double-tagged vlan
packet with the skb->data at the network header.

The solution for the bug is to preserve "skb->data at second vlan header"
semantics in the skb_vlan_push function. We do this by manipulating
skb->network_header rather than skb->mac_len. skb_vlan_push callers are
updated to do skb_reset_mac_len.

Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/filter.c         | 1 +
 net/core/skbuff.c         | 2 +-
 net/openvswitch/actions.c | 8 ++++++--
 net/sched/act_vlan.c      | 1 +
 4 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 40b2cacc0df0..f09d875cc053 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3190,6 +3190,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto,
 	bpf_push_mac_rcsum(skb);
 	ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
 	bpf_pull_mac_rcsum(skb);
+	skb_reset_mac_len(skb);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6022c7359385..a52638363ea5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6243,7 +6243,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 			return err;
 
 		skb->protocol = skb->vlan_proto;
-		skb->mac_len += VLAN_HLEN;
+		skb->network_header -= VLAN_HLEN;
 
 		skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN);
 	}
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 101f9a23792c..16e260014684 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -237,14 +237,18 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
 		     const struct ovs_action_push_vlan *vlan)
 {
+	int err;
+
 	if (skb_vlan_tag_present(skb)) {
 		invalidate_flow_key(key);
 	} else {
 		key->eth.vlan.tci = vlan->vlan_tci;
 		key->eth.vlan.tpid = vlan->vlan_tpid;
 	}
-	return skb_vlan_push(skb, vlan->vlan_tpid,
-			     ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
+	err = skb_vlan_push(skb, vlan->vlan_tpid,
+			    ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
+	skb_reset_mac_len(skb);
+	return err;
 }
 
 /* 'src' is already properly masked. */
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 22f4b1e8ade9..383bf18b6862 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -96,6 +96,7 @@ out:
 	if (skb_at_tc_ingress(skb))
 		skb_pull_rcsum(skb, skb->mac_len);
 
+	skb_reset_mac_len(skb);
 	return action;
 
 drop:
-- 
cgit v1.3-3-g829e


From 59c330eccee82f9e53421dd8a83b1bc236f4557a Mon Sep 17 00:00:00 2001
From: Boris Sukholitko <boris.sukholitko@broadcom.com>
Date: Thu, 22 Aug 2024 13:35:09 +0300
Subject: selftests: tc_actions: test ingress 2nd vlan push

Add new test checking the correctness of inner vlan flushing to the skb
data when outer vlan tag is added through act_vlan on ingress.

Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../testing/selftests/net/forwarding/tc_actions.sh | 23 +++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index 589629636502..f2f1e99a90b2 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -4,7 +4,7 @@
 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
 	mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
 	gact_trap_test mirred_egress_to_ingress_test \
-	mirred_egress_to_ingress_tcp_test"
+	mirred_egress_to_ingress_tcp_test ingress_2nd_vlan_push"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -244,6 +244,27 @@ mirred_egress_to_ingress_tcp_test()
 	log_test "mirred_egress_to_ingress_tcp ($tcflags)"
 }
 
+ingress_2nd_vlan_push()
+{
+	tc filter add dev $swp1 ingress pref 20 chain 0 handle 20 flower \
+		$tcflags num_of_vlans 1 \
+		action vlan push id 100 protocol 0x8100 action goto chain 5
+	tc filter add dev $swp1 ingress pref 30 chain 5 handle 30 flower \
+		$tcflags num_of_vlans 2 \
+		cvlan_ethtype 0x800 action pass
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -Q 10 -q
+
+	tc_check_packets "dev $swp1 ingress" 30 1
+	check_err $? "No double-vlan packets received"
+
+	tc filter del dev $swp1 ingress pref 20 chain 0 handle 20 flower
+	tc filter del dev $swp1 ingress pref 30 chain 5 handle 30 flower
+
+	log_test "ingress_2nd_vlan_push ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.3-3-g829e


From 2da44703a54403b9048ba268b2896dc0537a154f Mon Sep 17 00:00:00 2001
From: Boris Sukholitko <boris.sukholitko@broadcom.com>
Date: Thu, 22 Aug 2024 13:35:10 +0300
Subject: selftests: tc_actions: test egress 2nd vlan push

Add new test checking the correctness of inner vlan flushing to the skb
data when outer vlan tag is added through act_vlan on egress.

Signed-off-by: Boris Sukholitko <boris.sukholitko@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../testing/selftests/net/forwarding/tc_actions.sh | 25 +++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index f2f1e99a90b2..ea89e558672d 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -4,7 +4,8 @@
 ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
 	mirred_egress_mirror_test matchall_mirred_egress_mirror_test \
 	gact_trap_test mirred_egress_to_ingress_test \
-	mirred_egress_to_ingress_tcp_test ingress_2nd_vlan_push"
+	mirred_egress_to_ingress_tcp_test \
+	ingress_2nd_vlan_push egress_2nd_vlan_push"
 NUM_NETIFS=4
 source tc_common.sh
 source lib.sh
@@ -265,6 +266,28 @@ ingress_2nd_vlan_push()
 	log_test "ingress_2nd_vlan_push ($tcflags)"
 }
 
+egress_2nd_vlan_push()
+{
+	tc filter add dev $h1 egress pref 20 chain 0 handle 20 flower \
+		$tcflags num_of_vlans 0 \
+		action vlan push id 10 protocol 0x8100 \
+		pipe action vlan push id 100 protocol 0x8100 action goto chain 5
+	tc filter add dev $h1 egress pref 30 chain 5 handle 30 flower \
+		$tcflags num_of_vlans 2 \
+		cvlan_ethtype 0x800 action pass
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h1 egress" 30 1
+	check_err $? "No double-vlan packets received"
+
+	tc filter del dev $h1 egress pref 20 chain 0 handle 20 flower
+	tc filter del dev $h1 egress pref 30 chain 5 handle 30 flower
+
+	log_test "egress_2nd_vlan_push ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.3-3-g829e


From d96608794889d5a2419fb4077fa5d5bbffea07bc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 23 Aug 2024 14:00:53 +0200
Subject: netkit: Disable netpoll support

Follow-up to 45160cebd6ac ("net: veth: Disable netpoll support") to
also disable netpoll for netkit interfaces. Same conditions apply
here as well.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Breno Leitao <leitao@debian.org>
Cc: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/eab2d69ba2f4c260aef62e4ff0d803e9f60c2c5d.1724414250.git.daniel@iogearbox.net
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 drivers/net/netkit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 16789cd446e9..0681cf86284d 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -255,6 +255,7 @@ static void netkit_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_DISABLE_NETPOLL;
 
 	dev->ethtool_ops = &netkit_ethtool_ops;
 	dev->netdev_ops  = &netkit_netdev_ops;
-- 
cgit v1.3-3-g829e


From 3d6a0c4f4552c8b08ba63b9da97c8255db4c6a56 Mon Sep 17 00:00:00 2001
From: Diogo Jahchan Koike <djahchankoike@gmail.com>
Date: Mon, 26 Aug 2024 10:45:46 -0300
Subject: net: fix unreleased lock in cable test

fix an unreleased lock in out_dev_put path by removing the (now)
unnecessary path.

Reported-by: syzbot+c641161e97237326ea74@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=c641161e97237326ea74
Fixes: 3688ff3077d3 ("net: ethtool: cable-test: Target the command to the requested PHY")
Signed-off-by: Diogo Jahchan Koike <djahchankoike@gmail.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20240826134656.94892-1-djahchankoike@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/cabletest.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index ff2fe3566ace..3a91b65c1f9a 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -77,7 +77,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
-		goto out_dev_put;
+		goto out_rtnl;
 	}
 
 	ops = ethtool_phy_ops;
@@ -99,7 +99,6 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 
 out_rtnl:
 	rtnl_unlock();
-out_dev_put:
 	ethnl_parse_header_dev_put(&req_info);
 	return ret;
 }
-- 
cgit v1.3-3-g829e


From 3333df3b4bc8904768c0fd3d8a93564163c7962d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andy.shevchenko@gmail.com>
Date: Fri, 23 Aug 2024 02:05:50 +0300
Subject: net: ethernet: ti: am65-cpsw-nuss: Replace of_node_to_fwnode() with
 more suitable API

of_node_to_fwnode() is a IRQ domain specific implementation of
of_fwnode_handle(). Replace the former with more suitable API.

Signed-off-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822230550.708112-1-andy.shevchenko@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 81d9f21086ec..555aca4ffa24 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2761,7 +2761,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	}
 
 	phylink = phylink_create(&port->slave.phylink_config,
-				 of_node_to_fwnode(port->slave.port_np),
+				 of_fwnode_handle(port->slave.port_np),
 				 port->slave.phy_if,
 				 &am65_cpsw_phylink_mac_ops);
 	if (IS_ERR(phylink))
-- 
cgit v1.3-3-g829e


From 78a60497a020ff526ae067125eef0dee10df5771 Mon Sep 17 00:00:00 2001
From: Detlev Casanova <detlev.casanova@collabora.com>
Date: Fri, 23 Aug 2024 10:11:13 -0400
Subject: ethernet: stmmac: dwmac-rk: Fix typo for RK3588 code

Fix SELET -> SELECT in RK3588_GMAC_CLK_SELET_CRU and
RK3588_GMAC_CLK_SELET_IO

Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240823141318.51201-2-detlev.casanova@collabora.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 7ae04d8d291c..9cf0aa58d13b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1141,8 +1141,8 @@ static const struct rk_gmac_ops rk3568_ops = {
 #define RK3588_GMAC_CLK_RMII_MODE(id)		GRF_BIT(5 * (id))
 #define RK3588_GMAC_CLK_RGMII_MODE(id)		GRF_CLR_BIT(5 * (id))
 
-#define RK3588_GMAC_CLK_SELET_CRU(id)		GRF_BIT(5 * (id) + 4)
-#define RK3588_GMAC_CLK_SELET_IO(id)		GRF_CLR_BIT(5 * (id) + 4)
+#define RK3588_GMAC_CLK_SELECT_CRU(id)		GRF_BIT(5 * (id) + 4)
+#define RK3588_GMAC_CLK_SELECT_IO(id)		GRF_CLR_BIT(5 * (id) + 4)
 
 #define RK3588_GMA_CLK_RMII_DIV2(id)		GRF_BIT(5 * (id) + 2)
 #define RK3588_GMA_CLK_RMII_DIV20(id)		GRF_CLR_BIT(5 * (id) + 2)
@@ -1240,8 +1240,8 @@ err:
 static void rk3588_set_clock_selection(struct rk_priv_data *bsp_priv, bool input,
 				       bool enable)
 {
-	unsigned int val = input ? RK3588_GMAC_CLK_SELET_IO(bsp_priv->id) :
-				   RK3588_GMAC_CLK_SELET_CRU(bsp_priv->id);
+	unsigned int val = input ? RK3588_GMAC_CLK_SELECT_IO(bsp_priv->id) :
+				   RK3588_GMAC_CLK_SELECT_CRU(bsp_priv->id);
 
 	val |= enable ? RK3588_GMAC_CLK_RMII_NOGATE(bsp_priv->id) :
 			RK3588_GMAC_CLK_RMII_GATE(bsp_priv->id);
-- 
cgit v1.3-3-g829e


From 299e2aefb159e83f920de79a85100aa4cefec740 Mon Sep 17 00:00:00 2001
From: Detlev Casanova <detlev.casanova@collabora.com>
Date: Fri, 23 Aug 2024 10:11:14 -0400
Subject: dt-bindings: net: Add support for rk3576 dwmac

Add a rockchip,rk3576-gmac compatible for supporting the 2 gmac
devices on the rk3576.

Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240823141318.51201-3-detlev.casanova@collabora.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/rockchip-dwmac.yaml | 2 ++
 Documentation/devicetree/bindings/net/snps,dwmac.yaml     | 1 +
 2 files changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
index 6bbe96e35250..f8a576611d6c 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
@@ -25,6 +25,7 @@ select:
           - rockchip,rk3368-gmac
           - rockchip,rk3399-gmac
           - rockchip,rk3568-gmac
+          - rockchip,rk3576-gmac
           - rockchip,rk3588-gmac
           - rockchip,rv1108-gmac
           - rockchip,rv1126-gmac
@@ -52,6 +53,7 @@ properties:
       - items:
           - enum:
               - rockchip,rk3568-gmac
+              - rockchip,rk3576-gmac
               - rockchip,rk3588-gmac
               - rockchip,rv1126-gmac
           - const: snps,dwmac-4.20a
diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 3eb65e63fdae..4e2ba1bf788c 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -80,6 +80,7 @@ properties:
         - rockchip,rk3328-gmac
         - rockchip,rk3366-gmac
         - rockchip,rk3368-gmac
+        - rockchip,rk3576-gmac
         - rockchip,rk3588-gmac
         - rockchip,rk3399-gmac
         - rockchip,rv1108-gmac
-- 
cgit v1.3-3-g829e


From f9cc9997cba9defaf00c8e70d25f88271cbd6d4d Mon Sep 17 00:00:00 2001
From: David Wu <david.wu@rock-chips.com>
Date: Fri, 23 Aug 2024 10:11:15 -0400
Subject: ethernet: stmmac: dwmac-rk: Add GMAC support for RK3576

Add constants and callback functions for the dwmac on RK3576 soc.

Signed-off-by: David Wu <david.wu@rock-chips.com>
[rebase, extracted bindings]
Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240823141318.51201-4-detlev.casanova@collabora.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 156 +++++++++++++++++++++++++
 1 file changed, 156 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 9cf0aa58d13b..50073bdade46 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1116,6 +1116,161 @@ static const struct rk_gmac_ops rk3568_ops = {
 	},
 };
 
+/* VCCIO0_1_3_IOC */
+#define RK3576_VCCIO0_1_3_IOC_CON2		0X6408
+#define RK3576_VCCIO0_1_3_IOC_CON3		0X640c
+#define RK3576_VCCIO0_1_3_IOC_CON4		0X6410
+#define RK3576_VCCIO0_1_3_IOC_CON5		0X6414
+
+#define RK3576_GMAC_RXCLK_DLY_ENABLE		GRF_BIT(15)
+#define RK3576_GMAC_RXCLK_DLY_DISABLE		GRF_CLR_BIT(15)
+#define RK3576_GMAC_TXCLK_DLY_ENABLE		GRF_BIT(7)
+#define RK3576_GMAC_TXCLK_DLY_DISABLE		GRF_CLR_BIT(7)
+
+#define RK3576_GMAC_CLK_RX_DL_CFG(val)		HIWORD_UPDATE(val, 0x7F, 8)
+#define RK3576_GMAC_CLK_TX_DL_CFG(val)		HIWORD_UPDATE(val, 0x7F, 0)
+
+/* SDGMAC_GRF */
+#define RK3576_GRF_GMAC_CON0			0X0020
+#define RK3576_GRF_GMAC_CON1			0X0024
+
+#define RK3576_GMAC_RMII_MODE			GRF_BIT(3)
+#define RK3576_GMAC_RGMII_MODE			GRF_CLR_BIT(3)
+
+#define RK3576_GMAC_CLK_SELECT_IO		GRF_BIT(7)
+#define RK3576_GMAC_CLK_SELECT_CRU		GRF_CLR_BIT(7)
+
+#define RK3576_GMAC_CLK_RMII_DIV2		GRF_BIT(5)
+#define RK3576_GMAC_CLK_RMII_DIV20		GRF_CLR_BIT(5)
+
+#define RK3576_GMAC_CLK_RGMII_DIV1		\
+			(GRF_CLR_BIT(6) | GRF_CLR_BIT(5))
+#define RK3576_GMAC_CLK_RGMII_DIV5		\
+			(GRF_BIT(6) | GRF_BIT(5))
+#define RK3576_GMAC_CLK_RGMII_DIV50		\
+			(GRF_BIT(6) | GRF_CLR_BIT(5))
+
+#define RK3576_GMAC_CLK_RMII_GATE		GRF_BIT(4)
+#define RK3576_GMAC_CLK_RMII_NOGATE		GRF_CLR_BIT(4)
+
+static void rk3576_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	unsigned int offset_con;
+
+	if (IS_ERR(bsp_priv->grf) || IS_ERR(bsp_priv->php_grf)) {
+		dev_err(dev, "Missing rockchip,grf or rockchip,php-grf property\n");
+		return;
+	}
+
+	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
+					 RK3576_GRF_GMAC_CON0;
+
+	regmap_write(bsp_priv->grf, offset_con, RK3576_GMAC_RGMII_MODE);
+
+	offset_con = bsp_priv->id == 1 ? RK3576_VCCIO0_1_3_IOC_CON4 :
+					 RK3576_VCCIO0_1_3_IOC_CON2;
+
+	/* m0 && m1 delay enabled */
+	regmap_write(bsp_priv->php_grf, offset_con,
+		     DELAY_ENABLE(RK3576, tx_delay, rx_delay));
+	regmap_write(bsp_priv->php_grf, offset_con + 0x4,
+		     DELAY_ENABLE(RK3576, tx_delay, rx_delay));
+
+	/* m0 && m1 delay value */
+	regmap_write(bsp_priv->php_grf, offset_con,
+		     RK3576_GMAC_CLK_TX_DL_CFG(tx_delay) |
+		     RK3576_GMAC_CLK_RX_DL_CFG(rx_delay));
+	regmap_write(bsp_priv->php_grf, offset_con + 0x4,
+		     RK3576_GMAC_CLK_TX_DL_CFG(tx_delay) |
+		     RK3576_GMAC_CLK_RX_DL_CFG(rx_delay));
+}
+
+static void rk3576_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	unsigned int offset_con;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
+					 RK3576_GRF_GMAC_CON0;
+
+	regmap_write(bsp_priv->grf, offset_con, RK3576_GMAC_RMII_MODE);
+}
+
+static void rk3576_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	unsigned int val = 0, offset_con;
+
+	switch (speed) {
+	case 10:
+		if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
+			val = RK3576_GMAC_CLK_RMII_DIV20;
+		else
+			val = RK3576_GMAC_CLK_RGMII_DIV50;
+		break;
+	case 100:
+		if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
+			val = RK3576_GMAC_CLK_RMII_DIV2;
+		else
+			val = RK3576_GMAC_CLK_RGMII_DIV5;
+		break;
+	case 1000:
+		if (bsp_priv->phy_iface != PHY_INTERFACE_MODE_RMII)
+			val = RK3576_GMAC_CLK_RGMII_DIV1;
+		else
+			goto err;
+		break;
+	default:
+		goto err;
+	}
+
+	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
+					 RK3576_GRF_GMAC_CON0;
+
+	regmap_write(bsp_priv->grf, offset_con, val);
+
+	return;
+err:
+	dev_err(dev, "unknown speed value for GMAC speed=%d", speed);
+}
+
+static void rk3576_set_clock_selection(struct rk_priv_data *bsp_priv, bool input,
+				       bool enable)
+{
+	unsigned int val = input ? RK3576_GMAC_CLK_SELECT_IO :
+				   RK3576_GMAC_CLK_SELECT_CRU;
+	unsigned int offset_con;
+
+	val |= enable ? RK3576_GMAC_CLK_RMII_NOGATE :
+			RK3576_GMAC_CLK_RMII_GATE;
+
+	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
+					 RK3576_GRF_GMAC_CON0;
+
+	regmap_write(bsp_priv->grf, offset_con, val);
+}
+
+static const struct rk_gmac_ops rk3576_ops = {
+	.set_to_rgmii = rk3576_set_to_rgmii,
+	.set_to_rmii = rk3576_set_to_rmii,
+	.set_rgmii_speed = rk3576_set_gmac_speed,
+	.set_rmii_speed = rk3576_set_gmac_speed,
+	.set_clock_selection = rk3576_set_clock_selection,
+	.regs_valid = true,
+	.regs = {
+		0x2a220000, /* gmac0 */
+		0x2a230000, /* gmac1 */
+		0x0, /* sentinel */
+	},
+};
+
 /* sys_grf */
 #define RK3588_GRF_GMAC_CON7			0X031c
 #define RK3588_GRF_GMAC_CON8			0X0320
@@ -1908,6 +2063,7 @@ static const struct of_device_id rk_gmac_dwmac_match[] = {
 	{ .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops },
 	{ .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops },
 	{ .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops },
+	{ .compatible = "rockchip,rk3576-gmac", .data = &rk3576_ops },
 	{ .compatible = "rockchip,rk3588-gmac", .data = &rk3588_ops },
 	{ .compatible = "rockchip,rv1108-gmac", .data = &rv1108_ops },
 	{ .compatible = "rockchip,rv1126-gmac", .data = &rv1126_ops },
-- 
cgit v1.3-3-g829e


From 73d33bd063c4cfef3db17f9bec3d202928ed8631 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Fri, 23 Aug 2024 15:22:57 +0100
Subject: l2tp: avoid using drain_workqueue in l2tp_pre_exit_net

Recent commit fc7ec7f554d7 ("l2tp: delete sessions using work queue")
incorrectly uses drain_workqueue. The use of drain_workqueue in
l2tp_pre_exit_net is flawed because the workqueue is shared by all
nets and it is therefore possible for new work items to be queued
for other nets while drain_workqueue runs.

Instead of using drain_workqueue, use __flush_workqueue twice. The
first one will run all tunnel delete work items and any work already
queued. When tunnel delete work items are run, they may queue
new session delete work items, which the second __flush_workqueue will
run.

In l2tp_exit_net, warn if any of the net's idr lists are not empty.

Fixes: fc7ec7f554d7 ("l2tp: delete sessions using work queue")
Signed-off-by: James Chapman <jchapman@katalix.com>
Link: https://patch.msgid.link/20240823142257.692667-1-jchapman@katalix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/l2tp/l2tp_core.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index df73c35363cb..32102d1ed4cd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1859,14 +1859,14 @@ static __net_exit void l2tp_pre_exit_net(struct net *net)
 	rcu_read_unlock_bh();
 
 	if (l2tp_wq) {
-		/* ensure that all TUNNEL_DELETE work items are run before
-		 * draining the work queue since TUNNEL_DELETE requests may
-		 * queue SESSION_DELETE work items for each session in the
-		 * tunnel. drain_workqueue may otherwise warn if SESSION_DELETE
-		 * requests are queued while the work queue is being drained.
+		/* Run all TUNNEL_DELETE work items just queued. */
+		__flush_workqueue(l2tp_wq);
+
+		/* Each TUNNEL_DELETE work item will queue a SESSION_DELETE
+		 * work item for each session in the tunnel. Flush the
+		 * workqueue again to process these.
 		 */
 		__flush_workqueue(l2tp_wq);
-		drain_workqueue(l2tp_wq);
 	}
 }
 
@@ -1874,8 +1874,11 @@ static __net_exit void l2tp_exit_net(struct net *net)
 {
 	struct l2tp_net *pn = l2tp_pernet(net);
 
+	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v2_session_idr));
 	idr_destroy(&pn->l2tp_v2_session_idr);
+	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v3_session_idr));
 	idr_destroy(&pn->l2tp_v3_session_idr);
+	WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_tunnel_idr));
 	idr_destroy(&pn->l2tp_tunnel_idr);
 }
 
-- 
cgit v1.3-3-g829e


From 79504a47339cd9a1574d974869aecaba838e1213 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:51 +0100
Subject: selftests/net: Clean-up double assignment

Correct copy'n'paste typo: the previous line already initialises get_all
to 1.

Reported-by: Nassiri, Mohammad <mnassiri@ciena.com>
Closes: https://lore.kernel.org/all/DM6PR04MB4202BC58A9FD5BDD24A16E8EC56F2@DM6PR04MB4202.namprd04.prod.outlook.com/
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-1-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/lib/sock.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 15aeb0963058..0ffda966c677 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -379,7 +379,6 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
 
 	key_dump[0].nkeys = nr_keys;
 	key_dump[0].get_all = 1;
-	key_dump[0].get_all = 1;
 	err = getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS,
 			 key_dump, &key_dump_sz);
 	if (err) {
-- 
cgit v1.3-3-g829e


From 7053e788ded5f8ec589e4507d764d6a894780d6c Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:52 +0100
Subject: selftests/net: Provide test_snprintf() helper

Instead of pre-allocating a fixed-sized buffer of TEST_MSG_BUFFER_SIZE
and printing into it, call vsnprintf() with str = NULL, which will
return the needed size of the buffer. This hack is documented in
man 3 vsnprintf.

Essentially, in C++ terms, it re-invents std::stringstream, which is
going to be used to print different tracing paths and formatted strings.
Use it straight away in __test_print() - which is thread-safe version of
printing in selftests.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-2-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/lib/aolib.h | 61 +++++++++++++++++++++-----
 1 file changed, 51 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index fbc7f6111815..78466863435f 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -37,17 +37,58 @@ extern void __test_xfail(const char *buf);
 extern void __test_error(const char *buf);
 extern void __test_skip(const char *buf);
 
-__attribute__((__format__(__printf__, 2, 3)))
-static inline void __test_print(void (*fn)(const char *), const char *fmt, ...)
+static inline char *test_snprintf(const char *fmt, va_list vargs)
 {
-#define TEST_MSG_BUFFER_SIZE 4096
-	char buf[TEST_MSG_BUFFER_SIZE];
-	va_list arg;
-
-	va_start(arg, fmt);
-	vsnprintf(buf, sizeof(buf), fmt, arg);
-	va_end(arg);
-	fn(buf);
+	char *ret = NULL;
+	size_t size = 0;
+	va_list tmp;
+	int n = 0;
+
+	va_copy(tmp, vargs);
+	n = vsnprintf(ret, size, fmt, tmp);
+	if (n < 0)
+		return NULL;
+
+	size = n + 1;
+	ret = malloc(size);
+	if (!ret)
+		return NULL;
+
+	n = vsnprintf(ret, size, fmt, vargs);
+	if (n < 0 || n > size - 1) {
+		free(ret);
+		return NULL;
+	}
+	return ret;
+}
+
+static __printf(1, 2) inline char *test_sprintf(const char *fmt, ...)
+{
+	va_list vargs;
+	char *ret;
+
+	va_start(vargs, fmt);
+	ret = test_snprintf(fmt, vargs);
+	va_end(vargs);
+
+	return ret;
+}
+
+static __printf(2, 3) inline void __test_print(void (*fn)(const char *),
+					       const char *fmt, ...)
+{
+	va_list vargs;
+	char *msg;
+
+	va_start(vargs, fmt);
+	msg = test_snprintf(fmt, vargs);
+	va_end(vargs);
+
+	if (!msg)
+		return;
+
+	fn(msg);
+	free(msg);
 }
 
 #define test_print(fmt, ...)						\
-- 
cgit v1.3-3-g829e


From bc2468f98221a194769cac80051da6b86cc39c2f Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:53 +0100
Subject: selftests/net: Be consistent in kconfig checks

Most of the functions in tcp-ao lib/ return negative errno or -1 in case
of a failure. That creates inconsistencies in lib/kconfig, which saves
what was the error code. As well as the uninitialized kconfig value is
-1, which also may be the result of a check.

Define KCONFIG_UNKNOWN and save negative return code, rather than
libc-style errno.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-3-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/lib/kconfig.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
index f279ffc3843b..3bf4a7e4b3c9 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
@@ -6,7 +6,7 @@
 #include "aolib.h"
 
 struct kconfig_t {
-	int _errno;		/* the returned error if not supported */
+	int _error;		/* negative errno if not supported */
 	int (*check_kconfig)(int *error);
 };
 
@@ -62,7 +62,7 @@ static int has_tcp_ao(int *err)
 	memcpy(&tmp.addr, &addr, sizeof(addr));
 	*err = 0;
 	if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp)) < 0) {
-		*err = errno;
+		*err = -errno;
 		if (errno != ENOPROTOOPT)
 			ret = -errno;
 	}
@@ -87,7 +87,7 @@ static int has_tcp_md5(int *err)
 	 */
 	*err = 0;
 	if (test_set_md5(sk, addr_any, 0, -1, DEFAULT_TEST_PASSWORD)) {
-		*err = errno;
+		*err = -errno;
 		if (errno != ENOPROTOOPT && errno == ENOMEM) {
 			test_print("setsockopt(TCP_MD5SIG_EXT): %m");
 			ret = -errno;
@@ -116,13 +116,14 @@ static int has_vrfs(int *err)
 	return ret;
 }
 
+#define KCONFIG_UNKNOWN			1
 static pthread_mutex_t kconfig_lock = PTHREAD_MUTEX_INITIALIZER;
 static struct kconfig_t kconfig[__KCONFIG_LAST__] = {
-	{ -1, has_net_ns },
-	{ -1, has_veth },
-	{ -1, has_tcp_ao },
-	{ -1, has_tcp_md5 },
-	{ -1, has_vrfs },
+	{ KCONFIG_UNKNOWN, has_net_ns },
+	{ KCONFIG_UNKNOWN, has_veth },
+	{ KCONFIG_UNKNOWN, has_tcp_ao },
+	{ KCONFIG_UNKNOWN, has_tcp_md5 },
+	{ KCONFIG_UNKNOWN, has_vrfs },
 };
 
 const char *tests_skip_reason[__KCONFIG_LAST__] = {
@@ -138,11 +139,11 @@ bool kernel_config_has(enum test_needs_kconfig k)
 	bool ret;
 
 	pthread_mutex_lock(&kconfig_lock);
-	if (kconfig[k]._errno == -1) {
-		if (kconfig[k].check_kconfig(&kconfig[k]._errno))
+	if (kconfig[k]._error == KCONFIG_UNKNOWN) {
+		if (kconfig[k].check_kconfig(&kconfig[k]._error))
 			test_error("Failed to initialize kconfig %u", k);
 	}
-	ret = kconfig[k]._errno == 0;
+	ret = kconfig[k]._error == 0;
 	pthread_mutex_unlock(&kconfig_lock);
 	return ret;
 }
-- 
cgit v1.3-3-g829e


From 8acb1806e8c2846ae619f500a3229a325c3304f5 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:54 +0100
Subject: selftests/net: Open /proc/thread-self in open_netns()

It turns to be that open_netns() is called rarely from the child-thread
and more often from parent-thread. Yet, on initialization of kconfig
checks, either of threads may reach kconfig_lock mutex first.
VRF-related checks do create a temporary ksft-check VRF in
an unshare()'d namespace and than setns() back to the original.
As original was opened from "/proc/self/ns/net", it's valid for
thread-leader (parent), but it's invalid for the child, resulting
in the following failure on tests that check has_vrfs() support:
> # ok 54 TCP-AO required on socket + TCP-MD5 key: prefailed as expected: Key was rejected by service
> # not ok 55 # error 381[unsigned-md5.c:24] Failed to add a VRF: -17
> # not ok 56 # error 383[unsigned-md5.c:33] Failed to add a route to VRF: -22: Key was rejected by service
> not ok 1 selftests: net/tcp_ao: unsigned-md5_ipv6 # exit=1

Use "/proc/thread-self/ns/net" which is valid for any thread.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-4-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/lib/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c
index e408b9243b2c..d5212ffe9489 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/setup.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c
@@ -111,7 +111,7 @@ static void sig_int(int signo)
 
 int open_netns(void)
 {
-	const char *netns_path = "/proc/self/ns/net";
+	const char *netns_path = "/proc/thread-self/ns/net";
 	int fd;
 
 	fd = open(netns_path, O_RDONLY);
-- 
cgit v1.3-3-g829e


From a9e1693406f96f3739611dd08518c9eda3acecfd Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:55 +0100
Subject: selftests/net: Don't forget to close nsfd after switch_save_ns()

The switch_save_ns() helper suppose to help switching to another
namespace for some action and to return back to original namespace.

The fd should be closed.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-5-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/lib/setup.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c
index d5212ffe9489..86a4f6e20450 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/setup.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c
@@ -142,6 +142,13 @@ int switch_save_ns(int new_ns)
 	return ret;
 }
 
+void switch_close_ns(int fd)
+{
+	if (setns(fd, CLONE_NEWNET))
+		test_error("setns()");
+	close(fd);
+}
+
 static int nsfd_outside	= -1;
 static int nsfd_parent	= -1;
 static int nsfd_child	= -1;
@@ -296,7 +303,7 @@ static bool is_optmem_namespaced(void)
 		int old_ns = switch_save_ns(nsfd_child);
 
 		optmem_ns = !access(optmem_file, F_OK);
-		switch_ns(old_ns);
+		switch_close_ns(old_ns);
 	}
 	return !!optmem_ns;
 }
@@ -317,7 +324,7 @@ size_t test_get_optmem(void)
 		test_error("can't read from %s", optmem_file);
 	fclose(foptmem);
 	if (!is_optmem_namespaced())
-		switch_ns(old_ns);
+		switch_close_ns(old_ns);
 	return ret;
 }
 
@@ -339,7 +346,7 @@ static void __test_set_optmem(size_t new, size_t *old)
 		test_error("can't write %zu to %s", new, optmem_file);
 	fclose(foptmem);
 	if (!is_optmem_namespaced())
-		switch_ns(old_ns);
+		switch_close_ns(old_ns);
 }
 
 static void test_revert_optmem(void)
-- 
cgit v1.3-3-g829e


From 1c69e1f433990a81b5a5d415d8892ebcaacb985b Mon Sep 17 00:00:00 2001
From: Mohammad Nassiri <mnassiri@ciena.com>
Date: Fri, 23 Aug 2024 23:04:56 +0100
Subject: selftests/tcp_ao: Fix printing format for uint64_t

It's not safe to use '%zu' specifier for printing uint64_t on 32-bit
systems. For uint64_t, we should use the 'PRIu64' macro from
the inttypes.h library. This ensures that the uint64_t is printed
correctly from the selftests regardless of the system architecture.

Signed-off-by: Mohammad Nassiri <mnassiri@ciena.com>
[Added missing spaces in fail/ok messages and uint64_t cast in
 setsockopt-closed, as otherwise it was giving warnings on 64bit.
 And carried it to netdev ml]
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-6-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/connect-deny.c      |  4 ++--
 tools/testing/selftests/net/tcp_ao/connect.c           |  4 ++--
 tools/testing/selftests/net/tcp_ao/restore.c           |  8 ++++----
 tools/testing/selftests/net/tcp_ao/self-connect.c      |  4 ++--
 tools/testing/selftests/net/tcp_ao/seq-ext.c           | 12 ++++++------
 tools/testing/selftests/net/tcp_ao/setsockopt-closed.c |  4 ++--
 tools/testing/selftests/net/tcp_ao/unsigned-md5.c      |  4 ++--
 7 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index 185a2f6e5ff3..5691f3d00603 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -84,10 +84,10 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 	after_cnt = netstat_get_one(cnt_name, NULL);
 
 	if (after_cnt <= before_cnt) {
-		test_fail("%s: %s counter did not increase: %zu <= %zu",
+		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
 				tst_name, cnt_name, after_cnt, before_cnt);
 	} else {
-		test_ok("%s: counter %s increased %zu => %zu",
+		test_ok("%s: counter %s increased %" PRIu64  " => %" PRIu64,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 
diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
index 81653b47f303..9eecc4a1072e 100644
--- a/tools/testing/selftests/net/tcp_ao/connect.c
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -67,14 +67,14 @@ static void *client_fn(void *arg)
 	netstat_free(ns_after);
 
 	if (nr_packets > (after_aogood - before_aogood)) {
-		test_fail("TCPAOGood counter mismatch: %zu > (%zu - %zu)",
+		test_fail("TCPAOGood counter mismatch: %zu > (%" PRIu64 " - %" PRIu64 ")",
 				nr_packets, after_aogood, before_aogood);
 		return NULL;
 	}
 	if (test_tcp_ao_counters_cmp("connect", &ao1, &ao2, TEST_CNT_GOOD))
 		return NULL;
 
-	test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %" PRIu64,
+	test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %zu",
 			before_aogood, ao1.ao_info_pkt_good,
 			ao1.key_cnts[0].pkt_good,
 			after_aogood, ao2.ao_info_pkt_good,
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index 8fdc808df325..7b91d7fde2bc 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -71,10 +71,10 @@ static void try_server_run(const char *tst_name, unsigned int port,
 	test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
 
 	if (after_cnt <= before_cnt) {
-		test_fail("%s: %s counter did not increase: %zu <= %zu",
+		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
 				tst_name, cnt_name, after_cnt, before_cnt);
 	} else {
-		test_ok("%s: counter %s increased %zu => %zu",
+		test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 
@@ -183,10 +183,10 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 	test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
 
 	if (after_cnt <= before_cnt) {
-		test_fail("%s: %s counter did not increase: %zu <= %zu",
+		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
 				tst_name, cnt_name, after_cnt, before_cnt);
 	} else {
-		test_ok("%s: counter %s increased %zu => %zu",
+		test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 	synchronize_threads(); /* 3: verified => closed */
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index a5698b0a3718..e56931d38e06 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -87,7 +87,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 	netstat_free(ns_after);
 
 	if (after_aogood <= before_aogood) {
-		test_fail("%s: TCPAOGood counter mismatch: %zu <= %zu",
+		test_fail("%s: TCPAOGood counter mismatch: %" PRIu64 " <= %" PRIu64,
 			  tst, after_aogood, before_aogood);
 		close(sk);
 		return;
@@ -148,7 +148,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 	netstat_free(ns_after);
 	close(sk);
 	if (after_aogood <= before_aogood) {
-		test_fail("%s: TCPAOGood counter mismatch: %zu <= %zu",
+		test_fail("%s: TCPAOGood counter mismatch: %" PRIu64 " <= %" PRIu64,
 			  tst, after_aogood, before_aogood);
 		return;
 	}
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index ad4e77d6823e..9c7dde7fd776 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -134,15 +134,15 @@ static void *server_fn(void *arg)
 	test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
 
 	if (after_good <= before_good) {
-		test_fail("TCPAOGood counter did not increase: %zu <= %zu",
+		test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
 			  after_good, before_good);
 	} else {
-		test_ok("TCPAOGood counter increased %zu => %zu",
+		test_ok("TCPAOGood counter increased %" PRIu64 " => %" PRIu64,
 			before_good, after_good);
 	}
 	after_bad = netstat_get_one("TCPAOBad", NULL);
 	if (after_bad)
-		test_fail("TCPAOBad counter is non-zero: %zu", after_bad);
+		test_fail("TCPAOBad counter is non-zero: %" PRIu64, after_bad);
 	else
 		test_ok("TCPAOBad counter didn't increase");
 	test_enable_repair(sk);
@@ -219,15 +219,15 @@ static void *client_fn(void *arg)
 	test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
 
 	if (after_good <= before_good) {
-		test_fail("TCPAOGood counter did not increase: %zu <= %zu",
+		test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
 			  after_good, before_good);
 	} else {
-		test_ok("TCPAOGood counter increased %zu => %zu",
+		test_ok("TCPAOGood counter increased %" PRIu64 " => %" PRIu64,
 			before_good, after_good);
 	}
 	after_bad = netstat_get_one("TCPAOBad", NULL);
 	if (after_bad)
-		test_fail("TCPAOBad counter is non-zero: %zu", after_bad);
+		test_fail("TCPAOBad counter is non-zero: %" PRIu64, after_bad);
 	else
 		test_ok("TCPAOBad counter didn't increase");
 
diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
index 517930f9721b..5eee826c37aa 100644
--- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
+++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
@@ -30,8 +30,8 @@ static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info,
 #define __cmp_ao(member)							\
 do {										\
 	if (info->member != tmp.member) {					\
-		test_fail("%s: getsockopt(): " __stringify(member) " %zu != %zu",	\
-			  tst, (size_t)info->member, (size_t)tmp.member);	\
+		test_fail("%s: getsockopt(): " __stringify(member) " %" PRIu64 " != %" PRIu64,	\
+			  tst, (uint64_t)info->member, (uint64_t)tmp.member);	\
 		return;								\
 	}									\
 } while(0)
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index 6b59a652159f..ec2848036341 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -100,10 +100,10 @@ static void try_accept(const char *tst_name, unsigned int port,
 	after_cnt = netstat_get_one(cnt_name, NULL);
 
 	if (after_cnt <= before_cnt) {
-		test_fail("%s: %s counter did not increase: %zu <= %zu",
+		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
 				tst_name, cnt_name, after_cnt, before_cnt);
 	} else {
-		test_ok("%s: counter %s increased %zu => %zu",
+		test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 	if (ao_addr)
-- 
cgit v1.3-3-g829e


From 044e037051252ca8df07e1355bf4d7964645a6e8 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:57 +0100
Subject: selftests/net: Synchronize client/server before counters checks

On tests that are expecting failure the timeout value is
TEST_RETRANSMIT_SEC == 1 second. Which is big enough for most of devices
under tests. But on a particularly slow machine/VM, 1 second might be
not enough for another thread to be scheduled and attempt to connect().
It is not a problem for tests that expect connect() to succeed as
the timeout value for them (TEST_TIMEOUT_SEC) is intentionally bigger.

One obvious way to solve this would be to increase TEST_RETRANSMIT_SEC.
But as all tests would increase the timeouts, that's going to sum up.

But here is less obvious way that keeps timeouts for expected connect()
failures low: just synchronize the two threads, which will assure that
before counter checks the other thread got a chance to run and timeout
on connect(). The expected increase of the related counter for listen()
socket will yet test the expected failure.

Never happens on my machine, but I suppose the majority of netdev's
connect-deny-* flakes [1] are caused by this.

Prevents the following testing issue:
> # selftests: net/tcp_ao: connect-deny_ipv6
> # 1..21
> # # 462[lib/setup.c:243] rand seed 1720905426
> # TAP version 13
> # ok 1 Non-AO server + AO client
> # not ok 2 Non-AO server + AO client: TCPAOKeyNotFound counter did not increase: 0 <= 0
> # ok 3 AO server + Non-AO client
> # ok 4 AO server + Non-AO client: counter TCPAORequired increased 0 => 1
...

[1]: https://netdev-3.bots.linux.dev/vmksft-tcp-ao/results/681741/6-connect-deny-ipv6/stdout
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-7-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/connect-deny.c | 3 +++
 tools/testing/selftests/net/tcp_ao/restore.c      | 6 ++++--
 tools/testing/selftests/net/tcp_ao/seq-ext.c      | 6 ++++--
 tools/testing/selftests/net/tcp_ao/unsigned-md5.c | 3 +++
 4 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index 5691f3d00603..166ad4549ef2 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -71,10 +71,12 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 		}
 	}
 
+	synchronize_threads(); /* before counter checks */
 	if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt2))
 		test_error("test_get_tcp_ao_counters()");
 
 	close(lsk);
+
 	if (pwd)
 		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 
@@ -180,6 +182,7 @@ static void try_connect(const char *tst_name, unsigned int port,
 	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
 	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
 
+	synchronize_threads(); /* before counter checks */
 	if (ret < 0) {
 		if (fault(KEYREJECT) && ret == -EKEYREJECTED) {
 			test_ok("%s: connect() was prevented", tst_name);
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index 7b91d7fde2bc..f6ea2190f43d 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -64,6 +64,7 @@ static void try_server_run(const char *tst_name, unsigned int port,
 		else
 			test_ok("%s: server alive", tst_name);
 	}
+	synchronize_threads(); /* 3: counters checks */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 	after_cnt = netstat_get_one(cnt_name, NULL);
@@ -82,7 +83,7 @@ static void try_server_run(const char *tst_name, unsigned int port,
 	 * Before close() as that will send FIN and move the peer in TCP_CLOSE
 	 * and that will prevent reading AO counters from the peer's socket.
 	 */
-	synchronize_threads(); /* 3: verified => closed */
+	synchronize_threads(); /* 4: verified => closed */
 out:
 	close(sk);
 }
@@ -176,6 +177,7 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 		else
 			test_ok("%s: post-migrate connection is alive", tst_name);
 	}
+	synchronize_threads(); /* 3: counters checks */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 	after_cnt = netstat_get_one(cnt_name, NULL);
@@ -189,7 +191,7 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 		test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
-	synchronize_threads(); /* 3: verified => closed */
+	synchronize_threads(); /* 4: verified => closed */
 	close(sk);
 }
 
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index 9c7dde7fd776..885866cc193c 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -116,7 +116,7 @@ static void *server_fn(void *arg)
 	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
 			     client_new_port, &ao1);
 
-	synchronize_threads(); /* 5: verify counters during SEQ-number rollover */
+	synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */
 	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
 	if (bytes != quota) {
 		if (bytes > 0)
@@ -127,6 +127,7 @@ static void *server_fn(void *arg)
 		test_ok("server alive");
 	}
 
+	synchronize_threads(); /* 6: verify counters after SEQ-number rollover */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 	after_good = netstat_get_one("TCPAOGood", NULL);
@@ -206,12 +207,13 @@ static void *client_fn(void *arg)
 	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
 			     test_server_port + 1, &ao1);
 
-	synchronize_threads(); /* 5: verify counters during SEQ-number rollover */
+	synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("post-migrate verify failed");
 	else
 		test_ok("post-migrate connection alive");
 
+	synchronize_threads(); /* 5: verify counters after SEQ-number rollover */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 	after_good = netstat_get_one("TCPAOGood", NULL);
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index ec2848036341..02346b58efbd 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -70,6 +70,7 @@ static void try_accept(const char *tst_name, unsigned int port,
 
 	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
 	err = test_wait_fd(lsk, timeout, 0);
+	synchronize_threads(); /* connect()/accept() timeouts */
 	if (err == -ETIMEDOUT) {
 		if (!fault(TIMEOUT))
 			test_fail("timed out for accept()");
@@ -283,6 +284,7 @@ static void try_connect(const char *tst_name, unsigned int port,
 	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
 	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
 
+	synchronize_threads(); /* connect()/accept() timeouts */
 	if (ret < 0) {
 		if (fault(KEYREJECT) && ret == -EKEYREJECTED)
 			test_ok("%s: connect() was prevented", tst_name);
@@ -451,6 +453,7 @@ static void try_to_add(const char *tst_name, unsigned int port,
 	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
 	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
 
+	synchronize_threads(); /* connect()/accept() timeouts */
 	if (ret <= 0) {
 		test_error("%s: connect() returned %d", tst_name, ret);
 		goto out;
-- 
cgit v1.3-3-g829e


From 586d87021f224b0434372f5b4418216e29b0a544 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Fri, 23 Aug 2024 23:04:58 +0100
Subject: selftests/net: Add trace events matching to tcp_ao

Setup trace points, add a new ftrace instance in order to not interfere
with the rest of the system, filtering by net namespace cookies.
Raise a new background thread that parses trace_pipe, matches them with
the list of expected events.

Wiring up trace events to selftests provides another insight if there is
anything unexpected happining in the tcp-ao code (i.e. key rotation when
it's not expected).

Note: in real programs libtraceevent should be used instead of this
manual labor of setting ftrace up and parsing. I'm not using it here
as I don't want to have an .so library dependency that one would have to
bring into VM or DUT (Device Under Test). Please, don't copy it over
into any real world programs, that aren't tests.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Link: https://patch.msgid.link/20240823-tcp-ao-selftests-upd-6-12-v4-8-05623636fe8c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tcp_ao/Makefile        |   3 +-
 tools/testing/selftests/net/tcp_ao/bench-lookups.c |   2 +-
 tools/testing/selftests/net/tcp_ao/config          |   1 +
 tools/testing/selftests/net/tcp_ao/connect-deny.c  |  18 +-
 tools/testing/selftests/net/tcp_ao/connect.c       |   2 +-
 tools/testing/selftests/net/tcp_ao/icmps-discard.c |   2 +-
 .../testing/selftests/net/tcp_ao/key-management.c  |  18 +-
 tools/testing/selftests/net/tcp_ao/lib/aolib.h     | 119 +++++
 .../testing/selftests/net/tcp_ao/lib/ftrace-tcp.c  | 559 +++++++++++++++++++++
 tools/testing/selftests/net/tcp_ao/lib/ftrace.c    | 543 ++++++++++++++++++++
 tools/testing/selftests/net/tcp_ao/lib/kconfig.c   |   8 +
 tools/testing/selftests/net/tcp_ao/lib/setup.c     |   2 +-
 tools/testing/selftests/net/tcp_ao/lib/utils.c     |  26 +
 tools/testing/selftests/net/tcp_ao/restore.c       |  16 +-
 tools/testing/selftests/net/tcp_ao/rst.c           |   2 +-
 tools/testing/selftests/net/tcp_ao/self-connect.c  |  15 +-
 tools/testing/selftests/net/tcp_ao/seq-ext.c       |  10 +-
 .../selftests/net/tcp_ao/setsockopt-closed.c       |   2 +-
 tools/testing/selftests/net/tcp_ao/unsigned-md5.c  |  28 +-
 19 files changed, 1358 insertions(+), 18 deletions(-)
 create mode 100644 tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
 create mode 100644 tools/testing/selftests/net/tcp_ao/lib/ftrace.c

diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile
index bd88b90b902b..5b0205c70c39 100644
--- a/tools/testing/selftests/net/tcp_ao/Makefile
+++ b/tools/testing/selftests/net/tcp_ao/Makefile
@@ -31,7 +31,8 @@ CFLAGS	+= $(KHDR_INCLUDES)
 CFLAGS	+= -iquote ./lib/ -I ../../../../include/
 
 # Library
-LIBSRC	:= kconfig.c netlink.c proc.c repair.c setup.c sock.c utils.c
+LIBSRC	:= ftrace.c ftrace-tcp.c kconfig.c netlink.c
+LIBSRC	+= proc.c repair.c setup.c sock.c utils.c
 LIBOBJ	:= $(LIBSRC:%.c=$(LIBDIR)/%.o)
 EXTRA_CLEAN += $(LIBOBJ) $(LIB)
 
diff --git a/tools/testing/selftests/net/tcp_ao/bench-lookups.c b/tools/testing/selftests/net/tcp_ao/bench-lookups.c
index a1e6e007c291..6736484996a3 100644
--- a/tools/testing/selftests/net/tcp_ao/bench-lookups.c
+++ b/tools/testing/selftests/net/tcp_ao/bench-lookups.c
@@ -355,6 +355,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(30, server_fn, client_fn);
+	test_init(31, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config
index d3277a9de987..3605e38711cb 100644
--- a/tools/testing/selftests/net/tcp_ao/config
+++ b/tools/testing/selftests/net/tcp_ao/config
@@ -7,4 +7,5 @@ CONFIG_NET_L3_MASTER_DEV=y
 CONFIG_NET_VRF=y
 CONFIG_TCP_AO=y
 CONFIG_TCP_MD5SIG=y
+CONFIG_TRACEPOINTS=y
 CONFIG_VETH=m
diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index 166ad4549ef2..d418162d335f 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -215,30 +215,44 @@ out:
 
 static void *client_fn(void *arg)
 {
-	union tcp_addr wrong_addr, network_addr;
+	union tcp_addr wrong_addr, network_addr, addr_any = {};
 	unsigned int port = test_server_port;
 
 	if (inet_pton(TEST_FAMILY, TEST_WRONG_IP, &wrong_addr) != 1)
 		test_error("Can't convert ip address %s", TEST_WRONG_IP);
 
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("Non-AO server + AO client", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	trace_hash_event_expect(TCP_HASH_AO_REQUIRED, this_ip_addr, this_ip_dest,
+				-1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO server + Non-AO client", port++, NULL,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("Wrong password", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	trace_ao_event_sk_expect(TCP_AO_SYNACK_NO_KEY, this_ip_dest, addr_any,
+				 port, 0, 100, 100);
 	try_connect("Wrong snd id", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	trace_ao_event_expect(TCP_AO_WRONG_MACLEN, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("Different maclen", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("Server: Wrong addr", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
@@ -262,6 +276,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(21, server_fn, client_fn);
+	test_init(22, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
index 9eecc4a1072e..f1d8d29e393f 100644
--- a/tools/testing/selftests/net/tcp_ao/connect.c
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -85,6 +85,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(1, server_fn, client_fn);
+	test_init(2, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
index d69bcba3c929..a1614f0d8c44 100644
--- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -444,6 +444,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(3, server_fn, client_fn);
+	test_init(4, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index 24e62120b792..d4385b52c10b 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -965,7 +965,7 @@ static void end_client(const char *tst_name, int sk, unsigned int nr_keys,
 	synchronize_threads(); /* 5: counters */
 }
 
-static void try_unmatched_keys(int sk, int *rnext_index)
+static void try_unmatched_keys(int sk, int *rnext_index, unsigned int port)
 {
 	struct test_key *key;
 	unsigned int i = 0;
@@ -1013,6 +1013,9 @@ static void try_unmatched_keys(int sk, int *rnext_index)
 		test_error("all keys on server match the client");
 	if (test_set_key(sk, -1, key->server_keyid))
 		test_error("Can't change the current key");
+	trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_addr, this_ip_dest,
+			      -1, port, 0, -1, -1, -1, -1, -1,
+			      -1, key->server_keyid, -1);
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("verify failed");
 	*rnext_index = i;
@@ -1054,6 +1057,10 @@ static void check_current_back(const char *tst_name, unsigned int port,
 		return;
 	if (test_set_key(sk, collection.keys[rotate_to_index].client_keyid, -1))
 		test_error("Can't change the current key");
+	trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_dest, this_ip_addr,
+			      port, -1, 0, -1, -1, -1, -1, -1,
+			      collection.keys[rotate_to_index].client_keyid,
+			      collection.keys[current_index].client_keyid, -1);
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("verify failed");
 	/* There is a race here: between setting the current_key with
@@ -1085,6 +1092,11 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 	for (i = rnext_index + 1; rotations > 0; i++, rotations--) {
 		if (i >= collection.nr_keys)
 			i = 0;
+		trace_ao_event_expect(TCP_AO_RNEXT_REQUEST,
+				this_ip_addr, this_ip_dest,
+				-1, port, 0, -1, -1, -1, -1, -1,
+				i == 0 ? -1 : collection.keys[i - 1].server_keyid,
+				collection.keys[i].server_keyid, -1);
 		if (test_set_key(sk, -1, collection.keys[i].server_keyid))
 			test_error("Can't change the Rnext key");
 		if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
@@ -1124,7 +1136,7 @@ static void try_client_match(const char *tst_name, unsigned int port,
 				 rnext_index, msg_len, nr_packets);
 	if (sk < 0)
 		return;
-	try_unmatched_keys(sk, &rnext_index);
+	try_unmatched_keys(sk, &rnext_index, port);
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, NULL);
 }
 
@@ -1181,6 +1193,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(120, server_fn, client_fn);
+	test_init(121, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index 78466863435f..db44e77428dd 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -144,6 +144,7 @@ enum test_needs_kconfig {
 	KCONFIG_TCP_AO,			/* required */
 	KCONFIG_TCP_MD5,		/* optional, for TCP-MD5 features */
 	KCONFIG_NET_VRF,		/* optional, for L3/VRF testing */
+	KCONFIG_FTRACE,			/* optional, for tracepoints checks */
 	__KCONFIG_LAST__
 };
 extern bool kernel_config_has(enum test_needs_kconfig k);
@@ -183,6 +184,8 @@ static inline void test_init2(unsigned int ntests,
 	__test_init(ntests, family, prefix, taddr1, taddr2, peer1, peer2);
 }
 extern void test_add_destructor(void (*d)(void));
+extern void test_init_ftrace(int nsfd1, int nsfd2);
+extern int test_setup_tracing(void);
 
 /* To adjust optmem socket limit, approximately estimate a number,
  * that is bigger than sizeof(struct tcp_ao_key).
@@ -257,12 +260,17 @@ static inline void test_init(unsigned int ntests,
 }
 extern void synchronize_threads(void);
 extern void switch_ns(int fd);
+extern int switch_save_ns(int fd);
+extern void switch_close_ns(int fd);
 
 extern __thread union tcp_addr this_ip_addr;
 extern __thread union tcp_addr this_ip_dest;
 extern int test_family;
 
 extern void randomize_buffer(void *buf, size_t buflen);
+extern __printf(3, 4) int test_echo(const char *fname, bool append,
+				    const char *fmt, ...);
+
 extern int open_netns(void);
 extern int unshare_open_netns(void);
 extern const char veth_name[];
@@ -643,4 +651,115 @@ static inline int test_add_repaired_key(int sk,
 	return test_verify_socket_key(sk, &tmp);
 }
 
+#define DEFAULT_FTRACE_BUFFER_KB	10000
+#define DEFAULT_TRACER_LINES_ARR	200
+struct test_ftracer;
+extern uint64_t ns_cookie1, ns_cookie2;
+
+enum ftracer_op {
+	FTRACER_LINE_DISCARD = 0,
+	FTRACER_LINE_PRESERVE,
+	FTRACER_EXIT,
+};
+
+extern struct test_ftracer *create_ftracer(const char *name,
+		enum ftracer_op (*process_line)(const char *line),
+		void (*destructor)(struct test_ftracer *tracer),
+		bool (*expecting_more)(void),
+		size_t lines_buf_sz, size_t buffer_size_kb);
+extern int setup_trace_event(struct test_ftracer *tracer,
+			     const char *event, const char *filter);
+extern void destroy_ftracer(struct test_ftracer *tracer);
+extern const size_t tracer_get_savedlines_nr(struct test_ftracer *tracer);
+extern const char **tracer_get_savedlines(struct test_ftracer *tracer);
+
+enum trace_events {
+	/* TCP_HASH_EVENT */
+	TCP_HASH_BAD_HEADER = 0,
+	TCP_HASH_MD5_REQUIRED,
+	TCP_HASH_MD5_UNEXPECTED,
+	TCP_HASH_MD5_MISMATCH,
+	TCP_HASH_AO_REQUIRED,
+	/* TCP_AO_EVENT */
+	TCP_AO_HANDSHAKE_FAILURE,
+	TCP_AO_WRONG_MACLEN,
+	TCP_AO_MISMATCH,
+	TCP_AO_KEY_NOT_FOUND,
+	TCP_AO_RNEXT_REQUEST,
+	/* TCP_AO_EVENT_SK */
+	TCP_AO_SYNACK_NO_KEY,
+	/* TCP_AO_EVENT_SNE */
+	TCP_AO_SND_SNE_UPDATE,
+	TCP_AO_RCV_SNE_UPDATE,
+	__MAX_TRACE_EVENTS
+};
+
+extern int __trace_event_expect(enum trace_events type, int family,
+				union tcp_addr src, union tcp_addr dst,
+				int src_port, int dst_port, int L3index,
+				int fin, int syn, int rst, int psh, int ack,
+				int keyid, int rnext, int maclen, int sne);
+
+static inline void trace_hash_event_expect(enum trace_events type,
+				union tcp_addr src, union tcp_addr dst,
+				int src_port, int dst_port, int L3index,
+				int fin, int syn, int rst, int psh, int ack)
+{
+	int err;
+
+	err = __trace_event_expect(type, TEST_FAMILY, src, dst,
+				   src_port, dst_port, L3index,
+				   fin, syn, rst, psh, ack,
+				   -1, -1, -1, -1);
+	if (err)
+		test_error("Couldn't add a trace event: %d", err);
+}
+
+static inline void trace_ao_event_expect(enum trace_events type,
+				union tcp_addr src, union tcp_addr dst,
+				int src_port, int dst_port, int L3index,
+				int fin, int syn, int rst, int psh, int ack,
+				int keyid, int rnext, int maclen)
+{
+	int err;
+
+	err = __trace_event_expect(type, TEST_FAMILY, src, dst,
+				   src_port, dst_port, L3index,
+				   fin, syn, rst, psh, ack,
+				   keyid, rnext, maclen, -1);
+	if (err)
+		test_error("Couldn't add a trace event: %d", err);
+}
+
+static inline void trace_ao_event_sk_expect(enum trace_events type,
+				union tcp_addr src, union tcp_addr dst,
+				int src_port, int dst_port,
+				int keyid, int rnext)
+{
+	int err;
+
+	err = __trace_event_expect(type, TEST_FAMILY, src, dst,
+				   src_port, dst_port, -1,
+				   -1, -1, -1, -1, -1,
+				   keyid, rnext, -1, -1);
+	if (err)
+		test_error("Couldn't add a trace event: %d", err);
+}
+
+static inline void trace_ao_event_sne_expect(enum trace_events type,
+				union tcp_addr src, union tcp_addr dst,
+				int src_port, int dst_port, int sne)
+{
+	int err;
+
+	err = __trace_event_expect(type, TEST_FAMILY, src, dst,
+				   src_port, dst_port, -1,
+				   -1, -1, -1, -1, -1,
+				   -1, -1, -1, sne);
+	if (err)
+		test_error("Couldn't add a trace event: %d", err);
+}
+
+extern int setup_aolib_ftracer(void);
+
 #endif /* _AOLIB_H_ */
diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
new file mode 100644
index 000000000000..24380c68fec6
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <pthread.h>
+#include "aolib.h"
+
+static const char *trace_event_names[__MAX_TRACE_EVENTS] = {
+	/* TCP_HASH_EVENT */
+	"tcp_hash_bad_header",
+	"tcp_hash_md5_required",
+	"tcp_hash_md5_unexpected",
+	"tcp_hash_md5_mismatch",
+	"tcp_hash_ao_required",
+	/* TCP_AO_EVENT */
+	"tcp_ao_handshake_failure",
+	"tcp_ao_wrong_maclen",
+	"tcp_ao_mismatch",
+	"tcp_ao_key_not_found",
+	"tcp_ao_rnext_request",
+	/* TCP_AO_EVENT_SK */
+	"tcp_ao_synack_no_key",
+	/* TCP_AO_EVENT_SNE */
+	"tcp_ao_snd_sne_update",
+	"tcp_ao_rcv_sne_update"
+};
+
+struct expected_trace_point {
+	/* required */
+	enum trace_events type;
+	int family;
+	union tcp_addr src;
+	union tcp_addr dst;
+
+	/* optional */
+	int src_port;
+	int dst_port;
+	int L3index;
+
+	int fin;
+	int syn;
+	int rst;
+	int psh;
+	int ack;
+
+	int keyid;
+	int rnext;
+	int maclen;
+	int sne;
+
+	size_t matched;
+};
+
+static struct expected_trace_point *exp_tps;
+static size_t exp_tps_nr;
+static size_t exp_tps_size;
+static pthread_mutex_t exp_tps_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+int __trace_event_expect(enum trace_events type, int family,
+			 union tcp_addr src, union tcp_addr dst,
+			 int src_port, int dst_port, int L3index,
+			 int fin, int syn, int rst, int psh, int ack,
+			 int keyid, int rnext, int maclen, int sne)
+{
+	struct expected_trace_point new_tp = {
+		.type           = type,
+		.family         = family,
+		.src            = src,
+		.dst            = dst,
+		.src_port       = src_port,
+		.dst_port       = dst_port,
+		.L3index        = L3index,
+		.fin            = fin,
+		.syn            = syn,
+		.rst            = rst,
+		.psh            = psh,
+		.ack            = ack,
+		.keyid          = keyid,
+		.rnext          = rnext,
+		.maclen         = maclen,
+		.sne            = sne,
+		.matched        = 0,
+	};
+	int ret = 0;
+
+	if (!kernel_config_has(KCONFIG_FTRACE))
+		return 0;
+
+	pthread_mutex_lock(&exp_tps_mutex);
+	if (exp_tps_nr == exp_tps_size) {
+		struct expected_trace_point *tmp;
+
+		if (exp_tps_size == 0)
+			exp_tps_size = 10;
+		else
+			exp_tps_size = exp_tps_size * 1.6;
+
+		tmp = reallocarray(exp_tps, exp_tps_size, sizeof(exp_tps[0]));
+		if (!tmp) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		exp_tps = tmp;
+	}
+	exp_tps[exp_tps_nr] = new_tp;
+	exp_tps_nr++;
+out:
+	pthread_mutex_unlock(&exp_tps_mutex);
+	return ret;
+}
+
+static void free_expected_events(void)
+{
+	/* We're from the process destructor - not taking the mutex */
+	exp_tps_size = 0;
+	exp_tps = NULL;
+	free(exp_tps);
+}
+
+struct trace_point {
+	int family;
+	union tcp_addr src;
+	union tcp_addr dst;
+	unsigned int src_port;
+	unsigned int dst_port;
+	int L3index;
+	unsigned int fin:1,
+		     syn:1,
+		     rst:1,
+		     psh:1,
+		     ack:1;
+
+	unsigned int keyid;
+	unsigned int rnext;
+	unsigned int maclen;
+
+	unsigned int sne;
+};
+
+static bool lookup_expected_event(int event_type, struct trace_point *e)
+{
+	size_t i;
+
+	pthread_mutex_lock(&exp_tps_mutex);
+	for (i = 0; i < exp_tps_nr; i++) {
+		struct expected_trace_point *p = &exp_tps[i];
+		size_t sk_size;
+
+		if (p->type != event_type)
+			continue;
+		if (p->family != e->family)
+			continue;
+		if (p->family == AF_INET)
+			sk_size = sizeof(p->src.a4);
+		else
+			sk_size = sizeof(p->src.a6);
+		if (memcmp(&p->src, &e->src, sk_size))
+			continue;
+		if (memcmp(&p->dst, &e->dst, sk_size))
+			continue;
+		if (p->src_port >= 0 && p->src_port != e->src_port)
+			continue;
+		if (p->dst_port >= 0 && p->dst_port != e->dst_port)
+			continue;
+		if (p->L3index >= 0 && p->L3index != e->L3index)
+			continue;
+
+		if (p->fin >= 0 && p->fin != e->fin)
+			continue;
+		if (p->syn >= 0 && p->syn != e->syn)
+			continue;
+		if (p->rst >= 0 && p->rst != e->rst)
+			continue;
+		if (p->psh >= 0 && p->psh != e->psh)
+			continue;
+		if (p->ack >= 0 && p->ack != e->ack)
+			continue;
+
+		if (p->keyid >= 0 && p->keyid != e->keyid)
+			continue;
+		if (p->rnext >= 0 && p->rnext != e->rnext)
+			continue;
+		if (p->maclen >= 0 && p->maclen != e->maclen)
+			continue;
+		if (p->sne >= 0 && p->sne != e->sne)
+			continue;
+		p->matched++;
+		pthread_mutex_unlock(&exp_tps_mutex);
+		return true;
+	}
+	pthread_mutex_unlock(&exp_tps_mutex);
+	return false;
+}
+
+static int check_event_type(const char *line)
+{
+	size_t i;
+
+	/*
+	 * This should have been a set or hashmap, but it's a selftest,
+	 * so... KISS.
+	 */
+	for (i = 0; i < __MAX_TRACE_EVENTS; i++) {
+		if (!strncmp(trace_event_names[i], line, strlen(trace_event_names[i])))
+			return i;
+	}
+	return -1;
+}
+
+static bool event_has_flags(enum trace_events event)
+{
+	switch (event) {
+	case TCP_HASH_BAD_HEADER:
+	case TCP_HASH_MD5_REQUIRED:
+	case TCP_HASH_MD5_UNEXPECTED:
+	case TCP_HASH_MD5_MISMATCH:
+	case TCP_HASH_AO_REQUIRED:
+	case TCP_AO_HANDSHAKE_FAILURE:
+	case TCP_AO_WRONG_MACLEN:
+	case TCP_AO_MISMATCH:
+	case TCP_AO_KEY_NOT_FOUND:
+	case TCP_AO_RNEXT_REQUEST:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static int tracer_ip_split(int family, char *src, char **addr, char **port)
+{
+	char *p;
+
+	if (family == AF_INET) {
+		/* fomat is <addr>:port, i.e.: 10.0.254.1:7015 */
+		*addr = src;
+		p = strchr(src, ':');
+		if (!p) {
+			test_print("Couldn't parse trace event addr:port %s", src);
+			return -EINVAL;
+		}
+		*p++ = '\0';
+		*port = p;
+		return 0;
+	}
+	if (family != AF_INET6)
+		return -EAFNOSUPPORT;
+
+	/* format is [<addr>]:port, i.e.: [2001:db8:254::1]:7013 */
+	*addr = strchr(src, '[');
+	p = strchr(src, ']');
+
+	if (!p || !*addr) {
+		test_print("Couldn't parse trace event [addr]:port %s", src);
+		return -EINVAL;
+	}
+
+	*addr = *addr + 1;      /* '[' */
+	*p++ = '\0';            /* ']' */
+	if (*p != ':') {
+		test_print("Couldn't parse trace event :port %s", p);
+		return -EINVAL;
+	}
+	*p++ = '\0';            /* ':' */
+	*port = p;
+	return 0;
+}
+
+static int tracer_scan_address(int family, char *src,
+			       union tcp_addr *dst, unsigned int *port)
+{
+	char *addr, *port_str;
+	int ret;
+
+	ret = tracer_ip_split(family, src, &addr, &port_str);
+	if (ret)
+		return ret;
+
+	if (inet_pton(family, addr, dst) != 1) {
+		test_print("Couldn't parse trace event addr %s", addr);
+		return -EINVAL;
+	}
+	errno = 0;
+	*port = (unsigned int)strtoul(port_str, NULL, 10);
+	if (errno != 0) {
+		test_print("Couldn't parse trace event port %s", port_str);
+		return -errno;
+	}
+	return 0;
+}
+
+static int tracer_scan_event(const char *line, enum trace_events event,
+			     struct trace_point *out)
+{
+	char *src = NULL, *dst = NULL, *family = NULL;
+	char fin, syn, rst, psh, ack;
+	int nr_matched, ret = 0;
+	uint64_t netns_cookie;
+
+	switch (event) {
+	case TCP_HASH_BAD_HEADER:
+	case TCP_HASH_MD5_REQUIRED:
+	case TCP_HASH_MD5_UNEXPECTED:
+	case TCP_HASH_MD5_MISMATCH:
+	case TCP_HASH_AO_REQUIRED: {
+		nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms L3index=%d [%c%c%c%c%c]",
+				    &netns_cookie, &family,
+				    &src, &dst, &out->L3index,
+				    &fin, &syn, &rst, &psh, &ack);
+		if (nr_matched != 10)
+			test_print("Couldn't parse trace event, matched = %d/10",
+				   nr_matched);
+		break;
+	}
+	case TCP_AO_HANDSHAKE_FAILURE:
+	case TCP_AO_WRONG_MACLEN:
+	case TCP_AO_MISMATCH:
+	case TCP_AO_KEY_NOT_FOUND:
+	case TCP_AO_RNEXT_REQUEST: {
+		nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms L3index=%d [%c%c%c%c%c] keyid=%u rnext=%u maclen=%u",
+				    &netns_cookie, &family,
+				    &src, &dst, &out->L3index,
+				    &fin, &syn, &rst, &psh, &ack,
+				    &out->keyid, &out->rnext, &out->maclen);
+		if (nr_matched != 13)
+			test_print("Couldn't parse trace event, matched = %d/13",
+				   nr_matched);
+		break;
+	}
+	case TCP_AO_SYNACK_NO_KEY: {
+		nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms keyid=%u rnext=%u",
+				    &netns_cookie, &family,
+				    &src, &dst, &out->keyid, &out->rnext);
+		if (nr_matched != 6)
+			test_print("Couldn't parse trace event, matched = %d/6",
+				   nr_matched);
+		break;
+	}
+	case TCP_AO_SND_SNE_UPDATE:
+	case TCP_AO_RCV_SNE_UPDATE: {
+		nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms sne=%u",
+				    &netns_cookie, &family,
+				    &src, &dst, &out->sne);
+		if (nr_matched != 5)
+			test_print("Couldn't parse trace event, matched = %d/5",
+				   nr_matched);
+		break;
+	}
+	default:
+		return -1;
+	}
+
+	if (family) {
+		if (!strcmp(family, "AF_INET")) {
+			out->family = AF_INET;
+		} else if (!strcmp(family, "AF_INET6")) {
+			out->family = AF_INET6;
+		} else {
+			test_print("Couldn't parse trace event family %s", family);
+			ret = -EINVAL;
+			goto out_free;
+		}
+	}
+
+	if (event_has_flags(event)) {
+		out->fin = (fin == 'F');
+		out->syn = (syn == 'S');
+		out->rst = (rst == 'R');
+		out->psh = (psh == 'P');
+		out->ack = (ack == '.');
+
+		if ((fin != 'F' && fin != ' ') ||
+		    (syn != 'S' && syn != ' ') ||
+		    (rst != 'R' && rst != ' ') ||
+		    (psh != 'P' && psh != ' ') ||
+		    (ack != '.' && ack != ' ')) {
+			test_print("Couldn't parse trace event flags %c%c%c%c%c",
+				   fin, syn, rst, psh, ack);
+			ret = -EINVAL;
+			goto out_free;
+		}
+	}
+
+	if (src && tracer_scan_address(out->family, src, &out->src, &out->src_port)) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	if (dst && tracer_scan_address(out->family, dst, &out->dst, &out->dst_port)) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	if (netns_cookie != ns_cookie1 && netns_cookie != ns_cookie2) {
+		test_print("Net namespace filter for trace event didn't work: %" PRIu64 " != %" PRIu64 " OR %" PRIu64,
+			   netns_cookie, ns_cookie1, ns_cookie2);
+		ret = -EINVAL;
+	}
+
+out_free:
+	free(src);
+	free(dst);
+	free(family);
+	return ret;
+}
+
+static enum ftracer_op aolib_tracer_process_event(const char *line)
+{
+	int event_type = check_event_type(line);
+	struct trace_point tmp = {};
+
+	if (event_type < 0)
+		return FTRACER_LINE_PRESERVE;
+
+	if (tracer_scan_event(line, event_type, &tmp))
+		return FTRACER_LINE_PRESERVE;
+
+	return lookup_expected_event(event_type, &tmp) ?
+		FTRACER_LINE_DISCARD : FTRACER_LINE_PRESERVE;
+}
+
+static void dump_trace_event(struct expected_trace_point *e)
+{
+	char src[INET6_ADDRSTRLEN], dst[INET6_ADDRSTRLEN];
+
+	if (!inet_ntop(e->family, &e->src, src, INET6_ADDRSTRLEN))
+		test_error("inet_ntop()");
+	if (!inet_ntop(e->family, &e->dst, dst, INET6_ADDRSTRLEN))
+		test_error("inet_ntop()");
+	test_print("trace event filter %s [%s:%d => %s:%d, L3index %d, flags: %s%s%s%s%s, keyid: %d, rnext: %d, maclen: %d, sne: %d] = %zu",
+		   trace_event_names[e->type],
+		   src, e->src_port, dst, e->dst_port, e->L3index,
+		   (e->fin > 0) ? "F" : (e->fin == 0) ? "!F" : "",
+		   (e->syn > 0) ? "S" : (e->syn == 0) ? "!S" : "",
+		   (e->rst > 0) ? "R" : (e->rst == 0) ? "!R" : "",
+		   (e->psh > 0) ? "P" : (e->psh == 0) ? "!P" : "",
+		   (e->ack > 0) ? "." : (e->ack == 0) ? "!." : "",
+		   e->keyid, e->rnext, e->maclen, e->sne, e->matched);
+}
+
+static void print_match_stats(bool unexpected_events)
+{
+	size_t matches_per_type[__MAX_TRACE_EVENTS] = {};
+	bool expected_but_none = false;
+	size_t i, total_matched = 0;
+	char *stat_line = NULL;
+
+	for (i = 0; i < exp_tps_nr; i++) {
+		struct expected_trace_point *e = &exp_tps[i];
+
+		total_matched += e->matched;
+		matches_per_type[e->type] += e->matched;
+		if (!e->matched)
+			expected_but_none = true;
+	}
+	for (i = 0; i < __MAX_TRACE_EVENTS; i++) {
+		if (!matches_per_type[i])
+			continue;
+		stat_line = test_sprintf("%s%s[%zu] ", stat_line ?: "",
+					 trace_event_names[i],
+					 matches_per_type[i]);
+		if (!stat_line)
+			test_error("test_sprintf()");
+	}
+
+	if (unexpected_events || expected_but_none) {
+		for (i = 0; i < exp_tps_nr; i++)
+			dump_trace_event(&exp_tps[i]);
+	}
+
+	if (unexpected_events)
+		return;
+
+	if (expected_but_none)
+		test_fail("Some trace events were expected, but didn't occur");
+	else if (total_matched)
+		test_ok("Trace events matched expectations: %zu %s",
+			total_matched, stat_line);
+	else
+		test_ok("No unexpected trace events during the test run");
+}
+
+#define dump_events(fmt, ...)                           \
+	__test_print(__test_msg, fmt, ##__VA_ARGS__)
+static void check_free_events(struct test_ftracer *tracer)
+{
+	const char **lines;
+	size_t nr;
+
+	if (!kernel_config_has(KCONFIG_FTRACE)) {
+		test_skip("kernel config doesn't have ftrace - no checks");
+		return;
+	}
+
+	nr = tracer_get_savedlines_nr(tracer);
+	lines = tracer_get_savedlines(tracer);
+	print_match_stats(!!nr);
+	if (!nr)
+		return;
+
+	errno = 0;
+	test_xfail("Trace events [%zu] were not expected:", nr);
+	while (nr)
+		dump_events("\t%s", lines[--nr]);
+}
+
+static int setup_tcp_trace_events(struct test_ftracer *tracer)
+{
+	char *filter;
+	size_t i;
+	int ret;
+
+	filter = test_sprintf("net_cookie == %zu || net_cookie == %zu",
+			      ns_cookie1, ns_cookie2);
+	if (!filter)
+		return -ENOMEM;
+
+	for (i = 0; i < __MAX_TRACE_EVENTS; i++) {
+		char *event_name = test_sprintf("tcp/%s", trace_event_names[i]);
+
+		if (!event_name) {
+			ret = -ENOMEM;
+			break;
+		}
+		ret = setup_trace_event(tracer, event_name, filter);
+		free(event_name);
+		if (ret)
+			break;
+	}
+
+	free(filter);
+	return ret;
+}
+
+static void aolib_tracer_destroy(struct test_ftracer *tracer)
+{
+	check_free_events(tracer);
+	free_expected_events();
+}
+
+static bool aolib_tracer_expecting_more(void)
+{
+	size_t i;
+
+	for (i = 0; i < exp_tps_nr; i++)
+		if (!exp_tps[i].matched)
+			return true;
+	return false;
+}
+
+int setup_aolib_ftracer(void)
+{
+	struct test_ftracer *f;
+
+	f = create_ftracer("aolib", aolib_tracer_process_event,
+			   aolib_tracer_destroy, aolib_tracer_expecting_more,
+			   DEFAULT_FTRACE_BUFFER_KB, DEFAULT_TRACER_LINES_ARR);
+	if (!f)
+		return -1;
+
+	return setup_tcp_trace_events(f);
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace.c
new file mode 100644
index 000000000000..e4d0b173bc94
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace.c
@@ -0,0 +1,543 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mount.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include "../../../../../include/linux/kernel.h"
+#include "aolib.h"
+
+static char ftrace_path[] = "ksft-ftrace-XXXXXX";
+static bool ftrace_mounted;
+uint64_t ns_cookie1, ns_cookie2;
+
+struct test_ftracer {
+	pthread_t tracer_thread;
+	int	error;
+	char	*instance_path;
+	FILE	*trace_pipe;
+
+	enum ftracer_op (*process_line)(const char *line);
+	void (*destructor)(struct test_ftracer *tracer);
+	bool (*expecting_more)(void);
+
+	char	**saved_lines;
+	size_t	saved_lines_size;
+	size_t	next_line_ind;
+
+	pthread_cond_t met_all_expected;
+	pthread_mutex_t met_all_expected_lock;
+
+	struct test_ftracer *next;
+};
+
+static struct test_ftracer *ftracers;
+static pthread_mutex_t ftracers_lock = PTHREAD_MUTEX_INITIALIZER;
+
+static int mount_ftrace(void)
+{
+	if (!mkdtemp(ftrace_path))
+		test_error("Can't create temp dir");
+
+	if (mount("tracefs", ftrace_path, "tracefs", 0, "rw"))
+		return -errno;
+
+	ftrace_mounted = true;
+
+	return 0;
+}
+
+static void unmount_ftrace(void)
+{
+	if (ftrace_mounted && umount(ftrace_path))
+		test_print("Failed on cleanup: can't unmount tracefs: %m");
+
+	if (rmdir(ftrace_path))
+		test_error("Failed on cleanup: can't remove ftrace dir %s",
+			   ftrace_path);
+}
+
+struct opts_list_t {
+	char *opt_name;
+	struct opts_list_t *next;
+};
+
+static int disable_trace_options(const char *ftrace_path)
+{
+	struct opts_list_t *opts_list = NULL;
+	char *fopts, *line = NULL;
+	size_t buf_len = 0;
+	ssize_t line_len;
+	int ret = 0;
+	FILE *opts;
+
+	fopts = test_sprintf("%s/%s", ftrace_path, "trace_options");
+	if (!fopts)
+		return -ENOMEM;
+
+	opts = fopen(fopts, "r+");
+	if (!opts) {
+		ret = -errno;
+		goto out_free;
+	}
+
+	while ((line_len = getline(&line, &buf_len, opts)) != -1) {
+		struct opts_list_t *tmp;
+
+		if (!strncmp(line, "no", 2))
+			continue;
+
+		tmp = malloc(sizeof(*tmp));
+		if (!tmp) {
+			ret = -ENOMEM;
+			goto out_free_opts_list;
+		}
+		tmp->next = opts_list;
+		tmp->opt_name = test_sprintf("no%s", line);
+		if (!tmp->opt_name) {
+			ret = -ENOMEM;
+			free(tmp);
+			goto out_free_opts_list;
+		}
+		opts_list = tmp;
+	}
+
+	while (opts_list) {
+		struct opts_list_t *tmp = opts_list;
+
+		fseek(opts, 0, SEEK_SET);
+		fwrite(tmp->opt_name, 1, strlen(tmp->opt_name), opts);
+
+		opts_list = opts_list->next;
+		free(tmp->opt_name);
+		free(tmp);
+	}
+
+out_free_opts_list:
+	while (opts_list) {
+		struct opts_list_t *tmp = opts_list;
+
+		opts_list = opts_list->next;
+		free(tmp->opt_name);
+		free(tmp);
+	}
+	free(line);
+	fclose(opts);
+out_free:
+	free(fopts);
+	return ret;
+}
+
+static int setup_buffer_size(const char *ftrace_path, size_t sz)
+{
+	char *fbuf_size = test_sprintf("%s/buffer_size_kb", ftrace_path);
+	int ret;
+
+	if (!fbuf_size)
+		return -1;
+
+	ret = test_echo(fbuf_size, 0, "%zu", sz);
+	free(fbuf_size);
+	return ret;
+}
+
+static int setup_ftrace_instance(struct test_ftracer *tracer, const char *name)
+{
+	char *tmp;
+
+	tmp = test_sprintf("%s/instances/ksft-%s-XXXXXX", ftrace_path, name);
+	if (!tmp)
+		return -ENOMEM;
+
+	tracer->instance_path = mkdtemp(tmp);
+	if (!tracer->instance_path) {
+		free(tmp);
+		return -errno;
+	}
+
+	return 0;
+}
+
+static void remove_ftrace_instance(struct test_ftracer *tracer)
+{
+	if (rmdir(tracer->instance_path))
+		test_print("Failed on cleanup: can't remove ftrace instance %s",
+			   tracer->instance_path);
+	free(tracer->instance_path);
+}
+
+static void tracer_cleanup(void *arg)
+{
+	struct test_ftracer *tracer = arg;
+
+	fclose(tracer->trace_pipe);
+}
+
+static void tracer_set_error(struct test_ftracer *tracer, int error)
+{
+	if (!tracer->error)
+		tracer->error = error;
+}
+
+const size_t tracer_get_savedlines_nr(struct test_ftracer *tracer)
+{
+	return tracer->next_line_ind;
+}
+
+const char **tracer_get_savedlines(struct test_ftracer *tracer)
+{
+	return (const char **)tracer->saved_lines;
+}
+
+static void *tracer_thread_func(void *arg)
+{
+	struct test_ftracer *tracer = arg;
+
+	pthread_cleanup_push(tracer_cleanup, arg);
+
+	while (tracer->next_line_ind < tracer->saved_lines_size) {
+		char **lp = &tracer->saved_lines[tracer->next_line_ind];
+		enum ftracer_op op;
+		size_t buf_len = 0;
+		ssize_t line_len;
+
+		line_len = getline(lp, &buf_len, tracer->trace_pipe);
+		if (line_len == -1)
+			break;
+
+		pthread_setcancelstate(PTHREAD_CANCEL_DISABLE, NULL);
+		op = tracer->process_line(*lp);
+		pthread_setcancelstate(PTHREAD_CANCEL_ENABLE, NULL);
+
+		if (tracer->expecting_more) {
+			pthread_mutex_lock(&tracer->met_all_expected_lock);
+			if (!tracer->expecting_more())
+				pthread_cond_signal(&tracer->met_all_expected);
+			pthread_mutex_unlock(&tracer->met_all_expected_lock);
+		}
+
+		if (op == FTRACER_LINE_DISCARD)
+			continue;
+		if (op == FTRACER_EXIT)
+			break;
+		if (op != FTRACER_LINE_PRESERVE)
+			test_error("unexpected tracer command %d", op);
+
+		tracer->next_line_ind++;
+		buf_len = 0;
+	}
+	test_print("too many lines in ftracer buffer %zu, exiting tracer",
+		   tracer->next_line_ind);
+
+	pthread_cleanup_pop(1);
+	return NULL;
+}
+
+static int setup_trace_thread(struct test_ftracer *tracer)
+{
+	int ret = 0;
+	char *path;
+
+	path = test_sprintf("%s/trace_pipe", tracer->instance_path);
+	if (!path)
+		return -ENOMEM;
+
+	tracer->trace_pipe = fopen(path, "r");
+	if (!tracer->trace_pipe) {
+		ret = -errno;
+		goto out_free;
+	}
+
+	if (pthread_create(&tracer->tracer_thread, NULL,
+			   tracer_thread_func, (void *)tracer)) {
+		ret = -errno;
+		fclose(tracer->trace_pipe);
+	}
+
+out_free:
+	free(path);
+	return ret;
+}
+
+static void stop_trace_thread(struct test_ftracer *tracer)
+{
+	void *res;
+
+	if (pthread_cancel(tracer->tracer_thread)) {
+		test_print("Can't stop tracer pthread: %m");
+		tracer_set_error(tracer, -errno);
+	}
+	if (pthread_join(tracer->tracer_thread, &res)) {
+		test_print("Can't join tracer pthread: %m");
+		tracer_set_error(tracer, -errno);
+	}
+	if (res != PTHREAD_CANCELED) {
+		test_print("Tracer thread wasn't canceled");
+		tracer_set_error(tracer, -errno);
+	}
+	if (tracer->error)
+		test_fail("tracer errored by %s", strerror(tracer->error));
+}
+
+static void final_wait_for_events(struct test_ftracer *tracer,
+				  unsigned timeout_sec)
+{
+	struct timespec timeout;
+	struct timeval now;
+	int ret = 0;
+
+	if (!tracer->expecting_more)
+		return;
+
+	pthread_mutex_lock(&tracer->met_all_expected_lock);
+	gettimeofday(&now, NULL);
+	timeout.tv_sec = now.tv_sec + timeout_sec;
+	timeout.tv_nsec = now.tv_usec * 1000;
+
+	while (tracer->expecting_more() && ret != ETIMEDOUT)
+		ret = pthread_cond_timedwait(&tracer->met_all_expected,
+				&tracer->met_all_expected_lock, &timeout);
+	pthread_mutex_unlock(&tracer->met_all_expected_lock);
+}
+
+int setup_trace_event(struct test_ftracer *tracer,
+		      const char *event, const char *filter)
+{
+	char *enable_path, *filter_path, *instance = tracer->instance_path;
+	int ret;
+
+	enable_path = test_sprintf("%s/events/%s/enable", instance, event);
+	if (!enable_path)
+		return -ENOMEM;
+
+	filter_path = test_sprintf("%s/events/%s/filter", instance, event);
+	if (!filter_path) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	ret = test_echo(filter_path, 0, "%s", filter);
+	if (!ret)
+		ret = test_echo(enable_path, 0, "1");
+
+out_free:
+	free(filter_path);
+	free(enable_path);
+	return ret;
+}
+
+struct test_ftracer *create_ftracer(const char *name,
+				    enum ftracer_op (*process_line)(const char *line),
+				    void (*destructor)(struct test_ftracer *tracer),
+				    bool (*expecting_more)(void),
+				    size_t lines_buf_sz, size_t buffer_size_kb)
+{
+	struct test_ftracer *tracer;
+	int err;
+
+	/* XXX: separate __create_ftracer() helper and do here
+	 * if (!kernel_config_has(KCONFIG_FTRACE))
+	 *	return NULL;
+	 */
+
+	tracer = malloc(sizeof(*tracer));
+	if (!tracer) {
+		test_print("malloc()");
+		return NULL;
+	}
+
+	memset(tracer, 0, sizeof(*tracer));
+
+	err = setup_ftrace_instance(tracer, name);
+	if (err) {
+		test_print("setup_ftrace_instance(): %d", err);
+		goto err_free;
+	}
+
+	err = disable_trace_options(tracer->instance_path);
+	if (err) {
+		test_print("disable_trace_options(): %d", err);
+		goto err_remove;
+	}
+
+	err = setup_buffer_size(tracer->instance_path, buffer_size_kb);
+	if (err) {
+		test_print("disable_trace_options(): %d", err);
+		goto err_remove;
+	}
+
+	tracer->saved_lines = calloc(lines_buf_sz, sizeof(tracer->saved_lines[0]));
+	if (!tracer->saved_lines) {
+		test_print("calloc()");
+		goto err_remove;
+	}
+	tracer->saved_lines_size = lines_buf_sz;
+
+	tracer->process_line	= process_line;
+	tracer->destructor	= destructor;
+	tracer->expecting_more	= expecting_more;
+
+	err = pthread_cond_init(&tracer->met_all_expected, NULL);
+	if (err) {
+		test_print("pthread_cond_init(): %d", err);
+		goto err_free_lines;
+	}
+
+	err = pthread_mutex_init(&tracer->met_all_expected_lock, NULL);
+	if (err) {
+		test_print("pthread_mutex_init(): %d", err);
+		goto err_cond_destroy;
+	}
+
+	err = setup_trace_thread(tracer);
+	if (err) {
+		test_print("setup_trace_thread(): %d", err);
+		goto err_mutex_destroy;
+	}
+
+	pthread_mutex_lock(&ftracers_lock);
+	tracer->next = ftracers;
+	ftracers = tracer;
+	pthread_mutex_unlock(&ftracers_lock);
+
+	return tracer;
+
+err_mutex_destroy:
+	pthread_mutex_destroy(&tracer->met_all_expected_lock);
+err_cond_destroy:
+	pthread_cond_destroy(&tracer->met_all_expected);
+err_free_lines:
+	free(tracer->saved_lines);
+err_remove:
+	remove_ftrace_instance(tracer);
+err_free:
+	free(tracer);
+	return NULL;
+}
+
+static void __destroy_ftracer(struct test_ftracer *tracer)
+{
+	size_t i;
+
+	final_wait_for_events(tracer, TEST_TIMEOUT_SEC);
+	stop_trace_thread(tracer);
+	remove_ftrace_instance(tracer);
+	if (tracer->destructor)
+		tracer->destructor(tracer);
+	for (i = 0; i < tracer->saved_lines_size; i++)
+		free(tracer->saved_lines[i]);
+	pthread_cond_destroy(&tracer->met_all_expected);
+	pthread_mutex_destroy(&tracer->met_all_expected_lock);
+	free(tracer);
+}
+
+void destroy_ftracer(struct test_ftracer *tracer)
+{
+	pthread_mutex_lock(&ftracers_lock);
+	if (tracer == ftracers) {
+		ftracers = tracer->next;
+	} else {
+		struct test_ftracer *f = ftracers;
+
+		while (f->next != tracer) {
+			if (!f->next)
+				test_error("tracers list corruption or double free %p", tracer);
+			f = f->next;
+		}
+		f->next = tracer->next;
+	}
+	tracer->next = NULL;
+	pthread_mutex_unlock(&ftracers_lock);
+	__destroy_ftracer(tracer);
+}
+
+static void destroy_all_ftracers(void)
+{
+	struct test_ftracer *f;
+
+	pthread_mutex_lock(&ftracers_lock);
+	f = ftracers;
+	ftracers = NULL;
+	pthread_mutex_unlock(&ftracers_lock);
+
+	while (f) {
+		struct test_ftracer *n = f->next;
+
+		f->next = NULL;
+		__destroy_ftracer(f);
+		f = n;
+	}
+}
+
+static void test_unset_tracing(void)
+{
+	destroy_all_ftracers();
+	unmount_ftrace();
+}
+
+int test_setup_tracing(void)
+{
+	/*
+	 * Just a basic protection - this should be called only once from
+	 * lib/kconfig. Not thread safe, which is fine as it's early, before
+	 * threads are created.
+	 */
+	static int already_set;
+	int err;
+
+	if (already_set)
+		return -1;
+
+	/* Needs net-namespace cookies for filters */
+	if (ns_cookie1 == ns_cookie2) {
+		test_print("net-namespace cookies: %" PRIu64 " == %" PRIu64 ", can't set up tracing",
+			   ns_cookie1, ns_cookie2);
+		return -1;
+	}
+
+	already_set = 1;
+
+	test_add_destructor(test_unset_tracing);
+
+	err = mount_ftrace();
+	if (err) {
+		test_print("failed to mount_ftrace(): %d", err);
+		return err;
+	}
+
+	return setup_aolib_ftracer();
+}
+
+static int get_ns_cookie(int nsfd, uint64_t *out)
+{
+	int old_ns = switch_save_ns(nsfd);
+	socklen_t size = sizeof(*out);
+	int sk;
+
+	sk = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
+	if (sk < 0) {
+		test_print("socket(): %m");
+		return -errno;
+	}
+
+	if (getsockopt(sk, SOL_SOCKET, SO_NETNS_COOKIE, out, &size)) {
+		test_print("getsockopt(SO_NETNS_COOKIE): %m");
+		close(sk);
+		return -errno;
+	}
+
+	close(sk);
+	switch_close_ns(old_ns);
+	return 0;
+}
+
+void test_init_ftrace(int nsfd1, int nsfd2)
+{
+	get_ns_cookie(nsfd1, &ns_cookie1);
+	get_ns_cookie(nsfd2, &ns_cookie2);
+	/* Populate kernel config state */
+	kernel_config_has(KCONFIG_FTRACE);
+}
diff --git a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
index 3bf4a7e4b3c9..9f1c175846f8 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c
@@ -116,6 +116,12 @@ static int has_vrfs(int *err)
 	return ret;
 }
 
+static int has_ftrace(int *err)
+{
+	*err = test_setup_tracing();
+	return 0;
+}
+
 #define KCONFIG_UNKNOWN			1
 static pthread_mutex_t kconfig_lock = PTHREAD_MUTEX_INITIALIZER;
 static struct kconfig_t kconfig[__KCONFIG_LAST__] = {
@@ -124,6 +130,7 @@ static struct kconfig_t kconfig[__KCONFIG_LAST__] = {
 	{ KCONFIG_UNKNOWN, has_tcp_ao },
 	{ KCONFIG_UNKNOWN, has_tcp_md5 },
 	{ KCONFIG_UNKNOWN, has_vrfs },
+	{ KCONFIG_UNKNOWN, has_ftrace },
 };
 
 const char *tests_skip_reason[__KCONFIG_LAST__] = {
@@ -132,6 +139,7 @@ const char *tests_skip_reason[__KCONFIG_LAST__] = {
 	"Tests require TCP-AO support (CONFIG_TCP_AO)",
 	"setsockopt(TCP_MD5SIG_EXT) is not supported (CONFIG_TCP_MD5)",
 	"VRFs are not supported (CONFIG_NET_VRF)",
+	"Ftrace points are not supported (CONFIG_TRACEPOINTS)",
 };
 
 bool kernel_config_has(enum test_needs_kconfig k)
diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c
index 86a4f6e20450..a27cc03c9fbd 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/setup.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c
@@ -250,9 +250,9 @@ void __test_init(unsigned int ntests, int family, unsigned int prefix,
 	test_print("rand seed %u", (unsigned int)seed);
 	srand(seed);
 
-
 	ksft_print_header();
 	init_namespaces();
+	test_init_ftrace(nsfd_parent, nsfd_child);
 
 	if (add_veth(veth_name, nsfd_parent, nsfd_child))
 		test_error("Failed to add veth");
diff --git a/tools/testing/selftests/net/tcp_ao/lib/utils.c b/tools/testing/selftests/net/tcp_ao/lib/utils.c
index 372daca525f5..bdf5522c9213 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/utils.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/utils.c
@@ -21,6 +21,32 @@ void randomize_buffer(void *buf, size_t buflen)
 	}
 }
 
+__printf(3, 4) int test_echo(const char *fname, bool append,
+			     const char *fmt, ...)
+{
+	size_t len, written;
+	va_list vargs;
+	char *msg;
+	FILE *f;
+
+	f = fopen(fname, append ? "a" : "w");
+	if (!f)
+		return -errno;
+
+	va_start(vargs, fmt);
+	msg = test_snprintf(fmt, vargs);
+	va_end(vargs);
+	if (!msg) {
+		fclose(f);
+		return -1;
+	}
+	len = strlen(msg);
+	written = fwrite(msg, 1, len, f);
+	fclose(f);
+	free(msg);
+	return written == len ? 0 : -1;
+}
+
 const struct sockaddr_in6 addr_any6 = {
 	.sin6_family	= AF_INET6,
 };
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index f6ea2190f43d..ecc6f1e3a414 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -208,22 +208,36 @@ static void *client_fn(void *arg)
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
 	ao_img.snt_isn += 1;
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest,
+			      -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
+			      port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
 	test_sk_restore("TCP-AO with wrong send ISN", port++,
 			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
 	ao_img.rcv_isn += 1;
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest,
+			      -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
+			      port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
 	test_sk_restore("TCP-AO with wrong receive ISN", port++,
 			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
 	ao_img.snd_sne += 1;
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest,
+			      -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
+	/* not expecting server => client mismatches as only snd sne is broken */
 	test_sk_restore("TCP-AO with wrong send SEQ ext number", port++,
 			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
 			TEST_CNT_NS_BAD | TEST_CNT_GOOD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
 	ao_img.rcv_sne += 1;
+	/* not expecting client => server mismatches as only rcv sne is broken */
+	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
+			      port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
 	test_sk_restore("TCP-AO with wrong receive SEQ ext number", port++,
 			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
 			TEST_CNT_NS_GOOD | TEST_CNT_BAD);
@@ -233,6 +247,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(20, server_fn, client_fn);
+	test_init(21, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index a2fe88d35ac0..6364facaa63e 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -455,6 +455,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(14, server_fn, client_fn);
+	test_init(15, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index e56931d38e06..3ecd2b58de6a 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -163,17 +163,26 @@ static void *client_fn(void *arg)
 	setup_lo_intf("lo");
 
 	tcp_self_connect("self-connect(same keyids)", port++, false, false);
+
+	/* expecting rnext to change based on the first segment RNext != Current */
+	trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, local_addr, local_addr,
+			      port, port, 0, -1, -1, -1, -1, -1, 7, 5, -1);
 	tcp_self_connect("self-connect(different keyids)", port++, true, false);
 	tcp_self_connect("self-connect(restore)", port, false, true);
-	port += 2;
+	port += 2; /* restore test restores over different port */
+	trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, local_addr, local_addr,
+			      port, port, 0, -1, -1, -1, -1, -1, 7, 5, -1);
+	/* intentionally on restore they are added to the socket in different order */
+	trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, local_addr, local_addr,
+			      port + 1, port + 1, 0, -1, -1, -1, -1, -1, 5, 7, -1);
 	tcp_self_connect("self-connect(restore, different keyids)", port, true, true);
-	port += 2;
+	port += 2; /* restore test restores over different port */
 
 	return NULL;
 }
 
 int main(int argc, char *argv[])
 {
-	test_init(4, client_fn, NULL);
+	test_init(5, client_fn, NULL);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index 885866cc193c..8901a6785dc8 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -116,6 +116,14 @@ static void *server_fn(void *arg)
 	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
 			     client_new_port, &ao1);
 
+	trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_addr,
+			this_ip_dest, test_server_port + 1, client_new_port, 1);
+	trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_dest,
+			this_ip_addr, client_new_port, test_server_port + 1, 1);
+	trace_ao_event_sne_expect(TCP_AO_RCV_SNE_UPDATE, this_ip_addr,
+			this_ip_dest, test_server_port + 1, client_new_port, 1);
+	trace_ao_event_sne_expect(TCP_AO_RCV_SNE_UPDATE, this_ip_dest,
+			this_ip_addr, client_new_port, test_server_port + 1, 1);
 	synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */
 	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
 	if (bytes != quota) {
@@ -242,6 +250,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(7, server_fn, client_fn);
+	test_init(8, server_fn, client_fn);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
index 5eee826c37aa..084db4ecdff6 100644
--- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
+++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c
@@ -830,6 +830,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(120, client_fn, NULL);
+	test_init(121, client_fn, NULL);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index 02346b58efbd..f779e5892bc1 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -674,24 +674,38 @@ static void *client_fn(void *arg)
 
 	try_connect("AO server (INADDR_ANY): AO client", port++, NULL, 0,
 		    &addr_any, 0, 100, 100, 0, 0, 0, &this_ip_addr);
+	trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, this_ip_addr,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
 		    NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
+	trace_hash_event_expect(TCP_HASH_AO_REQUIRED, this_ip_addr,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO server (INADDR_ANY): unsigned client", port++, NULL, 0,
 		    NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &this_ip_addr);
 	try_connect("AO server (AO_REQUIRED): AO client", port++, NULL, 0,
 		    &addr_any, 0, 100, 100, 0, 0, 0, &this_ip_addr);
+	trace_hash_event_expect(TCP_HASH_AO_REQUIRED, client2,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
 		    NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &client2);
 
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("MD5 server (INADDR_ANY): AO client", port++, NULL, 0,
 		   &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
 	try_connect("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
 		   NULL, 0, 100, 100, 0, 0, 1, &this_ip_addr);
+	trace_hash_event_expect(TCP_HASH_MD5_REQUIRED, this_ip_addr,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("MD5 server (INADDR_ANY): no sign client", port++, NULL, 0,
 		   NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
 
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("no sign server: AO client", port++, NULL, 0,
 		   &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &this_ip_addr);
+	trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, this_ip_addr,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("no sign server: MD5 client", port++, &addr_any, 0,
 		   NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr);
 	try_connect("no sign server: no sign client", port++, NULL, 0,
@@ -699,25 +713,37 @@ static void *client_fn(void *arg)
 
 	try_connect("AO+MD5 server: AO client (matching)", port++, NULL, 0,
 		   &addr_any, 0, 100, 100, 0, 0, 1, &client2);
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("AO+MD5 server: AO client (misconfig, matching MD5)",
 		   port++, NULL, 0, &addr_any, 0, 100, 100, 0,
 		   FAULT_TIMEOUT, 1, &this_ip_addr);
+	trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, client3, this_ip_dest,
+			      -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1);
 	try_connect("AO+MD5 server: AO client (misconfig, non-matching)",
 		   port++, NULL, 0, &addr_any, 0, 100, 100, 0,
 		   FAULT_TIMEOUT, 1, &client3);
 	try_connect("AO+MD5 server: MD5 client (matching)", port++, &addr_any, 0,
 		   NULL, 0, 100, 100, 0, 0, 1, &this_ip_addr);
+	trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, client2,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO+MD5 server: MD5 client (misconfig, matching AO)",
 		   port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
 		   1, &client2);
+	trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, client3,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO+MD5 server: MD5 client (misconfig, non-matching)",
 		   port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
 		   1, &client3);
 	try_connect("AO+MD5 server: no sign client (unmatched)",
 		   port++, NULL, 0, NULL, 0, 100, 100, 0, 0, 1, &client3);
+	trace_hash_event_expect(TCP_HASH_AO_REQUIRED, client2,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO+MD5 server: no sign client (misconfig, matching AO)",
 		   port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
 		   1, &client2);
+	trace_hash_event_expect(TCP_HASH_MD5_REQUIRED, this_ip_addr,
+				this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0);
 	try_connect("AO+MD5 server: no sign client (misconfig, matching MD5)",
 		   port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT,
 		   1, &this_ip_addr);
@@ -739,6 +765,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(72, server_fn, client_fn);
+	test_init(73, server_fn, client_fn);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 9a4556862d1f0f4d3a77c5252a616e006a4c3432 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 24 Aug 2024 16:27:54 +0800
Subject: net: thunderx: Remove unused declarations

Commit 4863dea3fab0 ("net: Adding support for Cavium ThunderX network
controller") declared nicvf_qset_reg_{write,read}() but never implemented.

Commit 4863dea3fab0 ("net: Adding support for Cavium ThunderX network
controller") declared bgx_add_dmac_addr() but no implementation.

After commit 5fc7cf179449 ("net: thunderx: Cleanup PHY probing code.")
octeon_mdiobus_force_mod_depencency() is not used any more.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240824082754.3637963-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/thunder/nicvf_queues.h | 2 --
 drivers/net/ethernet/cavium/thunder/thunder_bgx.h  | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 8453defc296c..b7531041c56d 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -359,8 +359,6 @@ int nicvf_is_intr_enabled(struct nicvf *nic, int int_type, int q_idx);
 /* Register access APIs */
 void nicvf_reg_write(struct nicvf *nic, u64 offset, u64 val);
 u64  nicvf_reg_read(struct nicvf *nic, u64 offset);
-void nicvf_qset_reg_write(struct nicvf *nic, u64 offset, u64 val);
-u64 nicvf_qset_reg_read(struct nicvf *nic, u64 offset);
 void nicvf_queue_reg_write(struct nicvf *nic, u64 offset,
 			   u64 qidx, u64 val);
 u64  nicvf_queue_reg_read(struct nicvf *nic,
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index cdea49392185..84f16ababaee 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -219,9 +219,7 @@
 void bgx_set_dmac_cam_filter(int node, int bgx_idx, int lmacid, u64 mac, u8 vf);
 void bgx_reset_xcast_mode(int node, int bgx_idx, int lmacid, u8 vf);
 void bgx_set_xcast_mode(int node, int bgx_idx, int lmacid, u8 mode);
-void octeon_mdiobus_force_mod_depencency(void);
 void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable);
-void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac);
 unsigned bgx_get_map(int node);
 int bgx_get_lmac_count(int node, int bgx);
 const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid);
-- 
cgit v1.3-3-g829e


From 0eaebf738e6ec45d1f8a268155b13afcf17e2c97 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 24 Aug 2024 16:31:07 +0800
Subject: net: liquidio: Remove unused declarations

Commit da15c78b5664 ("liquidio CN23XX: VF register access") declared
cn23xx_dump_vf_initialized_regs() but never implemented it.

octeon_dump_soft_command() is never implemented and used since introduction in
commit 35878618c92d ("liquidio: Added delayed work for periodically updating
the link statistics.").

And finally, a few other declarations were never implenmented since introduction
in commit f21fb3ed364b ("Add support of Cavium Liquidio ethernet adapters").

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240824083107.3639602-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h | 2 --
 drivers/net/ethernet/cavium/liquidio/cn66xx_device.h    | 1 -
 drivers/net/ethernet/cavium/liquidio/octeon_device.h    | 7 -------
 drivers/net/ethernet/cavium/liquidio/octeon_droq.h      | 2 --
 drivers/net/ethernet/cavium/liquidio/octeon_iq.h        | 3 ---
 5 files changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h
index 2d06097d3f61..40f529d0bc4c 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h
@@ -43,6 +43,4 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct);
 int cn23xx_setup_octeon_vf_device(struct octeon_device *oct);
 
 u32 cn23xx_vf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us);
-
-void cn23xx_dump_vf_initialized_regs(struct octeon_device *oct);
 #endif
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
index 8ed57134ee0c..129c8b84f549 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h
@@ -86,7 +86,6 @@ u32
 lio_cn6xxx_update_read_index(struct octeon_instr_queue *iq);
 void lio_cn6xxx_enable_interrupt(struct octeon_device *oct, u8 unused);
 void lio_cn6xxx_disable_interrupt(struct octeon_device *oct, u8 unused);
-void cn6xxx_get_pcie_qlmport(struct octeon_device *oct);
 void lio_cn6xxx_setup_reg_address(struct octeon_device *oct, void *chip,
 				  struct octeon_reg_list *reg_list);
 u32 lio_cn6xxx_coprocessor_clock(struct octeon_device *oct);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index fb380b4f3e02..d26364c2ac81 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -804,13 +804,6 @@ int octeon_init_consoles(struct octeon_device *oct);
 int octeon_add_console(struct octeon_device *oct, u32 console_num,
 		       char *dbg_enb);
 
-/** write or read from a console */
-int octeon_console_write(struct octeon_device *oct, u32 console_num,
-			 char *buffer, u32 write_request_size, u32 flags);
-int octeon_console_write_avail(struct octeon_device *oct, u32 console_num);
-
-int octeon_console_read_avail(struct octeon_device *oct, u32 console_num);
-
 /** Removes all attached consoles. */
 void octeon_remove_consoles(struct octeon_device *oct);
 
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
index c9b19e624dce..232ae72c0e37 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h
@@ -395,8 +395,6 @@ int octeon_register_dispatch_fn(struct octeon_device *oct,
 void *octeon_get_dispatch_arg(struct octeon_device *oct,
 			      u16 opcode, u16 subcode);
 
-void octeon_droq_print_stats(void);
-
 u32 octeon_droq_check_hw_for_pkts(struct octeon_droq *droq);
 
 int octeon_create_droq(struct octeon_device *oct, u32 q_no,
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index bebf3bd349c6..a04f36a0e1a0 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -378,9 +378,6 @@ int octeon_send_command(struct octeon_device *oct, u32 iq_no,
 			u32 force_db, void *cmd, void *buf,
 			u32 datasize, u32 reqtype);
 
-void octeon_dump_soft_command(struct octeon_device *oct,
-			      struct octeon_soft_command *sc);
-
 void octeon_prepare_soft_command(struct octeon_device *oct,
 				 struct octeon_soft_command *sc,
 				 u8 opcode, u8 subcode,
-- 
cgit v1.3-3-g829e


From be04024a24a93f761a7b2c5f2de46db0f3acdc74 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Sat, 24 Aug 2024 13:02:37 -0700
Subject: net: ag71xx: support probe defferal for getting MAC address

Currently, of_get_ethdev_address() return is checked for any return error
code which means that trying to get the MAC from NVMEM cells that is backed
by MTD will fail if it was not probed before ag71xx.

So, lets check the return error code for EPROBE_DEFER and defer the ag71xx
probe in that case until the underlying NVMEM device is live.

Signed-off-by: Robert Marko <robimarko@gmail.com>
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240824200249.137209-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index bf02bea03a7b..543cbea47138 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1895,6 +1895,8 @@ static int ag71xx_probe(struct platform_device *pdev)
 	ag->stop_desc->next = (u32)ag->stop_desc_dma;
 
 	err = of_get_ethdev_address(np, ndev);
+	if (err == -EPROBE_DEFER)
+		return err;
 	if (err) {
 		netif_err(ag, probe, ndev, "invalid MAC address, using random address\n");
 		eth_hw_addr_random(ndev);
-- 
cgit v1.3-3-g829e


From d76867efebcb20752345e5a41d38bd456427b325 Mon Sep 17 00:00:00 2001
From: Yu Liao <liaoyu15@huawei.com>
Date: Mon, 26 Aug 2024 09:21:00 +0800
Subject: net: txgbe: use pci_dev_id() helper

PCI core API pci_dev_id() can be used to get the BDF number for a PCI
device. We don't need to compose it manually. Use pci_dev_id() to
simplify the code a little bit.

Signed-off-by: Yu Liao <liaoyu15@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240826012100.3975175-1-liaoyu15@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 5f502265f0a6..67b61afdde96 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -688,8 +688,7 @@ static int txgbe_ext_phy_init(struct txgbe *txgbe)
 	mii_bus->parent = &pdev->dev;
 	mii_bus->phy_mask = GENMASK(31, 1);
 	mii_bus->priv = wx;
-	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe-%x",
-		 (pdev->bus->number << 8) | pdev->devfn);
+	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe-%x", pci_dev_id(pdev));
 
 	ret = devm_mdiobus_register(&pdev->dev, mii_bus);
 	if (ret) {
-- 
cgit v1.3-3-g829e


From 2e25147a6560b684917d7f7142422c9901badfdd Mon Sep 17 00:00:00 2001
From: Liao Chen <liaochen4@huawei.com>
Date: Mon, 26 Aug 2024 09:18:56 +0000
Subject: net: dm9051: fix module autoloading

Add MODULE_DEVICE_TABLE(), so modules could be properly autoloaded
based on the alias from of_device_id table.

Signed-off-by: Liao Chen <liaochen4@huawei.com>
Link: https://patch.msgid.link/20240826091858.369910-2-liaochen4@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/davicom/dm9051.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c
index bcfe52c11804..59ea48d4c9de 100644
--- a/drivers/net/ethernet/davicom/dm9051.c
+++ b/drivers/net/ethernet/davicom/dm9051.c
@@ -1235,6 +1235,7 @@ static const struct of_device_id dm9051_match_table[] = {
 	{ .compatible = "davicom,dm9051" },
 	{}
 };
+MODULE_DEVICE_TABLE(of, dm9051_match_table);
 
 static const struct spi_device_id dm9051_id_table[] = {
 	{ "dm9051", 0 },
-- 
cgit v1.3-3-g829e


From c76afed1bace01f5634ca18b3a5c85650ea653ad Mon Sep 17 00:00:00 2001
From: Liao Chen <liaochen4@huawei.com>
Date: Mon, 26 Aug 2024 09:18:57 +0000
Subject: net: ag71xx: fix module autoloading

Add MODULE_DEVICE_TABLE(), so modules could be properly autoloaded
based on the alias from of_device_id table.

Signed-off-by: Liao Chen <liaochen4@huawei.com>
Link: https://patch.msgid.link/20240826091858.369910-3-liaochen4@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 543cbea47138..db2a8ade6205 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -2022,6 +2022,7 @@ static const struct of_device_id ag71xx_match[] = {
 	{ .compatible = "qca,qca9560-eth", .data = &ag71xx_dcfg_qca9550 },
 	{}
 };
+MODULE_DEVICE_TABLE(of, ag71xx_match);
 
 static struct platform_driver ag71xx_driver = {
 	.probe		= ag71xx_probe,
-- 
cgit v1.3-3-g829e


From 7d2bd8ac9d2494cf9b16c4b00df9424ad24ed18c Mon Sep 17 00:00:00 2001
From: Liao Chen <liaochen4@huawei.com>
Date: Mon, 26 Aug 2024 09:18:58 +0000
Subject: net: airoha: fix module autoloading

Add MODULE_DEVICE_TABLE(), so modules could be properly autoloaded
based on the alias from of_device_id table.

Signed-off-by: Liao Chen <liaochen4@huawei.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20240826091858.369910-4-liaochen4@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 0c012efca3b0..930f180688e5 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -2775,6 +2775,7 @@ static const struct of_device_id of_airoha_match[] = {
 	{ .compatible = "airoha,en7581-eth" },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, of_airoha_match);
 
 static struct platform_driver airoha_driver = {
 	.probe = airoha_probe,
-- 
cgit v1.3-3-g829e


From cf740e3cc761560beefae4d772fd350e46f600fc Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Mon, 26 Aug 2024 11:37:10 +0200
Subject: net: phy: vitesse: implement MDI-X configuration in vsc73xx

This commit introduces MDI-X configuration support in vsc73xx phys.

Vsc73xx supports only auto mode or forced MDI.

Vsc73xx have auto MDI-X disabled by default in forced speed mode.
This commit enables it.

Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240826093710.511837-1-paweldembicki@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/vitesse.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 93 insertions(+)

diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 54eb4e8377c4..2377179de017 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -71,6 +71,19 @@
 #define MII_VSC73XX_DOWNSHIFT_MAX		5
 #define MII_VSC73XX_DOWNSHIFT_INVAL		1
 
+/* VSC73XX PHY_BYPASS_CTRL register*/
+#define MII_VSC73XX_PHY_BYPASS_CTRL		MII_DCOUNTER
+#define MII_VSC73XX_PBC_TX_DIS			BIT(15)
+#define MII_VSC73XX_PBC_FOR_SPD_AUTO_MDIX_DIS	BIT(7)
+#define MII_VSC73XX_PBC_PAIR_SWAP_DIS		BIT(5)
+#define MII_VSC73XX_PBC_POL_INV_DIS		BIT(4)
+#define MII_VSC73XX_PBC_PARALLEL_DET_DIS	BIT(3)
+#define MII_VSC73XX_PBC_AUTO_NP_EXCHANGE_DIS	BIT(1)
+
+/* VSC73XX PHY_AUX_CTRL_STAT register */
+#define MII_VSC73XX_PHY_AUX_CTRL_STAT	MII_NCONFIG
+#define MII_VSC73XX_PACS_NO_MDI_X_IND	BIT(13)
+
 /* Vitesse VSC8601 Extended PHY Control Register 1 */
 #define MII_VSC8601_EPHY_CTL		0x17
 #define MII_VSC8601_EPHY_CTL_RGMII_SKEW	(1 << 8)
@@ -219,6 +232,9 @@ static void vsc73xx_config_init(struct phy_device *phydev)
 
 	/* Enable downshift by default */
 	vsc73xx_set_downshift(phydev, MII_VSC73XX_DOWNSHIFT_MAX);
+
+	/* Set Auto MDI-X by default */
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
 }
 
 static int vsc738x_config_init(struct phy_device *phydev)
@@ -319,6 +335,75 @@ static int vsc739x_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+static int vsc73xx_mdix_set(struct phy_device *phydev, u8 mdix)
+{
+	int ret;
+	u16 val;
+
+	val = phy_read(phydev, MII_VSC73XX_PHY_BYPASS_CTRL);
+
+	switch (mdix) {
+	case ETH_TP_MDI:
+		val |= MII_VSC73XX_PBC_FOR_SPD_AUTO_MDIX_DIS |
+		       MII_VSC73XX_PBC_PAIR_SWAP_DIS |
+		       MII_VSC73XX_PBC_POL_INV_DIS;
+		break;
+	case ETH_TP_MDI_X:
+		/* When MDI-X auto configuration is disabled, is possible
+		 * to force only MDI mode. Let's use autoconfig for forced
+		 * MDIX mode.
+		 */
+	case ETH_TP_MDI_AUTO:
+		val &= ~(MII_VSC73XX_PBC_FOR_SPD_AUTO_MDIX_DIS |
+			 MII_VSC73XX_PBC_PAIR_SWAP_DIS |
+			 MII_VSC73XX_PBC_POL_INV_DIS);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = phy_write(phydev, MII_VSC73XX_PHY_BYPASS_CTRL, val);
+	if (ret)
+		return ret;
+
+	return genphy_restart_aneg(phydev);
+}
+
+static int vsc73xx_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = vsc73xx_mdix_set(phydev, phydev->mdix_ctrl);
+	if (ret)
+		return ret;
+
+	return genphy_config_aneg(phydev);
+}
+
+static int vsc73xx_mdix_get(struct phy_device *phydev, u8 *mdix)
+{
+	u16 reg_val;
+
+	reg_val = phy_read(phydev, MII_VSC73XX_PHY_AUX_CTRL_STAT);
+	if (reg_val & MII_VSC73XX_PACS_NO_MDI_X_IND)
+		*mdix = ETH_TP_MDI;
+	else
+		*mdix = ETH_TP_MDI_X;
+
+	return 0;
+}
+
+static int vsc73xx_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = vsc73xx_mdix_get(phydev, &phydev->mdix);
+	if (ret < 0)
+		return ret;
+
+	return genphy_read_status(phydev);
+}
+
 /* This adds a skew for both TX and RX clocks, so the skew should only be
  * applied to "rgmii-id" interfaces. It may not work as expected
  * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces.
@@ -516,6 +601,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask    = 0x000ffff0,
 	/* PHY_GBIT_FEATURES */
 	.config_init    = vsc738x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_status	= vsc73xx_read_status,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
 	.get_tunable    = vsc73xx_get_tunable,
@@ -526,6 +613,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask    = 0x000ffff0,
 	/* PHY_GBIT_FEATURES */
 	.config_init    = vsc738x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_status	= vsc73xx_read_status,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
 	.get_tunable    = vsc73xx_get_tunable,
@@ -536,6 +625,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask    = 0x000ffff0,
 	/* PHY_GBIT_FEATURES */
 	.config_init    = vsc739x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_status	= vsc73xx_read_status,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
 	.get_tunable    = vsc73xx_get_tunable,
@@ -546,6 +637,8 @@ static struct phy_driver vsc82xx_driver[] = {
 	.phy_id_mask    = 0x000ffff0,
 	/* PHY_GBIT_FEATURES */
 	.config_init    = vsc739x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_status	= vsc73xx_read_status,
 	.read_page      = vsc73xx_read_page,
 	.write_page     = vsc73xx_write_page,
 	.get_tunable    = vsc73xx_get_tunable,
-- 
cgit v1.3-3-g829e


From 3410d0e14f9a6856386c6a8eb2310cbc58191777 Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Mon, 26 Aug 2024 09:07:41 -0700
Subject: net: mana: Implement get_ringparam/set_ringparam for mana

Currently the values of WQs for RX and TX queues for MANA devices
are hardcoded to default sizes.
Allow configuring these values for MANA devices as ringparam
configuration(get/set) through ethtool_ops.
Pre-allocate buffers at the beginning of this operation, to
prevent complete network loss in low-memory conditions.

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Link: https://patch.msgid.link/1724688461-12203-1-git-send-email-shradhagupta@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c      | 27 ++++----
 drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 74 ++++++++++++++++++++++
 include/net/mana/mana.h                            | 23 ++++++-
 3 files changed, 110 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 39f56973746d..3e865985340e 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -511,7 +511,7 @@ static u16 mana_select_queue(struct net_device *ndev, struct sk_buff *skb,
 }
 
 /* Release pre-allocated RX buffers */
-static void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc)
+void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc)
 {
 	struct device *dev;
 	int i;
@@ -608,7 +608,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
 	*datasize = mtu + ETH_HLEN;
 }
 
-static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
+int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
 {
 	struct device *dev;
 	struct page *page;
@@ -622,7 +622,7 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
 
 	dev = mpc->ac->gdma_dev->gdma_context->dev;
 
-	num_rxb = mpc->num_queues * RX_BUFFERS_PER_QUEUE;
+	num_rxb = mpc->num_queues * mpc->rx_queue_size;
 
 	WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n");
 	mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL);
@@ -1909,15 +1909,17 @@ static int mana_create_txq(struct mana_port_context *apc,
 		return -ENOMEM;
 
 	/*  The minimum size of the WQE is 32 bytes, hence
-	 *  MAX_SEND_BUFFERS_PER_QUEUE represents the maximum number of WQEs
+	 *  apc->tx_queue_size represents the maximum number of WQEs
 	 *  the SQ can store. This value is then used to size other queues
 	 *  to prevent overflow.
+	 *  Also note that the txq_size is always going to be MANA_PAGE_ALIGNED,
+	 *  as min val of apc->tx_queue_size is 128 and that would make
+	 *  txq_size 128*32 = 4096 and the other higher values of apc->tx_queue_size
+	 *  are always power of two
 	 */
-	txq_size = MAX_SEND_BUFFERS_PER_QUEUE * 32;
-	BUILD_BUG_ON(!MANA_PAGE_ALIGNED(txq_size));
+	txq_size = apc->tx_queue_size * 32;
 
-	cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE;
-	cq_size = MANA_PAGE_ALIGN(cq_size);
+	cq_size = apc->tx_queue_size * COMP_ENTRY_SIZE;
 
 	gc = gd->gdma_context;
 
@@ -2155,10 +2157,11 @@ static int mana_push_wqe(struct mana_rxq *rxq)
 
 static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 {
+	struct mana_port_context *mpc = netdev_priv(rxq->ndev);
 	struct page_pool_params pprm = {};
 	int ret;
 
-	pprm.pool_size = RX_BUFFERS_PER_QUEUE;
+	pprm.pool_size = mpc->rx_queue_size;
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
@@ -2190,13 +2193,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	gc = gd->gdma_context;
 
-	rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE),
+	rxq = kzalloc(struct_size(rxq, rx_oobs, apc->rx_queue_size),
 		      GFP_KERNEL);
 	if (!rxq)
 		return NULL;
 
 	rxq->ndev = ndev;
-	rxq->num_rx_buf = RX_BUFFERS_PER_QUEUE;
+	rxq->num_rx_buf = apc->rx_queue_size;
 	rxq->rxq_idx = rxq_idx;
 	rxq->rxobj = INVALID_MANA_HANDLE;
 
@@ -2744,6 +2747,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->ndev = ndev;
 	apc->max_queues = gc->max_num_queues;
 	apc->num_queues = gc->max_num_queues;
+	apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE;
+	apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE;
 	apc->port_handle = INVALID_MANA_HANDLE;
 	apc->pf_filter_handle = INVALID_MANA_HANDLE;
 	apc->port_idx = port_idx;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 146d5db1792f..d6a35fbda447 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -369,6 +369,78 @@ static int mana_set_channels(struct net_device *ndev,
 	return err;
 }
 
+static void mana_get_ringparam(struct net_device *ndev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+
+	ring->rx_pending = apc->rx_queue_size;
+	ring->tx_pending = apc->tx_queue_size;
+	ring->rx_max_pending = MAX_RX_BUFFERS_PER_QUEUE;
+	ring->tx_max_pending = MAX_TX_BUFFERS_PER_QUEUE;
+}
+
+static int mana_set_ringparam(struct net_device *ndev,
+			      struct ethtool_ringparam *ring,
+			      struct kernel_ethtool_ringparam *kernel_ring,
+			      struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	u32 new_tx, new_rx;
+	u32 old_tx, old_rx;
+	int err;
+
+	old_tx = apc->tx_queue_size;
+	old_rx = apc->rx_queue_size;
+
+	if (ring->tx_pending < MIN_TX_BUFFERS_PER_QUEUE) {
+		NL_SET_ERR_MSG_FMT(extack, "tx:%d less than the min:%d", ring->tx_pending,
+				   MIN_TX_BUFFERS_PER_QUEUE);
+		return -EINVAL;
+	}
+
+	if (ring->rx_pending < MIN_RX_BUFFERS_PER_QUEUE) {
+		NL_SET_ERR_MSG_FMT(extack, "rx:%d less than the min:%d", ring->rx_pending,
+				   MIN_RX_BUFFERS_PER_QUEUE);
+		return -EINVAL;
+	}
+
+	new_rx = roundup_pow_of_two(ring->rx_pending);
+	new_tx = roundup_pow_of_two(ring->tx_pending);
+	netdev_info(ndev, "Using nearest power of 2 values for Txq:%d Rxq:%d\n",
+		    new_tx, new_rx);
+
+	/* pre-allocating new buffers to prevent failures in mana_attach() later */
+	apc->rx_queue_size = new_rx;
+	err = mana_pre_alloc_rxbufs(apc, ndev->mtu);
+	apc->rx_queue_size = old_rx;
+	if (err) {
+		netdev_err(ndev, "Insufficient memory for new allocations\n");
+		return err;
+	}
+
+	err = mana_detach(ndev, false);
+	if (err) {
+		netdev_err(ndev, "mana_detach failed: %d\n", err);
+		goto out;
+	}
+
+	apc->tx_queue_size = new_tx;
+	apc->rx_queue_size = new_rx;
+
+	err = mana_attach(ndev);
+	if (err) {
+		netdev_err(ndev, "mana_attach failed: %d\n", err);
+		apc->tx_queue_size = old_tx;
+		apc->rx_queue_size = old_rx;
+	}
+out:
+	mana_pre_dealloc_rxbufs(apc);
+	return err;
+}
+
 const struct ethtool_ops mana_ethtool_ops = {
 	.get_ethtool_stats	= mana_get_ethtool_stats,
 	.get_sset_count		= mana_get_sset_count,
@@ -380,4 +452,6 @@ const struct ethtool_ops mana_ethtool_ops = {
 	.set_rxfh		= mana_set_rxfh,
 	.get_channels		= mana_get_channels,
 	.set_channels		= mana_set_channels,
+	.get_ringparam          = mana_get_ringparam,
+	.set_ringparam          = mana_set_ringparam,
 };
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 7caa334f4888..1f869624811d 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -38,9 +38,21 @@ enum TRI_STATE {
 
 #define COMP_ENTRY_SIZE 64
 
-#define RX_BUFFERS_PER_QUEUE 512
+/* This Max value for RX buffers is derived from __alloc_page()'s max page
+ * allocation calculation. It allows maximum 2^(MAX_ORDER -1) pages. RX buffer
+ * size beyond this value gets rejected by __alloc_page() call.
+ */
+#define MAX_RX_BUFFERS_PER_QUEUE 8192
+#define DEF_RX_BUFFERS_PER_QUEUE 512
+#define MIN_RX_BUFFERS_PER_QUEUE 128
 
-#define MAX_SEND_BUFFERS_PER_QUEUE 256
+/* This max value for TX buffers is derived as the maximum allocatable
+ * pages supported on host per guest through testing. TX buffer size beyond
+ * this value is rejected by the hardware.
+ */
+#define MAX_TX_BUFFERS_PER_QUEUE 16384
+#define DEF_TX_BUFFERS_PER_QUEUE 256
+#define MIN_TX_BUFFERS_PER_QUEUE 128
 
 #define EQ_SIZE (8 * MANA_PAGE_SIZE)
 
@@ -286,7 +298,7 @@ struct mana_recv_buf_oob {
 	void *buf_va;
 	bool from_pool; /* allocated from a page pool */
 
-	/* SGL of the buffer going to be sent has part of the work request. */
+	/* SGL of the buffer going to be sent as part of the work request. */
 	u32 num_sge;
 	struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES];
 
@@ -438,6 +450,9 @@ struct mana_port_context {
 	unsigned int max_queues;
 	unsigned int num_queues;
 
+	unsigned int rx_queue_size;
+	unsigned int tx_queue_size;
+
 	mana_handle_t port_handle;
 	mana_handle_t pf_filter_handle;
 
@@ -473,6 +488,8 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
 void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 void mana_query_gf_stats(struct mana_port_context *apc);
+int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu);
+void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
 
 extern const struct ethtool_ops mana_ethtool_ops;
 
-- 
cgit v1.3-3-g829e


From 85d4cf56e95ae0bb381587f229420a0eb6ab1d0a Mon Sep 17 00:00:00 2001
From: A K M Fazla Mehrab <a.mehrab@bytedance.com>
Date: Mon, 26 Aug 2024 18:26:52 +0000
Subject: net/handshake: use sockfd_put() helper

Replace fput() with sockfd_put() in handshake_nl_done_doit().

Signed-off-by: A K M Fazla Mehrab <a.mehrab@bytedance.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://patch.msgid.link/20240826182652.2449359-1-a.mehrab@bytedance.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/handshake/netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c
index 89637e732866..7e46d130dce2 100644
--- a/net/handshake/netlink.c
+++ b/net/handshake/netlink.c
@@ -153,7 +153,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
 	if (!req) {
 		err = -EBUSY;
 		trace_handshake_cmd_done_err(net, req, sock->sk, err);
-		fput(sock->file);
+		sockfd_put(sock);
 		return err;
 	}
 
@@ -164,7 +164,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
 		status = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_STATUS]);
 
 	handshake_complete(req, status, info);
-	fput(sock->file);
+	sockfd_put(sock);
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From e3717f2ad1a2620730a7086e032ffa7242f8aa23 Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Mon, 26 Aug 2024 21:43:05 +0000
Subject: dt-bindings: net: dsa: microchip: Add KSZ8895/KSZ8864 switch support

KSZ8895/KSZ8864 is a switch family developed before KSZ8795 and after
KSZ8863, so it shares some registers and functions in those switches.
KSZ8895 has 5 ports and so is more similar to KSZ8795.

KSZ8864 is a 4-port version of KSZ8895.  The first port is removed
while port 5 remains as a host port.

Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/BYAPR11MB3558FD0717772263FAD86846EC8B2@BYAPR11MB3558.namprd11.prod.outlook.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
index c589ebc2c7be..30c0c3e6f37a 100644
--- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml
@@ -22,7 +22,9 @@ properties:
       - microchip,ksz8794
       - microchip,ksz8795
       - microchip,ksz8863
+      - microchip,ksz8864  # 4-port version of KSZ8895 family switch
       - microchip,ksz8873
+      - microchip,ksz8895  # 5-port version of KSZ8895 family switch
       - microchip,ksz9477
       - microchip,ksz9897
       - microchip,ksz9896
-- 
cgit v1.3-3-g829e


From a96c5515d0d15df103598b2bc57245d66143b5dd Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Mon, 26 Aug 2024 21:43:08 +0000
Subject: net: dsa: microchip: Add KSZ8895/KSZ8864 switch support

KSZ8895/KSZ8864 is a switch family between KSZ8863/73 and KSZ8795, so it
shares some registers and functions in those switches already
implemented in the KSZ DSA driver.

Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Tested-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz8795.c         |  16 ++--
 drivers/net/dsa/microchip/ksz_common.c      | 134 ++++++++++++++++++++++++++--
 drivers/net/dsa/microchip/ksz_common.h      |  25 +++++-
 drivers/net/dsa/microchip/ksz_dcb.c         |   2 +-
 drivers/net/dsa/microchip/ksz_spi.c         |  15 +++-
 include/linux/platform_data/microchip-ksz.h |   2 +
 6 files changed, 178 insertions(+), 16 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index a01079297a8c..aa09d89debf0 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -188,6 +188,8 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu)
 	case KSZ8765_CHIP_ID:
 		return ksz8795_change_mtu(dev, frame_size);
 	case KSZ8830_CHIP_ID:
+	case KSZ8864_CHIP_ID:
+	case KSZ8895_CHIP_ID:
 		return ksz8863_change_mtu(dev, frame_size);
 	}
 
@@ -384,7 +386,7 @@ static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
 void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
 		    u64 *dropped, u64 *cnt)
 {
-	if (ksz_is_ksz88x3(dev))
+	if (is_ksz88xx(dev))
 		ksz8863_r_mib_pkt(dev, port, addr, dropped, cnt);
 	else
 		ksz8795_r_mib_pkt(dev, port, addr, dropped, cnt);
@@ -392,7 +394,7 @@ void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
 
 void ksz8_freeze_mib(struct ksz_device *dev, int port, bool freeze)
 {
-	if (ksz_is_ksz88x3(dev))
+	if (is_ksz88xx(dev))
 		return;
 
 	/* enable the port for flush/freeze function */
@@ -410,7 +412,8 @@ void ksz8_port_init_cnt(struct ksz_device *dev, int port)
 	struct ksz_port_mib *mib = &dev->ports[port].mib;
 	u64 *dropped;
 
-	if (!ksz_is_ksz88x3(dev)) {
+	/* For KSZ8795 family. */
+	if (ksz_is_ksz87xx(dev)) {
 		/* flush all enabled port MIB counters */
 		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true);
 		ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FLUSH, true);
@@ -609,11 +612,11 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr,
 			shifts[STATIC_MAC_FWD_PORTS];
 	alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0;
 
-	/* KSZ8795 family switches have STATIC_MAC_TABLE_USE_FID and
+	/* KSZ8795/KSZ8895 family switches have STATIC_MAC_TABLE_USE_FID and
 	 * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the
 	 * static MAC table compared to doing write.
 	 */
-	if (ksz_is_ksz87xx(dev))
+	if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev))
 		data_hi >>= 1;
 	alu->is_static = true;
 	alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0;
@@ -1692,7 +1695,8 @@ void ksz8_config_cpu_port(struct dsa_switch *ds)
 	for (i = 0; i < dev->phy_port_cnt; i++) {
 		p = &dev->ports[i];
 
-		if (!ksz_is_ksz88x3(dev)) {
+		/* For KSZ8795 family. */
+		if (ksz_is_ksz87xx(dev)) {
 			ksz_pread8(dev, i, regs[P_REMOTE_STATUS], &remote);
 			if (remote & KSZ8_PORT_FIBER_MODE)
 				p->fiber = 1;
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index cd3991792b69..6609bf271ad0 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2,7 +2,7 @@
 /*
  * Microchip switch driver main logic
  *
- * Copyright (C) 2017-2019 Microchip Technology Inc.
+ * Copyright (C) 2017-2024 Microchip Technology Inc.
  */
 
 #include <linux/delay.h>
@@ -277,7 +277,7 @@ static const struct phylink_mac_ops ksz8_phylink_mac_ops = {
 	.mac_link_up	= ksz8_phylink_mac_link_up,
 };
 
-static const struct ksz_dev_ops ksz88x3_dev_ops = {
+static const struct ksz_dev_ops ksz88xx_dev_ops = {
 	.setup = ksz8_setup,
 	.get_port_addr = ksz8_get_port_addr,
 	.cfg_port_member = ksz8_cfg_port_member,
@@ -572,6 +572,61 @@ static u8 ksz8863_shifts[] = {
 	[DYNAMIC_MAC_SRC_PORT]		= 20,
 };
 
+static const u16 ksz8895_regs[] = {
+	[REG_SW_MAC_ADDR]		= 0x68,
+	[REG_IND_CTRL_0]		= 0x6E,
+	[REG_IND_DATA_8]		= 0x70,
+	[REG_IND_DATA_CHECK]		= 0x72,
+	[REG_IND_DATA_HI]		= 0x71,
+	[REG_IND_DATA_LO]		= 0x75,
+	[REG_IND_MIB_CHECK]		= 0x75,
+	[P_FORCE_CTRL]			= 0x0C,
+	[P_LINK_STATUS]			= 0x0E,
+	[P_LOCAL_CTRL]			= 0x0C,
+	[P_NEG_RESTART_CTRL]		= 0x0D,
+	[P_REMOTE_STATUS]		= 0x0E,
+	[P_SPEED_STATUS]		= 0x09,
+	[S_TAIL_TAG_CTRL]		= 0x0C,
+	[P_STP_CTRL]			= 0x02,
+	[S_START_CTRL]			= 0x01,
+	[S_BROADCAST_CTRL]		= 0x06,
+	[S_MULTICAST_CTRL]		= 0x04,
+};
+
+static const u32 ksz8895_masks[] = {
+	[PORT_802_1P_REMAPPING]		= BIT(7),
+	[SW_TAIL_TAG_ENABLE]		= BIT(1),
+	[MIB_COUNTER_OVERFLOW]		= BIT(7),
+	[MIB_COUNTER_VALID]		= BIT(6),
+	[VLAN_TABLE_FID]		= GENMASK(6, 0),
+	[VLAN_TABLE_MEMBERSHIP]		= GENMASK(11, 7),
+	[VLAN_TABLE_VALID]		= BIT(12),
+	[STATIC_MAC_TABLE_VALID]	= BIT(21),
+	[STATIC_MAC_TABLE_USE_FID]	= BIT(23),
+	[STATIC_MAC_TABLE_FID]		= GENMASK(30, 24),
+	[STATIC_MAC_TABLE_OVERRIDE]	= BIT(22),
+	[STATIC_MAC_TABLE_FWD_PORTS]	= GENMASK(20, 16),
+	[DYNAMIC_MAC_TABLE_ENTRIES_H]	= GENMASK(6, 0),
+	[DYNAMIC_MAC_TABLE_MAC_EMPTY]	= BIT(7),
+	[DYNAMIC_MAC_TABLE_NOT_READY]	= BIT(7),
+	[DYNAMIC_MAC_TABLE_ENTRIES]	= GENMASK(31, 29),
+	[DYNAMIC_MAC_TABLE_FID]		= GENMASK(22, 16),
+	[DYNAMIC_MAC_TABLE_SRC_PORT]	= GENMASK(26, 24),
+	[DYNAMIC_MAC_TABLE_TIMESTAMP]	= GENMASK(28, 27),
+};
+
+static const u8 ksz8895_shifts[] = {
+	[VLAN_TABLE_MEMBERSHIP_S]	= 7,
+	[VLAN_TABLE]			= 13,
+	[STATIC_MAC_FWD_PORTS]		= 16,
+	[STATIC_MAC_FID]		= 24,
+	[DYNAMIC_MAC_ENTRIES_H]		= 3,
+	[DYNAMIC_MAC_ENTRIES]		= 29,
+	[DYNAMIC_MAC_FID]		= 16,
+	[DYNAMIC_MAC_TIMESTAMP]		= 27,
+	[DYNAMIC_MAC_SRC_PORT]		= 24,
+};
+
 static const u16 ksz9477_regs[] = {
 	[REG_SW_MAC_ADDR]		= 0x0302,
 	[P_STP_CTRL]			= 0x0B04,
@@ -1397,7 +1452,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.port_cnt = 3,
 		.num_tx_queues = 4,
 		.num_ipms = 4,
-		.ops = &ksz88x3_dev_ops,
+		.ops = &ksz88xx_dev_ops,
 		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
 		.mib_names = ksz88xx_mib_names,
 		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
@@ -1412,6 +1467,61 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.rd_table = &ksz8873_register_set,
 	},
 
+	[KSZ8864] = {
+		/* WARNING
+		 * =======
+		 * KSZ8864 is similar to KSZ8895, except the first port
+		 * does not exist.
+		 *           external  cpu
+		 * KSZ8864   1,2,3      4
+		 * KSZ8895   0,1,2,3    4
+		 * port_cnt is configured as 5, even though it is 4
+		 */
+		.chip_id = KSZ8864_CHIP_ID,
+		.dev_name = "KSZ8864",
+		.num_vlans = 4096,
+		.num_alus = 0,
+		.num_statics = 32,
+		.cpu_ports = 0x10,	/* can be configured as cpu port */
+		.port_cnt = 5,		/* total cpu and user ports */
+		.num_tx_queues = 4,
+		.num_ipms = 4,
+		.ops = &ksz88xx_dev_ops,
+		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
+		.mib_names = ksz88xx_mib_names,
+		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
+		.reg_mib_cnt = MIB_COUNTER_NUM,
+		.regs = ksz8895_regs,
+		.masks = ksz8895_masks,
+		.shifts = ksz8895_shifts,
+		.supports_mii = {false, false, false, false, true},
+		.supports_rmii = {false, false, false, false, true},
+		.internal_phy = {false, true, true, true, false},
+	},
+
+	[KSZ8895] = {
+		.chip_id = KSZ8895_CHIP_ID,
+		.dev_name = "KSZ8895",
+		.num_vlans = 4096,
+		.num_alus = 0,
+		.num_statics = 32,
+		.cpu_ports = 0x10,	/* can be configured as cpu port */
+		.port_cnt = 5,		/* total cpu and user ports */
+		.num_tx_queues = 4,
+		.num_ipms = 4,
+		.ops = &ksz88xx_dev_ops,
+		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
+		.mib_names = ksz88xx_mib_names,
+		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
+		.reg_mib_cnt = MIB_COUNTER_NUM,
+		.regs = ksz8895_regs,
+		.masks = ksz8895_masks,
+		.shifts = ksz8895_shifts,
+		.supports_mii = {false, false, false, false, true},
+		.supports_rmii = {false, false, false, false, true},
+		.internal_phy = {true, true, true, true, false},
+	},
+
 	[KSZ9477] = {
 		.chip_id = KSZ9477_CHIP_ID,
 		.dev_name = "KSZ9477",
@@ -2937,9 +3047,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 	struct ksz_device *dev = ds->priv;
 	enum dsa_tag_protocol proto = DSA_TAG_PROTO_NONE;
 
-	if (dev->chip_id == KSZ8795_CHIP_ID ||
-	    dev->chip_id == KSZ8794_CHIP_ID ||
-	    dev->chip_id == KSZ8765_CHIP_ID)
+	if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev))
 		proto = DSA_TAG_PROTO_KSZ8795;
 
 	if (dev->chip_id == KSZ8830_CHIP_ID ||
@@ -3055,6 +3163,8 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
 	case KSZ8765_CHIP_ID:
 		return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
 	case KSZ8830_CHIP_ID:
+	case KSZ8864_CHIP_ID:
+	case KSZ8895_CHIP_ID:
 		return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
 	case KSZ8563_CHIP_ID:
 	case KSZ8567_CHIP_ID:
@@ -3412,6 +3522,18 @@ static int ksz_switch_detect(struct ksz_device *dev)
 		else
 			return -ENODEV;
 		break;
+	case KSZ8895_FAMILY_ID:
+		if (id2 == KSZ8895_CHIP_ID_95 ||
+		    id2 == KSZ8895_CHIP_ID_95R)
+			dev->chip_id = KSZ8895_CHIP_ID;
+		else
+			return -ENODEV;
+		ret = ksz_read8(dev, REG_KSZ8864_CHIP_ID, &id4);
+		if (ret)
+			return ret;
+		if (id4 & SW_KSZ8864)
+			dev->chip_id = KSZ8864_CHIP_ID;
+		break;
 	default:
 		ret = ksz_read32(dev, REG_CHIP_ID0, &id32);
 		if (ret)
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index 8094d90d6ca4..e08d5a1339f4 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Microchip switch driver common header
  *
- * Copyright (C) 2017-2019 Microchip Technology Inc.
+ * Copyright (C) 2017-2024 Microchip Technology Inc.
  */
 
 #ifndef __KSZ_COMMON_H
@@ -201,6 +201,8 @@ enum ksz_model {
 	KSZ8794,
 	KSZ8765,
 	KSZ8830,
+	KSZ8864,
+	KSZ8895,
 	KSZ9477,
 	KSZ9896,
 	KSZ9897,
@@ -629,9 +631,21 @@ static inline bool ksz_is_ksz88x3(struct ksz_device *dev)
 	return dev->chip_id == KSZ8830_CHIP_ID;
 }
 
+static inline bool ksz_is_8895_family(struct ksz_device *dev)
+{
+	return dev->chip_id == KSZ8895_CHIP_ID ||
+	       dev->chip_id == KSZ8864_CHIP_ID;
+}
+
 static inline bool is_ksz8(struct ksz_device *dev)
 {
-	return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev);
+	return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev) ||
+	       ksz_is_8895_family(dev);
+}
+
+static inline bool is_ksz88xx(struct ksz_device *dev)
+{
+	return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev);
 }
 
 static inline bool is_ksz9477(struct ksz_device *dev)
@@ -665,6 +679,7 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define SW_FAMILY_ID_M			GENMASK(15, 8)
 #define KSZ87_FAMILY_ID			0x87
 #define KSZ88_FAMILY_ID			0x88
+#define KSZ8895_FAMILY_ID		0x95
 
 #define KSZ8_PORT_STATUS_0		0x08
 #define KSZ8_PORT_FIBER_MODE		BIT(7)
@@ -673,6 +688,12 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port)
 #define KSZ87_CHIP_ID_94		0x6
 #define KSZ87_CHIP_ID_95		0x9
 #define KSZ88_CHIP_ID_63		0x3
+#define KSZ8895_CHIP_ID_95		0x4
+#define KSZ8895_CHIP_ID_95R		0x6
+
+/* KSZ8895 specific register */
+#define REG_KSZ8864_CHIP_ID		0xFE
+#define SW_KSZ8864			BIT(7)
 
 #define SW_REV_ID_M			GENMASK(7, 4)
 
diff --git a/drivers/net/dsa/microchip/ksz_dcb.c b/drivers/net/dsa/microchip/ksz_dcb.c
index 086bc9b3cf53..30b4a6186e38 100644
--- a/drivers/net/dsa/microchip/ksz_dcb.c
+++ b/drivers/net/dsa/microchip/ksz_dcb.c
@@ -113,7 +113,7 @@ static void ksz_get_default_port_prio_reg(struct ksz_device *dev, int *reg,
 static void ksz_get_dscp_prio_reg(struct ksz_device *dev, int *reg,
 				  int *per_reg, u8 *mask)
 {
-	if (ksz_is_ksz87xx(dev)) {
+	if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) {
 		*reg = KSZ8765_REG_TOS_DSCP_CTRL;
 		*per_reg = 4;
 		*mask = GENMASK(1, 0);
diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c
index 8e8d83213b04..f4287310e89f 100644
--- a/drivers/net/dsa/microchip/ksz_spi.c
+++ b/drivers/net/dsa/microchip/ksz_spi.c
@@ -2,7 +2,7 @@
 /*
  * Microchip ksz series register access through SPI
  *
- * Copyright (C) 2017 Microchip Technology Inc.
+ * Copyright (C) 2017-2024 Microchip Technology Inc.
  *	Tristram Ha <Tristram.Ha@microchip.com>
  */
 
@@ -60,6 +60,9 @@ static int ksz_spi_probe(struct spi_device *spi)
 		 chip->chip_id == KSZ8794_CHIP_ID ||
 		 chip->chip_id == KSZ8765_CHIP_ID)
 		regmap_config = ksz8795_regmap_config;
+	else if (chip->chip_id == KSZ8895_CHIP_ID ||
+		 chip->chip_id == KSZ8864_CHIP_ID)
+		regmap_config = ksz8863_regmap_config;
 	else
 		regmap_config = ksz9477_regmap_config;
 
@@ -136,10 +139,18 @@ static const struct of_device_id ksz_dt_ids[] = {
 		.compatible = "microchip,ksz8863",
 		.data = &ksz_switch_chips[KSZ8830]
 	},
+	{
+		.compatible = "microchip,ksz8864",
+		.data = &ksz_switch_chips[KSZ8864]
+	},
 	{
 		.compatible = "microchip,ksz8873",
 		.data = &ksz_switch_chips[KSZ8830]
 	},
+	{
+		.compatible = "microchip,ksz8895",
+		.data = &ksz_switch_chips[KSZ8895]
+	},
 	{
 		.compatible = "microchip,ksz9477",
 		.data = &ksz_switch_chips[KSZ9477]
@@ -201,7 +212,9 @@ static const struct spi_device_id ksz_spi_ids[] = {
 	{ "ksz8794" },
 	{ "ksz8795" },
 	{ "ksz8863" },
+	{ "ksz8864" },
 	{ "ksz8873" },
+	{ "ksz8895" },
 	{ "ksz9477" },
 	{ "ksz9896" },
 	{ "ksz9897" },
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index 8c659db4da6b..d074019474f5 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -28,6 +28,8 @@ enum ksz_chip_id {
 	KSZ8794_CHIP_ID = 0x8794,
 	KSZ8765_CHIP_ID = 0x8765,
 	KSZ8830_CHIP_ID = 0x8830,
+	KSZ8864_CHIP_ID = 0x8864,
+	KSZ8895_CHIP_ID = 0x8895,
 	KSZ9477_CHIP_ID = 0x00947700,
 	KSZ9896_CHIP_ID = 0x00989600,
 	KSZ9897_CHIP_ID = 0x00989700,
-- 
cgit v1.3-3-g829e


From 08c2182cf0b47646af7f3daa292980f95f5e1ea6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 27 Aug 2024 15:37:32 +0200
Subject: xfrm: policy: use recently added helper in more places

No logical change intended.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b79ac453ea37..94859b2182ec 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1276,11 +1276,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		struct xfrm_pol_inexact_bin *bin;
 		u8 dbits, sbits;
 
-		if (policy->walk.dead)
-			continue;
-
-		dir = xfrm_policy_id2dir(policy->index);
-		if (dir >= XFRM_POLICY_MAX)
+		if (xfrm_policy_is_dead_or_sk(policy))
 			continue;
 
 		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
@@ -1331,13 +1327,8 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 
 	/* re-insert all policies by order of creation */
 	list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
-		if (policy->walk.dead)
-			continue;
-		dir = xfrm_policy_id2dir(policy->index);
-		if (dir >= XFRM_POLICY_MAX) {
-			/* skip socket policies */
+		if (xfrm_policy_is_dead_or_sk(policy))
 			continue;
-		}
 
 		hlist_del_rcu(&policy->bydst);
 
-- 
cgit v1.3-3-g829e


From 17163f23678c7599e40758d7b96f68e3f3f2ea15 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 27 Aug 2024 15:38:23 +0200
Subject: xfrm: minor update to sdb and xfrm_policy comments

The spd is no longer maintained as a linear list.
We also haven't been caching bundles in the xfrm_policy
struct since 2010.

While at it, add kdoc style comments for the xfrm_policy structure
and extend the description of the current rbtree based search to
mention why it needs to search the candidate set.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     | 40 +++++++++++++++++++++++++++++++++++-----
 net/xfrm/xfrm_policy.c |  6 +++++-
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 1fa2da22a49e..b6bfdc6416c7 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -67,13 +67,15 @@
    - instance of a transformer, struct xfrm_state (=SA)
    - template to clone xfrm_state, struct xfrm_tmpl
 
-   SPD is plain linear list of xfrm_policy rules, ordered by priority.
+   SPD is organized as hash table (for policies that meet minimum address prefix
+   length setting, net->xfrm.policy_hthresh).  Other policies are stored in
+   lists, sorted into rbtree ordered by destination and source address networks.
+   See net/xfrm/xfrm_policy.c for details.
+
    (To be compatible with existing pfkeyv2 implementations,
    many rules with priority of 0x7fffffff are allowed to exist and
    such rules are ordered in an unpredictable way, thanks to bsd folks.)
 
-   Lookup is plain linear search until the first match with selector.
-
    If "action" is "block", then we prohibit the flow, otherwise:
    if "xfrms_nr" is zero, the flow passes untransformed. Otherwise,
    policy entry has list of up to XFRM_MAX_DEPTH transformations,
@@ -86,8 +88,6 @@
                      |---. child .-> dst -. xfrm .-> xfrm_state #3
                                       |---. child .-> NULL
 
-   Bundles are cached at xrfm_policy struct (field ->bundles).
-
 
    Resolution of xrfm_tmpl
    -----------------------
@@ -526,6 +526,36 @@ struct xfrm_policy_queue {
 	unsigned long		timeout;
 };
 
+/**
+ *	struct xfrm_policy - xfrm policy
+ *	@xp_net: network namespace the policy lives in
+ *	@bydst: hlist node for SPD hash table or rbtree list
+ *	@byidx: hlist node for index hash table
+ *	@lock: serialize changes to policy structure members
+ *	@refcnt: reference count, freed once it reaches 0
+ *	@pos: kernel internal tie-breaker to determine age of policy
+ *	@timer: timer
+ *	@genid: generation, used to invalidate old policies
+ *	@priority: priority, set by userspace
+ *	@index:  policy index (autogenerated)
+ *	@if_id: virtual xfrm interface id
+ *	@mark: packet mark
+ *	@selector: selector
+ *	@lft: liftime configuration data
+ *	@curlft: liftime state
+ *	@walk: list head on pernet policy list
+ *	@polq: queue to hold packets while aqcuire operaion in progress
+ *	@bydst_reinsert: policy tree node needs to be merged
+ *	@type: XFRM_POLICY_TYPE_MAIN or _SUB
+ *	@action: XFRM_POLICY_ALLOW or _BLOCK
+ *	@flags: XFRM_POLICY_LOCALOK, XFRM_POLICY_ICMP
+ *	@xfrm_nr: number of used templates in @xfrm_vec
+ *	@family: protocol family
+ *	@security: SELinux security label
+ *	@xfrm_vec: array of templates to resolve state
+ *	@rcu: rcu head, used to defer memory release
+ *	@xdo: hardware offload state
+ */
 struct xfrm_policy {
 	possible_net_t		xp_net;
 	struct hlist_node	bydst;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 94859b2182ec..6336baa8a93c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -109,7 +109,11 @@ struct xfrm_pol_inexact_node {
  * 4. saddr:any list from saddr tree
  *
  * This result set then needs to be searched for the policy with
- * the lowest priority.  If two results have same prio, youngest one wins.
+ * the lowest priority.  If two candidates have the same priority, the
+ * struct xfrm_policy pos member with the lower number is used.
+ *
+ * This replicates previous single-list-search algorithm which would
+ * return first matching policy in the (ordered-by-priority) list.
  */
 
 struct xfrm_pol_inexact_key {
-- 
cgit v1.3-3-g829e


From ac35180032fbc5d80b29af00ba4881815ceefcb6 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 27 Aug 2024 09:49:40 +0200
Subject: wifi: mac80211: fix RCU list iterations

There are a number of places where RCU list iteration is
used, but that aren't (always) called with RCU held. Use
just list_for_each_entry() in most, and annotate iface
iteration with the required locks.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240827094939.ed8ac0b2f897.I8443c9c3c0f8051841353491dae758021b53115e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/chan.c | 4 +++-
 net/mac80211/mlme.c | 2 +-
 net/mac80211/scan.c | 2 +-
 net/mac80211/util.c | 4 +++-
 4 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index e8567723e94d..b72e4036526b 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -286,7 +286,9 @@ ieee80211_get_max_required_bw(struct ieee80211_link_data *link)
 	enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT;
 	struct sta_info *sta;
 
-	list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) {
+	lockdep_assert_wiphy(sdata->local->hw.wiphy);
+
+	list_for_each_entry(sta, &sdata->local->sta_list, list) {
 		if (sdata != sta->sdata &&
 		    !(sta->sdata->bss && sta->sdata->bss == sdata->bss))
 			continue;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 0285924269cf..acd4fe703990 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1231,7 +1231,7 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 		bool disable_mu_mimo = false;
 		struct ieee80211_sub_if_data *other;
 
-		list_for_each_entry_rcu(other, &local->interfaces, list) {
+		list_for_each_entry(other, &local->interfaces, list) {
 			if (other->vif.bss_conf.mu_mimo_owner) {
 				disable_mu_mimo = true;
 				break;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 1c5d99975ad0..3b2bde6360bc 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -504,7 +504,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted)
 	 * the scan was in progress; if there was none this will
 	 * just be a no-op for the particular interface.
 	 */
-	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+	list_for_each_entry(sdata, &local->interfaces, list) {
 		if (ieee80211_sdata_running(sdata))
 			wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work);
 	}
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 830f736f9c13..ba61de90ba35 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -751,7 +751,9 @@ static void __iterate_interfaces(struct ieee80211_local *local,
 	struct ieee80211_sub_if_data *sdata;
 	bool active_only = iter_flags & IEEE80211_IFACE_ITER_ACTIVE;
 
-	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
+	list_for_each_entry_rcu(sdata, &local->interfaces, list,
+				lockdep_is_held(&local->iflist_mtx) ||
+				lockdep_is_held(&local->hw.wiphy->mtx)) {
 		switch (sdata->vif.type) {
 		case NL80211_IFTYPE_MONITOR:
 			if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE))
-- 
cgit v1.3-3-g829e


From 67bb124cd9ae38870667e4f9c876ef8e0f82ec44 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Tue, 27 Aug 2024 10:39:20 +0200
Subject: wifi: mac80211: Check for missing VHT elements only for 5 GHz

Check for missing VHT Capabilities and VHT Operation elements in
association response frame only for 5 GHz links.

Fixes: 310c8387c638 ("wifi: mac80211: clean up connection process")
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240827103920.dd711282d543.Iaba245cebc52209b0499d5bab7d8a8ef1df9dd65@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index acd4fe703990..6e99db7addf1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4715,7 +4715,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 	    ((assoc_data->wmm && !elems->wmm_param) ||
 	     (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT &&
 	      (!elems->ht_cap_elem || !elems->ht_operation)) ||
-	     (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT &&
+	     (is_5ghz && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT &&
 	      (!elems->vht_cap_elem || !elems->vht_operation)))) {
 		const struct cfg80211_bss_ies *ies;
 		struct ieee802_11_elems *bss_elems;
@@ -4763,19 +4763,22 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 			sdata_info(sdata,
 				   "AP bug: HT operation missing from AssocResp\n");
 		}
-		if (!elems->vht_cap_elem && bss_elems->vht_cap_elem &&
-		    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
-			elems->vht_cap_elem = bss_elems->vht_cap_elem;
-			sdata_info(sdata,
-				   "AP bug: VHT capa missing from AssocResp\n");
-		}
-		if (!elems->vht_operation && bss_elems->vht_operation &&
-		    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
-			elems->vht_operation = bss_elems->vht_operation;
-			sdata_info(sdata,
-				   "AP bug: VHT operation missing from AssocResp\n");
-		}
 
+		if (is_5ghz) {
+			if (!elems->vht_cap_elem && bss_elems->vht_cap_elem &&
+			    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
+				elems->vht_cap_elem = bss_elems->vht_cap_elem;
+				sdata_info(sdata,
+					   "AP bug: VHT capa missing from AssocResp\n");
+			}
+
+			if (!elems->vht_operation && bss_elems->vht_operation &&
+			    link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
+				elems->vht_operation = bss_elems->vht_operation;
+				sdata_info(sdata,
+					   "AP bug: VHT operation missing from AssocResp\n");
+			}
+		}
 		kfree(bss_elems);
 	}
 
-- 
cgit v1.3-3-g829e


From 8109b226f23af2b9f4a866196349992e5cdfc5d8 Mon Sep 17 00:00:00 2001
From: Yan Zhen <yanzhen@vivo.com>
Date: Tue, 27 Aug 2024 18:30:12 +0800
Subject: wifi: mac80211: scan: Use max macro

When the original file is guaranteed to contain the minmax.h header
file and compile correctly, using the real macro is usually
more intuitive and readable.

Signed-off-by: Yan Zhen <yanzhen@vivo.com>
Link: https://patch.msgid.link/20240827103012.3853588-1-yanzhen@vivo.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/scan.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 3b2bde6360bc..14e18fd9e919 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -1013,10 +1013,8 @@ set_channel:
 	 */
 	if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) ||
 	    !scan_req->n_ssids) {
-		*next_delay = msecs_to_jiffies(scan_req->duration) >
-			      IEEE80211_PASSIVE_CHANNEL_TIME ?
-			      msecs_to_jiffies(scan_req->duration) :
-			      IEEE80211_PASSIVE_CHANNEL_TIME;
+		*next_delay = max(msecs_to_jiffies(scan_req->duration),
+				  IEEE80211_PASSIVE_CHANNEL_TIME);
 		local->next_scan_state = SCAN_DECISION;
 		if (scan_req->n_ssids)
 			set_bit(SCAN_BEACON_WAIT, &local->scanning);
-- 
cgit v1.3-3-g829e


From 20361712880396e44ce80aaeec2d93d182035651 Mon Sep 17 00:00:00 2001
From: Issam Hamdi <ih@simonwunderlich.de>
Date: Fri, 16 Aug 2024 16:24:18 +0200
Subject: wifi: cfg80211: Set correct chandef when starting CAC

When starting CAC in a mode other than AP mode, it return a
"WARNING: CPU: 0 PID: 63 at cfg80211_chandef_dfs_usable+0x20/0xaf [cfg80211]"
caused by the chandef.chan being null at the end of CAC.

Solution: Ensure the channel definition is set for the different modes
when starting CAC to avoid getting a NULL 'chan' at the end of CAC.

 Call Trace:
  ? show_regs.part.0+0x14/0x16
  ? __warn+0x67/0xc0
  ? cfg80211_chandef_dfs_usable+0x20/0xaf [cfg80211]
  ? report_bug+0xa7/0x130
  ? exc_overflow+0x30/0x30
  ? handle_bug+0x27/0x50
  ? exc_invalid_op+0x18/0x60
  ? handle_exception+0xf6/0xf6
  ? exc_overflow+0x30/0x30
  ? cfg80211_chandef_dfs_usable+0x20/0xaf [cfg80211]
  ? exc_overflow+0x30/0x30
  ? cfg80211_chandef_dfs_usable+0x20/0xaf [cfg80211]
  ? regulatory_propagate_dfs_state.cold+0x1b/0x4c [cfg80211]
  ? cfg80211_propagate_cac_done_wk+0x1a/0x30 [cfg80211]
  ? process_one_work+0x165/0x280
  ? worker_thread+0x120/0x3f0
  ? kthread+0xc2/0xf0
  ? process_one_work+0x280/0x280
  ? kthread_complete_and_exit+0x20/0x20
  ? ret_from_fork+0x19/0x24

Reported-by: Kretschmer Mathias <mathias.kretschmer@fit.fraunhofer.de>
Signed-off-by: Issam Hamdi <ih@simonwunderlich.de>
Link: https://patch.msgid.link/20240816142418.3381951-1-ih@simonwunderlich.de
[shorten subject, remove OCB, reorder cases to match previous list]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7397a372c78e..b368e23847dd 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10143,7 +10143,20 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 
 	err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms);
 	if (!err) {
-		wdev->links[0].ap.chandef = chandef;
+		switch (wdev->iftype) {
+		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_P2P_GO:
+			wdev->links[0].ap.chandef = chandef;
+			break;
+		case NL80211_IFTYPE_ADHOC:
+			wdev->u.ibss.chandef = chandef;
+			break;
+		case NL80211_IFTYPE_MESH_POINT:
+			wdev->u.mesh.chandef = chandef;
+			break;
+		default:
+			break;
+		}
 		wdev->cac_started = true;
 		wdev->cac_start_time = jiffies;
 		wdev->cac_time_ms = cac_time_ms;
-- 
cgit v1.3-3-g829e


From 0fa5e94a1811d68fbffa0725efe6d4ca62c03d12 Mon Sep 17 00:00:00 2001
From: Jeongjun Park <aha310510@gmail.com>
Date: Fri, 23 Aug 2024 03:11:09 +0900
Subject: net/xen-netback: prevent UAF in xenvif_flush_hash()

During the list_for_each_entry_rcu iteration call of xenvif_flush_hash,
kfree_rcu does not exist inside the rcu read critical section, so if
kfree_rcu is called when the rcu grace period ends during the iteration,
UAF occurs when accessing head->next after the entry becomes free.

Therefore, to solve this, you need to change it to list_for_each_entry_safe.

Signed-off-by: Jeongjun Park <aha310510@gmail.com>
Link: https://patch.msgid.link/20240822181109.2577354-1-aha310510@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/xen-netback/hash.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index ff96f22648ef..45ddce35f6d2 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -95,7 +95,7 @@ static u32 xenvif_new_hash(struct xenvif *vif, const u8 *data,
 
 static void xenvif_flush_hash(struct xenvif *vif)
 {
-	struct xenvif_hash_cache_entry *entry;
+	struct xenvif_hash_cache_entry *entry, *n;
 	unsigned long flags;
 
 	if (xenvif_hash_cache_size == 0)
@@ -103,8 +103,7 @@ static void xenvif_flush_hash(struct xenvif *vif)
 
 	spin_lock_irqsave(&vif->hash.cache.lock, flags);
 
-	list_for_each_entry_rcu(entry, &vif->hash.cache.list, link,
-				lockdep_is_held(&vif->hash.cache.lock)) {
+	list_for_each_entry_safe(entry, n, &vif->hash.cache.list, link) {
 		list_del_rcu(&entry->link);
 		vif->hash.cache.count--;
 		kfree_rcu(entry, rcu);
-- 
cgit v1.3-3-g829e


From 3e5cbbb1fb9a64588a2c6ddc5e432a303d36a488 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Aug 2024 01:52:49 +0000
Subject: tcp: remove volatile qualifier on tw_substate

Using a volatile qualifier for a specific struct field is unusual.

Use instead READ_ONCE()/WRITE_ONCE() where necessary.

tcp_timewait_state_process() can change tw_substate while other
threads are reading this field.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20240827015250.3509197-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_timewait_sock.h | 2 +-
 net/ipv4/inet_diag.c             | 4 ++--
 net/ipv4/tcp_ipv4.c              | 4 ++--
 net/ipv4/tcp_minisocks.c         | 4 ++--
 net/ipv6/tcp_ipv6.c              | 2 +-
 5 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index f88b68269012..beb533a0e880 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -58,7 +58,7 @@ struct inet_timewait_sock {
 #define tw_dr			__tw_common.skc_tw_dr
 
 	__u32			tw_mark;
-	volatile unsigned char	tw_substate;
+	unsigned char		tw_substate;
 	unsigned char		tw_rcv_wscale;
 
 	/* Socket demultiplex comparisons on incoming packets. */
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 9712cdb8087c..67639309163d 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -442,7 +442,7 @@ static int inet_twsk_diag_fill(struct sock *sk,
 	inet_diag_msg_common_fill(r, sk);
 	r->idiag_retrans      = 0;
 
-	r->idiag_state	      = tw->tw_substate;
+	r->idiag_state	      = READ_ONCE(tw->tw_substate);
 	r->idiag_timer	      = 3;
 	tmo = tw->tw_timer.expires - jiffies;
 	r->idiag_expires      = jiffies_delta_to_msecs(tmo);
@@ -1209,7 +1209,7 @@ next_chunk:
 			if (num < s_num)
 				goto next_normal;
 			state = (sk->sk_state == TCP_TIME_WAIT) ?
-				inet_twsk(sk)->tw_substate : sk->sk_state;
+				READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state;
 			if (!(idiag_states & (1 << state)))
 				goto next_normal;
 			if (r->sdiag_family != AF_UNSPEC &&
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5087e12209a1..7c29158e1abc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -120,7 +120,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int ts_recent_stamp;
 
-	if (tw->tw_substate == TCP_FIN_WAIT2)
+	if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2)
 		reuse = 0;
 
 	if (reuse == 2) {
@@ -2948,7 +2948,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
 		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK",
-		i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
+		i, src, srcp, dest, destp, READ_ONCE(tw->tw_substate), 0, 0,
 		3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
 		refcount_read(&tw->tw_refcnt), tw);
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a19a9dbd3409..b6d547d29f9a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -117,7 +117,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		}
 	}
 
-	if (tw->tw_substate == TCP_FIN_WAIT2) {
+	if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) {
 		/* Just repeat all the checks of tcp_rcv_state_process() */
 
 		/* Out of window, send ACK */
@@ -150,7 +150,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			return TCP_TW_RST;
 
 		/* FIN arrived, enter true time-wait state. */
-		tw->tw_substate	  = TCP_TIME_WAIT;
+		WRITE_ONCE(tw->tw_substate, TCP_TIME_WAIT);
 		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
 
 		if (tmp_opt.saw_tstamp) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 200fea92f12f..fb2e64ce660f 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2258,7 +2258,7 @@ static void get_timewait6_sock(struct seq_file *seq,
 		   src->s6_addr32[2], src->s6_addr32[3], srcp,
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
-		   tw->tw_substate, 0, 0,
+		   READ_ONCE(tw->tw_substate), 0, 0,
 		   3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
 		   refcount_read(&tw->tw_refcnt), tw);
 }
-- 
cgit v1.3-3-g829e


From c0a11493ee6141d475fc96cf3ba24441299c9f16 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 27 Aug 2024 01:52:50 +0000
Subject: tcp: annotate data-races around tcptw->tw_rcv_nxt

No lock protects tcp tw fields.

tcptw->tw_rcv_nxt can be changed from twsk_rcv_nxt_update()
while other threads might read this field.

Add READ_ONCE()/WRITE_ONCE() annotations, and make sure
tcp_timewait_state_process() reads tcptw->tw_rcv_nxt only once.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20240827015250.3509197-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_ipv4.c      |  2 +-
 net/ipv4/tcp_minisocks.c | 27 +++++++++++++++------------
 net/ipv6/tcp_ipv6.c      |  3 ++-
 3 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7c29158e1abc..eb631e66ee03 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1073,7 +1073,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	}
 
 	tcp_v4_send_ack(sk, skb,
-			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+			tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt),
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_tw_tsval(tcptw),
 			READ_ONCE(tcptw->tw_ts_recent),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b6d547d29f9a..ad562272db2e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -52,16 +52,17 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
 	return TCP_TW_SUCCESS;
 }
 
-static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq)
+static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq,
+				u32 rcv_nxt)
 {
 #ifdef CONFIG_TCP_AO
 	struct tcp_ao_info *ao;
 
 	ao = rcu_dereference(tcptw->ao_info);
-	if (unlikely(ao && seq < tcptw->tw_rcv_nxt))
+	if (unlikely(ao && seq < rcv_nxt))
 		WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1);
 #endif
-	tcptw->tw_rcv_nxt = seq;
+	WRITE_ONCE(tcptw->tw_rcv_nxt, seq);
 }
 
 /*
@@ -98,8 +99,9 @@ enum tcp_tw_status
 tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 			   const struct tcphdr *th, u32 *tw_isn)
 {
-	struct tcp_options_received tmp_opt;
 	struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+	u32 rcv_nxt = READ_ONCE(tcptw->tw_rcv_nxt);
+	struct tcp_options_received tmp_opt;
 	bool paws_reject = false;
 	int ts_recent_stamp;
 
@@ -123,20 +125,20 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		/* Out of window, send ACK */
 		if (paws_reject ||
 		    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
-				   tcptw->tw_rcv_nxt,
-				   tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
+				   rcv_nxt,
+				   rcv_nxt + tcptw->tw_rcv_wnd))
 			return tcp_timewait_check_oow_rate_limit(
 				tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2);
 
 		if (th->rst)
 			goto kill;
 
-		if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt))
+		if (th->syn && !before(TCP_SKB_CB(skb)->seq, rcv_nxt))
 			return TCP_TW_RST;
 
 		/* Dup ACK? */
 		if (!th->ack ||
-		    !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) ||
+		    !after(TCP_SKB_CB(skb)->end_seq, rcv_nxt) ||
 		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) {
 			inet_twsk_put(tw);
 			return TCP_TW_SUCCESS;
@@ -146,12 +148,13 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		 * reset.
 		 */
 		if (!th->fin ||
-		    TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1)
+		    TCP_SKB_CB(skb)->end_seq != rcv_nxt + 1)
 			return TCP_TW_RST;
 
 		/* FIN arrived, enter true time-wait state. */
 		WRITE_ONCE(tw->tw_substate, TCP_TIME_WAIT);
-		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
+		twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq,
+				    rcv_nxt);
 
 		if (tmp_opt.saw_tstamp) {
 			WRITE_ONCE(tcptw->tw_ts_recent_stamp,
@@ -182,7 +185,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	 */
 
 	if (!paws_reject &&
-	    (TCP_SKB_CB(skb)->seq == tcptw->tw_rcv_nxt &&
+	    (TCP_SKB_CB(skb)->seq == rcv_nxt &&
 	     (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) {
 		/* In window segment, it may be only reset or bare ack. */
 
@@ -229,7 +232,7 @@ kill:
 	 */
 
 	if (th->syn && !th->rst && !th->ack && !paws_reject &&
-	    (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) ||
+	    (after(TCP_SKB_CB(skb)->seq, rcv_nxt) ||
 	     (tmp_opt.saw_tstamp &&
 	      (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) {
 		u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fb2e64ce660f..d71ab4e1efe1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1193,7 +1193,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 #endif
 	}
 
-	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt,
+			READ_ONCE(tcptw->tw_rcv_nxt),
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_tw_tsval(tcptw),
 			READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,
-- 
cgit v1.3-3-g829e


From e24a6c874601efb3de6e535895dd8e4f56fa98f1 Mon Sep 17 00:00:00 2001
From: Jacky Chou <jacky_chou@aspeedtech.com>
Date: Tue, 27 Aug 2024 11:05:13 +0800
Subject: net: ftgmac100: Get link speed and duplex for NC-SI

The ethtool of this driver uses the phy API of ethtool
to get the link information from PHY driver.
Because the NC-SI is forced on 100Mbps and full duplex,
the driver connect a fixed-link phy driver for NC-SI.
The ethtool will get the link information from the
fixed-link phy driver.

Signed-off-by: Jacky Chou <jacky_chou@aspeedtech.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240827030513.481469-1-jacky_chou@aspeedtech.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/faraday/ftgmac100.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index fddfd1dd5070..444671b8bbe2 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -24,6 +24,7 @@
 #include <linux/crc32.h>
 #include <linux/if_vlan.h>
 #include <linux/of_net.h>
+#include <linux/phy_fixed.h>
 #include <net/ip.h>
 #include <net/ncsi.h>
 
@@ -50,6 +51,15 @@
 #define FTGMAC_100MHZ		100000000
 #define FTGMAC_25MHZ		25000000
 
+/* For NC-SI to register a fixed-link phy device */
+static struct fixed_phy_status ncsi_phy_status = {
+	.link = 1,
+	.speed = SPEED_100,
+	.duplex = DUPLEX_FULL,
+	.pause = 0,
+	.asym_pause = 0
+};
+
 struct ftgmac100 {
 	/* Registers */
 	struct resource *res;
@@ -1531,7 +1541,8 @@ static int ftgmac100_open(struct net_device *netdev)
 	if (netdev->phydev) {
 		/* If we have a PHY, start polling */
 		phy_start(netdev->phydev);
-	} else if (priv->use_ncsi) {
+	}
+	if (priv->use_ncsi) {
 		/* If using NC-SI, set our carrier on and start the stack */
 		netif_carrier_on(netdev);
 
@@ -1544,6 +1555,7 @@ static int ftgmac100_open(struct net_device *netdev)
 	return 0;
 
  err_ncsi:
+	phy_stop(netdev->phydev);
 	napi_disable(&priv->napi);
 	netif_stop_queue(netdev);
  err_alloc:
@@ -1577,7 +1589,7 @@ static int ftgmac100_stop(struct net_device *netdev)
 	netif_napi_del(&priv->napi);
 	if (netdev->phydev)
 		phy_stop(netdev->phydev);
-	else if (priv->use_ncsi)
+	if (priv->use_ncsi)
 		ncsi_stop_dev(priv->ndev);
 
 	ftgmac100_stop_hw(priv);
@@ -1715,6 +1727,9 @@ static void ftgmac100_phy_disconnect(struct net_device *netdev)
 	phy_disconnect(netdev->phydev);
 	if (of_phy_is_fixed_link(priv->dev->of_node))
 		of_phy_deregister_fixed_link(priv->dev->of_node);
+
+	if (priv->use_ncsi)
+		fixed_phy_unregister(netdev->phydev);
 }
 
 static void ftgmac100_destroy_mdio(struct net_device *netdev)
@@ -1792,6 +1807,7 @@ static int ftgmac100_probe(struct platform_device *pdev)
 	struct resource *res;
 	int irq;
 	struct net_device *netdev;
+	struct phy_device *phydev;
 	struct ftgmac100 *priv;
 	struct device_node *np;
 	int err = 0;
@@ -1879,6 +1895,14 @@ static int ftgmac100_probe(struct platform_device *pdev)
 			err = -EINVAL;
 			goto err_phy_connect;
 		}
+
+		phydev = fixed_phy_register(PHY_POLL, &ncsi_phy_status, NULL);
+		err = phy_connect_direct(netdev, phydev, ftgmac100_adjust_link,
+					 PHY_INTERFACE_MODE_MII);
+		if (err) {
+			dev_err(&pdev->dev, "Connecting PHY failed\n");
+			goto err_phy_connect;
+		}
 	} else if (np && of_phy_is_fixed_link(np)) {
 		struct phy_device *phy;
 
-- 
cgit v1.3-3-g829e


From 646f071d315b75e87583de290d333478d42ccde1 Mon Sep 17 00:00:00 2001
From: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Date: Mon, 26 Aug 2024 22:16:31 -0700
Subject: net: netvsc: Update default VMBus channels

Change VMBus channels macro (VRSS_CHANNEL_DEFAULT) in
Linux netvsc from 8 to 16 to align with Azure Windows VM
and improve networking throughput.

For VMs having less than 16 vCPUS, the channels depend
on number of vCPUs. For greater than 16 vCPUs,
set the channels to maximum of VRSS_CHANNEL_DEFAULT and
number of physical cores / 2 which is returned by
netif_get_num_default_rss_queues() as a way to optimize CPU
resource utilization and scale for high-end processors with
many cores.
Maximum number of channels are by default set to 64.

Based on this change the channel creation would change as follows:

-----------------------------------------------------------------
| No. of vCPU |  dev_info->num_chn |    channels created        |
-----------------------------------------------------------------
|    1-16     |        16	   |          vCPU              |
|    >16      |  max(16,#cores/2)  | min(64 , max(16,#cores/2)) |
-----------------------------------------------------------------

Performance tests showed significant improvement in throughput:
- 0.54% for 16 vCPUs
- 0.83% for 32 vCPUs
- 0.86% for 48 vCPUs
- 9.72% for 64 vCPUs
- 13.57% for 96 vCPUs

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Link: https://patch.msgid.link/1724735791-22815-1-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hyperv/hyperv_net.h | 2 +-
 drivers/net/hyperv/netvsc_drv.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 810977952f95..e690b95b1bbb 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -882,7 +882,7 @@ struct nvsp_message {
 
 #define VRSS_SEND_TAB_SIZE 16  /* must be power of 2 */
 #define VRSS_CHANNEL_MAX 64
-#define VRSS_CHANNEL_DEFAULT 8
+#define VRSS_CHANNEL_DEFAULT 16
 
 #define RNDIS_MAX_PKT_DEFAULT 8
 #define RNDIS_PKT_ALIGN_DEFAULT 8
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 44142245343d..153b97f8ec0d 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -987,7 +987,8 @@ struct netvsc_device_info *netvsc_devinfo_get(struct netvsc_device *nvdev)
 			dev_info->bprog = prog;
 		}
 	} else {
-		dev_info->num_chn = VRSS_CHANNEL_DEFAULT;
+		dev_info->num_chn = max(VRSS_CHANNEL_DEFAULT,
+					netif_get_num_default_rss_queues());
 		dev_info->send_sections = NETVSC_DEFAULT_TX;
 		dev_info->send_section_size = NETVSC_SEND_SECTION_SIZE;
 		dev_info->recv_sections = NETVSC_DEFAULT_RX;
-- 
cgit v1.3-3-g829e


From ad78337cb20c1a52781a7b329b1a747d91be3491 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 27 Aug 2024 11:23:13 +0200
Subject: net: ethtool: cable-test: Release RTNL when the PHY isn't found

Use the correct logic to check for the presence of a PHY device, and
jump to a label that correctly releases RTNL in case of an error, as we
are holding RTNL at that point.

Fixes: 3688ff3077d3 ("net: ethtool: cable-test: Target the command to the requested PHY")
Closes: https://lore.kernel.org/netdev/20240827104825.5cbe0602@fedora-3.home/T/#m6bc49cdcc5cfab0d162516b92916b944a01c833f
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20240827092314.2500284-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/cabletest.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index 3a91b65c1f9a..f22051f33868 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -342,9 +342,9 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 	phydev = ethnl_req_get_phydev(&req_info,
 				      tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER],
 				      info->extack);
-	if (!IS_ERR_OR_NULL(phydev)) {
+	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
-		goto out_dev_put;
+		goto out_rtnl;
 	}
 
 	ops = ethtool_phy_ops;
-- 
cgit v1.3-3-g829e


From 387c415200c3c1099b29446b6e567810bc2dfffc Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 27 Aug 2024 20:10:05 +0300
Subject: net: dsa: mv88e6xxx: Remove stale comment

GPIOF_DIR_* definitions are legacy and subject to remove.
Taking this into account, remove stale comment.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240827171005.2301845-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mv88e6xxx/global2_scratch.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c
index 61ab6cc4fbfc..53a6d3ed63b3 100644
--- a/drivers/net/dsa/mv88e6xxx/global2_scratch.c
+++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c
@@ -146,7 +146,7 @@ static int mv88e6352_g2_scratch_gpio_set_data(struct mv88e6xxx_chip *chip,
  * @chip: chip private data
  * @pin: gpio index
  *
- * Return: 0 for output, 1 for input (same as GPIOF_DIR_XXX).
+ * Return: 0 for output, 1 for input.
  */
 static int mv88e6352_g2_scratch_gpio_get_dir(struct mv88e6xxx_chip *chip,
 					     unsigned int pin)
-- 
cgit v1.3-3-g829e


From 17555297dbd5bccc93a01516117547e26a61caf1 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 27 Aug 2024 16:44:19 +0200
Subject: net: hisilicon: hip04: fix OF node leak in probe()

Driver is leaking OF node reference from
of_parse_phandle_with_fixed_args() in probe().

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827144421.52852-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hip04_eth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index b91e7a06b97f..beb815e5289b 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -947,6 +947,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	priv->tx_coalesce_timer.function = tx_done;
 
 	priv->map = syscon_node_to_regmap(arg.np);
+	of_node_put(arg.np);
 	if (IS_ERR(priv->map)) {
 		dev_warn(d, "no syscon hisilicon,hip04-ppe\n");
 		ret = PTR_ERR(priv->map);
-- 
cgit v1.3-3-g829e


From 5680cf8d34e1552df987e2f4bb1bff0b2a8c8b11 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 27 Aug 2024 16:44:20 +0200
Subject: net: hisilicon: hns_dsaf_mac: fix OF node leak in hns_mac_get_info()

Driver is leaking OF node reference from
of_parse_phandle_with_fixed_args() in hns_mac_get_info().

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827144421.52852-3-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index f75668c47935..616a2768e504 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -933,6 +933,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb)
 			mac_cb->cpld_ctrl = NULL;
 		} else {
 			syscon = syscon_node_to_regmap(cpld_args.np);
+			of_node_put(cpld_args.np);
 			if (IS_ERR_OR_NULL(syscon)) {
 				dev_dbg(mac_cb->dev, "no cpld-syscon found!\n");
 				mac_cb->cpld_ctrl = NULL;
-- 
cgit v1.3-3-g829e


From e62beddc45f487b9969821fad3a0913d9bc18a2f Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 27 Aug 2024 16:44:21 +0200
Subject: net: hisilicon: hns_mdio: fix OF node leak in probe()

Driver is leaking OF node reference from
of_parse_phandle_with_fixed_args() in probe().

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827144421.52852-4-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns_mdio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index ed73707176c1..8a047145f0c5 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -575,6 +575,7 @@ static int hns_mdio_probe(struct platform_device *pdev)
 						MDIO_SC_RESET_ST;
 				}
 			}
+			of_node_put(reg_args.np);
 		} else {
 			dev_warn(&pdev->dev, "find syscon ret = %#x\n", ret);
 			mdio_dev->subctrl_vbase = NULL;
-- 
cgit v1.3-3-g829e


From 0a8b08c554dabea952a75363c89050b1fbcbfffb Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 27 Aug 2024 11:00:12 +0200
Subject: selftests: netfilter: nft_queue.sh: reduce test file size for debug
 build

The sctp selftest is very slow on debug kernels.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20240826192500.32efa22c@kernel.org/
Fixes: 4e97d521c2be ("selftests: netfilter: nft_queue.sh: sctp coverage")
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Link: https://patch.msgid.link/20240827090023.8917-1-fw@strlen.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/netfilter/nft_queue.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index f3bdeb1271eb..9e5f423bff09 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -39,7 +39,9 @@ TMPFILE2=$(mktemp)
 TMPFILE3=$(mktemp)
 
 TMPINPUT=$(mktemp)
-dd conv=sparse status=none if=/dev/zero bs=1M count=200 of="$TMPINPUT"
+COUNT=200
+[ "$KSFT_MACHINE_SLOW" = "yes" ] && COUNT=25
+dd conv=sparse status=none if=/dev/zero bs=1M count=$COUNT of="$TMPINPUT"
 
 if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1; then
     echo "SKIP: No virtual ethernet pair device support in kernel"
-- 
cgit v1.3-3-g829e


From c88908baec1a5f594bc70f28808a8e676311a69f Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 27 Aug 2024 21:09:56 +0200
Subject: net: vertexcom: mse102x: Use DEFINE_SIMPLE_DEV_PM_OPS

This macro has the advantage over SET_SYSTEM_SLEEP_PM_OPS that we don't
have to care about when the functions are actually used.

Also make use of pm_sleep_ptr() to discard all PM_SLEEP related
stuff if CONFIG_PM_SLEEP isn't enabled.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827191000.3244-2-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/vertexcom/mse102x.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index edd8b59680e5..0711641fc3c9 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -622,8 +622,6 @@ static const struct ethtool_ops mse102x_ethtool_ops = {
 
 /* driver bus management functions */
 
-#ifdef CONFIG_PM_SLEEP
-
 static int mse102x_suspend(struct device *dev)
 {
 	struct mse102x_net *mse = dev_get_drvdata(dev);
@@ -649,9 +647,8 @@ static int mse102x_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
-static SIMPLE_DEV_PM_OPS(mse102x_pm_ops, mse102x_suspend, mse102x_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(mse102x_pm_ops, mse102x_suspend, mse102x_resume);
 
 static int mse102x_probe_spi(struct spi_device *spi)
 {
@@ -761,7 +758,7 @@ static struct spi_driver mse102x_driver = {
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = mse102x_match_table,
-		.pm = &mse102x_pm_ops,
+		.pm = pm_sleep_ptr(&mse102x_pm_ops),
 	},
 	.probe = mse102x_probe_spi,
 	.remove = mse102x_remove_spi,
-- 
cgit v1.3-3-g829e


From 0069716da006146809c9b5714bec79285453fbee Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 27 Aug 2024 21:09:57 +0200
Subject: net: vertexcom: mse102x: Silence TX timeout

As long as the MSE102x is not operational, every packet transmission
will run into a TX timeout and flood the kernel log. So log only the
first TX timeout and a user is at least informed about this issue.
The amount of timeouts are still available via netstat.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827191000.3244-3-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/vertexcom/mse102x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 0711641fc3c9..336435fe8241 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -451,7 +451,7 @@ static void mse102x_tx_work(struct work_struct *work)
 
 	if (ret == -ETIMEDOUT) {
 		if (netif_msg_timer(mse))
-			netdev_err(mse->ndev, "tx work timeout\n");
+			netdev_err_once(mse->ndev, "tx work timeout\n");
 
 		mse->stats.tx_timeout++;
 	}
-- 
cgit v1.3-3-g829e


From d3a41dc7e9b04aca289e4bad0b96f1ac9b135f0c Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 27 Aug 2024 21:09:58 +0200
Subject: net: vertexcom: mse102x: Fix random MAC address log

At the time of MAC address assignment the netdev is not registered yet,
so netdev log functions won't work as expected. While we are at this
downgrade the log level to a warning, because a random MAC address is
not a real error.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827191000.3244-4-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/vertexcom/mse102x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 336435fe8241..4ce027f8e376 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -485,8 +485,8 @@ static void mse102x_init_mac(struct mse102x_net *mse, struct device_node *np)
 
 	if (ret) {
 		eth_hw_addr_random(ndev);
-		netdev_err(ndev, "Using random MAC address: %pM\n",
-			   ndev->dev_addr);
+		dev_warn(ndev->dev.parent, "Using random MAC address: %pM\n",
+			 ndev->dev_addr);
 	}
 }
 
-- 
cgit v1.3-3-g829e


From 7f37d20929c05bf7817b59615b79a0167f3690a3 Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 27 Aug 2024 21:09:59 +0200
Subject: net: vertexcom: mse102x: Drop log message on remove

This message is a leftover from initial development. It's
unnecessary now and can be dropped.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827191000.3244-5-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/vertexcom/mse102x.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 4ce027f8e376..8a72d8699b84 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -733,9 +733,6 @@ static void mse102x_remove_spi(struct spi_device *spi)
 	struct mse102x_net *mse = dev_get_drvdata(&spi->dev);
 	struct mse102x_net_spi *mses = to_mse102x_spi(mse);
 
-	if (netif_msg_drv(mse))
-		dev_info(&spi->dev, "remove\n");
-
 	mse102x_remove_device_debugfs(mses);
 	unregister_netdev(mse->ndev);
 }
-- 
cgit v1.3-3-g829e


From bc682b8064be82f5f9d2fda79f5b8a14e3ecc4df Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Tue, 27 Aug 2024 21:10:00 +0200
Subject: net: vertexcom: mse102x: Use ETH_ZLEN

There is already a define for minimum Ethernet frame length without FCS.
So used this instead of the magic number.

Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240827191000.3244-6-wahrenst@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/vertexcom/mse102x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c
index 8a72d8699b84..a04d4073def9 100644
--- a/drivers/net/ethernet/vertexcom/mse102x.c
+++ b/drivers/net/ethernet/vertexcom/mse102x.c
@@ -377,8 +377,8 @@ static int mse102x_tx_pkt_spi(struct mse102x_net *mse, struct sk_buff *txb,
 	int ret;
 	bool first = true;
 
-	if (txb->len < 60)
-		pad = 60 - txb->len;
+	if (txb->len < ETH_ZLEN)
+		pad = ETH_ZLEN - txb->len;
 
 	while (1) {
 		mse102x_tx_cmd_spi(mse, CMD_RTS | (txb->len + pad));
-- 
cgit v1.3-3-g829e


From a41de3b12ec17dbaba443d7aa7cb481dc21aea28 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:15:51 +0800
Subject: net: ipa: make use of dev_err_cast_probe()

Using dev_err_cast_probe() to simplify the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240828121551.3696520-1-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/ipa_power.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c
index 65fd14da0f86..c572da9e9bc4 100644
--- a/drivers/net/ipa/ipa_power.c
+++ b/drivers/net/ipa/ipa_power.c
@@ -242,11 +242,8 @@ ipa_power_init(struct device *dev, const struct ipa_power_data *data)
 	int ret;
 
 	clk = clk_get(dev, "core");
-	if (IS_ERR(clk)) {
-		dev_err_probe(dev, PTR_ERR(clk), "error getting core clock\n");
-
-		return ERR_CAST(clk);
-	}
+	if (IS_ERR(clk))
+		return dev_err_cast_probe(dev, clk, "error getting core clock\n");
 
 	ret = clk_set_rate(clk, data->core_clock_rate);
 	if (ret) {
-- 
cgit v1.3-3-g829e


From 9023fda2f186168e45bb8e7397ad15ff17fd7bf8 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:18:05 +0800
Subject: net: dsa: realtek: make use of dev_err_cast_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using dev_err_cast_probe() to simplify the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk>
Link: https://patch.msgid.link/20240828121805.3696631-1-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl83xx.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl83xx.c b/drivers/net/dsa/realtek/rtl83xx.c
index 35709a1756ae..3c5018d5e1f9 100644
--- a/drivers/net/dsa/realtek/rtl83xx.c
+++ b/drivers/net/dsa/realtek/rtl83xx.c
@@ -185,11 +185,9 @@ rtl83xx_probe(struct device *dev,
 
 	/* TODO: if power is software controlled, set up any regulators here */
 	priv->reset_ctl = devm_reset_control_get_optional(dev, NULL);
-	if (IS_ERR(priv->reset_ctl)) {
-		ret = PTR_ERR(priv->reset_ctl);
-		dev_err_probe(dev, ret, "failed to get reset control\n");
-		return ERR_CAST(priv->reset_ctl);
-	}
+	if (IS_ERR(priv->reset_ctl))
+		return dev_err_cast_probe(dev, priv->reset_ctl,
+					  "failed to get reset control\n");
 
 	priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
 	if (IS_ERR(priv->reset)) {
-- 
cgit v1.3-3-g829e


From 4266563afbb1eb1735aa7063fe8ff6377991ae42 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:23:36 +0800
Subject: net: hns: Use IS_ERR_OR_NULL() helper function

Use the IS_ERR_OR_NULL() helper instead of open-coding a
NULL and an error pointer checks to simplify the code and
improve readability.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240828122336.3697176-1-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 616a2768e504..58baac7103b3 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -734,7 +734,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 		return -ENODATA;
 
 	phy = get_phy_device(mdio, addr, is_c45);
-	if (!phy || IS_ERR(phy))
+	if (IS_ERR_OR_NULL(phy))
 		return -EIO;
 
 	phy->irq = mdio->irq[addr];
-- 
cgit v1.3-3-g829e


From bf4d87f884fe8a4b6b61fe4d0e05f293d08df61c Mon Sep 17 00:00:00 2001
From: Yang Ruibin <11162571@vivo.com>
Date: Wed, 28 Aug 2024 20:26:49 +0800
Subject: net: alacritech: Switch to use dev_err_probe()

use dev_err_probe() instead of dev_err() to simplify the error path and
standardize the format of the error code.

Signed-off-by: Yang Ruibin <11162571@vivo.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240828122650.1324246-1-11162571@vivo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/alacritech/slicoss.c | 34 +++++++++++++------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 78231c85234d..7f0c07c20be3 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -1051,11 +1051,9 @@ static int slic_load_rcvseq_firmware(struct slic_device *sdev)
 	file = (sdev->model == SLIC_MODEL_OASIS) ?  SLIC_RCV_FIRMWARE_OASIS :
 						    SLIC_RCV_FIRMWARE_MOJAVE;
 	err = request_firmware(&fw, file, &sdev->pdev->dev);
-	if (err) {
-		dev_err(&sdev->pdev->dev,
+	if (err)
+		return dev_err_probe(&sdev->pdev->dev, err,
 			"failed to load receive sequencer firmware %s\n", file);
-		return err;
-	}
 	/* Do an initial sanity check concerning firmware size now. A further
 	 * check follows below.
 	 */
@@ -1126,10 +1124,9 @@ static int slic_load_firmware(struct slic_device *sdev)
 	file = (sdev->model == SLIC_MODEL_OASIS) ?  SLIC_FIRMWARE_OASIS :
 						    SLIC_FIRMWARE_MOJAVE;
 	err = request_firmware(&fw, file, &sdev->pdev->dev);
-	if (err) {
-		dev_err(&sdev->pdev->dev, "failed to load firmware %s\n", file);
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&sdev->pdev->dev, err,
+				"failed to load firmware %s\n", file);
 	/* Do an initial sanity check concerning firmware size now. A further
 	 * check follows below.
 	 */
@@ -1678,17 +1675,15 @@ static int slic_init(struct slic_device *sdev)
 	slic_card_reset(sdev);
 
 	err = slic_load_firmware(sdev);
-	if (err) {
-		dev_err(&sdev->pdev->dev, "failed to load firmware\n");
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&sdev->pdev->dev, err,
+			"failed to load firmware\n");
 
 	/* we need the shared memory to read EEPROM so set it up temporarily */
 	err = slic_init_shmem(sdev);
-	if (err) {
-		dev_err(&sdev->pdev->dev, "failed to init shared memory\n");
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&sdev->pdev->dev, err,
+			"failed to init shared memory\n");
 
 	err = slic_read_eeprom(sdev);
 	if (err) {
@@ -1741,10 +1736,9 @@ static int slic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int err;
 
 	err = pci_enable_device(pdev);
-	if (err) {
-		dev_err(&pdev->dev, "failed to enable PCI device\n");
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&pdev->dev, err,
+			"failed to enable PCI device\n");
 
 	pci_set_master(pdev);
 	pci_try_set_mwi(pdev);
-- 
cgit v1.3-3-g829e


From 68016b997222c9f866912f6911815105ed2ce473 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:32:19 +0800
Subject: net: prefer strscpy over strcpy

The deprecated helper strcpy() performs no bounds checking on the
destination buffer. This could result in linear overflows beyond
the end of the buffer, leading to all kinds of misbehaviors.
The safe replacement is strscpy() [1].

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 63987b8b7c85..932d67b975f5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11143,7 +11143,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (!dev->ethtool)
 		goto free_all;
 
-	strcpy(dev->name, name);
+	strscpy(dev->name, name);
 	dev->name_assign_type = name_assign_type;
 	dev->group = INIT_NETDEV_GROUP;
 	if (!dev->ethtool_ops)
-- 
cgit v1.3-3-g829e


From b19f69a958300dcc93e453d7ed3fa354fc0f590c Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:32:20 +0800
Subject: net/ipv6: replace deprecated strcpy with strscpy

The deprecated helper strcpy() performs no bounds checking on the
destination buffer. This could result in linear overflows beyond
the end of the buffer, leading to all kinds of misbehaviors.
The safe replacement is strscpy() [1].

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240828123224.3697672-3-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ndisc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 1e42e40fb379..aba94a348673 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1944,7 +1944,7 @@ static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl,
 	static char warncomm[TASK_COMM_LEN];
 	static int warned;
 	if (strcmp(warncomm, current->comm) && warned < 5) {
-		strcpy(warncomm, current->comm);
+		strscpy(warncomm, current->comm);
 		pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n",
 			warncomm, func,
 			dev_name, ctl->procname,
-- 
cgit v1.3-3-g829e


From 597be7bd17c36c8fa7e075f0da4decc7ca3b9d1d Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:32:21 +0800
Subject: net/netrom: prefer strscpy over strcpy

The deprecated helper strcpy() performs no bounds checking on the
destination buffer. This could result in linear overflows beyond
the end of the buffer, leading to all kinds of misbehaviors.
The safe replacement is strscpy() [1].

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240828123224.3697672-4-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netrom/nr_route.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index bd2b17b219ae..2b5e246b8d9a 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -189,7 +189,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 		}
 
 		nr_node->callsign = *nr;
-		strcpy(nr_node->mnemonic, mnemonic);
+		strscpy(nr_node->mnemonic, mnemonic);
 
 		nr_node->which = 0;
 		nr_node->count = 1;
@@ -214,7 +214,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic,
 	nr_node_lock(nr_node);
 
 	if (quality != 0)
-		strcpy(nr_node->mnemonic, mnemonic);
+		strscpy(nr_node->mnemonic, mnemonic);
 
 	for (found = 0, i = 0; i < nr_node->count; i++) {
 		if (nr_node->routes[i].neighbour == nr_neigh) {
-- 
cgit v1.3-3-g829e


From af1052fd49cc7c78e577bb1d6241171a8ce05bab Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:32:23 +0800
Subject: net/tipc: replace deprecated strcpy with strscpy

The deprecated helper strcpy() performs no bounds checking on the
destination buffer. This could result in linear overflows beyond
the end of the buffer, leading to all kinds of misbehaviors.
The safe replacement is strscpy() [1].

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240828123224.3697672-6-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/bearer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 3c9e25f6a1d2..ae1ddbf71853 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -326,7 +326,7 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 	if (!b)
 		return -ENOMEM;
 
-	strcpy(b->name, name);
+	strscpy(b->name, name);
 	b->media = m;
 	res = m->enable_media(net, b, attr);
 	if (res) {
-- 
cgit v1.3-3-g829e


From 82183b03de5f80f5d9c45cbb7129cd03f592f474 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 28 Aug 2024 20:32:24 +0800
Subject: net/ipv4: net: prefer strscpy over strcpy

The deprecated helper strcpy() performs no bounds checking on the
destination buffer. This could result in linear overflows beyond
the end of the buffer, leading to all kinds of misbehaviors.
The safe replacement is strscpy() [1].

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strcpy [1]

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240828123224.3697672-7-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_tunnel.c            | 2 +-
 net/ipv4/netfilter/arp_tables.c | 2 +-
 net/ipv4/netfilter/ip_tables.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5cffad42fe8c..0cd2f3de100c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1326,7 +1326,7 @@ int ip_tunnel_init(struct net_device *dev)
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
-	strcpy(tunnel->parms.name, dev->name);
+	strscpy(tunnel->parms.name, dev->name);
 	iph->version		= 4;
 	iph->ihl		= 5;
 
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 14365b20f1c5..42c34e8952da 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -826,7 +826,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 		       sizeof(info.underflow));
 		info.num_entries = private->number;
 		info.size = private->size;
-		strcpy(info.name, name);
+		strscpy(info.name, name);
 
 		if (copy_to_user(user, &info, *len) != 0)
 			ret = -EFAULT;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index fe89a056eb06..97e754ddc155 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -981,7 +981,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 		       sizeof(info.underflow));
 		info.num_entries = private->number;
 		info.size = private->size;
-		strcpy(info.name, name);
+		strscpy(info.name, name);
 
 		if (copy_to_user(user, &info, *len) != 0)
 			ret = -EFAULT;
-- 
cgit v1.3-3-g829e


From 3d8806f37d318b10ddf9fa686821f58bc6301c7b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 28 Aug 2024 10:36:09 -0700
Subject: tools: ynl: error check scanf() in a sample
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Someone reported on GitHub that the YNL NIPA test is failing
when run locally. The test builds the tools, and it hits:

  netdev.c:82:9: warning: ignoring return value of ‘scanf’ declared with attribute ‘warn_unused_result’ [-Wunused-result]
  82 | scanf("%d", &ifindex);

I can't repro this on my setups but error seems clear enough.

Link: https://github.com/linux-netdev/nipa/discussions/37
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://patch.msgid.link/20240828173609.2951335-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/samples/netdev.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c
index 3e7b29bd55d5..22609d44c89a 100644
--- a/tools/net/ynl/samples/netdev.c
+++ b/tools/net/ynl/samples/netdev.c
@@ -79,7 +79,10 @@ int main(int argc, char **argv)
 		goto err_close;
 
 	printf("Select ifc ($ifindex; or 0 = dump; or -2 ntf check): ");
-	scanf("%d", &ifindex);
+	if (scanf("%d", &ifindex) != 1) {
+		fprintf(stderr, "Error: unable to parse input\n");
+		goto err_destroy;
+	}
 
 	if (ifindex > 0) {
 		struct netdev_dev_get_req *req;
@@ -119,6 +122,7 @@ int main(int argc, char **argv)
 
 err_close:
 	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_destroy:
 	ynl_sock_destroy(ys);
 	return 2;
 }
-- 
cgit v1.3-3-g829e


From be9a4fb831b8b6dc5724dd3e61973ea91b413ec1 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jmaloy@redhat.com>
Date: Wed, 28 Aug 2024 14:37:51 -0400
Subject: tcp: add SO_PEEK_OFF socket option tor TCPv6

When doing further testing of the recently added SO_PEEK_OFF feature
for TCP I realized I had omitted to add it for TCP/IPv6.

I do that here.

Fixes: 05ea491641d3 ("tcp: add support for SO_PEEK_OFF socket option")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Tested-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20240828183752.660267-2-jmaloy@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/af_inet6.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 90d2c7e3f5e9..ba69b86f1c7d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -708,6 +708,7 @@ const struct proto_ops inet6_stream_ops = {
 	.splice_eof	   = inet_splice_eof,
 	.sendmsg_locked    = tcp_sendmsg_locked,
 	.splice_read	   = tcp_splice_read,
+	.set_peek_off      = sk_set_peek_off,
 	.read_sock	   = tcp_read_sock,
 	.read_skb	   = tcp_read_skb,
 	.peek_len	   = tcp_peek_len,
-- 
cgit v1.3-3-g829e


From b24d22ac74bfdde2e1146e1838abdc99131b1d19 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jmaloy@redhat.com>
Date: Wed, 28 Aug 2024 14:37:52 -0400
Subject: selftests: add selftest for tcp SO_PEEK_OFF support

We add a selftest to check that the new feature added in
commit 05ea491641d3 ("tcp: add support for SO_PEEK_OFF socket option")
works correctly.

Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Stefano Brivio <sbrivio@redhat.com>
Tested-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jon Maloy <jmaloy@redhat.com>
Link: https://patch.msgid.link/20240828183752.660267-3-jmaloy@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          |   1 +
 tools/testing/selftests/net/tcp_so_peek_off.c | 183 ++++++++++++++++++++++++++
 2 files changed, 184 insertions(+)
 create mode 100644 tools/testing/selftests/net/tcp_so_peek_off.c

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8eaffd7a641c..1179e3261bef 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -80,6 +80,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh
 TEST_GEN_FILES += bind_bhash
 TEST_GEN_PROGS += sk_bind_sendto_listen
 TEST_GEN_PROGS += sk_connect_zero_addr
+TEST_GEN_PROGS += tcp_so_peek_off
 TEST_PROGS += test_ingress_egress_chaining.sh
 TEST_GEN_PROGS += so_incoming_cpu
 TEST_PROGS += sctp_vrf.sh
diff --git a/tools/testing/selftests/net/tcp_so_peek_off.c b/tools/testing/selftests/net/tcp_so_peek_off.c
new file mode 100644
index 000000000000..df8a39d9d3c3
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_so_peek_off.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include "../kselftest.h"
+
+static char *afstr(int af)
+{
+	return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6";
+}
+
+int tcp_peek_offset_probe(sa_family_t af)
+{
+	int optv = 0;
+	int ret = 0;
+	int s;
+
+	s = socket(af, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
+	if (s < 0) {
+		ksft_perror("Temporary TCP socket creation failed");
+	} else {
+		if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int)))
+			ret = 1;
+		else
+			printf("%s does not support SO_PEEK_OFF\n", afstr(af));
+		close(s);
+	}
+	return ret;
+}
+
+static void tcp_peek_offset_set(int s, int offset)
+{
+	if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset)))
+		ksft_perror("Failed to set SO_PEEK_OFF value\n");
+}
+
+static int tcp_peek_offset_get(int s)
+{
+	int offset;
+	socklen_t len = sizeof(offset);
+
+	if (getsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, &len))
+		ksft_perror("Failed to get SO_PEEK_OFF value\n");
+	return offset;
+}
+
+static int tcp_peek_offset_test(sa_family_t af)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_in a4;
+		struct sockaddr_in6 a6;
+	} a;
+	int res = 0;
+	int s[2] = {0, 0};
+	int recv_sock = 0;
+	int offset = 0;
+	ssize_t len;
+	char buf;
+
+	memset(&a, 0, sizeof(a));
+	a.sa.sa_family = af;
+
+	s[0] = socket(af, SOCK_STREAM, IPPROTO_TCP);
+	s[1] = socket(af, SOCK_STREAM | SOCK_NONBLOCK, IPPROTO_TCP);
+
+	if (s[0] < 0 || s[1] < 0) {
+		ksft_perror("Temporary socket creation failed\n");
+		goto out;
+	}
+	if (bind(s[0], &a.sa, sizeof(a)) < 0) {
+		ksft_perror("Temporary socket bind() failed\n");
+		goto out;
+	}
+	if (getsockname(s[0], &a.sa, &((socklen_t) { sizeof(a) })) < 0) {
+		ksft_perror("Temporary socket getsockname() failed\n");
+		goto out;
+	}
+	if (listen(s[0], 0) < 0) {
+		ksft_perror("Temporary socket listen() failed\n");
+		goto out;
+	}
+	if (connect(s[1], &a.sa, sizeof(a)) >= 0 || errno != EINPROGRESS) {
+		ksft_perror("Temporary socket connect() failed\n");
+		goto out;
+	}
+	recv_sock = accept(s[0], NULL, NULL);
+	if (recv_sock <= 0) {
+		ksft_perror("Temporary socket accept() failed\n");
+		goto out;
+	}
+
+	/* Some basic tests of getting/setting offset */
+	offset = tcp_peek_offset_get(recv_sock);
+	if (offset != -1) {
+		ksft_perror("Initial value of socket offset not -1\n");
+		goto out;
+	}
+	tcp_peek_offset_set(recv_sock, 0);
+	offset = tcp_peek_offset_get(recv_sock);
+	if (offset != 0) {
+		ksft_perror("Failed to set socket offset to 0\n");
+		goto out;
+	}
+
+	/* Transfer a message */
+	if (send(s[1], (char *)("ab"), 2, 0) <= 0 || errno != EINPROGRESS) {
+		ksft_perror("Temporary probe socket send() failed\n");
+		goto out;
+	}
+	/* Read first byte */
+	len = recv(recv_sock, &buf, 1, MSG_PEEK);
+	if (len != 1 || buf != 'a') {
+		ksft_perror("Failed to read first byte of message\n");
+		goto out;
+	}
+	offset = tcp_peek_offset_get(recv_sock);
+	if (offset != 1) {
+		ksft_perror("Offset not forwarded correctly at first byte\n");
+		goto out;
+	}
+	/* Try to read beyond last byte */
+	len = recv(recv_sock, &buf, 2, MSG_PEEK);
+	if (len != 1 || buf != 'b') {
+		ksft_perror("Failed to read last byte of message\n");
+		goto out;
+	}
+	offset = tcp_peek_offset_get(recv_sock);
+	if (offset != 2) {
+		ksft_perror("Offset not forwarded correctly at last byte\n");
+		goto out;
+	}
+	/* Flush message */
+	len = recv(recv_sock, NULL, 2, MSG_TRUNC);
+	if (len != 2) {
+		ksft_perror("Failed to flush message\n");
+		goto out;
+	}
+	offset = tcp_peek_offset_get(recv_sock);
+	if (offset != 0) {
+		ksft_perror("Offset not reverted correctly after flush\n");
+		goto out;
+	}
+
+	printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af));
+	res = 1;
+out:
+	if (recv_sock >= 0)
+		close(recv_sock);
+	if (s[1] >= 0)
+		close(s[1]);
+	if (s[0] >= 0)
+		close(s[0]);
+	return res;
+}
+
+int main(void)
+{
+	int res4, res6;
+
+	res4 = tcp_peek_offset_probe(AF_INET);
+	res6 = tcp_peek_offset_probe(AF_INET6);
+
+	if (!res4 && !res6)
+		return KSFT_SKIP;
+
+	if (res4)
+		res4 = tcp_peek_offset_test(AF_INET);
+
+	if (res6)
+		res6 = tcp_peek_offset_test(AF_INET6);
+
+	if (!res4 || !res6)
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
-- 
cgit v1.3-3-g829e


From c33626d83e937428cc7ffe1e41382ca454ec148a Mon Sep 17 00:00:00 2001
From: Vikas Gupta <vikas.gupta@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:27 -0700
Subject: bnxt_en: add support for storing crash dump into host memory

Newer firmware supports automatic DMA of crash dump to host memory
when it crashes.  If the feature is supported, allocate the required
memory using the existing context memory infrastructure.  Communicate
the page table containing the DMA addresses to the firmware.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c          | 92 ++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h          |  3 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c | 18 +++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h |  8 ++
 4 files changed, 116 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b26a7e2aa132..671dc598324a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -69,6 +69,7 @@
 #include "bnxt_tc.h"
 #include "bnxt_devlink.h"
 #include "bnxt_debugfs.h"
+#include "bnxt_coredump.h"
 #include "bnxt_hwmon.h"
 
 #define BNXT_TX_TIMEOUT		(5 * HZ)
@@ -8946,6 +8947,80 @@ skip_rdma:
 	return 0;
 }
 
+static int bnxt_hwrm_crash_dump_mem_cfg(struct bnxt *bp)
+{
+	struct hwrm_dbg_crashdump_medium_cfg_input *req;
+	u16 page_attr;
+	int rc;
+
+	if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR))
+		return 0;
+
+	rc = hwrm_req_init(bp, req, HWRM_DBG_CRASHDUMP_MEDIUM_CFG);
+	if (rc)
+		return rc;
+
+	if (BNXT_PAGE_SIZE == 0x2000)
+		page_attr = DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K;
+	else if (BNXT_PAGE_SIZE == 0x10000)
+		page_attr = DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K;
+	else
+		page_attr = DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K;
+	req->pg_size_lvl = cpu_to_le16(page_attr |
+				       bp->fw_crash_mem->ring_mem.depth);
+	req->pbl = cpu_to_le64(bp->fw_crash_mem->ring_mem.pg_tbl_map);
+	req->size = cpu_to_le32(bp->fw_crash_len);
+	req->output_dest_flags = cpu_to_le16(BNXT_DBG_CR_DUMP_MDM_CFG_DDR);
+	return hwrm_req_send(bp, req);
+}
+
+static void bnxt_free_crash_dump_mem(struct bnxt *bp)
+{
+	if (bp->fw_crash_mem) {
+		bnxt_free_ctx_pg_tbls(bp, bp->fw_crash_mem);
+		kfree(bp->fw_crash_mem);
+		bp->fw_crash_mem = NULL;
+	}
+}
+
+static int bnxt_alloc_crash_dump_mem(struct bnxt *bp)
+{
+	u32 mem_size = 0;
+	int rc;
+
+	if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR))
+		return 0;
+
+	rc = bnxt_hwrm_get_dump_len(bp, BNXT_DUMP_CRASH, &mem_size);
+	if (rc)
+		return rc;
+
+	mem_size = round_up(mem_size, 4);
+
+	/* keep and use the existing pages */
+	if (bp->fw_crash_mem &&
+	    mem_size <= bp->fw_crash_mem->nr_pages * BNXT_PAGE_SIZE)
+		goto alloc_done;
+
+	if (bp->fw_crash_mem)
+		bnxt_free_ctx_pg_tbls(bp, bp->fw_crash_mem);
+	else
+		bp->fw_crash_mem = kzalloc(sizeof(*bp->fw_crash_mem),
+					   GFP_KERNEL);
+	if (!bp->fw_crash_mem)
+		return -ENOMEM;
+
+	rc = bnxt_alloc_ctx_pg_tbls(bp, bp->fw_crash_mem, mem_size, 1, NULL);
+	if (rc) {
+		bnxt_free_crash_dump_mem(bp);
+		return rc;
+	}
+
+alloc_done:
+	bp->fw_crash_len = mem_size;
+	return 0;
+}
+
 int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 {
 	struct hwrm_func_resource_qcaps_output *resp;
@@ -13986,6 +14061,19 @@ static int bnxt_fw_init_one_p2(struct bnxt *bp)
 	if (rc)
 		return -ENODEV;
 
+	rc = bnxt_alloc_crash_dump_mem(bp);
+	if (rc)
+		netdev_warn(bp->dev, "crash dump mem alloc failure rc: %d\n",
+			    rc);
+	if (!rc) {
+		rc = bnxt_hwrm_crash_dump_mem_cfg(bp);
+		if (rc) {
+			bnxt_free_crash_dump_mem(bp);
+			netdev_warn(bp->dev,
+				    "hwrm crash dump mem failure rc: %d\n", rc);
+		}
+	}
+
 	if (bnxt_fw_pre_resv_vnics(bp))
 		bp->fw_cap |= BNXT_FW_CAP_PRE_RESV_VNICS;
 
@@ -15294,6 +15382,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
+	bnxt_free_crash_dump_mem(bp);
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 	bnxt_free_port_stats(bp);
@@ -15933,6 +16022,7 @@ init_err_pci_clean:
 	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
+	bnxt_free_crash_dump_mem(bp);
 	kfree(bp->rss_indir_tbl);
 	bp->rss_indir_tbl = NULL;
 
@@ -16024,6 +16114,8 @@ static int bnxt_resume(struct device *device)
 		rc = -ENODEV;
 		goto resume_exit;
 	}
+	if (bp->fw_crash_mem)
+		bnxt_hwrm_crash_dump_mem_cfg(bp);
 
 	bnxt_get_wol_settings(bp);
 	if (netif_running(dev)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 610c0fe468ad..e7dcb59c3cdd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2649,6 +2649,9 @@ struct bnxt {
 #endif
 	u32			thermal_threshold_type;
 	enum board_idx		board_idx;
+
+	struct bnxt_ctx_pg_info	*fw_crash_mem;
+	u32			fw_crash_len;
 };
 
 #define BNXT_NUM_RX_RING_STATS			8
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index c06789882036..ebbad9ccab6a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -385,7 +385,7 @@ int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len)
 	}
 }
 
-static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
+int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 {
 	struct hwrm_dbg_qcfg_output *resp;
 	struct hwrm_dbg_qcfg_input *req;
@@ -395,7 +395,8 @@ static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 		return -EOPNOTSUPP;
 
 	if (dump_type == BNXT_DUMP_CRASH &&
-	    !(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR))
+	    !(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR ||
+	     (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR)))
 		return -EOPNOTSUPP;
 
 	rc = hwrm_req_init(bp, req, HWRM_DBG_QCFG);
@@ -403,8 +404,12 @@ static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 		return rc;
 
 	req->fid = cpu_to_le16(0xffff);
-	if (dump_type == BNXT_DUMP_CRASH)
-		req->flags = cpu_to_le16(DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR);
+	if (dump_type == BNXT_DUMP_CRASH) {
+		if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR)
+			req->flags = cpu_to_le16(BNXT_DBG_FL_CR_DUMP_SIZE_SOC);
+		else
+			req->flags = cpu_to_le16(BNXT_DBG_FL_CR_DUMP_SIZE_HOST);
+	}
 
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
@@ -412,7 +417,10 @@ static int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len)
 		goto get_dump_len_exit;
 
 	if (dump_type == BNXT_DUMP_CRASH) {
-		*dump_len = le32_to_cpu(resp->crashdump_size);
+		if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR)
+			*dump_len = BNXT_CRASH_DUMP_LEN;
+		else
+			*dump_len = le32_to_cpu(resp->crashdump_size);
 	} else {
 		/* Driver adds coredump header and "HWRM_VER_GET response"
 		 * segment additionally to coredump.
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
index b1a1b2fffb19..a76d5c281413 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
@@ -111,7 +111,15 @@ struct hwrm_dbg_cmn_output {
 	#define HWRM_DBG_CMN_FLAGS_MORE	1
 };
 
+#define BNXT_DBG_FL_CR_DUMP_SIZE_SOC	\
+	DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
+#define BNXT_DBG_FL_CR_DUMP_SIZE_HOST	\
+	DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR
+#define BNXT_DBG_CR_DUMP_MDM_CFG_DDR	\
+	DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR
+
 int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len);
+int bnxt_hwrm_get_dump_len(struct bnxt *bp, u16 dump_type, u32 *dump_len);
 u32 bnxt_get_coredump_length(struct bnxt *bp, u16 dump_type);
 
 #endif
-- 
cgit v1.3-3-g829e


From 9e7b880b92a7b37c5d72bcd7883da537eba049d6 Mon Sep 17 00:00:00 2001
From: Vikas Gupta <vikas.gupta@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:28 -0700
Subject: bnxt_en: add support for retrieving crash dump using ethtool

Add support for retrieving crash dump using ethtool -w on the
supported interface.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c | 80 ++++++++++++++++++++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  | 13 +++-
 2 files changed, 84 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index ebbad9ccab6a..4e2b938ed1f7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -372,14 +372,75 @@ err:
 	return rc;
 }
 
+static u32 bnxt_copy_crash_data(struct bnxt_ring_mem_info *rmem, void *buf,
+				u32 dump_len)
+{
+	u32 data_copied = 0;
+	u32 data_len;
+	int i;
+
+	for (i = 0; i < rmem->nr_pages; i++) {
+		data_len = rmem->page_size;
+		if (data_copied + data_len > dump_len)
+			data_len = dump_len - data_copied;
+		memcpy(buf + data_copied, rmem->pg_arr[i], data_len);
+		data_copied += data_len;
+		if (data_copied >= dump_len)
+			break;
+	}
+	return data_copied;
+}
+
+static int bnxt_copy_crash_dump(struct bnxt *bp, void *buf, u32 dump_len)
+{
+	struct bnxt_ring_mem_info *rmem;
+	u32 offset = 0;
+
+	if (!bp->fw_crash_mem)
+		return -ENOENT;
+
+	rmem = &bp->fw_crash_mem->ring_mem;
+
+	if (rmem->depth > 1) {
+		int i;
+
+		for (i = 0; i < rmem->nr_pages; i++) {
+			struct bnxt_ctx_pg_info *pg_tbl;
+
+			pg_tbl = bp->fw_crash_mem->ctx_pg_tbl[i];
+			offset += bnxt_copy_crash_data(&pg_tbl->ring_mem,
+						       buf + offset,
+						       dump_len - offset);
+			if (offset >= dump_len)
+				break;
+		}
+	} else {
+		bnxt_copy_crash_data(rmem, buf, dump_len);
+	}
+
+	return 0;
+}
+
+static bool bnxt_crash_dump_avail(struct bnxt *bp)
+{
+	u32 sig = 0;
+
+	/* First 4 bytes(signature) of crash dump is always non-zero */
+	bnxt_copy_crash_dump(bp, &sig, sizeof(sig));
+	return !!sig;
+}
+
 int bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf, u32 *dump_len)
 {
 	if (dump_type == BNXT_DUMP_CRASH) {
+		if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR)
+			return bnxt_copy_crash_dump(bp, buf, *dump_len);
 #ifdef CONFIG_TEE_BNXT_FW
-		return tee_bnxt_copy_coredump(buf, 0, *dump_len);
-#else
-		return -EOPNOTSUPP;
+		else if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR)
+			return tee_bnxt_copy_coredump(buf, 0, *dump_len);
 #endif
+		else
+			return -EOPNOTSUPP;
 	} else {
 		return __bnxt_get_coredump(bp, buf, dump_len);
 	}
@@ -442,10 +503,17 @@ u32 bnxt_get_coredump_length(struct bnxt *bp, u16 dump_type)
 {
 	u32 len = 0;
 
+	if (dump_type == BNXT_DUMP_CRASH &&
+	    bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR &&
+	    bp->fw_crash_mem) {
+		if (!bnxt_crash_dump_avail(bp))
+			return 0;
+
+		return bp->fw_crash_len;
+	}
+
 	if (bnxt_hwrm_get_dump_len(bp, dump_type, &len)) {
-		if (dump_type == BNXT_DUMP_CRASH)
-			len = BNXT_CRASH_DUMP_LEN;
-		else
+		if (dump_type != BNXT_DUMP_CRASH)
 			__bnxt_get_coredump(bp, NULL, &len);
 	}
 	return len;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 194f47316c77..7392a716f28d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -4989,9 +4989,16 @@ static int bnxt_set_dump(struct net_device *dev, struct ethtool_dump *dump)
 		return -EINVAL;
 	}
 
-	if (!IS_ENABLED(CONFIG_TEE_BNXT_FW) && dump->flag == BNXT_DUMP_CRASH) {
-		netdev_info(dev, "Cannot collect crash dump as TEE_BNXT_FW config option is not enabled.\n");
-		return -EOPNOTSUPP;
+	if (dump->flag == BNXT_DUMP_CRASH) {
+		if (bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR &&
+		    (!IS_ENABLED(CONFIG_TEE_BNXT_FW))) {
+			netdev_info(dev,
+				    "Cannot collect crash dump as TEE_BNXT_FW config option is not enabled.\n");
+			return -EOPNOTSUPP;
+		} else if (!(bp->fw_dbg_cap & DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR)) {
+			netdev_info(dev, "Crash dump collection from host memory is not supported on this interface.\n");
+			return -EOPNOTSUPP;
+		}
 	}
 
 	bp->dump_flag = dump->flag;
-- 
cgit v1.3-3-g829e


From 26e3846e23b49ec15a534e95bdc65e090eaaa42e Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:29 -0700
Subject: bnxt_en: Support QOS and TPID settings for the SRIOV VLAN

With recent changes in the .ndo_set_vf_*() guidelines, resubmitting
this patch that was reverted eariler in 2023:

c27153682eac ("Revert "bnxt_en: Support QOS and TPID settings for the SRIOV VLAN")

Add these missing settings in the .ndo_set_vf_vlan() method.
Older firmware does not support the TPID setting so check for
proper support.

Remove the unused BNXT_VF_QOS flag.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       |  2 ++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 24 +++++++++++++-----------
 3 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 671dc598324a..b236a76c0188 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9196,6 +9196,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH;
+	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED))
+		bp->fw_cap |= BNXT_FW_CAP_DFLT_VLAN_TPID_PCP;
 	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED)
 		bp->fw_cap |= BNXT_FW_CAP_BACKING_STORE_V2;
 	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index e7dcb59c3cdd..da6fad403f52 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1356,7 +1356,6 @@ struct bnxt_vf_info {
 	u16	vlan;
 	u16	func_qcfg_flags;
 	u32	flags;
-#define BNXT_VF_QOS		0x1
 #define BNXT_VF_SPOOFCHK	0x2
 #define BNXT_VF_LINK_FORCED	0x4
 #define BNXT_VF_LINK_UP		0x8
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 22898d3d088b..58bd84b59f0e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -15,6 +15,7 @@
 #include <linux/if_vlan.h>
 #include <linux/interrupt.h>
 #include <linux/etherdevice.h>
+#include <net/dcbnl.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
@@ -196,11 +197,8 @@ int bnxt_get_vf_config(struct net_device *dev, int vf_id,
 		memcpy(&ivi->mac, vf->vf_mac_addr, ETH_ALEN);
 	ivi->max_tx_rate = vf->max_tx_rate;
 	ivi->min_tx_rate = vf->min_tx_rate;
-	ivi->vlan = vf->vlan;
-	if (vf->flags & BNXT_VF_QOS)
-		ivi->qos = vf->vlan >> VLAN_PRIO_SHIFT;
-	else
-		ivi->qos = 0;
+	ivi->vlan = vf->vlan & VLAN_VID_MASK;
+	ivi->qos = vf->vlan >> VLAN_PRIO_SHIFT;
 	ivi->spoofchk = !!(vf->flags & BNXT_VF_SPOOFCHK);
 	ivi->trusted = bnxt_is_trusted_vf(bp, vf);
 	if (!(vf->flags & BNXT_VF_LINK_FORCED))
@@ -256,21 +254,21 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 	if (bp->hwrm_spec_code < 0x10201)
 		return -ENOTSUPP;
 
-	if (vlan_proto != htons(ETH_P_8021Q))
+	if (vlan_proto != htons(ETH_P_8021Q) &&
+	    (vlan_proto != htons(ETH_P_8021AD) ||
+	     !(bp->fw_cap & BNXT_FW_CAP_DFLT_VLAN_TPID_PCP)))
 		return -EPROTONOSUPPORT;
 
 	rc = bnxt_vf_ndo_prep(bp, vf_id);
 	if (rc)
 		return rc;
 
-	/* TODO: needed to implement proper handling of user priority,
-	 * currently fail the command if there is valid priority
-	 */
-	if (vlan_id > 4095 || qos)
+	if (vlan_id >= VLAN_N_VID || qos >= IEEE_8021Q_MAX_PRIORITIES ||
+	    (!vlan_id && qos))
 		return -EINVAL;
 
 	vf = &bp->pf.vf[vf_id];
-	vlan_tag = vlan_id;
+	vlan_tag = vlan_id | (u16)qos << VLAN_PRIO_SHIFT;
 	if (vlan_tag == vf->vlan)
 		return 0;
 
@@ -279,6 +277,10 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos,
 		req->fid = cpu_to_le16(vf->fw_fid);
 		req->dflt_vlan = cpu_to_le16(vlan_tag);
 		req->enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN);
+		if (bp->fw_cap & BNXT_FW_CAP_DFLT_VLAN_TPID_PCP) {
+			req->enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_TPID);
+			req->tpid = vlan_proto;
+		}
 		rc = hwrm_req_send(bp, req);
 		if (!rc)
 			vf->vlan = vlan_tag;
-- 
cgit v1.3-3-g829e


From 2a659a46034f3024b6044dbb054c1cef31bcfdfd Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:30 -0700
Subject: bnxt_en: Deprecate support for legacy INTX mode

Firmware has deprecated support for legacy INTX in 2022 (since v2.27)
and INTX hasn't been tested for many years before that.  INTX was
only used as a fallback mechansim in case MSIX wasn't available.  MSIX
is always supported by all firmware.  If MSIX capability in PCI config
space is not found during probe, abort.

Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-5-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 43 ++++++-------------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 -
 2 files changed, 8 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b236a76c0188..b5a5c4911143 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10770,7 +10770,7 @@ static int bnxt_get_num_msix(struct bnxt *bp)
 	return bnxt_nq_rings_in_use(bp);
 }
 
-static int bnxt_init_msix(struct bnxt *bp)
+static int bnxt_init_int_mode(struct bnxt *bp)
 {
 	int i, total_vecs, max, rc = 0, min = 1, ulp_msix, tx_cp;
 	struct msix_entry *msix_ent;
@@ -10828,7 +10828,7 @@ static int bnxt_init_msix(struct bnxt *bp)
 	return 0;
 
 msix_setup_exit:
-	netdev_err(bp->dev, "bnxt_init_msix err: %x\n", rc);
+	netdev_err(bp->dev, "bnxt_init_int_mode err: %x\n", rc);
 	kfree(bp->irq_tbl);
 	bp->irq_tbl = NULL;
 	pci_disable_msix(bp->pdev);
@@ -10836,35 +10836,6 @@ msix_setup_exit:
 	return rc;
 }
 
-static int bnxt_init_inta(struct bnxt *bp)
-{
-	bp->irq_tbl = kzalloc(sizeof(struct bnxt_irq), GFP_KERNEL);
-	if (!bp->irq_tbl)
-		return -ENOMEM;
-
-	bp->total_irqs = 1;
-	bp->rx_nr_rings = 1;
-	bp->tx_nr_rings = 1;
-	bp->cp_nr_rings = 1;
-	bp->flags |= BNXT_FLAG_SHARED_RINGS;
-	bp->irq_tbl[0].vector = bp->pdev->irq;
-	return 0;
-}
-
-static int bnxt_init_int_mode(struct bnxt *bp)
-{
-	int rc = -ENODEV;
-
-	if (bp->flags & BNXT_FLAG_MSIX_CAP)
-		rc = bnxt_init_msix(bp);
-
-	if (!(bp->flags & BNXT_FLAG_USING_MSIX) && BNXT_PF(bp)) {
-		/* fallback to INTA */
-		rc = bnxt_init_inta(bp);
-	}
-	return rc;
-}
-
 static void bnxt_clear_int_mode(struct bnxt *bp)
 {
 	if (bp->flags & BNXT_FLAG_USING_MSIX)
@@ -12910,7 +12881,7 @@ bool bnxt_rfs_capable(struct bnxt *bp, bool new_rss_ctx)
 	    !BNXT_SUPPORTS_NTUPLE_VNIC(bp))
 		return bnxt_rfs_supported(bp);
 
-	if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings)
+	if (!bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings)
 		return false;
 
 	hwr.grp = bp->rx_nr_rings;
@@ -15772,6 +15743,11 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (pci_is_bridge(pdev))
 		return -ENODEV;
 
+	if (!pdev->msix_cap) {
+		dev_err(&pdev->dev, "MSIX capability not found, aborting\n");
+		return -ENODEV;
+	}
+
 	/* Clear any pending DMA transactions from crash kernel
 	 * while loading driver in capture kernel.
 	 */
@@ -15798,9 +15774,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (BNXT_PF(bp))
 		SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
 
-	if (pdev->msix_cap)
-		bp->flags |= BNXT_FLAG_MSIX_CAP;
-
 	rc = bnxt_init_board(pdev, dev);
 	if (rc < 0)
 		goto init_err_free;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index da6fad403f52..9192cf26c871 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2200,7 +2200,6 @@ struct bnxt {
 	#define BNXT_FLAG_AGG_RINGS	(BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \
 					 BNXT_FLAG_LRO)
 	#define BNXT_FLAG_USING_MSIX	0x40
-	#define BNXT_FLAG_MSIX_CAP	0x80
 	#define BNXT_FLAG_RFS		0x100
 	#define BNXT_FLAG_SHARED_RINGS	0x200
 	#define BNXT_FLAG_PORT_STATS	0x400
-- 
cgit v1.3-3-g829e


From e94d8d97c798900a1c944e479a22a144654fa15f Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:31 -0700
Subject: bnxt_en: Remove BNXT_FLAG_USING_MSIX flag

Now that we only support MSIX, the BNXT_FLAG_USING_MSIX is always true.
Remove it and any if conditions checking for it.  Remove the INTX
handler and associated logic.

Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-6-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       | 99 +++++--------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  1 -
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c |  5 --
 3 files changed, 17 insertions(+), 88 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b5a5c4911143..67f09e22a25c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2854,34 +2854,6 @@ static inline int bnxt_has_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr)
 	return TX_CMP_VALID(txcmp, raw_cons);
 }
 
-static irqreturn_t bnxt_inta(int irq, void *dev_instance)
-{
-	struct bnxt_napi *bnapi = dev_instance;
-	struct bnxt *bp = bnapi->bp;
-	struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
-	u32 cons = RING_CMP(cpr->cp_raw_cons);
-	u32 int_status;
-
-	prefetch(&cpr->cp_desc_ring[CP_RING(cons)][CP_IDX(cons)]);
-
-	if (!bnxt_has_work(bp, cpr)) {
-		int_status = readl(bp->bar0 + BNXT_CAG_REG_LEGACY_INT_STATUS);
-		/* return if erroneous interrupt */
-		if (!(int_status & (0x10000 << cpr->cp_ring_struct.fw_ring_id)))
-			return IRQ_NONE;
-	}
-
-	/* disable ring IRQ */
-	BNXT_CP_DB_IRQ_DIS(cpr->cp_db.doorbell);
-
-	/* Return here if interrupt is shared and is disabled. */
-	if (unlikely(atomic_read(&bp->intr_sem) != 0))
-		return IRQ_HANDLED;
-
-	napi_schedule(&bnapi->napi);
-	return IRQ_HANDLED;
-}
-
 static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			    int budget)
 {
@@ -6876,15 +6848,14 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 			req->cq_handle = cpu_to_le64(ring->handle);
 			req->enables |= cpu_to_le32(
 				RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID);
-		} else if (bp->flags & BNXT_FLAG_USING_MSIX) {
+		} else {
 			req->int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
 		}
 		break;
 	case HWRM_RING_ALLOC_NQ:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_NQ;
 		req->length = cpu_to_le32(bp->cp_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_USING_MSIX)
-			req->int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
+		req->int_mode = RING_ALLOC_REQ_INT_MODE_MSIX;
 		break;
 	default:
 		netdev_err(bp->dev, "hwrm alloc invalid ring type %d\n",
@@ -10653,20 +10624,6 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	}
 }
 
-static void bnxt_setup_inta(struct bnxt *bp)
-{
-	const int len = sizeof(bp->irq_tbl[0].name);
-
-	if (bp->num_tc) {
-		netdev_reset_tc(bp->dev);
-		bp->num_tc = 0;
-	}
-
-	snprintf(bp->irq_tbl[0].name, len, "%s-%s-%d", bp->dev->name, "TxRx",
-		 0);
-	bp->irq_tbl[0].handler = bnxt_inta;
-}
-
 static int bnxt_init_int_mode(struct bnxt *bp);
 
 static int bnxt_setup_int_mode(struct bnxt *bp)
@@ -10679,10 +10636,7 @@ static int bnxt_setup_int_mode(struct bnxt *bp)
 			return rc ?: -ENODEV;
 	}
 
-	if (bp->flags & BNXT_FLAG_USING_MSIX)
-		bnxt_setup_msix(bp);
-	else
-		bnxt_setup_inta(bp);
+	bnxt_setup_msix(bp);
 
 	rc = bnxt_set_real_num_queues(bp);
 	return rc;
@@ -10823,7 +10777,6 @@ static int bnxt_init_int_mode(struct bnxt *bp)
 		rc = -ENOMEM;
 		goto msix_setup_exit;
 	}
-	bp->flags |= BNXT_FLAG_USING_MSIX;
 	kfree(msix_ent);
 	return 0;
 
@@ -10838,12 +10791,10 @@ msix_setup_exit:
 
 static void bnxt_clear_int_mode(struct bnxt *bp)
 {
-	if (bp->flags & BNXT_FLAG_USING_MSIX)
-		pci_disable_msix(bp->pdev);
+	pci_disable_msix(bp->pdev);
 
 	kfree(bp->irq_tbl);
 	bp->irq_tbl = NULL;
-	bp->flags &= ~BNXT_FLAG_USING_MSIX;
 }
 
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
@@ -10941,9 +10892,6 @@ static int bnxt_request_irq(struct bnxt *bp)
 #ifdef CONFIG_RFS_ACCEL
 	rmap = bp->dev->rx_cpu_rmap;
 #endif
-	if (!(bp->flags & BNXT_FLAG_USING_MSIX))
-		flags = IRQF_SHARED;
-
 	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
@@ -11008,29 +10956,22 @@ static void bnxt_del_napi(struct bnxt *bp)
 
 static void bnxt_init_napi(struct bnxt *bp)
 {
-	int i;
+	int (*poll_fn)(struct napi_struct *, int) = bnxt_poll;
 	unsigned int cp_nr_rings = bp->cp_nr_rings;
 	struct bnxt_napi *bnapi;
+	int i;
 
-	if (bp->flags & BNXT_FLAG_USING_MSIX) {
-		int (*poll_fn)(struct napi_struct *, int) = bnxt_poll;
-
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-			poll_fn = bnxt_poll_p5;
-		else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
-			cp_nr_rings--;
-		for (i = 0; i < cp_nr_rings; i++) {
-			bnapi = bp->bnapi[i];
-			netif_napi_add(bp->dev, &bnapi->napi, poll_fn);
-		}
-		if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
-			bnapi = bp->bnapi[cp_nr_rings];
-			netif_napi_add(bp->dev, &bnapi->napi,
-				       bnxt_poll_nitroa0);
-		}
-	} else {
-		bnapi = bp->bnapi[0];
-		netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll);
+	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+		poll_fn = bnxt_poll_p5;
+	else if (BNXT_CHIP_TYPE_NITRO_A0(bp))
+		cp_nr_rings--;
+	for (i = 0; i < cp_nr_rings; i++) {
+		bnapi = bp->bnapi[i];
+		netif_napi_add(bp->dev, &bnapi->napi, poll_fn);
+	}
+	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
+		bnapi = bp->bnapi[cp_nr_rings];
+		netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
 	}
 }
 
@@ -12149,12 +12090,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	rc = bnxt_reserve_rings(bp, irq_re_init);
 	if (rc)
 		return rc;
-	if ((bp->flags & BNXT_FLAG_RFS) &&
-	    !(bp->flags & BNXT_FLAG_USING_MSIX)) {
-		/* disable RFS if falling back to INTA */
-		bp->dev->hw_features &= ~NETIF_F_NTUPLE;
-		bp->flags &= ~BNXT_FLAG_RFS;
-	}
 
 	rc = bnxt_alloc_mem(bp, irq_re_init);
 	if (rc) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 9192cf26c871..b1903a1617f1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2199,7 +2199,6 @@ struct bnxt {
 	#define BNXT_FLAG_STRIP_VLAN	0x20
 	#define BNXT_FLAG_AGG_RINGS	(BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \
 					 BNXT_FLAG_LRO)
-	#define BNXT_FLAG_USING_MSIX	0x40
 	#define BNXT_FLAG_RFS		0x100
 	#define BNXT_FLAG_SHARED_RINGS	0x200
 	#define BNXT_FLAG_PORT_STATS	0x400
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 58bd84b59f0e..7bb8a5d74430 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -902,11 +902,6 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (!(bp->flags & BNXT_FLAG_USING_MSIX)) {
-		netdev_warn(dev, "Not allow SRIOV if the irq mode is not MSIX\n");
-		return 0;
-	}
-
 	rtnl_lock();
 	if (!netif_running(dev)) {
 		netdev_warn(dev, "Reject SRIOV config request since if is down!\n");
-- 
cgit v1.3-3-g829e


From af756aad3d5700c22079e37dc3bbf448559fce8e Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:32 -0700
Subject: bnxt_en: Remove register mapping to support INTX

In legacy INTX mode, a register is mapped so that the INTX handler can
read it to determine if the NIC is the source of the interrupt.  This
and all the related macros are no longer needed now that INTX is no
longer supported.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-7-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 19 -------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 --
 2 files changed, 21 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 67f09e22a25c..2ecf9e324f2e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -302,10 +302,6 @@ static bool bnxt_vf_pciid(enum board_idx idx)
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
 #define DB_CP_FLAGS		(DB_KEY_CP | DB_IDX_VALID | DB_IRQ_DIS)
-#define DB_CP_IRQ_DIS_FLAGS	(DB_KEY_CP | DB_IRQ_DIS)
-
-#define BNXT_CP_DB_IRQ_DIS(db)						\
-		writel(DB_CP_IRQ_DIS_FLAGS, db)
 
 #define BNXT_DB_CQ(db, idx)						\
 	writel(DB_CP_FLAGS | DB_RING_IDX(db, idx), (db)->doorbell)
@@ -11959,20 +11955,6 @@ static int bnxt_update_phy_setting(struct bnxt *bp)
 	return rc;
 }
 
-/* Common routine to pre-map certain register block to different GRC window.
- * A PF has 16 4K windows and a VF has 4 4K windows. However, only 15 windows
- * in PF and 3 windows in VF that can be customized to map in different
- * register blocks.
- */
-static void bnxt_preset_reg_win(struct bnxt *bp)
-{
-	if (BNXT_PF(bp)) {
-		/* CAG registers map to GRC window #4 */
-		writel(BNXT_CAG_REG_BASE,
-		       bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + 12);
-	}
-}
-
 static int bnxt_init_dflt_ring_mode(struct bnxt *bp);
 
 static int bnxt_reinit_after_abort(struct bnxt *bp)
@@ -12077,7 +12059,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
 
-	bnxt_preset_reg_win(bp);
 	netif_carrier_off(bp->dev);
 	if (irq_re_init) {
 		/* Reserve rings now if none were reserved at driver probe. */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b1903a1617f1..3b805ed433ed 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1755,8 +1755,6 @@ struct bnxt_test_info {
 #define BNXT_GRCPF_REG_CHIMP_COMM		0x0
 #define BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER	0x100
 #define BNXT_GRCPF_REG_WINDOW_BASE_OUT		0x400
-#define BNXT_CAG_REG_LEGACY_INT_STATUS		0x4014
-#define BNXT_CAG_REG_BASE			0x300000
 
 #define BNXT_GRC_REG_STATUS_P5			0x520
 
-- 
cgit v1.3-3-g829e


From 4343838ca5ebf9fb52fb9be2459092272a7f70b7 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:33 -0700
Subject: bnxt_en: Replace deprecated PCI MSIX APIs

Use the new pci_alloc_irq_vectors() and pci_free_irq_vectors() to
replace the deprecated pci_enable_msix_range() and pci_disable_msix().

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-8-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2ecf9e324f2e..03598f8e0e07 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10723,7 +10723,6 @@ static int bnxt_get_num_msix(struct bnxt *bp)
 static int bnxt_init_int_mode(struct bnxt *bp)
 {
 	int i, total_vecs, max, rc = 0, min = 1, ulp_msix, tx_cp;
-	struct msix_entry *msix_ent;
 
 	total_vecs = bnxt_get_num_msix(bp);
 	max = bnxt_get_max_func_irqs(bp);
@@ -10733,19 +10732,11 @@ static int bnxt_init_int_mode(struct bnxt *bp)
 	if (!total_vecs)
 		return 0;
 
-	msix_ent = kcalloc(total_vecs, sizeof(struct msix_entry), GFP_KERNEL);
-	if (!msix_ent)
-		return -ENOMEM;
-
-	for (i = 0; i < total_vecs; i++) {
-		msix_ent[i].entry = i;
-		msix_ent[i].vector = 0;
-	}
-
 	if (!(bp->flags & BNXT_FLAG_SHARED_RINGS))
 		min = 2;
 
-	total_vecs = pci_enable_msix_range(bp->pdev, msix_ent, min, total_vecs);
+	total_vecs = pci_alloc_irq_vectors(bp->pdev, min, total_vecs,
+					   PCI_IRQ_MSIX);
 	ulp_msix = bnxt_get_ulp_msix_num(bp);
 	if (total_vecs < 0 || total_vecs < ulp_msix) {
 		rc = -ENODEV;
@@ -10755,7 +10746,7 @@ static int bnxt_init_int_mode(struct bnxt *bp)
 	bp->irq_tbl = kcalloc(total_vecs, sizeof(struct bnxt_irq), GFP_KERNEL);
 	if (bp->irq_tbl) {
 		for (i = 0; i < total_vecs; i++)
-			bp->irq_tbl[i].vector = msix_ent[i].vector;
+			bp->irq_tbl[i].vector = pci_irq_vector(bp->pdev, i);
 
 		bp->total_irqs = total_vecs;
 		/* Trim rings based upon num of vectors allocated */
@@ -10773,21 +10764,19 @@ static int bnxt_init_int_mode(struct bnxt *bp)
 		rc = -ENOMEM;
 		goto msix_setup_exit;
 	}
-	kfree(msix_ent);
 	return 0;
 
 msix_setup_exit:
 	netdev_err(bp->dev, "bnxt_init_int_mode err: %x\n", rc);
 	kfree(bp->irq_tbl);
 	bp->irq_tbl = NULL;
-	pci_disable_msix(bp->pdev);
-	kfree(msix_ent);
+	pci_free_irq_vectors(bp->pdev);
 	return rc;
 }
 
 static void bnxt_clear_int_mode(struct bnxt *bp)
 {
-	pci_disable_msix(bp->pdev);
+	pci_free_irq_vectors(bp->pdev);
 
 	kfree(bp->irq_tbl);
 	bp->irq_tbl = NULL;
-- 
cgit v1.3-3-g829e


From f049d699aeee219ca33d08b48b7e14d7d86aebd5 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:34 -0700
Subject: bnxt_en: Allocate the max bp->irq_tbl size for dynamic msix
 allocation

If dynamic MSIX allocation is supported, additional MSIX can be
allocated at run-time without reinitializing the existing MSIX entries.
The first step to support this dynamic scheme is to allocate a large
enough bp->irq_tbl if dynamic allocation is supported.

Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240828183235.128948-9-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 03598f8e0e07..fa4115f6dafe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10722,7 +10722,7 @@ static int bnxt_get_num_msix(struct bnxt *bp)
 
 static int bnxt_init_int_mode(struct bnxt *bp)
 {
-	int i, total_vecs, max, rc = 0, min = 1, ulp_msix, tx_cp;
+	int i, total_vecs, max, rc = 0, min = 1, ulp_msix, tx_cp, tbl_size;
 
 	total_vecs = bnxt_get_num_msix(bp);
 	max = bnxt_get_max_func_irqs(bp);
@@ -10743,7 +10743,10 @@ static int bnxt_init_int_mode(struct bnxt *bp)
 		goto msix_setup_exit;
 	}
 
-	bp->irq_tbl = kcalloc(total_vecs, sizeof(struct bnxt_irq), GFP_KERNEL);
+	tbl_size = total_vecs;
+	if (pci_msix_can_alloc_dyn(bp->pdev))
+		tbl_size = max;
+	bp->irq_tbl = kcalloc(tbl_size, sizeof(*bp->irq_tbl), GFP_KERNEL);
 	if (bp->irq_tbl) {
 		for (i = 0; i < total_vecs; i++)
 			bp->irq_tbl[i].vector = pci_irq_vector(bp->pdev, i);
-- 
cgit v1.3-3-g829e


From e68256c8a73cafacc7976bb80359511ee0d0ab91 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 28 Aug 2024 11:32:35 -0700
Subject: bnxt_en: Support dynamic MSIX

A range of MSIX vectors are allocated at initialization for the number
needed for RocE and L2.  During run-time, if the user increases or
decreases the number of L2 rings, all the MSIX vectors have to be
freed and a new range has to be allocated.  This is not optimal and
causes disruptions to RoCE traffic every time there is a change in L2
MSIX.

If the system supports dynamic MSIX allocations, use dynamic
allocation to add new L2 MSIX vectors or free unneeded L2 MSIX
vectors.  RoCE traffic is not affected using this scheme.

Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20240828183235.128948-10-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 37 ++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fa4115f6dafe..c9248ed9330c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10622,6 +10622,30 @@ static void bnxt_setup_msix(struct bnxt *bp)
 
 static int bnxt_init_int_mode(struct bnxt *bp);
 
+static int bnxt_change_msix(struct bnxt *bp, int total)
+{
+	struct msi_map map;
+	int i;
+
+	/* add MSIX to the end if needed */
+	for (i = bp->total_irqs; i < total; i++) {
+		map = pci_msix_alloc_irq_at(bp->pdev, i, NULL);
+		if (map.index < 0)
+			return bp->total_irqs;
+		bp->irq_tbl[i].vector = map.virq;
+		bp->total_irqs++;
+	}
+
+	/* trim MSIX from the end if needed */
+	for (i = bp->total_irqs; i > total; i--) {
+		map.index = i - 1;
+		map.virq = bp->irq_tbl[i - 1].vector;
+		pci_msix_free_irq(bp->pdev, map);
+		bp->total_irqs--;
+	}
+	return bp->total_irqs;
+}
+
 static int bnxt_setup_int_mode(struct bnxt *bp)
 {
 	int rc;
@@ -10788,6 +10812,7 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 {
 	bool irq_cleared = false;
+	bool irq_change = false;
 	int tcs = bp->num_tc;
 	int irqs_required;
 	int rc;
@@ -10806,15 +10831,21 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 	}
 
 	if (irq_re_init && BNXT_NEW_RM(bp) && irqs_required != bp->total_irqs) {
-		bnxt_ulp_irq_stop(bp);
-		bnxt_clear_int_mode(bp);
-		irq_cleared = true;
+		irq_change = true;
+		if (!pci_msix_can_alloc_dyn(bp->pdev)) {
+			bnxt_ulp_irq_stop(bp);
+			bnxt_clear_int_mode(bp);
+			irq_cleared = true;
+		}
 	}
 	rc = __bnxt_reserve_rings(bp);
 	if (irq_cleared) {
 		if (!rc)
 			rc = bnxt_init_int_mode(bp);
 		bnxt_ulp_irq_restart(bp, rc);
+	} else if (irq_change && !rc) {
+		if (bnxt_change_msix(bp, irqs_required) != irqs_required)
+			rc = -ENOSPC;
 	}
 	if (rc) {
 		netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc);
-- 
cgit v1.3-3-g829e


From 4d080a029db1b2ff7e173d86886b3429596f3c63 Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Wed, 28 Aug 2024 07:35:11 +0000
Subject: rust: sizes: add commonly used constants

Add rust equivalent to include/linux/sizes.h, makes code more
readable. Only SZ_*K that QT2025 PHY driver uses are added.

Make generated constants accessible with a proper type.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 rust/kernel/lib.rs   |  1 +
 rust/kernel/sizes.rs | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)
 create mode 100644 rust/kernel/sizes.rs

diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 274bdc1b0a82..58ed400198bf 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -43,6 +43,7 @@ pub mod net;
 pub mod page;
 pub mod prelude;
 pub mod print;
+pub mod sizes;
 mod static_assert;
 #[doc(hidden)]
 pub mod std_vendor;
diff --git a/rust/kernel/sizes.rs b/rust/kernel/sizes.rs
new file mode 100644
index 000000000000..834c343e4170
--- /dev/null
+++ b/rust/kernel/sizes.rs
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Commonly used sizes.
+//!
+//! C headers: [`include/linux/sizes.h`](srctree/include/linux/sizes.h).
+
+/// 0x00000400
+pub const SZ_1K: usize = bindings::SZ_1K as usize;
+/// 0x00000800
+pub const SZ_2K: usize = bindings::SZ_2K as usize;
+/// 0x00001000
+pub const SZ_4K: usize = bindings::SZ_4K as usize;
+/// 0x00002000
+pub const SZ_8K: usize = bindings::SZ_8K as usize;
+/// 0x00004000
+pub const SZ_16K: usize = bindings::SZ_16K as usize;
+/// 0x00008000
+pub const SZ_32K: usize = bindings::SZ_32K as usize;
+/// 0x00010000
+pub const SZ_64K: usize = bindings::SZ_64K as usize;
+/// 0x00020000
+pub const SZ_128K: usize = bindings::SZ_128K as usize;
+/// 0x00040000
+pub const SZ_256K: usize = bindings::SZ_256K as usize;
+/// 0x00080000
+pub const SZ_512K: usize = bindings::SZ_512K as usize;
-- 
cgit v1.3-3-g829e


From ffd2747de6ab1545883bffe23f24e60625c1f455 Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Wed, 28 Aug 2024 07:35:12 +0000
Subject: rust: net::phy support probe callback

Support phy_driver probe callback, used to set up device-specific
structures.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 rust/kernel/net/phy.rs | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index fd40b703d224..5e8137a1972f 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -338,6 +338,21 @@ impl<T: Driver> Adapter<T> {
         })
     }
 
+    /// # Safety
+    ///
+    /// `phydev` must be passed by the corresponding callback in `phy_driver`.
+    unsafe extern "C" fn probe_callback(phydev: *mut bindings::phy_device) -> core::ffi::c_int {
+        from_result(|| {
+            // SAFETY: This callback is called only in contexts
+            // where we can exclusively access `phy_device` because
+            // it's not published yet, so the accessors on `Device` are okay
+            // to call.
+            let dev = unsafe { Device::from_raw(phydev) };
+            T::probe(dev)?;
+            Ok(0)
+        })
+    }
+
     /// # Safety
     ///
     /// `phydev` must be passed by the corresponding callback in `phy_driver`.
@@ -511,6 +526,11 @@ pub const fn create_phy_driver<T: Driver>() -> DriverVTable {
         } else {
             None
         },
+        probe: if T::HAS_PROBE {
+            Some(Adapter::<T>::probe_callback)
+        } else {
+            None
+        },
         get_features: if T::HAS_GET_FEATURES {
             Some(Adapter::<T>::get_features_callback)
         } else {
@@ -583,6 +603,11 @@ pub trait Driver {
         kernel::build_error(VTABLE_DEFAULT_ERROR)
     }
 
+    /// Sets up device-specific structures during discovery.
+    fn probe(_dev: &mut Device) -> Result {
+        kernel::build_error(VTABLE_DEFAULT_ERROR)
+    }
+
     /// Probes the hardware to determine what abilities it has.
     fn get_features(_dev: &mut Device) -> Result {
         kernel::build_error(VTABLE_DEFAULT_ERROR)
-- 
cgit v1.3-3-g829e


From 7909892a9fbb3e60623e60c3c3e95e10fc56f687 Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Wed, 28 Aug 2024 07:35:13 +0000
Subject: rust: net::phy implement AsRef<kernel::device::Device> trait

Implement AsRef<kernel::device::Device> trait for Device. A PHY driver
needs a reference to device::Device to call the firmware API.

Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 rust/kernel/net/phy.rs | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 5e8137a1972f..b16e8c10a0a2 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -7,8 +7,7 @@
 //! C headers: [`include/linux/phy.h`](srctree/include/linux/phy.h).
 
 use crate::{error::*, prelude::*, types::Opaque};
-
-use core::marker::PhantomData;
+use core::{marker::PhantomData, ptr::addr_of_mut};
 
 /// PHY state machine states.
 ///
@@ -58,8 +57,9 @@ pub enum DuplexMode {
 ///
 /// # Invariants
 ///
-/// Referencing a `phy_device` using this struct asserts that you are in
-/// a context where all methods defined on this struct are safe to call.
+/// - Referencing a `phy_device` using this struct asserts that you are in
+///   a context where all methods defined on this struct are safe to call.
+/// - This struct always has a valid `self.0.mdio.dev`.
 ///
 /// [`struct phy_device`]: srctree/include/linux/phy.h
 // During the calls to most functions in [`Driver`], the C side (`PHYLIB`) holds a lock that is
@@ -76,9 +76,11 @@ impl Device {
     ///
     /// # Safety
     ///
-    /// For the duration of 'a, the pointer must point at a valid `phy_device`,
-    /// and the caller must be in a context where all methods defined on this struct
-    /// are safe to call.
+    /// For the duration of `'a`,
+    /// - the pointer must point at a valid `phy_device`, and the caller
+    ///   must be in a context where all methods defined on this struct
+    ///   are safe to call.
+    /// - `(*ptr).mdio.dev` must be a valid.
     unsafe fn from_raw<'a>(ptr: *mut bindings::phy_device) -> &'a mut Self {
         // CAST: `Self` is a `repr(transparent)` wrapper around `bindings::phy_device`.
         let ptr = ptr.cast::<Self>();
@@ -302,6 +304,14 @@ impl Device {
     }
 }
 
+impl AsRef<kernel::device::Device> for Device {
+    fn as_ref(&self) -> &kernel::device::Device {
+        let phydev = self.0.get();
+        // SAFETY: The struct invariant ensures that `mdio.dev` is valid.
+        unsafe { kernel::device::Device::as_ref(addr_of_mut!((*phydev).mdio.dev)) }
+    }
+}
+
 /// Defines certain other features this PHY supports (like interrupts).
 ///
 /// These flag values are used in [`Driver::FLAGS`].
-- 
cgit v1.3-3-g829e


From b2e47002b2350f57bfa8fe1c231e9fbb6baef78b Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Wed, 28 Aug 2024 07:35:14 +0000
Subject: rust: net::phy unified read/write API for C22 and C45 registers

Add the unified read/write API for C22 and C45 registers. The
abstractions support access to only C22 registers now. Instead of
adding read/write_c45 methods specifically for C45, a new reg module
supports the unified API to access C22 and C45 registers with trait,
by calling an appropriate phylib functions.

Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                      |   1 +
 drivers/net/phy/ax88796b_rust.rs |   7 +-
 rust/kernel/net/phy.rs           |  31 ++-----
 rust/kernel/net/phy/reg.rs       | 196 +++++++++++++++++++++++++++++++++++++++
 rust/uapi/uapi_helper.h          |   1 +
 5 files changed, 209 insertions(+), 27 deletions(-)
 create mode 100644 rust/kernel/net/phy/reg.rs

diff --git a/MAINTAINERS b/MAINTAINERS
index 289a6b5615ce..66107b9960aa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8357,6 +8357,7 @@ L:	netdev@vger.kernel.org
 L:	rust-for-linux@vger.kernel.org
 S:	Maintained
 F:	rust/kernel/net/phy.rs
+F:	rust/kernel/net/phy/reg.rs
 
 EXEC & BINFMT API, ELF
 R:	Eric Biederman <ebiederm@xmission.com>
diff --git a/drivers/net/phy/ax88796b_rust.rs b/drivers/net/phy/ax88796b_rust.rs
index 5c92572962dc..8c7eb009d9fc 100644
--- a/drivers/net/phy/ax88796b_rust.rs
+++ b/drivers/net/phy/ax88796b_rust.rs
@@ -6,7 +6,7 @@
 //! C version of this driver: [`drivers/net/phy/ax88796b.c`](./ax88796b.c)
 use kernel::{
     c_str,
-    net::phy::{self, DeviceId, Driver},
+    net::phy::{self, reg::C22, DeviceId, Driver},
     prelude::*,
     uapi,
 };
@@ -24,7 +24,6 @@ kernel::module_phy_driver! {
     license: "GPL",
 }
 
-const MII_BMCR: u16 = uapi::MII_BMCR as u16;
 const BMCR_SPEED100: u16 = uapi::BMCR_SPEED100 as u16;
 const BMCR_FULLDPLX: u16 = uapi::BMCR_FULLDPLX as u16;
 
@@ -33,7 +32,7 @@ const BMCR_FULLDPLX: u16 = uapi::BMCR_FULLDPLX as u16;
 // Toggle BMCR_RESET bit off to accommodate broken AX8796B PHY implementation
 // such as used on the Individual Computers' X-Surf 100 Zorro card.
 fn asix_soft_reset(dev: &mut phy::Device) -> Result {
-    dev.write(uapi::MII_BMCR as u16, 0)?;
+    dev.write(C22::BMCR, 0)?;
     dev.genphy_soft_reset()
 }
 
@@ -55,7 +54,7 @@ impl Driver for PhyAX88772A {
         }
         // If MII_LPA is 0, phy_resolve_aneg_linkmode() will fail to resolve
         // linkmode so use MII_BMCR as default values.
-        let ret = dev.read(MII_BMCR)?;
+        let ret = dev.read(C22::BMCR)?;
 
         if ret & BMCR_SPEED100 != 0 {
             dev.set_speed(uapi::SPEED_100);
diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index b16e8c10a0a2..45866db14c76 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -9,6 +9,8 @@
 use crate::{error::*, prelude::*, types::Opaque};
 use core::{marker::PhantomData, ptr::addr_of_mut};
 
+pub mod reg;
+
 /// PHY state machine states.
 ///
 /// Corresponds to the kernel's [`enum phy_state`].
@@ -177,32 +179,15 @@ impl Device {
         unsafe { (*phydev).duplex = v };
     }
 
-    /// Reads a given C22 PHY register.
+    /// Reads a PHY register.
     // This function reads a hardware register and updates the stats so takes `&mut self`.
-    pub fn read(&mut self, regnum: u16) -> Result<u16> {
-        let phydev = self.0.get();
-        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
-        // So it's just an FFI call, open code of `phy_read()` with a valid `phy_device` pointer
-        // `phydev`.
-        let ret = unsafe {
-            bindings::mdiobus_read((*phydev).mdio.bus, (*phydev).mdio.addr, regnum.into())
-        };
-        if ret < 0 {
-            Err(Error::from_errno(ret))
-        } else {
-            Ok(ret as u16)
-        }
+    pub fn read<R: reg::Register>(&mut self, reg: R) -> Result<u16> {
+        reg.read(self)
     }
 
-    /// Writes a given C22 PHY register.
-    pub fn write(&mut self, regnum: u16, val: u16) -> Result {
-        let phydev = self.0.get();
-        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
-        // So it's just an FFI call, open code of `phy_write()` with a valid `phy_device` pointer
-        // `phydev`.
-        to_result(unsafe {
-            bindings::mdiobus_write((*phydev).mdio.bus, (*phydev).mdio.addr, regnum.into(), val)
-        })
+    /// Writes a PHY register.
+    pub fn write<R: reg::Register>(&mut self, reg: R, val: u16) -> Result {
+        reg.write(self, val)
     }
 
     /// Reads a paged register.
diff --git a/rust/kernel/net/phy/reg.rs b/rust/kernel/net/phy/reg.rs
new file mode 100644
index 000000000000..4563737a9675
--- /dev/null
+++ b/rust/kernel/net/phy/reg.rs
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2024 FUJITA Tomonori <fujita.tomonori@gmail.com>
+
+//! PHY register interfaces.
+//!
+//! This module provides support for accessing PHY registers in the
+//! Ethernet management interface clauses 22 and 45 register namespaces, as
+//! defined in IEEE 802.3.
+
+use super::Device;
+use crate::build_assert;
+use crate::error::*;
+use crate::uapi;
+
+mod private {
+    /// Marker that a trait cannot be implemented outside of this crate
+    pub trait Sealed {}
+}
+
+/// Accesses PHY registers.
+///
+/// This trait is used to implement the unified interface to access
+/// C22 and C45 PHY registers.
+///
+/// # Examples
+///
+/// ```ignore
+/// fn link_change_notify(dev: &mut Device) {
+///     // read C22 BMCR register
+///     dev.read(C22::BMCR);
+///     // read C45 PMA/PMD control 1 register
+///     dev.read(C45::new(Mmd::PMAPMD, 0));
+/// }
+/// ```
+pub trait Register: private::Sealed {
+    /// Reads a PHY register.
+    fn read(&self, dev: &mut Device) -> Result<u16>;
+
+    /// Writes a PHY register.
+    fn write(&self, dev: &mut Device, val: u16) -> Result;
+}
+
+/// A single MDIO clause 22 register address (5 bits).
+#[derive(Copy, Clone, Debug)]
+pub struct C22(u8);
+
+impl C22 {
+    /// Basic mode control.
+    pub const BMCR: Self = C22(0x00);
+    /// Basic mode status.
+    pub const BMSR: Self = C22(0x01);
+    /// PHY identifier 1.
+    pub const PHYSID1: Self = C22(0x02);
+    /// PHY identifier 2.
+    pub const PHYSID2: Self = C22(0x03);
+    /// Auto-negotiation advertisement.
+    pub const ADVERTISE: Self = C22(0x04);
+    /// Auto-negotiation link partner base page ability.
+    pub const LPA: Self = C22(0x05);
+    /// Auto-negotiation expansion.
+    pub const EXPANSION: Self = C22(0x06);
+    /// Auto-negotiation next page transmit.
+    pub const NEXT_PAGE_TRANSMIT: Self = C22(0x07);
+    /// Auto-negotiation link partner received next page.
+    pub const LP_RECEIVED_NEXT_PAGE: Self = C22(0x08);
+    /// Master-slave control.
+    pub const MASTER_SLAVE_CONTROL: Self = C22(0x09);
+    /// Master-slave status.
+    pub const MASTER_SLAVE_STATUS: Self = C22(0x0a);
+    /// PSE Control.
+    pub const PSE_CONTROL: Self = C22(0x0b);
+    /// PSE Status.
+    pub const PSE_STATUS: Self = C22(0x0c);
+    /// MMD Register control.
+    pub const MMD_CONTROL: Self = C22(0x0d);
+    /// MMD Register address data.
+    pub const MMD_DATA: Self = C22(0x0e);
+    /// Extended status.
+    pub const EXTENDED_STATUS: Self = C22(0x0f);
+
+    /// Creates a new instance of `C22` with a vendor specific register.
+    pub const fn vendor_specific<const N: u8>() -> Self {
+        build_assert!(
+            N > 0x0f && N < 0x20,
+            "Vendor-specific register address must be between 16 and 31"
+        );
+        C22(N)
+    }
+}
+
+impl private::Sealed for C22 {}
+
+impl Register for C22 {
+    fn read(&self, dev: &mut Device) -> Result<u16> {
+        let phydev = dev.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Device`.
+        // So it's just an FFI call, open code of `phy_read()` with a valid `phy_device` pointer
+        // `phydev`.
+        let ret = unsafe {
+            bindings::mdiobus_read((*phydev).mdio.bus, (*phydev).mdio.addr, self.0.into())
+        };
+        to_result(ret)?;
+        Ok(ret as u16)
+    }
+
+    fn write(&self, dev: &mut Device, val: u16) -> Result {
+        let phydev = dev.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Device`.
+        // So it's just an FFI call, open code of `phy_write()` with a valid `phy_device` pointer
+        // `phydev`.
+        to_result(unsafe {
+            bindings::mdiobus_write((*phydev).mdio.bus, (*phydev).mdio.addr, self.0.into(), val)
+        })
+    }
+}
+
+/// A single MDIO clause 45 register device and address.
+#[derive(Copy, Clone, Debug)]
+pub struct Mmd(u8);
+
+impl Mmd {
+    /// Physical Medium Attachment/Dependent.
+    pub const PMAPMD: Self = Mmd(uapi::MDIO_MMD_PMAPMD as u8);
+    /// WAN interface sublayer.
+    pub const WIS: Self = Mmd(uapi::MDIO_MMD_WIS as u8);
+    /// Physical coding sublayer.
+    pub const PCS: Self = Mmd(uapi::MDIO_MMD_PCS as u8);
+    /// PHY Extender sublayer.
+    pub const PHYXS: Self = Mmd(uapi::MDIO_MMD_PHYXS as u8);
+    /// DTE Extender sublayer.
+    pub const DTEXS: Self = Mmd(uapi::MDIO_MMD_DTEXS as u8);
+    /// Transmission convergence.
+    pub const TC: Self = Mmd(uapi::MDIO_MMD_TC as u8);
+    /// Auto negotiation.
+    pub const AN: Self = Mmd(uapi::MDIO_MMD_AN as u8);
+    /// Separated PMA (1).
+    pub const SEPARATED_PMA1: Self = Mmd(8);
+    /// Separated PMA (2).
+    pub const SEPARATED_PMA2: Self = Mmd(9);
+    /// Separated PMA (3).
+    pub const SEPARATED_PMA3: Self = Mmd(10);
+    /// Separated PMA (4).
+    pub const SEPARATED_PMA4: Self = Mmd(11);
+    /// OFDM PMA/PMD.
+    pub const OFDM_PMAPMD: Self = Mmd(12);
+    /// Power unit.
+    pub const POWER_UNIT: Self = Mmd(13);
+    /// Clause 22 extension.
+    pub const C22_EXT: Self = Mmd(uapi::MDIO_MMD_C22EXT as u8);
+    /// Vendor specific 1.
+    pub const VEND1: Self = Mmd(uapi::MDIO_MMD_VEND1 as u8);
+    /// Vendor specific 2.
+    pub const VEND2: Self = Mmd(uapi::MDIO_MMD_VEND2 as u8);
+}
+
+/// A single MDIO clause 45 register device and address.
+///
+/// Clause 45 uses a 5-bit device address to access a specific MMD within
+/// a port, then a 16-bit register address to access a location within
+/// that device. `C45` represents this by storing a [`Mmd`] and
+/// a register number.
+pub struct C45 {
+    devad: Mmd,
+    regnum: u16,
+}
+
+impl C45 {
+    /// Creates a new instance of `C45`.
+    pub fn new(devad: Mmd, regnum: u16) -> Self {
+        Self { devad, regnum }
+    }
+}
+
+impl private::Sealed for C45 {}
+
+impl Register for C45 {
+    fn read(&self, dev: &mut Device) -> Result<u16> {
+        let phydev = dev.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Device`.
+        // So it's just an FFI call.
+        let ret =
+            unsafe { bindings::phy_read_mmd(phydev, self.devad.0.into(), self.regnum.into()) };
+        to_result(ret)?;
+        Ok(ret as u16)
+    }
+
+    fn write(&self, dev: &mut Device, val: u16) -> Result {
+        let phydev = dev.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Device`.
+        // So it's just an FFI call.
+        to_result(unsafe {
+            bindings::phy_write_mmd(phydev, self.devad.0.into(), self.regnum.into(), val)
+        })
+    }
+}
diff --git a/rust/uapi/uapi_helper.h b/rust/uapi/uapi_helper.h
index 08f5e9334c9e..76d3f103e764 100644
--- a/rust/uapi/uapi_helper.h
+++ b/rust/uapi/uapi_helper.h
@@ -7,5 +7,6 @@
  */
 
 #include <uapi/asm-generic/ioctl.h>
+#include <uapi/linux/mdio.h>
 #include <uapi/linux/mii.h>
 #include <uapi/linux/ethtool.h>
-- 
cgit v1.3-3-g829e


From 5114e05a3cfa61c2ea20fa2e223a8e519aa163e4 Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Wed, 28 Aug 2024 07:35:15 +0000
Subject: rust: net::phy unified genphy_read_status function for C22 and C45
 registers

Add unified genphy_read_status function for C22 and C45
registers. Instead of having genphy_c22 and genphy_c45 methods, this
unifies genphy_read_status functions for C22 and C45.

Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 rust/kernel/net/phy.rs     | 12 ++----------
 rust/kernel/net/phy/reg.rs | 28 ++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs
index 45866db14c76..1d47884aa3cf 100644
--- a/rust/kernel/net/phy.rs
+++ b/rust/kernel/net/phy.rs
@@ -252,16 +252,8 @@ impl Device {
     }
 
     /// Checks the link status and updates current link state.
-    pub fn genphy_read_status(&mut self) -> Result<u16> {
-        let phydev = self.0.get();
-        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
-        // So it's just an FFI call.
-        let ret = unsafe { bindings::genphy_read_status(phydev) };
-        if ret < 0 {
-            Err(Error::from_errno(ret))
-        } else {
-            Ok(ret as u16)
-        }
+    pub fn genphy_read_status<R: reg::Register>(&mut self) -> Result<u16> {
+        R::read_status(self)
     }
 
     /// Updates the link status.
diff --git a/rust/kernel/net/phy/reg.rs b/rust/kernel/net/phy/reg.rs
index 4563737a9675..a7db0064cb7d 100644
--- a/rust/kernel/net/phy/reg.rs
+++ b/rust/kernel/net/phy/reg.rs
@@ -31,6 +31,13 @@ mod private {
 ///     dev.read(C22::BMCR);
 ///     // read C45 PMA/PMD control 1 register
 ///     dev.read(C45::new(Mmd::PMAPMD, 0));
+///
+///     // Checks the link status as reported by registers in the C22 namespace
+///     // and updates current link state.
+///     dev.genphy_read_status::<phy::C22>();
+///     // Checks the link status as reported by registers in the C45 namespace
+///     // and updates current link state.
+///     dev.genphy_read_status::<phy::C45>();
 /// }
 /// ```
 pub trait Register: private::Sealed {
@@ -39,6 +46,9 @@ pub trait Register: private::Sealed {
 
     /// Writes a PHY register.
     fn write(&self, dev: &mut Device, val: u16) -> Result;
+
+    /// Checks the link status and updates current link state.
+    fn read_status(dev: &mut Device) -> Result<u16>;
 }
 
 /// A single MDIO clause 22 register address (5 bits).
@@ -113,6 +123,15 @@ impl Register for C22 {
             bindings::mdiobus_write((*phydev).mdio.bus, (*phydev).mdio.addr, self.0.into(), val)
         })
     }
+
+    fn read_status(dev: &mut Device) -> Result<u16> {
+        let phydev = dev.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        let ret = unsafe { bindings::genphy_read_status(phydev) };
+        to_result(ret)?;
+        Ok(ret as u16)
+    }
 }
 
 /// A single MDIO clause 45 register device and address.
@@ -193,4 +212,13 @@ impl Register for C45 {
             bindings::phy_write_mmd(phydev, self.devad.0.into(), self.regnum.into(), val)
         })
     }
+
+    fn read_status(dev: &mut Device) -> Result<u16> {
+        let phydev = dev.0.get();
+        // SAFETY: `phydev` is pointing to a valid object by the type invariant of `Self`.
+        // So it's just an FFI call.
+        let ret = unsafe { bindings::genphy_c45_read_status(phydev) };
+        to_result(ret)?;
+        Ok(ret as u16)
+    }
 }
-- 
cgit v1.3-3-g829e


From fd3eaad826daf4774835599e264b216a30129c32 Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Wed, 28 Aug 2024 07:35:16 +0000
Subject: net: phy: add Applied Micro QT2025 PHY driver

This driver supports Applied Micro Circuits Corporation QT2025 PHY,
based on a driver for Tehuti Networks TN40xx chips.

The original driver for TN40xx chips supports multiple PHY hardware
(AMCC QT2025, TI TLK10232, Aqrate AQR105, and Marvell 88X3120,
88X3310, and MV88E2010). This driver is extracted from the original
driver and modified to a PHY driver in Rust.

This has been tested with Edimax EN-9320SFP+ 10G network adapter.

Reviewed-by: Trevor Gross <tmgross@umich.edu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS               |   8 ++++
 drivers/net/phy/Kconfig   |   7 ++++
 drivers/net/phy/Makefile  |   1 +
 drivers/net/phy/qt2025.rs | 103 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 119 insertions(+)
 create mode 100644 drivers/net/phy/qt2025.rs

diff --git a/MAINTAINERS b/MAINTAINERS
index 66107b9960aa..baf88e74c907 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1609,6 +1609,14 @@ F:	Documentation/admin-guide/perf/xgene-pmu.rst
 F:	Documentation/devicetree/bindings/perf/apm-xgene-pmu.txt
 F:	drivers/perf/xgene_pmu.c
 
+APPLIED MICRO QT2025 PHY DRIVER
+M:	FUJITA Tomonori <fujita.tomonori@gmail.com>
+R:	Trevor Gross <tmgross@umich.edu>
+L:	netdev@vger.kernel.org
+L:	rust-for-linux@vger.kernel.org
+S:	Maintained
+F:	drivers/net/phy/qt2025.rs
+
 APTINA CAMERA SENSOR PLL
 M:	Laurent Pinchart <Laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index f530fcd092fe..01b235b3bb7e 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -112,6 +112,13 @@ config ADIN1100_PHY
 	  Currently supports the:
 	  - ADIN1100 - Robust,Industrial, Low Power 10BASE-T1L Ethernet PHY
 
+config AMCC_QT2025_PHY
+	tristate "AMCC QT2025 PHY"
+	depends on RUST_PHYLIB_ABSTRACTIONS
+	depends on RUST_FW_LOADER_ABSTRACTIONS
+	help
+	  Adds support for the Applied Micro Circuits Corporation QT2025 PHY.
+
 source "drivers/net/phy/aquantia/Kconfig"
 
 config AX88796B_PHY
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 33adb3df5f64..90f886844381 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_ADIN_PHY)		+= adin.o
 obj-$(CONFIG_ADIN1100_PHY)	+= adin1100.o
 obj-$(CONFIG_AIR_EN8811H_PHY)   += air_en8811h.o
 obj-$(CONFIG_AMD_PHY)		+= amd.o
+obj-$(CONFIG_AMCC_QT2025_PHY)	+= qt2025.o
 obj-$(CONFIG_AQUANTIA_PHY)	+= aquantia/
 ifdef CONFIG_AX88796B_RUST_PHY
   obj-$(CONFIG_AX88796B_PHY)	+= ax88796b_rust.o
diff --git a/drivers/net/phy/qt2025.rs b/drivers/net/phy/qt2025.rs
new file mode 100644
index 000000000000..28d8981f410b
--- /dev/null
+++ b/drivers/net/phy/qt2025.rs
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) Tehuti Networks Ltd.
+// Copyright (C) 2024 FUJITA Tomonori <fujita.tomonori@gmail.com>
+
+//! Applied Micro Circuits Corporation QT2025 PHY driver
+//!
+//! This driver is based on the vendor driver `QT2025_phy.c`. This source
+//! and firmware can be downloaded on the EN-9320SFP+ support site.
+//!
+//! The QT2025 PHY integrates an Intel 8051 micro-controller.
+
+use kernel::c_str;
+use kernel::error::code;
+use kernel::firmware::Firmware;
+use kernel::net::phy::{
+    self,
+    reg::{Mmd, C45},
+    DeviceId, Driver,
+};
+use kernel::prelude::*;
+use kernel::sizes::{SZ_16K, SZ_8K};
+
+kernel::module_phy_driver! {
+    drivers: [PhyQT2025],
+    device_table: [
+        DeviceId::new_with_driver::<PhyQT2025>(),
+    ],
+    name: "qt2025_phy",
+    author: "FUJITA Tomonori <fujita.tomonori@gmail.com>",
+    description: "AMCC QT2025 PHY driver",
+    license: "GPL",
+    firmware: ["qt2025-2.0.3.3.fw"],
+}
+
+struct PhyQT2025;
+
+#[vtable]
+impl Driver for PhyQT2025 {
+    const NAME: &'static CStr = c_str!("QT2025 10Gpbs SFP+");
+    const PHY_DEVICE_ID: phy::DeviceId = phy::DeviceId::new_with_exact_mask(0x0043a400);
+
+    fn probe(dev: &mut phy::Device) -> Result<()> {
+        // Check the hardware revision code.
+        // Only 0x3b works with this driver and firmware.
+        let hw_rev = dev.read(C45::new(Mmd::PMAPMD, 0xd001))?;
+        if (hw_rev >> 8) != 0xb3 {
+            return Err(code::ENODEV);
+        }
+
+        // `MICRO_RESETN`: hold the micro-controller in reset while configuring.
+        dev.write(C45::new(Mmd::PMAPMD, 0xc300), 0x0000)?;
+        // `SREFCLK_FREQ`: configure clock frequency of the micro-controller.
+        dev.write(C45::new(Mmd::PMAPMD, 0xc302), 0x0004)?;
+        // Non loopback mode.
+        dev.write(C45::new(Mmd::PMAPMD, 0xc319), 0x0038)?;
+        // `CUS_LAN_WAN_CONFIG`: select between LAN and WAN (WIS) mode.
+        dev.write(C45::new(Mmd::PMAPMD, 0xc31a), 0x0098)?;
+        // The following writes use standardized registers (3.38 through
+        // 3.41 5/10/25GBASE-R PCS test pattern seed B) for something else.
+        // We don't know what.
+        dev.write(C45::new(Mmd::PCS, 0x0026), 0x0e00)?;
+        dev.write(C45::new(Mmd::PCS, 0x0027), 0x0893)?;
+        dev.write(C45::new(Mmd::PCS, 0x0028), 0xa528)?;
+        dev.write(C45::new(Mmd::PCS, 0x0029), 0x0003)?;
+        // Configure transmit and recovered clock.
+        dev.write(C45::new(Mmd::PMAPMD, 0xa30a), 0x06e1)?;
+        // `MICRO_RESETN`: release the micro-controller from the reset state.
+        dev.write(C45::new(Mmd::PMAPMD, 0xc300), 0x0002)?;
+        // The micro-controller will start running from the boot ROM.
+        dev.write(C45::new(Mmd::PCS, 0xe854), 0x00c0)?;
+
+        let fw = Firmware::request(c_str!("qt2025-2.0.3.3.fw"), dev.as_ref())?;
+        if fw.data().len() > SZ_16K + SZ_8K {
+            return Err(code::EFBIG);
+        }
+
+        // The 24kB of program memory space is accessible by MDIO.
+        // The first 16kB of memory is located in the address range 3.8000h - 3.BFFFh.
+        // The next 8kB of memory is located at 4.8000h - 4.9FFFh.
+        let mut dst_offset = 0;
+        let mut dst_mmd = Mmd::PCS;
+        for (src_idx, val) in fw.data().iter().enumerate() {
+            if src_idx == SZ_16K {
+                // Start writing to the next register with no offset
+                dst_offset = 0;
+                dst_mmd = Mmd::PHYXS;
+            }
+
+            dev.write(C45::new(dst_mmd, 0x8000 + dst_offset), (*val).into())?;
+
+            dst_offset += 1;
+        }
+        // The micro-controller will start running from SRAM.
+        dev.write(C45::new(Mmd::PCS, 0xe854), 0x0040)?;
+
+        // TODO: sleep here until the hw becomes ready.
+        Ok(())
+    }
+
+    fn read_status(dev: &mut phy::Device) -> Result<u16> {
+        dev.genphy_read_status::<C45>()
+    }
+}
-- 
cgit v1.3-3-g829e


From 9f3297511dae19b28b333134cbf7e8746722d6a5 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Fri, 21 Jun 2024 09:25:55 +0200
Subject: igc: Add MQPRIO offload support

Add support for offloading MQPRIO. The hardware has four priorities as well
as four queues. Each queue must be a assigned with a unique priority.

However, the priorities are only considered in TSN Tx mode. There are two
TSN Tx modes. In case of MQPRIO the Qbv capability is not required.
Therefore, use the legacy TSN Tx mode, which performs strict priority
arbitration.

Example for mqprio with hardware offload:

|tc qdisc replace dev ${INTERFACE} handle 100 parent root mqprio num_tc 4 \
|   map 0 0 0 0 0 1 2 3 0 0 0 0 0 0 0 0 \
|   queues 1@0 1@1 1@2 1@3 \
|   hw 1

The mqprio Qdisc also allows to configure the `preemptible_tcs'. However,
frame preemption is not supported yet.

Tested on Intel i225 and implemented by following data sheet section 7.5.2,
Transmit Scheduling.

Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h         | 10 +++-
 drivers/net/ethernet/intel/igc/igc_defines.h | 11 +++++
 drivers/net/ethernet/intel/igc/igc_ethtool.c |  4 ++
 drivers/net/ethernet/intel/igc/igc_main.c    | 69 ++++++++++++++++++++++++++++
 drivers/net/ethernet/intel/igc/igc_regs.h    |  2 +
 drivers/net/ethernet/intel/igc/igc_tsn.c     | 67 +++++++++++++++++++++++++++
 6 files changed, 161 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index c38b4d0f00ce..8642d67af6cc 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -259,6 +259,10 @@ struct igc_adapter {
 	 */
 	spinlock_t qbv_tx_lock;
 
+	bool strict_priority_enable;
+	u8 num_tc;
+	u16 queue_per_tc[IGC_MAX_TX_QUEUES];
+
 	/* OS defined structs */
 	struct pci_dev *pdev;
 	/* lock for statistics */
@@ -382,9 +386,11 @@ extern char igc_driver_name[];
 #define IGC_FLAG_RX_LEGACY		BIT(16)
 #define IGC_FLAG_TSN_QBV_ENABLED	BIT(17)
 #define IGC_FLAG_TSN_QAV_ENABLED	BIT(18)
+#define IGC_FLAG_TSN_LEGACY_ENABLED	BIT(19)
 
-#define IGC_FLAG_TSN_ANY_ENABLED \
-	(IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED)
+#define IGC_FLAG_TSN_ANY_ENABLED				\
+	(IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED |	\
+	 IGC_FLAG_TSN_LEGACY_ENABLED)
 
 #define IGC_FLAG_RSS_FIELD_IPV4_UDP	BIT(6)
 #define IGC_FLAG_RSS_FIELD_IPV6_UDP	BIT(7)
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 511384f3ec5c..52fe10b44b35 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -4,6 +4,8 @@
 #ifndef _IGC_DEFINES_H_
 #define _IGC_DEFINES_H_
 
+#include <linux/bitfield.h>
+
 /* Number of Transmit and Receive Descriptors must be a multiple of 8 */
 #define REQ_TX_DESCRIPTOR_MULTIPLE	8
 #define REQ_RX_DESCRIPTOR_MULTIPLE	8
@@ -553,6 +555,15 @@
 
 #define IGC_MAX_SR_QUEUES		2
 
+#define IGC_TXARB_TXQ_PRIO_0_MASK	GENMASK(1, 0)
+#define IGC_TXARB_TXQ_PRIO_1_MASK	GENMASK(3, 2)
+#define IGC_TXARB_TXQ_PRIO_2_MASK	GENMASK(5, 4)
+#define IGC_TXARB_TXQ_PRIO_3_MASK	GENMASK(7, 6)
+#define IGC_TXARB_TXQ_PRIO_0(x)		FIELD_PREP(IGC_TXARB_TXQ_PRIO_0_MASK, (x))
+#define IGC_TXARB_TXQ_PRIO_1(x)		FIELD_PREP(IGC_TXARB_TXQ_PRIO_1_MASK, (x))
+#define IGC_TXARB_TXQ_PRIO_2(x)		FIELD_PREP(IGC_TXARB_TXQ_PRIO_2_MASK, (x))
+#define IGC_TXARB_TXQ_PRIO_3(x)		FIELD_PREP(IGC_TXARB_TXQ_PRIO_3_MASK, (x))
+
 /* Receive Checksum Control */
 #define IGC_RXCSUM_CRCOFL	0x00000800   /* CRC32 offload enable */
 #define IGC_RXCSUM_PCSD		0x00002000   /* packet checksum disabled */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 3d3ef4e1547c..9ecb2cbbe8e5 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1540,6 +1540,10 @@ static int igc_ethtool_set_channels(struct net_device *netdev,
 	if (ch->other_count != NON_Q_VECTORS)
 		return -EINVAL;
 
+	/* Do not allow channel reconfiguration when mqprio is enabled */
+	if (adapter->strict_priority_enable)
+		return -EINVAL;
+
 	/* Verify the number of channels doesn't exceed hw limits */
 	max_combined = igc_get_max_rss_queues(adapter);
 	if (count > max_combined)
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index dfd6c00b4205..96b2f2a37bc3 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6515,6 +6515,13 @@ static int igc_tc_query_caps(struct igc_adapter *adapter,
 	struct igc_hw *hw = &adapter->hw;
 
 	switch (base->type) {
+	case TC_SETUP_QDISC_MQPRIO: {
+		struct tc_mqprio_caps *caps = base->caps;
+
+		caps->validate_queue_counts = true;
+
+		return 0;
+	}
 	case TC_SETUP_QDISC_TAPRIO: {
 		struct tc_taprio_caps *caps = base->caps;
 
@@ -6532,6 +6539,65 @@ static int igc_tc_query_caps(struct igc_adapter *adapter,
 	}
 }
 
+static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc,
+				   u16 *offset)
+{
+	int i;
+
+	adapter->strict_priority_enable = true;
+	adapter->num_tc = num_tc;
+
+	for (i = 0; i < num_tc; i++)
+		adapter->queue_per_tc[i] = offset[i];
+}
+
+static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
+				 struct tc_mqprio_qopt_offload *mqprio)
+{
+	struct igc_hw *hw = &adapter->hw;
+	int i;
+
+	if (hw->mac.type != igc_i225)
+		return -EOPNOTSUPP;
+
+	if (!mqprio->qopt.num_tc) {
+		adapter->strict_priority_enable = false;
+		goto apply;
+	}
+
+	/* There are as many TCs as Tx queues. */
+	if (mqprio->qopt.num_tc != adapter->num_tx_queues) {
+		NL_SET_ERR_MSG_FMT_MOD(mqprio->extack,
+				       "Only %d traffic classes supported",
+				       adapter->num_tx_queues);
+		return -EOPNOTSUPP;
+	}
+
+	/* Only one queue per TC is supported. */
+	for (i = 0; i < mqprio->qopt.num_tc; i++) {
+		if (mqprio->qopt.count[i] != 1) {
+			NL_SET_ERR_MSG_MOD(mqprio->extack,
+					   "Only one queue per TC supported");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	/* Preemption is not supported yet. */
+	if (mqprio->preemptible_tcs) {
+		NL_SET_ERR_MSG_MOD(mqprio->extack,
+				   "Preemption is not supported yet");
+		return -EOPNOTSUPP;
+	}
+
+	igc_save_mqprio_params(adapter, mqprio->qopt.num_tc,
+			       mqprio->qopt.offset);
+
+	mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+
+apply:
+	return igc_tsn_offload_apply(adapter);
+}
+
 static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -6551,6 +6617,9 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	case TC_SETUP_QDISC_CBS:
 		return igc_tsn_enable_cbs(adapter, type_data);
 
+	case TC_SETUP_QDISC_MQPRIO:
+		return igc_tsn_enable_mqprio(adapter, type_data);
+
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index e5b893fc5b66..c83c723f7c7e 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -238,6 +238,8 @@
 #define IGC_TQAVCC(_n)		(0x3004 + ((_n) * 0x40))
 #define IGC_TQAVHC(_n)		(0x300C + ((_n) * 0x40))
 
+#define IGC_TXARB		0x3354 /* Tx Arbitration Control TxARB - RW */
+
 /* System Time Registers */
 #define IGC_SYSTIML	0x0B600  /* System time register Low - RO */
 #define IGC_SYSTIMH	0x0B604  /* System time register High - RO */
diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
index d68fa7f3d5f0..1e44374ca1ff 100644
--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
+++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
@@ -46,6 +46,9 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
 	if (is_cbs_enabled(adapter))
 		new_flags |= IGC_FLAG_TSN_QAV_ENABLED;
 
+	if (adapter->strict_priority_enable)
+		new_flags |= IGC_FLAG_TSN_LEGACY_ENABLED;
+
 	return new_flags;
 }
 
@@ -102,11 +105,32 @@ bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter)
 		adapter->taprio_offload_enable;
 }
 
+static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 txarb;
+
+	txarb = rd32(IGC_TXARB);
+
+	txarb &= ~(IGC_TXARB_TXQ_PRIO_0_MASK |
+		   IGC_TXARB_TXQ_PRIO_1_MASK |
+		   IGC_TXARB_TXQ_PRIO_2_MASK |
+		   IGC_TXARB_TXQ_PRIO_3_MASK);
+
+	txarb |= IGC_TXARB_TXQ_PRIO_0(queue_per_tc[3]);
+	txarb |= IGC_TXARB_TXQ_PRIO_1(queue_per_tc[2]);
+	txarb |= IGC_TXARB_TXQ_PRIO_2(queue_per_tc[1]);
+	txarb |= IGC_TXARB_TXQ_PRIO_3(queue_per_tc[0]);
+
+	wr32(IGC_TXARB, txarb);
+}
+
 /* Returns the TSN specific registers to their default values after
  * the adapter is reset.
  */
 static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 {
+	u16 queue_per_tc[4] = { 3, 2, 1, 0 };
 	struct igc_hw *hw = &adapter->hw;
 	u32 tqavctrl;
 	int i;
@@ -133,7 +157,16 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
 	wr32(IGC_QBVCYCLET_S, 0);
 	wr32(IGC_QBVCYCLET, NSEC_PER_SEC);
 
+	/* Reset mqprio TC configuration. */
+	netdev_reset_tc(adapter->netdev);
+
+	/* Restore the default Tx arbitration: Priority 0 has the highest
+	 * priority and is assigned to queue 0 and so on and so forth.
+	 */
+	igc_tsn_tx_arb(adapter, queue_per_tc);
+
 	adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED;
+	adapter->flags &= ~IGC_FLAG_TSN_LEGACY_ENABLED;
 
 	return 0;
 }
@@ -172,6 +205,40 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
 	if (igc_is_device_id_i226(hw))
 		igc_tsn_set_retx_qbvfullthreshold(adapter);
 
+	if (adapter->strict_priority_enable) {
+		int err;
+
+		err = netdev_set_num_tc(adapter->netdev, adapter->num_tc);
+		if (err)
+			return err;
+
+		for (i = 0; i < adapter->num_tc; i++) {
+			err = netdev_set_tc_queue(adapter->netdev, i, 1,
+						  adapter->queue_per_tc[i]);
+			if (err)
+				return err;
+		}
+
+		/* In case the card is configured with less than four queues. */
+		for (; i < IGC_MAX_TX_QUEUES; i++)
+			adapter->queue_per_tc[i] = i;
+
+		/* Configure queue priorities according to the user provided
+		 * mapping.
+		 */
+		igc_tsn_tx_arb(adapter, adapter->queue_per_tc);
+
+		/* Enable legacy TSN mode which will do strict priority without
+		 * any other TSN features.
+		 */
+		tqavctrl = rd32(IGC_TQAVCTRL);
+		tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN;
+		tqavctrl &= ~IGC_TQAVCTRL_ENHANCED_QAV;
+		wr32(IGC_TQAVCTRL, tqavctrl);
+
+		return 0;
+	}
+
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igc_ring *ring = adapter->tx_ring[i];
 		u32 txqctl = 0;
-- 
cgit v1.3-3-g829e


From 8dcf2c212078d8ac0714ae872a5496a36eda21e6 Mon Sep 17 00:00:00 2001
From: Kurt Kanzenbach <kurt@linutronix.de>
Date: Fri, 21 Jun 2024 08:56:30 +0200
Subject: igc: Get rid of spurious interrupts

When running the igc with XDP/ZC in busy polling mode with deferral of hard
interrupts, interrupts still happen from time to time. That is caused by
the igc task watchdog which triggers Rx interrupts periodically.

That mechanism has been introduced to overcome skb/memory allocation
failures [1]. So the Rx clean functions stop processing the Rx ring in case
of such failure. The task watchdog triggers Rx interrupts periodically in
the hope that memory became available in the mean time.

The current behavior is undesirable for real time applications, because the
driver induced Rx interrupts trigger also the softirq processing. However,
all real time packets should be processed by the application which uses the
busy polling method.

Therefore, only trigger the Rx interrupts in case of real allocation
failures. Introduce a new flag for signaling that condition.

[1] - https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/?id=3be507547e6177e5c808544bd6a2efa2c7f1d436

Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc.h      |  1 +
 drivers/net/ethernet/intel/igc/igc_main.c | 30 ++++++++++++++++++++++++++----
 2 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 8642d67af6cc..eac0f966e0e4 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -687,6 +687,7 @@ enum igc_ring_flags_t {
 	IGC_RING_FLAG_TX_DETECT_HANG,
 	IGC_RING_FLAG_AF_XDP_ZC,
 	IGC_RING_FLAG_TX_HWTSTAMP,
+	IGC_RING_FLAG_RX_ALLOC_FAILED,
 };
 
 #define ring_uses_large_buffer(ring) \
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 96b2f2a37bc3..da322899e834 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2191,6 +2191,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
 	page = dev_alloc_pages(igc_rx_pg_order(rx_ring));
 	if (unlikely(!page)) {
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -2207,6 +2208,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
 		__free_page(page);
 
 		rx_ring->rx_stats.alloc_failed++;
+		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 		return false;
 	}
 
@@ -2658,6 +2660,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		if (!skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
+			set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
 			break;
 		}
 
@@ -2738,6 +2741,7 @@ static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 	skb = igc_construct_skb_zc(ring, xdp);
 	if (!skb) {
 		ring->rx_stats.alloc_failed++;
+		set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
 		return;
 	}
 
@@ -5807,11 +5811,29 @@ no_wait:
 	if (adapter->flags & IGC_FLAG_HAS_MSIX) {
 		u32 eics = 0;
 
-		for (i = 0; i < adapter->num_q_vectors; i++)
-			eics |= adapter->q_vector[i]->eims_value;
-		wr32(IGC_EICS, eics);
+		for (i = 0; i < adapter->num_q_vectors; i++) {
+			struct igc_q_vector *q_vector = adapter->q_vector[i];
+			struct igc_ring *rx_ring;
+
+			if (!q_vector->rx.ring)
+				continue;
+
+			rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index];
+
+			if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+				eics |= q_vector->eims_value;
+				clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			}
+		}
+		if (eics)
+			wr32(IGC_EICS, eics);
 	} else {
-		wr32(IGC_ICS, IGC_ICS_RXDMT0);
+		struct igc_ring *rx_ring = adapter->rx_ring[0];
+
+		if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
+			clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
+			wr32(IGC_ICS, IGC_ICS_RXDMT0);
+		}
 	}
 
 	igc_ptp_tx_hang(adapter);
-- 
cgit v1.3-3-g829e


From ad7dffae4e40b5ed3b145b08625a4b1a9725211f Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sat, 13 Jul 2024 22:02:09 +0300
Subject: igc: Add Energy Efficient Ethernet ability

According to the IEEE standard report the EEE ability (registers 7.60 and
7.62) and the EEE Link Partner ability (registers 7.61 and 7.63). Use the
kernel's 'ethtool_keee' structure and report EEE link modes.

Example:
ethtool --show-eee <device>

Before:
Advertised EEE link modes:  Not reported
Link partner advertised EEE link modes:  Not reported

After:
	Advertised EEE link modes:  100baseT/Full
	                            1000baseT/Full
	                            2500baseT/Full
	Link partner advertised EEE link modes:  100baseT/Full
	                                         1000baseT/Full
	                                         2500baseT/Full

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 10 ++++
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 73 +++++++++++++++++++++++++++-
 drivers/net/ethernet/intel/igc/igc_regs.h    |  7 +++
 3 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 52fe10b44b35..6d6717ba4ffd 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -652,6 +652,16 @@
 #define IGC_MDIC_READY		0x10000000
 #define IGC_MDIC_ERROR		0x40000000
 
+/* EEE Link Ability */
+#define IGC_EEE_2500BT_MASK	BIT(0)
+#define IGC_EEE_1000BT_MASK	BIT(2)
+#define IGC_EEE_100BT_MASK	BIT(1)
+
+/* EEE Link-Partner Ability */
+#define IGC_LP_EEE_2500BT_MASK	BIT(0)
+#define IGC_LP_EEE_1000BT_MASK	BIT(2)
+#define IGC_LP_EEE_100BT_MASK	BIT(1)
+
 #define IGC_N0_QUEUE		-1
 
 #define IGC_MAX_MAC_HDR_LEN	127
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 9ecb2cbbe8e5..457b5d7f1610 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1631,8 +1631,11 @@ static int igc_ethtool_get_eee(struct net_device *netdev,
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct igc_hw *hw = &adapter->hw;
-	u32 eeer;
+	struct igc_phy_info *phy = &hw->phy;
+	u16 eee_advert, eee_lp_advert;
+	u32 eeer, ret_val;
 
+	/* EEE supported */
 	linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
 			 edata->supported);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
@@ -1640,6 +1643,74 @@ static int igc_ethtool_get_eee(struct net_device *netdev,
 	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
 			 edata->supported);
 
+	/* EEE Advertisement 1 - reg 7.60 */
+	ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
+				    MMD_DEVADDR_SHIFT) |
+				    IGC_ANEG_EEE_AB1,
+				    &eee_advert);
+	if (ret_val) {
+		netdev_err(adapter->netdev,
+			   "Failed to read IEEE 7.60 register\n");
+		return -EINVAL;
+	}
+
+	if (eee_advert & IGC_EEE_1000BT_MASK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 edata->advertised);
+
+	if (eee_advert & IGC_EEE_100BT_MASK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 edata->advertised);
+
+	/* EEE Advertisement 2 - reg 7.62 */
+	ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
+				    MMD_DEVADDR_SHIFT) |
+				    IGC_ANEG_EEE_AB2,
+				    &eee_advert);
+	if (ret_val) {
+		netdev_err(adapter->netdev,
+			   "Failed to read IEEE 7.62 register\n");
+		return -EINVAL;
+	}
+
+	if (eee_advert & IGC_EEE_2500BT_MASK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+				 edata->advertised);
+
+	/* EEE Link-Partner Ability 1 - reg 7.61 */
+	ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
+				    MMD_DEVADDR_SHIFT) |
+				    IGC_ANEG_EEE_LP_AB1,
+				    &eee_lp_advert);
+	if (ret_val) {
+		netdev_err(adapter->netdev,
+			   "Failed to read IEEE 7.61 register\n");
+		return -EINVAL;
+	}
+
+	if (eee_lp_advert & IGC_LP_EEE_1000BT_MASK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 edata->lp_advertised);
+
+	if (eee_lp_advert & IGC_LP_EEE_100BT_MASK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 edata->lp_advertised);
+
+	/* EEE Link-Partner Ability 2 - reg 7.63 */
+	ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
+				    MMD_DEVADDR_SHIFT) |
+				    IGC_ANEG_EEE_LP_AB2,
+				    &eee_lp_advert);
+	if (ret_val) {
+		netdev_err(adapter->netdev,
+			   "Failed to read IEEE 7.63 register\n");
+		return -EINVAL;
+	}
+
+	if (eee_lp_advert & IGC_LP_EEE_2500BT_MASK)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+				 edata->lp_advertised);
+
 	eeer = rd32(IGC_EEER);
 
 	/* EEE status on negotiated link */
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index c83c723f7c7e..bb6f37f5d3a5 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -310,6 +310,13 @@
 #define IGC_IPCNFG	0x0E38 /* Internal PHY Configuration */
 #define IGC_EEE_SU	0x0E34 /* EEE Setup */
 
+/* EEE ANeg Advertisement Register - reg 7.60 and reg 7.62 */
+#define IGC_ANEG_EEE_AB1	0x003c
+#define IGC_ANEG_EEE_AB2	0x003e
+/* EEE ANeg Link-Partner Advertisement Register - reg 7.61 and reg 7.63 */
+#define IGC_ANEG_EEE_LP_AB1	0x003d
+#define IGC_ANEG_EEE_LP_AB2	0x003f
+
 /* LTR registers */
 #define IGC_LTRC	0x01A0 /* Latency Tolerance Reporting Control */
 #define IGC_LTRMINV	0x5BB0 /* LTR Minimum Value */
-- 
cgit v1.3-3-g829e


From f9cb5e01cc4e57d86e906330828139efc06de602 Mon Sep 17 00:00:00 2001
From: Sasha Neftin <sasha.neftin@intel.com>
Date: Sun, 18 Aug 2024 11:32:50 +0300
Subject: igc: Move the MULTI GBT AN Control Register to _regs file

MULTI GBT AN Control Register is IEEE Standard Register 7.32 (not a mask).
The right place should be in igc_reg.h file. In accordance with the
registers naming convention added IGC_' prefix.

Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_defines.h | 1 -
 drivers/net/ethernet/intel/igc/igc_phy.c     | 4 ++--
 drivers/net/ethernet/intel/igc/igc_regs.h    | 3 +++
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 6d6717ba4ffd..8e449904aa7d 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -178,7 +178,6 @@
 
 /* PHY GPY 211 registers */
 #define STANDARD_AN_REG_MASK	0x0007 /* MMD */
-#define ANEG_MULTIGBT_AN_CTRL	0x0020 /* MULTI GBT AN Control Register */
 #define MMD_DEVADDR_SHIFT	16     /* Shift MMD to higher bits */
 #define CR_2500T_FD_CAPS	0x0080 /* Advertise 2500T FD capability */
 
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 861f37076861..2801e5f24df9 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -240,7 +240,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw)
 		/* Read the MULTI GBT AN Control Register - reg 7.32 */
 		ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK <<
 					    MMD_DEVADDR_SHIFT) |
-					    ANEG_MULTIGBT_AN_CTRL,
+					    IGC_ANEG_MULTIGBT_AN_CTRL,
 					    &aneg_multigbt_an_ctrl);
 
 		if (ret_val)
@@ -380,7 +380,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw)
 		ret_val = phy->ops.write_reg(hw,
 					     (STANDARD_AN_REG_MASK <<
 					     MMD_DEVADDR_SHIFT) |
-					     ANEG_MULTIGBT_AN_CTRL,
+					     IGC_ANEG_MULTIGBT_AN_CTRL,
 					     aneg_multigbt_an_ctrl);
 
 	return ret_val;
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index bb6f37f5d3a5..12ddc5793651 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -310,6 +310,9 @@
 #define IGC_IPCNFG	0x0E38 /* Internal PHY Configuration */
 #define IGC_EEE_SU	0x0E34 /* EEE Setup */
 
+/* MULTI GBT AN Control Register - reg. 7.32 */
+#define IGC_ANEG_MULTIGBT_AN_CTRL	0x0020
+
 /* EEE ANeg Advertisement Register - reg 7.60 and reg 7.62 */
 #define IGC_ANEG_EEE_AB1	0x003c
 #define IGC_ANEG_EEE_AB2	0x003e
-- 
cgit v1.3-3-g829e


From 74ce94ac38a6eac2ffc235739294f24964fd0a86 Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Thu, 29 Aug 2024 10:12:53 +0800
Subject: sfc: Convert to use ERR_CAST()

As opposed to open-code, using the ERR_CAST macro clearly indicates that
this is a pointer to an error value and a type conversion was performed.

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20240829021253.3066-1-shenlichuan@vivo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/tc_counters.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/tc_counters.c b/drivers/net/ethernet/sfc/tc_counters.c
index c44088424323..a421b0123506 100644
--- a/drivers/net/ethernet/sfc/tc_counters.c
+++ b/drivers/net/ethernet/sfc/tc_counters.c
@@ -249,7 +249,7 @@ struct efx_tc_counter_index *efx_tc_flower_get_counter_index(
 					       &ctr->linkage,
 					       efx_tc_counter_id_ht_params);
 			kfree(ctr);
-			return (void *)cnt; /* it's an ERR_PTR */
+			return ERR_CAST(cnt);
 		}
 		ctr->cnt = cnt;
 		refcount_set(&ctr->ref, 1);
-- 
cgit v1.3-3-g829e


From f24f966feb62164f4a68d1b84e866504904ac4ac Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Thu, 29 Aug 2024 15:25:38 +0800
Subject: nfp: Convert to use ERR_CAST()

Use ERR_CAST() as it is designed for casting an error pointer to
another type.

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Link: https://patch.msgid.link/20240829072538.33195-1-shenlichuan@vivo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index 7136bc48530b..df0234a338a8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -278,7 +278,7 @@ struct nfp_nsp *nfp_nsp_open(struct nfp_cpp *cpp)
 
 	res = nfp_resource_acquire(cpp, NFP_RESOURCE_NSP);
 	if (IS_ERR(res))
-		return (void *)res;
+		return ERR_CAST(res);
 
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state) {
-- 
cgit v1.3-3-g829e


From b26b64493343659cce8bbffa358bf39e4f68bdec Mon Sep 17 00:00:00 2001
From: Yan Zhen <yanzhen@vivo.com>
Date: Thu, 29 Aug 2024 17:55:09 +0800
Subject: net: openvswitch: Use ERR_CAST() to return

Using ERR_CAST() is more reasonable and safer, When it is necessary
to convert the type of an error pointer and return it.

Signed-off-by: Yan Zhen <yanzhen@vivo.com>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Link: https://patch.msgid.link/20240829095509.3151987-1-yanzhen@vivo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/openvswitch/flow_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index c92bdc4dfe19..729ef582a3a8 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2491,7 +2491,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 
 	acts = nla_alloc_flow_actions(new_acts_size);
 	if (IS_ERR(acts))
-		return (void *)acts;
+		return ERR_CAST(acts);
 
 	memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len);
 	acts->actions_len = (*sfa)->actions_len;
-- 
cgit v1.3-3-g829e


From 8c2bd38b95f75f3d2a08c93e35303e26d480d24e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Aug 2024 14:46:39 +0000
Subject: icmp: change the order of rate limits

ICMP messages are ratelimited :

After the blamed commits, the two rate limiters are applied in this order:

1) host wide ratelimit (icmp_global_allow())

2) Per destination ratelimit (inetpeer based)

In order to avoid side-channels attacks, we need to apply
the per destination check first.

This patch makes the following change :

1) icmp_global_allow() checks if the host wide limit is reached.
   But credits are not yet consumed. This is deferred to 3)

2) The per destination limit is checked/updated.
   This might add a new node in inetpeer tree.

3) icmp_global_consume() consumes tokens if prior operations succeeded.

This means that host wide ratelimit is still effective
in keeping inetpeer tree small even under DDOS.

As a bonus, I removed icmp_global.lock as the fast path
can use a lock-free operation.

Fixes: c0303efeab73 ("net: reduce cycles spend on ICMP replies that gets rate limited")
Fixes: 4cdf507d5452 ("icmp: add a global rate limitation")
Reported-by: Keyu Man <keyu.man@email.ucr.edu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Cc: Jesper Dangaard Brouer <hawk@kernel.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20240829144641.3880376-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h |   2 ++
 net/ipv4/icmp.c  | 103 ++++++++++++++++++++++++++++++-------------------------
 net/ipv6/icmp.c  |  28 +++++++++------
 3 files changed, 76 insertions(+), 57 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index c5606cadb1a5..82248813619e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -795,6 +795,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 }
 
 bool icmp_global_allow(void);
+void icmp_global_consume(void);
+
 extern int sysctl_icmp_msgs_per_sec;
 extern int sysctl_icmp_msgs_burst;
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index b8f56d03fcbb..0078e8fb2e86 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -224,57 +224,59 @@ int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
 int sysctl_icmp_msgs_burst __read_mostly = 50;
 
 static struct {
-	spinlock_t	lock;
-	u32		credit;
+	atomic_t	credit;
 	u32		stamp;
-} icmp_global = {
-	.lock		= __SPIN_LOCK_UNLOCKED(icmp_global.lock),
-};
+} icmp_global;
 
 /**
  * icmp_global_allow - Are we allowed to send one more ICMP message ?
  *
  * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec.
  * Returns false if we reached the limit and can not send another packet.
- * Note: called with BH disabled
+ * Works in tandem with icmp_global_consume().
  */
 bool icmp_global_allow(void)
 {
-	u32 credit, delta, incr = 0, now = (u32)jiffies;
-	bool rc = false;
+	u32 delta, now, oldstamp;
+	int incr, new, old;
 
-	/* Check if token bucket is empty and cannot be refilled
-	 * without taking the spinlock. The READ_ONCE() are paired
-	 * with the following WRITE_ONCE() in this same function.
+	/* Note: many cpus could find this condition true.
+	 * Then later icmp_global_consume() could consume more credits,
+	 * this is an acceptable race.
 	 */
-	if (!READ_ONCE(icmp_global.credit)) {
-		delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ);
-		if (delta < HZ / 50)
-			return false;
-	}
+	if (atomic_read(&icmp_global.credit) > 0)
+		return true;
 
-	spin_lock(&icmp_global.lock);
-	delta = min_t(u32, now - icmp_global.stamp, HZ);
-	if (delta >= HZ / 50) {
-		incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
-		if (incr)
-			WRITE_ONCE(icmp_global.stamp, now);
-	}
-	credit = min_t(u32, icmp_global.credit + incr,
-		       READ_ONCE(sysctl_icmp_msgs_burst));
-	if (credit) {
-		/* We want to use a credit of one in average, but need to randomize
-		 * it for security reasons.
-		 */
-		credit = max_t(int, credit - get_random_u32_below(3), 0);
-		rc = true;
+	now = jiffies;
+	oldstamp = READ_ONCE(icmp_global.stamp);
+	delta = min_t(u32, now - oldstamp, HZ);
+	if (delta < HZ / 50)
+		return false;
+
+	incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
+	if (!incr)
+		return false;
+
+	if (cmpxchg(&icmp_global.stamp, oldstamp, now) == oldstamp) {
+		old = atomic_read(&icmp_global.credit);
+		do {
+			new = min(old + incr, READ_ONCE(sysctl_icmp_msgs_burst));
+		} while (!atomic_try_cmpxchg(&icmp_global.credit, &old, new));
 	}
-	WRITE_ONCE(icmp_global.credit, credit);
-	spin_unlock(&icmp_global.lock);
-	return rc;
+	return true;
 }
 EXPORT_SYMBOL(icmp_global_allow);
 
+void icmp_global_consume(void)
+{
+	int credits = get_random_u32_below(3);
+
+	/* Note: this might make icmp_global.credit negative. */
+	if (credits)
+		atomic_sub(credits, &icmp_global.credit);
+}
+EXPORT_SYMBOL(icmp_global_consume);
+
 static bool icmpv4_mask_allow(struct net *net, int type, int code)
 {
 	if (type > NR_ICMP_TYPES)
@@ -291,14 +293,16 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
 	return false;
 }
 
-static bool icmpv4_global_allow(struct net *net, int type, int code)
+static bool icmpv4_global_allow(struct net *net, int type, int code,
+				bool *apply_ratelimit)
 {
 	if (icmpv4_mask_allow(net, type, code))
 		return true;
 
-	if (icmp_global_allow())
+	if (icmp_global_allow()) {
+		*apply_ratelimit = true;
 		return true;
-
+	}
 	__ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
 	return false;
 }
@@ -308,15 +312,16 @@ static bool icmpv4_global_allow(struct net *net, int type, int code)
  */
 
 static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
-			       struct flowi4 *fl4, int type, int code)
+			       struct flowi4 *fl4, int type, int code,
+			       bool apply_ratelimit)
 {
 	struct dst_entry *dst = &rt->dst;
 	struct inet_peer *peer;
 	bool rc = true;
 	int vif;
 
-	if (icmpv4_mask_allow(net, type, code))
-		goto out;
+	if (!apply_ratelimit)
+		return true;
 
 	/* No rate limit on loopback */
 	if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
@@ -331,6 +336,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 out:
 	if (!rc)
 		__ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST);
+	else
+		icmp_global_consume();
 	return rc;
 }
 
@@ -402,6 +409,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	struct ipcm_cookie ipc;
 	struct rtable *rt = skb_rtable(skb);
 	struct net *net = dev_net(rt->dst.dev);
+	bool apply_ratelimit = false;
 	struct flowi4 fl4;
 	struct sock *sk;
 	struct inet_sock *inet;
@@ -413,11 +421,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb))
 		return;
 
-	/* Needed by both icmp_global_allow and icmp_xmit_lock */
+	/* Needed by both icmpv4_global_allow and icmp_xmit_lock */
 	local_bh_disable();
 
-	/* global icmp_msgs_per_sec */
-	if (!icmpv4_global_allow(net, type, code))
+	/* is global icmp_msgs_per_sec exhausted ? */
+	if (!icmpv4_global_allow(net, type, code, &apply_ratelimit))
 		goto out_bh_enable;
 
 	sk = icmp_xmit_lock(net);
@@ -450,7 +458,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		goto out_unlock;
-	if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
+	if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit))
 		icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt);
 	ip_rt_put(rt);
 out_unlock:
@@ -596,6 +604,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	int room;
 	struct icmp_bxm icmp_param;
 	struct rtable *rt = skb_rtable(skb_in);
+	bool apply_ratelimit = false;
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	__be32 saddr;
@@ -677,7 +686,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		}
 	}
 
-	/* Needed by both icmp_global_allow and icmp_xmit_lock */
+	/* Needed by both icmpv4_global_allow and icmp_xmit_lock */
 	local_bh_disable();
 
 	/* Check global sysctl_icmp_msgs_per_sec ratelimit, unless
@@ -685,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	 * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow)
 	 */
 	if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) &&
-	      !icmpv4_global_allow(net, type, code))
+	      !icmpv4_global_allow(net, type, code, &apply_ratelimit))
 		goto out_bh_enable;
 
 	sk = icmp_xmit_lock(net);
@@ -744,7 +753,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		goto out_unlock;
 
 	/* peer icmp_ratelimit */
-	if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code))
+	if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit))
 		goto ende;
 
 	/* RFC says return as much as we can without exceeding 576 bytes. */
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 7b31674644ef..46f70e4a8351 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -175,14 +175,16 @@ static bool icmpv6_mask_allow(struct net *net, int type)
 	return false;
 }
 
-static bool icmpv6_global_allow(struct net *net, int type)
+static bool icmpv6_global_allow(struct net *net, int type,
+				bool *apply_ratelimit)
 {
 	if (icmpv6_mask_allow(net, type))
 		return true;
 
-	if (icmp_global_allow())
+	if (icmp_global_allow()) {
+		*apply_ratelimit = true;
 		return true;
-
+	}
 	__ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
 	return false;
 }
@@ -191,13 +193,13 @@ static bool icmpv6_global_allow(struct net *net, int type)
  * Check the ICMP output rate limit
  */
 static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
-			       struct flowi6 *fl6)
+			       struct flowi6 *fl6, bool apply_ratelimit)
 {
 	struct net *net = sock_net(sk);
 	struct dst_entry *dst;
 	bool res = false;
 
-	if (icmpv6_mask_allow(net, type))
+	if (!apply_ratelimit)
 		return true;
 
 	/*
@@ -228,6 +230,8 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 	if (!res)
 		__ICMP6_INC_STATS(net, ip6_dst_idev(dst),
 				  ICMP6_MIB_RATELIMITHOST);
+	else
+		icmp_global_consume();
 	dst_release(dst);
 	return res;
 }
@@ -452,6 +456,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	struct net *net;
 	struct ipv6_pinfo *np;
 	const struct in6_addr *saddr = NULL;
+	bool apply_ratelimit = false;
 	struct dst_entry *dst;
 	struct icmp6hdr tmp_hdr;
 	struct flowi6 fl6;
@@ -533,11 +538,12 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		return;
 	}
 
-	/* Needed by both icmp_global_allow and icmpv6_xmit_lock */
+	/* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */
 	local_bh_disable();
 
 	/* Check global sysctl_icmp_msgs_per_sec ratelimit */
-	if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
+	if (!(skb->dev->flags & IFF_LOOPBACK) &&
+	    !icmpv6_global_allow(net, type, &apply_ratelimit))
 		goto out_bh_enable;
 
 	mip6_addr_swap(skb, parm);
@@ -575,7 +581,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 
 	np = inet6_sk(sk);
 
-	if (!icmpv6_xrlim_allow(sk, type, &fl6))
+	if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit))
 		goto out;
 
 	tmp_hdr.icmp6_type = type;
@@ -717,6 +723,7 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
 	struct ipv6_pinfo *np;
 	const struct in6_addr *saddr = NULL;
 	struct icmp6hdr *icmph = icmp6_hdr(skb);
+	bool apply_ratelimit = false;
 	struct icmp6hdr tmp_hdr;
 	struct flowi6 fl6;
 	struct icmpv6_msg msg;
@@ -781,8 +788,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
 		goto out;
 
 	/* Check the ratelimit */
-	if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) ||
-	    !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6))
+	if ((!(skb->dev->flags & IFF_LOOPBACK) &&
+	    !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) ||
+	    !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit))
 		goto out_dst_release;
 
 	idev = __in6_dev_get(skb->dev);
-- 
cgit v1.3-3-g829e


From b056b4cd9178f7a1d5d57f7b48b073c29729ddaa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Aug 2024 14:46:40 +0000
Subject: icmp: move icmp_global.credit and icmp_global.stamp to per netns
 storage

Host wide ICMP ratelimiter should be per netns, to provide better isolation.

Following patch in this series makes the sysctl per netns.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240829144641.3880376-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h         |  4 ++--
 include/net/netns/ipv4.h |  3 ++-
 net/ipv4/icmp.c          | 26 +++++++++++---------------
 net/ipv6/icmp.c          |  4 ++--
 4 files changed, 17 insertions(+), 20 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 82248813619e..d3bca4e83979 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -794,8 +794,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 	ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0);
 }
 
-bool icmp_global_allow(void);
-void icmp_global_consume(void);
+bool icmp_global_allow(struct net *net);
+void icmp_global_consume(struct net *net);
 
 extern int sysctl_icmp_msgs_per_sec;
 extern int sysctl_icmp_msgs_burst;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 5fcd61ada622..54fe7c079fff 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -122,7 +122,8 @@ struct netns_ipv4 {
 	u8 sysctl_icmp_errors_use_inbound_ifaddr;
 	int sysctl_icmp_ratelimit;
 	int sysctl_icmp_ratemask;
-
+	atomic_t icmp_global_credit;
+	u32 icmp_global_stamp;
 	u32 ip_rt_min_pmtu;
 	int ip_rt_mtu_expires;
 	int ip_rt_min_advmss;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 0078e8fb2e86..2e1d81dbdbb6 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -223,19 +223,15 @@ static inline void icmp_xmit_unlock(struct sock *sk)
 int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
 int sysctl_icmp_msgs_burst __read_mostly = 50;
 
-static struct {
-	atomic_t	credit;
-	u32		stamp;
-} icmp_global;
-
 /**
  * icmp_global_allow - Are we allowed to send one more ICMP message ?
+ * @net: network namespace
  *
  * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec.
  * Returns false if we reached the limit and can not send another packet.
  * Works in tandem with icmp_global_consume().
  */
-bool icmp_global_allow(void)
+bool icmp_global_allow(struct net *net)
 {
 	u32 delta, now, oldstamp;
 	int incr, new, old;
@@ -244,11 +240,11 @@ bool icmp_global_allow(void)
 	 * Then later icmp_global_consume() could consume more credits,
 	 * this is an acceptable race.
 	 */
-	if (atomic_read(&icmp_global.credit) > 0)
+	if (atomic_read(&net->ipv4.icmp_global_credit) > 0)
 		return true;
 
 	now = jiffies;
-	oldstamp = READ_ONCE(icmp_global.stamp);
+	oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp);
 	delta = min_t(u32, now - oldstamp, HZ);
 	if (delta < HZ / 50)
 		return false;
@@ -257,23 +253,23 @@ bool icmp_global_allow(void)
 	if (!incr)
 		return false;
 
-	if (cmpxchg(&icmp_global.stamp, oldstamp, now) == oldstamp) {
-		old = atomic_read(&icmp_global.credit);
+	if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) {
+		old = atomic_read(&net->ipv4.icmp_global_credit);
 		do {
 			new = min(old + incr, READ_ONCE(sysctl_icmp_msgs_burst));
-		} while (!atomic_try_cmpxchg(&icmp_global.credit, &old, new));
+		} while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new));
 	}
 	return true;
 }
 EXPORT_SYMBOL(icmp_global_allow);
 
-void icmp_global_consume(void)
+void icmp_global_consume(struct net *net)
 {
 	int credits = get_random_u32_below(3);
 
 	/* Note: this might make icmp_global.credit negative. */
 	if (credits)
-		atomic_sub(credits, &icmp_global.credit);
+		atomic_sub(credits, &net->ipv4.icmp_global_credit);
 }
 EXPORT_SYMBOL(icmp_global_consume);
 
@@ -299,7 +295,7 @@ static bool icmpv4_global_allow(struct net *net, int type, int code,
 	if (icmpv4_mask_allow(net, type, code))
 		return true;
 
-	if (icmp_global_allow()) {
+	if (icmp_global_allow(net)) {
 		*apply_ratelimit = true;
 		return true;
 	}
@@ -337,7 +333,7 @@ out:
 	if (!rc)
 		__ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST);
 	else
-		icmp_global_consume();
+		icmp_global_consume(net);
 	return rc;
 }
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 46f70e4a8351..071b0bc1179d 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -181,7 +181,7 @@ static bool icmpv6_global_allow(struct net *net, int type,
 	if (icmpv6_mask_allow(net, type))
 		return true;
 
-	if (icmp_global_allow()) {
+	if (icmp_global_allow(net)) {
 		*apply_ratelimit = true;
 		return true;
 	}
@@ -231,7 +231,7 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
 		__ICMP6_INC_STATS(net, ip6_dst_idev(dst),
 				  ICMP6_MIB_RATELIMITHOST);
 	else
-		icmp_global_consume();
+		icmp_global_consume(net);
 	dst_release(dst);
 	return res;
 }
-- 
cgit v1.3-3-g829e


From f17bf505ff89595df5147755e51441632a5dc563 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 29 Aug 2024 14:46:41 +0000
Subject: icmp: icmp_msgs_per_sec and icmp_msgs_burst sysctls become per netns

Previous patch made ICMP rate limits per netns, it makes sense
to allow each netns to change the associated sysctl.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240829144641.3880376-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h           |  3 ---
 include/net/netns/ipv4.h   |  2 ++
 net/ipv4/icmp.c            |  9 ++++-----
 net/ipv4/sysctl_net_ipv4.c | 32 ++++++++++++++++----------------
 4 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index d3bca4e83979..1ee472fa8b37 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -797,9 +797,6 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 bool icmp_global_allow(struct net *net);
 void icmp_global_consume(struct net *net);
 
-extern int sysctl_icmp_msgs_per_sec;
-extern int sysctl_icmp_msgs_burst;
-
 #ifdef CONFIG_PROC_FS
 int ip_misc_proc_init(void);
 #endif
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 54fe7c079fff..276f622f3516 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -122,6 +122,8 @@ struct netns_ipv4 {
 	u8 sysctl_icmp_errors_use_inbound_ifaddr;
 	int sysctl_icmp_ratelimit;
 	int sysctl_icmp_ratemask;
+	int sysctl_icmp_msgs_per_sec;
+	int sysctl_icmp_msgs_burst;
 	atomic_t icmp_global_credit;
 	u32 icmp_global_stamp;
 	u32 ip_rt_min_pmtu;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 2e1d81dbdbb6..1ed88883e1f2 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -220,9 +220,6 @@ static inline void icmp_xmit_unlock(struct sock *sk)
 	spin_unlock(&sk->sk_lock.slock);
 }
 
-int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
-int sysctl_icmp_msgs_burst __read_mostly = 50;
-
 /**
  * icmp_global_allow - Are we allowed to send one more ICMP message ?
  * @net: network namespace
@@ -249,14 +246,14 @@ bool icmp_global_allow(struct net *net)
 	if (delta < HZ / 50)
 		return false;
 
-	incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
+	incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec) * delta / HZ;
 	if (!incr)
 		return false;
 
 	if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) {
 		old = atomic_read(&net->ipv4.icmp_global_credit);
 		do {
-			new = min(old + incr, READ_ONCE(sysctl_icmp_msgs_burst));
+			new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst));
 		} while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new));
 	}
 	return true;
@@ -1492,6 +1489,8 @@ static int __net_init icmp_sk_init(struct net *net)
 	net->ipv4.sysctl_icmp_ratelimit = 1 * HZ;
 	net->ipv4.sysctl_icmp_ratemask = 0x1818;
 	net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;
+	net->ipv4.sysctl_icmp_msgs_per_sec = 1000;
+	net->ipv4.sysctl_icmp_msgs_burst = 50;
 
 	return 0;
 }
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4af0c234d8d7..a79b2a52ce01 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -600,22 +600,6 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0444,
 		.proc_handler   = proc_tcp_available_ulp,
 	},
-	{
-		.procname	= "icmp_msgs_per_sec",
-		.data		= &sysctl_icmp_msgs_per_sec,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-	},
-	{
-		.procname	= "icmp_msgs_burst",
-		.data		= &sysctl_icmp_msgs_burst,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-	},
 	{
 		.procname	= "udp_mem",
 		.data		= &sysctl_udp_mem,
@@ -701,6 +685,22 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "icmp_msgs_per_sec",
+		.data		= &init_net.ipv4.sysctl_icmp_msgs_per_sec,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
+	{
+		.procname	= "icmp_msgs_burst",
+		.data		= &init_net.ipv4.sysctl_icmp_msgs_burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+	},
 	{
 		.procname	= "ping_group_range",
 		.data		= &init_net.ipv4.ping_group_range.range,
-- 
cgit v1.3-3-g829e


From 6af91e3d2cfc8bb579b1aa2d22cd91f8c34acdf6 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Thu, 29 Aug 2024 15:57:42 +0000
Subject: Documentation: Add missing fields to net_cachelines

Two fields, page_pools and *irq_moder, were added to struct net_device
in commit 083772c9f972 ("net: page_pool: record pools per netdev") and
commit f750dfe825b9 ("ethtool: provide customized dim profile
management"), respectively.

Add both to the net_cachelines documentation, as well.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20240829155742.366584-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/net_cachelines/net_device.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 70c4fb9d4e5c..a0e0fab8161a 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -176,3 +176,5 @@ netdevice_tracker                   dev_registered_tracker
 struct_rtnl_hw_stats64*             offload_xstats_l3                                               
 struct_devlink_port*                devlink_port                                                    
 struct_dpll_pin*                    dpll_pin                                                        
+struct hlist_head                   page_pools
+struct dim_irq_moder*               irq_moder
-- 
cgit v1.3-3-g829e


From cff69f72d33318f4ccfe7d5ff6c5616d00dd45a7 Mon Sep 17 00:00:00 2001
From: Diogo Jahchan Koike <djahchankoike@gmail.com>
Date: Thu, 29 Aug 2024 15:48:27 -0300
Subject: ethtool: pse-pd: move pse validation into set

Move validation into set, removing .set_validate operation as its current
implementation holds the rtnl lock for acquiring the PHY device, defeating
the intended purpose of checking before grabbing the lock.

Reported-by: syzbot+ec369e6d58e210135f71@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=ec369e6d58e210135f71
Fixes: 31748765bed3 ("net: ethtool: pse-pd: Target the command to the requested PHY")
Signed-off-by: Diogo Jahchan Koike <djahchankoike@gmail.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20240829184830.5861-1-djahchankoike@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/pse-pd.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 507cb21d6bf0..a0705edca22a 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -222,13 +222,10 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = {
 };
 
 static int
-ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info)
+ethnl_set_pse_validate(struct phy_device *phydev, struct genl_info *info)
 {
 	struct nlattr **tb = info->attrs;
-	struct phy_device *phydev;
 
-	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER],
-				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		NL_SET_ERR_MSG(info->extack, "No PHY is attached");
 		return -EOPNOTSUPP;
@@ -254,7 +251,7 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info)
 		return -EOPNOTSUPP;
 	}
 
-	return 1;
+	return 0;
 }
 
 static int
@@ -262,12 +259,13 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 {
 	struct nlattr **tb = info->attrs;
 	struct phy_device *phydev;
-	int ret = 0;
+	int ret;
 
 	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER],
 				      info->extack);
-	if (IS_ERR_OR_NULL(phydev))
-		return -ENODEV;
+	ret = ethnl_set_pse_validate(phydev, info);
+	if (ret)
+		return ret;
 
 	if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) {
 		unsigned int pw_limit;
@@ -314,7 +312,6 @@ const struct ethnl_request_ops ethnl_pse_request_ops = {
 	.fill_reply		= pse_fill_reply,
 	.cleanup_data		= pse_cleanup_data,
 
-	.set_validate		= ethnl_set_pse_validate,
 	.set			= ethnl_set_pse,
 	/* PSE has no notification */
 };
-- 
cgit v1.3-3-g829e


From 0a6ad4d9e1690c7faa3a53f762c877e477093657 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Tue, 6 Aug 2024 16:23:48 +0300
Subject: e1000e: avoid failing the system during pm_suspend

Occasionally when the system goes into pm_suspend, the suspend might fail
due to a PHY access error on the network adapter. Previously, this would
have caused the whole system to fail to go to a low power state.
An example of this was reported in the following Bugzilla:
https://bugzilla.kernel.org/show_bug.cgi?id=205015

[ 1663.694828] e1000e 0000:00:19.0 eth0: Failed to disable ULP
[ 1664.731040] asix 2-3:1.0 eth1: link up, 100Mbps, full-duplex, lpa 0xC1E1
[ 1665.093513] e1000e 0000:00:19.0 eth0: Hardware Error
[ 1665.596760] e1000e 0000:00:19.0: pci_pm_resume+0x0/0x80 returned 0 after 2975399 usecs

and then the system never recovers from it, and all the following suspend failed due to this
[22909.393854] PM: pci_pm_suspend(): e1000e_pm_suspend+0x0/0x760 [e1000e] returns -2
[22909.393858] PM: dpm_run_callback(): pci_pm_suspend+0x0/0x160 returns -2
[22909.393861] PM: Device 0000:00:1f.6 failed to suspend async: error -2

This can be avoided by changing the return values of __e1000_shutdown and
e1000e_pm_suspend functions so that they always return 0 (success). This
is consistent with what other drivers do.

If the e1000e driver encounters a hardware error during suspend, potential
side effects include slightly higher power draw or non-working wake on
LAN. This is preferred to a system-level suspend failure, and a warning
message is written to the system log, so that the user can be aware that
the LAN controller experienced a problem during suspend.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=205015
Suggested-by: Dima Ruinskiy <dima.ruinskiy@intel.com>
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 360ee26557f7..f103249b12fa 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6671,8 +6671,10 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 		if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) {
 			/* enable wakeup by the PHY */
 			retval = e1000_init_phy_wakeup(adapter, wufc);
-			if (retval)
-				return retval;
+			if (retval) {
+				e_err("Failed to enable wakeup\n");
+				goto skip_phy_configurations;
+			}
 		} else {
 			/* enable wakeup by the MAC */
 			ew32(WUFC, wufc);
@@ -6693,8 +6695,10 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 			 * or broadcast.
 			 */
 			retval = e1000_enable_ulp_lpt_lp(hw, !runtime);
-			if (retval)
-				return retval;
+			if (retval) {
+				e_err("Failed to enable ULP\n");
+				goto skip_phy_configurations;
+			}
 		}
 	}
 
@@ -6726,6 +6730,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 		hw->phy.ops.release(hw);
 	}
 
+skip_phy_configurations:
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant.
 	 */
@@ -6968,15 +6973,13 @@ static int e1000e_pm_suspend(struct device *dev)
 	e1000e_pm_freeze(dev);
 
 	rc = __e1000_shutdown(pdev, false);
-	if (rc) {
-		e1000e_pm_thaw(dev);
-	} else {
+	if (!rc) {
 		/* Introduce S0ix implementation */
 		if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS)
 			e1000e_s0ix_entry_flow(adapter);
 	}
 
-	return rc;
+	return 0;
 }
 
 static int e1000e_pm_resume(struct device *dev)
-- 
cgit v1.3-3-g829e


From 0568ee1198f8645864f55671b82e5175b08d8c83 Mon Sep 17 00:00:00 2001
From: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Date: Mon, 19 Aug 2024 11:27:56 +0200
Subject: i40e: Add Energy Efficient Ethernet ability for X710 Base-T/KR/KX
 cards

Add "EEE: Enabled/Disabled" to dmesg for supported X710 Base-T/KR/KX
cards. According to the IEEE standard report the EEE ability and the
EEE Link Partner ability. Use the kernel's 'ethtool_keee' structure
and report EEE link modes.

Example:
dmesg | grep 'NIC Link is'
ethtool --show-eee <device>

Before:
	NIC Link is Up, 10 Gbps Full Duplex, Flow Control: None

        Supported EEE link modes:  Not reported
        Advertised EEE link modes:  Not reported
        Link partner advertised EEE link modes:  Not reported

After:
	NIC Link is Up, 10 Gbps Full Duplex, Flow Control: None, EEE: Enabled

        Supported EEE link modes:  100baseT/Full
                                   1000baseT/Full
                                   10000baseT/Full
        Advertised EEE link modes:  100baseT/Full
                                    1000baseT/Full
                                    10000baseT/Full
        Link partner advertised EEE link modes:  100baseT/Full
                                                 1000baseT/Full
                                                 10000baseT/Full

Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e.h         |  1 +
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 36 +++++++++++++++++++++++---
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 24 ++++++++++++++---
 3 files changed, 54 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d546567e0286..2089a0e172bf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -4,6 +4,7 @@
 #ifndef _I40E_H_
 #define _I40E_H_
 
+#include <linux/linkmode.h>
 #include <linux/pci.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 1d0d2e526adb..3a6bece623f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -5641,6 +5641,26 @@ static int i40e_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
+static void i40e_eee_capability_to_kedata_supported(__le16 eee_capability_,
+						    unsigned long *supported)
+{
+	const int eee_capability = le16_to_cpu(eee_capability_);
+	static const int lut[] = {
+		ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+		ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+		ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+		ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+		ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+		ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+		ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+	};
+
+	linkmode_zero(supported);
+	for (unsigned int i = ARRAY_SIZE(lut); i--; )
+		if (eee_capability & BIT(i + 1))
+			linkmode_set_bit(lut[i], supported);
+}
+
 static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
@@ -5648,7 +5668,7 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
-	int status = 0;
+	int status;
 
 	/* Get initial PHY capabilities */
 	status = i40e_aq_get_phy_capabilities(hw, false, true, &phy_cfg, NULL);
@@ -5661,11 +5681,18 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_keee *edata)
 	if (phy_cfg.eee_capability == 0)
 		return -EOPNOTSUPP;
 
+	i40e_eee_capability_to_kedata_supported(phy_cfg.eee_capability,
+						edata->supported);
+	linkmode_copy(edata->lp_advertised, edata->supported);
+
 	/* Get current configuration */
 	status = i40e_aq_get_phy_capabilities(hw, false, false, &phy_cfg, NULL);
 	if (status)
 		return -EAGAIN;
 
+	linkmode_zero(edata->advertised);
+	if (phy_cfg.eee_capability)
+		linkmode_copy(edata->advertised, edata->supported);
 	edata->eee_enabled = !!phy_cfg.eee_capability;
 	edata->tx_lpi_enabled = pf->stats.tx_lpi_status;
 
@@ -5681,10 +5708,11 @@ static int i40e_is_eee_param_supported(struct net_device *netdev,
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_ethtool_not_used {
-		u32 value;
+		bool value;
 		const char *name;
 	} param[] = {
-		{edata->tx_lpi_timer, "tx-timer"},
+		{!!(edata->advertised[0] & ~edata->supported[0]), "advertise"},
+		{!!edata->tx_lpi_timer, "tx-timer"},
 		{edata->tx_lpi_enabled != pf->stats.tx_lpi_status, "tx-lpi"}
 	};
 	int i;
@@ -5710,7 +5738,7 @@ static int i40e_set_eee(struct net_device *netdev, struct ethtool_keee *edata)
 	struct i40e_pf *pf = vsi->back;
 	struct i40e_hw *hw = &pf->hw;
 	__le16 eee_capability;
-	int status = 0;
+	int status;
 
 	/* Deny parameters we don't support */
 	if (i40e_is_eee_param_supported(netdev, edata))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index cbcfada7b357..03205eb9f925 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7264,6 +7264,26 @@ out:
 }
 #endif /* CONFIG_I40E_DCB */
 
+static void i40e_print_link_message_eee(struct i40e_vsi *vsi,
+					const char *speed, const char *fc)
+{
+	struct ethtool_keee kedata;
+
+	memzero_explicit(&kedata, sizeof(kedata));
+	if (vsi->netdev->ethtool_ops->get_eee)
+		vsi->netdev->ethtool_ops->get_eee(vsi->netdev, &kedata);
+
+	if (!linkmode_empty(kedata.supported))
+		netdev_info(vsi->netdev,
+			    "NIC Link is Up, %sbps Full Duplex, Flow Control: %s, EEE: %s\n",
+			    speed, fc,
+			    kedata.eee_enabled ? "Enabled" : "Disabled");
+	else
+		netdev_info(vsi->netdev,
+			    "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n",
+			    speed, fc);
+}
+
 /**
  * i40e_print_link_message - print link up or down
  * @vsi: the VSI for which link needs a message
@@ -7395,9 +7415,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup)
 			    "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n",
 			    speed, req_fec, fec, an, fc);
 	} else {
-		netdev_info(vsi->netdev,
-			    "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n",
-			    speed, fc);
+		i40e_print_link_message_eee(vsi, speed, fc);
 	}
 
 }
-- 
cgit v1.3-3-g829e


From 7eba264a3c102b6c006aa429f7eb25d2b8533da7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 29 Aug 2024 17:10:49 +0100
Subject: mac802154: Correct spelling in mac802154.h

Correct spelling in mac802154.h.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Message-ID: <20240829-wpan-spell-v1-1-799d840e02c4@kernel.org>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 include/net/mac802154.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 4a3a9de9da73..1b5488fa2ff0 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -140,7 +140,7 @@ enum ieee802154_hw_flags {
  *
  * xmit_sync:
  *	  Handler that 802.15.4 module calls for each transmitted frame.
- *	  skb cntains the buffer starting from the IEEE 802.15.4 header.
+ *	  skb contains the buffer starting from the IEEE 802.15.4 header.
  *	  The low-level driver should send the frame based on available
  *	  configuration. This is called by a workqueue and useful for
  *	  synchronous 802.15.4 drivers.
@@ -152,7 +152,7 @@ enum ieee802154_hw_flags {
  *
  * xmit_async:
  *	  Handler that 802.15.4 module calls for each transmitted frame.
- *	  skb cntains the buffer starting from the IEEE 802.15.4 header.
+ *	  skb contains the buffer starting from the IEEE 802.15.4 header.
  *	  The low-level driver should send the frame based on available
  *	  configuration.
  *	  This function should return zero or negative errno.
-- 
cgit v1.3-3-g829e


From 3682c302e72d71abeb17a81a6d29f281b22928e2 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 29 Aug 2024 17:10:50 +0100
Subject: ieee802154: Correct spelling in nl802154.h

Correct spelling in nl802154.h.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Message-ID: <20240829-wpan-spell-v1-2-799d840e02c4@kernel.org>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 include/net/nl802154.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/nl802154.h b/include/net/nl802154.h
index 4c752f799957..a994dea74596 100644
--- a/include/net/nl802154.h
+++ b/include/net/nl802154.h
@@ -192,7 +192,7 @@ enum nl802154_iftype {
  * @NL802154_CAP_ATTR_TX_POWERS: a nested attribute for
  *	nl802154_wpan_phy_tx_power
  * @NL802154_CAP_ATTR_MIN_CCA_ED_LEVEL: minimum value for cca_ed_level
- * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maxmimum value for cca_ed_level
+ * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maximum value for cca_ed_level
  * @NL802154_CAP_ATTR_CCA_MODES: nl802154_cca_modes flags
  * @NL802154_CAP_ATTR_CCA_OPTS: nl802154_cca_opts flags
  * @NL802154_CAP_ATTR_MIN_MINBE: minimum of minbe value
-- 
cgit v1.3-3-g829e


From ced52c6ed257315c922dc870aafbc64dc8bd746d Mon Sep 17 00:00:00 2001
From: Duy Nguyen <duy.nguyen.rh@renesas.com>
Date: Thu, 1 Aug 2024 16:03:17 +0200
Subject: dt-bindings: can: renesas,rcar-canfd: Document R-Car V4M support

Document support for the CAN-FD Interface on the Renesas R-Car V4M
(R8A779H0) SoC, which supports up to four channels.

The CAN-FD module on R-Car V4M is very similar to the one on R-Car V4H,
but differs in some hardware parameters, as reflected by the Parameter
Status Information part of the Global IP Version Register.  However,
none of this parameterization should have any impact on the driver, as
the driver does not access any register that is impacted by the
parameterization (except for the number of channels).

Signed-off-by: Duy Nguyen <duy.nguyen.rh@renesas.com>
[geert: Clarify R-Car V4M differences]
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/68b5f910bef89508e3455c768844ebe859d6ff1d.1722520779.git.geert+renesas@glider.be
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../bindings/net/can/renesas,rcar-canfd.yaml       | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
index d3f45d29fa0a..7c5ac5d2e880 100644
--- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
+++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
@@ -32,6 +32,7 @@ properties:
           - enum:
               - renesas,r8a779a0-canfd     # R-Car V3U
               - renesas,r8a779g0-canfd     # R-Car V4H
+              - renesas,r8a779h0-canfd     # R-Car V4M
           - const: renesas,rcar-gen4-canfd # R-Car Gen4
 
       - items:
@@ -163,14 +164,23 @@ allOf:
           maxItems: 1
 
   - if:
-      not:
-        properties:
-          compatible:
-            contains:
-              const: renesas,rcar-gen4-canfd
+      properties:
+        compatible:
+          contains:
+            const: renesas,r8a779h0-canfd
     then:
       patternProperties:
-        "^channel[2-7]$": false
+        "^channel[5-7]$": false
+    else:
+      if:
+        not:
+          properties:
+            compatible:
+              contains:
+                const: renesas,rcar-gen4-canfd
+      then:
+        patternProperties:
+          "^channel[2-7]$": false
 
 unevaluatedProperties: false
 
-- 
cgit v1.3-3-g829e


From 09328600c2f930e8814cb9deff630a56788cc8e4 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Wed, 14 Aug 2024 12:44:06 -0400
Subject: dt-bindings: can: convert microchip,mcp251x.txt to yaml

Convert binding doc microchip,mcp251x.txt to yaml.
Additional change:
- add ref to spi-peripheral-props.yaml

Fix below warning:
arch/arm64/boot/dts/freescale/imx8dx-colibri-eval-v3.dtb: /bus@5a000000/spi@5a020000/can@0:
	failed to match any schema with compatible: ['microchip,mcp2515']

Signed-off-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://patch.msgid.link/20240814164407.4022211-1-Frank.Li@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../bindings/net/can/microchip,mcp2510.yaml        | 70 ++++++++++++++++++++++
 .../bindings/net/can/microchip,mcp251x.txt         | 30 ----------
 2 files changed, 70 insertions(+), 30 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
 delete mode 100644 Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt

diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
new file mode 100644
index 000000000000..db446dde6842
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp2510.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/can/microchip,mcp2510.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip MCP251X stand-alone CAN controller
+
+maintainers:
+  - Marc Kleine-Budde <mkl@pengutronix.de>
+
+properties:
+  compatible:
+    enum:
+      - microchip,mcp2510
+      - microchip,mcp2515
+      - microchip,mcp25625
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  vdd-supply:
+    description: Regulator that powers the CAN controller.
+
+  xceiver-supply:
+    description: Regulator that powers the CAN transceiver.
+
+  gpio-controller: true
+
+  "#gpio-cells":
+    const: 2
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+
+allOf:
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        can@1 {
+             compatible = "microchip,mcp2515";
+             reg = <1>;
+             clocks = <&clk24m>;
+             interrupt-parent = <&gpio4>;
+             interrupts = <13 IRQ_TYPE_LEVEL_LOW>;
+             vdd-supply = <&reg5v0>;
+             xceiver-supply = <&reg5v0>;
+             gpio-controller;
+             #gpio-cells = <2>;
+        };
+    };
+
diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
deleted file mode 100644
index 381f8fb3e865..000000000000
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-* Microchip MCP251X stand-alone CAN controller device tree bindings
-
-Required properties:
- - compatible: Should be one of the following:
-   - "microchip,mcp2510" for MCP2510.
-   - "microchip,mcp2515" for MCP2515.
-   - "microchip,mcp25625" for MCP25625.
- - reg: SPI chip select.
- - clocks: The clock feeding the CAN controller.
- - interrupts: Should contain IRQ line for the CAN controller.
-
-Optional properties:
- - vdd-supply: Regulator that powers the CAN controller.
- - xceiver-supply: Regulator that powers the CAN transceiver.
- - gpio-controller: Indicates this device is a GPIO controller.
- - #gpio-cells: Should be two. The first cell is the pin number and
-                the second cell is used to specify the gpio polarity.
-
-Example:
-	can0: can@1 {
-		compatible = "microchip,mcp2515";
-		reg = <1>;
-		clocks = <&clk24m>;
-		interrupt-parent = <&gpio4>;
-		interrupts = <13 IRQ_TYPE_LEVEL_LOW>;
-		vdd-supply = <&reg5v0>;
-		xceiver-supply = <&reg5v0>;
-		gpio-controller;
-		#gpio-cells = <2>;
-	};
-- 
cgit v1.3-3-g829e


From dc2ddcd136fe9b6196a7dd01f75f824beb02d43f Mon Sep 17 00:00:00 2001
From: Zhang Changzhong <zhangchangzhong@huawei.com>
Date: Thu, 29 Aug 2024 20:48:23 +0800
Subject: can: j1939: use correct function name in comment

The function j1939_cancel_all_active_sessions() was renamed to
j1939_cancel_active_session() but name in comment wasn't updated.

Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://patch.msgid.link/1724935703-44621-1-git-send-email-zhangchangzhong@huawei.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/transport.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 4be73de5033c..319f47df3330 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1179,10 +1179,10 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer)
 		break;
 	case -ENETDOWN:
 		/* In this case we should get a netdev_event(), all active
-		 * sessions will be cleared by
-		 * j1939_cancel_all_active_sessions(). So handle this as an
-		 * error, but let j1939_cancel_all_active_sessions() do the
-		 * cleanup including propagation of the error to user space.
+		 * sessions will be cleared by j1939_cancel_active_session().
+		 * So handle this as an error, but let
+		 * j1939_cancel_active_session() do the cleanup including
+		 * propagation of the error to user space.
 		 */
 		break;
 	case -EOVERFLOW:
-- 
cgit v1.3-3-g829e


From 2423cc20087ae9a7b7af575aa62304ef67cad7b6 Mon Sep 17 00:00:00 2001
From: Stefan Mätje <stefan.maetje@esd.eu>
Date: Thu, 8 Aug 2024 18:42:24 +0200
Subject: can: netlink: avoid call to do_set_data_bittiming callback with stale
 can_priv::ctrlmode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch moves the evaluation of data[IFLA_CAN_CTRLMODE] in function
can_changelink in front of the evaluation of data[IFLA_CAN_BITTIMING].

This avoids a call to do_set_data_bittiming providing a stale
can_priv::ctrlmode with a CAN_CTRLMODE_FD flag not matching the
requested state when switching between a CAN Classic and CAN-FD bitrate.

In the same manner the evaluation of data[IFLA_CAN_CTRLMODE] in function
can_validate is also moved in front of the evaluation of
data[IFLA_CAN_BITTIMING].

This is a preparation for patches where the nominal and data bittiming
may have interdependencies on the driver side depending on the
CAN_CTRLMODE_FD flag state.

Signed-off-by: Stefan Mätje <stefan.maetje@esd.eu>
Link: https://patch.msgid.link/20240808164224.213522-1-stefan.maetje@esd.eu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/netlink.c | 102 +++++++++++++++++++++---------------------
 1 file changed, 51 insertions(+), 51 deletions(-)

diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index dfdc039d92a6..01aacdcda260 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -65,15 +65,6 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[],
 	if (!data)
 		return 0;
 
-	if (data[IFLA_CAN_BITTIMING]) {
-		struct can_bittiming bt;
-
-		memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
-		err = can_validate_bittiming(&bt, extack);
-		if (err)
-			return err;
-	}
-
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
 		u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK;
@@ -114,6 +105,15 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
+	if (data[IFLA_CAN_BITTIMING]) {
+		struct can_bittiming bt;
+
+		memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
+		err = can_validate_bittiming(&bt, extack);
+		if (err)
+			return err;
+	}
+
 	if (is_can_fd) {
 		if (!data[IFLA_CAN_BITTIMING] || !data[IFLA_CAN_DATA_BITTIMING])
 			return -EOPNOTSUPP;
@@ -195,48 +195,6 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	/* We need synchronization with dev->stop() */
 	ASSERT_RTNL();
 
-	if (data[IFLA_CAN_BITTIMING]) {
-		struct can_bittiming bt;
-
-		/* Do not allow changing bittiming while running */
-		if (dev->flags & IFF_UP)
-			return -EBUSY;
-
-		/* Calculate bittiming parameters based on
-		 * bittiming_const if set, otherwise pass bitrate
-		 * directly via do_set_bitrate(). Bail out if neither
-		 * is given.
-		 */
-		if (!priv->bittiming_const && !priv->do_set_bittiming &&
-		    !priv->bitrate_const)
-			return -EOPNOTSUPP;
-
-		memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
-		err = can_get_bittiming(dev, &bt,
-					priv->bittiming_const,
-					priv->bitrate_const,
-					priv->bitrate_const_cnt,
-					extack);
-		if (err)
-			return err;
-
-		if (priv->bitrate_max && bt.bitrate > priv->bitrate_max) {
-			NL_SET_ERR_MSG_FMT(extack,
-					   "arbitration bitrate %u bps surpasses transceiver capabilities of %u bps",
-					   bt.bitrate, priv->bitrate_max);
-			return -EINVAL;
-		}
-
-		memcpy(&priv->bittiming, &bt, sizeof(bt));
-
-		if (priv->do_set_bittiming) {
-			/* Finally, set the bit-timing registers */
-			err = priv->do_set_bittiming(dev);
-			if (err)
-				return err;
-		}
-	}
-
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm;
 		u32 ctrlstatic;
@@ -284,6 +242,48 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			priv->ctrlmode &= cm->flags | ~CAN_CTRLMODE_TDC_MASK;
 	}
 
+	if (data[IFLA_CAN_BITTIMING]) {
+		struct can_bittiming bt;
+
+		/* Do not allow changing bittiming while running */
+		if (dev->flags & IFF_UP)
+			return -EBUSY;
+
+		/* Calculate bittiming parameters based on
+		 * bittiming_const if set, otherwise pass bitrate
+		 * directly via do_set_bitrate(). Bail out if neither
+		 * is given.
+		 */
+		if (!priv->bittiming_const && !priv->do_set_bittiming &&
+		    !priv->bitrate_const)
+			return -EOPNOTSUPP;
+
+		memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt));
+		err = can_get_bittiming(dev, &bt,
+					priv->bittiming_const,
+					priv->bitrate_const,
+					priv->bitrate_const_cnt,
+					extack);
+		if (err)
+			return err;
+
+		if (priv->bitrate_max && bt.bitrate > priv->bitrate_max) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "arbitration bitrate %u bps surpasses transceiver capabilities of %u bps",
+					   bt.bitrate, priv->bitrate_max);
+			return -EINVAL;
+		}
+
+		memcpy(&priv->bittiming, &bt, sizeof(bt));
+
+		if (priv->do_set_bittiming) {
+			/* Finally, set the bit-timing registers */
+			err = priv->do_set_bittiming(dev);
+			if (err)
+				return err;
+		}
+	}
+
 	if (data[IFLA_CAN_RESTART_MS]) {
 		/* Do not allow changing restart delay while running */
 		if (dev->flags & IFF_UP)
-- 
cgit v1.3-3-g829e


From a9c0fb33fd454fda5283281e47d556c81ee9fa47 Mon Sep 17 00:00:00 2001
From: Martin Jocic <martin.jocic@kvaser.com>
Date: Thu, 22 Aug 2024 18:38:59 +0200
Subject: can: kvaser_pciefd: Use IS_ENABLED() instead of #ifdef

Use the IS_ENABLED() macro to check kernel config defines instead of
ifdef. Use upper_32_bits() to avoid warnings about "right shift count
>= width of type" on systems with CONFIG_ARCH_DMA_ADDR_T_64BIT not
set. In kvaser_pciefd_write_dma_map_altera() use lower_32_bits() for
symmetry.

Signed-off-by: Martin Jocic <martin.jocic@kvaser.com>
Link: https://patch.msgid.link/20240830141038.1402217-1-mkl@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/kvaser_pciefd.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index a60d9efd5f8d..dc7e5ea1e3ac 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -1053,13 +1053,13 @@ static void kvaser_pciefd_write_dma_map_altera(struct kvaser_pciefd *pcie,
 	void __iomem *serdes_base;
 	u32 word1, word2;
 
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	word1 = addr | KVASER_PCIEFD_ALTERA_DMA_64BIT;
-	word2 = addr >> 32;
-#else
-	word1 = addr;
-	word2 = 0;
-#endif
+	if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)) {
+		word1 = lower_32_bits(addr) | KVASER_PCIEFD_ALTERA_DMA_64BIT;
+		word2 = upper_32_bits(addr);
+	} else {
+		word1 = addr;
+		word2 = 0;
+	}
 	serdes_base = KVASER_PCIEFD_SERDES_ADDR(pcie) + 0x8 * index;
 	iowrite32(word1, serdes_base);
 	iowrite32(word2, serdes_base + 0x4);
@@ -1072,9 +1072,9 @@ static void kvaser_pciefd_write_dma_map_sf2(struct kvaser_pciefd *pcie,
 	u32 lsb = addr & KVASER_PCIEFD_SF2_DMA_LSB_MASK;
 	u32 msb = 0x0;
 
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	msb = addr >> 32;
-#endif
+	if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT))
+		msb = upper_32_bits(addr);
+
 	serdes_base = KVASER_PCIEFD_SERDES_ADDR(pcie) + 0x10 * index;
 	iowrite32(lsb, serdes_base);
 	iowrite32(msb, serdes_base + 0x4);
@@ -1087,9 +1087,9 @@ static void kvaser_pciefd_write_dma_map_xilinx(struct kvaser_pciefd *pcie,
 	u32 lsb = addr & KVASER_PCIEFD_XILINX_DMA_LSB_MASK;
 	u32 msb = 0x0;
 
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	msb = addr >> 32;
-#endif
+	if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT))
+		msb = upper_32_bits(addr);
+
 	serdes_base = KVASER_PCIEFD_SERDES_ADDR(pcie) + 0x8 * index;
 	iowrite32(msb, serdes_base);
 	iowrite32(lsb, serdes_base + 0x4);
-- 
cgit v1.3-3-g829e


From 0315c0b5ed253853a7b07dc97487522345110548 Mon Sep 17 00:00:00 2001
From: Yan Zhen <yanzhen@vivo.com>
Date: Fri, 30 Aug 2024 19:06:51 +0800
Subject: can: kvaser_usb: Simplify with dev_err_probe()

dev_err_probe() is used to log an error message during the probe process
of a device.

It can simplify the error path and unify a message template.

Using this helper is totally fine even if err is known to never
be -EPROBE_DEFER.

The benefit compared to a normal dev_err() is the standardized format
of the error code, it being emitted symbolically and the fact that
the error code is returned which allows more compact error paths.

Signed-off-by: Yan Zhen <yanzhen@vivo.com>
Link: https://patch.msgid.link/20240830110651.519119-1-yanzhen@vivo.com
mkl: fix indention
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 42 +++++++++---------------
 1 file changed, 16 insertions(+), 26 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 35b4132b0639..7d12776ab63e 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -898,10 +898,8 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	ops = driver_info->ops;
 
 	err = ops->dev_setup_endpoints(dev);
-	if (err) {
-		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&intf->dev, err, "Cannot get usb endpoint(s)");
 
 	dev->udev = interface_to_usbdev(intf);
 
@@ -912,26 +910,20 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	dev->card_data.ctrlmode_supported = 0;
 	dev->card_data.capabilities = 0;
 	err = ops->dev_init_card(dev);
-	if (err) {
-		dev_err(&intf->dev,
-			"Failed to initialize card, error %d\n", err);
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&intf->dev, err,
+				     "Failed to initialize card\n");
 
 	err = ops->dev_get_software_info(dev);
-	if (err) {
-		dev_err(&intf->dev,
-			"Cannot get software info, error %d\n", err);
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&intf->dev, err,
+				     "Cannot get software info\n");
 
 	if (ops->dev_get_software_details) {
 		err = ops->dev_get_software_details(dev);
-		if (err) {
-			dev_err(&intf->dev,
-				"Cannot get software details, error %d\n", err);
-			return err;
-		}
+		if (err)
+			return dev_err_probe(&intf->dev, err,
+					     "Cannot get software details\n");
 	}
 
 	if (WARN_ON(!dev->cfg))
@@ -945,18 +937,16 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
 
 	err = ops->dev_get_card_info(dev);
-	if (err) {
-		dev_err(&intf->dev, "Cannot get card info, error %d\n", err);
-		return err;
-	}
+	if (err)
+		return dev_err_probe(&intf->dev, err,
+				     "Cannot get card info\n");
 
 	if (ops->dev_get_capabilities) {
 		err = ops->dev_get_capabilities(dev);
 		if (err) {
-			dev_err(&intf->dev,
-				"Cannot get capabilities, error %d\n", err);
 			kvaser_usb_remove_interfaces(dev);
-			return err;
+			return dev_err_probe(&intf->dev, err,
+					     "Cannot get capabilities\n");
 		}
 	}
 
-- 
cgit v1.3-3-g829e


From 47afa284b96c62bda127604e6091fd5c9fd7e42c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:48 +0300
Subject: ipv4: Unmask upper DSCP bits in RTM_GETROUTE output route lookup

Unmask the upper DSCP bits when looking up an output route via the
RTM_GETROUTE netlink message so that in the future the lookup could be
performed according to the full DSCP value.

No functional changes intended since the upper DSCP bits are masked when
comparing against the TOS selectors in FIB rules and routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f6972b24664a..e4b45aa18470 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3261,7 +3261,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	fl4.daddr = dst;
 	fl4.saddr = src;
-	fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK;
+	fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK;
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
-- 
cgit v1.3-3-g829e


From a63cef46adcbedd4f4ea7401773a310edca53131 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:49 +0300
Subject: ipv4: Unmask upper DSCP bits in ip_route_output_key_hash()

Unmask the upper DSCP bits so that in the future output routes could be
looked up according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e4b45aa18470..5a77dc6d9c72 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2618,7 +2618,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
 	struct rtable *rth;
 
 	fl4->flowi4_iif = LOOPBACK_IFINDEX;
-	fl4->flowi4_tos &= IPTOS_RT_MASK;
+	fl4->flowi4_tos &= INET_DSCP_MASK;
 
 	rcu_read_lock();
 	rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);
-- 
cgit v1.3-3-g829e


From 4805646c42e51d2fbf142864d281473ad453ad5d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:50 +0300
Subject: ipv4: icmp: Unmask upper DSCP bits in icmp_route_lookup()

The function is called to resolve a route for an ICMP message that is
sent in response to a situation. Based on the type of the generated ICMP
message, the function is either passed the DS field of the packet that
generated the ICMP message or a DS field that is derived from it.

Unmask the upper DSCP bits before resolving and output route via
ip_route_output_key_hash() so that in the future the lookup could be
performed according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 1ed88883e1f2..d2463b6e390e 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -93,6 +93,7 @@
 #include <net/ip_fib.h>
 #include <net/l3mdev.h>
 #include <net/addrconf.h>
+#include <net/inet_dscp.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/icmp.h>
 
@@ -497,7 +498,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->saddr = saddr;
 	fl4->flowi4_mark = mark;
 	fl4->flowi4_uid = sock_net_uid(net, NULL);
-	fl4->flowi4_tos = RT_TOS(tos);
+	fl4->flowi4_tos = tos & INET_DSCP_MASK;
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
-- 
cgit v1.3-3-g829e


From ff95cb5e521b60d046e6571ada697a0977b189c3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:51 +0300
Subject: ipv4: Unmask upper DSCP bits in ip_sock_rt_tos()

The function is used to read the DS field that was stored in IPv4
sockets via the IP_TOS socket option so that it could be used to
initialize the flowi4_tos field before resolving an output route.

Unmask the upper DSCP bits so that in the future the output route lookup
could be performed according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/route.h b/include/net/route.h
index 93833cfe9c96..b896f086ec8e 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -27,6 +27,7 @@
 #include <net/ip_fib.h>
 #include <net/arp.h>
 #include <net/ndisc.h>
+#include <net/inet_dscp.h>
 #include <linux/in_route.h>
 #include <linux/rtnetlink.h>
 #include <linux/rcupdate.h>
@@ -45,7 +46,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk)
 
 static inline __u8 ip_sock_rt_tos(const struct sock *sk)
 {
-	return RT_TOS(READ_ONCE(inet_sk(sk)->tos));
+	return READ_ONCE(inet_sk(sk)->tos) & INET_DSCP_MASK;
 }
 
 struct ip_tunnel_info;
-- 
cgit v1.3-3-g829e


From 356d054a4967e6190ee558b8e839fad3e9db35ec Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:52 +0300
Subject: ipv4: Unmask upper DSCP bits in get_rttos()

The function is used by a few socket types to retrieve the TOS value
with which to perform the FIB lookup for packets sent through the socket
(flowi4_tos). If a DS field was passed using the IP_TOS control message,
then it is used. Otherwise the one specified via the IP_TOS socket
option.

Unmask the upper DSCP bits so that in the future the lookup could be
performed according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 1ee472fa8b37..d92d3bc3ec0e 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,7 @@
 #include <net/flow_dissector.h>
 #include <net/netns/hash.h>
 #include <net/lwtunnel.h>
+#include <net/inet_dscp.h>
 
 #define IPV4_MAX_PMTU		65535U		/* RFC 2675, Section 5.1 */
 #define IPV4_MIN_MTU		68			/* RFC 791 */
@@ -258,7 +259,9 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
 
 static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
 {
-	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos));
+	u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos);
+
+	return dsfield & INET_DSCP_MASK;
 }
 
 /* datagram.c */
-- 
cgit v1.3-3-g829e


From f6c89e95555ace0cb10d01b07756bfa5db5ee7fa Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:53 +0300
Subject: ipv4: Unmask upper DSCP bits when building flow key

build_sk_flow_key() and __build_flow_key() are used to build an IPv4
flow key before calling one of the FIB lookup APIs.

Unmask the upper DSCP bits so that in the future the lookup could be
performed according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5a77dc6d9c72..723ac9181558 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -512,7 +512,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
 						    sk->sk_protocol;
 	}
 
-	flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope,
+	flowi4_init_output(fl4, oif, mark, tos & INET_DSCP_MASK, scope,
 			   prot, flow_flags, iph->daddr, iph->saddr, 0, 0,
 			   sock_net_uid(net, sk));
 }
@@ -541,7 +541,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
 	if (inet_opt && inet_opt->opt.srr)
 		daddr = inet_opt->opt.faddr;
 	flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
-			   ip_sock_rt_tos(sk) & IPTOS_RT_MASK,
+			   ip_sock_rt_tos(sk),
 			   ip_sock_rt_scope(sk),
 			   inet_test_bit(HDRINCL, sk) ?
 				IPPROTO_RAW : sk->sk_protocol,
-- 
cgit v1.3-3-g829e


From b261b2c6c18bcb81d69de011fd991bdfb97259f7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:54 +0300
Subject: xfrm: Unmask upper DSCP bits in xfrm_get_tos()

The function returns a value that is used to initialize 'flowi4_tos'
before being passed to the FIB lookup API in the following call chain:

xfrm_bundle_create()
	tos = xfrm_get_tos(fl, family)
	xfrm_dst_lookup(..., tos, ...)
		__xfrm_dst_lookup(..., tos, ...)
			xfrm4_dst_lookup(..., tos, ...)
				__xfrm4_dst_lookup(..., tos, ...)
					fl4->flowi4_tos = tos
					__ip_route_output_key(net, fl4)

Unmask the upper DSCP bits so that in the future the output route lookup
could be performed according to the full DSCP value.

Remove IPTOS_RT_MASK since it is no longer used.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h    | 2 --
 net/xfrm/xfrm_policy.c | 3 ++-
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index b896f086ec8e..1789f1e6640b 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -266,8 +266,6 @@ static inline void ip_rt_put(struct rtable *rt)
 	dst_release(&rt->dst);
 }
 
-#define IPTOS_RT_MASK	(IPTOS_TOS_MASK & ~3)
-
 extern const __u8 ip_tos2prio[16];
 
 static inline char rt_tos2priority(u8 tos)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index c56c61b0c12e..b22767c0c078 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -45,6 +45,7 @@
 #ifdef CONFIG_XFRM_ESPINTCP
 #include <net/espintcp.h>
 #endif
+#include <net/inet_dscp.h>
 
 #include "xfrm_hash.h"
 
@@ -2561,7 +2562,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
 static int xfrm_get_tos(const struct flowi *fl, int family)
 {
 	if (family == AF_INET)
-		return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos;
+		return fl->u.ip4.flowi4_tos & INET_DSCP_MASK;
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 13f6538de2b845650e68996621489de547b0337e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:55 +0300
Subject: ipv4: Unmask upper DSCP bits in ip_send_unicast_reply()

The function calls flowi4_init_output() to initialize an IPv4 flow key
with which it then performs a FIB lookup using ip_route_output_flow().

'arg->tos' with which the TOS value in the IPv4 flow key (flowi4_tos) is
initialized contains the full DS field. Unmask the upper DSCP bits so
that in the future the FIB lookup could be performed according to the
full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b90d0f78ac80..eea443b7f65e 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -77,6 +77,7 @@
 #include <net/inetpeer.h>
 #include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
+#include <net/inet_dscp.h>
 #include <linux/bpf-cgroup.h>
 #include <linux/igmp.h>
 #include <linux/netfilter_ipv4.h>
@@ -1621,7 +1622,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 
 	flowi4_init_output(&fl4, oif,
 			   IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark,
-			   RT_TOS(arg->tos),
+			   arg->tos & INET_DSCP_MASK,
 			   RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
 			   ip_reply_arg_flowi_flags(arg),
 			   daddr, saddr,
-- 
cgit v1.3-3-g829e


From 6a59526628ad6dadf389f45ddb3f75db44930897 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:56 +0300
Subject: ipv6: sit: Unmask upper DSCP bits in ipip6_tunnel_xmit()

The function calls flowi4_init_output() to initialize an IPv4 flow key
with which it then performs a FIB lookup using ip_route_output_flow().

The 'tos' variable with which the TOS value in the IPv4 flow key
(flowi4_tos) is initialized contains the full DS field. Unmask the upper
DSCP bits so that in the future the FIB lookup could be performed
according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/sit.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 83b195f09561..3b2eed7fc765 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -51,6 +51,7 @@
 #include <net/dsfield.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/inet_dscp.h>
 
 /*
    This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c
@@ -935,8 +936,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark,
-			   RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6,
-			   0, dst, tiph->saddr, 0, 0,
+			   tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE,
+			   IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0,
 			   sock_net_uid(tunnel->net, NULL));
 
 	rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr);
-- 
cgit v1.3-3-g829e


From 939cd1abf080c629552a9c5e6db4c0509d13e4c7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:57 +0300
Subject: ipvlan: Unmask upper DSCP bits in ipvlan_process_v4_outbound()

Unmask the upper DSCP bits when calling ip_route_output_flow() so that
in the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ipvlan/ipvlan_core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index fef4eff7753a..b1afcb8740de 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -2,6 +2,8 @@
 /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com>
  */
 
+#include <net/inet_dscp.h>
+
 #include "ipvlan.h"
 
 static u32 ipvlan_jhash_secret __read_mostly;
@@ -420,7 +422,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 	int err, ret = NET_XMIT_DROP;
 	struct flowi4 fl4 = {
 		.flowi4_oif = dev->ifindex,
-		.flowi4_tos = RT_TOS(ip4h->tos),
+		.flowi4_tos = ip4h->tos & INET_DSCP_MASK,
 		.flowi4_flags = FLOWI_FLAG_ANYSRC,
 		.flowi4_mark = skb->mark,
 		.daddr = ip4h->daddr,
-- 
cgit v1.3-3-g829e


From c5d8ffe29cf2873b62e4bc008ca48d045b6cde88 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:58 +0300
Subject: vrf: Unmask upper DSCP bits in vrf_process_v4_outbound()

Unmask the upper DSCP bits when calling ip_route_output_flow() so that
in the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vrf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 040f0bb36c0e..a900908eb24a 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -37,6 +37,7 @@
 #include <net/sch_generic.h>
 #include <net/netns/generic.h>
 #include <net/netfilter/nf_conntrack.h>
+#include <net/inet_dscp.h>
 
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.1"
@@ -520,7 +521,7 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
 	/* needed to match OIF rule */
 	fl4.flowi4_l3mdev = vrf_dev->ifindex;
 	fl4.flowi4_iif = LOOPBACK_IFINDEX;
-	fl4.flowi4_tos = RT_TOS(ip4h->tos);
+	fl4.flowi4_tos = ip4h->tos & INET_DSCP_MASK;
 	fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 	fl4.flowi4_proto = ip4h->protocol;
 	fl4.daddr = ip4h->daddr;
-- 
cgit v1.3-3-g829e


From 50033400fc3a4744ea3ef6b7ec6443c5ec15a797 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 29 Aug 2024 09:54:59 +0300
Subject: bpf: Unmask upper DSCP bits in __bpf_redirect_neigh_v4()

Unmask the upper DSCP bits when calling ip_route_output_flow() so that
in the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index f09d875cc053..8569cd2482ee 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2372,7 +2372,7 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
 		struct flowi4 fl4 = {
 			.flowi4_flags = FLOWI_FLAG_ANYSRC,
 			.flowi4_mark  = skb->mark,
-			.flowi4_tos   = RT_TOS(ip4h->tos),
+			.flowi4_tos   = ip4h->tos & INET_DSCP_MASK,
 			.flowi4_oif   = dev->ifindex,
 			.flowi4_proto = ip4h->protocol,
 			.daddr	      = ip4h->daddr,
-- 
cgit v1.3-3-g829e


From 4ebe78e15b95e8baaf7c3686694b59319b215f38 Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Thu, 29 Aug 2024 13:39:33 +0530
Subject: octeontx2-af: use dynamic interrupt vectors for CN10K

This patch updates the driver to use a dynamic number of vectors instead
of a hard-coded value. This change accommodates the CN10KB, which has 2
vectors, unlike the previously supported chips that have 3 vectors.

Signed-off-by: Srujana Challa <schalla@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/mbox.h   |  5 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_cpt.c    | 89 ++++++++++++++++++----
 .../net/ethernet/marvell/octeontx2/af/rvu_struct.h |  6 +-
 3 files changed, 80 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index ed2160cc5acb..6ea2f3071fe8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -1856,8 +1856,9 @@ struct cpt_flt_eng_info_req {
 
 struct cpt_flt_eng_info_rsp {
 	struct mbox_msghdr hdr;
-	u64 flt_eng_map[CPT_10K_AF_INT_VEC_RVU];
-	u64 rcvrd_eng_map[CPT_10K_AF_INT_VEC_RVU];
+#define CPT_AF_MAX_FLT_INT_VECS 3
+	u64 flt_eng_map[CPT_AF_MAX_FLT_INT_VECS];
+	u64 rcvrd_eng_map[CPT_AF_MAX_FLT_INT_VECS];
 	u64 rsvd;
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index daf4b951e905..cd5b21cb0427 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -19,6 +19,9 @@
 /* Length of initial context fetch in 128 byte words */
 #define CPT_CTX_ILEN    1ULL
 
+/* Interrupt vector count of CPT RVU and RAS interrupts */
+#define CPT_10K_AF_RVU_RAS_INT_VEC_CNT  2
+
 #define cpt_get_eng_sts(e_min, e_max, rsp, etype)                   \
 ({                                                                  \
 	u64 free_sts = 0, busy_sts = 0;                             \
@@ -37,6 +40,41 @@
 	(_rsp)->free_sts_##etype = free_sts;                        \
 })
 
+#define MAX_AE  GENMASK_ULL(47, 32)
+#define MAX_IE  GENMASK_ULL(31, 16)
+#define MAX_SE  GENMASK_ULL(15, 0)
+
+static u16 cpt_max_engines_get(struct rvu *rvu)
+{
+	u16 max_ses, max_ies, max_aes;
+	u64 reg;
+
+	reg = rvu_read64(rvu, BLKADDR_CPT0, CPT_AF_CONSTANTS1);
+	max_ses = FIELD_GET(MAX_SE, reg);
+	max_ies = FIELD_GET(MAX_IE, reg);
+	max_aes = FIELD_GET(MAX_AE, reg);
+
+	return max_ses + max_ies + max_aes;
+}
+
+/* Number of flt interrupt vectors are depends on number of engines that the
+ * chip has. Each flt vector represents 64 engines.
+ */
+static int cpt_10k_flt_nvecs_get(struct rvu *rvu, u16 max_engs)
+{
+	int flt_vecs;
+
+	flt_vecs = DIV_ROUND_UP(max_engs, 64);
+
+	if (flt_vecs > CPT_10K_AF_INT_VEC_FLT_MAX) {
+		dev_warn_once(rvu->dev, "flt_vecs:%d exceeds the max vectors:%d\n",
+			      flt_vecs, CPT_10K_AF_INT_VEC_FLT_MAX);
+		flt_vecs = CPT_10K_AF_INT_VEC_FLT_MAX;
+	}
+
+	return flt_vecs;
+}
+
 static irqreturn_t cpt_af_flt_intr_handler(int vec, void *ptr)
 {
 	struct rvu_block *block = ptr;
@@ -150,17 +188,26 @@ static void cpt_10k_unregister_interrupts(struct rvu_block *block, int off)
 {
 	struct rvu *rvu = block->rvu;
 	int blkaddr = block->addr;
-	int i;
+	int i, flt_vecs;
+	u16 max_engs;
+	u8 nr;
+
+	max_engs = cpt_max_engines_get(rvu);
+	flt_vecs = cpt_10k_flt_nvecs_get(rvu, max_engs);
 
 	/* Disable all CPT AF interrupts */
-	rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(0), ~0ULL);
-	rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(1), ~0ULL);
-	rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(2), 0xFFFF);
+	for (i = CPT_10K_AF_INT_VEC_FLT0; i < flt_vecs; i++) {
+		nr = (max_engs > 64) ? 64 : max_engs;
+		max_engs -= nr;
+		rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1C(i),
+			    INTR_MASK(nr));
+	}
 
 	rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1C, 0x1);
 	rvu_write64(rvu, blkaddr, CPT_AF_RAS_INT_ENA_W1C, 0x1);
 
-	for (i = 0; i < CPT_10K_AF_INT_VEC_CNT; i++)
+	/* CPT AF interrupt vectors are flt_int, rvu_int and ras_int. */
+	for (i = 0; i < flt_vecs + CPT_10K_AF_RVU_RAS_INT_VEC_CNT; i++)
 		if (rvu->irq_allocated[off + i]) {
 			free_irq(pci_irq_vector(rvu->pdev, off + i), block);
 			rvu->irq_allocated[off + i] = false;
@@ -206,12 +253,18 @@ void rvu_cpt_unregister_interrupts(struct rvu *rvu)
 
 static int cpt_10k_register_interrupts(struct rvu_block *block, int off)
 {
+	int rvu_intr_vec, ras_intr_vec;
 	struct rvu *rvu = block->rvu;
 	int blkaddr = block->addr;
 	irq_handler_t flt_fn;
-	int i, ret;
+	int i, ret, flt_vecs;
+	u16 max_engs;
+	u8 nr;
+
+	max_engs = cpt_max_engines_get(rvu);
+	flt_vecs = cpt_10k_flt_nvecs_get(rvu, max_engs);
 
-	for (i = CPT_10K_AF_INT_VEC_FLT0; i < CPT_10K_AF_INT_VEC_RVU; i++) {
+	for (i = CPT_10K_AF_INT_VEC_FLT0; i < flt_vecs; i++) {
 		sprintf(&rvu->irq_name[(off + i) * NAME_SIZE], "CPTAF FLT%d", i);
 
 		switch (i) {
@@ -229,20 +282,24 @@ static int cpt_10k_register_interrupts(struct rvu_block *block, int off)
 						    flt_fn, &rvu->irq_name[(off + i) * NAME_SIZE]);
 		if (ret)
 			goto err;
-		if (i == CPT_10K_AF_INT_VEC_FLT2)
-			rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), 0xFFFF);
-		else
-			rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i), ~0ULL);
+
+		nr = (max_engs > 64) ? 64 : max_engs;
+		max_engs -= nr;
+		rvu_write64(rvu, blkaddr, CPT_AF_FLTX_INT_ENA_W1S(i),
+			    INTR_MASK(nr));
 	}
 
-	ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RVU,
+	rvu_intr_vec = flt_vecs;
+	ras_intr_vec = rvu_intr_vec + 1;
+
+	ret = rvu_cpt_do_register_interrupt(block, off + rvu_intr_vec,
 					    rvu_cpt_af_rvu_intr_handler,
 					    "CPTAF RVU");
 	if (ret)
 		goto err;
 	rvu_write64(rvu, blkaddr, CPT_AF_RVU_INT_ENA_W1S, 0x1);
 
-	ret = rvu_cpt_do_register_interrupt(block, off + CPT_10K_AF_INT_VEC_RAS,
+	ret = rvu_cpt_do_register_interrupt(block, off + ras_intr_vec,
 					    rvu_cpt_af_ras_intr_handler,
 					    "CPTAF RAS");
 	if (ret)
@@ -921,13 +978,17 @@ int rvu_mbox_handler_cpt_flt_eng_info(struct rvu *rvu, struct cpt_flt_eng_info_r
 	struct rvu_block *block;
 	unsigned long flags;
 	int blkaddr, vec;
+	int flt_vecs;
+	u16 max_engs;
 
 	blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr);
 	if (blkaddr < 0)
 		return blkaddr;
 
 	block = &rvu->hw->block[blkaddr];
-	for (vec = 0; vec < CPT_10K_AF_INT_VEC_RVU; vec++) {
+	max_engs = cpt_max_engines_get(rvu);
+	flt_vecs = cpt_10k_flt_nvecs_get(rvu, max_engs);
+	for (vec = 0; vec < flt_vecs; vec++) {
 		spin_lock_irqsave(&rvu->cpt_intr_lock, flags);
 		rsp->flt_eng_map[vec] = block->cpt_flt_eng_map[vec];
 		rsp->rcvrd_eng_map[vec] = block->cpt_rcvrd_eng_map[vec];
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
index 5ef406c7e8a4..fc8da2090657 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h
@@ -71,13 +71,11 @@ enum cpt_af_int_vec_e {
 	CPT_AF_INT_VEC_CNT	= 0x4,
 };
 
-enum cpt_10k_af_int_vec_e {
+enum cpt_cn10k_flt_int_vec_e {
 	CPT_10K_AF_INT_VEC_FLT0	= 0x0,
 	CPT_10K_AF_INT_VEC_FLT1	= 0x1,
 	CPT_10K_AF_INT_VEC_FLT2	= 0x2,
-	CPT_10K_AF_INT_VEC_RVU	= 0x3,
-	CPT_10K_AF_INT_VEC_RAS	= 0x4,
-	CPT_10K_AF_INT_VEC_CNT	= 0x5,
+	CPT_10K_AF_INT_VEC_FLT_MAX = 0x3,
 };
 
 /* NPA Admin function Interrupt Vector Enumeration */
-- 
cgit v1.3-3-g829e


From 1652623291c50a9ec4db3c416b7d01701b4012ff Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Thu, 29 Aug 2024 13:39:34 +0530
Subject: octeontx2-af: avoid RXC register access for CN10KB

This patch modifies the driver to prevent access to RXC hardware
registers on the CN10KB, as RXC is not available on this chip.

Signed-off-by: Srujana Challa <schalla@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h     | 10 ++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c | 17 ++++++++++++++---
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 03ee93fd9e94..64c9c9ee000d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -400,6 +400,7 @@ struct hw_cap {
 	bool	nix_multiple_dwrr_mtu;   /* Multiple DWRR_MTU to choose from */
 	bool	npc_hash_extract; /* Hash extract enabled ? */
 	bool	npc_exact_match_enabled; /* Exact match supported ? */
+	bool    cpt_rxc;   /* Is CPT-RXC supported */
 };
 
 struct rvu_hwinfo {
@@ -690,6 +691,15 @@ static inline bool is_cnf10ka_a0(struct rvu *rvu)
 	return false;
 }
 
+static inline bool is_cn10kb(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	if (pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_B)
+		return true;
+	return false;
+}
+
 static inline bool is_rvu_npc_hash_extract_en(struct rvu *rvu)
 {
 	u64 npc_const3;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index cd5b21cb0427..d44614a63a7b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -789,6 +789,8 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
 
 static void get_ctx_pc(struct rvu *rvu, struct cpt_sts_rsp *rsp, int blkaddr)
 {
+	struct rvu_hwinfo *hw = rvu->hw;
+
 	if (is_rvu_otx2(rvu))
 		return;
 
@@ -812,14 +814,16 @@ static void get_ctx_pc(struct rvu *rvu, struct cpt_sts_rsp *rsp, int blkaddr)
 	rsp->ctx_err = rvu_read64(rvu, blkaddr, CPT_AF_CTX_ERR);
 	rsp->ctx_enc_id = rvu_read64(rvu, blkaddr, CPT_AF_CTX_ENC_ID);
 	rsp->ctx_flush_timer = rvu_read64(rvu, blkaddr, CPT_AF_CTX_FLUSH_TIMER);
+	rsp->x2p_link_cfg0 = rvu_read64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(0));
+	rsp->x2p_link_cfg1 = rvu_read64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(1));
 
+	if (!hw->cap.cpt_rxc)
+		return;
 	rsp->rxc_time = rvu_read64(rvu, blkaddr, CPT_AF_RXC_TIME);
 	rsp->rxc_time_cfg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_TIME_CFG);
 	rsp->rxc_active_sts = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ACTIVE_STS);
 	rsp->rxc_zombie_sts = rvu_read64(rvu, blkaddr, CPT_AF_RXC_ZOMBIE_STS);
 	rsp->rxc_dfrg = rvu_read64(rvu, blkaddr, CPT_AF_RXC_DFRG);
-	rsp->x2p_link_cfg0 = rvu_read64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(0));
-	rsp->x2p_link_cfg1 = rvu_read64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(1));
 }
 
 static void get_eng_sts(struct rvu *rvu, struct cpt_sts_rsp *rsp, int blkaddr)
@@ -1004,10 +1008,11 @@ int rvu_mbox_handler_cpt_flt_eng_info(struct rvu *rvu, struct cpt_flt_eng_info_r
 static void cpt_rxc_teardown(struct rvu *rvu, int blkaddr)
 {
 	struct cpt_rxc_time_cfg_req req, prev;
+	struct rvu_hwinfo *hw = rvu->hw;
 	int timeout = 2000;
 	u64 reg;
 
-	if (is_rvu_otx2(rvu))
+	if (!hw->cap.cpt_rxc)
 		return;
 
 	/* Set time limit to minimum values, so that rxc entries will be
@@ -1282,8 +1287,14 @@ unlock:
 
 int rvu_cpt_init(struct rvu *rvu)
 {
+	struct rvu_hwinfo *hw = rvu->hw;
+
 	/* Retrieve CPT PF number */
 	rvu->cpt_pf_num = get_cpt_pf_num(rvu);
+	if (is_block_implemented(rvu->hw, BLKADDR_CPT0) && !is_rvu_otx2(rvu) &&
+	    !is_cn10kb(rvu))
+		hw->cap.cpt_rxc = true;
+
 	spin_lock_init(&rvu->cpt_intr_lock);
 
 	return 0;
-- 
cgit v1.3-3-g829e


From 5da8de8cb3e3b01fd838536c75a36b667eca128b Mon Sep 17 00:00:00 2001
From: Srujana Challa <schalla@marvell.com>
Date: Thu, 29 Aug 2024 13:39:35 +0530
Subject: octeontx2-af: configure default CPT credits for CN10KA B0

The maximum CPT credits that RXC can use are now configurable on CN10KA B0
through a hardware CSR. This patch sets the default value to optimize peak
performance, aligning it with other chip versions.

Signed-off-by: Srujana Challa <schalla@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h     | 20 ++++++++++++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c | 18 ++++++++++++++++++
 drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h |  1 +
 3 files changed, 39 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 64c9c9ee000d..43b1d83686d1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -691,6 +691,26 @@ static inline bool is_cnf10ka_a0(struct rvu *rvu)
 	return false;
 }
 
+static inline bool is_cn10ka_a0(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	if (pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A &&
+	    (pdev->revision & 0x0F) == 0x0)
+		return true;
+	return false;
+}
+
+static inline bool is_cn10ka_a1(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	if (pdev->subsystem_device == PCI_SUBSYS_DEVID_CN10K_A &&
+	    (pdev->revision & 0x0F) == 0x1)
+		return true;
+	return false;
+}
+
 static inline bool is_cn10kb(struct rvu *rvu)
 {
 	struct pci_dev *pdev = rvu->pdev;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index d44614a63a7b..3c5bbaf12e59 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -22,6 +22,9 @@
 /* Interrupt vector count of CPT RVU and RAS interrupts */
 #define CPT_10K_AF_RVU_RAS_INT_VEC_CNT  2
 
+/* Default CPT_AF_RXC_CFG1:max_rxc_icb_cnt */
+#define CPT_DFLT_MAX_RXC_ICB_CNT  0xC0ULL
+
 #define cpt_get_eng_sts(e_min, e_max, rsp, etype)                   \
 ({                                                                  \
 	u64 free_sts = 0, busy_sts = 0;                             \
@@ -737,6 +740,7 @@ static bool validate_and_update_reg_offset(struct rvu *rvu,
 		case CPT_AF_BLK_RST:
 		case CPT_AF_CONSTANTS1:
 		case CPT_AF_CTX_FLUSH_TIMER:
+		case CPT_AF_RXC_CFG1:
 			return true;
 		}
 
@@ -1285,9 +1289,12 @@ unlock:
 	return 0;
 }
 
+#define MAX_RXC_ICB_CNT  GENMASK_ULL(40, 32)
+
 int rvu_cpt_init(struct rvu *rvu)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
+	u64 reg_val;
 
 	/* Retrieve CPT PF number */
 	rvu->cpt_pf_num = get_cpt_pf_num(rvu);
@@ -1295,6 +1302,17 @@ int rvu_cpt_init(struct rvu *rvu)
 	    !is_cn10kb(rvu))
 		hw->cap.cpt_rxc = true;
 
+	if (hw->cap.cpt_rxc && !is_cn10ka_a0(rvu) && !is_cn10ka_a1(rvu)) {
+		/* Set CPT_AF_RXC_CFG1:max_rxc_icb_cnt to 0xc0 to not effect
+		 * inline inbound peak performance
+		 */
+		reg_val = rvu_read64(rvu, BLKADDR_CPT0, CPT_AF_RXC_CFG1);
+		reg_val &= ~MAX_RXC_ICB_CNT;
+		reg_val |= FIELD_PREP(MAX_RXC_ICB_CNT,
+				      CPT_DFLT_MAX_RXC_ICB_CNT);
+		rvu_write64(rvu, BLKADDR_CPT0, CPT_AF_RXC_CFG1, reg_val);
+	}
+
 	spin_lock_init(&rvu->cpt_intr_lock);
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
index d56be5fb7eb4..2b299fa85159 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h
@@ -545,6 +545,7 @@
 #define CPT_AF_CTX_PSH_PC               (0x49450ull)
 #define CPT_AF_CTX_PSH_LATENCY_PC       (0x49458ull)
 #define CPT_AF_CTX_CAM_DATA(a)          (0x49800ull | (u64)(a) << 3)
+#define CPT_AF_RXC_CFG1                 (0x50000ull)
 #define CPT_AF_RXC_TIME                 (0x50010ull)
 #define CPT_AF_RXC_TIME_CFG             (0x50018ull)
 #define CPT_AF_RXC_DFRG                 (0x50020ull)
-- 
cgit v1.3-3-g829e


From faa2e484b393c56bc1243dca6676a70bc485f775 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Wed, 21 Aug 2024 16:11:03 +0300
Subject: wifi: rtw88: Fix USB/SDIO devices not transmitting beacons

All USB devices supported by rtw88 have the same problem: they don't
transmit beacons in AP mode. (Some?) SDIO devices are also affected.
The cause appears to be clearing BIT_EN_BCNQ_DL of REG_FWHW_TXQ_CTRL
before uploading the beacon reserved page, so don't clear the bit for
USB and SDIO devices.

Tested with RTL8811CU and RTL8723DU.

Cc: <stable@vger.kernel.org> # 6.6.x
Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/49de73b5-698f-4865-ab63-100e28dfc4a1@gmail.com
---
 drivers/net/wireless/realtek/rtw88/fw.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index ab7d414d0ba6..b9b0114e253b 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -1468,10 +1468,12 @@ int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr,
 	val |= BIT_ENSWBCN >> 8;
 	rtw_write8(rtwdev, REG_CR + 1, val);
 
-	val = rtw_read8(rtwdev, REG_FWHW_TXQ_CTRL + 2);
-	bckp[1] = val;
-	val &= ~(BIT_EN_BCNQ_DL >> 16);
-	rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, val);
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE) {
+		val = rtw_read8(rtwdev, REG_FWHW_TXQ_CTRL + 2);
+		bckp[1] = val;
+		val &= ~(BIT_EN_BCNQ_DL >> 16);
+		rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, val);
+	}
 
 	ret = rtw_hci_write_data_rsvd_page(rtwdev, buf, size);
 	if (ret) {
@@ -1496,7 +1498,8 @@ restore:
 	rsvd_pg_head = rtwdev->fifo.rsvd_boundary;
 	rtw_write16(rtwdev, REG_FIFOPAGE_CTRL_2,
 		    rsvd_pg_head | BIT_BCN_VALID_V1);
-	rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, bckp[1]);
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE)
+		rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, bckp[1]);
 	rtw_write8(rtwdev, REG_CR + 1, bckp[0]);
 
 	return ret;
-- 
cgit v1.3-3-g829e


From 902cb7b11f9a7ff07233cc4c626b54c3e4703149 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 19 Aug 2024 10:52:48 +0800
Subject: wifi: rtw88: assign mac_id for vif/sta and update to TX desc

A mac_id as an instance in firmware has to be assigned for each station
including AP and connected stations. Firmware will use the mac_id to
control TX rate and do statistics.

Assignment rule is to assign mac_id to each vif when adding vif.
For station mode, sta->mac_id will reuse vif->mac_id. For AP mode,
dynamically allocate an sta->mac_id to a station, and vif->mac_id is
used to send broadcast/multicast packets which are not belong to
a station. For example,

                  vif->mac_id      sta->mac_id
vif0 (STA mode)        0               0
vif1 (AP mode)         1               2...

By the way, remove unused RTW_BC_MC_MACID, which was planed to send
broadcast/multicast packets on fixed mac_id.

Tested-on RTL8822CE with STA + AP SCC mode.

Link: https://lore.kernel.org/linux-wireless/e4be0a75-43b2-4ae5-9aab-5c4a88e78097@gmail.com/
Cc: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240819025248.17939-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw88/mac80211.c | 13 ++++++++++--
 drivers/net/wireless/realtek/rtw88/main.c     | 30 +++++++++++----------------
 drivers/net/wireless/realtek/rtw88/main.h     | 14 +++++++++++--
 drivers/net/wireless/realtek/rtw88/tx.c       | 11 +++++++---
 drivers/net/wireless/realtek/rtw88/tx.h       |  1 +
 5 files changed, 44 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c
index 63326b352738..b39e90fb66b4 100644
--- a/drivers/net/wireless/realtek/rtw88/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw88/mac80211.c
@@ -167,6 +167,12 @@ static int rtw_ops_add_interface(struct ieee80211_hw *hw,
 
 	mutex_lock(&rtwdev->mutex);
 
+	rtwvif->mac_id = rtw_acquire_macid(rtwdev);
+	if (rtwvif->mac_id >= RTW_MAX_MAC_ID_NUM) {
+		mutex_unlock(&rtwdev->mutex);
+		return -ENOSPC;
+	}
+
 	port = find_first_zero_bit(rtwdev->hw_port, RTW_PORT_NUM);
 	if (port >= RTW_PORT_NUM) {
 		mutex_unlock(&rtwdev->mutex);
@@ -214,7 +220,8 @@ static int rtw_ops_add_interface(struct ieee80211_hw *hw,
 
 	mutex_unlock(&rtwdev->mutex);
 
-	rtw_dbg(rtwdev, RTW_DBG_STATE, "start vif %pM on port %d\n", vif->addr, rtwvif->port);
+	rtw_dbg(rtwdev, RTW_DBG_STATE, "start vif %pM mac_id %d on port %d\n",
+		vif->addr, rtwvif->mac_id, rtwvif->port);
 	return 0;
 }
 
@@ -225,7 +232,8 @@ static void rtw_ops_remove_interface(struct ieee80211_hw *hw,
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
 	u32 config = 0;
 
-	rtw_dbg(rtwdev, RTW_DBG_STATE, "stop vif %pM on port %d\n", vif->addr, rtwvif->port);
+	rtw_dbg(rtwdev, RTW_DBG_STATE, "stop vif %pM mac_id %d on port %d\n",
+		vif->addr, rtwvif->mac_id, rtwvif->port);
 
 	mutex_lock(&rtwdev->mutex);
 
@@ -242,6 +250,7 @@ static void rtw_ops_remove_interface(struct ieee80211_hw *hw,
 	config |= PORT_SET_BCN_CTRL;
 	rtw_vif_port_config(rtwdev, rtwvif, config);
 	clear_bit(rtwvif->port, rtwdev->hw_port);
+	rtw_release_macid(rtwdev, rtwvif->mac_id);
 	rtw_recalc_lps(rtwdev, NULL);
 
 	mutex_unlock(&rtwdev->mutex);
diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index b0c9b0ff7017..bbdef38c7e34 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -311,17 +311,6 @@ static void rtw_ips_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
-static u8 rtw_acquire_macid(struct rtw_dev *rtwdev)
-{
-	unsigned long mac_id;
-
-	mac_id = find_first_zero_bit(rtwdev->mac_id_map, RTW_MAX_MAC_ID_NUM);
-	if (mac_id < RTW_MAX_MAC_ID_NUM)
-		set_bit(mac_id, rtwdev->mac_id_map);
-
-	return mac_id;
-}
-
 static void rtw_sta_rc_work(struct work_struct *work)
 {
 	struct rtw_sta_info *si = container_of(work, struct rtw_sta_info,
@@ -340,12 +329,14 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
 	struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv;
 	int i;
 
-	si->mac_id = rtw_acquire_macid(rtwdev);
-	if (si->mac_id >= RTW_MAX_MAC_ID_NUM)
-		return -ENOSPC;
+	if (vif->type == NL80211_IFTYPE_STATION) {
+		si->mac_id = rtwvif->mac_id;
+	} else {
+		si->mac_id = rtw_acquire_macid(rtwdev);
+		if (si->mac_id >= RTW_MAX_MAC_ID_NUM)
+			return -ENOSPC;
+	}
 
-	if (vif->type == NL80211_IFTYPE_STATION && vif->cfg.assoc == 0)
-		rtwvif->mac_id = si->mac_id;
 	si->rtwdev = rtwdev;
 	si->sta = sta;
 	si->vif = vif;
@@ -370,11 +361,13 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta,
 		    bool fw_exist)
 {
 	struct rtw_sta_info *si = (struct rtw_sta_info *)sta->drv_priv;
+	struct ieee80211_vif *vif = si->vif;
 	int i;
 
 	cancel_work_sync(&si->rc_work);
 
-	rtw_release_macid(rtwdev, si->mac_id);
+	if (vif->type != NL80211_IFTYPE_STATION)
+		rtw_release_macid(rtwdev, si->mac_id);
 	if (fw_exist)
 		rtw_fw_media_status_report(rtwdev, si->mac_id, false);
 
@@ -614,6 +607,8 @@ static void rtw_reset_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 	rtw_bf_disassoc(rtwdev, vif, NULL);
 	rtw_vif_assoc_changed(rtwvif, NULL);
 	rtw_txq_cleanup(rtwdev, vif->txq);
+
+	rtw_release_macid(rtwdev, rtwvif->mac_id);
 }
 
 void rtw_fw_recovery(struct rtw_dev *rtwdev)
@@ -2139,7 +2134,6 @@ int rtw_core_init(struct rtw_dev *rtwdev)
 	rtwdev->sec.total_cam_num = 32;
 	rtwdev->hal.current_channel = 1;
 	rtwdev->dm_info.fix_rate = U8_MAX;
-	set_bit(RTW_BC_MC_MACID, rtwdev->mac_id_map);
 
 	rtw_stats_init(rtwdev);
 
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 12b564ad3a58..945117afe143 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -742,7 +742,6 @@ struct rtw_txq {
 	unsigned long flags;
 };
 
-#define RTW_BC_MC_MACID 1
 DECLARE_EWMA(rssi, 10, 16);
 
 struct rtw_sta_info {
@@ -805,7 +804,7 @@ struct rtw_bf_info {
 struct rtw_vif {
 	enum rtw_net_type net_type;
 	u16 aid;
-	u8 mac_id; /* for STA mode only */
+	u8 mac_id;
 	u8 mac_addr[ETH_ALEN];
 	u8 bssid[ETH_ALEN];
 	u8 port;
@@ -2131,6 +2130,17 @@ static inline bool rtw_chip_has_tx_stbc(struct rtw_dev *rtwdev)
 	return rtwdev->chip->tx_stbc;
 }
 
+static inline u8 rtw_acquire_macid(struct rtw_dev *rtwdev)
+{
+	unsigned long mac_id;
+
+	mac_id = find_first_zero_bit(rtwdev->mac_id_map, RTW_MAX_MAC_ID_NUM);
+	if (mac_id < RTW_MAX_MAC_ID_NUM)
+		set_bit(mac_id, rtwdev->mac_id_map);
+
+	return mac_id;
+}
+
 static inline void rtw_release_macid(struct rtw_dev *rtwdev, u8 mac_id)
 {
 	clear_bit(mac_id, rtwdev->mac_id_map);
diff --git a/drivers/net/wireless/realtek/rtw88/tx.c b/drivers/net/wireless/realtek/rtw88/tx.c
index c02ac673be32..dae7ca148865 100644
--- a/drivers/net/wireless/realtek/rtw88/tx.c
+++ b/drivers/net/wireless/realtek/rtw88/tx.c
@@ -46,7 +46,8 @@ void rtw_tx_fill_tx_desc(struct rtw_tx_pkt_info *pkt_info, struct sk_buff *skb)
 		      le32_encode_bits(pkt_info->ls, RTW_TX_DESC_W0_LS) |
 		      le32_encode_bits(pkt_info->dis_qselseq, RTW_TX_DESC_W0_DISQSELSEQ);
 
-	tx_desc->w1 = le32_encode_bits(pkt_info->qsel, RTW_TX_DESC_W1_QSEL) |
+	tx_desc->w1 = le32_encode_bits(pkt_info->mac_id, RTW_TX_DESC_W1_MACID) |
+		      le32_encode_bits(pkt_info->qsel, RTW_TX_DESC_W1_QSEL) |
 		      le32_encode_bits(pkt_info->rate_id, RTW_TX_DESC_W1_RATE_ID) |
 		      le32_encode_bits(pkt_info->sec_type, RTW_TX_DESC_W1_SEC_TYPE) |
 		      le32_encode_bits(pkt_info->pkt_offset, RTW_TX_DESC_W1_PKT_OFFSET) |
@@ -401,14 +402,18 @@ void rtw_tx_pkt_info_update(struct rtw_dev *rtwdev,
 	const struct rtw_chip_info *chip = rtwdev->chip;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_vif *vif = info->control.vif;
 	struct rtw_sta_info *si;
-	struct ieee80211_vif *vif = NULL;
+	struct rtw_vif *rtwvif;
 	__le16 fc = hdr->frame_control;
 	bool bmc;
 
 	if (sta) {
 		si = (struct rtw_sta_info *)sta->drv_priv;
-		vif = si->vif;
+		pkt_info->mac_id = si->mac_id;
+	} else if (vif) {
+		rtwvif = (struct rtw_vif *)vif->drv_priv;
+		pkt_info->mac_id = rtwvif->mac_id;
 	}
 
 	if (ieee80211_is_mgmt(fc) || ieee80211_is_nullfunc(fc))
diff --git a/drivers/net/wireless/realtek/rtw88/tx.h b/drivers/net/wireless/realtek/rtw88/tx.h
index 324189606257..3d544fd7f60f 100644
--- a/drivers/net/wireless/realtek/rtw88/tx.h
+++ b/drivers/net/wireless/realtek/rtw88/tx.h
@@ -27,6 +27,7 @@ struct rtw_tx_desc {
 #define RTW_TX_DESC_W0_BMC BIT(24)
 #define RTW_TX_DESC_W0_LS BIT(26)
 #define RTW_TX_DESC_W0_DISQSELSEQ BIT(31)
+#define RTW_TX_DESC_W1_MACID GENMASK(7, 0)
 #define RTW_TX_DESC_W1_QSEL GENMASK(12, 8)
 #define RTW_TX_DESC_W1_RATE_ID GENMASK(20, 16)
 #define RTW_TX_DESC_W1_SEC_TYPE GENMASK(23, 22)
-- 
cgit v1.3-3-g829e


From d9dd3ac77cf7cabd35732893f3aefba1daa1c2e1 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 26 Aug 2024 17:04:36 +0800
Subject: wifi: rtw89: wow: fix wait condition for AOAC report request

Each condition binding to the same wait should be unique. AOAC code misused
the wait of FW offload series and broke the above rule. It added another
macro to generate wait condition of WoWLAN/AOAC, but the results conflict
to the ones of FW offload series. It means that we might be completed
wrongly in logic. We don't want things work/read like this and should
have avoided this.

Fix this by adding another wait which aims for WoWLAN functions.

Fixes: ff53fce5c78b ("wifi: rtw89: wow: update latest PTK GTK info to mac80211 after resume")
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240826090439.17242-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 1 +
 drivers/net/wireless/realtek/rtw89/core.h | 3 +++
 drivers/net/wireless/realtek/rtw89/fw.c   | 6 ++----
 drivers/net/wireless/realtek/rtw89/fw.h   | 7 +++++--
 drivers/net/wireless/realtek/rtw89/mac.c  | 6 ++----
 5 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index dc642697d74a..436c01880ed4 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4320,6 +4320,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 
 	rtw89_init_wait(&rtwdev->mcc.wait);
 	rtw89_init_wait(&rtwdev->mac.fw_ofld_wait);
+	rtw89_init_wait(&rtwdev->wow.wait);
 
 	INIT_WORK(&rtwdev->c2h_work, rtw89_fw_c2h_work);
 	INIT_WORK(&rtwdev->ips_work, rtw89_ips_work);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 34dbe7f132f8..0f881cf99289 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5367,6 +5367,9 @@ struct rtw89_wow_param {
 	u8 ptk_keyidx;
 	u8 akm;
 
+	/* see RTW89_WOW_WAIT_COND series for wait condition */
+	struct rtw89_wait_info wait;
+
 	bool pno_inited;
 	struct list_head pno_pkt_list;
 	struct cfg80211_sched_scan_request *nd_config;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 023dd3456783..fa2f0d8c2ec0 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -7212,11 +7212,10 @@ fail:
 
 int rtw89_fw_h2c_wow_request_aoac(struct rtw89_dev *rtwdev)
 {
-	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
+	struct rtw89_wait_info *wait = &rtwdev->wow.wait;
 	struct rtw89_h2c_wow_aoac *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
-	unsigned int cond;
 
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
@@ -7235,8 +7234,7 @@ int rtw89_fw_h2c_wow_request_aoac(struct rtw89_dev *rtwdev)
 			      H2C_FUNC_AOAC_REPORT_REQ, 1, 0,
 			      len);
 
-	cond = RTW89_WOW_WAIT_COND(H2C_FUNC_AOAC_REPORT_REQ);
-	return rtw89_h2c_tx_and_wait(rtwdev, skb, wait, cond);
+	return rtw89_h2c_tx_and_wait(rtwdev, skb, wait, RTW89_WOW_WAIT_COND_AOAC);
 }
 
 /* Return < 0, if failures happen during waiting for the condition.
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 6e43cbc9559c..deda384a5251 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4015,8 +4015,11 @@ enum rtw89_wow_h2c_func {
 	NUM_OF_RTW89_WOW_H2C_FUNC,
 };
 
-#define RTW89_WOW_WAIT_COND(func) \
-	(NUM_OF_RTW89_WOW_H2C_FUNC + (func))
+#define RTW89_WOW_WAIT_COND(tag, func) \
+	((tag) * NUM_OF_RTW89_WOW_H2C_FUNC + (func))
+
+#define RTW89_WOW_WAIT_COND_AOAC \
+	RTW89_WOW_WAIT_COND(0 /* don't care */, H2C_FUNC_AOAC_REPORT_REQ)
 
 /* CLASS 2 - PS */
 #define H2C_CL_MAC_PS			0x2
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index a661c176100c..f336362ad45e 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -5165,11 +5165,10 @@ rtw89_mac_c2h_wow_aoac_rpt(struct rtw89_dev *rtwdev, struct sk_buff *skb, u32 le
 {
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct rtw89_wow_aoac_report *aoac_rpt = &rtw_wow->aoac_rpt;
-	struct rtw89_wait_info *wait = &rtwdev->mac.fw_ofld_wait;
+	struct rtw89_wait_info *wait = &rtw_wow->wait;
 	const struct rtw89_c2h_wow_aoac_report *c2h =
 		(const struct rtw89_c2h_wow_aoac_report *)skb->data;
 	struct rtw89_completion_data data = {};
-	unsigned int cond;
 
 	aoac_rpt->rpt_ver = c2h->rpt_ver;
 	aoac_rpt->sec_type = c2h->sec_type;
@@ -5187,8 +5186,7 @@ rtw89_mac_c2h_wow_aoac_rpt(struct rtw89_dev *rtwdev, struct sk_buff *skb, u32 le
 	aoac_rpt->igtk_ipn = le64_to_cpu(c2h->igtk_ipn);
 	memcpy(aoac_rpt->igtk, c2h->igtk, sizeof(aoac_rpt->igtk));
 
-	cond = RTW89_WOW_WAIT_COND(H2C_FUNC_AOAC_REPORT_REQ);
-	rtw89_complete_cond(wait, cond, &data);
+	rtw89_complete_cond(wait, RTW89_WOW_WAIT_COND_AOAC, &data);
 }
 
 static void
-- 
cgit v1.3-3-g829e


From f6409a8a0aab2ffc5df5ecbd0e73c9be1f84af4e Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 26 Aug 2024 17:04:37 +0800
Subject: wifi: rtw89: wow: add wait for H2C of FW-IPS mode

The C2H packet of FW-IPS mode is not handled by driver in the suspend
flow, and lead to WoWLAN firmware fail to enter PS mode and even some
SER happen. So add wait function for H2C of FW-IPS mode to check driver
handle the C2H packet before disabling interrupt and make the net-detect
function work fine.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240826090439.17242-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |  1 +
 drivers/net/wireless/realtek/rtw89/core.h |  2 ++
 drivers/net/wireless/realtek/rtw89/fw.c   | 13 ++-----------
 drivers/net/wireless/realtek/rtw89/fw.h   | 16 +++++++++++++---
 drivers/net/wireless/realtek/rtw89/mac.c  | 13 +++++++++++++
 5 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 436c01880ed4..f3db1a199b24 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4321,6 +4321,7 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	rtw89_init_wait(&rtwdev->mcc.wait);
 	rtw89_init_wait(&rtwdev->mac.fw_ofld_wait);
 	rtw89_init_wait(&rtwdev->wow.wait);
+	rtw89_init_wait(&rtwdev->mac.ps_wait);
 
 	INIT_WORK(&rtwdev->c2h_work, rtw89_fw_c2h_work);
 	INIT_WORK(&rtwdev->ips_work, rtw89_ips_work);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 0f881cf99289..7c3aeedfd93a 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4397,6 +4397,8 @@ struct rtw89_mac_info {
 
 	/* see RTW89_FW_OFLD_WAIT_COND series for wait condition */
 	struct rtw89_wait_info fw_ofld_wait;
+	/* see RTW89_PS_WAIT_COND series for wait condition */
+	struct rtw89_wait_info ps_wait;
 };
 
 enum rtw89_fwdl_check_type {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index fa2f0d8c2ec0..d9b0e7ebe619 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -7176,10 +7176,10 @@ fail:
 int rtw89_fw_h2c_fwips(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 		       bool enable)
 {
+	struct rtw89_wait_info *wait = &rtwdev->mac.ps_wait;
 	struct rtw89_h2c_fwips *h2c;
 	u32 len = sizeof(*h2c);
 	struct sk_buff *skb;
-	int ret;
 
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
@@ -7198,16 +7198,7 @@ int rtw89_fw_h2c_fwips(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 			      H2C_FUNC_IPS_CFG, 0, 1,
 			      len);
 
-	ret = rtw89_h2c_tx(rtwdev, skb, false);
-	if (ret) {
-		rtw89_err(rtwdev, "failed to send h2c\n");
-		goto fail;
-	}
-	return 0;
-fail:
-	dev_kfree_skb_any(skb);
-
-	return ret;
+	return rtw89_h2c_tx_and_wait(rtwdev, skb, wait, RTW89_PS_WAIT_COND_IPS_CFG);
 }
 
 int rtw89_fw_h2c_wow_request_aoac(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index deda384a5251..ad47e77d740b 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4023,9 +4023,19 @@ enum rtw89_wow_h2c_func {
 
 /* CLASS 2 - PS */
 #define H2C_CL_MAC_PS			0x2
-#define H2C_FUNC_MAC_LPS_PARM		0x0
-#define H2C_FUNC_P2P_ACT		0x1
-#define H2C_FUNC_IPS_CFG		0x3
+enum rtw89_ps_h2c_func {
+	H2C_FUNC_MAC_LPS_PARM		= 0x0,
+	H2C_FUNC_P2P_ACT		= 0x1,
+	H2C_FUNC_IPS_CFG		= 0x3,
+
+	NUM_OF_RTW89_PS_H2C_FUNC,
+};
+
+#define RTW89_PS_WAIT_COND(tag, func) \
+	((tag) * NUM_OF_RTW89_PS_H2C_FUNC + (func))
+
+#define RTW89_PS_WAIT_COND_IPS_CFG \
+	RTW89_PS_WAIT_COND(0 /* don't care */, H2C_FUNC_IPS_CFG)
 
 /* CLASS 3 - FW download */
 #define H2C_CL_MAC_FWDL		0x3
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index f336362ad45e..c70a23a763b0 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4887,6 +4887,7 @@ rtw89_mac_c2h_done_ack(struct rtw89_dev *rtwdev, struct sk_buff *skb_c2h, u32 le
 {
 	/* N.B. This will run in interrupt context. */
 	struct rtw89_wait_info *fw_ofld_wait = &rtwdev->mac.fw_ofld_wait;
+	struct rtw89_wait_info *ps_wait = &rtwdev->mac.ps_wait;
 	const struct rtw89_c2h_done_ack *c2h =
 		(const struct rtw89_c2h_done_ack *)skb_c2h->data;
 	u8 h2c_cat = le32_get_bits(c2h->w2, RTW89_C2H_DONE_ACK_W2_CAT);
@@ -4907,6 +4908,18 @@ rtw89_mac_c2h_done_ack(struct rtw89_dev *rtwdev, struct sk_buff *skb_c2h, u32 le
 	switch (h2c_class) {
 	default:
 		return;
+	case H2C_CL_MAC_PS:
+		switch (h2c_func) {
+		default:
+			return;
+		case H2C_FUNC_IPS_CFG:
+			cond = RTW89_PS_WAIT_COND_IPS_CFG;
+			break;
+		}
+
+		data.err = !!h2c_return;
+		rtw89_complete_cond(ps_wait, cond, &data);
+		return;
 	case H2C_CL_MAC_FW_OFLD:
 		switch (h2c_func) {
 		default:
-- 
cgit v1.3-3-g829e


From 1de40069417e0f2b9779eb4781fb4852f3d87680 Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 26 Aug 2024 17:04:38 +0800
Subject: wifi: rtw89: wow: add net-detect support for 8922ae

Enable net-detect in WoWLAN stub of 8922a, and declare net-detect
support up to 8 SSIDs.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240826090439.17242-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/rtw8922a.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 3387989299c9..0ff9c9b275f8 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2516,10 +2516,12 @@ static int rtw8922a_mac_disable_bb_rf(struct rtw89_dev *rtwdev)
 
 #ifdef CONFIG_PM
 static const struct wiphy_wowlan_support rtw_wowlan_stub_8922a = {
-	.flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT,
+	.flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT |
+		 WIPHY_WOWLAN_NET_DETECT,
 	.n_patterns = RTW89_MAX_PATTERN_NUM,
 	.pattern_max_len = RTW89_MAX_PATTERN_SIZE,
 	.pattern_min_len = 1,
+	.max_nd_match_sets = RTW89_SCANOFLD_MAX_SSID,
 };
 #endif
 
-- 
cgit v1.3-3-g829e


From 30ce797d4654015c179a8909ef6945f0c0d64e7e Mon Sep 17 00:00:00 2001
From: Chin-Yen Lee <timlee@realtek.com>
Date: Mon, 26 Aug 2024 17:04:39 +0800
Subject: wifi: rtw89: wow: add scan interval option for net-detect

The scan interval option is the period in unit of second for WoWLAN
firmware to do each scan. We get the option from cfg80211 and practice it.
If the interval is too short for firmware to finish one scan, the firmware
will start next scan immediately after finishing one and the WiFi chip
could never enter idle mode to reduce power consumption.

Signed-off-by: Chin-Yen Lee <timlee@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240826090439.17242-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/wow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 0f0f4beec4d9..86e24e07780d 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -1438,6 +1438,7 @@ static int rtw89_pno_scan_offload(struct rtw89_dev *rtwdev, bool enable)
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct ieee80211_vif *wow_vif = rtw_wow->wow_vif;
 	struct rtw89_vif *rtwvif = (struct rtw89_vif *)wow_vif->drv_priv;
+	int interval = rtw_wow->nd_config->scan_plans[0].interval;
 	struct rtw89_scan_option opt = {};
 	int ret;
 
@@ -1457,7 +1458,7 @@ static int rtw89_pno_scan_offload(struct rtw89_dev *rtwdev, bool enable)
 
 	opt.enable = enable;
 	opt.repeat = RTW89_SCAN_NORMAL;
-	opt.norm_pd = 10; /* in unit of 100ms */
+	opt.norm_pd = max(interval, 1) * 10; /* in unit of 100ms */
 	opt.delay = max(rtw_wow->nd_config->delay, 1);
 
 	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE) {
-- 
cgit v1.3-3-g829e


From 55ddb6c5a3aef8d8658fe31b1ddda007693ae797 Mon Sep 17 00:00:00 2001
From: Andrew Halaney <ahalaney@redhat.com>
Date: Thu, 29 Aug 2024 15:48:44 -0500
Subject: net: stmmac: drop the ethtool begin() callback

This callback doesn't seem to serve much purpose, and prevents things
like:

    - systemd.link files from disabling autonegotiation
    - carrier detection in NetworkManager
    - any ethtool setting

prior to userspace bringing the link up.

The only fear I can think of is accessing unclocked resources due to
pm_runtime, but ethtool ioctls handle that as of commit
f32a21376573 ("ethtool: runtime-resume netdev parent before ethtool ioctl ops")

Reviewed-by: Dmitry Dolenko <d.dolenko@metrotek.ru>
Tested-by: Dmitry Dolenko <d.dolenko@metrotek.ru>
Signed-off-by: Andrew Halaney <ahalaney@redhat.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 7008219fd88d..220c582904f4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -438,13 +438,6 @@ static void stmmac_ethtool_setmsglevel(struct net_device *dev, u32 level)
 
 }
 
-static int stmmac_check_if_running(struct net_device *dev)
-{
-	if (!netif_running(dev))
-		return -EBUSY;
-	return 0;
-}
-
 static int stmmac_ethtool_get_regs_len(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -1273,7 +1266,6 @@ static int stmmac_set_tunable(struct net_device *dev,
 static const struct ethtool_ops stmmac_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
-	.begin = stmmac_check_if_running,
 	.get_drvinfo = stmmac_ethtool_getdrvinfo,
 	.get_msglevel = stmmac_ethtool_getmsglevel,
 	.set_msglevel = stmmac_ethtool_setmsglevel,
-- 
cgit v1.3-3-g829e


From 731733c6234855b26d468aa2f89a3051c170e63a Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 29 Aug 2024 16:45:51 +0100
Subject: bpf, sockmap: Correct spelling skmsg.c

Correct spelling in skmsg.c. As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://lore.kernel.org/bpf/20240829-sockmap-spell-v1-1-a614d76564cc@kernel.org
---
 net/core/skmsg.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index bbf40b999713..b1dcbd3be89e 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -293,7 +293,7 @@ out:
 	/* If we trim data a full sg elem before curr pointer update
 	 * copybreak and current so that any future copy operations
 	 * start at new copy location.
-	 * However trimed data that has not yet been used in a copy op
+	 * However trimmed data that has not yet been used in a copy op
 	 * does not require an update.
 	 */
 	if (!msg->sg.size) {
-- 
cgit v1.3-3-g829e


From 5d1622831064abf2633a1bc9a6446e83a669f58d Mon Sep 17 00:00:00 2001
From: Yaxin Chen <yaxin.chen1@bytedance.com>
Date: Fri, 23 Aug 2024 15:48:43 -0700
Subject: tcp_bpf: Remove an unused parameter for bpf_tcp_ingress()

Parameter flags is not used in bpf_tcp_ingress().

Signed-off-by: Yaxin Chen <yaxin.chen1@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20240823224843.1985277-1-yaxin.chen1@bytedance.com
---
 net/ipv4/tcp_bpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 53b0d62fd2c2..57a1614c55f9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -30,7 +30,7 @@ void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
 }
 
 static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock,
-			   struct sk_msg *msg, u32 apply_bytes, int flags)
+			   struct sk_msg *msg, u32 apply_bytes)
 {
 	bool apply = apply_bytes;
 	struct scatterlist *sge;
@@ -167,7 +167,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress,
 	if (unlikely(!psock))
 		return -EPIPE;
 
-	ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) :
+	ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes) :
 			tcp_bpf_push_locked(sk, msg, bytes, flags, false);
 	sk_psock_put(sk, psock);
 	return ret;
-- 
cgit v1.3-3-g829e


From 4e3a024b437ec0aee82550cc66a0f4e1a7a88a67 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Sat, 31 Aug 2024 12:17:04 +0000
Subject: netdev-genl: Set extack and fix error on napi-get

In commit 27f91aaf49b3 ("netdev-genl: Add netlink framework functions
for napi"), when an invalid NAPI ID is specified the return value
-EINVAL is used and no extack is set.

Change the return value to -ENOENT and set the extack.

Before this commit:

$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
                          --do napi-get --json='{"id": 451}'
Netlink error: Invalid argument
nl_len = 36 (20) nl_flags = 0x100 nl_type = 2
	error: -22

After this commit:

$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
                         --do napi-get --json='{"id": 451}'
Netlink error: No such file or directory
nl_len = 44 (28) nl_flags = 0x300 nl_type = 2
	error: -2
	extack: {'bad-attr': '.id'}

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20240831121707.17562-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netdev-genl.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 05f9515d2c05..a17d7eaeb001 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -216,10 +216,12 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info)
 	rtnl_lock();
 
 	napi = napi_by_id(napi_id);
-	if (napi)
+	if (napi) {
 		err = netdev_nl_napi_fill_one(rsp, napi, info);
-	else
-		err = -EINVAL;
+	} else {
+		NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]);
+		err = -ENOENT;
+	}
 
 	rtnl_unlock();
 
-- 
cgit v1.3-3-g829e


From 69cb89981c7a181d857b634c0740e914d5df79ea Mon Sep 17 00:00:00 2001
From: ChunHao Lin <hau@realtek.com>
Date: Fri, 30 Aug 2024 10:18:10 +0800
Subject: r8169: add support for RTL8126A rev.b

Add support for RTL8126A rev.b. Its XID is 0x64a. It is basically
based on the one with XID 0x649, but with different firmware file.

Signed-off-by: ChunHao Lin <hau@realtek.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/20240830021810.11993-1-hau@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169.h            |  1 +
 drivers/net/ethernet/realtek/r8169_main.c       | 42 ++++++++++++++++---------
 drivers/net/ethernet/realtek/r8169_phy_config.c |  1 +
 3 files changed, 29 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 00882ffc7a02..e2db944e6fa8 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -69,6 +69,7 @@ enum mac_version {
 	RTL_GIGA_MAC_VER_61,
 	RTL_GIGA_MAC_VER_63,
 	RTL_GIGA_MAC_VER_65,
+	RTL_GIGA_MAC_VER_66,
 	RTL_GIGA_MAC_NONE
 };
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 3507c2e28110..3cb1c4f5c91a 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -56,6 +56,7 @@
 #define FIRMWARE_8125A_3	"rtl_nic/rtl8125a-3.fw"
 #define FIRMWARE_8125B_2	"rtl_nic/rtl8125b-2.fw"
 #define FIRMWARE_8126A_2	"rtl_nic/rtl8126a-2.fw"
+#define FIRMWARE_8126A_3	"rtl_nic/rtl8126a-3.fw"
 
 #define TX_DMA_BURST	7	/* Maximum PCI burst, '7' is unlimited */
 #define InterFrameGap	0x03	/* 3 means InterFrameGap = the shortest one */
@@ -138,6 +139,7 @@ static const struct {
 	/* reserve 62 for CFG_METHOD_4 in the vendor driver */
 	[RTL_GIGA_MAC_VER_63] = {"RTL8125B",		FIRMWARE_8125B_2},
 	[RTL_GIGA_MAC_VER_65] = {"RTL8126A",		FIRMWARE_8126A_2},
+	[RTL_GIGA_MAC_VER_66] = {"RTL8126A",		FIRMWARE_8126A_3},
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
@@ -1201,7 +1203,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val)
 	case RTL_GIGA_MAC_VER_31:
 		r8168dp_2_mdio_write(tp, location, val);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
 		r8168g_mdio_write(tp, location, val);
 		break;
 	default:
@@ -1216,7 +1218,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location)
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
 		return r8168dp_2_mdio_read(tp, location);
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
 		return r8168g_mdio_read(tp, location);
 	default:
 		return r8169_mdio_read(tp, location);
@@ -1425,7 +1427,7 @@ static void rtl_set_d3_pll_down(struct rtl8169_private *tp, bool enable)
 	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26:
 	case RTL_GIGA_MAC_VER_29 ... RTL_GIGA_MAC_VER_30:
 	case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_37:
-	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66:
 		if (enable)
 			RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~D3_NO_PLL_DOWN);
 		else
@@ -1592,7 +1594,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	case RTL_GIGA_MAC_VER_34:
 	case RTL_GIGA_MAC_VER_37:
-	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_66:
 		if (wolopts)
 			rtl_mod_config2(tp, 0, PME_SIGNAL);
 		else
@@ -2071,6 +2073,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_61:
 	case RTL_GIGA_MAC_VER_63:
 	case RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_66:
 		tp->tx_lpi_timer = timer_val;
 		RTL_W16(tp, EEE_TXIDLE_TIMER_8125, timer_val);
 		break;
@@ -2199,6 +2202,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 		enum mac_version ver;
 	} mac_info[] = {
 		/* 8126A family. */
+		{ 0x7cf, 0x64a,	RTL_GIGA_MAC_VER_66 },
 		{ 0x7cf, 0x649,	RTL_GIGA_MAC_VER_65 },
 
 		/* 8125B family. */
@@ -2470,6 +2474,7 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp)
 		break;
 	case RTL_GIGA_MAC_VER_63:
 	case RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_66:
 		RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST |
 			RX_PAUSE_SLOT_ON);
 		break;
@@ -2656,7 +2661,7 @@ static void rtl_wait_txrx_fifo_empty(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_61:
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		break;
-	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_63 ... RTL_GIGA_MAC_VER_66:
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42);
 		rtl_loop_wait_high(tp, &rtl_rxtx_empty_cond_2, 100, 42);
@@ -2899,7 +2904,7 @@ static void rtl_enable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_set_bits(tp, 0xd4, 0x0c00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0, 0x1f80);
 		break;
 	default:
@@ -2913,7 +2918,7 @@ static void rtl_disable_exit_l1(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
 		rtl_eri_clear_bits(tp, 0xd4, 0x1f00);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
 		r8168_mac_ocp_modify(tp, 0xc0ac, 0x1f80, 0);
 		break;
 	default:
@@ -2940,6 +2945,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 		rtl_mod_config5(tp, 0, ASPM_en);
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_65:
+		case RTL_GIGA_MAC_VER_66:
 			val8 = RTL_R8(tp, INT_CFG0_8125) | INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -2950,7 +2956,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_65:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
 			/* reset ephy tx/rx disable timer */
 			r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0);
 			/* chip can trigger L1.2 */
@@ -2962,7 +2968,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 	} else {
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
-		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_65:
+		case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
 			r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0);
 			break;
 		default:
@@ -2971,6 +2977,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
 
 		switch (tp->mac_version) {
 		case RTL_GIGA_MAC_VER_65:
+		case RTL_GIGA_MAC_VER_66:
 			val8 = RTL_R8(tp, INT_CFG0_8125) & ~INT_CFG0_CLKREQEN;
 			RTL_W8(tp, INT_CFG0_8125, val8);
 			break;
@@ -3690,10 +3697,12 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	/* disable new tx descriptor format */
 	r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_66)
 		RTL_W8(tp, 0xD8, RTL_R8(tp, 0xD8) & ~0x02);
 
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_66)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400);
 	else if (tp->mac_version == RTL_GIGA_MAC_VER_63)
 		r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0200);
@@ -3711,7 +3720,8 @@ static void rtl_hw_start_8125_common(struct rtl8169_private *tp)
 	r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0030);
 	r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000);
 	r8168_mac_ocp_modify(tp, 0xea1c, 0x0003, 0x0001);
-	if (tp->mac_version == RTL_GIGA_MAC_VER_65)
+	if (tp->mac_version == RTL_GIGA_MAC_VER_65 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_66)
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0300, 0x0000);
 	else
 		r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000);
@@ -3825,6 +3835,7 @@ static void rtl_hw_config(struct rtl8169_private *tp)
 		[RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125a_2,
 		[RTL_GIGA_MAC_VER_63] = rtl_hw_start_8125b,
 		[RTL_GIGA_MAC_VER_65] = rtl_hw_start_8126a,
+		[RTL_GIGA_MAC_VER_66] = rtl_hw_start_8126a,
 	};
 
 	if (hw_configs[tp->mac_version])
@@ -3845,6 +3856,7 @@ static void rtl_hw_start_8125(struct rtl8169_private *tp)
 		break;
 	case RTL_GIGA_MAC_VER_63:
 	case RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_66:
 		for (i = 0xa00; i < 0xa80; i += 4)
 			RTL_W32(tp, i, 0);
 		RTL_W16(tp, INT_CFG1_8125, 0x0000);
@@ -4073,7 +4085,7 @@ static void rtl8169_cleanup(struct rtl8169_private *tp)
 		RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq);
 		rtl_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666);
 		break;
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_66:
 		rtl_enable_rxdvgate(tp);
 		fsleep(2000);
 		break;
@@ -4224,7 +4236,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp,
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_34:
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
 		padto = max_t(unsigned int, padto, ETH_ZLEN);
 		break;
 	default:
@@ -5257,7 +5269,7 @@ static void rtl_hw_initialize(struct rtl8169_private *tp)
 	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48:
 		rtl_hw_init_8168g(tp);
 		break;
-	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_65:
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_66:
 		rtl_hw_init_8125(tp);
 		break;
 	default:
diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index 1f74317beb88..2c8845e08f86 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -1159,6 +1159,7 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev,
 		[RTL_GIGA_MAC_VER_61] = rtl8125a_2_hw_phy_config,
 		[RTL_GIGA_MAC_VER_63] = rtl8125b_hw_phy_config,
 		[RTL_GIGA_MAC_VER_65] = rtl8126a_hw_phy_config,
+		[RTL_GIGA_MAC_VER_66] = rtl8126a_hw_phy_config,
 	};
 
 	if (phy_configs[ver])
-- 
cgit v1.3-3-g829e


From 075e3d30e4a3da8eadd12f2f063dc8e2ea9e1f08 Mon Sep 17 00:00:00 2001
From: Pawel Dembicki <paweldembicki@gmail.com>
Date: Tue, 27 Aug 2024 14:39:38 +0200
Subject: net: dsa: vsc73xx: implement FDB operations

This commit introduces implementations of three functions:
.port_fdb_dump
.port_fdb_add
.port_fdb_del

The FDB database organization is the same as in other old Vitesse chips:
It has 2048 rows and 4 columns (buckets). The row index is calculated by
the hash function 'vsc73xx_calc_hash' and the FDB entry must be placed
exactly into row[hash]. The chip selects the bucket number by itself.

Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Link: https://patch.msgid.link/20240827123938.582789-1-paweldembicki@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/vitesse-vsc73xx-core.c | 355 +++++++++++++++++++++++++++++++++
 drivers/net/dsa/vitesse-vsc73xx.h      |   2 +
 2 files changed, 357 insertions(+)

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index 4d693c029c1f..1f2acd3dfcd2 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -46,6 +46,8 @@
 #define VSC73XX_BLOCK_MII_EXTERNAL	0x1 /* External MDIO subblock */
 
 #define CPU_PORT	6 /* CPU port */
+#define VSC73XX_NUM_FDB_ROWS	2048
+#define VSC73XX_NUM_BUCKETS	4
 
 /* MAC Block registers */
 #define VSC73XX_MAC_CFG		0x00
@@ -197,6 +199,40 @@
 #define VSC73XX_SRCMASKS_MIRROR			BIT(26)
 #define VSC73XX_SRCMASKS_PORTS_MASK		GENMASK(7, 0)
 
+#define VSC73XX_MACHDATA_VID			GENMASK(27, 16)
+#define VSC73XX_MACHDATA_MAC0			GENMASK(15, 8)
+#define VSC73XX_MACHDATA_MAC1			GENMASK(7, 0)
+#define VSC73XX_MACLDATA_MAC2			GENMASK(31, 24)
+#define VSC73XX_MACLDATA_MAC3			GENMASK(23, 16)
+#define VSC73XX_MACLDATA_MAC4			GENMASK(15, 8)
+#define VSC73XX_MACLDATA_MAC5			GENMASK(7, 0)
+
+#define VSC73XX_HASH0_VID_FROM_MASK		GENMASK(5, 0)
+#define VSC73XX_HASH0_MAC0_FROM_MASK		GENMASK(7, 4)
+#define VSC73XX_HASH1_MAC0_FROM_MASK		GENMASK(3, 0)
+#define VSC73XX_HASH1_MAC1_FROM_MASK		GENMASK(7, 1)
+#define VSC73XX_HASH2_MAC1_FROM_MASK		BIT(0)
+#define VSC73XX_HASH2_MAC2_FROM_MASK		GENMASK(7, 0)
+#define VSC73XX_HASH2_MAC3_FROM_MASK		GENMASK(7, 6)
+#define VSC73XX_HASH3_MAC3_FROM_MASK		GENMASK(5, 0)
+#define VSC73XX_HASH3_MAC4_FROM_MASK		GENMASK(7, 3)
+#define VSC73XX_HASH4_MAC4_FROM_MASK		GENMASK(2, 0)
+
+#define VSC73XX_HASH0_VID_TO_MASK		GENMASK(9, 4)
+#define VSC73XX_HASH0_MAC0_TO_MASK		GENMASK(3, 0)
+#define VSC73XX_HASH1_MAC0_TO_MASK		GENMASK(10, 7)
+#define VSC73XX_HASH1_MAC1_TO_MASK		GENMASK(6, 0)
+#define VSC73XX_HASH2_MAC1_TO_MASK		BIT(10)
+#define VSC73XX_HASH2_MAC2_TO_MASK		GENMASK(9, 2)
+#define VSC73XX_HASH2_MAC3_TO_MASK		GENMASK(1, 0)
+#define VSC73XX_HASH3_MAC3_TO_MASK		GENMASK(10, 5)
+#define VSC73XX_HASH3_MAC4_TO_MASK		GENMASK(4, 0)
+#define VSC73XX_HASH4_MAC4_TO_MASK		GENMASK(10, 8)
+
+#define VSC73XX_MACTINDX_SHADOW			BIT(13)
+#define VSC73XX_MACTINDX_BUCKET_MSK		GENMASK(12, 11)
+#define VSC73XX_MACTINDX_INDEX_MSK		GENMASK(10, 0)
+
 #define VSC73XX_MACACCESS_CPU_COPY		BIT(14)
 #define VSC73XX_MACACCESS_FWD_KILL		BIT(13)
 #define VSC73XX_MACACCESS_IGNORE_VLAN		BIT(12)
@@ -332,6 +368,13 @@ struct vsc73xx_counter {
 	const char *name;
 };
 
+struct vsc73xx_fdb {
+	u16 vid;
+	u8 port;
+	u8 mac[ETH_ALEN];
+	bool valid;
+};
+
 /* Counters are named according to the MIB standards where applicable.
  * Some counters are custom, non-standard. The standard counters are
  * named in accordance with RFC2819, RFC2021 and IEEE Std 802.3-2002 Annex
@@ -804,6 +847,7 @@ static int vsc73xx_setup(struct dsa_switch *ds)
 
 	ds->untag_bridge_pvid = true;
 	ds->max_num_bridges = DSA_TAG_8021Q_MAX_NUM_BRIDGES;
+	ds->fdb_isolation = true;
 
 	/* Issue RESET */
 	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
@@ -1854,6 +1898,312 @@ static void vsc73xx_port_stp_state_set(struct dsa_switch *ds, int port,
 		vsc73xx_refresh_fwd_map(ds, port, state);
 }
 
+static u16 vsc73xx_calc_hash(const unsigned char *addr, u16 vid)
+{
+	/* VID 5-0, MAC 47-44 */
+	u16 hash = FIELD_PREP(VSC73XX_HASH0_VID_TO_MASK,
+			      FIELD_GET(VSC73XX_HASH0_VID_FROM_MASK, vid)) |
+		   FIELD_PREP(VSC73XX_HASH0_MAC0_TO_MASK,
+			      FIELD_GET(VSC73XX_HASH0_MAC0_FROM_MASK, addr[0]));
+	/* MAC 43-33 */
+	hash ^= FIELD_PREP(VSC73XX_HASH1_MAC0_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH1_MAC0_FROM_MASK, addr[0])) |
+		FIELD_PREP(VSC73XX_HASH1_MAC1_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH1_MAC1_FROM_MASK, addr[1]));
+	/* MAC 32-22 */
+	hash ^= FIELD_PREP(VSC73XX_HASH2_MAC1_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH2_MAC1_FROM_MASK, addr[1])) |
+		FIELD_PREP(VSC73XX_HASH2_MAC2_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH2_MAC2_FROM_MASK, addr[2])) |
+		FIELD_PREP(VSC73XX_HASH2_MAC3_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH2_MAC3_FROM_MASK, addr[3]));
+	/* MAC 21-11 */
+	hash ^= FIELD_PREP(VSC73XX_HASH3_MAC3_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH3_MAC3_FROM_MASK, addr[3])) |
+		FIELD_PREP(VSC73XX_HASH3_MAC4_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH3_MAC4_FROM_MASK, addr[4]));
+	/* MAC 10-0 */
+	hash ^= FIELD_PREP(VSC73XX_HASH4_MAC4_TO_MASK,
+			   FIELD_GET(VSC73XX_HASH4_MAC4_FROM_MASK, addr[4])) |
+		addr[5];
+
+	return hash;
+}
+
+static int
+vsc73xx_port_wait_for_mac_table_cmd(struct vsc73xx *vsc)
+{
+	int ret, err;
+	u32 val;
+
+	ret = read_poll_timeout(vsc73xx_read, err,
+				err < 0 ||
+				((val & VSC73XX_MACACCESS_CMD_MASK) ==
+				 VSC73XX_MACACCESS_CMD_IDLE),
+				VSC73XX_POLL_SLEEP_US, VSC73XX_POLL_TIMEOUT_US,
+				false, vsc, VSC73XX_BLOCK_ANALYZER,
+				0, VSC73XX_MACACCESS, &val);
+	if (ret)
+		return ret;
+	return err;
+}
+
+static int vsc73xx_port_read_mac_table_row(struct vsc73xx *vsc, u16 index,
+					   struct vsc73xx_fdb *fdb)
+{
+	int ret, i;
+	u32 val;
+
+	if (!fdb)
+		return -EINVAL;
+	if (index >= VSC73XX_NUM_FDB_ROWS)
+		return -EINVAL;
+
+	for (i = 0; i < VSC73XX_NUM_BUCKETS; i++) {
+		ret = vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				    VSC73XX_MACTINDX,
+				    (i ? 0 : VSC73XX_MACTINDX_SHADOW) |
+				    FIELD_PREP(VSC73XX_MACTINDX_BUCKET_MSK, i) |
+				    index);
+		if (ret)
+			return ret;
+
+		ret = vsc73xx_port_wait_for_mac_table_cmd(vsc);
+		if (ret)
+			return ret;
+
+		ret = vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+					  VSC73XX_MACACCESS,
+					  VSC73XX_MACACCESS_CMD_MASK,
+					  VSC73XX_MACACCESS_CMD_READ_ENTRY);
+		if (ret)
+			return ret;
+
+		ret = vsc73xx_port_wait_for_mac_table_cmd(vsc);
+		if (ret)
+			return ret;
+
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				   VSC73XX_MACACCESS, &val);
+		if (ret)
+			return ret;
+
+		fdb[i].valid = FIELD_GET(VSC73XX_MACACCESS_VALID, val);
+		if (!fdb[i].valid)
+			continue;
+
+		fdb[i].port = FIELD_GET(VSC73XX_MACACCESS_DEST_IDX_MASK, val);
+
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				   VSC73XX_MACHDATA, &val);
+		if (ret)
+			return ret;
+
+		fdb[i].vid = FIELD_GET(VSC73XX_MACHDATA_VID, val);
+		fdb[i].mac[0] = FIELD_GET(VSC73XX_MACHDATA_MAC0, val);
+		fdb[i].mac[1] = FIELD_GET(VSC73XX_MACHDATA_MAC1, val);
+
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				   VSC73XX_MACLDATA, &val);
+		if (ret)
+			return ret;
+
+		fdb[i].mac[2] = FIELD_GET(VSC73XX_MACLDATA_MAC2, val);
+		fdb[i].mac[3] = FIELD_GET(VSC73XX_MACLDATA_MAC3, val);
+		fdb[i].mac[4] = FIELD_GET(VSC73XX_MACLDATA_MAC4, val);
+		fdb[i].mac[5] = FIELD_GET(VSC73XX_MACLDATA_MAC5, val);
+	}
+
+	return ret;
+}
+
+static int
+vsc73xx_fdb_operation(struct vsc73xx *vsc, const unsigned char *addr, u16 vid,
+		      u16 hash, u16 cmd_mask, u16 cmd_val)
+{
+	int ret;
+	u32 val;
+
+	val = FIELD_PREP(VSC73XX_MACHDATA_VID, vid) |
+	      FIELD_PREP(VSC73XX_MACHDATA_MAC0, addr[0]) |
+	      FIELD_PREP(VSC73XX_MACHDATA_MAC1, addr[1]);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_MACHDATA,
+			    val);
+	if (ret)
+		return ret;
+
+	val = FIELD_PREP(VSC73XX_MACLDATA_MAC2, addr[2]) |
+	      FIELD_PREP(VSC73XX_MACLDATA_MAC3, addr[3]) |
+	      FIELD_PREP(VSC73XX_MACLDATA_MAC4, addr[4]) |
+	      FIELD_PREP(VSC73XX_MACLDATA_MAC5, addr[5]);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_MACLDATA,
+			    val);
+	if (ret)
+		return ret;
+
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_MACTINDX,
+			    hash);
+	if (ret)
+		return ret;
+
+	ret = vsc73xx_port_wait_for_mac_table_cmd(vsc);
+	if (ret)
+		return ret;
+
+	ret = vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				  VSC73XX_MACACCESS, cmd_mask, cmd_val);
+	if (ret)
+		return ret;
+
+	return vsc73xx_port_wait_for_mac_table_cmd(vsc);
+}
+
+static int vsc73xx_fdb_del_entry(struct vsc73xx *vsc, int port,
+				 const unsigned char *addr, u16 vid)
+{
+	struct vsc73xx_fdb fdb[VSC73XX_NUM_BUCKETS];
+	u16 hash = vsc73xx_calc_hash(addr, vid);
+	int bucket, ret;
+
+	mutex_lock(&vsc->fdb_lock);
+
+	ret = vsc73xx_port_read_mac_table_row(vsc, hash, fdb);
+	if (ret)
+		goto err;
+
+	for (bucket = 0; bucket < VSC73XX_NUM_BUCKETS; bucket++) {
+		if (fdb[bucket].valid && fdb[bucket].port == port &&
+		    ether_addr_equal(addr, fdb[bucket].mac))
+			break;
+	}
+
+	if (bucket == VSC73XX_NUM_BUCKETS) {
+		/* Can't find MAC in MAC table */
+		ret = -ENODATA;
+		goto err;
+	}
+
+	ret = vsc73xx_fdb_operation(vsc, addr, vid, hash,
+				    VSC73XX_MACACCESS_CMD_MASK,
+				    VSC73XX_MACACCESS_CMD_FORGET);
+err:
+	mutex_unlock(&vsc->fdb_lock);
+	return ret;
+}
+
+static int vsc73xx_fdb_add_entry(struct vsc73xx *vsc, int port,
+				 const unsigned char *addr, u16 vid)
+{
+	struct vsc73xx_fdb fdb[VSC73XX_NUM_BUCKETS];
+	u16 hash = vsc73xx_calc_hash(addr, vid);
+	int bucket, ret;
+	u32 val;
+
+	mutex_lock(&vsc->fdb_lock);
+
+	ret = vsc73xx_port_read_mac_table_row(vsc, hash, fdb);
+	if (ret)
+		goto err;
+
+	for (bucket = 0; bucket < VSC73XX_NUM_BUCKETS; bucket++) {
+		if (!fdb[bucket].valid)
+			break;
+	}
+
+	if (bucket == VSC73XX_NUM_BUCKETS) {
+		/* Bucket is full */
+		ret = -EOVERFLOW;
+		goto err;
+	}
+
+	val = VSC73XX_MACACCESS_VALID | VSC73XX_MACACCESS_LOCKED |
+	      FIELD_PREP(VSC73XX_MACACCESS_DEST_IDX_MASK, port) |
+	      VSC73XX_MACACCESS_CMD_LEARN;
+	ret = vsc73xx_fdb_operation(vsc, addr, vid, hash,
+				    VSC73XX_MACACCESS_VALID |
+				    VSC73XX_MACACCESS_LOCKED |
+				    VSC73XX_MACACCESS_DEST_IDX_MASK |
+				    VSC73XX_MACACCESS_CMD_MASK, val);
+err:
+	mutex_unlock(&vsc->fdb_lock);
+	return ret;
+}
+
+static int vsc73xx_fdb_add(struct dsa_switch *ds, int port,
+			   const unsigned char *addr, u16 vid, struct dsa_db db)
+{
+	struct vsc73xx *vsc = ds->priv;
+
+	if (!vid) {
+		switch (db.type) {
+		case DSA_DB_PORT:
+			vid = dsa_tag_8021q_standalone_vid(db.dp);
+			break;
+		case DSA_DB_BRIDGE:
+			vid = dsa_tag_8021q_bridge_vid(db.bridge.num);
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return vsc73xx_fdb_add_entry(vsc, port, addr, vid);
+}
+
+static int vsc73xx_fdb_del(struct dsa_switch *ds, int port,
+			   const unsigned char *addr, u16 vid, struct dsa_db db)
+{
+	struct vsc73xx *vsc = ds->priv;
+
+	if (!vid) {
+		switch (db.type) {
+		case DSA_DB_PORT:
+			vid = dsa_tag_8021q_standalone_vid(db.dp);
+			break;
+		case DSA_DB_BRIDGE:
+			vid = dsa_tag_8021q_bridge_vid(db.bridge.num);
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return vsc73xx_fdb_del_entry(vsc, port, addr, vid);
+}
+
+static int vsc73xx_port_fdb_dump(struct dsa_switch *ds,
+				 int port, dsa_fdb_dump_cb_t *cb, void *data)
+{
+	struct vsc73xx_fdb fdb[VSC73XX_NUM_BUCKETS];
+	struct vsc73xx *vsc = ds->priv;
+	u16 i, bucket;
+	int err = 0;
+
+	mutex_lock(&vsc->fdb_lock);
+
+	for (i = 0; i < VSC73XX_NUM_FDB_ROWS; i++) {
+		err = vsc73xx_port_read_mac_table_row(vsc, i, fdb);
+		if (err)
+			goto unlock;
+
+		for (bucket = 0; bucket < VSC73XX_NUM_BUCKETS; bucket++) {
+			if (!fdb[bucket].valid || fdb[bucket].port != port)
+				continue;
+
+			/* We need to hide dsa_8021q VLANs from the user */
+			if (vid_is_dsa_8021q(fdb[bucket].vid))
+				fdb[bucket].vid = 0;
+
+			err = cb(fdb[bucket].mac, fdb[bucket].vid, false, data);
+			if (err)
+				goto unlock;
+		}
+	}
+unlock:
+	mutex_unlock(&vsc->fdb_lock);
+	return err;
+}
+
 static const struct phylink_mac_ops vsc73xx_phylink_mac_ops = {
 	.mac_config = vsc73xx_mac_config,
 	.mac_link_down = vsc73xx_mac_link_down,
@@ -1876,6 +2226,9 @@ static const struct dsa_switch_ops vsc73xx_ds_ops = {
 	.port_bridge_join = dsa_tag_8021q_bridge_join,
 	.port_bridge_leave = dsa_tag_8021q_bridge_leave,
 	.port_change_mtu = vsc73xx_change_mtu,
+	.port_fdb_add = vsc73xx_fdb_add,
+	.port_fdb_del = vsc73xx_fdb_del,
+	.port_fdb_dump = vsc73xx_port_fdb_dump,
 	.port_max_mtu = vsc73xx_get_max_mtu,
 	.port_stp_state_set = vsc73xx_port_stp_state_set,
 	.port_vlan_filtering = vsc73xx_port_vlan_filtering,
@@ -2006,6 +2359,8 @@ int vsc73xx_probe(struct vsc73xx *vsc)
 		return -ENODEV;
 	}
 
+	mutex_init(&vsc->fdb_lock);
+
 	eth_random_addr(vsc->addr);
 	dev_info(vsc->dev,
 		 "MAC for control frames: %02X:%02X:%02X:%02X:%02X:%02X\n",
diff --git a/drivers/net/dsa/vitesse-vsc73xx.h b/drivers/net/dsa/vitesse-vsc73xx.h
index 3ca579acc798..3c30e143c14f 100644
--- a/drivers/net/dsa/vitesse-vsc73xx.h
+++ b/drivers/net/dsa/vitesse-vsc73xx.h
@@ -45,6 +45,7 @@ struct vsc73xx_portinfo {
  * @vlans: List of configured vlans. Contains port mask and untagged status of
  *	every vlan configured in port vlan operation. It doesn't cover tag_8021q
  *	vlans.
+ * @fdb_lock: Mutex protects fdb access
  */
 struct vsc73xx {
 	struct device			*dev;
@@ -57,6 +58,7 @@ struct vsc73xx {
 	void				*priv;
 	struct vsc73xx_portinfo		portinfo[VSC73XX_MAX_NUM_PORTS];
 	struct list_head		vlans;
+	struct mutex			fdb_lock;
 };
 
 /**
-- 
cgit v1.3-3-g829e


From 1ef7f50ccc6e8e2b5de96ad1e304684a277a3055 Mon Sep 17 00:00:00 2001
From: Changliang Wu <changliang.wu@smartx.com>
Date: Thu, 20 Jun 2024 19:35:27 +0800
Subject: netfilter: ctnetlink: support CTA_FILTER for flush

From cb8aa9a, we can use kernel side filtering for dump, but
this capability is not available for flush.

This Patch allows advanced filter with CTA_FILTER for flush

Performace
1048576 ct flows in total, delete 50,000 flows by origin src ip
3.06s -> dump all, compare and delete
584ms -> directly flush with filter

Signed-off-by: Changliang Wu <changliang.wu@smartx.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_netlink.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 4cbf71d0786b..123e2e933e9b 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1579,9 +1579,6 @@ static int ctnetlink_flush_conntrack(struct net *net,
 	};
 
 	if (ctnetlink_needs_filter(family, cda)) {
-		if (cda[CTA_FILTER])
-			return -EOPNOTSUPP;
-
 		filter = ctnetlink_alloc_filter(cda, family);
 		if (IS_ERR(filter))
 			return PTR_ERR(filter);
@@ -1610,14 +1607,14 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (cda[CTA_TUPLE_ORIG])
+	if (cda[CTA_TUPLE_ORIG] && !cda[CTA_FILTER])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG,
 					    family, &zone);
-	else if (cda[CTA_TUPLE_REPLY])
+	else if (cda[CTA_TUPLE_REPLY] && !cda[CTA_FILTER])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY,
 					    family, &zone);
 	else {
-		u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC;
+		u8 u3 = info->nfmsg->version || cda[CTA_FILTER] ? family : AF_UNSPEC;
 
 		return ctnetlink_flush_conntrack(info->net, cda,
 						 NETLINK_CB(skb).portid,
-- 
cgit v1.3-3-g829e


From 4a1d3acd6ea86075e77fcc1188c3fc372833ba73 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 20 Aug 2024 09:54:32 +0200
Subject: netfilter: nft_counter: Use u64_stats_t for statistic.

The nft_counter uses two s64 counters for statistics. Those two are
protected by a seqcount to ensure that the 64bit variable is always
properly seen during updates even on 32bit architectures where the store
is performed by two writes. A side effect is that the two counter (bytes
and packet) are written and read together in the same window.

This can be replaced with u64_stats_t. write_seqcount_begin()/ end() is
replaced with u64_stats_update_begin()/ end() and behaves the same way
as with seqcount_t on 32bit architectures. Additionally there is a
preempt_disable on PREEMPT_RT to ensure that a reader does not preempt a
writer.
On 64bit architectures the macros are removed and the reads happen
without any retries. This also means that the reader can observe one
counter (bytes) from before the update and the other counter (packets)
but that is okay since there is no requirement to have both counter from
the same update window.

Convert the statistic to u64_stats_t. There is one optimisation:
nft_counter_do_init() and nft_counter_clone() allocate a new per-CPU
counter and assign a value to it. During this assignment preemption is
disabled which is not needed because the counter is not yet exposed to
the system so there can not be another writer or reader. Therefore
disabling preemption is omitted and raw_cpu_ptr() is used to obtain a
pointer to a counter for the assignment.

Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_counter.c | 90 +++++++++++++++++++++++----------------------
 1 file changed, 46 insertions(+), 44 deletions(-)

diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index eab0dc66bee6..cc7325329496 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -8,7 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/seqlock.h>
+#include <linux/u64_stats_sync.h>
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
@@ -17,6 +17,11 @@
 #include <net/netfilter/nf_tables_offload.h>
 
 struct nft_counter {
+	u64_stats_t	bytes;
+	u64_stats_t	packets;
+};
+
+struct nft_counter_tot {
 	s64		bytes;
 	s64		packets;
 };
@@ -25,25 +30,24 @@ struct nft_counter_percpu_priv {
 	struct nft_counter __percpu *counter;
 };
 
-static DEFINE_PER_CPU(seqcount_t, nft_counter_seq);
+static DEFINE_PER_CPU(struct u64_stats_sync, nft_counter_sync);
 
 static inline void nft_counter_do_eval(struct nft_counter_percpu_priv *priv,
 				       struct nft_regs *regs,
 				       const struct nft_pktinfo *pkt)
 {
+	struct u64_stats_sync *nft_sync;
 	struct nft_counter *this_cpu;
-	seqcount_t *myseq;
 
 	local_bh_disable();
 	this_cpu = this_cpu_ptr(priv->counter);
-	myseq = this_cpu_ptr(&nft_counter_seq);
-
-	write_seqcount_begin(myseq);
+	nft_sync = this_cpu_ptr(&nft_counter_sync);
 
-	this_cpu->bytes += pkt->skb->len;
-	this_cpu->packets++;
+	u64_stats_update_begin(nft_sync);
+	u64_stats_add(&this_cpu->bytes, pkt->skb->len);
+	u64_stats_inc(&this_cpu->packets);
+	u64_stats_update_end(nft_sync);
 
-	write_seqcount_end(myseq);
 	local_bh_enable();
 }
 
@@ -66,17 +70,16 @@ static int nft_counter_do_init(const struct nlattr * const tb[],
 	if (cpu_stats == NULL)
 		return -ENOMEM;
 
-	preempt_disable();
-	this_cpu = this_cpu_ptr(cpu_stats);
+	this_cpu = raw_cpu_ptr(cpu_stats);
 	if (tb[NFTA_COUNTER_PACKETS]) {
-	        this_cpu->packets =
-			be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+		u64_stats_set(&this_cpu->packets,
+			      be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])));
 	}
 	if (tb[NFTA_COUNTER_BYTES]) {
-		this_cpu->bytes =
-			be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
+		u64_stats_set(&this_cpu->bytes,
+			      be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])));
 	}
-	preempt_enable();
+
 	priv->counter = cpu_stats;
 	return 0;
 }
@@ -104,40 +107,41 @@ static void nft_counter_obj_destroy(const struct nft_ctx *ctx,
 }
 
 static void nft_counter_reset(struct nft_counter_percpu_priv *priv,
-			      struct nft_counter *total)
+			      struct nft_counter_tot *total)
 {
+	struct u64_stats_sync *nft_sync;
 	struct nft_counter *this_cpu;
-	seqcount_t *myseq;
 
 	local_bh_disable();
 	this_cpu = this_cpu_ptr(priv->counter);
-	myseq = this_cpu_ptr(&nft_counter_seq);
+	nft_sync = this_cpu_ptr(&nft_counter_sync);
+
+	u64_stats_update_begin(nft_sync);
+	u64_stats_add(&this_cpu->packets, -total->packets);
+	u64_stats_add(&this_cpu->bytes, -total->bytes);
+	u64_stats_update_end(nft_sync);
 
-	write_seqcount_begin(myseq);
-	this_cpu->packets -= total->packets;
-	this_cpu->bytes -= total->bytes;
-	write_seqcount_end(myseq);
 	local_bh_enable();
 }
 
 static void nft_counter_fetch(struct nft_counter_percpu_priv *priv,
-			      struct nft_counter *total)
+			      struct nft_counter_tot *total)
 {
 	struct nft_counter *this_cpu;
-	const seqcount_t *myseq;
 	u64 bytes, packets;
 	unsigned int seq;
 	int cpu;
 
 	memset(total, 0, sizeof(*total));
 	for_each_possible_cpu(cpu) {
-		myseq = per_cpu_ptr(&nft_counter_seq, cpu);
+		struct u64_stats_sync *nft_sync = per_cpu_ptr(&nft_counter_sync, cpu);
+
 		this_cpu = per_cpu_ptr(priv->counter, cpu);
 		do {
-			seq	= read_seqcount_begin(myseq);
-			bytes	= this_cpu->bytes;
-			packets	= this_cpu->packets;
-		} while (read_seqcount_retry(myseq, seq));
+			seq	= u64_stats_fetch_begin(nft_sync);
+			bytes	= u64_stats_read(&this_cpu->bytes);
+			packets	= u64_stats_read(&this_cpu->packets);
+		} while (u64_stats_fetch_retry(nft_sync, seq));
 
 		total->bytes	+= bytes;
 		total->packets	+= packets;
@@ -148,7 +152,7 @@ static int nft_counter_do_dump(struct sk_buff *skb,
 			       struct nft_counter_percpu_priv *priv,
 			       bool reset)
 {
-	struct nft_counter total;
+	struct nft_counter_tot total;
 
 	nft_counter_fetch(priv, &total);
 
@@ -237,7 +241,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g
 	struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst);
 	struct nft_counter __percpu *cpu_stats;
 	struct nft_counter *this_cpu;
-	struct nft_counter total;
+	struct nft_counter_tot total;
 
 	nft_counter_fetch(priv, &total);
 
@@ -245,11 +249,9 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g
 	if (cpu_stats == NULL)
 		return -ENOMEM;
 
-	preempt_disable();
-	this_cpu = this_cpu_ptr(cpu_stats);
-	this_cpu->packets = total.packets;
-	this_cpu->bytes = total.bytes;
-	preempt_enable();
+	this_cpu = raw_cpu_ptr(cpu_stats);
+	u64_stats_set(&this_cpu->packets, total.packets);
+	u64_stats_set(&this_cpu->bytes, total.bytes);
 
 	priv_clone->counter = cpu_stats;
 	return 0;
@@ -267,17 +269,17 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
 				      const struct flow_stats *stats)
 {
 	struct nft_counter_percpu_priv *priv = nft_expr_priv(expr);
+	struct u64_stats_sync *nft_sync;
 	struct nft_counter *this_cpu;
-	seqcount_t *myseq;
 
 	local_bh_disable();
 	this_cpu = this_cpu_ptr(priv->counter);
-	myseq = this_cpu_ptr(&nft_counter_seq);
+	nft_sync = this_cpu_ptr(&nft_counter_sync);
 
-	write_seqcount_begin(myseq);
-	this_cpu->packets += stats->pkts;
-	this_cpu->bytes += stats->bytes;
-	write_seqcount_end(myseq);
+	u64_stats_update_begin(nft_sync);
+	u64_stats_add(&this_cpu->packets, stats->pkts);
+	u64_stats_add(&this_cpu->bytes, stats->bytes);
+	u64_stats_update_end(nft_sync);
 	local_bh_enable();
 }
 
@@ -286,7 +288,7 @@ void nft_counter_init_seqcount(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		seqcount_init(per_cpu_ptr(&nft_counter_seq, cpu));
+		u64_stats_init(per_cpu_ptr(&nft_counter_sync, cpu));
 }
 
 struct nft_expr_type nft_counter_type;
-- 
cgit v1.3-3-g829e


From 20eb5e7cb78c331107fbdf2f77a30fbea9338638 Mon Sep 17 00:00:00 2001
From: Yan Zhen <yanzhen@vivo.com>
Date: Mon, 26 Aug 2024 11:41:36 +0800
Subject: netfilter: Use kmemdup_array instead of kmemdup for multiple
 allocation

When we are allocating an array, using kmemdup_array() to take care about
multiplication and possible overflows.

Also it makes auditing the code easier.

Signed-off-by: Yan Zhen <yanzhen@vivo.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/bridge/netfilter/ebtables.c | 2 +-
 net/ipv4/netfilter/arp_tables.c | 2 +-
 net/ipv4/netfilter/ip_tables.c  | 2 +-
 net/ipv6/netfilter/ip6_tables.c | 2 +-
 net/netfilter/nf_nat_core.c     | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index cbd0e3586c3f..3e67d4aff419 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1256,7 +1256,7 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table,
 		goto free_unlock;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		if (newinfo->nentries)
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 42c34e8952da..1cdd9c28ab2d 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -1547,7 +1547,7 @@ int arpt_register_table(struct net *net,
 		goto out_free;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto out_free;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 97e754ddc155..3d101613f27f 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1767,7 +1767,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 		goto out_free;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto out_free;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 131f7bb2110d..7d5602950ae7 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1773,7 +1773,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table,
 		goto out_free;
 	}
 
-	ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL);
+	ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL);
 	if (!ops) {
 		ret = -ENOMEM;
 		goto out_free;
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 016c816d91cb..6d8da6dddf99 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1104,7 +1104,7 @@ int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,
 	if (!nat_proto_net->nat_hook_ops) {
 		WARN_ON(nat_proto_net->users != 0);
 
-		nat_ops = kmemdup(orig_nat_ops, sizeof(*orig_nat_ops) * ops_count, GFP_KERNEL);
+		nat_ops = kmemdup_array(orig_nat_ops, ops_count, sizeof(*orig_nat_ops), GFP_KERNEL);
 		if (!nat_ops) {
 			mutex_unlock(&nf_nat_proto_mutex);
 			return -ENOMEM;
-- 
cgit v1.3-3-g829e


From 09c0d0aef56b3b026b55be092fd9e81f3ae0c8a9 Mon Sep 17 00:00:00 2001
From: Shen Lichuan <shenlichuan@vivo.com>
Date: Wed, 28 Aug 2024 19:06:51 +0800
Subject: netfilter: conntrack: Convert to use ERR_CAST()

Use the ERR_CAST macro to clearly indicate that this is a pointer
to an error value and that a type conversion was performed.

Signed-off-by: Shen Lichuan <shenlichuan@vivo.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 9384426ddc06..d3cb53b008f5 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1722,7 +1722,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
 				  hash);
 	if (IS_ERR(ct))
-		return (struct nf_conntrack_tuple_hash *)ct;
+		return ERR_CAST(ct);
 
 	if (!nf_ct_add_synproxy(ct, tmpl)) {
 		nf_conntrack_free(ct);
-- 
cgit v1.3-3-g829e


From eaf9b2c875ece22768b78aa38da8b232e5de021b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 28 Aug 2024 11:34:02 +0200
Subject: netfilter: nf_tables: drop unused 3rd argument from validate callback
 ops

Since commit a654de8fdc18 ("netfilter: nf_tables: fix chain dependency validation")
the validate() callback no longer needs the return pointer argument.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        | 3 +--
 include/net/netfilter/nft_fib.h          | 4 +---
 include/net/netfilter/nft_meta.h         | 3 +--
 include/net/netfilter/nft_reject.h       | 3 +--
 net/bridge/netfilter/nft_meta_bridge.c   | 5 ++---
 net/bridge/netfilter/nft_reject_bridge.c | 3 +--
 net/netfilter/nf_tables_api.c            | 3 +--
 net/netfilter/nft_compat.c               | 6 ++----
 net/netfilter/nft_fib.c                  | 3 +--
 net/netfilter/nft_flow_offload.c         | 3 +--
 net/netfilter/nft_fwd_netdev.c           | 3 +--
 net/netfilter/nft_immediate.c            | 3 +--
 net/netfilter/nft_lookup.c               | 3 +--
 net/netfilter/nft_masq.c                 | 3 +--
 net/netfilter/nft_meta.c                 | 6 ++----
 net/netfilter/nft_nat.c                  | 3 +--
 net/netfilter/nft_osf.c                  | 3 +--
 net/netfilter/nft_queue.c                | 3 +--
 net/netfilter/nft_redir.c                | 3 +--
 net/netfilter/nft_reject.c               | 3 +--
 net/netfilter/nft_reject_inet.c          | 3 +--
 net/netfilter/nft_reject_netdev.c        | 3 +--
 net/netfilter/nft_rt.c                   | 3 +--
 net/netfilter/nft_socket.c               | 3 +--
 net/netfilter/nft_synproxy.c             | 3 +--
 net/netfilter/nft_tproxy.c               | 3 +--
 net/netfilter/nft_xfrm.c                 | 3 +--
 27 files changed, 30 insertions(+), 60 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1cc33d946d41..7cd60ea7cdee 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -961,8 +961,7 @@ struct nft_expr_ops {
 						const struct nft_expr *expr,
 						bool reset);
 	int				(*validate)(const struct nft_ctx *ctx,
-						    const struct nft_expr *expr,
-						    const struct nft_data **data);
+						    const struct nft_expr *expr);
 	bool				(*reduce)(struct nft_regs_track *track,
 						  const struct nft_expr *expr);
 	bool				(*gc)(struct net *net,
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
index 167640b843ef..38cae7113de4 100644
--- a/include/net/netfilter/nft_fib.h
+++ b/include/net/netfilter/nft_fib.h
@@ -21,9 +21,7 @@ nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in)
 int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset);
 int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		 const struct nlattr * const tb[]);
-int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		     const struct nft_data **data);
-
+int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr);
 
 void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
 			const struct nft_pktinfo *pkt);
diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h
index ba1238f12a48..d602263590fe 100644
--- a/include/net/netfilter/nft_meta.h
+++ b/include/net/netfilter/nft_meta.h
@@ -41,8 +41,7 @@ void nft_meta_set_destroy(const struct nft_ctx *ctx,
 			  const struct nft_expr *expr);
 
 int nft_meta_set_validate(const struct nft_ctx *ctx,
-			  const struct nft_expr *expr,
-			  const struct nft_data **data);
+			  const struct nft_expr *expr);
 
 bool nft_meta_get_reduce(struct nft_regs_track *track,
 			 const struct nft_expr *expr);
diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h
index 6d9ba62efd75..19060212988a 100644
--- a/include/net/netfilter/nft_reject.h
+++ b/include/net/netfilter/nft_reject.h
@@ -15,8 +15,7 @@ struct nft_reject {
 extern const struct nla_policy nft_reject_policy[];
 
 int nft_reject_validate(const struct nft_ctx *ctx,
-			const struct nft_expr *expr,
-			const struct nft_data **data);
+			const struct nft_expr *expr);
 
 int nft_reject_init(const struct nft_ctx *ctx,
 		    const struct nft_expr *expr,
diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c
index 4d8e15927217..d12a221366d6 100644
--- a/net/bridge/netfilter/nft_meta_bridge.c
+++ b/net/bridge/netfilter/nft_meta_bridge.c
@@ -168,8 +168,7 @@ static bool nft_meta_bridge_set_reduce(struct nft_regs_track *track,
 }
 
 static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx,
-					const struct nft_expr *expr,
-					const struct nft_data **data)
+					const struct nft_expr *expr)
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
 	unsigned int hooks;
@@ -179,7 +178,7 @@ static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx,
 		hooks = 1 << NF_BR_PRE_ROUTING;
 		break;
 	default:
-		return nft_meta_set_validate(ctx, expr, data);
+		return nft_meta_set_validate(ctx, expr);
 	}
 
 	return nft_chain_validate_hooks(ctx->chain, hooks);
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 71b54fed7263..1cb5c16e97b7 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -170,8 +170,7 @@ out:
 }
 
 static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
+				      const struct nft_expr *expr)
 {
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) |
 						    (1 << NF_BR_LOCAL_IN));
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 904f2e25b4a4..b6547fe22bd8 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3886,7 +3886,6 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r
 int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 {
 	struct nft_expr *expr, *last;
-	const struct nft_data *data;
 	struct nft_rule *rule;
 	int err;
 
@@ -3907,7 +3906,7 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 			/* This may call nft_chain_validate() recursively,
 			 * callers that do so must increment ctx->level.
 			 */
-			err = expr->ops->validate(ctx, expr, &data);
+			err = expr->ops->validate(ctx, expr);
 			if (err < 0)
 				return err;
 		}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index d3d11dede545..52cdfee17f73 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -350,8 +350,7 @@ nla_put_failure:
 }
 
 static int nft_target_validate(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr,
-			       const struct nft_data **data)
+			       const struct nft_expr *expr)
 {
 	struct xt_target *target = expr->ops->data;
 	unsigned int hook_mask = 0;
@@ -611,8 +610,7 @@ static int nft_match_large_dump(struct sk_buff *skb,
 }
 
 static int nft_match_validate(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nft_data **data)
+			      const struct nft_expr *expr)
 {
 	struct xt_match *match = expr->ops->data;
 	unsigned int hook_mask = 0;
diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c
index b58f62195ff3..96e02a83c045 100644
--- a/net/netfilter/nft_fib.c
+++ b/net/netfilter/nft_fib.c
@@ -26,8 +26,7 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = {
 };
 EXPORT_SYMBOL(nft_fib_policy);
 
-int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		     const struct nft_data **data)
+int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	const struct nft_fib *priv = nft_expr_priv(expr);
 	unsigned int hooks;
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index ab9576098701..9dcd1548df9d 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -380,8 +380,7 @@ out:
 }
 
 static int nft_flow_offload_validate(const struct nft_ctx *ctx,
-				     const struct nft_expr *expr,
-				     const struct nft_data **data)
+				     const struct nft_expr *expr)
 {
 	unsigned int hook_mask = (1 << NF_INET_FORWARD);
 
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index c83a794025f9..152a9fb4d23a 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -204,8 +204,7 @@ nla_put_failure:
 }
 
 static int nft_fwd_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
+			    const struct nft_expr *expr)
 {
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS) |
 						    (1 << NF_NETDEV_EGRESS));
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index ac2422c215e5..02ee5fb69871 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -244,8 +244,7 @@ nla_put_failure:
 }
 
 static int nft_immediate_validate(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr,
-				  const struct nft_data **d)
+				  const struct nft_expr *expr)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
 	struct nft_ctx *pctx = (struct nft_ctx *)ctx;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 580e4b1deb9b..63ef832b8aa7 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -206,8 +206,7 @@ nla_put_failure:
 }
 
 static int nft_lookup_validate(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr,
-			       const struct nft_data **d)
+			       const struct nft_expr *expr)
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	struct nft_set_iter iter;
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index cb43c72a8c2a..868bd4d73555 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -27,8 +27,7 @@ static const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
 };
 
 static int nft_masq_validate(const struct nft_ctx *ctx,
-			     const struct nft_expr *expr,
-			     const struct nft_data **data)
+			     const struct nft_expr *expr)
 {
 	int err;
 
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 0214ad1ced2f..8c8eb14d647b 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -581,8 +581,7 @@ static int nft_meta_get_validate_xfrm(const struct nft_ctx *ctx)
 }
 
 static int nft_meta_get_validate(const struct nft_ctx *ctx,
-				 const struct nft_expr *expr,
-				 const struct nft_data **data)
+				 const struct nft_expr *expr)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 
@@ -600,8 +599,7 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx,
 }
 
 int nft_meta_set_validate(const struct nft_ctx *ctx,
-			  const struct nft_expr *expr,
-			  const struct nft_data **data)
+			  const struct nft_expr *expr)
 {
 	struct nft_meta *priv = nft_expr_priv(expr);
 	unsigned int hooks;
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 983dd937fe02..6e21f72c5b57 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -137,8 +137,7 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = {
 };
 
 static int nft_nat_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
+			    const struct nft_expr *expr)
 {
 	struct nft_nat *priv = nft_expr_priv(expr);
 	int err;
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index 7fec57ff736f..1c0b493ef0a9 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -108,8 +108,7 @@ nla_put_failure:
 }
 
 static int nft_osf_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
+			    const struct nft_expr *expr)
 {
 	unsigned int hooks;
 
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index 44e6817e6e29..344fe311878f 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -69,8 +69,7 @@ static void nft_queue_sreg_eval(const struct nft_expr *expr,
 }
 
 static int nft_queue_validate(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nft_data **data)
+			      const struct nft_expr *expr)
 {
 	static const unsigned int supported_hooks = ((1 << NF_INET_PRE_ROUTING) |
 						     (1 << NF_INET_LOCAL_IN) |
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 6568cc264078..95eedad85c83 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -27,8 +27,7 @@ static const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
 };
 
 static int nft_redir_validate(const struct nft_ctx *ctx,
-			      const struct nft_expr *expr,
-			      const struct nft_data **data)
+			      const struct nft_expr *expr)
 {
 	int err;
 
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index ed2e668474d6..196a92c7ea09 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -24,8 +24,7 @@ const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
 EXPORT_SYMBOL_GPL(nft_reject_policy);
 
 int nft_reject_validate(const struct nft_ctx *ctx,
-			const struct nft_expr *expr,
-			const struct nft_data **data)
+			const struct nft_expr *expr)
 {
 	return nft_chain_validate_hooks(ctx->chain,
 					(1 << NF_INET_LOCAL_IN) |
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index 973fa31a9dd6..49020e67304a 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -61,8 +61,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 }
 
 static int nft_reject_inet_validate(const struct nft_ctx *ctx,
-				    const struct nft_expr *expr,
-				    const struct nft_data **data)
+				    const struct nft_expr *expr)
 {
 	return nft_chain_validate_hooks(ctx->chain,
 					(1 << NF_INET_LOCAL_IN) |
diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c
index 7865cd8b11bb..2558ce1505d9 100644
--- a/net/netfilter/nft_reject_netdev.c
+++ b/net/netfilter/nft_reject_netdev.c
@@ -145,8 +145,7 @@ out:
 }
 
 static int nft_reject_netdev_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
+				      const struct nft_expr *expr)
 {
 	return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS));
 }
diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c
index 14d88394bcb7..dc50b9a5bd68 100644
--- a/net/netfilter/nft_rt.c
+++ b/net/netfilter/nft_rt.c
@@ -160,8 +160,7 @@ nla_put_failure:
 	return -1;
 }
 
-static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			   const struct nft_data **data)
+static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	const struct nft_rt *priv = nft_expr_priv(expr);
 	unsigned int hooks;
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index f30163e2ca62..947566dba1ea 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -239,8 +239,7 @@ static bool nft_socket_reduce(struct nft_regs_track *track,
 }
 
 static int nft_socket_validate(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr,
-			       const struct nft_data **data)
+			       const struct nft_expr *expr)
 {
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c
index 1d737f89dfc1..5d3e51825985 100644
--- a/net/netfilter/nft_synproxy.c
+++ b/net/netfilter/nft_synproxy.c
@@ -248,8 +248,7 @@ static void nft_synproxy_eval(const struct nft_expr *expr,
 }
 
 static int nft_synproxy_validate(const struct nft_ctx *ctx,
-				 const struct nft_expr *expr,
-				 const struct nft_data **data)
+				 const struct nft_expr *expr)
 {
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index 1b691393d8b1..50481280abd2 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -313,8 +313,7 @@ static int nft_tproxy_dump(struct sk_buff *skb,
 }
 
 static int nft_tproxy_validate(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr,
-			       const struct nft_data **data)
+			       const struct nft_expr *expr)
 {
 	if (ctx->family != NFPROTO_IPV4 &&
 	    ctx->family != NFPROTO_IPV6 &&
diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c
index 1c866757db55..8a07b46cc8fb 100644
--- a/net/netfilter/nft_xfrm.c
+++ b/net/netfilter/nft_xfrm.c
@@ -229,8 +229,7 @@ static int nft_xfrm_get_dump(struct sk_buff *skb,
 	return 0;
 }
 
-static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-			     const struct nft_data **data)
+static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	const struct nft_xfrm *priv = nft_expr_priv(expr);
 	unsigned int hooks;
-- 
cgit v1.3-3-g829e


From 85dfb34bb7d24c4585fa6a8186c3bf207470ecd7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 28 Aug 2024 21:30:16 +0100
Subject: netfilter: nf_tables: Correct spelling in nf_tables.h

Correct spelling in nf_tables.h.
As reported by codespell.

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 7cd60ea7cdee..02626ad17e99 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -687,7 +687,7 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
  *	@NFT_SET_EXT_TIMEOUT: element timeout
  *	@NFT_SET_EXT_EXPIRATION: element expiration time
  *	@NFT_SET_EXT_USERDATA: user data associated with the element
- *	@NFT_SET_EXT_EXPRESSIONS: expressions assiciated with the element
+ *	@NFT_SET_EXT_EXPRESSIONS: expressions associated with the element
  *	@NFT_SET_EXT_OBJREF: stateful object reference associated with element
  *	@NFT_SET_EXT_NUM: number of extension types
  */
-- 
cgit v1.3-3-g829e


From c362646b6fc15009219020c443f5256190be6436 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Fri, 30 Aug 2024 18:23:00 +0100
Subject: netfilter: nf_tables: Add missing Kernel doc

- Add missing documentation of struct field and enum items.
- Add missing documentation of function parameter.

Flagged by ./scripts/kernel-doc -none.

No functional change intended.
Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 2 ++
 include/net/netfilter/nf_tproxy.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 02626ad17e99..c302b396e1a7 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -209,6 +209,7 @@ static inline void nft_data_copy(u32 *dst, const struct nft_data *src,
  *	@family: protocol family
  *	@level: depth of the chains
  *	@report: notify via unicast netlink message
+ *	@reg_inited: bitmap of initialised registers
  */
 struct nft_ctx {
 	struct net			*net;
@@ -313,6 +314,7 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv)
 /**
  * enum nft_iter_type - nftables set iterator type
  *
+ * @NFT_ITER_UNSPEC: unspecified, to catch errors
  * @NFT_ITER_READ: read-only iteration over set elements
  * @NFT_ITER_UPDATE: iteration under mutex to update set element state
  */
diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h
index faa108b1ba67..5adf6fda11e8 100644
--- a/include/net/netfilter/nf_tproxy.h
+++ b/include/net/netfilter/nf_tproxy.h
@@ -36,6 +36,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr);
 
 /**
  * nf_tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections
+ * @net:	The network namespace.
  * @skb:	The skb being processed.
  * @laddr:	IPv4 address to redirect to or zero.
  * @lport:	TCP port to redirect to or zero.
-- 
cgit v1.3-3-g829e


From beb5a9bea8239cdf4adf6b62672e30db3e9fa5ce Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 29 Aug 2024 14:33:36 +0200
Subject: netdevice: convert private flags > BIT(31) to bitfields

Make dev->priv_flags `u32` back and define bits higher than 31 as
bitfield booleans as per Jakub's suggestion. This simplifies code
which accesses these bits with no optimization loss (testb both
before/after), allows to not extend &netdev_priv_flags each time,
but also scales better as bits > 63 in the future would only add
a new u64 to the structure with no complications, comparing to
that extending ::priv_flags would require converting it to a bitmap.
Note that I picked `unsigned long :1` to not lose any potential
optimizations comparing to `bool :1` etc.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../networking/net_cachelines/net_device.rst       |  4 +++-
 .../net/ethernet/microchip/lan966x/lan966x_main.c  |  2 +-
 drivers/net/macvlan.c                              |  3 ++-
 drivers/net/vxlan/vxlan_core.c                     |  3 ++-
 include/linux/netdevice.h                          | 28 ++++++++++++++--------
 net/8021q/vlanproc.c                               |  4 ++--
 net/core/dev.c                                     |  4 ++--
 net/core/dev_ioctl.c                               |  9 ++++---
 net/core/rtnetlink.c                               |  2 +-
 9 files changed, 35 insertions(+), 24 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index a0e0fab8161a..1fe3cdfe3582 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -7,6 +7,7 @@ net_device struct fast path usage breakdown
 
 Type                                Name                    fastpath_tx_access  fastpath_rx_access  Comments
 ..struct                            ..net_device                                                    
+unsigned_long:32                    priv_flags              read_mostly         -                   __dev_queue_xmit(tx)
 char                                name[16]                -                   -                   
 struct_netdev_name_node*            name_node                                                       
 struct_dev_ifalias*                 ifalias                                                         
@@ -23,7 +24,6 @@ struct_list_head                    ptype_specific
 struct                              adj_list                                                        
 unsigned_int                        flags                   read_mostly         read_mostly         __dev_queue_xmit,__dev_xmit_skb,ip6_output,__ip6_finish_output(tx);ip6_rcv_core(rx)
 xdp_features_t                      xdp_features                                                    
-unsigned_long_long                  priv_flags              read_mostly         -                   __dev_queue_xmit(tx)
 struct_net_device_ops*              netdev_ops              read_mostly         -                   netdev_core_pick_tx,netdev_start_xmit(tx)
 struct_xdp_metadata_ops*            xdp_metadata_ops                                                
 int                                 ifindex                 -                   read_mostly         ip6_rcv_core
@@ -163,6 +163,8 @@ struct_lock_class_key*              qdisc_tx_busylock
 bool                                proto_down                                                      
 unsigned:1                          wol_enabled                                                     
 unsigned:1                          threaded                -                   -                   napi_poll(napi_enable,dev_set_threaded)
+unsigned_long:1                     see_all_hwtstamp_requests                                       
+unsigned_long:1                     change_proto_down                                               
 struct_list_head                    net_notifier_list                                               
 struct_macsec_ops*                  macsec_ops                                                      
 struct_udp_tunnel_nic_info*         udp_tunnel_nic_info                                             
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index ec672af12e25..534d4716d5f7 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -816,7 +816,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 			 NETIF_F_HW_VLAN_STAG_TX |
 			 NETIF_F_HW_TC;
 	dev->hw_features |= NETIF_F_HW_TC;
-	dev->priv_flags |= IFF_SEE_ALL_HWTSTAMP_REQUESTS;
+	dev->see_all_hwtstamp_requests = true;
 	dev->needed_headroom = IFH_LEN_BYTES;
 
 	eth_hw_addr_gen(dev, lan966x->base_mac, p + 1);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 24298a33e0e9..b45f137f365e 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1213,7 +1213,8 @@ void macvlan_common_setup(struct net_device *dev)
 	dev->max_mtu		= ETH_MAX_MTU;
 	dev->priv_flags	       &= ~IFF_TX_SKB_SHARING;
 	netif_keep_dst(dev);
-	dev->priv_flags	       |= IFF_UNICAST_FLT | IFF_CHANGE_PROTO_DOWN;
+	dev->priv_flags	       |= IFF_UNICAST_FLT;
+	dev->change_proto_down	= true;
 	dev->netdev_ops		= &macvlan_netdev_ops;
 	dev->needs_free_netdev	= true;
 	dev->priv_destructor	= macvlan_dev_free;
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 34391c18bba7..4a54dd1950c1 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -3331,7 +3331,8 @@ static void vxlan_setup(struct net_device *dev)
 	dev->hw_features |= NETIF_F_RXCSUM;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
 	netif_keep_dst(dev);
-	dev->priv_flags |= IFF_NO_QUEUE | IFF_CHANGE_PROTO_DOWN;
+	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->change_proto_down = true;
 
 	/* MTU range: 68 - 65535 */
 	dev->min_mtu = ETH_MIN_MTU;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fce70990b209..d6f35c9d8580 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1613,7 +1613,8 @@ struct net_device_ops {
  * userspace; this means that the order of these flags can change
  * during any kernel release.
  *
- * You should have a pretty good reason to be extending these flags.
+ * You should add bitfield booleans after either net_device::priv_flags
+ * (hotpath) or ::threaded (slowpath) instead of extending these flags.
  *
  * @IFF_802_1Q_VLAN: 802.1Q VLAN device
  * @IFF_EBRIDGE: Ethernet bridging device
@@ -1652,10 +1653,6 @@ struct net_device_ops {
  * @IFF_NO_ADDRCONF: prevent ipv6 addrconf
  * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
  *	skb_headlen(skb) == 0 (data starts from frag0)
- * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN
- * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to
- *	ndo_hwtstamp_set() for all timestamp requests regardless of source,
- *	even if those aren't HWTSTAMP_SOURCE_NETDEV.
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1690,8 +1687,6 @@ enum netdev_priv_flags {
 	IFF_L3MDEV_RX_HANDLER		= 1<<29,
 	IFF_NO_ADDRCONF			= BIT_ULL(30),
 	IFF_TX_SKB_NO_LINEAR		= BIT_ULL(31),
-	IFF_CHANGE_PROTO_DOWN		= BIT_ULL(32),
-	IFF_SEE_ALL_HWTSTAMP_REQUESTS	= BIT_ULL(33),
 };
 
 /* Specifies the type of the struct net_device::ml_priv pointer */
@@ -1723,6 +1718,9 @@ enum netdev_reg_state {
  *	data with strictly "high-level" data, and it has to know about
  *	almost every data structure used in the INET module.
  *
+ *	@priv_flags:	flags invisible to userspace defined as bits, see
+ *			enum netdev_priv_flags for the definitions
+ *
  *	@name:	This is the first field of the "visible" part of this structure
  *		(i.e. as seen by users in the "Space.c" file).  It is the name
  *		of the interface.
@@ -1789,8 +1787,6 @@ enum netdev_reg_state {
  *
  *	@flags:		Interface flags (a la BSD)
  *	@xdp_features:	XDP capability supported by the device
- *	@priv_flags:	Like 'flags' but invisible to userspace,
- *			see if.h for the definitions
  *	@gflags:	Global flags ( kept as legacy )
  *	@priv_len:	Size of the ->priv flexible array
  *	@priv:		Flexible array containing private data
@@ -1964,6 +1960,12 @@ enum netdev_reg_state {
  *
  *	@threaded:	napi threaded mode is enabled
  *
+ *	@see_all_hwtstamp_requests: device wants to see calls to
+ *			ndo_hwtstamp_set() for all timestamp requests
+ *			regardless of source, even if those aren't
+ *			HWTSTAMP_SOURCE_NETDEV
+ *	@change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
+ *
  *	@net_notifier_list:	List of per-net netdev notifier block
  *				that follow this device when it is moved
  *				to another network namespace.
@@ -2014,7 +2016,9 @@ struct net_device {
 
 	/* TX read-mostly hotpath */
 	__cacheline_group_begin(net_device_read_tx);
-	unsigned long long	priv_flags;
+	struct_group(priv_flags_fast,
+		unsigned long		priv_flags:32;
+	);
 	const struct net_device_ops *netdev_ops;
 	const struct header_ops *header_ops;
 	struct netdev_queue	*_tx;
@@ -2350,6 +2354,10 @@ struct net_device {
 	bool			proto_down;
 	bool			threaded;
 
+	/* priv_flags_slow, ungrouped to save space */
+	unsigned long		see_all_hwtstamp_requests:1;
+	unsigned long		change_proto_down:1;
+
 	struct list_head	net_notifier_list;
 
 #if IS_ENABLED(CONFIG_MACSEC)
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index 87b959da00cd..fa67374bda49 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -238,9 +238,9 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
 
 	stats = dev_get_stats(vlandev, &temp);
 	seq_printf(seq,
-		   "%s  VID: %d	 REORDER_HDR: %i  dev->priv_flags: %llx\n",
+		   "%s  VID: %d	 REORDER_HDR: %i  dev->priv_flags: %x\n",
 		   vlandev->name, vlan->vlan_id,
-		   (int)(vlan->flags & 1), vlandev->priv_flags);
+		   (int)(vlan->flags & 1), (u32)vlandev->priv_flags);
 
 	seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
 	seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
diff --git a/net/core/dev.c b/net/core/dev.c
index 932d67b975f5..56aed88ceadf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9274,7 +9274,7 @@ EXPORT_SYMBOL(netdev_port_same_parent_id);
  */
 int dev_change_proto_down(struct net_device *dev, bool proto_down)
 {
-	if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN))
+	if (!dev->change_proto_down)
 		return -EOPNOTSUPP;
 	if (!netif_device_present(dev))
 		return -ENODEV;
@@ -11930,7 +11930,7 @@ static struct pernet_operations __net_initdata default_device_ops = {
 static void __init net_dev_struct_check(void)
 {
 	/* TX read-mostly hotpath */
-	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 8592c052c0f4..473c437b6b53 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -317,8 +317,7 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
  * should take precedence in front of hardware timestamping provided by the
  * netdev. If the netdev driver needs to perform specific actions even for PHY
  * timestamping to work properly (a switch port must trap the timestamped
- * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in
- * dev->priv_flags.
+ * frames and not forward them), it must set dev->see_all_hwtstamp_requests.
  */
 int dev_set_hwtstamp_phylib(struct net_device *dev,
 			    struct kernel_hwtstamp_config *cfg,
@@ -332,13 +331,13 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 
 	cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV;
 
-	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+	if (phy_ts && dev->see_all_hwtstamp_requests) {
 		err = ops->ndo_hwtstamp_get(dev, &old_cfg);
 		if (err)
 			return err;
 	}
 
-	if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) {
+	if (!phy_ts || dev->see_all_hwtstamp_requests) {
 		err = ops->ndo_hwtstamp_set(dev, cfg, extack);
 		if (err) {
 			if (extack->_msg)
@@ -347,7 +346,7 @@ int dev_set_hwtstamp_phylib(struct net_device *dev,
 		}
 	}
 
-	if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS))
+	if (phy_ts && dev->see_all_hwtstamp_requests)
 		changed = kernel_hwtstamp_config_changed(&old_cfg, cfg);
 
 	if (phy_ts) {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cd9487a12d1a..f0a520987085 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2724,7 +2724,7 @@ static int do_set_proto_down(struct net_device *dev,
 	bool proto_down;
 	int err;
 
-	if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) {
+	if (!dev->change_proto_down) {
 		NL_SET_ERR_MSG(extack,  "Protodown not supported by device");
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.3-3-g829e


From 00d066a4d4edbe559ba6c35153da71d4b2b8a383 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 29 Aug 2024 14:33:37 +0200
Subject: netdev_features: convert NETIF_F_LLTX to dev->lltx

NETIF_F_LLTX can't be changed via Ethtool and is not a feature,
rather an attribute, very similar to IFF_NO_QUEUE (and hot).
Free one netdev_features_t bit and make it a "hot" private flag.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/net_cachelines/net_device.rst |  1 +
 Documentation/networking/netdev-features.rst           |  8 --------
 Documentation/networking/netdevices.rst                |  4 ++--
 drivers/net/amt.c                                      |  2 +-
 drivers/net/bareudp.c                                  |  2 +-
 drivers/net/bonding/bond_main.c                        |  2 +-
 drivers/net/dummy.c                                    |  3 ++-
 drivers/net/ethernet/chelsio/cxgb/cxgb2.c              |  3 ++-
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c         |  3 ++-
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c       |  3 ++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c         |  3 ++-
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c      |  3 +--
 drivers/net/ethernet/pasemi/pasemi_mac.c               |  5 +++--
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c        |  2 +-
 drivers/net/ethernet/sfc/ef100_rep.c                   |  4 ++--
 drivers/net/ethernet/tehuti/tehuti.c                   |  4 ++--
 drivers/net/ethernet/tehuti/tehuti.h                   |  2 +-
 drivers/net/ethernet/toshiba/spider_net.c              |  3 ++-
 drivers/net/geneve.c                                   |  2 +-
 drivers/net/gtp.c                                      |  2 +-
 drivers/net/hamradio/bpqether.c                        |  2 +-
 drivers/net/ipvlan/ipvlan_main.c                       |  3 ++-
 drivers/net/loopback.c                                 |  2 +-
 drivers/net/macsec.c                                   |  4 ++--
 drivers/net/macvlan.c                                  |  3 ++-
 drivers/net/net_failover.c                             |  2 +-
 drivers/net/netkit.c                                   |  3 ++-
 drivers/net/nlmon.c                                    |  4 ++--
 drivers/net/ppp/ppp_generic.c                          |  2 +-
 drivers/net/rionet.c                                   |  2 +-
 drivers/net/team/team_core.c                           |  2 +-
 drivers/net/tun.c                                      |  5 +++--
 drivers/net/veth.c                                     |  2 +-
 drivers/net/vrf.c                                      |  2 +-
 drivers/net/vsockmon.c                                 |  4 ++--
 drivers/net/vxlan/vxlan_core.c                         |  2 +-
 drivers/net/wireguard/device.c                         |  2 +-
 drivers/staging/octeon/ethernet.c                      |  2 +-
 include/linux/netdev_features.h                        |  6 ++----
 include/linux/netdevice.h                              | 10 +++++++---
 lib/test_bpf.c                                         |  3 +--
 net/8021q/vlan_dev.c                                   |  4 ++--
 net/batman-adv/soft-interface.c                        |  2 +-
 net/bridge/br_device.c                                 |  3 ++-
 net/core/net-sysfs.c                                   |  3 +--
 net/dsa/user.c                                         |  3 ++-
 net/ethtool/common.c                                   |  1 -
 net/hsr/hsr_device.c                                   |  4 ++--
 net/ipv4/ip_gre.c                                      |  4 +++-
 net/ipv4/ip_vti.c                                      |  2 +-
 net/ipv4/ipip.c                                        |  2 +-
 net/ipv6/ip6_gre.c                                     |  4 +++-
 net/ipv6/ip6_tunnel.c                                  |  2 +-
 net/ipv6/sit.c                                         |  2 +-
 net/l2tp/l2tp_eth.c                                    |  2 +-
 net/openvswitch/vport-internal_dev.c                   |  9 +++++----
 net/xfrm/xfrm_interface_core.c                         |  2 +-
 57 files changed, 93 insertions(+), 84 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 1fe3cdfe3582..e55319277074 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -8,6 +8,7 @@ net_device struct fast path usage breakdown
 Type                                Name                    fastpath_tx_access  fastpath_rx_access  Comments
 ..struct                            ..net_device                                                    
 unsigned_long:32                    priv_flags              read_mostly         -                   __dev_queue_xmit(tx)
+unsigned_long:1                     lltx                    read_mostly         -                   HARD_TX_LOCK,HARD_TX_TRYLOCK,HARD_TX_UNLOCK(tx)
 char                                name[16]                -                   -                   
 struct_netdev_name_node*            name_node                                                       
 struct_dev_ifalias*                 ifalias                                                         
diff --git a/Documentation/networking/netdev-features.rst b/Documentation/networking/netdev-features.rst
index d7b15bb64deb..f29d982ebf5d 100644
--- a/Documentation/networking/netdev-features.rst
+++ b/Documentation/networking/netdev-features.rst
@@ -139,14 +139,6 @@ chained skbs (skb->next/prev list).
 Features contained in NETIF_F_SOFT_FEATURES are features of networking
 stack. Driver should not change behaviour based on them.
 
- * LLTX driver (deprecated for hardware drivers)
-
-NETIF_F_LLTX is meant to be used by drivers that don't need locking at all,
-e.g. software tunnels.
-
-This is also used in a few legacy drivers that implement their
-own locking, don't use it for new (hardware) drivers.
-
  * netns-local device
 
 NETIF_F_NETNS_LOCAL is set for devices that are not allowed to move between
diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index c2476917a6c3..857c9784f87e 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -258,11 +258,11 @@ ndo_get_stats:
 ndo_start_xmit:
 	Synchronization: __netif_tx_lock spinlock.
 
-	When the driver sets NETIF_F_LLTX in dev->features this will be
+	When the driver sets dev->lltx this will be
 	called without holding netif_tx_lock. In this case the driver
 	has to lock by itself when needed.
 	The locking there should also properly protect against
-	set_rx_mode. WARNING: use of NETIF_F_LLTX is deprecated.
+	set_rx_mode. WARNING: use of dev->lltx is deprecated.
 	Don't use it for new drivers.
 
 	Context: Process with BHs disabled or BH (timer),
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 6d15ab3bfbbc..921bbfd72a38 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3098,7 +3098,7 @@ static void amt_link_setup(struct net_device *dev)
 	dev->hard_header_len	= 0;
 	dev->addr_len		= 0;
 	dev->priv_flags		|= IFF_NO_QUEUE;
-	dev->features		|= NETIF_F_LLTX;
+	dev->lltx		= true;
 	dev->features		|= NETIF_F_GSO_SOFTWARE;
 	dev->features		|= NETIF_F_NETNS_LOCAL;
 	dev->hw_features	|= NETIF_F_SG | NETIF_F_HW_CSUM;
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index d5c56ca91b77..6f4de883e872 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -553,7 +553,6 @@ static void bareudp_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &bareudp_type);
 	dev->features    |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST;
 	dev->features    |= NETIF_F_RXCSUM;
-	dev->features    |= NETIF_F_LLTX;
 	dev->features    |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST;
 	dev->hw_features |= NETIF_F_RXCSUM;
@@ -566,6 +565,7 @@ static void bareudp_setup(struct net_device *dev)
 	dev->type = ARPHRD_NONE;
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->lltx = true;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index cb6a694313d5..8ae887cdc231 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5928,7 +5928,7 @@ void bond_setup(struct net_device *bond_dev)
 #endif /* CONFIG_XFRM_OFFLOAD */
 
 	/* don't acquire bond device's netif_tx_lock when transmitting */
-	bond_dev->features |= NETIF_F_LLTX;
+	bond_dev->lltx = true;
 
 	/* By default, we declare the bond to be fully
 	 * VLAN hardware accelerated capable. Special
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index d29b5d7af0d7..e9c5e1e11fa0 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -109,9 +109,10 @@ static void dummy_setup(struct net_device *dev)
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
+	dev->lltx = true;
 	dev->features	|= NETIF_F_SG | NETIF_F_FRAGLIST;
 	dev->features	|= NETIF_F_GSO_SOFTWARE;
-	dev->features	|= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX;
+	dev->features	|= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA;
 	dev->features	|= NETIF_F_GSO_ENCAP_ALL;
 	dev->hw_features |= dev->features;
 	dev->hw_enc_features |= dev->features;
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 7d7d3e0098df..3b7068832f95 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -1034,7 +1034,8 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		netdev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM |
 			NETIF_F_RXCSUM;
 		netdev->features |= NETIF_F_SG | NETIF_F_IP_CSUM |
-			NETIF_F_RXCSUM | NETIF_F_LLTX | NETIF_F_HIGHDMA;
+			NETIF_F_RXCSUM | NETIF_F_HIGHDMA;
+		netdev->lltx = true;
 
 		if (vlan_tso_capable(adapter)) {
 			netdev->features |=
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 5d99cfb4e994..1d0208b5db7d 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -229,7 +229,7 @@ static int dpaa_netdev_init(struct net_device *net_dev,
 	net_dev->max_mtu = dpaa_get_max_mtu();
 
 	net_dev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-				 NETIF_F_LLTX | NETIF_F_RXHASH);
+				 NETIF_F_RXHASH);
 
 	net_dev->hw_features |= NETIF_F_SG | NETIF_F_HIGHDMA;
 	/* The kernels enables GSO automatically, if we declare NETIF_F_SG.
@@ -239,6 +239,7 @@ static int dpaa_netdev_init(struct net_device *net_dev,
 	net_dev->features |= NETIF_F_RXCSUM;
 
 	net_dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	net_dev->lltx = true;
 	/* we do not want shared skbs on TX */
 	net_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 6866807973da..29886a8ba73f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4594,12 +4594,13 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev)
 
 	net_dev->priv_flags |= supported;
 	net_dev->priv_flags &= ~not_supported;
+	net_dev->lltx = true;
 
 	/* Features */
 	net_dev->features = NETIF_F_RXCSUM |
 			    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			    NETIF_F_SG | NETIF_F_HIGHDMA |
-			    NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO;
+			    NETIF_F_HW_TC | NETIF_F_TSO;
 	net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS;
 	net_dev->hw_features = net_dev->features;
 	net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f064789f3240..44d6e125bd6f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1676,9 +1676,10 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 
 	netif_carrier_off(dev);
 
-	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG |
+	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_SG |
 			 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC;
 	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
+	dev->lltx = true;
 
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index eee0bfc41074..227e7a5d712e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -248,7 +248,6 @@ nfp_repr_fix_features(struct net_device *netdev, netdev_features_t features)
 
 	features = netdev_intersect_features(features, lower_features);
 	features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_HW_TC);
-	features |= NETIF_F_LLTX;
 
 	return features;
 }
@@ -386,7 +385,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	netif_set_tso_max_segs(netdev, NFP_NET_LSO_MAX_SEGS);
 
 	netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
-	netdev->features |= NETIF_F_LLTX;
+	netdev->lltx = true;
 
 	if (nfp_app_has_tc(app)) {
 		netdev->features |= NETIF_F_HW_TC;
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index 62ba269da902..cb4e12df7719 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -1699,8 +1699,9 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	netif_napi_add(dev, &mac->napi, pasemi_mac_poll);
 
-	dev->features = NETIF_F_IP_CSUM | NETIF_F_LLTX | NETIF_F_SG |
-			NETIF_F_HIGHDMA | NETIF_F_GSO;
+	dev->features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_HIGHDMA |
+			NETIF_F_GSO;
+	dev->lltx = true;
 
 	mac->dma_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa007, NULL);
 	if (!mac->dma_pdev) {
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index f1e40aade127..4f0ddcedfa97 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -286,7 +286,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev)
 	rmnet_dev->needs_free_netdev = true;
 	rmnet_dev->ethtool_ops = &rmnet_ethtool_ops;
 
-	rmnet_dev->features |= NETIF_F_LLTX;
+	rmnet_dev->lltx = true;
 
 	/* This perm addr will be used as interface identifier by IPv6 */
 	rmnet_dev->addr_assign_type = NET_ADDR_RANDOM;
diff --git a/drivers/net/ethernet/sfc/ef100_rep.c b/drivers/net/ethernet/sfc/ef100_rep.c
index 0b3083ef0ead..e923e1796369 100644
--- a/drivers/net/ethernet/sfc/ef100_rep.c
+++ b/drivers/net/ethernet/sfc/ef100_rep.c
@@ -233,8 +233,8 @@ static struct efx_rep *efx_ef100_rep_create_netdev(struct efx_nic *efx,
 	net_dev->ethtool_ops = &efx_ef100_rep_ethtool_ops;
 	net_dev->min_mtu = EFX_MIN_MTU;
 	net_dev->max_mtu = EFX_MAX_MTU;
-	net_dev->features |= NETIF_F_LLTX;
-	net_dev->hw_features |= NETIF_F_LLTX;
+	net_dev->lltx = true;
+
 	return efv;
 fail1:
 	free_netdev(net_dev);
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index ede5f7890fb4..fc77f424f90b 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1671,7 +1671,7 @@ static netdev_tx_t bdx_tx_transmit(struct sk_buff *skb,
 
 #endif
 #ifdef BDX_LLTX
-	netif_trans_update(ndev); /* NETIF_F_LLTX driver :( */
+	netif_trans_update(ndev); /* dev->lltx driver :( */
 #endif
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += skb->len;
@@ -2019,7 +2019,7 @@ bdx_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		 * set multicast list callback has to use priv->tx_lock.
 		 */
 #ifdef BDX_LLTX
-		ndev->features |= NETIF_F_LLTX;
+		ndev->lltx = true;
 #endif
 		/* MTU range: 60 - 16384 */
 		ndev->min_mtu = ETH_ZLEN;
diff --git a/drivers/net/ethernet/tehuti/tehuti.h b/drivers/net/ethernet/tehuti/tehuti.h
index 909e7296cecf..47a2d3e5f8ed 100644
--- a/drivers/net/ethernet/tehuti/tehuti.h
+++ b/drivers/net/ethernet/tehuti/tehuti.h
@@ -260,7 +260,7 @@ struct bdx_priv {
 	int tx_update_mark;
 	int tx_noupd;
 #endif
-	spinlock_t tx_lock;	/* NETIF_F_LLTX mode */
+	spinlock_t tx_lock;	/* dev->lltx mode */
 
 	/* rarely used */
 	u8 port;
diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c
index 87e67121477c..a4937c18d7cb 100644
--- a/drivers/net/ethernet/toshiba/spider_net.c
+++ b/drivers/net/ethernet/toshiba/spider_net.c
@@ -2277,10 +2277,11 @@ spider_net_setup_netdev(struct spider_net_card *card)
 	netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM;
 	if (SPIDER_NET_RX_CSUM_DEFAULT)
 		netdev->features |= NETIF_F_RXCSUM;
-	netdev->features |= NETIF_F_IP_CSUM | NETIF_F_LLTX;
+	netdev->features |= NETIF_F_IP_CSUM;
 	/* some time: NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 	 *		NETIF_F_HW_VLAN_CTAG_FILTER
 	 */
+	netdev->lltx = true;
 
 	/* MTU range: 64 - 2294 */
 	netdev->min_mtu = SPIDER_NET_MIN_MTU;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 838e85ddec67..7f611c74eb62 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1194,7 +1194,6 @@ static void geneve_setup(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &geneve_type);
 
-	dev->features    |= NETIF_F_LLTX;
 	dev->features    |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST;
 	dev->features    |= NETIF_F_RXCSUM;
 	dev->features    |= NETIF_F_GSO_SOFTWARE;
@@ -1215,6 +1214,7 @@ static void geneve_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
+	dev->lltx = true;
 	eth_hw_addr_random(dev);
 }
 
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 2e94d10348cc..a60bfb1abb7f 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1356,7 +1356,7 @@ static void gtp_link_setup(struct net_device *dev)
 
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	dev->priv_flags	|= IFF_NO_QUEUE;
-	dev->features	|= NETIF_F_LLTX;
+	dev->lltx = true;
 	netif_keep_dst(dev);
 
 	dev->needed_headroom	= LL_MAX_HEADER + GTP_IPV4_MAXLEN;
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 83a16d10eedb..bac1bb69d63a 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -458,7 +458,7 @@ static void bpq_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 
 	dev->flags      = 0;
-	dev->features	= NETIF_F_LLTX;	/* Allow recursion */
+	dev->lltx = true;	/* Allow recursion */
 
 #if IS_ENABLED(CONFIG_AX25)
 	dev->header_ops      = &ax25_header_ops;
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 094f44dac5c8..ee2c3cf4df36 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -114,7 +114,7 @@ static void ipvlan_port_destroy(struct net_device *dev)
 	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL)
 
 #define IPVLAN_ALWAYS_ON \
-	(IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED)
+	(IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_VLAN_CHALLENGED)
 
 #define IPVLAN_FEATURES \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
@@ -141,6 +141,7 @@ static int ipvlan_init(struct net_device *dev)
 	dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES;
 	dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS;
 	dev->hw_enc_features |= dev->features;
+	dev->lltx = true;
 	netif_inherit_tso_max(dev, phy_dev);
 	dev->hard_header_len = phy_dev->hard_header_len;
 
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 2b486e7c749c..bf857782be0f 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -171,6 +171,7 @@ static void gen_lo_setup(struct net_device *dev,
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
+	dev->lltx		= true;
 	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
 	dev->features		= NETIF_F_SG | NETIF_F_FRAGLIST
@@ -179,7 +180,6 @@ static void gen_lo_setup(struct net_device *dev,
 		| NETIF_F_RXCSUM
 		| NETIF_F_SCTP_CRC
 		| NETIF_F_HIGHDMA
-		| NETIF_F_LLTX
 		| NETIF_F_NETNS_LOCAL
 		| NETIF_F_VLAN_CHALLENGED
 		| NETIF_F_LOOPBACK;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 2da70bc3dd86..12d1b205f6d1 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -3550,7 +3550,8 @@ static int macsec_dev_init(struct net_device *dev)
 		return err;
 
 	dev->features = real_dev->features & MACSEC_FEATURES;
-	dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE;
+	dev->features |= NETIF_F_GSO_SOFTWARE;
+	dev->lltx = true;
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 
 	macsec_set_head_tail_room(dev);
@@ -3581,7 +3582,6 @@ static netdev_features_t macsec_fix_features(struct net_device *dev,
 
 	features &= (real_dev->features & MACSEC_FEATURES) |
 		    NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES;
-	features |= NETIF_F_LLTX;
 
 	return features;
 }
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b45f137f365e..cf18e66de142 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -900,7 +900,7 @@ static struct lock_class_key macvlan_netdev_addr_lock_key;
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \
 	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL)
 
-#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX)
+#define ALWAYS_ON_FEATURES ALWAYS_ON_OFFLOADS
 
 #define MACVLAN_FEATURES \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
@@ -932,6 +932,7 @@ static int macvlan_init(struct net_device *dev)
 	dev->vlan_features	= lowerdev->vlan_features & MACVLAN_FEATURES;
 	dev->vlan_features	|= ALWAYS_ON_OFFLOADS;
 	dev->hw_enc_features    |= dev->features;
+	dev->lltx		= true;
 	netif_inherit_tso_max(dev, lowerdev);
 	dev->hard_header_len	= lowerdev->hard_header_len;
 	macvlan_set_lockdep_class(dev);
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index 963d8b4af28d..06728385a35f 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -731,7 +731,7 @@ struct failover *net_failover_create(struct net_device *standby_dev)
 				       IFF_TX_SKB_SHARING);
 
 	/* don't acquire failover netdev's netif_tx_lock when transmitting */
-	failover_dev->features |= NETIF_F_LLTX;
+	failover_dev->lltx = true;
 
 	/* Don't allow failover devices to change network namespaces. */
 	failover_dev->features |= NETIF_F_NETNS_LOCAL;
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 16789cd446e9..79232f5cc088 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -255,11 +255,12 @@ static void netkit_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->lltx = true;
 
 	dev->ethtool_ops = &netkit_ethtool_ops;
 	dev->netdev_ops  = &netkit_netdev_ops;
 
-	dev->features |= netkit_features | NETIF_F_LLTX;
+	dev->features |= netkit_features;
 	dev->hw_features = netkit_features;
 	dev->hw_enc_features = netkit_features;
 	dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index e5a0987a263e..8bfd4ee5a8c4 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -63,13 +63,13 @@ static void nlmon_setup(struct net_device *dev)
 {
 	dev->type = ARPHRD_NETLINK;
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->lltx = true;
 
 	dev->netdev_ops	= &nlmon_ops;
 	dev->ethtool_ops = &nlmon_ethtool_ops;
 	dev->needs_free_netdev = true;
 
-	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST |
-			NETIF_F_HIGHDMA | NETIF_F_LLTX;
+	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
 	dev->flags = IFF_NOARP;
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_LSTATS;
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index eb9acfcaeb09..4b2971e2bf48 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1631,7 +1631,7 @@ static void ppp_setup(struct net_device *dev)
 	dev->netdev_ops = &ppp_netdev_ops;
 	SET_NETDEV_DEVTYPE(dev, &ppp_type);
 
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 
 	dev->hard_header_len = PPP_HDRLEN;
 	dev->mtu = PPP_MRU;
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 4eececc94513..318a0ef1af50 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -515,7 +515,7 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev)
 	/* MTU range: 68 - 4082 */
 	ndev->min_mtu = ETH_MIN_MTU;
 	ndev->max_mtu = RIONET_MAX_MTU;
-	ndev->features = NETIF_F_LLTX;
+	ndev->lltx = true;
 	SET_NETDEV_DEV(ndev, &mport->dev);
 	ndev->ethtool_ops = &rionet_ethtool_ops;
 
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index ab1935a4aa2c..1d1bad3cedc2 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -2189,8 +2189,8 @@ static void team_setup(struct net_device *dev)
 	 * Let this up to underlay drivers.
 	 */
 	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
+	dev->lltx = true;
 
-	dev->features |= NETIF_F_LLTX;
 	dev->features |= NETIF_F_GRO;
 
 	/* Don't allow team devices to change network namespaces. */
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 1d06c560c5e6..a645c36f2cee 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -990,10 +990,11 @@ static int tun_net_init(struct net_device *dev)
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			   TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_STAG_TX;
-	dev->features = dev->hw_features | NETIF_F_LLTX;
+	dev->features = dev->hw_features;
 	dev->vlan_features = dev->features &
 			     ~(NETIF_F_HW_VLAN_CTAG_TX |
 			       NETIF_F_HW_VLAN_STAG_TX);
+	dev->lltx = true;
 
 	tun->flags = (tun->flags & ~TUN_FEATURES) |
 		      (ifr->ifr_flags & TUN_FEATURES);
@@ -1129,7 +1130,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	/* NETIF_F_LLTX requires to do our own update of trans_start */
+	/* dev->lltx requires to do our own update of trans_start */
 	queue = netdev_get_tx_queue(dev, txq);
 	txq_trans_cond_update(queue);
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 34499b91a8bd..18148e068aa0 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1697,11 +1697,11 @@ static void veth_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->priv_flags |= IFF_PHONY_HEADROOM;
 	dev->priv_flags |= IFF_DISABLE_NETPOLL;
+	dev->lltx = true;
 
 	dev->netdev_ops = &veth_netdev_ops;
 	dev->xdp_metadata_ops = &veth_xdp_metadata_ops;
 	dev->ethtool_ops = &veth_ethtool_ops;
-	dev->features |= NETIF_F_LLTX;
 	dev->features |= VETH_FEATURES;
 	dev->vlan_features = dev->features &
 			     ~(NETIF_F_HW_VLAN_CTAG_TX |
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index a900908eb24a..b1d4ef538995 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1635,7 +1635,7 @@ static void vrf_setup(struct net_device *dev)
 	eth_hw_addr_random(dev);
 
 	/* don't acquire vrf device's netif_tx_lock when transmitting */
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 
 	/* don't allow vrf devices to change network namespaces. */
 	dev->features |= NETIF_F_NETNS_LOCAL;
diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c
index 4c260074c091..53fb76d574c6 100644
--- a/drivers/net/vsockmon.c
+++ b/drivers/net/vsockmon.c
@@ -83,13 +83,13 @@ static void vsockmon_setup(struct net_device *dev)
 {
 	dev->type = ARPHRD_VSOCKMON;
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->lltx = true;
 
 	dev->netdev_ops	= &vsockmon_ops;
 	dev->ethtool_ops = &vsockmon_ethtool_ops;
 	dev->needs_free_netdev = true;
 
-	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST |
-			NETIF_F_HIGHDMA | NETIF_F_LLTX;
+	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
 
 	dev->flags = IFF_NOARP;
 
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 4a54dd1950c1..53dcb9fffc04 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -3321,7 +3321,6 @@ static void vxlan_setup(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	SET_NETDEV_DEVTYPE(dev, &vxlan_type);
 
-	dev->features	|= NETIF_F_LLTX;
 	dev->features	|= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_FRAGLIST;
 	dev->features   |= NETIF_F_RXCSUM;
 	dev->features   |= NETIF_F_GSO_SOFTWARE;
@@ -3333,6 +3332,7 @@ static void vxlan_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->change_proto_down = true;
+	dev->lltx = true;
 
 	/* MTU range: 68 - 65535 */
 	dev->min_mtu = ETH_MIN_MTU;
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 3feb36ee5bfb..45e9b908dbfb 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -289,7 +289,7 @@ static void wg_setup(struct net_device *dev)
 	dev->type = ARPHRD_NONE;
 	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
 	dev->priv_flags |= IFF_NO_QUEUE;
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 	dev->features |= WG_NETDEV_FEATURES;
 	dev->hw_features |= WG_NETDEV_FEATURES;
 	dev->hw_enc_features |= WG_NETDEV_FEATURES;
diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c
index 9eee28f2940c..a5e99cc78a45 100644
--- a/drivers/staging/octeon/ethernet.c
+++ b/drivers/staging/octeon/ethernet.c
@@ -425,7 +425,7 @@ int cvm_oct_common_init(struct net_device *dev)
 		dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM;
 
 	/* We do our own locking, Linux doesn't need to */
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 	dev->ethtool_ops = &cvm_oct_ethtool_ops;
 
 	cvm_oct_set_mac_filter(dev);
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 7c2d77d75a88..a2e20b517584 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -24,8 +24,7 @@ enum {
 	NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */
 	NETIF_F_VLAN_CHALLENGED_BIT,	/* Device cannot handle VLAN packets */
 	NETIF_F_GSO_BIT,		/* Enable software GSO. */
-	NETIF_F_LLTX_BIT,		/* LockLess TX - deprecated. Please */
-					/* do not use LLTX in new drivers */
+	__UNUSED_NETIF_F_12,
 	NETIF_F_NETNS_LOCAL_BIT,	/* Does not change network namespaces */
 	NETIF_F_GRO_BIT,		/* Generic receive offload */
 	NETIF_F_LRO_BIT,		/* large receive offload */
@@ -120,7 +119,6 @@ enum {
 #define NETIF_F_HW_VLAN_CTAG_TX	__NETIF_F(HW_VLAN_CTAG_TX)
 #define NETIF_F_IP_CSUM		__NETIF_F(IP_CSUM)
 #define NETIF_F_IPV6_CSUM	__NETIF_F(IPV6_CSUM)
-#define NETIF_F_LLTX		__NETIF_F(LLTX)
 #define NETIF_F_LOOPBACK	__NETIF_F(LOOPBACK)
 #define NETIF_F_LRO		__NETIF_F(LRO)
 #define NETIF_F_NETNS_LOCAL	__NETIF_F(NETNS_LOCAL)
@@ -193,7 +191,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
 #define NETIF_F_NEVER_CHANGE	(NETIF_F_VLAN_CHALLENGED | \
-				 NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+				 NETIF_F_NETNS_LOCAL)
 
 /* remember that ((t)1 << t_BITS) is undefined in C99 */
 #define NETIF_F_ETHTOOL_BITS	((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d6f35c9d8580..e22ca5e07490 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1720,6 +1720,9 @@ enum netdev_reg_state {
  *
  *	@priv_flags:	flags invisible to userspace defined as bits, see
  *			enum netdev_priv_flags for the definitions
+ *	@lltx:		device supports lockless Tx. Deprecated for real HW
+ *			drivers. Mainly used by logical interfaces, such as
+ *			bonding and tunnels
  *
  *	@name:	This is the first field of the "visible" part of this structure
  *		(i.e. as seen by users in the "Space.c" file).  It is the name
@@ -2018,6 +2021,7 @@ struct net_device {
 	__cacheline_group_begin(net_device_read_tx);
 	struct_group(priv_flags_fast,
 		unsigned long		priv_flags:32;
+		unsigned long		lltx:1;
 	);
 	const struct net_device_ops *netdev_ops;
 	const struct header_ops *header_ops;
@@ -4433,7 +4437,7 @@ static inline void netif_tx_unlock_bh(struct net_device *dev)
 }
 
 #define HARD_TX_LOCK(dev, txq, cpu) {			\
-	if ((dev->features & NETIF_F_LLTX) == 0) {	\
+	if (!(dev)->lltx) {				\
 		__netif_tx_lock(txq, cpu);		\
 	} else {					\
 		__netif_tx_acquire(txq);		\
@@ -4441,12 +4445,12 @@ static inline void netif_tx_unlock_bh(struct net_device *dev)
 }
 
 #define HARD_TX_TRYLOCK(dev, txq)			\
-	(((dev->features & NETIF_F_LLTX) == 0) ?	\
+	(!(dev)->lltx ?					\
 		__netif_tx_trylock(txq) :		\
 		__netif_tx_acquire(txq))
 
 #define HARD_TX_UNLOCK(dev, txq) {			\
-	if ((dev->features & NETIF_F_LLTX) == 0) {	\
+	if (!(dev)->lltx) {				\
 		__netif_tx_unlock(txq);			\
 	} else {					\
 		__netif_tx_release(txq);		\
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index ca4b0eea81a2..fa5edd6ef7f7 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -15077,8 +15077,7 @@ static struct skb_segment_test skb_segment_tests[] __initconst = {
 		.build_skb = build_test_skb_linear_no_head_frag,
 		.features = NETIF_F_SG | NETIF_F_FRAGLIST |
 			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_GSO |
-			    NETIF_F_LLTX | NETIF_F_GRO |
-			    NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
+			    NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
 			    NETIF_F_HW_VLAN_STAG_TX
 	}
 };
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 217be32426b5..3ca485537d77 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -569,7 +569,8 @@ static int vlan_dev_init(struct net_device *dev)
 	if (real_dev->vlan_features & NETIF_F_HW_MACSEC)
 		dev->hw_features |= NETIF_F_HW_MACSEC;
 
-	dev->features |= dev->hw_features | NETIF_F_LLTX;
+	dev->features |= dev->hw_features;
+	dev->lltx = true;
 	netif_inherit_tso_max(dev, real_dev);
 	if (dev->features & NETIF_F_VLAN_FEATURES)
 		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
@@ -655,7 +656,6 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
 		lower_features |= NETIF_F_HW_CSUM;
 	features = netdev_intersect_features(features, lower_features);
 	features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE);
-	features |= NETIF_F_LLTX;
 
 	return features;
 }
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 30ecbc2ef1fd..e791a73ef901 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1021,8 +1021,8 @@ static void batadv_softif_init_early(struct net_device *dev)
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = batadv_softif_free;
 	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL;
-	dev->features |= NETIF_F_LLTX;
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->lltx = true;
 
 	/* can't call min_mtu, because the needed variables
 	 * have not been initialized yet
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index fb1115857e49..a6d25113dfb1 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -487,8 +487,9 @@ void br_dev_setup(struct net_device *dev)
 	dev->ethtool_ops = &br_ethtool_ops;
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
+	dev->lltx = true;
 
-	dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL |
+	dev->features = COMMON_FEATURES | NETIF_F_NETNS_LOCAL |
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_STAG_TX;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 444f23e74f8e..01a9fb54ef42 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1764,8 +1764,7 @@ static const struct kobj_type netdev_queue_ktype = {
 
 static bool netdev_uses_bql(const struct net_device *dev)
 {
-	if (dev->features & NETIF_F_LLTX ||
-	    dev->priv_flags & IFF_NO_QUEUE)
+	if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE))
 		return false;
 
 	return IS_ENABLED(CONFIG_BQL);
diff --git a/net/dsa/user.c b/net/dsa/user.c
index f5adfa1d978a..74eda9b30608 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -2642,11 +2642,12 @@ void dsa_user_setup_tagger(struct net_device *user)
 
 	user->features = conduit->vlan_features | NETIF_F_HW_TC;
 	user->hw_features |= NETIF_F_HW_TC;
-	user->features |= NETIF_F_LLTX;
 	if (user->needed_tailroom)
 		user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST);
 	if (ds->needs_standalone_vlan_filtering)
 		user->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	user->lltx = true;
 }
 
 int dsa_user_suspend(struct net_device *user_dev)
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 7257ae272296..447fc80e1b00 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -25,7 +25,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter",
 	[NETIF_F_VLAN_CHALLENGED_BIT] =  "vlan-challenged",
 	[NETIF_F_GSO_BIT] =              "tx-generic-segmentation",
-	[NETIF_F_LLTX_BIT] =             "tx-lockless",
 	[NETIF_F_NETNS_LOCAL_BIT] =      "netns-local",
 	[NETIF_F_GRO_BIT] =              "rx-gro",
 	[NETIF_F_GRO_HW_BIT] =           "rx-gro-hw",
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index e4cc6b78dcfc..d4c783076662 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -554,6 +554,8 @@ void hsr_dev_setup(struct net_device *dev)
 	dev->netdev_ops = &hsr_device_ops;
 	SET_NETDEV_DEVTYPE(dev, &hsr_type);
 	dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
+	/* Prevent recursive tx locking */
+	dev->lltx = true;
 
 	dev->needs_free_netdev = true;
 
@@ -563,8 +565,6 @@ void hsr_dev_setup(struct net_device *dev)
 
 	dev->features = dev->hw_features;
 
-	/* Prevent recursive tx locking */
-	dev->features |= NETIF_F_LLTX;
 	/* VLAN on top of HSR needs testing and probably some work on
 	 * hsr_header_create() etc.
 	 */
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index ba205473522e..b54c41f3ae3c 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -996,7 +996,7 @@ static void __gre_tunnel_init(struct net_device *dev)
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
 	dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph);
 
-	dev->features		|= GRE_FEATURES | NETIF_F_LLTX;
+	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 
 	/* TCP offload with GRE SEQ is not supported, nor can we support 2
@@ -1010,6 +1010,8 @@ static void __gre_tunnel_init(struct net_device *dev)
 
 	dev->features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+
+	dev->lltx = true;
 }
 
 static int ipgre_tunnel_init(struct net_device *dev)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 14536da9f5dc..f0b4419cef34 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -443,7 +443,7 @@ static int vti_tunnel_init(struct net_device *dev)
 
 	dev->flags		= IFF_NOARP;
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_LLTX;
+	dev->lltx		= true;
 	netif_keep_dst(dev);
 
 	return ip_tunnel_init(dev);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 923a2ef68c2f..dc0db5895e0e 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -378,7 +378,7 @@ static void ipip_tunnel_setup(struct net_device *dev)
 	dev->type		= ARPHRD_TUNNEL;
 	dev->flags		= IFF_NOARP;
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_LLTX;
+	dev->lltx		= true;
 	netif_keep_dst(dev);
 
 	dev->features		|= IPIP_FEATURES;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3942bd2ade78..08beab638bda 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1471,7 +1471,7 @@ static void ip6gre_tnl_init_features(struct net_device *dev)
 {
 	struct ip6_tnl *nt = netdev_priv(dev);
 
-	dev->features		|= GRE6_FEATURES | NETIF_F_LLTX;
+	dev->features		|= GRE6_FEATURES;
 	dev->hw_features	|= GRE6_FEATURES;
 
 	/* TCP offload with GRE SEQ is not supported, nor can we support 2
@@ -1485,6 +1485,8 @@ static void ip6gre_tnl_init_features(struct net_device *dev)
 
 	dev->features |= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+
+	dev->lltx = true;
 }
 
 static int ip6gre_tunnel_init_common(struct net_device *dev)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 87dfb565a9f8..cbef0fcece71 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1849,7 +1849,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
 	dev->type = ARPHRD_TUNNEL6;
 	dev->flags |= IFF_NOARP;
 	dev->addr_len = sizeof(struct in6_addr);
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	netif_keep_dst(dev);
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3b2eed7fc765..58306522fb1e 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1436,7 +1436,7 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->flags		= IFF_NOARP;
 	netif_keep_dst(dev);
 	dev->addr_len		= 4;
-	dev->features		|= NETIF_F_LLTX;
+	dev->lltx		= true;
 	dev->features		|= SIT_FEATURES;
 	dev->hw_features	|= SIT_FEATURES;
 	dev->pcpu_stat_type	= NETDEV_PCPU_STAT_TSTATS;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 15a862f33f76..d692b902e120 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -97,7 +97,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &l2tpeth_type);
 	ether_setup(dev);
 	dev->priv_flags		&= ~IFF_TX_SKB_SHARING;
-	dev->features		|= NETIF_F_LLTX;
+	dev->lltx		= true;
 	dev->netdev_ops		= &l2tp_eth_netdev_ops;
 	dev->needs_free_netdev	= true;
 	dev->pcpu_stat_type	= NETDEV_PCPU_STAT_TSTATS;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 4b33133cbdff..3a369a31c5cc 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -102,19 +102,20 @@ static void do_setup(struct net_device *netdev)
 	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
 			      IFF_NO_QUEUE;
+	netdev->lltx = true;
 	netdev->needs_free_netdev = true;
 	netdev->priv_destructor = NULL;
 	netdev->ethtool_ops = &internal_dev_ethtool_ops;
 	netdev->rtnl_link_ops = &internal_dev_link_ops;
 
-	netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
-			   NETIF_F_HIGHDMA | NETIF_F_HW_CSUM |
-			   NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL;
+	netdev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
+			   NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE |
+			   NETIF_F_GSO_ENCAP_ALL;
 
 	netdev->vlan_features = netdev->features;
 	netdev->hw_enc_features = netdev->features;
 	netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
-	netdev->hw_features = netdev->features & ~NETIF_F_LLTX;
+	netdev->hw_features = netdev->features;
 
 	eth_hw_addr_random(netdev);
 }
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index e50e4bf993fa..98f1e2b67c76 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -769,7 +769,7 @@ static int xfrmi_dev_init(struct net_device *dev)
 	if (err)
 		return err;
 
-	dev->features |= NETIF_F_LLTX;
+	dev->lltx = true;
 	dev->features |= XFRMI_FEATURES;
 	dev->hw_features |= XFRMI_FEATURES;
 
-- 
cgit v1.3-3-g829e


From 05c1280a2bcfca187fe7fa90bb240602cf54af0a Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 29 Aug 2024 14:33:38 +0200
Subject: netdev_features: convert NETIF_F_NETNS_LOCAL to dev->netns_local

"Interface can't change network namespaces" is rather an attribute,
not a feature, and it can't be changed via Ethtool.
Make it a "cold" private flag instead of a netdev_feature and free
one more bit.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/net_cachelines/net_device.rst |  1 +
 Documentation/networking/netdev-features.rst           |  7 -------
 Documentation/networking/switchdev.rst                 |  4 ++--
 drivers/net/amt.c                                      |  2 +-
 drivers/net/bonding/bond_main.c                        |  6 +++---
 drivers/net/ethernet/adi/adin1110.c                    |  2 +-
 drivers/net/ethernet/marvell/prestera/prestera_main.c  |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c      |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c       |  3 ++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c         |  5 +++--
 drivers/net/ethernet/rocker/rocker_main.c              |  3 ++-
 drivers/net/ethernet/ti/cpsw_new.c                     |  3 ++-
 drivers/net/loopback.c                                 |  2 +-
 drivers/net/net_failover.c                             |  2 +-
 drivers/net/team/team_core.c                           |  6 +++---
 drivers/net/vrf.c                                      |  2 +-
 include/linux/netdev_features.h                        |  6 ++----
 include/linux/netdevice.h                              |  2 ++
 net/batman-adv/soft-interface.c                        |  3 ++-
 net/bridge/br_device.c                                 |  5 +++--
 net/core/dev.c                                         |  4 ++--
 net/ethtool/common.c                                   |  1 -
 net/hsr/hsr_device.c                                   |  8 ++++----
 net/ieee802154/6lowpan/core.c                          |  2 +-
 net/ieee802154/core.c                                  | 10 +++++-----
 net/ipv4/ip_tunnel.c                                   |  2 +-
 net/ipv4/ipmr.c                                        |  2 +-
 net/ipv6/ip6_gre.c                                     |  3 +--
 net/ipv6/ip6_tunnel.c                                  |  2 +-
 net/ipv6/ip6mr.c                                       |  2 +-
 net/ipv6/sit.c                                         |  2 +-
 net/openvswitch/vport-internal_dev.c                   |  2 +-
 net/wireless/core.c                                    | 10 +++++-----
 tools/testing/selftests/net/forwarding/README          |  2 +-
 34 files changed, 61 insertions(+), 62 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index e55319277074..e649d8e9556f 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -166,6 +166,7 @@ unsigned:1                          wol_enabled
 unsigned:1                          threaded                -                   -                   napi_poll(napi_enable,dev_set_threaded)
 unsigned_long:1                     see_all_hwtstamp_requests                                       
 unsigned_long:1                     change_proto_down                                               
+unsigned_long:1                     netns_local                                                     
 struct_list_head                    net_notifier_list                                               
 struct_macsec_ops*                  macsec_ops                                                      
 struct_udp_tunnel_nic_info*         udp_tunnel_nic_info                                             
diff --git a/Documentation/networking/netdev-features.rst b/Documentation/networking/netdev-features.rst
index f29d982ebf5d..5014f7cc1398 100644
--- a/Documentation/networking/netdev-features.rst
+++ b/Documentation/networking/netdev-features.rst
@@ -139,13 +139,6 @@ chained skbs (skb->next/prev list).
 Features contained in NETIF_F_SOFT_FEATURES are features of networking
 stack. Driver should not change behaviour based on them.
 
- * netns-local device
-
-NETIF_F_NETNS_LOCAL is set for devices that are not allowed to move between
-network namespaces (e.g. loopback).
-
-Don't use it in drivers.
-
  * VLAN challenged
 
 NETIF_F_VLAN_CHALLENGED should be set for devices which can't cope with VLAN
diff --git a/Documentation/networking/switchdev.rst b/Documentation/networking/switchdev.rst
index 758f1dae3fce..f355f0166f1b 100644
--- a/Documentation/networking/switchdev.rst
+++ b/Documentation/networking/switchdev.rst
@@ -137,10 +137,10 @@ would be sub-port 0 on port 1 on switch 1.
 Port Features
 ^^^^^^^^^^^^^
 
-NETIF_F_NETNS_LOCAL
+dev->netns_local
 
 If the switchdev driver (and device) only supports offloading of the default
-network namespace (netns), the driver should set this feature flag to prevent
+network namespace (netns), the driver should set this private flag to prevent
 the port netdev from being moved out of the default netns.  A netns-aware
 driver/device would not set this flag and be responsible for partitioning
 hardware to preserve netns containment.  This means hardware cannot forward
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 921bbfd72a38..0433a0f36d1b 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3099,8 +3099,8 @@ static void amt_link_setup(struct net_device *dev)
 	dev->addr_len		= 0;
 	dev->priv_flags		|= IFF_NO_QUEUE;
 	dev->lltx		= true;
+	dev->netns_local	= true;
 	dev->features		|= NETIF_F_GSO_SOFTWARE;
-	dev->features		|= NETIF_F_NETNS_LOCAL;
 	dev->hw_features	|= NETIF_F_SG | NETIF_F_HW_CSUM;
 	dev->hw_features	|= NETIF_F_FRAGLIST | NETIF_F_RXCSUM;
 	dev->hw_features	|= NETIF_F_GSO_SOFTWARE;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8ae887cdc231..f13d413ad26c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5930,6 +5930,9 @@ void bond_setup(struct net_device *bond_dev)
 	/* don't acquire bond device's netif_tx_lock when transmitting */
 	bond_dev->lltx = true;
 
+	/* Don't allow bond devices to change network namespaces. */
+	bond_dev->netns_local = true;
+
 	/* By default, we declare the bond to be fully
 	 * VLAN hardware accelerated capable. Special
 	 * care is taken in the various xmit functions
@@ -5937,9 +5940,6 @@ void bond_setup(struct net_device *bond_dev)
 	 * capable
 	 */
 
-	/* Don't allow bond devices to change network namespaces. */
-	bond_dev->features |= NETIF_F_NETNS_LOCAL;
-
 	bond_dev->hw_features = BOND_VLAN_FEATURES |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER |
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 0713f1e2c7f3..3431a7e62b0d 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -1599,7 +1599,7 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv)
 		netdev->netdev_ops = &adin1110_netdev_ops;
 		netdev->ethtool_ops = &adin1110_ethtool_ops;
 		netdev->priv_flags |= IFF_UNICAST_FLT;
-		netdev->features |= NETIF_F_NETNS_LOCAL;
+		netdev->netns_local = true;
 
 		port_priv->phydev = get_phy_device(priv->mii_bus, i + 1, false);
 		if (IS_ERR(port_priv->phydev)) {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 63ae01954dfc..22ca6ee9665e 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -633,7 +633,8 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
 	if (err)
 		goto err_dl_port_register;
 
-	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
+	dev->features |= NETIF_F_HW_TC;
+	dev->netns_local = true;
 	dev->netdev_ops = &prestera_netdev_ops;
 	dev->ethtool_ops = &prestera_ethtool_ops;
 	SET_NETDEV_DEV(dev, sw->dev->dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 16b67c457b60..47e7a80d221b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4414,9 +4414,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 
 	if (mlx5e_is_uplink_rep(priv)) {
 		features = mlx5e_fix_uplink_rep_features(netdev, features);
-		features |= NETIF_F_NETNS_LOCAL;
+		netdev->netns_local = true;
 	} else {
-		features &= ~NETIF_F_NETNS_LOCAL;
+		netdev->netns_local = false;
 	}
 
 	mutex_unlock(&priv->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index b885042eef14..92094bf60d59 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -898,7 +898,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
 	netdev->features |= netdev->hw_features;
-	netdev->features |= NETIF_F_NETNS_LOCAL;
+
+	netdev->netns_local = true;
 }
 
 static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 44d6e125bd6f..b9ffd7236aff 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1676,10 +1676,11 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 
 	netif_carrier_off(dev);
 
-	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_SG |
-			 NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC;
+	dev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER |
+			 NETIF_F_HW_TC;
 	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
 	dev->lltx = true;
+	dev->netns_local = true;
 
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index e097ce3e69ea..84fa911c78db 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2575,7 +2575,8 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx);
 	rocker_carrier_init(rocker_port);
 
-	dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_SG;
+	dev->features |= NETIF_F_SG;
+	dev->netns_local = true;
 
 	/* MTU range: 68 - 9000 */
 	dev->min_mtu = ROCKER_PORT_MIN_MTU;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 2baa198ebfa0..557cc71b9dd2 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1407,7 +1407,8 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		cpsw->slaves[i].ndev = ndev;
 
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
-				  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
+				  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_TC;
+		ndev->netns_local = true;
 
 		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
 				     NETDEV_XDP_ACT_REDIRECT |
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index bf857782be0f..1993b90b1a5f 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -172,6 +172,7 @@ static void gen_lo_setup(struct net_device *dev,
 	dev->flags		= IFF_LOOPBACK;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	dev->lltx		= true;
+	dev->netns_local	= true;
 	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
 	dev->features		= NETIF_F_SG | NETIF_F_FRAGLIST
@@ -180,7 +181,6 @@ static void gen_lo_setup(struct net_device *dev,
 		| NETIF_F_RXCSUM
 		| NETIF_F_SCTP_CRC
 		| NETIF_F_HIGHDMA
-		| NETIF_F_NETNS_LOCAL
 		| NETIF_F_VLAN_CHALLENGED
 		| NETIF_F_LOOPBACK;
 	dev->ethtool_ops	= eth_ops;
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index 06728385a35f..54c8b9d5b5fc 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -734,7 +734,7 @@ struct failover *net_failover_create(struct net_device *standby_dev)
 	failover_dev->lltx = true;
 
 	/* Don't allow failover devices to change network namespaces. */
-	failover_dev->features |= NETIF_F_NETNS_LOCAL;
+	failover_dev->netns_local = true;
 
 	failover_dev->hw_features = FAILOVER_VLAN_FEATURES |
 				    NETIF_F_HW_VLAN_CTAG_TX |
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index 1d1bad3cedc2..18191d5a8bd4 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -2191,10 +2191,10 @@ static void team_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
 	dev->lltx = true;
 
-	dev->features |= NETIF_F_GRO;
-
 	/* Don't allow team devices to change network namespaces. */
-	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->netns_local = true;
+
+	dev->features |= NETIF_F_GRO;
 
 	dev->hw_features = TEAM_VLAN_FEATURES |
 			   NETIF_F_HW_VLAN_CTAG_RX |
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index b1d4ef538995..4d8ccaf9a2b4 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1638,7 +1638,7 @@ static void vrf_setup(struct net_device *dev)
 	dev->lltx = true;
 
 	/* don't allow vrf devices to change network namespaces. */
-	dev->features |= NETIF_F_NETNS_LOCAL;
+	dev->netns_local = true;
 
 	/* does not make sense for a VLAN to be added to a vrf device */
 	dev->features   |= NETIF_F_VLAN_CHALLENGED;
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index a2e20b517584..d5a3836f4793 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -25,7 +25,7 @@ enum {
 	NETIF_F_VLAN_CHALLENGED_BIT,	/* Device cannot handle VLAN packets */
 	NETIF_F_GSO_BIT,		/* Enable software GSO. */
 	__UNUSED_NETIF_F_12,
-	NETIF_F_NETNS_LOCAL_BIT,	/* Does not change network namespaces */
+	__UNUSED_NETIF_F_13,
 	NETIF_F_GRO_BIT,		/* Generic receive offload */
 	NETIF_F_LRO_BIT,		/* large receive offload */
 
@@ -121,7 +121,6 @@ enum {
 #define NETIF_F_IPV6_CSUM	__NETIF_F(IPV6_CSUM)
 #define NETIF_F_LOOPBACK	__NETIF_F(LOOPBACK)
 #define NETIF_F_LRO		__NETIF_F(LRO)
-#define NETIF_F_NETNS_LOCAL	__NETIF_F(NETNS_LOCAL)
 #define NETIF_F_NOCACHE_COPY	__NETIF_F(NOCACHE_COPY)
 #define NETIF_F_NTUPLE		__NETIF_F(NTUPLE)
 #define NETIF_F_RXCSUM		__NETIF_F(RXCSUM)
@@ -190,8 +189,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
-#define NETIF_F_NEVER_CHANGE	(NETIF_F_VLAN_CHALLENGED | \
-				 NETIF_F_NETNS_LOCAL)
+#define NETIF_F_NEVER_CHANGE	NETIF_F_VLAN_CHALLENGED
 
 /* remember that ((t)1 << t_BITS) is undefined in C99 */
 #define NETIF_F_ETHTOOL_BITS	((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e22ca5e07490..a698e2402420 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1968,6 +1968,7 @@ enum netdev_reg_state {
  *			regardless of source, even if those aren't
  *			HWTSTAMP_SOURCE_NETDEV
  *	@change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
+ *	@netns_local: interface can't change network namespaces
  *
  *	@net_notifier_list:	List of per-net netdev notifier block
  *				that follow this device when it is moved
@@ -2361,6 +2362,7 @@ struct net_device {
 	/* priv_flags_slow, ungrouped to save space */
 	unsigned long		see_all_hwtstamp_requests:1;
 	unsigned long		change_proto_down:1;
+	unsigned long		netns_local:1;
 
 	struct list_head	net_notifier_list;
 
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index e791a73ef901..2758aba47a2f 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1020,9 +1020,10 @@ static void batadv_softif_init_early(struct net_device *dev)
 	dev->netdev_ops = &batadv_netdev_ops;
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = batadv_softif_free;
-	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL;
+	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->lltx = true;
+	dev->netns_local = true;
 
 	/* can't call min_mtu, because the needed variables
 	 * have not been initialized yet
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index a6d25113dfb1..26b79feb385d 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -488,9 +488,10 @@ void br_dev_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
 	dev->lltx = true;
+	dev->netns_local = true;
 
-	dev->features = COMMON_FEATURES | NETIF_F_NETNS_LOCAL |
-			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
+	dev->features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
+			NETIF_F_HW_VLAN_STAG_TX;
 	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 			   NETIF_F_HW_VLAN_STAG_TX;
 	dev->vlan_features = COMMON_FEATURES;
diff --git a/net/core/dev.c b/net/core/dev.c
index 56aed88ceadf..98bb5f890b88 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11487,7 +11487,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 
 	/* Don't allow namespace local devices to be moved. */
 	err = -EINVAL;
-	if (dev->features & NETIF_F_NETNS_LOCAL)
+	if (dev->netns_local)
 		goto out;
 
 	/* Ensure the device has been registered */
@@ -11869,7 +11869,7 @@ static void __net_exit default_device_exit_net(struct net *net)
 		char fb_name[IFNAMSIZ];
 
 		/* Ignore unmoveable devices (i.e. loopback) */
-		if (dev->features & NETIF_F_NETNS_LOCAL)
+		if (dev->netns_local)
 			continue;
 
 		/* Leave virtual devices for the generic cleanup */
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 447fc80e1b00..ca8e64162104 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -25,7 +25,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter",
 	[NETIF_F_VLAN_CHALLENGED_BIT] =  "vlan-challenged",
 	[NETIF_F_GSO_BIT] =              "tx-generic-segmentation",
-	[NETIF_F_NETNS_LOCAL_BIT] =      "netns-local",
 	[NETIF_F_GRO_BIT] =              "rx-gro",
 	[NETIF_F_GRO_HW_BIT] =           "rx-gro-hw",
 	[NETIF_F_LRO_BIT] =              "rx-lro",
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index d4c783076662..a06e790042e2 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -556,6 +556,10 @@ void hsr_dev_setup(struct net_device *dev)
 	dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
 	/* Prevent recursive tx locking */
 	dev->lltx = true;
+	/* Not sure about this. Taken from bridge code. netdevice.h says
+	 * it means "Does not change network namespaces".
+	 */
+	dev->netns_local = true;
 
 	dev->needs_free_netdev = true;
 
@@ -569,10 +573,6 @@ void hsr_dev_setup(struct net_device *dev)
 	 * hsr_header_create() etc.
 	 */
 	dev->features |= NETIF_F_VLAN_CHALLENGED;
-	/* Not sure about this. Taken from bridge code. netdev_features.h says
-	 * it means "Does not change network namespaces".
-	 */
-	dev->features |= NETIF_F_NETNS_LOCAL;
 }
 
 /* Return true if dev is a HSR master; return false otherwise.
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 77b4e92027c5..175efd860f7b 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -116,7 +116,7 @@ static void lowpan_setup(struct net_device *ldev)
 	ldev->netdev_ops	= &lowpan_netdev_ops;
 	ldev->header_ops	= &lowpan_header_ops;
 	ldev->needs_free_netdev	= true;
-	ldev->features		|= NETIF_F_NETNS_LOCAL;
+	ldev->netns_local	= true;
 }
 
 static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 60e8fff1347e..88adb04e4072 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -226,11 +226,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 	list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) {
 		if (!wpan_dev->netdev)
 			continue;
-		wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL;
+		wpan_dev->netdev->netns_local = false;
 		err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d");
 		if (err)
 			break;
-		wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL;
+		wpan_dev->netdev->netns_local = true;
 	}
 
 	if (err) {
@@ -242,11 +242,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 						     list) {
 			if (!wpan_dev->netdev)
 				continue;
-			wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL;
+			wpan_dev->netdev->netns_local = false;
 			err = dev_change_net_namespace(wpan_dev->netdev, net,
 						       "wpan%d");
 			WARN_ON(err);
-			wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL;
+			wpan_dev->netdev->netns_local = true;
 		}
 
 		return err;
@@ -291,7 +291,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 	switch (state) {
 		/* TODO NETDEV_DEVTYPE */
 	case NETDEV_REGISTER:
-		dev->features |= NETIF_F_NETNS_LOCAL;
+		dev->netns_local = true;
 		wpan_dev->identifier = ++rdev->wpan_dev_id;
 		list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
 		rdev->devlist_generation++;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0cd2f3de100c..18964394d6bd 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1161,7 +1161,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
-		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->netns_local = true;
 		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 		itn->type = itn->fb_tunnel_dev->type;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b0eda745e3bc..f1a43199551b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -537,7 +537,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
 	dev->needs_free_netdev	= true;
-	dev->features		|= NETIF_F_NETNS_LOCAL;
+	dev->netns_local	= true;
 }
 
 static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 08beab638bda..235808cfec70 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1621,8 +1621,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
-
+	ign->fb_tunnel_dev->netns_local = true;
 
 	ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
 	ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index cbef0fcece71..ec51ab5063e8 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2258,7 +2258,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
+	ip6n->fb_tnl_dev->netns_local = true;
 
 	err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e3ee93c562c3..2ce4ae0d8dc3 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -640,7 +640,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
 	dev->needs_free_netdev	= true;
-	dev->features		|= NETIF_F_NETNS_LOCAL;
+	dev->netns_local	= true;
 }
 
 static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 58306522fb1e..16b90a24c9ba 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1856,7 +1856,7 @@ static int __net_init sit_init_net(struct net *net)
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+	sitn->fb_tunnel_dev->netns_local = true;
 
 	err = register_netdev(sitn->fb_tunnel_dev);
 	if (err)
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 3a369a31c5cc..5858d65ea1a9 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -149,7 +149,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 	/* Restrict bridge port to current netns. */
 	if (vport->port_no == OVSP_LOCAL)
-		vport->dev->features |= NETIF_F_NETNS_LOCAL;
+		vport->dev->netns_local = true;
 
 	rtnl_lock();
 	err = register_netdevice(vport->dev);
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 4d5d351bd0b5..661adfc77644 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -165,11 +165,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		if (!wdev->netdev)
 			continue;
-		wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL;
+		wdev->netdev->netns_local = false;
 		err = dev_change_net_namespace(wdev->netdev, net, "wlan%d");
 		if (err)
 			break;
-		wdev->netdev->features |= NETIF_F_NETNS_LOCAL;
+		wdev->netdev->netns_local = true;
 	}
 
 	if (err) {
@@ -181,11 +181,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 						     list) {
 			if (!wdev->netdev)
 				continue;
-			wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL;
+			wdev->netdev->netns_local = false;
 			err = dev_change_net_namespace(wdev->netdev, net,
 							"wlan%d");
 			WARN_ON(err);
-			wdev->netdev->features |= NETIF_F_NETNS_LOCAL;
+			wdev->netdev->netns_local = true;
 		}
 
 		return err;
@@ -1473,7 +1473,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		SET_NETDEV_DEVTYPE(dev, &wiphy_type);
 		wdev->netdev = dev;
 		/* can only change netns with wiphy */
-		dev->features |= NETIF_F_NETNS_LOCAL;
+		dev->netns_local = true;
 
 		cfg80211_init_wdev(wdev);
 		break;
diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README
index 7fdb6a9ca543..a652429bfd53 100644
--- a/tools/testing/selftests/net/forwarding/README
+++ b/tools/testing/selftests/net/forwarding/README
@@ -6,7 +6,7 @@ to easily create and test complex environments.
 
 Unfortunately, these namespaces can not be used with actual switching
 ASICs, as their ports can not be migrated to other network namespaces
-(NETIF_F_NETNS_LOCAL) and most of them probably do not support the
+(dev->netns_local) and most of them probably do not support the
 L1-separation provided by namespaces.
 
 However, a similar kind of flexibility can be achieved by using VRFs and
-- 
cgit v1.3-3-g829e


From 782dbbf589cd9082effaec522e3f1b4ce1594803 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 29 Aug 2024 14:33:39 +0200
Subject: netdev_features: convert NETIF_F_FCOE_MTU to dev->fcoe_mtu

Ability to handle maximum FCoE frames of 2158 bytes can never be changed
and thus more of an attribute, not a toggleable feature.
Move it from netdev_features_t to "cold" priv flags (bitfield bool) and
free yet another feature bit.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/net_cachelines/net_device.rst |  1 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c        |  6 ++----
 drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c        |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c          |  4 ++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c           |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c          | 11 ++++-------
 drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c         |  4 ++--
 drivers/scsi/fcoe/fcoe.c                               |  4 ++--
 include/linux/netdev_features.h                        |  6 ++----
 include/linux/netdevice.h                              |  2 ++
 net/8021q/vlan_dev.c                                   |  1 +
 net/ethtool/common.c                                   |  1 -
 12 files changed, 20 insertions(+), 24 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index e649d8e9556f..56d4bbaf8a2c 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -167,6 +167,7 @@ unsigned:1                          threaded                -
 unsigned_long:1                     see_all_hwtstamp_requests                                       
 unsigned_long:1                     change_proto_down                                               
 unsigned_long:1                     netns_local                                                     
+unsigned_long:1                     fcoe_mtu                                                        
 struct_list_head                    net_notifier_list                                               
 struct_macsec_ops*                  macsec_ops                                                      
 struct_udp_tunnel_nic_info*         udp_tunnel_nic_info                                             
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
index 33b2c0c45509..f6f745f5c022 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
@@ -81,8 +81,7 @@ int cxgb_fcoe_enable(struct net_device *netdev)
 
 	netdev->features |= NETIF_F_FCOE_CRC;
 	netdev->vlan_features |= NETIF_F_FCOE_CRC;
-	netdev->features |= NETIF_F_FCOE_MTU;
-	netdev->vlan_features |= NETIF_F_FCOE_MTU;
+	netdev->fcoe_mtu = true;
 
 	netdev_features_change(netdev);
 
@@ -112,8 +111,7 @@ int cxgb_fcoe_disable(struct net_device *netdev)
 
 	netdev->features &= ~NETIF_F_FCOE_CRC;
 	netdev->vlan_features &= ~NETIF_F_FCOE_CRC;
-	netdev->features &= ~NETIF_F_FCOE_MTU;
-	netdev->vlan_features &= ~NETIF_F_FCOE_MTU;
+	netdev->fcoe_mtu = false;
 
 	netdev_features_change(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index e85f7d2e8810..f2709b10c2e5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -317,7 +317,7 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 		int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 
 #ifdef IXGBE_FCOE
-		if (adapter->netdev->features & NETIF_F_FCOE_MTU)
+		if (adapter->netdev->fcoe_mtu)
 			max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
 #endif
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index 18d63c8c2ff4..955dced844a9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -858,7 +858,7 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
 
 	/* enable FCoE and notify stack */
 	adapter->flags |= IXGBE_FLAG_FCOE_ENABLED;
-	netdev->features |= NETIF_F_FCOE_MTU;
+	netdev->fcoe_mtu = true;
 	netdev_features_change(netdev);
 
 	/* release existing queues and reallocate them */
@@ -898,7 +898,7 @@ int ixgbe_fcoe_disable(struct net_device *netdev)
 
 	/* disable FCoE and notify stack */
 	adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED;
-	netdev->features &= ~NETIF_F_FCOE_MTU;
+	netdev->fcoe_mtu = false;
 
 	netdev_features_change(netdev);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 0ee943db3dc9..16fa621ce0ff 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -981,7 +981,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 			set_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state);
 
 #ifdef IXGBE_FCOE
-		if (adapter->netdev->features & NETIF_F_FCOE_MTU) {
+		if (adapter->netdev->fcoe_mtu) {
 			struct ixgbe_ring_feature *f;
 			f = &adapter->ring_feature[RING_F_FCOE];
 			if ((rxr_idx >= f->offset) &&
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 8057cef61f39..8b8404d8c946 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5079,7 +5079,7 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
 		netif_set_tso_max_size(adapter->netdev, 32768);
 
 #ifdef IXGBE_FCOE
-	if (adapter->netdev->features & NETIF_F_FCOE_MTU)
+	if (adapter->netdev->fcoe_mtu)
 		max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE);
 #endif
 
@@ -5136,8 +5136,7 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb)
 
 #ifdef IXGBE_FCOE
 	/* FCoE traffic class uses FCOE jumbo frames */
-	if ((dev->features & NETIF_F_FCOE_MTU) &&
-	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
+	if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE &&
 	    (pb == ixgbe_fcoe_get_tc(adapter)))
 		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;
 #endif
@@ -5197,8 +5196,7 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb)
 
 #ifdef IXGBE_FCOE
 	/* FCoE traffic class uses FCOE jumbo frames */
-	if ((dev->features & NETIF_F_FCOE_MTU) &&
-	    (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) &&
+	if (dev->fcoe_mtu && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE &&
 	    (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up)))
 		tc = IXGBE_FCOE_JUMBO_FRAME_SIZE;
 #endif
@@ -11096,8 +11094,7 @@ skip_sriov:
 				    NETIF_F_FCOE_CRC;
 
 		netdev->vlan_features |= NETIF_F_FSO |
-					 NETIF_F_FCOE_CRC |
-					 NETIF_F_FCOE_MTU;
+					 NETIF_F_FCOE_CRC;
 	}
 #endif /* IXGBE_FCOE */
 	if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index fcfd0a075eee..e71715f5da22 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -495,7 +495,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf
 		int err = 0;
 
 #ifdef CONFIG_FCOE
-		if (dev->features & NETIF_F_FCOE_MTU)
+		if (dev->fcoe_mtu)
 			pf_max_frame = max_t(int, pf_max_frame,
 					     IXGBE_FCOE_JUMBO_FRAME_SIZE);
 
@@ -857,7 +857,7 @@ static void ixgbe_set_vf_rx_tx(struct ixgbe_adapter *adapter, int vf)
 		int pf_max_frame = dev->mtu + ETH_HLEN;
 
 #if IS_ENABLED(CONFIG_FCOE)
-		if (dev->features & NETIF_F_FCOE_MTU)
+		if (dev->fcoe_mtu)
 			pf_max_frame = max_t(int, pf_max_frame,
 					     IXGBE_FCOE_JUMBO_FRAME_SIZE);
 #endif /* CONFIG_FCOE */
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index f1429f270170..39aec710660c 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -722,7 +722,7 @@ static int fcoe_netdev_config(struct fc_lport *lport, struct net_device *netdev)
 	 * will return 0, so do this first.
 	 */
 	mfs = netdev->mtu;
-	if (netdev->features & NETIF_F_FCOE_MTU) {
+	if (netdev->fcoe_mtu) {
 		mfs = FCOE_MTU;
 		FCOE_NETDEV_DBG(netdev, "Supports FCOE_MTU of %d bytes\n", mfs);
 	}
@@ -1863,7 +1863,7 @@ static int fcoe_device_notification(struct notifier_block *notifier,
 	case NETDEV_CHANGE:
 		break;
 	case NETDEV_CHANGEMTU:
-		if (netdev->features & NETIF_F_FCOE_MTU)
+		if (netdev->fcoe_mtu)
 			break;
 		mfs = netdev->mtu - (sizeof(struct fcoe_hdr) +
 				     sizeof(struct fcoe_crc_eof));
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index d5a3836f4793..37af2c6e7caf 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -58,7 +58,7 @@ enum {
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
-	NETIF_F_FCOE_MTU_BIT,		/* Supports max FCoE MTU, 2158 bytes*/
+	__UNUSED_NETIF_F_37,
 	NETIF_F_NTUPLE_BIT,		/* N-tuple filters supported */
 	NETIF_F_RXHASH_BIT,		/* Receive hashing offload */
 	NETIF_F_RXCSUM_BIT,		/* Receive checksumming offload */
@@ -105,7 +105,6 @@ enum {
 #define __NETIF_F(name)		__NETIF_F_BIT(NETIF_F_##name##_BIT)
 
 #define NETIF_F_FCOE_CRC	__NETIF_F(FCOE_CRC)
-#define NETIF_F_FCOE_MTU	__NETIF_F(FCOE_MTU)
 #define NETIF_F_FRAGLIST	__NETIF_F(FRAGLIST)
 #define NETIF_F_FSO		__NETIF_F(FSO)
 #define NETIF_F_GRO		__NETIF_F(GRO)
@@ -210,8 +209,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 #define NETIF_F_ALL_TSO 	(NETIF_F_TSO | NETIF_F_TSO6 | \
 				 NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
 
-#define NETIF_F_ALL_FCOE	(NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
-				 NETIF_F_FSO)
+#define NETIF_F_ALL_FCOE	(NETIF_F_FCOE_CRC | NETIF_F_FSO)
 
 /* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a698e2402420..ca5f0dda733b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1969,6 +1969,7 @@ enum netdev_reg_state {
  *			HWTSTAMP_SOURCE_NETDEV
  *	@change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
  *	@netns_local: interface can't change network namespaces
+ *	@fcoe_mtu:	device supports maximum FCoE MTU, 2158 bytes
  *
  *	@net_notifier_list:	List of per-net netdev notifier block
  *				that follow this device when it is moved
@@ -2363,6 +2364,7 @@ struct net_device {
 	unsigned long		see_all_hwtstamp_requests:1;
 	unsigned long		change_proto_down:1;
 	unsigned long		netns_local:1;
+	unsigned long		fcoe_mtu:1;
 
 	struct list_head	net_notifier_list;
 
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 3ca485537d77..09b46b057ab2 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -571,6 +571,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	dev->features |= dev->hw_features;
 	dev->lltx = true;
+	dev->fcoe_mtu = true;
 	netif_inherit_tso_max(dev, real_dev);
 	if (dev->features & NETIF_F_VLAN_FEATURES)
 		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index ca8e64162104..00f93c58b319 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -50,7 +50,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",
-	[NETIF_F_FCOE_MTU_BIT] =         "fcoe-mtu",
 	[NETIF_F_NTUPLE_BIT] =           "rx-ntuple-filter",
 	[NETIF_F_RXHASH_BIT] =           "rx-hashing",
 	[NETIF_F_RXCSUM_BIT] =           "rx-checksum",
-- 
cgit v1.3-3-g829e


From a61fec1c87be682b5c0fdba6074649c469c675a3 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 29 Aug 2024 14:33:40 +0200
Subject: netdev_features: remove NETIF_F_ALL_FCOE

NETIF_F_ALL_FCOE is used only in vlan_dev.c, 2 times. Now that it's only
2 bits, open-code it and remove the definition from netdev_features.h.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdev_features.h | 2 --
 net/8021q/vlan_dev.c            | 5 +++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 37af2c6e7caf..66e7d26b70a4 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -209,8 +209,6 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 #define NETIF_F_ALL_TSO 	(NETIF_F_TSO | NETIF_F_TSO6 | \
 				 NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
 
-#define NETIF_F_ALL_FCOE	(NETIF_F_FCOE_CRC | NETIF_F_FSO)
-
 /* List of features with software fallbacks. */
 #define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
 				 NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 09b46b057ab2..458040e8a0e0 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -564,7 +564,7 @@ static int vlan_dev_init(struct net_device *dev)
 			   NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
 			   NETIF_F_GSO_ENCAP_ALL |
 			   NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
-			   NETIF_F_ALL_FCOE;
+			   NETIF_F_FCOE_CRC | NETIF_F_FSO;
 
 	if (real_dev->vlan_features & NETIF_F_HW_MACSEC)
 		dev->hw_features |= NETIF_F_HW_MACSEC;
@@ -576,7 +576,8 @@ static int vlan_dev_init(struct net_device *dev)
 	if (dev->features & NETIF_F_VLAN_FEATURES)
 		netdev_warn(real_dev, "VLAN features are set incorrectly.  Q-in-Q configurations may not work correctly.\n");
 
-	dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE;
+	dev->vlan_features = real_dev->vlan_features &
+			     ~(NETIF_F_FCOE_CRC | NETIF_F_FSO);
 	dev->hw_enc_features = vlan_tnl_features(real_dev);
 	dev->mpls_features = real_dev->mpls_features;
 
-- 
cgit v1.3-3-g829e


From 2c9ffe872e64f5aec12f2ff6cec1b7542569a88f Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 3 Sep 2024 09:21:44 +0100
Subject: wifi: cfg80211: wext: Update spelling and grammar

Correct spelling in iw_handler.h.
As reported by codespell.

Also, while the "few shortcomings" line is being updated,
correct its grammar.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240903-wifi-spell-v2-1-bfcf7062face@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/iw_handler.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h
index b2cf243ebe44..7af1082ea9a0 100644
--- a/include/net/iw_handler.h
+++ b/include/net/iw_handler.h
@@ -23,7 +23,7 @@
  * to handle wireless statistics.
  *
  * The initial APIs served us well and has proven a reasonably good design.
- * However, there is a few shortcommings :
+ * However, there are a few shortcomings :
  *	o No events, everything is a request to the driver.
  *	o Large ioctl function in driver with gigantic switch statement
  *	  (i.e. spaghetti code).
@@ -38,13 +38,13 @@
  * -------------------------------
  * The new driver API is just a bunch of standard functions (handlers),
  * each handling a specific Wireless Extension. The driver just export
- * the list of handler it supports, and those will be called apropriately.
+ * the list of handler it supports, and those will be called appropriately.
  *
  * I tried to keep the main advantage of the previous API (simplicity,
  * efficiency and light weight), and also I provide a good dose of backward
  * compatibility (most structures are the same, driver can use both API
  * simultaneously, ...).
- * Hopefully, I've also addressed the shortcomming of the initial API.
+ * Hopefully, I've also addressed the shortcoming of the initial API.
  *
  * The advantage of the new API are :
  *	o Handling of Extensions in driver broken in small contained functions
@@ -84,7 +84,7 @@
 
 /* ---------------------- THE IMPLEMENTATION ---------------------- */
 /*
- * Some of the choice I've made are pretty controversials. Defining an
+ * Some of the choice I've made are pretty controversial. Defining an
  * API is very much weighting compromises. This goes into some of the
  * details and the thinking behind the implementation.
  *
@@ -140,7 +140,7 @@
  * example to distinguish setting max rate and basic rate), I would
  * break the prototype. Using iwreq_data is more flexible.
  * 3) Also, the above form is not generic (see above).
- * 4) I don't expect driver developper using the wrong field of the
+ * 4) I don't expect driver developer using the wrong field of the
  * union (Doh !), so static typechecking doesn't add much value.
  * 5) Lastly, you can skip the union by doing :
  *	static int mydriver_ioctl_setrate(struct net_device *dev,
@@ -459,7 +459,7 @@ int iw_handler_get_thrspy(struct net_device *dev, struct iw_request_info *info,
 void wireless_spy_update(struct net_device *dev, unsigned char *address,
 			 struct iw_quality *wstats);
 
-/************************* INLINE FUNTIONS *************************/
+/************************* INLINE FUNCTIONS *************************/
 /*
  * Function that are so simple that it's more efficient inlining them
  */
-- 
cgit v1.3-3-g829e


From 1a7d2870f472db94d2dada643651f1e604c67bcf Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 1 Sep 2024 07:17:50 +0300
Subject: wifi: iwlwifi: mvm: refactor scan channel description a bit

The channel number is at the same position across all versions
of the channel description struct, so move it out of the union
that versions it. Also add __packed annotations to all of the
sub-structs and the union so it's packed correctly, and fully
document the structure.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Daniel Gabay <daniel.gabay@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240901071542.e31623ae4201.I1ea69a8ec3d39492f39d84e31fb105b159359c28@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/scan.h | 33 ++++++++++++++----------
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c    | 12 ++++-----
 2 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index 0aefdf353b21..f486d624500b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -731,39 +731,46 @@ enum iwl_umac_scan_general_params_flags2 {
  * struct iwl_scan_channel_cfg_umac
  * @flags:		bitmap - 0-19:	directed scan to i'th ssid.
  * @channel_num:	channel number 1-13 etc.
- * @band:		band of channel: 0 for 2GHz, 1 for 5GHz
- * @iter_count:		repetition count for the channel.
- * @iter_interval:	interval between two scan iterations on one channel.
+ * @v1:			command version 1
+ * @v1.iter_count:	repetition count for the channel.
+ * @v1.iter_interval:	interval between two scan iterations on one channel.
+ * @v2:			command versions 2-4
+ * @v2.band:		band of channel: 0 for 2GHz, 1 for 5GHz
+ * @v2.iter_count:	repetition count for the channel.
+ * @v2.iter_interval:	interval between two scan iterations on one channel.
+ * @v5:			command versions 5 and up
+ * @v5.iter_count:	repetition count for the channel.
+ * @v5.iter_interval:	interval between two scan iterations on one channel.
+ * @v5.psd_20:		highest PSD value for all APs known so far
+ *			on this channel.
  */
 struct  iwl_scan_channel_cfg_umac {
 #define IWL_CHAN_CFG_FLAGS_BAND_POS 30
 	__le32 flags;
+	u8 channel_num;
 
 	/* All versions are of the same size, so use a union without adjusting
 	 * the command size later
 	 */
 	union {
 		struct {
-			u8 channel_num;
 			u8 iter_count;
 			__le16 iter_interval;
-		} v1;  /* SCAN_CHANNEL_CONFIG_API_S_VER_1 */
+		} __packed v1;  /* SCAN_CHANNEL_CONFIG_API_S_VER_1 */
 		struct {
-			u8 channel_num;
 			u8 band;
 			u8 iter_count;
 			u8 iter_interval;
-		 } v2; /* SCAN_CHANNEL_CONFIG_API_S_VER_2
-			* SCAN_CHANNEL_CONFIG_API_S_VER_3
-			* SCAN_CHANNEL_CONFIG_API_S_VER_4
-			*/
+		} __packed v2; /* SCAN_CHANNEL_CONFIG_API_S_VER_2
+				* SCAN_CHANNEL_CONFIG_API_S_VER_3
+				* SCAN_CHANNEL_CONFIG_API_S_VER_4
+				*/
 		struct {
-			u8 channel_num;
 			u8 psd_20;
 			u8 iter_count;
 			u8 iter_interval;
-		} v5;  /* SCAN_CHANNEL_CONFIG_API_S_VER_5 */
-	};
+		} __packed v5;  /* SCAN_CHANNEL_CONFIG_API_S_VER_5 */
+	} __packed;
 } __packed;
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index 4ae6339f87c7..296d8c562207 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1594,7 +1594,7 @@ iwl_mvm_umac_scan_cfg_channels(struct iwl_mvm *mvm,
 
 	for (i = 0; i < n_channels; i++) {
 		channel_cfg[i].flags = cpu_to_le32(flags);
-		channel_cfg[i].v1.channel_num = channels[i]->hw_value;
+		channel_cfg[i].channel_num = channels[i]->hw_value;
 		if (iwl_mvm_is_scan_ext_chan_supported(mvm)) {
 			enum nl80211_band band = channels[i]->band;
 
@@ -1626,13 +1626,13 @@ iwl_mvm_umac_scan_cfg_channels_v4(struct iwl_mvm *mvm,
 			&cp->channel_config[i];
 
 		cfg->flags = cpu_to_le32(flags);
-		cfg->v2.channel_num = channels[i]->hw_value;
+		cfg->channel_num = channels[i]->hw_value;
 		cfg->v2.band = iwl_mvm_phy_band_from_nl80211(band);
 		cfg->v2.iter_count = 1;
 		cfg->v2.iter_interval = 0;
 
 		iwl_mvm_scan_ch_add_n_aps_override(vif_type,
-						   cfg->v2.channel_num,
+						   cfg->channel_num,
 						   cfg->v2.band, bitmap,
 						   bitmap_n_entries);
 	}
@@ -1656,7 +1656,7 @@ iwl_mvm_umac_scan_cfg_channels_v7(struct iwl_mvm *mvm,
 		u8 iwl_band = iwl_mvm_phy_band_from_nl80211(band);
 
 		cfg->flags = cpu_to_le32(flags | n_aps_flag);
-		cfg->v2.channel_num = channels[i]->hw_value;
+		cfg->channel_num = channels[i]->hw_value;
 		if (cfg80211_channel_is_psc(channels[i]))
 			cfg->flags = 0;
 		cfg->v2.iter_count = 1;
@@ -1778,7 +1778,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm,
 		    !params->n_6ghz_params && params->n_ssids)
 			continue;
 
-		cfg->v1.channel_num = params->channels[i]->hw_value;
+		cfg->channel_num = params->channels[i]->hw_value;
 		if (version < 17)
 			cfg->v2.band = PHY_BAND_6;
 		else
@@ -2466,7 +2466,7 @@ iwl_mvm_scan_umac_fill_ch_p_v7(struct iwl_mvm *mvm,
 			if (!cfg80211_channel_is_psc(channel))
 				continue;
 
-			cfg->v5.channel_num = channel->hw_value;
+			cfg->channel_num = channel->hw_value;
 			cfg->v5.iter_count = 1;
 			cfg->v5.iter_interval = 0;
 
-- 
cgit v1.3-3-g829e


From 07fb53783be80ca14f08b07d83ed88727db48aac Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 1 Sep 2024 07:17:51 +0300
Subject: wifi: iwlwifi: mvm: tell the firmware about CSA with mode=1

When we de-activate a link because it started a CSA with mode=1, we want
to tell the firmware it can no longer transmit any frame for that link.
The firmware will do that on its own if the CSA indication (beacon /
action frame) was  received on that same link, but with MLO, things got
more complex and the firmware can't track cross link CSA.

Tell the firmware if we de-activate a link because of CSA with mode=1 to
prevent it from transmitting, even if it is only an NDP PM=1 frame that
is part of the de-activation flow.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240901071542.4bef89d438d4.If7147a7a84054e67c05414c753d73f4e2e0e6e37@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h   | 10 ++++++++--
 drivers/net/wireless/intel/iwlwifi/mvm/link.c         |  9 +++++++--
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c | 16 ++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h          |  2 ++
 4 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 7af580d1c99c..73586e547e57 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -454,6 +454,9 @@ enum iwl_link_ctx_flags {
  * @listen_lmac: indicates whether the link should be allocated on the Listen
  *	Lmac or on the Main Lmac. Cannot be changed on an active Link.
  *	Relevant only for eSR.
+ * @block_tx: tell the firmware that this link can't Tx. This should be used
+ *	only when a link is de-activated because of CSA with mode = 1.
+ *	Available since version 5.
  * @reserved1: in version 2, listen_lmac became reserved
  * @cck_rates: basic rates available for CCK
  * @ofdm_rates: basic rates available for OFDM
@@ -498,7 +501,10 @@ struct iwl_link_config_cmd {
 	__le32 active;
 	union {
 		__le32 listen_lmac;
-		__le32 reserved1;
+		struct {
+			u8 block_tx;
+			u8 reserved1[3];
+		};
 	};
 	__le32 cck_rates;
 	__le32 ofdm_rates;
@@ -529,7 +535,7 @@ struct iwl_link_config_cmd {
 	u8 ibss_bssid_addr[6];
 	__le16 reserved_for_ibss_bssid_addr;
 	__le32 reserved3[8];
-} __packed; /* LINK_CONTEXT_CONFIG_CMD_API_S_VER_1, _VER_2, _VER_3, _VER_4 */
+} __packed; /* LINK_CONTEXT_CONFIG_CMD_API_S_VER_1, _VER_2, _VER_3, _VER_4, _VER_5 */
 
 /* Currently FW supports link ids in the range 0-3 and can have
  * at most two active links for each vif.
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index d151d935e12a..bc8d06127747 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -234,10 +234,15 @@ int iwl_mvm_link_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 		WARN_ON_ONCE(active == link_info->active);
 
 		/* When deactivating a link session protection should
-		 * be stopped
+		 * be stopped. Also let the firmware know if we can't Tx.
 		 */
-		if (!active && vif->type == NL80211_IFTYPE_STATION)
+		if (!active && vif->type == NL80211_IFTYPE_STATION) {
 			iwl_mvm_stop_session_protection(mvm, vif);
+			if (link_info->csa_block_tx) {
+				cmd.block_tx = 1;
+				link_info->csa_block_tx = false;
+			}
+		}
 	}
 
 	cmd.link_id = cpu_to_le32(link_info->fw_link_id);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 72bb6865dd63..f2378e0fb2fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -1341,6 +1341,22 @@ iwl_mvm_mld_mac_pre_channel_switch(struct ieee80211_hw *hw,
 		else
 			selected = primary;
 
+		/*
+		 * remembers to tell the firmware that this link can't tx
+		 * Note that this logic seems to be unrelated to esr, but it
+		 * really is needed only when esr is active. When we have a
+		 * single link, the firmware will handle all this on its own.
+		 * In multi-link scenarios, we can learn about the CSA from
+		 * another link and this logic is too complex for the firmware
+		 * to track.
+		 * Since we want to de-activate the link that got a CSA, we
+		 * need to tell the firmware not to send any frame on that link
+		 * as the firmware may not be aware that link is under a CSA
+		 * with mode=1 (no Tx allowed).
+		 */
+		if (chsw->block_tx && mvmvif->link[chsw->link_id])
+			mvmvif->link[chsw->link_id]->csa_block_tx = true;
+
 		iwl_mvm_exit_esr(mvm, vif, IWL_MVM_ESR_EXIT_CSA, selected);
 		mutex_unlock(&mvm->mutex);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 68464f892e85..26adf9f9b8c3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -299,6 +299,7 @@ struct iwl_probe_resp_data {
  * @active: indicates the link is active in FW (for sanity checking)
  * @cab_queue: content-after-beacon (multicast) queue
  * @listen_lmac: indicates this link is allocated to the listen LMAC
+ * @csa_block_tx: we got CSA with mode=1
  * @mcast_sta: multicast station
  * @phy_ctxt: phy context allocated to this link, if any
  * @bf_data: beacon filtering data
@@ -324,6 +325,7 @@ struct iwl_mvm_vif_link_info {
 	bool he_ru_2mhz_block;
 	bool active;
 	bool listen_lmac;
+	bool csa_block_tx;
 
 	u16 cab_queue;
 	/* Assigned while mac80211 has the link in a channel context,
-- 
cgit v1.3-3-g829e


From b61ed2b80911f981fa500252012330c54b9af5a0 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 1 Sep 2024 07:17:52 +0300
Subject: wifi: iwlwifi: s/IWL_MVM_STATION_COUNT_MAX/IWL_STATION_COUNT_MAX

This isn't mvm specific.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240901071542.5d71a0a2b56c.I7e0fe636d914852963e7a2f5e6037d0c3e367145@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac.h   |  2 +-
 drivers/net/wireless/intel/iwlwifi/fw/api/stats.h | 10 +++++-----
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c      |  4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      |  4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c      |  4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/rx.c       |  8 ++++----
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c     |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c      |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h      |  2 +-
 9 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index 490215e71e5d..977ca4ac166d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -16,7 +16,7 @@
 #define NUM_MAC_INDEX		(NUM_MAC_INDEX_DRIVER + 1)
 #define NUM_MAC_INDEX_CDB	(NUM_MAC_INDEX_DRIVER + 2)
 
-#define IWL_MVM_STATION_COUNT_MAX	16
+#define IWL_STATION_COUNT_MAX	16
 #define IWL_MVM_INVALID_STA		0xFF
 
 enum iwl_ac {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
index 659cb40ecfb4..0a9f14fb04be 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h
@@ -327,14 +327,14 @@ struct mvm_statistics_load {
 	__le32 air_time[MAC_INDEX_AUX];
 	__le32 byte_count[MAC_INDEX_AUX];
 	__le32 pkt_count[MAC_INDEX_AUX];
-	u8 avg_energy[IWL_MVM_STATION_COUNT_MAX];
+	u8 avg_energy[IWL_STATION_COUNT_MAX];
 } __packed; /* STATISTICS_RX_MAC_STATION_S_VER_3 */
 
 struct mvm_statistics_load_v1 {
 	__le32 air_time[NUM_MAC_INDEX];
 	__le32 byte_count[NUM_MAC_INDEX];
 	__le32 pkt_count[NUM_MAC_INDEX];
-	u8 avg_energy[IWL_MVM_STATION_COUNT_MAX];
+	u8 avg_energy[IWL_STATION_COUNT_MAX];
 } __packed; /* STATISTICS_RX_MAC_STATION_S_VER_1 */
 
 struct mvm_statistics_rx {
@@ -608,7 +608,7 @@ struct iwl_system_statistics_notif_oper {
 	__le32 time_stamp;
 	struct iwl_stats_ntfy_per_link per_link[IWL_STATS_MAX_FW_LINKS];
 	struct iwl_stats_ntfy_per_phy per_phy[IWL_STATS_MAX_PHY_OPERATIONAL];
-	struct iwl_stats_ntfy_per_sta per_sta[IWL_MVM_STATION_COUNT_MAX];
+	struct iwl_stats_ntfy_per_sta per_sta[IWL_STATION_COUNT_MAX];
 } __packed; /* STATISTICS_FW_NTFY_OPERATIONAL_API_S_VER_3 */
 
 /**
@@ -651,7 +651,7 @@ struct iwl_statistics_operational_ntfy {
 	__le32 flags;
 	struct iwl_stats_ntfy_per_mac per_mac[MAC_INDEX_AUX];
 	struct iwl_stats_ntfy_per_phy per_phy[IWL_STATS_MAX_PHY_OPERATIONAL];
-	struct iwl_stats_ntfy_per_sta per_sta[IWL_MVM_STATION_COUNT_MAX];
+	struct iwl_stats_ntfy_per_sta per_sta[IWL_STATION_COUNT_MAX];
 	__le64 rx_time;
 	__le64 tx_time;
 	__le64 on_time_rf;
@@ -699,7 +699,7 @@ struct iwl_statistics_operational_ntfy_ver_14 {
 	__le64 tx_time;
 	__le64 on_time_rf;
 	__le64 on_time_scan;
-	__le32 average_energy[IWL_MVM_STATION_COUNT_MAX];
+	__le32 average_energy[IWL_STATION_COUNT_MAX];
 	__le32 reserved;
 } __packed; /* STATISTICS_OPERATIONAL_NTFY_API_S_VER_14 */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index aaaabd67f959..2abfc986701f 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1205,7 +1205,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 			if (tlv_len != sizeof(u32))
 				goto invalid_tlv_len;
 			if (le32_to_cpup((const __le32 *)tlv_data) >
-			    IWL_MVM_STATION_COUNT_MAX) {
+			    IWL_STATION_COUNT_MAX) {
 				IWL_ERR(drv,
 					"%d is an invalid number of station\n",
 					le32_to_cpup((const __le32 *)tlv_data));
@@ -1479,7 +1479,7 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	fw->ucode_capa.standard_phy_calibration_size =
 			IWL_DEFAULT_STANDARD_PHY_CALIBRATE_TBL_SIZE;
 	fw->ucode_capa.n_scan_channels = IWL_DEFAULT_SCAN_CHANNELS;
-	fw->ucode_capa.num_stations = IWL_MVM_STATION_COUNT_MAX;
+	fw->ucode_capa.num_stations = IWL_STATION_COUNT_MAX;
 	fw->ucode_capa.num_beacons = 1;
 	/* dump all fw memory areas by default */
 	fw->dbg.dump_mask = 0xffffffff;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 26adf9f9b8c3..ec9b8be12766 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1078,8 +1078,8 @@ struct iwl_mvm {
 
 	/* data related to data path */
 	struct iwl_rx_phy_info last_phy_info;
-	struct ieee80211_sta __rcu *fw_id_to_mac_id[IWL_MVM_STATION_COUNT_MAX];
-	struct ieee80211_link_sta __rcu *fw_id_to_link_sta[IWL_MVM_STATION_COUNT_MAX];
+	struct ieee80211_sta __rcu *fw_id_to_mac_id[IWL_STATION_COUNT_MAX];
+	struct ieee80211_link_sta __rcu *fw_id_to_link_sta[IWL_STATION_COUNT_MAX];
 	u8 rx_ba_sessions;
 
 	/* configured by mac80211 */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 273767b074b8..d3ab959f497a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1285,12 +1285,12 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	struct iwl_mvm_csme_conn_info *csme_conn_info __maybe_unused;
 
 	/*
-	 * We use IWL_MVM_STATION_COUNT_MAX to check the validity of the station
+	 * We use IWL_STATION_COUNT_MAX to check the validity of the station
 	 * index all over the driver - check that its value corresponds to the
 	 * array size.
 	 */
 	BUILD_BUG_ON(ARRAY_SIZE(mvm->fw_id_to_mac_id) !=
-		     IWL_MVM_STATION_COUNT_MAX);
+		     IWL_STATION_COUNT_MAX);
 
 	/********************************
 	 * 1. Allocating and configuring HW data
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
index 3b5bbece63f6..047c020f8efa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c
@@ -738,8 +738,8 @@ static void iwl_mvm_stats_energy_iter(void *_data,
 	u8 *energy = _data;
 	u32 sta_id = mvmsta->deflink.sta_id;
 
-	if (WARN_ONCE(sta_id >= IWL_MVM_STATION_COUNT_MAX, "sta_id %d >= %d",
-		      sta_id, IWL_MVM_STATION_COUNT_MAX))
+	if (WARN_ONCE(sta_id >= IWL_STATION_COUNT_MAX, "sta_id %d >= %d",
+		      sta_id, IWL_STATION_COUNT_MAX))
 		return;
 
 	if (energy[sta_id])
@@ -1042,7 +1042,7 @@ static void iwl_mvm_update_esr_mode_tpt(struct iwl_mvm *mvm)
 void iwl_mvm_handle_rx_system_oper_stats(struct iwl_mvm *mvm,
 					 struct iwl_rx_cmd_buffer *rxb)
 {
-	u8 average_energy[IWL_MVM_STATION_COUNT_MAX];
+	u8 average_energy[IWL_STATION_COUNT_MAX];
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_system_statistics_notif_oper *stats;
 	int i;
@@ -1101,7 +1101,7 @@ static void
 iwl_mvm_handle_rx_statistics_tlv(struct iwl_mvm *mvm,
 				 struct iwl_rx_packet *pkt)
 {
-	u8 average_energy[IWL_MVM_STATION_COUNT_MAX];
+	u8 average_energy[IWL_STATION_COUNT_MAX];
 	__le32 air_time[MAC_INDEX_AUX];
 	__le32 rx_bytes[MAC_INDEX_AUX];
 	__le32 flags = 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 1a210d0c22b3..ae0f2aabddc3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -2542,7 +2542,7 @@ void iwl_mvm_rx_bar_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi,
 		goto out;
 	}
 
-	if (WARN(tid != baid_data->tid || sta_id > IWL_MVM_STATION_COUNT_MAX ||
+	if (WARN(tid != baid_data->tid || sta_id > IWL_STATION_COUNT_MAX ||
 		 !(baid_data->sta_mask & BIT(sta_id)),
 		 "baid 0x%x is mapped to sta_mask:0x%x tid:%d, but BAR release received for sta:%d tid:%d\n",
 		 baid, baid_data->sta_mask, baid_data->tid, sta_id,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 74bbeebe69d5..b6c99cd6d9e5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -29,7 +29,7 @@ int iwl_mvm_find_free_sta_id(struct iwl_mvm *mvm, enum nl80211_iftype iftype)
 	int sta_id;
 	u32 reserved_ids = 0;
 
-	BUILD_BUG_ON(IWL_MVM_STATION_COUNT_MAX > 32);
+	BUILD_BUG_ON(IWL_STATION_COUNT_MAX > 32);
 	WARN_ON_ONCE(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status));
 
 	lockdep_assert_held(&mvm->mutex);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 193a1edc38d2..4a3799ae7c18 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -12,7 +12,7 @@
 #include <linux/wait.h>
 
 #include "iwl-trans.h" /* for IWL_MAX_TID_COUNT */
-#include "fw-api.h" /* IWL_MVM_STATION_COUNT_MAX */
+#include "fw-api.h" /* IWL_STATION_COUNT_MAX */
 #include "rs.h"
 
 struct iwl_mvm;
-- 
cgit v1.3-3-g829e


From 07aeccf161358b893e34376594a4cbcf95de3c06 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 1 Sep 2024 07:17:53 +0300
Subject: wifi: iwlwifi: STA command structure shouldn't be mvm specific

This strcuture is not specific to mvm, so rename it.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240901071542.39c9ceea41d3.I2a06bfca589c467fa84ad82ff86e73ec82e72a5e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h | 6 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c    | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 73586e547e57..6dd9401596e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -42,7 +42,7 @@ enum iwl_mac_conf_subcmd_ids {
 	 */
 	LINK_CONFIG_CMD = 0x9,
 	/**
-	 * @STA_CONFIG_CMD: &struct iwl_mvm_sta_cfg_cmd
+	 * @STA_CONFIG_CMD: &struct iwl_sta_cfg_cmd
 	 */
 	STA_CONFIG_CMD = 0xA,
 	/**
@@ -563,7 +563,7 @@ enum iwl_fw_sta_type {
 }; /* STATION_TYPE_E_VER_1 */
 
 /**
- * struct iwl_mvm_sta_cfg_cmd - cmd structure to add a peer sta to the uCode's
+ * struct iwl_sta_cfg_cmd - cmd structure to add a peer sta to the uCode's
  *	station table
  * ( STA_CONFIG_CMD = 0xA )
  *
@@ -595,7 +595,7 @@ enum iwl_fw_sta_type {
  *	capa
  * @htc_flags: which features are supported in HTC
  */
-struct iwl_mvm_sta_cfg_cmd {
+struct iwl_sta_cfg_cmd {
 	__le32 sta_id;
 	__le32 link_id;
 	u8 peer_mld_address[ETH_ALEN];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index 071de9372843..759b77d555b7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -46,7 +46,7 @@ u32 iwl_mvm_sta_fw_id_mask(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 }
 
 static int iwl_mvm_mld_send_sta_cmd(struct iwl_mvm *mvm,
-				    struct iwl_mvm_sta_cfg_cmd *cmd)
+				    struct iwl_sta_cfg_cmd *cmd)
 {
 	int ret = iwl_mvm_send_cmd_pdu(mvm,
 				       WIDE_ID(MAC_CONF_GROUP, STA_CONFIG_CMD),
@@ -63,7 +63,7 @@ static int iwl_mvm_mld_add_int_sta_to_fw(struct iwl_mvm *mvm,
 					 struct iwl_mvm_int_sta *sta,
 					 const u8 *addr, int link_id)
 {
-	struct iwl_mvm_sta_cfg_cmd cmd;
+	struct iwl_sta_cfg_cmd cmd;
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -438,7 +438,7 @@ static int iwl_mvm_mld_cfg_sta(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	struct iwl_mvm_vif *mvm_vif = iwl_mvm_vif_from_mac80211(vif);
 	struct iwl_mvm_vif_link_info *link_info =
 					mvm_vif->link[link_conf->link_id];
-	struct iwl_mvm_sta_cfg_cmd cmd = {
+	struct iwl_sta_cfg_cmd cmd = {
 		.sta_id = cpu_to_le32(mvm_link_sta->sta_id),
 		.station_type = cpu_to_le32(mvm_sta->sta_type),
 	};
-- 
cgit v1.3-3-g829e


From 530addf2d21fe11bffd1c441b541ab7047bbfd3a Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 1 Sep 2024 07:17:54 +0300
Subject: wifi: iwlwifi: s/iwl_mvm_remove_sta_cmd/iwl_remove_sta_cmd

This is not mvm specific.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240901071542.57efe93c2702.I4619885f691cc295cc440a62f23405392da338f4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h | 6 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c    | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 6dd9401596e9..c46e24fc6a1e 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -50,7 +50,7 @@ enum iwl_mac_conf_subcmd_ids {
 	 */
 	AUX_STA_CMD = 0xB,
 	/**
-	 * @STA_REMOVE_CMD: &struct iwl_mvm_remove_sta_cmd
+	 * @STA_REMOVE_CMD: &struct iwl_remove_sta_cmd
 	 */
 	STA_REMOVE_CMD = 0xC,
 	/**
@@ -636,13 +636,13 @@ struct iwl_mvm_aux_sta_cmd {
 } __packed; /* AUX_STA_CMD_API_S_VER_1 */
 
 /**
- * struct iwl_mvm_remove_sta_cmd - a cmd structure to remove a sta added by
+ * struct iwl_remove_sta_cmd - a cmd structure to remove a sta added by
  *	STA_CONFIG_CMD or AUX_STA_CONFIG_CMD
  * ( STA_REMOVE_CMD = 0xC )
  *
  * @sta_id: index of station to remove
  */
-struct iwl_mvm_remove_sta_cmd {
+struct iwl_remove_sta_cmd {
 	__le32 sta_id;
 } __packed; /* REMOVE_STA_API_S_VER_1 */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index 759b77d555b7..28a9d90ad1cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -94,7 +94,7 @@ static int iwl_mvm_mld_add_int_sta_to_fw(struct iwl_mvm *mvm,
  */
 static int iwl_mvm_mld_rm_sta_from_fw(struct iwl_mvm *mvm, u32 sta_id)
 {
-	struct iwl_mvm_remove_sta_cmd rm_sta_cmd = {
+	struct iwl_remove_sta_cmd rm_sta_cmd = {
 		.sta_id = cpu_to_le32(sta_id),
 	};
 	int ret;
-- 
cgit v1.3-3-g829e


From 5b0c478378e5c82c4c372cf194a2438f8743abcf Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 1 Sep 2024 07:17:55 +0300
Subject: wifi: iwlwifi: mvm: remove mvm prefix from iwl_mvm_tx_resp*

These are not mvm specific

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240901071542.22e28b56da2c.Ib859a05ed133fa5a1426c5feffa8999a18bba6f2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/commands.h |  4 ++--
 drivers/net/wireless/intel/iwlwifi/fw/api/tx.h       | 12 ++++++------
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c    |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h         |  4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c         |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c          | 12 ++++++------
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 852ea5d14051..2f40e69db318 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -147,8 +147,8 @@ enum iwl_legacy_cmds {
 	/**
 	 * @TX_CMD: uses &struct iwl_tx_cmd or &struct iwl_tx_cmd_gen2 or
 	 *	&struct iwl_tx_cmd_gen3,
-	 *	response in &struct iwl_mvm_tx_resp or
-	 *	&struct iwl_mvm_tx_resp_v3
+	 *	response in &struct iwl_tx_resp or
+	 *	&struct iwl_tx_resp_v3
 	 */
 	TX_CMD = 0x1c,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
index c5277e2f8cd4..f3bf2e087a40 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
@@ -486,7 +486,7 @@ struct agg_tx_status {
 #define IWL_MVM_TX_RES_GET_RA(_ra_tid) ((_ra_tid) >> 4)
 
 /**
- * struct iwl_mvm_tx_resp_v3 - notifies that fw is TXing a packet
+ * struct iwl_tx_resp_v3 - notifies that fw is TXing a packet
  * ( REPLY_TX = 0x1c )
  * @frame_count: 1 no aggregation, >1 aggregation
  * @bt_kill_count: num of times blocked by bluetooth (unused for agg)
@@ -517,7 +517,7 @@ struct agg_tx_status {
  * After the array of statuses comes the SSN of the SCD. Look at
  * %iwl_mvm_get_scd_ssn for more details.
  */
-struct iwl_mvm_tx_resp_v3 {
+struct iwl_tx_resp_v3 {
 	u8 frame_count;
 	u8 bt_kill_count;
 	u8 failure_rts;
@@ -543,7 +543,7 @@ struct iwl_mvm_tx_resp_v3 {
 } __packed; /* TX_RSP_API_S_VER_3 */
 
 /**
- * struct iwl_mvm_tx_resp - notifies that fw is TXing a packet
+ * struct iwl_tx_resp - notifies that fw is TXing a packet
  * ( REPLY_TX = 0x1c )
  * @frame_count: 1 no aggregation, >1 aggregation
  * @bt_kill_count: num of times blocked by bluetooth (unused for agg)
@@ -575,7 +575,7 @@ struct iwl_mvm_tx_resp_v3 {
  * After the array of statuses comes the SSN of the SCD. Look at
  * %iwl_mvm_get_scd_ssn for more details.
  */
-struct iwl_mvm_tx_resp {
+struct iwl_tx_resp {
 	u8 frame_count;
 	u8 bt_kill_count;
 	u8 failure_rts;
@@ -823,7 +823,7 @@ struct iwl_mac_beacon_cmd {
 	     */
 
 struct iwl_beacon_notif {
-	struct iwl_mvm_tx_resp beacon_notify_hdr;
+	struct iwl_tx_resp beacon_notify_hdr;
 	__le64 tsf;
 	__le32 ibss_mgr_status;
 } __packed;
@@ -836,7 +836,7 @@ struct iwl_beacon_notif {
  * @gp2: last beacon time in gp2
  */
 struct iwl_extended_beacon_notif_v5 {
-	struct iwl_mvm_tx_resp beacon_notify_hdr;
+	struct iwl_tx_resp beacon_notify_hdr;
 	__le64 tsf;
 	__le32 ibss_mgr_status;
 	__le32 gp2;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index bb864ec2e22a..bbddd984ddf9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1528,7 +1528,7 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm,
 	mvm->ap_last_beacon_gp2 = le32_to_cpu(beacon->gp2);
 
 	if (!iwl_mvm_is_short_beacon_notif_supported(mvm)) {
-		struct iwl_mvm_tx_resp *beacon_notify_hdr =
+		struct iwl_tx_resp *beacon_notify_hdr =
 			&beacon_v5->beacon_notify_hdr;
 
 		if (unlikely(pkt_len < sizeof(*beacon_v5)))
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index ec9b8be12766..be637f6e4074 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1708,9 +1708,9 @@ static inline struct agg_tx_status *
 iwl_mvm_get_agg_status(struct iwl_mvm *mvm, void *tx_resp)
 {
 	if (iwl_mvm_has_new_tx_api(mvm))
-		return &((struct iwl_mvm_tx_resp *)tx_resp)->status;
+		return &((struct iwl_tx_resp *)tx_resp)->status;
 	else
-		return ((struct iwl_mvm_tx_resp_v3 *)tx_resp)->status;
+		return ((struct iwl_tx_resp_v3 *)tx_resp)->status;
 }
 
 static inline bool iwl_mvm_is_tt_in_fw(struct iwl_mvm *mvm)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index d3ab959f497a..42b94c504041 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -368,7 +368,7 @@ struct iwl_rx_handlers {
  */
 static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 	RX_HANDLER(TX_CMD, iwl_mvm_rx_tx_cmd, RX_HANDLER_SYNC,
-		   struct iwl_mvm_tx_resp),
+		   struct iwl_tx_resp),
 	RX_HANDLER(BA_NOTIF, iwl_mvm_rx_ba_notif, RX_HANDLER_SYNC,
 		   struct iwl_mvm_ba_notif),
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index db926b2f4d8d..ca026b5256ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -1680,7 +1680,7 @@ static void iwl_mvm_tx_status_check_trigger(struct iwl_mvm *mvm,
  * For 22000-series and lower, this is just 12 bits. For later, 16 bits.
  */
 static inline u32 iwl_mvm_get_scd_ssn(struct iwl_mvm *mvm,
-				      struct iwl_mvm_tx_resp *tx_resp)
+				      struct iwl_tx_resp *tx_resp)
 {
 	u32 val = le32_to_cpup((__le32 *)iwl_mvm_get_agg_status(mvm, tx_resp) +
 			       tx_resp->frame_count);
@@ -1696,8 +1696,8 @@ static void iwl_mvm_rx_tx_cmd_single(struct iwl_mvm *mvm,
 	struct ieee80211_sta *sta;
 	u16 sequence = le16_to_cpu(pkt->hdr.sequence);
 	int txq_id = SEQ_TO_QUEUE(sequence);
-	/* struct iwl_mvm_tx_resp_v3 is almost the same */
-	struct iwl_mvm_tx_resp *tx_resp = (void *)pkt->data;
+	/* struct iwl_tx_resp_v3 is almost the same */
+	struct iwl_tx_resp *tx_resp = (void *)pkt->data;
 	int sta_id = IWL_MVM_TX_RES_GET_RA(tx_resp->ra_tid);
 	int tid = IWL_MVM_TX_RES_GET_TID(tx_resp->ra_tid);
 	struct agg_tx_status *agg_status =
@@ -1954,7 +1954,7 @@ static const char *iwl_get_agg_tx_status(u16 status)
 static void iwl_mvm_rx_tx_cmd_agg_dbg(struct iwl_mvm *mvm,
 				      struct iwl_rx_packet *pkt)
 {
-	struct iwl_mvm_tx_resp *tx_resp = (void *)pkt->data;
+	struct iwl_tx_resp *tx_resp = (void *)pkt->data;
 	struct agg_tx_status *frame_status =
 		iwl_mvm_get_agg_status(mvm, tx_resp);
 	int i;
@@ -1988,7 +1988,7 @@ static void iwl_mvm_rx_tx_cmd_agg_dbg(struct iwl_mvm *mvm,
 static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm,
 				  struct iwl_rx_packet *pkt)
 {
-	struct iwl_mvm_tx_resp *tx_resp = (void *)pkt->data;
+	struct iwl_tx_resp *tx_resp = (void *)pkt->data;
 	int sta_id = IWL_MVM_TX_RES_GET_RA(tx_resp->ra_tid);
 	int tid = IWL_MVM_TX_RES_GET_TID(tx_resp->ra_tid);
 	u16 sequence = le16_to_cpu(pkt->hdr.sequence);
@@ -2029,7 +2029,7 @@ static void iwl_mvm_rx_tx_cmd_agg(struct iwl_mvm *mvm,
 void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_mvm_tx_resp *tx_resp = (void *)pkt->data;
+	struct iwl_tx_resp *tx_resp = (void *)pkt->data;
 
 	if (tx_resp->frame_count == 1)
 		iwl_mvm_rx_tx_cmd_single(mvm, pkt);
-- 
cgit v1.3-3-g829e


From 36dc21bce962a56f748eb3711f5f4e2c70544d06 Mon Sep 17 00:00:00 2001
From: Daniel Gabay <daniel.gabay@intel.com>
Date: Sun, 1 Sep 2024 07:17:56 +0300
Subject: wifi: iwlwifi: mvm: Remove unused last_sub_index from reorder buffer

The last_sub_index field is not used and appears to be a leftover
from a previous implementation, remove it.

Signed-off-by: Daniel Gabay <daniel.gabay@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240901071542.da75cfef9144.I6e1fb635b2893618e6bd28501fb858042d8aa44e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  | 2 --
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 6 +-----
 2 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index be637f6e4074..650b562a22cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -774,7 +774,6 @@ struct iwl_mvm_tcm {
  * @num_stored: number of mpdus stored in the buffer
  * @queue: queue of this reorder buffer
  * @last_amsdu: track last ASMDU SN for duplication detection
- * @last_sub_index: track ASMDU sub frame index for duplication detection
  * @valid: reordering is valid for this queue
  * @lock: protect reorder buffer internal state
  */
@@ -783,7 +782,6 @@ struct iwl_mvm_reorder_buffer {
 	u16 num_stored;
 	int queue;
 	u16 last_amsdu;
-	u8 last_sub_index;
 	bool valid;
 	spinlock_t lock;
 } ____cacheline_aligned_in_smp;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index ae0f2aabddc3..65f8933c34b4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -729,8 +729,6 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 	bool last_subframe =
 		desc->amsdu_info & IWL_RX_MPDU_AMSDU_LAST_SUBFRAME;
 	u8 tid = ieee80211_get_tid(hdr);
-	u8 sub_frame_idx = desc->amsdu_info &
-			   IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
 	struct iwl_mvm_reorder_buf_entry *entries;
 	u32 sta_mask;
 	int index;
@@ -843,10 +841,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm,
 	__skb_queue_tail(&entries[index].frames, skb);
 	buffer->num_stored++;
 
-	if (amsdu) {
+	if (amsdu)
 		buffer->last_amsdu = sn;
-		buffer->last_sub_index = sub_frame_idx;
-	}
 
 	/*
 	 * We cannot trust NSSN for AMSDU sub-frames that are not the last.
-- 
cgit v1.3-3-g829e


From a032b5fc24fc1ddff0dce662b2e2d367cc73f040 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 1 Sep 2024 07:17:57 +0300
Subject: wifi: iwlwifi: mvm: properly set the rates in link cmd

When a channel ctx is assigned to a link, we set the
LINK_CONTEXT_MODIFY_RATES_INFO to indicate that the rate fields are now
valid. But then we always take the rates of 2.4 GHz regardless of actual
used band.
This is because we are getting the band from bss_conf->chanctx_conf, but
this is assigned only after drv_assign_vif_chanctx returns, so we take
the bands of 2.4 GHz.
Fix it by taking the band from the iwl_mvm_link_info::phy_ctxt instead,
as this has already assigned in this point.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20240901071542.11c2d3609609.I8fa59e29b6bb38e5d06f3536d54dfb2c5d5bab11@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/link.c     |  2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 17 ++++++++---------
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      |  2 +-
 3 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
index bc8d06127747..2b0652168002 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
@@ -264,7 +264,7 @@ int iwl_mvm_link_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 	if (vif->type == NL80211_IFTYPE_ADHOC && link_conf->bssid)
 		memcpy(cmd.ibss_bssid_addr, link_conf->bssid, ETH_ALEN);
 
-	iwl_mvm_set_fw_basic_rates(mvm, vif, link_conf,
+	iwl_mvm_set_fw_basic_rates(mvm, vif, link_info,
 				   &cmd.cck_rates, &cmd.ofdm_rates);
 
 	cmd.cck_short_preamble = cpu_to_le32(link_conf->use_short_preamble);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index bbddd984ddf9..a7a10e716e65 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -413,19 +413,18 @@ static void iwl_mvm_ack_rates(struct iwl_mvm *mvm,
 }
 
 void iwl_mvm_set_fw_basic_rates(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-				struct ieee80211_bss_conf *link_conf,
+				struct iwl_mvm_vif_link_info *link_info,
 				__le32 *cck_rates, __le32 *ofdm_rates)
 {
-	struct ieee80211_chanctx_conf *chanctx;
+	struct iwl_mvm_phy_ctxt *phy_ctxt;
 	u8 cck_ack_rates = 0, ofdm_ack_rates = 0;
+	enum nl80211_band band = NL80211_BAND_2GHZ;
 
-	rcu_read_lock();
-	chanctx = rcu_dereference(link_conf->chanctx_conf);
-	iwl_mvm_ack_rates(mvm, vif, chanctx ? chanctx->def.chan->band
-					    : NL80211_BAND_2GHZ,
-			  &cck_ack_rates, &ofdm_ack_rates);
+	phy_ctxt = link_info->phy_ctxt;
+	if (phy_ctxt && phy_ctxt->channel)
+		band = phy_ctxt->channel->band;
 
-	rcu_read_unlock();
+	iwl_mvm_ack_rates(mvm, vif, band, &cck_ack_rates, &ofdm_ack_rates);
 
 	*cck_rates = cpu_to_le32((u32)cck_ack_rates);
 	*ofdm_rates = cpu_to_le32((u32)ofdm_ack_rates);
@@ -563,7 +562,7 @@ static void iwl_mvm_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 	else
 		eth_broadcast_addr(cmd->bssid_addr);
 
-	iwl_mvm_set_fw_basic_rates(mvm, vif, &vif->bss_conf, &cmd->cck_rates,
+	iwl_mvm_set_fw_basic_rates(mvm, vif, &mvmvif->deflink, &cmd->cck_rates,
 				   &cmd->ofdm_rates);
 
 	cmd->cck_short_preamble =
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 650b562a22cd..c9b69c3a61fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2016,7 +2016,7 @@ int iwl_mvm_phy_send_rlc(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt,
 void iwl_mvm_prepare_mac_removal(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif);
 void iwl_mvm_set_fw_basic_rates(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-				struct ieee80211_bss_conf *link_conf,
+				struct iwl_mvm_vif_link_info *link_info,
 				__le32 *cck_rates, __le32 *ofdm_rates);
 void iwl_mvm_set_fw_protection_flags(struct iwl_mvm *mvm,
 				     struct ieee80211_vif *vif,
-- 
cgit v1.3-3-g829e


From 81b4eb62878a6b6722f28e64e6c7d62bba07292b Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:18 +0800
Subject: net: stmmac: dwmac-sun8i: Use for_each_child_of_node_scoped()

Avoid need to manually handle of_node_put() by using
for_each_child_of_node_scoped(), which can simplfy code.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index cc93f73a380e..4a0ae92b3055 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -774,8 +774,8 @@ static int sun8i_dwmac_reset(struct stmmac_priv *priv)
 static int get_ephy_nodes(struct stmmac_priv *priv)
 {
 	struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
-	struct device_node *mdio_mux, *iphynode;
 	struct device_node *mdio_internal;
+	struct device_node *mdio_mux;
 	int ret;
 
 	mdio_mux = of_get_child_by_name(priv->device->of_node, "mdio-mux");
@@ -793,7 +793,7 @@ static int get_ephy_nodes(struct stmmac_priv *priv)
 	}
 
 	/* Seek for internal PHY */
-	for_each_child_of_node(mdio_internal, iphynode) {
+	for_each_child_of_node_scoped(mdio_internal, iphynode) {
 		gmac->ephy_clk = of_clk_get(iphynode, 0);
 		if (IS_ERR(gmac->ephy_clk))
 			continue;
@@ -801,14 +801,12 @@ static int get_ephy_nodes(struct stmmac_priv *priv)
 		if (IS_ERR(gmac->rst_ephy)) {
 			ret = PTR_ERR(gmac->rst_ephy);
 			if (ret == -EPROBE_DEFER) {
-				of_node_put(iphynode);
 				of_node_put(mdio_internal);
 				return ret;
 			}
 			continue;
 		}
 		dev_info(priv->device, "Found internal PHY node\n");
-		of_node_put(iphynode);
 		of_node_put(mdio_internal);
 		return 0;
 	}
-- 
cgit v1.3-3-g829e


From 51c884291a94fd6598427d7d6c211f1f20780d57 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:19 +0800
Subject: net: dsa: realtek: Use for_each_child_of_node_scoped()

Avoid need to manually handle of_node_put() by using
for_each_child_of_node_scoped(), which can simplfy code.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/realtek/rtl8366rb.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 9e821b42e5f3..11243f89c98a 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -1009,8 +1009,8 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 
 static int rtl8366rb_setup_leds(struct realtek_priv *priv)
 {
-	struct device_node *leds_np, *led_np;
 	struct dsa_switch *ds = &priv->ds;
+	struct device_node *leds_np;
 	struct dsa_port *dp;
 	int ret = 0;
 
@@ -1025,13 +1025,11 @@ static int rtl8366rb_setup_leds(struct realtek_priv *priv)
 			continue;
 		}
 
-		for_each_child_of_node(leds_np, led_np) {
+		for_each_child_of_node_scoped(leds_np, led_np) {
 			ret = rtl8366rb_setup_led(priv, dp,
 						  of_fwnode_handle(led_np));
-			if (ret) {
-				of_node_put(led_np);
+			if (ret)
 				break;
-			}
 		}
 
 		of_node_put(leds_np);
-- 
cgit v1.3-3-g829e


From 1dce520abd461efcaf4a5a942d8eb833eef52d0b Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:20 +0800
Subject: net: phy: Use for_each_available_child_of_node_scoped()

Avoid need to manually handle of_node_put() by using
for_each_available_child_of_node_scoped(), which can simplfy code.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy_device.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8f5314c1fecc..7c4a09455493 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -3407,7 +3407,7 @@ static int of_phy_led(struct phy_device *phydev,
 static int of_phy_leds(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
-	struct device_node *leds, *led;
+	struct device_node *leds;
 	int err;
 
 	if (!IS_ENABLED(CONFIG_OF_MDIO))
@@ -3420,10 +3420,9 @@ static int of_phy_leds(struct phy_device *phydev)
 	if (!leds)
 		return 0;
 
-	for_each_available_child_of_node(leds, led) {
+	for_each_available_child_of_node_scoped(leds, led) {
 		err = of_phy_led(phydev, led);
 		if (err) {
-			of_node_put(led);
 			phy_leds_unregister(phydev);
 			return err;
 		}
-- 
cgit v1.3-3-g829e


From b00f7f4f8e936da55f2e6c7fd96391ef54c145fc Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:21 +0800
Subject: net: mdio: mux-mmioreg: Simplified with scoped function

Avoids the need for manual cleanup of_node_put() in early exits
from the loop by using for_each_available_child_of_node_scoped().

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mdio/mdio-mux-mmioreg.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/mdio/mdio-mux-mmioreg.c b/drivers/net/mdio/mdio-mux-mmioreg.c
index de08419d0c98..4d87e61fec7b 100644
--- a/drivers/net/mdio/mdio-mux-mmioreg.c
+++ b/drivers/net/mdio/mdio-mux-mmioreg.c
@@ -96,7 +96,7 @@ static int mdio_mux_mmioreg_switch_fn(int current_child, int desired_child,
 
 static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
 {
-	struct device_node *np2, *np = pdev->dev.of_node;
+	struct device_node *np = pdev->dev.of_node;
 	struct mdio_mux_mmioreg_state *s;
 	struct resource res;
 	const __be32 *iprop;
@@ -139,20 +139,18 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
 	 * Verify that the 'reg' property of each child MDIO bus does not
 	 * set any bits outside of the 'mask'.
 	 */
-	for_each_available_child_of_node(np, np2) {
+	for_each_available_child_of_node_scoped(np, np2) {
 		u64 reg;
 
 		if (of_property_read_reg(np2, 0, &reg, NULL)) {
 			dev_err(&pdev->dev, "mdio-mux child node %pOF is "
 				"missing a 'reg' property\n", np2);
-			of_node_put(np2);
 			return -ENODEV;
 		}
 		if ((u32)reg & ~s->mask) {
 			dev_err(&pdev->dev, "mdio-mux child node %pOF has "
 				"a 'reg' value with unmasked bits\n",
 				np2);
-			of_node_put(np2);
 			return -ENODEV;
 		}
 	}
-- 
cgit v1.3-3-g829e


From 4078513fc86c354e768954e8ebb67bc2bbddf69d Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:22 +0800
Subject: net: mdio: mux-mmioreg: Simplified with dev_err_probe()

Use the dev_err_probe() helper to simplify code.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mdio/mdio-mux-mmioreg.c | 48 ++++++++++++++++---------------------
 1 file changed, 20 insertions(+), 28 deletions(-)

diff --git a/drivers/net/mdio/mdio-mux-mmioreg.c b/drivers/net/mdio/mdio-mux-mmioreg.c
index 4d87e61fec7b..b70e6d1ad429 100644
--- a/drivers/net/mdio/mdio-mux-mmioreg.c
+++ b/drivers/net/mdio/mdio-mux-mmioreg.c
@@ -109,30 +109,25 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ret = of_address_to_resource(np, 0, &res);
-	if (ret) {
-		dev_err(&pdev->dev, "could not obtain memory map for node %pOF\n",
-			np);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "could not obtain memory map for node %pOF\n", np);
 	s->phys = res.start;
 
 	s->iosize = resource_size(&res);
 	if (s->iosize != sizeof(uint8_t) &&
 	    s->iosize != sizeof(uint16_t) &&
-	    s->iosize != sizeof(uint32_t)) {
-		dev_err(&pdev->dev, "only 8/16/32-bit registers are supported\n");
-		return -EINVAL;
-	}
+	    s->iosize != sizeof(uint32_t))
+		return dev_err_probe(&pdev->dev, -EINVAL,
+				     "only 8/16/32-bit registers are supported\n");
 
 	iprop = of_get_property(np, "mux-mask", &len);
-	if (!iprop || len != sizeof(uint32_t)) {
-		dev_err(&pdev->dev, "missing or invalid mux-mask property\n");
-		return -ENODEV;
-	}
-	if (be32_to_cpup(iprop) >= BIT(s->iosize * 8)) {
-		dev_err(&pdev->dev, "only 8/16/32-bit registers are supported\n");
-		return -EINVAL;
-	}
+	if (!iprop || len != sizeof(uint32_t))
+		return dev_err_probe(&pdev->dev, -ENODEV,
+				     "missing or invalid mux-mask property\n");
+	if (be32_to_cpup(iprop) >= BIT(s->iosize * 8))
+		return dev_err_probe(&pdev->dev, -EINVAL,
+				     "only 8/16/32-bit registers are supported\n");
 	s->mask = be32_to_cpup(iprop);
 
 	/*
@@ -142,17 +137,14 @@ static int mdio_mux_mmioreg_probe(struct platform_device *pdev)
 	for_each_available_child_of_node_scoped(np, np2) {
 		u64 reg;
 
-		if (of_property_read_reg(np2, 0, &reg, NULL)) {
-			dev_err(&pdev->dev, "mdio-mux child node %pOF is "
-				"missing a 'reg' property\n", np2);
-			return -ENODEV;
-		}
-		if ((u32)reg & ~s->mask) {
-			dev_err(&pdev->dev, "mdio-mux child node %pOF has "
-				"a 'reg' value with unmasked bits\n",
-				np2);
-			return -ENODEV;
-		}
+		if (of_property_read_reg(np2, 0, &reg, NULL))
+			return dev_err_probe(&pdev->dev, -ENODEV,
+					     "mdio-mux child node %pOF is missing a 'reg' property\n",
+					     np2);
+		if ((u32)reg & ~s->mask)
+			return dev_err_probe(&pdev->dev, -ENODEV,
+					     "mdio-mux child node %pOF has a 'reg' value with unmasked bits\n",
+					     np2);
 	}
 
 	ret = mdio_mux_init(&pdev->dev, pdev->dev.of_node,
-- 
cgit v1.3-3-g829e


From 3a3eea209e6d3c1ad3b8b3155a4350caf1d7fa16 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:23 +0800
Subject: net: mv643xx_eth: Simplify with scoped for each OF child loop

Use scoped for_each_available_child_of_node_scoped() when iterating
over device nodes to make code a bit simpler.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/mv643xx_eth.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index f35ae2c88091..9e80899546d9 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -2802,7 +2802,7 @@ port_err:
 static int mv643xx_eth_shared_of_probe(struct platform_device *pdev)
 {
 	struct mv643xx_eth_shared_platform_data *pd;
-	struct device_node *pnp, *np = pdev->dev.of_node;
+	struct device_node *np = pdev->dev.of_node;
 	int ret;
 
 	/* bail out if not registered from DT */
@@ -2816,10 +2816,9 @@ static int mv643xx_eth_shared_of_probe(struct platform_device *pdev)
 
 	mv643xx_eth_property(np, "tx-checksum-limit", pd->tx_csum_limit);
 
-	for_each_available_child_of_node(np, pnp) {
+	for_each_available_child_of_node_scoped(np, pnp) {
 		ret = mv643xx_eth_shared_of_add_port(pdev, pnp);
 		if (ret) {
-			of_node_put(pnp);
 			mv643xx_eth_shared_of_remove();
 			return ret;
 		}
-- 
cgit v1.3-3-g829e


From f834d572b7e995fa443f802da0f19d9c1285f41b Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:24 +0800
Subject: net: dsa: microchip: Use scoped function to simplfy code

Avoids the need for manual cleanup of_node_put() in early exits
from the loop by using for_each_available_child_of_node_scoped().

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/microchip/ksz_common.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 6609bf271ad0..cd116de3ddb8 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -4717,7 +4717,7 @@ static int ksz_parse_drive_strength(struct ksz_device *dev)
 int ksz_switch_register(struct ksz_device *dev)
 {
 	const struct ksz_chip_data *info;
-	struct device_node *port, *ports;
+	struct device_node *ports;
 	phy_interface_t interface;
 	unsigned int port_num;
 	int ret;
@@ -4803,12 +4803,11 @@ int ksz_switch_register(struct ksz_device *dev)
 		if (!ports)
 			ports = of_get_child_by_name(dev->dev->of_node, "ports");
 		if (ports) {
-			for_each_available_child_of_node(ports, port) {
+			for_each_available_child_of_node_scoped(ports, port) {
 				if (of_property_read_u32(port, "reg",
 							 &port_num))
 					continue;
 				if (!(dev->port_mask & BIT(port_num))) {
-					of_node_put(port);
 					of_node_put(ports);
 					return -EINVAL;
 				}
-- 
cgit v1.3-3-g829e


From e8ac8974451e6731cd3f4db6a664cc59d73c0d7b Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Fri, 30 Aug 2024 11:13:25 +0800
Subject: net: bcmasp: Simplify with scoped for each OF child loop

Use scoped for_each_available_child_of_node_scoped() when
iterating over device nodes to make code a bit simpler.

Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Justin Chen <justin.chen@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/asp2/bcmasp.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
index 20c6529ec135..297c2682a9cf 100644
--- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c
+++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c
@@ -1300,9 +1300,9 @@ static void bcmasp_remove_intfs(struct bcmasp_priv *priv)
 
 static int bcmasp_probe(struct platform_device *pdev)
 {
-	struct device_node *ports_node, *intf_node;
 	const struct bcmasp_plat_data *pdata;
 	struct device *dev = &pdev->dev;
+	struct device_node *ports_node;
 	struct bcmasp_priv *priv;
 	struct bcmasp_intf *intf;
 	int ret = 0, count = 0;
@@ -1374,12 +1374,11 @@ static int bcmasp_probe(struct platform_device *pdev)
 	}
 
 	i = 0;
-	for_each_available_child_of_node(ports_node, intf_node) {
+	for_each_available_child_of_node_scoped(ports_node, intf_node) {
 		intf = bcmasp_interface_create(priv, intf_node, i);
 		if (!intf) {
 			dev_err(dev, "Cannot create eth interface %d\n", i);
 			bcmasp_remove_intfs(priv);
-			of_node_put(intf_node);
 			ret = -ENOMEM;
 			goto of_put_exit;
 		}
-- 
cgit v1.3-3-g829e


From 5ceb87dc76ab269c940541ad9487cf0f3c0c793d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 30 Aug 2024 11:22:39 +0200
Subject: selftests: netfilter: nft_queue.sh: fix spurious timeout on debug
 kernel

The sctp selftest is very slow on debug kernels.

Its possible that the nf_queue listener program exits due to timeout
before first sctp packet is processed.

In this case socat hangs until script times out.
Fix this by removing the -t option where possible and kill the test
program once the file transfer/socat has exited.

-t sets SO_RCVTIMEO, its inteded for the 'ping' part of the selftest
where we want to make sure that packets get reinjected properly without
skipping a second queue request.

While at it, add a helper to compare the (binary) files instead of diff.
The 'diff' part was copied from a another sub-test that compares text.

Let helper dump file sizes on error so we can see the progress made.

Tested on an old 2010-ish box with a debug kernel and 100 iterations.

This is a followup to the earlier filesize reduction change.

Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20240829080109.GB30766@breakpoint.cc/
Fixes: 0a8b08c554da ("selftests: netfilter: nft_queue.sh: reduce test file size for debug build")
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20240830092254.8029-1-fw@strlen.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/netfilter/nft_queue.sh | 62 ++++++++++++++--------
 1 file changed, 40 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 9e5f423bff09..d66e3c4dfec6 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -8,7 +8,7 @@
 
 source lib.sh
 ret=0
-timeout=2
+timeout=5
 
 cleanup()
 {
@@ -255,17 +255,19 @@ listener_ready()
 
 test_tcp_forward()
 {
-	ip netns exec "$nsrouter" ./nf_queue -q 2 -t "$timeout" &
+	ip netns exec "$nsrouter" ./nf_queue -q 2 &
 	local nfqpid=$!
 
 	timeout 5 ip netns exec "$ns2" socat -u TCP-LISTEN:12345 STDOUT >/dev/null &
 	local rpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$ns2"
+	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 2
 
 	ip netns exec "$ns1" socat -u STDIN TCP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
 
 	wait "$rpid" && echo "PASS: tcp and nfqueue in forward chain"
+	kill "$nfqpid"
 }
 
 test_tcp_localhost()
@@ -273,26 +275,29 @@ test_tcp_localhost()
 	timeout 5 ip netns exec "$nsrouter" socat -u TCP-LISTEN:12345 STDOUT >/dev/null &
 	local rpid=$!
 
-	ip netns exec "$nsrouter" ./nf_queue -q 3 -t "$timeout" &
+	ip netns exec "$nsrouter" ./nf_queue -q 3 &
 	local nfqpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" listener_ready "$nsrouter"
+	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 3
 
 	ip netns exec "$nsrouter" socat -u STDIN TCP:127.0.0.1:12345 <"$TMPINPUT" >/dev/null
 
 	wait "$rpid" && echo "PASS: tcp via loopback"
-	wait 2>/dev/null
+	kill "$nfqpid"
 }
 
 test_tcp_localhost_connectclose()
 {
-	ip netns exec "$nsrouter" ./connect_close -p 23456 -t "$timeout" &
-	ip netns exec "$nsrouter" ./nf_queue -q 3 -t "$timeout" &
+	ip netns exec "$nsrouter" ./nf_queue -q 3 &
+	local nfqpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$nsrouter" 3
 
+	timeout 10 ip netns exec "$nsrouter" ./connect_close -p 23456 -t 3
+
+	kill "$nfqpid"
 	wait && echo "PASS: tcp via loopback with connect/close"
-	wait 2>/dev/null
 }
 
 test_tcp_localhost_requeue()
@@ -357,7 +362,7 @@ table inet filter {
 	}
 }
 EOF
-	ip netns exec "$ns1" ./nf_queue -q 1 -t "$timeout" &
+	ip netns exec "$ns1" ./nf_queue -q 1 &
 	local nfqpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$ns1" 1
@@ -367,6 +372,7 @@ EOF
 	for n in output post; do
 		for d in tvrf eth0; do
 			if ! ip netns exec "$ns1" nft list chain inet filter "$n" | grep -q "oifname \"$d\" icmp type echo-request counter packets 1"; then
+				kill "$nfqpid"
 				echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2
 				ip netns exec "$ns1" nft list ruleset
 				ret=1
@@ -375,8 +381,8 @@ EOF
 		done
 	done
 
-	wait "$nfqpid" && echo "PASS: icmp+nfqueue via vrf"
-	wait 2>/dev/null
+	kill "$nfqpid"
+	echo "PASS: icmp+nfqueue via vrf"
 }
 
 sctp_listener_ready()
@@ -384,6 +390,22 @@ sctp_listener_ready()
 	ss -S -N "$1" -ln -o "sport = :12345" | grep -q 12345
 }
 
+check_output_files()
+{
+	local f1="$1"
+	local f2="$2"
+	local err="$3"
+
+	if ! cmp "$f1" "$f2" ; then
+		echo "FAIL: $err: input and output file differ" 1>&2
+		echo -n " Input file" 1>&2
+		ls -l "$f1" 1>&2
+		echo -n "Output file" 1>&2
+		ls -l "$f2" 1>&2
+		ret=1
+	fi
+}
+
 test_sctp_forward()
 {
 	ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF
@@ -400,7 +422,7 @@ EOF
 
 	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
 
-	ip netns exec "$nsrouter" ./nf_queue -q 10 -G -t "$timeout" &
+	ip netns exec "$nsrouter" ./nf_queue -q 10 -G &
 	local nfqpid=$!
 
 	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
@@ -411,11 +433,9 @@ EOF
 	fi
 
 	wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain"
+	kill "$nfqpid"
 
-	if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then
-		echo "FAIL: lost packets?!" 1>&2
-		exit 1
-	fi
+	check_output_files "$TMPINPUT" "$TMPFILE1" "sctp forward"
 }
 
 test_sctp_output()
@@ -429,14 +449,14 @@ table inet sctpq {
 }
 EOF
 	# reduce test file size, software segmentation causes sk wmem increase.
-	dd conv=sparse status=none if=/dev/zero bs=1M count=50 of="$TMPINPUT"
+	dd conv=sparse status=none if=/dev/zero bs=1M count=$((COUNT/2)) of="$TMPINPUT"
 
 	timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" &
 	local rpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2"
 
-	ip netns exec "$ns1" ./nf_queue -q 11 -t "$timeout" &
+	ip netns exec "$ns1" ./nf_queue -q 11 &
 	local nfqpid=$!
 
 	ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null
@@ -448,11 +468,9 @@ EOF
 
 	# must wait before checking completeness of output file.
 	wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO"
+	kill "$nfqpid"
 
-	if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then
-		echo "FAIL: lost packets?!" 1>&2
-		exit 1
-	fi
+	check_output_files "$TMPINPUT" "$TMPFILE1" "sctp output"
 }
 
 test_queue_removal()
@@ -468,7 +486,7 @@ table ip filter {
 	}
 }
 EOF
-	ip netns exec "$ns1" ./nf_queue -q 0 -d 30000 -t "$timeout" &
+	ip netns exec "$ns1" ./nf_queue -q 0 -d 30000 &
 	local nfqpid=$!
 
 	busywait "$BUSYWAIT_TIMEOUT" nf_queue_wait "$ns1" 0
-- 
cgit v1.3-3-g829e


From bd11198da8ac239c0e831ac476490fd38db9cc37 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 30 Aug 2024 17:33:36 +0800
Subject: cxgb3: Remove unused declarations

Commit 4d22de3e6cc4 ("Add support for the latest 1G/10G Chelsio adapter,
T3.") declared but never implemented these.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/chelsio/cxgb3/cxgb3_defs.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_defs.h b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_defs.h
index f04e81f33795..a08fc762a438 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_defs.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_defs.h
@@ -106,6 +106,4 @@ static inline struct t3c_tid_entry *lookup_atid(const struct tid_info *t,
 	return &e->t3c_tid;
 }
 
-int attach_t3cdev(struct t3cdev *dev);
-void detach_t3cdev(struct t3cdev *dev);
 #endif
-- 
cgit v1.3-3-g829e


From 17d8aa831aa0d7335e86d544441bfdf65bb3497f Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 30 Aug 2024 17:33:37 +0800
Subject: cxgb4: Remove unused declarations

Commit e2d14b42c25c ("cxgb4: Remove WOL get/set ethtool support") removed
t4_wol_magic_enable() and t4_wol_pat_enable() but leave declarations.

Commit 02d805dc5fe3 ("cxgb4: use new fw interface to get the VIN and smt
index") leave behind cxgb4_tp_smt_idx().

cxgb4_dcb_set_caps() is never implemented and used since introduction in
commit 76bcb31efc06 ("cxgb4 : Add DCBx support codebase and dcbnl_ops").

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h     | 5 -----
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h | 1 -
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h | 1 -
 3 files changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index fca9533bc011..bbf7641a0fc7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1958,11 +1958,6 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf);
 void t4_get_chan_txrate(struct adapter *adap, u64 *nic_rate, u64 *ofld_rate);
 void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid);
 
-void t4_wol_magic_enable(struct adapter *adap, unsigned int port,
-			 const u8 *addr);
-int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,
-		      u64 mask0, u64 mask1, unsigned int crc, bool enable);
-
 int t4_fw_hello(struct adapter *adap, unsigned int mbox, unsigned int evt_mbox,
 		enum dev_master master, enum dev_state *state);
 int t4_fw_bye(struct adapter *adap, unsigned int mbox);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
index 80c6627fe981..c80a93347a8c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.h
@@ -122,7 +122,6 @@ void cxgb4_dcb_version_init(struct net_device *);
 void cxgb4_dcb_reset(struct net_device *dev);
 void cxgb4_dcb_state_fsm(struct net_device *, enum cxgb4_dcb_state_input);
 void cxgb4_dcb_handle_fw_update(struct adapter *, const struct fw_port_cmd *);
-void cxgb4_dcb_set_caps(struct adapter *, const struct fw_port_cmd *);
 extern const struct dcbnl_rtnl_ops cxgb4_dcb_ops;
 
 static inline __u8 bitswap_1(unsigned char val)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index a9599ba26975..d8cafaa7ddb4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -508,7 +508,6 @@ unsigned int cxgb4_dbfifo_count(const struct net_device *dev, int lpfifo);
 unsigned int cxgb4_port_chan(const struct net_device *dev);
 unsigned int cxgb4_port_e2cchan(const struct net_device *dev);
 unsigned int cxgb4_port_viid(const struct net_device *dev);
-unsigned int cxgb4_tp_smt_idx(enum chip_type chip, unsigned int viid);
 unsigned int cxgb4_port_idx(const struct net_device *dev);
 unsigned int cxgb4_best_mtu(const unsigned short *mtus, unsigned short mtu,
 			    unsigned int *idx);
-- 
cgit v1.3-3-g829e


From f5f840de659b39e7b3f285a2bb5117dd27bf0912 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 30 Aug 2024 17:33:38 +0800
Subject: cxgb: Remove unused declarations

These functions were never implenmented since introduction in
commit 8199d3a79c22 ("[PATCH] A new 10GB Ethernet Driver by Chelsio
Communications")

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/chelsio/cxgb/common.h | 2 --
 drivers/net/ethernet/chelsio/cxgb/tp.h     | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb/common.h b/drivers/net/ethernet/chelsio/cxgb/common.h
index e56eff701395..304bb282ab03 100644
--- a/drivers/net/ethernet/chelsio/cxgb/common.h
+++ b/drivers/net/ethernet/chelsio/cxgb/common.h
@@ -329,8 +329,6 @@ irqreturn_t t1_slow_intr_handler(adapter_t *adapter);
 
 int t1_link_start(struct cphy *phy, struct cmac *mac, struct link_config *lc);
 const struct board_info *t1_get_board_info(unsigned int board_id);
-const struct board_info *t1_get_board_info_from_ids(unsigned int devid,
-						    unsigned short ssid);
 int t1_seeprom_read(adapter_t *adapter, u32 addr, __le32 *data);
 int t1_get_board_rev(adapter_t *adapter, const struct board_info *bi,
 		     struct adapter_params *p);
diff --git a/drivers/net/ethernet/chelsio/cxgb/tp.h b/drivers/net/ethernet/chelsio/cxgb/tp.h
index ba15675d56df..64f93dcc676b 100644
--- a/drivers/net/ethernet/chelsio/cxgb/tp.h
+++ b/drivers/net/ethernet/chelsio/cxgb/tp.h
@@ -65,9 +65,7 @@ void t1_tp_intr_enable(struct petp *tp);
 void t1_tp_intr_clear(struct petp *tp);
 int t1_tp_intr_handler(struct petp *tp);
 
-void t1_tp_get_mib_statistics(adapter_t *adap, struct tp_mib_statistics *tps);
 void t1_tp_set_tcp_checksum_offload(struct petp *tp, int enable);
 void t1_tp_set_ip_checksum_offload(struct petp *tp, int enable);
-int t1_tp_set_coalescing_size(struct petp *tp, unsigned int size);
 int t1_tp_reset(struct petp *tp, struct tp_params *p, unsigned int tp_clk);
 #endif
-- 
cgit v1.3-3-g829e


From e0c47281723f301894c14e6f5cd5884fdfb813f9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:06:41 +0200
Subject: netfilter: nf_tables: elements with timeout below CONFIG_HZ never
 expire

Element timeout that is below CONFIG_HZ never expires because the
timeout extension is not allocated given that nf_msecs_to_jiffies64()
returns 0. Set timeout to the minimum value to honor timeout.

Fixes: 8e1102d5a159 ("netfilter: nf_tables: support timeouts larger than 23 days")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b6547fe22bd8..b49fcd7148d3 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4593,7 +4593,7 @@ int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
 		return -ERANGE;
 
 	ms *= NSEC_PER_MSEC;
-	*result = nsecs_to_jiffies64(ms);
+	*result = nsecs_to_jiffies64(ms) ? : !!ms;
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From d2dc429ecb4e79ad164028d965c00f689e6f6d06 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:06:49 +0200
Subject: netfilter: nf_tables: reject element expiration with no timeout

If element timeout is unset and set provides no default timeout, the
element expiration is silently ignored, reject this instead to let user
know this is unsupported.

Also prepare for supporting timeout that never expire, where zero
timeout and expiration must be also rejected.

Fixes: 8e1102d5a159 ("netfilter: nf_tables: support timeouts larger than 23 days")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b49fcd7148d3..da75bc1de466 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6923,6 +6923,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (nla[NFTA_SET_ELEM_EXPIRATION] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
+		if (timeout == 0)
+			return -EOPNOTSUPP;
+
 		err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_EXPIRATION],
 					    &expiration);
 		if (err)
-- 
cgit v1.3-3-g829e


From c0f38a8c60174368aed1d0f9965d733195f15033 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:06:58 +0200
Subject: netfilter: nf_tables: reject expiration higher than timeout

Report ERANGE to userspace if user specifies an expiration larger than
the timeout.

Fixes: 8e1102d5a159 ("netfilter: nf_tables: support timeouts larger than 23 days")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index da75bc1de466..6c0c6f8a08a8 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6930,6 +6930,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 					    &expiration);
 		if (err)
 			return err;
+
+		if (expiration > timeout)
+			return -ERANGE;
 	}
 
 	if (nla[NFTA_SET_ELEM_EXPR]) {
-- 
cgit v1.3-3-g829e


From 15d8605c0cf4fc9cf4386cae658c68a0fd4bdb92 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:07:06 +0200
Subject: netfilter: nf_tables: remove annotation to access set timeout while
 holding lock

Mutex is held when adding an element, no need for READ_ONCE, remove it.

Fixes: 123b99619cca ("netfilter: nf_tables: honor set timeout and garbage collection updates")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6c0c6f8a08a8..571aa30918e9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6916,7 +6916,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			return err;
 	} else if (set->flags & NFT_SET_TIMEOUT &&
 		   !(flags & NFT_SET_ELEM_INTERVAL_END)) {
-		timeout = READ_ONCE(set->timeout);
+		timeout = set->timeout;
 	}
 
 	expiration = 0;
@@ -7023,7 +7023,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		if (err < 0)
 			goto err_parse_key_end;
 
-		if (timeout != READ_ONCE(set->timeout)) {
+		if (timeout != set->timeout) {
 			err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
 			if (err < 0)
 				goto err_parse_key_end;
-- 
cgit v1.3-3-g829e


From c5ad8ed61fa8410b272c077ec167c593602b4542 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:08:49 +0200
Subject: netfilter: nft_dynset: annotate data-races around set timeout

set timeout can be read locklessly while being updated from control
plane, add annotation.

Fixes: 123b99619cca ("netfilter: nf_tables: honor set timeout and garbage collection updates")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_dynset.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 6920df754265..5812fd880b79 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -56,7 +56,7 @@ static struct nft_elem_priv *nft_dynset_new(struct nft_set *set,
 	if (!atomic_add_unless(&set->nelems, 1, set->size))
 		return NULL;
 
-	timeout = priv->timeout ? : set->timeout;
+	timeout = priv->timeout ? : READ_ONCE(set->timeout);
 	elem_priv = nft_set_elem_init(set, &priv->tmpl,
 				      &regs->data[priv->sreg_key], NULL,
 				      &regs->data[priv->sreg_data],
@@ -95,7 +95,7 @@ void nft_dynset_eval(const struct nft_expr *expr,
 			     expr, regs, &ext)) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
 		    nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
-			timeout = priv->timeout ? : set->timeout;
+			timeout = priv->timeout ? : READ_ONCE(set->timeout);
 			*nft_set_ext_expiration(ext) = get_jiffies_64() + timeout;
 		}
 
@@ -313,7 +313,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 		nft_dynset_ext_add_expr(priv);
 
 	if (set->flags & NFT_SET_TIMEOUT) {
-		if (timeout || set->timeout) {
+		if (timeout || READ_ONCE(set->timeout)) {
 			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT);
 			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION);
 		}
-- 
cgit v1.3-3-g829e


From 73d3c04b710f0c144ce873dfe4f173a55c749539 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:08:58 +0200
Subject: netfilter: nf_tables: annotate data-races around element expiration

element expiration can be read-write locklessly, it can be written by
dynset and read from netlink dump, add annotation.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 2 +-
 net/netfilter/nf_tables_api.c     | 2 +-
 net/netfilter/nft_dynset.c        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index c302b396e1a7..1528af3fe26f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -835,7 +835,7 @@ static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
 					  u64 tstamp)
 {
 	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+	       time_after_eq64(tstamp, READ_ONCE(*nft_set_ext_expiration(ext)));
 }
 
 static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 571aa30918e9..77dce3d61ae6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5827,7 +5827,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
 		u64 expires, now = get_jiffies_64();
 
-		expires = *nft_set_ext_expiration(ext);
+		expires = READ_ONCE(*nft_set_ext_expiration(ext));
 		if (time_before64(now, expires))
 			expires -= now;
 		else
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 5812fd880b79..ca4b52e68295 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -96,7 +96,7 @@ void nft_dynset_eval(const struct nft_expr *expr,
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
 		    nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
 			timeout = priv->timeout ? : READ_ONCE(set->timeout);
-			*nft_set_ext_expiration(ext) = get_jiffies_64() + timeout;
+			WRITE_ONCE(*nft_set_ext_expiration(ext), get_jiffies_64() + timeout);
 		}
 
 		nft_set_elem_update_expr(ext, regs, pkt);
-- 
cgit v1.3-3-g829e


From 4c5daea9af4fce6628b8ca9e6a332529bbf26809 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:09:17 +0200
Subject: netfilter: nf_tables: consolidate timeout extension for elements

Expiration and timeout are stored in separated set element extensions,
but they are tightly coupled. Consolidate them in a single extension to
simplify and prepare for set element updates.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 18 ++++++++--------
 net/netfilter/nf_tables_api.c     | 43 ++++++++++++++++-----------------------
 net/netfilter/nft_dynset.c        | 13 +++++-------
 3 files changed, 30 insertions(+), 44 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1528af3fe26f..1e9b5e1659a1 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -687,7 +687,6 @@ void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set);
  *	@NFT_SET_EXT_DATA: mapping data
  *	@NFT_SET_EXT_FLAGS: element flags
  *	@NFT_SET_EXT_TIMEOUT: element timeout
- *	@NFT_SET_EXT_EXPIRATION: element expiration time
  *	@NFT_SET_EXT_USERDATA: user data associated with the element
  *	@NFT_SET_EXT_EXPRESSIONS: expressions associated with the element
  *	@NFT_SET_EXT_OBJREF: stateful object reference associated with element
@@ -699,7 +698,6 @@ enum nft_set_extensions {
 	NFT_SET_EXT_DATA,
 	NFT_SET_EXT_FLAGS,
 	NFT_SET_EXT_TIMEOUT,
-	NFT_SET_EXT_EXPIRATION,
 	NFT_SET_EXT_USERDATA,
 	NFT_SET_EXT_EXPRESSIONS,
 	NFT_SET_EXT_OBJREF,
@@ -811,14 +809,14 @@ static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext)
 	return nft_set_ext(ext, NFT_SET_EXT_FLAGS);
 }
 
-static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext)
-{
-	return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
-}
+struct nft_timeout {
+	u64	timeout;
+	u64	expiration;
+};
 
-static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext)
+static inline struct nft_timeout *nft_set_ext_timeout(const struct nft_set_ext *ext)
 {
-	return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION);
+	return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
 }
 
 static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext)
@@ -834,8 +832,8 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
 static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
 					  u64 tstamp)
 {
-	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-	       time_after_eq64(tstamp, READ_ONCE(*nft_set_ext_expiration(ext)));
+	return nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+	       time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration));
 }
 
 static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 77dce3d61ae6..c295d6e6c1fb 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5694,12 +5694,8 @@ const struct nft_set_ext_type nft_set_ext_types[] = {
 		.align	= __alignof__(u8),
 	},
 	[NFT_SET_EXT_TIMEOUT]		= {
-		.len	= sizeof(u64),
-		.align	= __alignof__(u64),
-	},
-	[NFT_SET_EXT_EXPIRATION]	= {
-		.len	= sizeof(u64),
-		.align	= __alignof__(u64),
+		.len	= sizeof(struct nft_timeout),
+		.align	= __alignof__(struct nft_timeout),
 	},
 	[NFT_SET_EXT_USERDATA]		= {
 		.len	= sizeof(struct nft_userdata),
@@ -5818,16 +5814,16 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 		         htonl(*nft_set_ext_flags(ext))))
 		goto nla_put_failure;
 
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
-	    nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
-			 nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)),
-			 NFTA_SET_ELEM_PAD))
-		goto nla_put_failure;
-
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
 		u64 expires, now = get_jiffies_64();
 
-		expires = READ_ONCE(*nft_set_ext_expiration(ext));
+		if (nft_set_ext_timeout(ext)->timeout != READ_ONCE(set->timeout) &&
+		    nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
+				 nf_jiffies64_to_msecs(nft_set_ext_timeout(ext)->timeout),
+				 NFTA_SET_ELEM_PAD))
+			goto nla_put_failure;
+
+		expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration);
 		if (time_before64(now, expires))
 			expires -= now;
 		else
@@ -6499,13 +6495,14 @@ struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set,
 			       nft_set_ext_data(ext), data, set->dlen) < 0)
 		goto err_ext_check;
 
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
-		*nft_set_ext_expiration(ext) = get_jiffies_64() + expiration;
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
+		nft_set_ext_timeout(ext)->timeout = timeout;
+
 		if (expiration == 0)
-			*nft_set_ext_expiration(ext) += timeout;
+			expiration = timeout;
+
+		nft_set_ext_timeout(ext)->expiration = get_jiffies_64() + expiration;
 	}
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT))
-		*nft_set_ext_timeout(ext) = timeout;
 
 	return elem;
 
@@ -7019,15 +7016,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	}
 
 	if (timeout > 0) {
-		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION);
+		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
 		if (err < 0)
 			goto err_parse_key_end;
-
-		if (timeout != set->timeout) {
-			err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
-			if (err < 0)
-				goto err_parse_key_end;
-		}
 	}
 
 	if (num_exprs) {
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index ca4b52e68295..ed8d692bebe3 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -94,9 +94,9 @@ void nft_dynset_eval(const struct nft_expr *expr,
 	if (set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
 			     expr, regs, &ext)) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
-		    nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
+		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
 			timeout = priv->timeout ? : READ_ONCE(set->timeout);
-			WRITE_ONCE(*nft_set_ext_expiration(ext), get_jiffies_64() + timeout);
+			WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + timeout);
 		}
 
 		nft_set_elem_update_expr(ext, regs, pkt);
@@ -312,12 +312,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	if (priv->num_exprs)
 		nft_dynset_ext_add_expr(priv);
 
-	if (set->flags & NFT_SET_TIMEOUT) {
-		if (timeout || READ_ONCE(set->timeout)) {
-			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT);
-			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION);
-		}
-	}
+	if (set->flags & NFT_SET_TIMEOUT &&
+	    (timeout || READ_ONCE(set->timeout)))
+		nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT);
 
 	priv->timeout = timeout;
 
-- 
cgit v1.3-3-g829e


From 8bfb74ae12fa4cd3c9b49bb5913610b5709bffd7 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:09:27 +0200
Subject: netfilter: nf_tables: zero timeout means element never times out

This patch uses zero as timeout marker for those elements that never expire
when the element is created.

If userspace provides no timeout for an element, then the default set
timeout applies. However, if no default set timeout is specified and
timeout flag is set on, then timeout extension is allocated and timeout
is set to zero to allow for future updates.

Use of zero a never timeout marker has been suggested by Phil Sutter.

Note that, in older kernels, it is already possible to define elements
that never expire by declaring a set with the set timeout flag set on
and no global set timeout, in this case, new element with no explicit
timeout never expire do not allocate the timeout extension, hence, they
never expire. This approach makes it complicated to accomodate element
timeout update, because element extensions do not support reallocations.
Therefore, allocate the timeout extension and use the new marker for
this case, but do not expose it to userspace to retain backward
compatibility in the set listing.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h        |  7 ++++--
 include/uapi/linux/netfilter/nf_tables.h |  2 +-
 net/netfilter/nf_tables_api.c            | 39 +++++++++++++++++++-------------
 net/netfilter/nft_dynset.c               |  3 ++-
 4 files changed, 31 insertions(+), 20 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 1e9b5e1659a1..7511918dce6f 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -832,8 +832,11 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
 static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
 					  u64 tstamp)
 {
-	return nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
-	       time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration));
+	if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) ||
+	    nft_set_ext_timeout(ext)->timeout == 0)
+		return false;
+
+	return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration));
 }
 
 static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 639894ed1b97..d6476ca5d7a6 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -436,7 +436,7 @@ enum nft_set_elem_flags {
  * @NFTA_SET_ELEM_KEY: key value (NLA_NESTED: nft_data)
  * @NFTA_SET_ELEM_DATA: data value of mapping (NLA_NESTED: nft_data_attributes)
  * @NFTA_SET_ELEM_FLAGS: bitmask of nft_set_elem_flags (NLA_U32)
- * @NFTA_SET_ELEM_TIMEOUT: timeout value (NLA_U64)
+ * @NFTA_SET_ELEM_TIMEOUT: timeout value, zero means never times out (NLA_U64)
  * @NFTA_SET_ELEM_EXPIRATION: expiration time (NLA_U64)
  * @NFTA_SET_ELEM_USERDATA: user data (NLA_BINARY)
  * @NFTA_SET_ELEM_EXPR: expression (NLA_NESTED: nft_expr_attributes)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c295d6e6c1fb..ed85b10edb32 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5815,24 +5815,31 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
-		u64 expires, now = get_jiffies_64();
+		u64 timeout = nft_set_ext_timeout(ext)->timeout;
+		u64 set_timeout = READ_ONCE(set->timeout);
+		__be64 msecs = 0;
+
+		if (set_timeout != timeout) {
+			msecs = nf_jiffies64_to_msecs(timeout);
+			if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, msecs,
+					 NFTA_SET_ELEM_PAD))
+				goto nla_put_failure;
+		}
 
-		if (nft_set_ext_timeout(ext)->timeout != READ_ONCE(set->timeout) &&
-		    nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
-				 nf_jiffies64_to_msecs(nft_set_ext_timeout(ext)->timeout),
-				 NFTA_SET_ELEM_PAD))
-			goto nla_put_failure;
+		if (timeout > 0) {
+			u64 expires, now = get_jiffies_64();
 
-		expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration);
-		if (time_before64(now, expires))
-			expires -= now;
-		else
-			expires = 0;
+			expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration);
+			if (time_before64(now, expires))
+				expires -= now;
+			else
+				expires = 0;
 
-		if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION,
-				 nf_jiffies64_to_msecs(expires),
-				 NFTA_SET_ELEM_PAD))
-			goto nla_put_failure;
+			if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION,
+					 nf_jiffies64_to_msecs(expires),
+					 NFTA_SET_ELEM_PAD))
+				goto nla_put_failure;
+		}
 	}
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
@@ -7015,7 +7022,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			goto err_parse_key_end;
 	}
 
-	if (timeout > 0) {
+	if (set->flags & NFT_SET_TIMEOUT) {
 		err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
 		if (err < 0)
 			goto err_parse_key_end;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index ed8d692bebe3..6a10305de24b 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -94,7 +94,8 @@ void nft_dynset_eval(const struct nft_expr *expr,
 	if (set->ops->update(set, &regs->data[priv->sreg_key], nft_dynset_new,
 			     expr, regs, &ext)) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
-		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
+		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+		    nft_set_ext_timeout(ext)->timeout != 0) {
 			timeout = priv->timeout ? : READ_ONCE(set->timeout);
 			WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + timeout);
 		}
-- 
cgit v1.3-3-g829e


From 4201f3938914d8df3c761754b9726770c4225d66 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 3 Sep 2024 01:09:58 +0200
Subject: netfilter: nf_tables: set element timeout update support

Store new timeout and expiration in transaction object, use them to
update elements from .commit path. Otherwise, discard update if .abort
path is exercised.

Use update_flags in the transaction to note whether the timeout,
expiration, or both need to be updated.

Annotate access to timeout extension now that it can be updated while
lockless read access is possible.

Reject timeout updates on elements with no timeout extension.

Element transaction remains in the 96 bytes kmalloc slab on x86_64 after
this update.

This patch requires ("netfilter: nf_tables: use timestamp to check for
set element timeout") to make sure an element does not expire while
transaction is ongoing.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h | 16 ++++++++++++-
 net/netfilter/nf_tables_api.c     | 47 +++++++++++++++++++++++++++++++++++----
 net/netfilter/nft_dynset.c        |  2 +-
 3 files changed, 59 insertions(+), 6 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 7511918dce6f..49708e7e1339 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -833,7 +833,7 @@ static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
 					  u64 tstamp)
 {
 	if (!nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) ||
-	    nft_set_ext_timeout(ext)->timeout == 0)
+	    READ_ONCE(nft_set_ext_timeout(ext)->timeout) == 0)
 		return false;
 
 	return time_after_eq64(tstamp, READ_ONCE(nft_set_ext_timeout(ext)->expiration));
@@ -1749,10 +1749,18 @@ struct nft_trans_table {
 #define nft_trans_table_update(trans)			\
 	nft_trans_container_table(trans)->update
 
+enum nft_trans_elem_flags {
+	NFT_TRANS_UPD_TIMEOUT		= (1 << 0),
+	NFT_TRANS_UPD_EXPIRATION	= (1 << 1),
+};
+
 struct nft_trans_elem {
 	struct nft_trans		nft_trans;
 	struct nft_set			*set;
 	struct nft_elem_priv		*elem_priv;
+	u64				timeout;
+	u64				expiration;
+	u8				update_flags;
 	bool				bound;
 };
 
@@ -1762,6 +1770,12 @@ struct nft_trans_elem {
 	nft_trans_container_elem(trans)->set
 #define nft_trans_elem_priv(trans)			\
 	nft_trans_container_elem(trans)->elem_priv
+#define nft_trans_elem_update_flags(trans)		\
+	nft_trans_container_elem(trans)->update_flags
+#define nft_trans_elem_timeout(trans)			\
+	nft_trans_container_elem(trans)->timeout
+#define nft_trans_elem_expiration(trans)		\
+	nft_trans_container_elem(trans)->expiration
 #define nft_trans_elem_set_bound(trans)			\
 	nft_trans_container_elem(trans)->bound
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index ed85b10edb32..57259b5f3ef5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5815,7 +5815,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
-		u64 timeout = nft_set_ext_timeout(ext)->timeout;
+		u64 timeout = READ_ONCE(nft_set_ext_timeout(ext)->timeout);
 		u64 set_timeout = READ_ONCE(set->timeout);
 		__be64 msecs = 0;
 
@@ -6852,6 +6852,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	struct nft_data_desc desc;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
+	u8 update_flags;
 	u64 expiration;
 	u64 timeout;
 	int err, i;
@@ -7163,8 +7164,30 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			     nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) &&
 			     *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2)))
 				goto err_element_clash;
-			else if (!(nlmsg_flags & NLM_F_EXCL))
+			else if (!(nlmsg_flags & NLM_F_EXCL)) {
 				err = 0;
+				if (nft_set_ext_exists(ext2, NFT_SET_EXT_TIMEOUT)) {
+					update_flags = 0;
+					if (timeout != nft_set_ext_timeout(ext2)->timeout) {
+						nft_trans_elem_timeout(trans) = timeout;
+						if (expiration == 0)
+							expiration = timeout;
+
+						update_flags |= NFT_TRANS_UPD_TIMEOUT;
+					}
+					if (expiration) {
+						nft_trans_elem_expiration(trans) = expiration;
+						update_flags |= NFT_TRANS_UPD_EXPIRATION;
+					}
+
+					if (update_flags) {
+						nft_trans_elem_priv(trans) = elem_priv;
+						nft_trans_elem_update_flags(trans) = update_flags;
+						nft_trans_commit_list_add_tail(ctx->net, trans);
+						goto err_elem_free;
+					}
+				}
+			}
 		} else if (err == -ENOTEMPTY) {
 			/* ENOTEMPTY reports overlapping between this element
 			 * and an existing one.
@@ -10489,7 +10512,22 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 		case NFT_MSG_NEWSETELEM:
 			te = nft_trans_container_elem(trans);
 
-			nft_setelem_activate(net, te->set, te->elem_priv);
+			if (te->update_flags) {
+				const struct nft_set_ext *ext =
+					nft_set_elem_ext(te->set, te->elem_priv);
+
+				if (te->update_flags & NFT_TRANS_UPD_TIMEOUT) {
+					WRITE_ONCE(nft_set_ext_timeout(ext)->timeout,
+						   te->timeout);
+				}
+				if (te->update_flags & NFT_TRANS_UPD_EXPIRATION) {
+					WRITE_ONCE(nft_set_ext_timeout(ext)->expiration,
+						   get_jiffies_64() + te->expiration);
+				}
+			} else {
+				nft_setelem_activate(net, te->set, te->elem_priv);
+			}
+
 			nf_tables_setelem_notify(&ctx, te->set,
 						 te->elem_priv,
 						 NFT_MSG_NEWSETELEM);
@@ -10789,7 +10827,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSETELEM:
-			if (nft_trans_elem_set_bound(trans)) {
+			if (nft_trans_elem_update_flags(trans) ||
+			    nft_trans_elem_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 6a10305de24b..88922e0e8e83 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -95,7 +95,7 @@ void nft_dynset_eval(const struct nft_expr *expr,
 			     expr, regs, &ext)) {
 		if (priv->op == NFT_DYNSET_OP_UPDATE &&
 		    nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
-		    nft_set_ext_timeout(ext)->timeout != 0) {
+		    READ_ONCE(nft_set_ext_timeout(ext)->timeout) != 0) {
 			timeout = priv->timeout ? : READ_ONCE(set->timeout);
 			WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + timeout);
 		}
-- 
cgit v1.3-3-g829e


From 25f855413885bbce8a0dd5d7dea670a0da1cdbe5 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Tue, 20 Aug 2024 10:21:42 -0400
Subject: dt-bindings: net: wireless: convert marvel-8xxx.txt to yaml format

Convert binding doc marvel-8xxx.txt to yaml format.
Additional change:
- Remove marvell,caldata_00_txpwrlimit_2g_cfg_set in example.
- Remove mmc related property in example.
- Add wakeup-source property.
- Remove vmmc-supply and mmc-pwrseq.

Fix below warning:
arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dtb: /soc@0/bus@30800000/mmc@30b40000/wifi@1:
failed to match any schema with compatible: ['marvell,sd8997']

Acked-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240820142143.443151-1-Frank.Li@nxp.com
---
 .../bindings/net/wireless/marvell,sd8787.yaml      | 93 ++++++++++++++++++++++
 .../bindings/net/wireless/marvell-8xxx.txt         | 70 ----------------
 2 files changed, 93 insertions(+), 70 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml
 delete mode 100644 Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt

diff --git a/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml b/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml
new file mode 100644
index 000000000000..1715b22e0dcf
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/wireless/marvell,sd8787.yaml
@@ -0,0 +1,93 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/wireless/marvell,sd8787.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell 8787/8897/8978/8997 (sd8787/sd8897/sd8978/sd8997/pcie8997) SDIO/PCIE devices
+
+maintainers:
+  - Brian Norris <briannorris@chromium.org>
+  - Frank Li <Frank.Li@nxp.com>
+
+description:
+  This node provides properties for describing the Marvell SDIO/PCIE wireless device.
+  The node is expected to be specified as a child node to the SDIO/PCIE controller that
+  connects the device to the system.
+
+properties:
+  compatible:
+    enum:
+      - marvell,sd8787
+      - marvell,sd8897
+      - marvell,sd8978
+      - marvell,sd8997
+      - nxp,iw416
+      - pci11ab,2b42
+      - pci1b4b,2b42
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  wakeup-source: true
+
+  marvell,caldata-txpwrlimit-2g:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description: Calibration data for the 2GHz band.
+    maxItems: 566
+
+  marvell,caldata-txpwrlimit-5g-sub0:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description: Calibration data for sub-band 0 in the 5GHz band.
+    maxItems: 502
+
+  marvell,caldata-txpwrlimit-5g-sub1:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description: Calibration data for sub-band 1 in the 5GHz band.
+    maxItems: 688
+
+  marvell,caldata-txpwrlimit-5g-sub2:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description: Calibration data for sub-band 2 in the 5GHz band.
+    maxItems: 750
+
+  marvell,caldata-txpwrlimit-5g-sub3:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description: Calibration data for sub-band 3 in the 5GHz band.
+    maxItems: 502
+
+  marvell,wakeup-pin:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Provides the pin number for the wakeup pin from the device's point of
+      view. The wakeup pin is used for the device to wake the host system
+      from sleep. This property is only necessary if the wakeup pin is
+      wired in a non-standard way, such that the default pin assignments
+      are invalid.
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    mmc {
+         #address-cells = <1>;
+         #size-cells = <0>;
+
+         wifi@1 {
+             compatible = "marvell,sd8897";
+             reg = <1>;
+             interrupt-parent = <&pio>;
+             interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
+             marvell,wakeup-pin = <3>;
+        };
+    };
+
diff --git a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
deleted file mode 100644
index cdc303caf5f4..000000000000
--- a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
+++ /dev/null
@@ -1,70 +0,0 @@
-Marvell 8787/8897/8978/8997 (sd8787/sd8897/sd8978/sd8997/pcie8997) SDIO/PCIE devices
-------
-
-This node provides properties for controlling the Marvell SDIO/PCIE wireless device.
-The node is expected to be specified as a child node to the SDIO/PCIE controller that
-connects the device to the system.
-
-Required properties:
-
-  - compatible : should be one of the following:
-	* "marvell,sd8787"
-	* "marvell,sd8897"
-	* "marvell,sd8978"
-	* "marvell,sd8997"
-	* "nxp,iw416"
-	* "pci11ab,2b42"
-	* "pci1b4b,2b42"
-
-Optional properties:
-
-  - marvell,caldata* : A series of properties with marvell,caldata prefix,
-		      represent calibration data downloaded to the device during
-		      initialization. This is an array of unsigned 8-bit values.
-		      the properties should follow below property name and
-		      corresponding array length:
-	"marvell,caldata-txpwrlimit-2g" (length = 566).
-	"marvell,caldata-txpwrlimit-5g-sub0" (length = 502).
-	"marvell,caldata-txpwrlimit-5g-sub1" (length = 688).
-	"marvell,caldata-txpwrlimit-5g-sub2" (length = 750).
-	"marvell,caldata-txpwrlimit-5g-sub3" (length = 502).
-  - marvell,wakeup-pin : a wakeup pin number of wifi chip which will be configured
-		      to firmware. Firmware will wakeup the host using this pin
-		      during suspend/resume.
-  - interrupts : interrupt pin number to the cpu. driver will request an irq based on
-		 this interrupt number. during system suspend, the irq will be enabled
-		 so that the wifi chip can wakeup host platform under certain condition.
-		 during system resume, the irq will be disabled to make sure
-		 unnecessary interrupt is not received.
-  - vmmc-supply: a phandle of a regulator, supplying VCC to the card
-  - mmc-pwrseq:  phandle to the MMC power sequence node. See "mmc-pwrseq-*"
-		 for documentation of MMC power sequence bindings.
-
-Example:
-
-Tx power limit calibration data is configured in below example.
-The calibration data is an array of unsigned values, the length
-can vary between hw versions.
-IRQ pin 38 is used as system wakeup source interrupt. wakeup pin 3 is configured
-so that firmware can wakeup host using this device side pin.
-
-&mmc3 {
-	vmmc-supply = <&wlan_en_reg>;
-	mmc-pwrseq = <&wifi_pwrseq>;
-	bus-width = <4>;
-	cap-power-off-card;
-	keep-power-in-suspend;
-
-	#address-cells = <1>;
-	#size-cells = <0>;
-	mwifiex: wifi@1 {
-		compatible = "marvell,sd8897";
-		reg = <1>;
-		interrupt-parent = <&pio>;
-		interrupts = <38 IRQ_TYPE_LEVEL_LOW>;
-
-		marvell,caldata_00_txpwrlimit_2g_cfg_set = /bits/ 8 <
-	0x01 0x00 0x06 0x00 0x08 0x02 0x89 0x01>;
-		marvell,wakeup-pin = <3>;
-	};
-};
-- 
cgit v1.3-3-g829e


From d38792292be7113e73ba77383ed687ec87e8f7b5 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Wed, 21 Aug 2024 15:02:57 +0800
Subject: wifi: brcmsmac: Use kvmemdup to simplify the code

Use kvmemdup instead of kvmalloc() + memcpy() to simplify the code.

No functional change.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240821070257.2298559-1-ruanjinjie@huawei.com
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
index d86f28b8bc60..5b1d35601bbd 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
@@ -1611,10 +1611,9 @@ int brcms_ucode_init_buf(struct brcms_info *wl, void **pbuf, u32 idx)
 			if (le32_to_cpu(hdr->idx) == idx) {
 				pdata = wl->fw.fw_bin[i]->data +
 					le32_to_cpu(hdr->offset);
-				*pbuf = kvmalloc(len, GFP_KERNEL);
+				*pbuf = kvmemdup(pdata, len, GFP_KERNEL);
 				if (*pbuf == NULL)
-					goto fail;
-				memcpy(*pbuf, pdata, len);
+					return -ENOMEM;
 				return 0;
 			}
 		}
@@ -1622,7 +1621,6 @@ int brcms_ucode_init_buf(struct brcms_info *wl, void **pbuf, u32 idx)
 	brcms_err(wl->wlc->hw->d11core,
 		  "ERROR: ucode buf tag:%d can not be found!\n", idx);
 	*pbuf = NULL;
-fail:
 	return -ENODATA;
 }
 
-- 
cgit v1.3-3-g829e


From b0dc7018477e8fbb7e40c908c29cf663d06b17a7 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 21 Aug 2024 20:36:03 +0200
Subject: wifi: wilc1000: Do not operate uninitialized hardware during
 suspend/resume
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case the hardware is not initialized, do not operate it during
suspend/resume cycle, the hardware is already off so there is no
reason to access it.

In fact, wilc_sdio_enable_interrupt() in the resume callback does
interfere with the same call when initializing the hardware after
resume and makes such initialization after resume fail. Fix this
by not operating uninitialized hardware during suspend/resume.

Signed-off-by: Marek Vasut <marex@denx.de>
Reviewed-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240821183639.163187-1-marex@denx.de
---
 drivers/net/wireless/microchip/wilc1000/sdio.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 0043f7a0fdf9..7999aeb76901 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -977,6 +977,9 @@ static int wilc_sdio_suspend(struct device *dev)
 
 	dev_info(dev, "sdio suspend\n");
 
+	if (!wilc->initialized)
+		return 0;
+
 	if (!IS_ERR(wilc->rtc_clk))
 		clk_disable_unprepare(wilc->rtc_clk);
 
@@ -999,6 +1002,10 @@ static int wilc_sdio_resume(struct device *dev)
 	struct wilc *wilc = sdio_get_drvdata(func);
 
 	dev_info(dev, "sdio resume\n");
+
+	if (!wilc->initialized)
+		return 0;
+
 	wilc_sdio_init(wilc, true);
 	wilc_sdio_enable_interrupt(wilc);
 
-- 
cgit v1.3-3-g829e


From 0c896eceb5f348b5e314f5cd5faad966f09a56ff Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 21 Aug 2024 20:36:54 +0200
Subject: wifi: wilc1000: Re-enable RTC clock on resume
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The wilc_sdio_suspend() does clk_disable_unprepare() on rtc_clk clock,
make sure wilc_sdio_resume() does matching clk_prepare_enable(), else
any suspend/resume cycle leads to clock disable/enable imbalance. Fix
the imbalance.

Signed-off-by: Marek Vasut <marex@denx.de>
Reviewed-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240821183717.163235-1-marex@denx.de
---
 drivers/net/wireless/microchip/wilc1000/sdio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 7999aeb76901..683a35c682a8 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -1006,6 +1006,9 @@ static int wilc_sdio_resume(struct device *dev)
 	if (!wilc->initialized)
 		return 0;
 
+	if (!IS_ERR(wilc->rtc_clk))
+		clk_prepare_enable(wilc->rtc_clk);
+
 	wilc_sdio_init(wilc, true);
 	wilc_sdio_enable_interrupt(wilc);
 
-- 
cgit v1.3-3-g829e


From 97b766f989bcd06e5a7651b1080001d7327012f5 Mon Sep 17 00:00:00 2001
From: Chen Yufan <chenyufan@vivo.com>
Date: Fri, 23 Aug 2024 15:03:19 +0800
Subject: wifi: mwifiex: Convert to use jiffies macro

Use time_after macro instead of using jiffies directly to handle wraparound.
Change the type to to unsigned long to avoid unnecessary casts.

Signed-off-by: Chen Yufan <chenyufan@vivo.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240823070320.430753-1-chenyufan@vivo.com
---
 drivers/net/wireless/marvell/mwifiex/main.h | 2 +-
 drivers/net/wireless/marvell/mwifiex/tdls.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 529863edd7a2..566adce3413c 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -799,7 +799,7 @@ struct mwifiex_auto_tdls_peer {
 	u8 mac_addr[ETH_ALEN];
 	u8 tdls_status;
 	int rssi;
-	long rssi_jiffies;
+	unsigned long rssi_jiffies;
 	u8 failure_count;
 	u8 do_discover;
 	u8 do_setup;
diff --git a/drivers/net/wireless/marvell/mwifiex/tdls.c b/drivers/net/wireless/marvell/mwifiex/tdls.c
index 6c60621b6ccc..7823e67694e8 100644
--- a/drivers/net/wireless/marvell/mwifiex/tdls.c
+++ b/drivers/net/wireless/marvell/mwifiex/tdls.c
@@ -1439,8 +1439,8 @@ void mwifiex_check_auto_tdls(struct timer_list *t)
 
 	spin_lock_bh(&priv->auto_tdls_lock);
 	list_for_each_entry(tdls_peer, &priv->auto_tdls_list, list) {
-		if ((jiffies - tdls_peer->rssi_jiffies) >
-		    (MWIFIEX_AUTO_TDLS_IDLE_TIME * HZ)) {
+		if (time_after(jiffies, tdls_peer->rssi_jiffies +
+					 MWIFIEX_AUTO_TDLS_IDLE_TIME * HZ)) {
 			tdls_peer->rssi = 0;
 			tdls_peer->do_discover = true;
 			priv->check_tdls_tx = true;
-- 
cgit v1.3-3-g829e


From 1a5c486300e5ae9dac9bc294023a4667b75a5418 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 30 Aug 2024 21:19:19 +0200
Subject: ioam6: improve checks on user data

This patch improves two checks on user data.

The first one prevents bit 23 from being set, as specified by RFC 9197
(Sec 4.4.1):

  Bit 23    Reserved; MUST be set to zero upon transmission and be
            ignored upon receipt.  This bit is reserved to allow for
            future extensions of the IOAM Trace-Type bit field.

The second one checks that the tunnel destination address !=
IPV6_ADDR_ANY, just like we already do for the tunnel source address.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20240830191919.51439-1-justin.iurman@uliege.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ioam6_iptunnel.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index e34e1ff24546..beb6b4cfc551 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -89,7 +89,7 @@ static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace)
 	    trace->type.bit12 | trace->type.bit13 | trace->type.bit14 |
 	    trace->type.bit15 | trace->type.bit16 | trace->type.bit17 |
 	    trace->type.bit18 | trace->type.bit19 | trace->type.bit20 |
-	    trace->type.bit21)
+	    trace->type.bit21 | trace->type.bit23)
 		return false;
 
 	trace->nodelen = 0;
@@ -199,9 +199,17 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,
 		}
 	}
 
-	if (tb[IOAM6_IPTUNNEL_DST])
+	if (tb[IOAM6_IPTUNNEL_DST]) {
 		ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]);
 
+		if (ipv6_addr_any(&ilwt->tundst)) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_DST],
+					    "invalid tunnel dest address");
+			err = -EINVAL;
+			goto free_cache;
+		}
+	}
+
 	tuninfo = ioam6_lwt_info(lwt);
 	tuninfo->eh.hdrlen = ((sizeof(*tuninfo) + len_aligned) >> 3) - 1;
 	tuninfo->pad[0] = IPV6_TLV_PADN;
-- 
cgit v1.3-3-g829e


From 12d337339d9fd71cf24b337727e51d5b3d52bcef Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:49 +0300
Subject: ethtool: RX software timestamp for all

All devices support SOF_TIMESTAMPING_RX_SOFTWARE by virtue of
net_timestamp_check() being called in the device independent code.

Move the responsibility of reporting SOF_TIMESTAMPING_RX_SOFTWARE and
SOF_TIMESTAMPING_SOFTWARE, and setting PHC index to -1 to the core.
Device drivers no longer need to use them.

Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Link: https://lore.kernel.org/netdev/661550e348224_23a2b2294f7@willemb.c.googlers.com.notmuch/
Co-developed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240901112803.212753-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/common.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 00f93c58b319..781834ef57c3 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -692,20 +692,21 @@ int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct phy_device *phydev = dev->phydev;
+	int err = 0;
 
 	memset(info, 0, sizeof(*info));
 	info->cmd = ETHTOOL_GET_TS_INFO;
+	info->phc_index = -1;
 
 	if (phy_is_default_hwtstamp(phydev) && phy_has_tsinfo(phydev))
-		return phy_ts_info(phydev, info);
-	if (ops->get_ts_info)
-		return ops->get_ts_info(dev, info);
+		err = phy_ts_info(phydev, info);
+	else if (ops->get_ts_info)
+		err = ops->get_ts_info(dev, info);
 
-	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
-	info->phc_index = -1;
+	info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE |
+				 SOF_TIMESTAMPING_SOFTWARE;
 
-	return 0;
+	return err;
 }
 
 int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index)
-- 
cgit v1.3-3-g829e


From b5ed017a5658892ce99dc68413b506d175401528 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:50 +0300
Subject: can: dev: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://patch.msgid.link/20240901112803.212753-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/can/dev/dev.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c
index 87828f953073..6792c14fd7eb 100644
--- a/drivers/net/can/dev/dev.c
+++ b/drivers/net/can/dev/dev.c
@@ -380,12 +380,9 @@ int can_ethtool_op_get_ts_info_hwts(struct net_device *dev,
 {
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
-	info->phc_index = -1;
 	info->tx_types = BIT(HWTSTAMP_TX_ON);
 	info->rx_filters = BIT(HWTSTAMP_FILTER_ALL);
 
-- 
cgit v1.3-3-g829e


From 583fee8210cb1b9e96e7c33fd32f90df04402e46 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:51 +0300
Subject: can: peak_canfd: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://patch.msgid.link/20240901112803.212753-4-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/can/peak_canfd/peak_canfd.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index b50005397463..28f3fd805273 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -781,11 +781,8 @@ static int peak_get_ts_info(struct net_device *dev,
 {
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
-	info->phc_index = -1;
 	info->tx_types = BIT(HWTSTAMP_TX_OFF);
 	info->rx_filters = BIT(HWTSTAMP_FILTER_ALL);
 
-- 
cgit v1.3-3-g829e


From ab6ebf02f222fdaec6091913d8505a1f4ce5b392 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:52 +0300
Subject: can: peak_usb: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://patch.msgid.link/20240901112803.212753-5-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/can/usb/peak_usb/pcan_usb_core.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 3d68fef46ded..59f7cd8ceb39 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -901,11 +901,8 @@ int pcan_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info
 {
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
-	info->phc_index = -1;
 	info->tx_types = BIT(HWTSTAMP_TX_OFF);
 	info->rx_filters = BIT(HWTSTAMP_FILTER_ALL);
 
-- 
cgit v1.3-3-g829e


From 24186dc66b1018a33a12fadbcb40edd517abd5bc Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:53 +0300
Subject: tsnep: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20240901112803.212753-6-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/engleder/tsnep_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_ethtool.c b/drivers/net/ethernet/engleder/tsnep_ethtool.c
index 9aa286ba1f00..228a638eae16 100644
--- a/drivers/net/ethernet/engleder/tsnep_ethtool.c
+++ b/drivers/net/ethernet/engleder/tsnep_ethtool.c
@@ -310,16 +310,12 @@ static int tsnep_ethtool_get_ts_info(struct net_device *netdev,
 	struct tsnep_adapter *adapter = netdev_priv(netdev);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (adapter->ptp_clock)
 		info->phc_index = ptp_clock_index(adapter->ptp_clock);
-	else
-		info->phc_index = -1;
 
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
 			 BIT(HWTSTAMP_TX_ON);
-- 
cgit v1.3-3-g829e


From e052114e14c2c1cac8068bcfde8d499e3249114b Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:54 +0300
Subject: ionic: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240901112803.212753-7-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
index 4619fd74f3e3..dda22fa4448c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c
@@ -989,8 +989,6 @@ static int ionic_get_ts_info(struct net_device *netdev,
 	info->phc_index = ptp_clock_index(lif->phc->ptp);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 277901ee3a2620679e2c8797377d2a72f4358068 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:55 +0300
Subject: ravb: Remove setting of RX software timestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Sergey Shtylyov <s.shtylyov@omp.ru>
Link: https://patch.msgid.link/20240901112803.212753-8-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/ravb_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index c02fb296bf7d..c7ec23688d56 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1744,8 +1744,6 @@ static int ravb_get_ts_info(struct net_device *ndev,
 
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
@@ -1756,6 +1754,8 @@ static int ravb_get_ts_info(struct net_device *ndev,
 		(1 << HWTSTAMP_FILTER_ALL);
 	if (hw_info->gptp || hw_info->ccc_gac)
 		info->phc_index = ptp_clock_index(priv->ptp.clock);
+	else
+		info->phc_index = 0;
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 41ee62317087f249fca0eda56217de69cd399da5 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:56 +0300
Subject: net: renesas: rswitch: Remove setting of RX software timestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Link: https://patch.msgid.link/20240901112803.212753-9-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rswitch.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index ff50e20856ec..b80aa27a7214 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1815,8 +1815,6 @@ static int rswitch_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts
 
 	info->phc_index = ptp_clock_index(rdev->priv->ptp_priv->clock);
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 0f79953c001947d52e2eca14dd76aaacbbf46241 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:57 +0300
Subject: net: ethernet: rtsn: Remove setting of RX software timestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Link: https://patch.msgid.link/20240901112803.212753-10-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rtsn.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c
index 0e6cea42f007..f9f63c61d792 100644
--- a/drivers/net/ethernet/renesas/rtsn.c
+++ b/drivers/net/ethernet/renesas/rtsn.c
@@ -1219,8 +1219,6 @@ static int rtsn_get_ts_info(struct net_device *ndev,
 
 	info->phc_index = ptp_clock_index(priv->ptp_priv->clock);
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From c6a15576e60ef3f3bad012c0294beba9892943f2 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:58 +0300
Subject: net: hns3: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Jijie Shao <shaojijie@huawei.com>
Link: https://patch.msgid.link/20240901112803.212753-11-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 5fff8ed388f8..5505caea88e9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -389,16 +389,12 @@ int hclge_ptp_get_ts_info(struct hnae3_handle *handle,
 	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (hdev->ptp->clock)
 		info->phc_index = ptp_clock_index(hdev->ptp->clock);
-	else
-		info->phc_index = -1;
 
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
 
-- 
cgit v1.3-3-g829e


From 7d20c38d088e936735d5a5b472a55834456f1928 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:27:59 +0300
Subject: net: fec: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20240901112803.212753-12-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fec_main.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 8c3bf0faba63..acbb627d51bf 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2775,15 +2775,11 @@ static int fec_enet_get_ts_info(struct net_device *ndev,
 	if (fep->bufdesc_ex) {
 
 		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-					SOF_TIMESTAMPING_RX_SOFTWARE |
-					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_TX_HARDWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 		if (fep->ptp_clock)
 			info->phc_index = ptp_clock_index(fep->ptp_clock);
-		else
-			info->phc_index = -1;
 
 		info->tx_types = (1 << HWTSTAMP_TX_OFF) |
 				 (1 << HWTSTAMP_TX_ON);
-- 
cgit v1.3-3-g829e


From 3dd261ca7f84c65af40f37825bf1cbb0cf3d5583 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:28:00 +0300
Subject: net: enetc: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20240901112803.212753-13-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index 5e684b23c5f5..47c478e08d44 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -849,17 +849,13 @@ static int enetc_get_ts_info(struct net_device *ndev,
 	if (phc_idx) {
 		info->phc_index = *phc_idx;
 		symbol_put(enetc_phc_index);
-	} else {
-		info->phc_index = -1;
 	}
 
 #ifdef CONFIG_FSL_ENETC_PTP_CLOCK
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE |
-				SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
+				SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
 			 (1 << HWTSTAMP_TX_ON) |
@@ -867,9 +863,7 @@ static int enetc_get_ts_info(struct net_device *ndev,
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);
 #else
-	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 #endif
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 673ec22b1de8230014ef02e7f48de6c5fd47b35a Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:28:01 +0300
Subject: gianfar: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240901112803.212753-14-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/gianfar_ethtool.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index f581402ad740..a99b95c4bcfb 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1455,12 +1455,8 @@ static int gfar_get_ts_info(struct net_device *dev,
 	struct device_node *ptp_node;
 	struct ptp_qoriq *ptp = NULL;
 
-	info->phc_index = -1;
-
 	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)) {
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-					SOF_TIMESTAMPING_TX_SOFTWARE |
-					SOF_TIMESTAMPING_SOFTWARE;
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 		return 0;
 	}
 
@@ -1478,9 +1474,7 @@ static int gfar_get_ts_info(struct net_device *dev,
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
+				SOF_TIMESTAMPING_TX_SOFTWARE;
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
 			 (1 << HWTSTAMP_TX_ON);
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
-- 
cgit v1.3-3-g829e


From eb87a1daf6fb3b1ba8f19d94e243a638a844a7cc Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:28:02 +0300
Subject: octeontx2-pf: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Link: https://patch.msgid.link/20240901112803.212753-15-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 0db62eb0dab3..32468c663605 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -962,8 +962,6 @@ static int otx2_get_ts_info(struct net_device *netdev,
 		return ethtool_op_get_ts_info(netdev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 406e862b4583f5d2f87f116073f88d20419a6afa Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Sun, 1 Sep 2024 14:28:03 +0300
Subject: net: mvpp2: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Marcin Wojtas <marcin.s.wojtas@gmail.com>
Link: https://patch.msgid.link/20240901112803.212753-16-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 2fe8bae4eb3c..3880dcc0418b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5268,8 +5268,6 @@ static int mvpp2_ethtool_get_ts_info(struct net_device *dev,
 
 	info->phc_index = mvpp22_tai_ptp_clock_index(port->priv->tai);
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 7bcf4d8022f93c0af15a11f962fa55892853f2c0 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:52 +0200
Subject: mptcp: pm: rename helpers linked to 'flush'

Rename all the helpers specific to the flushing operations to make it
clear that the intention is to flush all created subflows, and remove
all announced addresses, not just a specific selection.

That way, it is easier to understand why the id_avail_bitmap and
local_addr_used are reset at the end.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-1-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index f891bc714668..275959581586 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1672,8 +1672,8 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
 }
 
 /* Called from the in-kernel PM only */
-static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
-					       struct list_head *rm_list)
+static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
+					      struct list_head *rm_list)
 {
 	struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
 	struct mptcp_pm_addr_entry *entry;
@@ -1701,8 +1701,8 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 	spin_unlock_bh(&msk->pm.lock);
 }
 
-static void mptcp_nl_remove_addrs_list(struct net *net,
-				       struct list_head *rm_list)
+static void mptcp_nl_flush_addrs_list(struct net *net,
+				      struct list_head *rm_list)
 {
 	long s_slot = 0, s_num = 0;
 	struct mptcp_sock *msk;
@@ -1715,7 +1715,7 @@ static void mptcp_nl_remove_addrs_list(struct net *net,
 
 		if (!mptcp_pm_is_userspace(msk)) {
 			lock_sock(sk);
-			mptcp_pm_remove_addrs_and_subflows(msk, rm_list);
+			mptcp_pm_flush_addrs_and_subflows(msk, rm_list);
 			release_sock(sk);
 		}
 
@@ -1756,7 +1756,7 @@ int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info)
 	pernet->next_id = 1;
 	bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	spin_unlock_bh(&pernet->lock);
-	mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list);
+	mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list);
 	synchronize_rcu();
 	__flush_addrs(&free_list);
 	return 0;
-- 
cgit v1.3-3-g829e


From b83fbca1b4c9c45628aa55d582c14825b0e71c2b Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:53 +0200
Subject: mptcp: pm: reduce entries iterations on connect

__mptcp_subflow_connect() is currently called from the path-managers,
which have all the required information to create subflows. No need to
call the PM again to re-iterate over the list of entries with RCU lock
to get more info.

Instead, it is possible to pass a mptcp_pm_addr_entry structure, instead
of a mptcp_addr_info one. The former contains the ifindex and the flags
that are required when creating the new subflow.

This is a partial revert of commit ee285257a9c1 ("mptcp: drop flags and
ifindex arguments").

While at it, the local ID can also be set if it is known and 0, to avoid
having to set it in the 'rebuild_header' hook, which will cause a new
iteration of the endpoint entries.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-2-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c           | 11 --------
 net/mptcp/pm_netlink.c   | 66 ++++++++++++++++++------------------------------
 net/mptcp/pm_userspace.c | 40 ++++++++++-------------------
 net/mptcp/protocol.h     | 16 +++++-------
 net/mptcp/subflow.c      | 29 +++++++++++++--------
 5 files changed, 62 insertions(+), 100 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 37f6dbcd8434..620264c75dc2 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -430,17 +430,6 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
-					 u8 *flags, int *ifindex)
-{
-	*flags = 0;
-	*ifindex = 0;
-
-	if (mptcp_pm_is_userspace(msk))
-		return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
-	return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
-}
-
 int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 275959581586..62a42f7ee7cb 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -149,7 +149,7 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
 static bool
 select_local_address(const struct pm_nl_pernet *pernet,
 		     const struct mptcp_sock *msk,
-		     struct mptcp_pm_addr_entry *new_entry)
+		     struct mptcp_pm_local *new_local)
 {
 	struct mptcp_pm_addr_entry *entry;
 	bool found = false;
@@ -164,7 +164,9 @@ select_local_address(const struct pm_nl_pernet *pernet,
 		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
 			continue;
 
-		*new_entry = *entry;
+		new_local->addr = entry->addr;
+		new_local->flags = entry->flags;
+		new_local->ifindex = entry->ifindex;
 		found = true;
 		break;
 	}
@@ -175,7 +177,7 @@ select_local_address(const struct pm_nl_pernet *pernet,
 
 static bool
 select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
-		      struct mptcp_pm_addr_entry *new_entry)
+		     struct mptcp_pm_local *new_local)
 {
 	struct mptcp_pm_addr_entry *entry;
 	bool found = false;
@@ -193,7 +195,9 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
 			continue;
 
-		*new_entry = *entry;
+		new_local->addr = entry->addr;
+		new_local->flags = entry->flags;
+		new_local->ifindex = entry->ifindex;
 		found = true;
 		break;
 	}
@@ -524,11 +528,11 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
-	struct mptcp_pm_addr_entry local;
 	unsigned int add_addr_signal_max;
 	bool signal_and_subflow = false;
 	unsigned int local_addr_max;
 	struct pm_nl_pernet *pernet;
+	struct mptcp_pm_local local;
 	unsigned int subflows_max;
 
 	pernet = pm_nl_get_pernet(sock_net(sk));
@@ -629,7 +633,7 @@ subflow:
 
 		spin_unlock_bh(&msk->pm.lock);
 		for (i = 0; i < nr; i++)
-			__mptcp_subflow_connect(sk, &local.addr, &addrs[i]);
+			__mptcp_subflow_connect(sk, &local, &addrs[i]);
 		spin_lock_bh(&msk->pm.lock);
 	}
 	mptcp_pm_nl_check_work_pending(msk);
@@ -650,7 +654,7 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
  */
 static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 					     struct mptcp_addr_info *remote,
-					     struct mptcp_addr_info *addrs)
+					     struct mptcp_pm_local *locals)
 {
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *entry;
@@ -673,13 +677,15 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 			continue;
 
 		if (msk->pm.subflows < subflows_max) {
-			msk->pm.subflows++;
-			addrs[i] = entry->addr;
+			locals[i].addr = entry->addr;
+			locals[i].flags = entry->flags;
+			locals[i].ifindex = entry->ifindex;
 
 			/* Special case for ID0: set the correct ID */
-			if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port))
-				addrs[i].id = 0;
+			if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port))
+				locals[i].addr.id = 0;
 
+			msk->pm.subflows++;
 			i++;
 		}
 	}
@@ -689,21 +695,19 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 	 * 'IPADDRANY' local address
 	 */
 	if (!i) {
-		struct mptcp_addr_info local;
-
-		memset(&local, 0, sizeof(local));
-		local.family =
+		memset(&locals[i], 0, sizeof(locals[i]));
+		locals[i].addr.family =
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 			       remote->family == AF_INET6 &&
 			       ipv6_addr_v4mapped(&remote->addr6) ? AF_INET :
 #endif
 			       remote->family;
 
-		if (!mptcp_pm_addr_families_match(sk, &local, remote))
+		if (!mptcp_pm_addr_families_match(sk, &locals[i].addr, remote))
 			return 0;
 
 		msk->pm.subflows++;
-		addrs[i++] = local;
+		i++;
 	}
 
 	return i;
@@ -711,7 +715,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 
 static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 {
-	struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
+	struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX];
 	struct sock *sk = (struct sock *)msk;
 	unsigned int add_addr_accept_max;
 	struct mptcp_addr_info remote;
@@ -740,13 +744,13 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	/* connect to the specified remote address, using whatever
 	 * local address the routing configuration will pick.
 	 */
-	nr = fill_local_addresses_vec(msk, &remote, addrs);
+	nr = fill_local_addresses_vec(msk, &remote, locals);
 	if (nr == 0)
 		return;
 
 	spin_unlock_bh(&msk->pm.lock);
 	for (i = 0; i < nr; i++)
-		if (__mptcp_subflow_connect(sk, &addrs[i], &remote) == 0)
+		if (__mptcp_subflow_connect(sk, &locals[i], &remote) == 0)
 			sf_created = true;
 	spin_lock_bh(&msk->pm.lock);
 
@@ -1433,28 +1437,6 @@ out_free:
 	return ret;
 }
 
-int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
-					    u8 *flags, int *ifindex)
-{
-	struct mptcp_pm_addr_entry *entry;
-	struct sock *sk = (struct sock *)msk;
-	struct net *net = sock_net(sk);
-
-	/* No entries with ID 0 */
-	if (id == 0)
-		return 0;
-
-	rcu_read_lock();
-	entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
-	if (entry) {
-		*flags = entry->flags;
-		*ifindex = entry->ifindex;
-	}
-	rcu_read_unlock();
-
-	return 0;
-}
-
 static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
 				      const struct mptcp_addr_info *addr)
 {
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 8eaa9fbe3e34..2cceded3a83a 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -119,23 +119,6 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id)
 	return NULL;
 }
 
-int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
-						   unsigned int id,
-						   u8 *flags, int *ifindex)
-{
-	struct mptcp_pm_addr_entry *match;
-
-	spin_lock_bh(&msk->pm.lock);
-	match = mptcp_userspace_pm_lookup_addr_by_id(msk, id);
-	spin_unlock_bh(&msk->pm.lock);
-	if (match) {
-		*flags = match->flags;
-		*ifindex = match->ifindex;
-	}
-
-	return 0;
-}
-
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 				    struct mptcp_addr_info *skc)
 {
@@ -352,8 +335,9 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
-	struct mptcp_pm_addr_entry local = { 0 };
+	struct mptcp_pm_addr_entry entry = { 0 };
 	struct mptcp_addr_info addr_r;
+	struct mptcp_pm_local local;
 	struct mptcp_sock *msk;
 	int err = -EINVAL;
 	struct sock *sk;
@@ -379,18 +363,18 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 		goto create_err;
 	}
 
-	err = mptcp_pm_parse_entry(laddr, info, true, &local);
+	err = mptcp_pm_parse_entry(laddr, info, true, &entry);
 	if (err < 0) {
 		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr");
 		goto create_err;
 	}
 
-	if (local.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
+	if (entry.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
 		GENL_SET_ERR_MSG(info, "invalid addr flags");
 		err = -EINVAL;
 		goto create_err;
 	}
-	local.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
+	entry.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
 
 	err = mptcp_pm_parse_addr(raddr, info, &addr_r);
 	if (err < 0) {
@@ -398,27 +382,29 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 		goto create_err;
 	}
 
-	if (!mptcp_pm_addr_families_match(sk, &local.addr, &addr_r)) {
+	if (!mptcp_pm_addr_families_match(sk, &entry.addr, &addr_r)) {
 		GENL_SET_ERR_MSG(info, "families mismatch");
 		err = -EINVAL;
 		goto create_err;
 	}
 
-	err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false);
+	err = mptcp_userspace_pm_append_new_local_addr(msk, &entry, false);
 	if (err < 0) {
 		GENL_SET_ERR_MSG(info, "did not match address and id");
 		goto create_err;
 	}
 
-	lock_sock(sk);
-
-	err = __mptcp_subflow_connect(sk, &local.addr, &addr_r);
+	local.addr = entry.addr;
+	local.flags = entry.flags;
+	local.ifindex = entry.ifindex;
 
+	lock_sock(sk);
+	err = __mptcp_subflow_connect(sk, &local, &addr_r);
 	release_sock(sk);
 
 	spin_lock_bh(&msk->pm.lock);
 	if (err)
-		mptcp_userspace_pm_delete_local_addr(msk, &local);
+		mptcp_userspace_pm_delete_local_addr(msk, &entry);
 	else
 		msk->pm.subflows++;
 	spin_unlock_bh(&msk->pm.lock);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3735b20f2626..bf03bff9ac44 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -236,6 +236,12 @@ struct mptcp_pm_data {
 	struct mptcp_rm_list rm_list_rx;
 };
 
+struct mptcp_pm_local {
+	struct mptcp_addr_info	addr;
+	u8			flags;
+	int			ifindex;
+};
+
 struct mptcp_pm_addr_entry {
 	struct list_head	list;
 	struct mptcp_addr_info	addr;
@@ -719,7 +725,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr);
 
 /* called with sk socket lock held */
-int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 			    const struct mptcp_addr_info *remote);
 int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 				struct socket **new_sock);
@@ -1014,14 +1020,6 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 struct mptcp_pm_add_entry *
 mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
 				const struct mptcp_addr_info *addr);
-int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
-					 unsigned int id,
-					 u8 *flags, int *ifindex);
-int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
-					    u8 *flags, int *ifindex);
-int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
-						   unsigned int id,
-						   u8 *flags, int *ifindex);
 int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
 int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info);
 int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 064ab3235893..0796122c9467 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1565,26 +1565,24 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 #endif
 }
 
-int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 			    const struct mptcp_addr_info *remote)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
+	int local_id = local->addr.id;
 	struct sockaddr_storage addr;
 	int remote_id = remote->id;
-	int local_id = loc->id;
 	int err = -ENOTCONN;
 	struct socket *sf;
 	struct sock *ssk;
 	u32 remote_token;
 	int addrlen;
-	int ifindex;
-	u8 flags;
 
 	if (!mptcp_is_fully_established(sk))
 		goto err_out;
 
-	err = mptcp_subflow_create_socket(sk, loc->family, &sf);
+	err = mptcp_subflow_create_socket(sk, local->addr.family, &sf);
 	if (err)
 		goto err_out;
 
@@ -1594,23 +1592,32 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 		get_random_bytes(&subflow->local_nonce, sizeof(u32));
 	} while (!subflow->local_nonce);
 
-	if (local_id)
+	/* if 'IPADDRANY', the ID will be set later, after the routing */
+	if (local->addr.family == AF_INET) {
+		if (!local->addr.addr.s_addr)
+			local_id = -1;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	} else if (sk->sk_family == AF_INET6) {
+		if (ipv6_addr_any(&local->addr.addr6))
+			local_id = -1;
+#endif
+	}
+
+	if (local_id >= 0)
 		subflow_set_local_id(subflow, local_id);
 
-	mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id,
-					     &flags, &ifindex);
 	subflow->remote_key_valid = 1;
 	subflow->remote_key = READ_ONCE(msk->remote_key);
 	subflow->local_key = READ_ONCE(msk->local_key);
 	subflow->token = msk->token;
-	mptcp_info2sockaddr(loc, &addr, ssk->sk_family);
+	mptcp_info2sockaddr(&local->addr, &addr, ssk->sk_family);
 
 	addrlen = sizeof(struct sockaddr_in);
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	if (addr.ss_family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	ssk->sk_bound_dev_if = ifindex;
+	ssk->sk_bound_dev_if = local->ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
 	if (err)
 		goto failed;
@@ -1621,7 +1628,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	subflow->remote_token = remote_token;
 	WRITE_ONCE(subflow->remote_id, remote_id);
 	subflow->request_join = 1;
-	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	subflow->request_bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	subflow->subflow_id = msk->subflow_id++;
 	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
 
-- 
cgit v1.3-3-g829e


From 1bd1788b6cabfe86fe1ced5a6324831f6a3081a1 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:54 +0200
Subject: mptcp: MIB counters for sent MP_JOIN

Recently, a few issues have been discovered around the creation of
additional subflows. Without these counters, it was difficult to point
out the reason why some subflows were not created as expected.

These counters should have been added earlier, because there is no other
simple ways to extract such information from the kernel, and understand
why subflows have not been created.

While at it, some pr_debug() have been added, just in case the errno
needs to be printed.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/509
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-3-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/mib.c     |  4 ++++
 net/mptcp/mib.h     |  4 ++++
 net/mptcp/subflow.c | 21 ++++++++++++++++++---
 3 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 7884217f33eb..ec0d461cb921 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -25,6 +25,10 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
 	SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
+	SNMP_MIB_ITEM("MPJoinSynTx", MPTCP_MIB_JOINSYNTX),
+	SNMP_MIB_ITEM("MPJoinSynTxCreatSkErr", MPTCP_MIB_JOINSYNTXCREATSKERR),
+	SNMP_MIB_ITEM("MPJoinSynTxBindErr", MPTCP_MIB_JOINSYNTXBINDERR),
+	SNMP_MIB_ITEM("MPJoinSynTxConnectErr", MPTCP_MIB_JOINSYNTXCONNECTERR),
 	SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
 	SNMP_MIB_ITEM("InfiniteMapTx", MPTCP_MIB_INFINITEMAPTX),
 	SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 66aa67f49d03..d68136f93dac 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -20,6 +20,10 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_JOINSYNACKMAC,	/* HMAC was wrong on SYN/ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKRX,		/* Received an ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */
+	MPTCP_MIB_JOINSYNTX,		/* Sending a SYN + MP_JOIN */
+	MPTCP_MIB_JOINSYNTXCREATSKERR,	/* Not able to create a socket when sending a SYN + MP_JOIN */
+	MPTCP_MIB_JOINSYNTXBINDERR,	/* Not able to bind() the address when sending a SYN + MP_JOIN */
+	MPTCP_MIB_JOINSYNTXCONNECTERR,	/* Not able to connect() when sending a SYN + MP_JOIN */
 	MPTCP_MIB_DSSNOMATCH,		/* Received a new mapping that did not match the previous one */
 	MPTCP_MIB_INFINITEMAPTX,	/* Sent an infinite mapping */
 	MPTCP_MIB_INFINITEMAPRX,	/* Received an infinite mapping */
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 0796122c9467..b9b14e75e8c2 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1579,12 +1579,17 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 	u32 remote_token;
 	int addrlen;
 
+	/* The userspace PM sent the request too early? */
 	if (!mptcp_is_fully_established(sk))
 		goto err_out;
 
 	err = mptcp_subflow_create_socket(sk, local->addr.family, &sf);
-	if (err)
+	if (err) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCREATSKERR);
+		pr_debug("msk=%p local=%d remote=%d create sock error: %d\n",
+			 msk, local_id, remote_id, err);
 		goto err_out;
+	}
 
 	ssk = sf->sk;
 	subflow = mptcp_subflow_ctx(ssk);
@@ -1619,8 +1624,12 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 #endif
 	ssk->sk_bound_dev_if = local->ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
-	if (err)
+	if (err) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXBINDERR);
+		pr_debug("msk=%p local=%d remote=%d bind error: %d\n",
+			 msk, local_id, remote_id, err);
 		goto failed;
+	}
 
 	mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
 	pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk,
@@ -1635,8 +1644,14 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,
 	sock_hold(ssk);
 	list_add_tail(&subflow->node, &msk->conn_list);
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
-	if (err && err != -EINPROGRESS)
+	if (err && err != -EINPROGRESS) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCONNECTERR);
+		pr_debug("msk=%p local=%d remote=%d connect error: %d\n",
+			 msk, local_id, remote_id, err);
 		goto failed_unlink;
+	}
+
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTX);
 
 	/* discard the subflow socket */
 	mptcp_sock_graft(ssk, sk->sk_socket);
-- 
cgit v1.3-3-g829e


From 1b2965a8cd8d444cbea891e55083b5987d00cc66 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:55 +0200
Subject: selftests: mptcp: join: reduce join_nr params

chk_join_nr() currently takes 9 positional parameters, 6 of them are
optional. It makes it hard to read:

  chk_join_nr 1 1 1 1 0 1 1 0 4

Naming these vars helps to make it easier to read:

  join_csum_ns1=1 join_csum_ns2=0 \
    join_fail_nr=1 join_rst_nr=1 join_infi_nr=0 \
    join_corrupted_pkts=4 \
    chk_join_nr 1 1 1

It will then be easier to add new optional parameters.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-4-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 31 ++++++++++++++++++-------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index a4762c49a878..51b226784c6b 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -61,6 +61,12 @@ unset sflags
 unset fastclose
 unset fullmesh
 unset speed
+unset join_csum_ns1
+unset join_csum_ns2
+unset join_fail_nr
+unset join_rst_nr
+unset join_infi_nr
+unset join_corrupted_pkts
 
 # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
 #				  (ip6 && (ip6[74] & 0xf0) == 0x30)'"
@@ -1319,12 +1325,12 @@ chk_join_nr()
 	local syn_nr=$1
 	local syn_ack_nr=$2
 	local ack_nr=$3
-	local csum_ns1=${4:-0}
-	local csum_ns2=${5:-0}
-	local fail_nr=${6:-0}
-	local rst_nr=${7:-0}
-	local infi_nr=${8:-0}
-	local corrupted_pkts=${9:-0}
+	local csum_ns1=${join_csum_ns1:-0}
+	local csum_ns2=${join_csum_ns2:-0}
+	local fail_nr=${join_fail_nr:-0}
+	local rst_nr=${join_rst_nr:-0}
+	local infi_nr=${join_infi_nr:-0}
+	local corrupted_pkts=${join_corrupted_pkts:-0}
 	local count
 	local with_cookie
 
@@ -3164,7 +3170,8 @@ fastclose_tests()
 		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0 0 0 0 1
+		join_rst_nr=1 \
+			chk_join_nr 0 0 0
 		chk_fclose_nr 1 1 invert
 		chk_rst_nr 1 1
 	fi
@@ -3183,7 +3190,10 @@ fail_tests()
 		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=128 \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)"
+		join_csum_ns1=+1 join_csum_ns2=+0 \
+			join_fail_nr=1 join_rst_nr=0 join_infi_nr=1 \
+			join_corrupted_pkts="$(pedit_action_pkts)" \
+			chk_join_nr 0 0 0
 		chk_fail_nr 1 -1 invert
 	fi
 
@@ -3196,7 +3206,10 @@ fail_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
 		test_linkfail=1024 \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1 1 0 1 1 0 "$(pedit_action_pkts)"
+		join_csum_ns1=1 join_csum_ns2=0 \
+			join_fail_nr=1 join_rst_nr=1 join_infi_nr=0 \
+			join_corrupted_pkts="$(pedit_action_pkts)" \
+			chk_join_nr 1 1 1
 	fi
 }
 
-- 
cgit v1.3-3-g829e


From ba8a664004da84e4e04205429043a1bc19e00d23 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:56 +0200
Subject: selftests: mptcp: join: one line for join check

Most tests are checking if the expected number of SYN/SYN+ACK/ACK JOINs
have been received, each of them on one line.

More Join related tests are going to be checked soon, no need to add 5
new lines per test in case of success, just one is enough. In case of
issue, the errors will still be reported like before.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-5-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 45 ++++++++++++++++---------
 1 file changed, 30 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 51b226784c6b..63580a5810bf 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -202,6 +202,22 @@ print_skip()
 	mptcp_lib_pr_skip "${@}"
 }
 
+# $1: check name; $2: rc
+print_results()
+{
+	local check="${1}"
+	local rc=${2}
+
+	print_check "${check}"
+	if [ ${rc} = ${KSFT_PASS} ]; then
+		print_ok
+	elif [ ${rc} = ${KSFT_SKIP} ]; then
+		print_skip
+	else
+		fail_test "see above"
+	fi
+}
+
 # [ $1: fail msg ]
 mark_as_skipped()
 {
@@ -1331,6 +1347,7 @@ chk_join_nr()
 	local rst_nr=${join_rst_nr:-0}
 	local infi_nr=${join_infi_nr:-0}
 	local corrupted_pkts=${join_corrupted_pkts:-0}
+	local rc=${KSFT_PASS}
 	local count
 	local with_cookie
 
@@ -1338,43 +1355,41 @@ chk_join_nr()
 		print_info "${corrupted_pkts} corrupted pkts"
 	fi
 
-	print_check "syn"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynRx")
 	if [ -z "$count" ]; then
-		print_skip
+		rc=${KSFT_SKIP}
 	elif [ "$count" != "$syn_nr" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn"
 		fail_test "got $count JOIN[s] syn expected $syn_nr"
-	else
-		print_ok
 	fi
 
-	print_check "synack"
 	with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies)
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckRx")
 	if [ -z "$count" ]; then
-		print_skip
+		rc=${KSFT_SKIP}
 	elif [ "$count" != "$syn_ack_nr" ]; then
 		# simult connections exceeding the limit with cookie enabled could go up to
 		# synack validation as the conn limit can be enforced reliably only after
 		# the subflow creation
-		if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then
-			print_ok
-		else
+		if [ "$with_cookie" != 2 ] || [ "$count" -le "$syn_ack_nr" ] || [ "$count" -gt "$syn_nr" ]; then
+			rc=${KSFT_FAIL}
+			print_check "synack"
 			fail_test "got $count JOIN[s] synack expected $syn_ack_nr"
 		fi
-	else
-		print_ok
 	fi
 
-	print_check "ack"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinAckRx")
 	if [ -z "$count" ]; then
-		print_skip
+		rc=${KSFT_SKIP}
 	elif [ "$count" != "$ack_nr" ]; then
+		rc=${KSFT_FAIL}
+		print_check "ack"
 		fail_test "got $count JOIN[s] ack expected $ack_nr"
-	else
-		print_ok
 	fi
+
+	print_results "join Rx" ${rc}
+
 	if $validate_checksum; then
 		chk_csum_nr $csum_ns1 $csum_ns2
 		chk_fail_nr $fail_nr $fail_nr
-- 
cgit v1.3-3-g829e


From 004125c251a6826d080bb28feb48ebc5454ada81 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:57 +0200
Subject: selftests: mptcp: join: validate MPJ SYN TX MIB counters

A few new MPJoinSynTx MIB counters have been added in a previous commit.
They are being validated here in mptcp_join.sh selftest, each time the
number of received MPJ are checked.

Most of the time, the number of sent SYN+MPJ is the same as the received
ones. But sometimes, there are more, because there are dropped, or there
are errors.

While at it, the "no MPC reuse with single endpoint" subtest has been
modified to force a bind() error.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-6-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 89 ++++++++++++++++++++++---
 1 file changed, 78 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 63580a5810bf..23f8e2254064 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -67,6 +67,10 @@ unset join_fail_nr
 unset join_rst_nr
 unset join_infi_nr
 unset join_corrupted_pkts
+unset join_syn_tx
+unset join_create_err
+unset join_bind_err
+unset join_connect_err
 
 # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
 #				  (ip6 && (ip6[74] & 0xf0) == 0x30)'"
@@ -1336,6 +1340,54 @@ chk_infi_nr()
 	fi
 }
 
+chk_join_tx_nr()
+{
+	local syn_tx=${join_syn_tx:-0}
+	local create=${join_create_err:-0}
+	local bind=${join_bind_err:-0}
+	local connect=${join_connect_err:-0}
+	local rc=${KSFT_PASS}
+	local count
+
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynTx")
+	if [ -z "$count" ]; then
+		rc=${KSFT_SKIP}
+	elif [ "$count" != "$syn_tx" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn tx"
+		fail_test "got $count JOIN[s] syn tx expected $syn_tx"
+	fi
+
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynTxCreatSkErr")
+	if [ -z "$count" ]; then
+		rc=${KSFT_SKIP}
+	elif [ "$count" != "$create" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn tx create socket error"
+		fail_test "got $count JOIN[s] syn tx create socket error expected $create"
+	fi
+
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynTxBindErr")
+	if [ -z "$count" ]; then
+		rc=${KSFT_SKIP}
+	elif [ "$count" != "$bind" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn tx bind error"
+		fail_test "got $count JOIN[s] syn tx bind error expected $bind"
+	fi
+
+	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynTxConnectErr")
+	if [ -z "$count" ]; then
+		rc=${KSFT_SKIP}
+	elif [ "$count" != "$connect" ]; then
+		rc=${KSFT_FAIL}
+		print_check "syn tx connect error"
+		fail_test "got $count JOIN[s] syn tx connect error expected $connect"
+	fi
+
+	print_results "join Tx" ${rc}
+}
+
 chk_join_nr()
 {
 	local syn_nr=$1
@@ -1390,6 +1442,9 @@ chk_join_nr()
 
 	print_results "join Rx" ${rc}
 
+	join_syn_tx="${join_syn_tx:-${syn_nr}}" \
+		chk_join_tx_nr
+
 	if $validate_checksum; then
 		chk_csum_nr $csum_ns1 $csum_ns2
 		chk_fail_nr $fail_nr $fail_nr
@@ -1930,9 +1985,11 @@ subflows_error_tests()
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
 		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow
+		pm_nl_add_endpoint $ns2 10.0.12.2 flags subflow
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
+		join_bind_err=1 \
+			chk_join_nr 0 0 0
 	fi
 
 	# multiple subflows, with subflow creation error
@@ -1944,7 +2001,8 @@ subflows_error_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1
+		join_syn_tx=2 \
+			chk_join_nr 1 1 1
 	fi
 
 	# multiple subflows, with subflow timeout on MPJ
@@ -1956,7 +2014,8 @@ subflows_error_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
 		speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1
+		join_syn_tx=2 \
+			chk_join_nr 1 1 1
 	fi
 
 	# multiple subflows, check that the endpoint corresponding to
@@ -1977,7 +2036,8 @@ subflows_error_tests()
 
 		# additional subflow could be created only if the PM select
 		# the later endpoint, skipping the already used one
-		chk_join_nr 1 1 1
+		join_syn_tx=2 \
+			chk_join_nr 1 1 1
 	fi
 }
 
@@ -2063,7 +2123,8 @@ signal_address_tests()
 		pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
 		pm_nl_set_limits $ns2 3 3
 		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1
+		join_syn_tx=3 \
+			chk_join_nr 1 1 1
 		chk_add_nr 3 3
 	fi
 
@@ -2231,7 +2292,8 @@ add_addr_timeout_tests()
 		pm_nl_set_limits $ns2 2 2
 		speed=10 \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1
+		join_syn_tx=2 \
+			chk_join_nr 1 1 1
 		chk_add_nr 8 0
 	fi
 }
@@ -2331,7 +2393,8 @@ remove_tests()
 		pm_nl_set_limits $ns2 2 2
 		addr_nr_ns1=-3 speed=10 \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1
+		join_syn_tx=2 join_connect_err=1 \
+			chk_join_nr 1 1 1
 		chk_add_nr 3 3
 		chk_rm_nr 3 1 invert
 		chk_rst_nr 0 0
@@ -2396,7 +2459,8 @@ remove_tests()
 		pm_nl_set_limits $ns2 3 3
 		addr_nr_ns1=-8 speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 1 1 1
+		join_syn_tx=3 \
+			chk_join_nr 1 1 1
 		chk_add_nr 3 3
 		chk_rm_nr 3 1 invert
 		chk_rst_nr 0 0
@@ -3703,7 +3767,8 @@ endpoint_tests()
 		chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_ESTABLISHED 6
 		chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 5 # one has been closed before estab
 
-		chk_join_nr 6 6 6
+		join_syn_tx=7 \
+			chk_join_nr 6 6 6
 		chk_rm_nr 4 4
 	fi
 
@@ -3775,7 +3840,8 @@ endpoint_tests()
 		chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_ESTABLISHED 5
 		chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 3
 
-		chk_join_nr 5 5 5
+		join_connect_err=1 \
+			chk_join_nr 5 5 5
 		chk_add_nr 6 6
 		chk_rm_nr 4 3 invert
 	fi
@@ -3806,7 +3872,8 @@ endpoint_tests()
 		wait_mpj $ns2
 		mptcp_lib_kill_wait $tests_pid
 
-		chk_join_nr 2 2 2
+		join_syn_tx=3 join_connect_err=1 \
+			chk_join_nr 2 2 2
 		chk_add_nr 2 2
 		chk_rm_nr 1 0 invert
 	fi
-- 
cgit v1.3-3-g829e


From 6ed495345be8113899986d21c6cbc7d8f550dedb Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:58 +0200
Subject: selftests: mptcp: join: more explicit check name

Before, the check names had to be very short. It is no longer the case
now that these checks are printed on a dedicated line.

Then, it looks better to have more explicit names.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-7-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 65 +++++++++++++------------
 1 file changed, 33 insertions(+), 32 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 23f8e2254064..7993e0e0029e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -865,7 +865,7 @@ chk_cestab_nr()
 	local cestab=$2
 	local count
 
-	print_check "cestab $cestab"
+	print_check "currently established: $cestab"
 	count=$(mptcp_lib_get_counter ${ns} "MPTcpExtMPCurrEstab")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1141,7 +1141,7 @@ chk_csum_nr()
 		csum_ns2=${csum_ns2:1}
 	fi
 
-	print_check "sum"
+	print_check "checksum server"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr")
 	if [ -n "$count" ] && [ "$count" != "$csum_ns1" ]; then
 		extra_msg+=" ns1=$count"
@@ -1154,7 +1154,8 @@ chk_csum_nr()
 	else
 		print_ok
 	fi
-	print_check "csum"
+
+	print_check "checksum client"
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr")
 	if [ -n "$count" ] && [ "$count" != "$csum_ns2" ]; then
 		extra_msg+=" ns2=$count"
@@ -1198,7 +1199,7 @@ chk_fail_nr()
 		fail_rx=${fail_rx:1}
 	fi
 
-	print_check "ftx"
+	print_check "fail tx"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx")
 	if [ -n "$count" ] && [ "$count" != "$fail_tx" ]; then
 		extra_msg+=",tx=$count"
@@ -1212,7 +1213,7 @@ chk_fail_nr()
 		print_ok
 	fi
 
-	print_check "failrx"
+	print_check "fail rx"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx")
 	if [ -n "$count" ] && [ "$count" != "$fail_rx" ]; then
 		extra_msg+=",rx=$count"
@@ -1245,7 +1246,7 @@ chk_fclose_nr()
 		extra_msg="invert"
 	fi
 
-	print_check "ctx"
+	print_check "fast close tx"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFastcloseTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1256,7 +1257,7 @@ chk_fclose_nr()
 		print_ok
 	fi
 
-	print_check "fclzrx"
+	print_check "fast close rx"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFastcloseRx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1286,7 +1287,7 @@ chk_rst_nr()
 		extra_msg="invert"
 	fi
 
-	print_check "rtx"
+	print_check "reset tx"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPRstTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1298,7 +1299,7 @@ chk_rst_nr()
 		print_ok
 	fi
 
-	print_check "rstrx"
+	print_check "reset rx"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPRstRx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1319,7 +1320,7 @@ chk_infi_nr()
 	local infi_rx=$2
 	local count
 
-	print_check "itx"
+	print_check "infi tx"
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtInfiniteMapTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1329,7 +1330,7 @@ chk_infi_nr()
 		print_ok
 	fi
 
-	print_check "infirx"
+	print_check "infi rx"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtInfiniteMapRx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1412,8 +1413,8 @@ chk_join_nr()
 		rc=${KSFT_SKIP}
 	elif [ "$count" != "$syn_nr" ]; then
 		rc=${KSFT_FAIL}
-		print_check "syn"
-		fail_test "got $count JOIN[s] syn expected $syn_nr"
+		print_check "syn rx"
+		fail_test "got $count JOIN[s] syn rx expected $syn_nr"
 	fi
 
 	with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies)
@@ -1426,8 +1427,8 @@ chk_join_nr()
 		# the subflow creation
 		if [ "$with_cookie" != 2 ] || [ "$count" -le "$syn_ack_nr" ] || [ "$count" -gt "$syn_nr" ]; then
 			rc=${KSFT_FAIL}
-			print_check "synack"
-			fail_test "got $count JOIN[s] synack expected $syn_ack_nr"
+			print_check "synack rx"
+			fail_test "got $count JOIN[s] synack rx expected $syn_ack_nr"
 		fi
 	fi
 
@@ -1436,8 +1437,8 @@ chk_join_nr()
 		rc=${KSFT_SKIP}
 	elif [ "$count" != "$ack_nr" ]; then
 		rc=${KSFT_FAIL}
-		print_check "ack"
-		fail_test "got $count JOIN[s] ack expected $ack_nr"
+		print_check "ack rx"
+		fail_test "got $count JOIN[s] ack rx expected $ack_nr"
 	fi
 
 	print_results "join Rx" ${rc}
@@ -1517,7 +1518,7 @@ chk_add_nr()
 
 	timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout)
 
-	print_check "add"
+	print_check "add addr rx"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1529,7 +1530,7 @@ chk_add_nr()
 		print_ok
 	fi
 
-	print_check "echo"
+	print_check "add addr echo rx"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtEchoAdd")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1540,7 +1541,7 @@ chk_add_nr()
 	fi
 
 	if [ $port_nr -gt 0 ]; then
-		print_check "pt"
+		print_check "add addr rx with port"
 		count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtPortAdd")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1550,7 +1551,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "syn"
+		print_check "syn rx port"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortSynRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1561,7 +1562,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "synack"
+		print_check "synack rx port"
 		count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPJoinPortSynAckRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1572,7 +1573,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "ack"
+		print_check "ack rx port"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortAckRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1583,7 +1584,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "syn"
+		print_check "syn rx port mismatch"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortSynRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1594,7 +1595,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "ack"
+		print_check "ack rx port mismatch"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortAckRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1618,7 +1619,7 @@ chk_add_tx_nr()
 
 	timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
 
-	print_check "add TX"
+	print_check "add addr tx"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1630,7 +1631,7 @@ chk_add_tx_nr()
 		print_ok
 	fi
 
-	print_check "echo TX"
+	print_check "add addr echo tx"
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtEchoAddTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1668,7 +1669,7 @@ chk_rm_nr()
 		extra_msg="invert"
 	fi
 
-	print_check "rm"
+	print_check "rm addr rx"
 	count=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmAddr")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1678,7 +1679,7 @@ chk_rm_nr()
 		print_ok
 	fi
 
-	print_check "rmsf"
+	print_check "rm subflow"
 	count=$(mptcp_lib_get_counter ${subflow_ns} "MPTcpExtRmSubflow")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1713,7 +1714,7 @@ chk_rm_tx_nr()
 {
 	local rm_addr_tx_nr=$1
 
-	print_check "rm TX"
+	print_check "rm addr tx"
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtRmAddrTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1732,7 +1733,7 @@ chk_prio_nr()
 	local mpj_syn_ack=$4
 	local count
 
-	print_check "ptx"
+	print_check "mp_prio tx"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1742,7 +1743,7 @@ chk_prio_nr()
 		print_ok
 	fi
 
-	print_check "prx"
+	print_check "mp_prio rx"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioRx")
 	if [ -z "$count" ]; then
 		print_skip
-- 
cgit v1.3-3-g829e


From 8d328dbcf61b50ca51f8a930561fe6ae2c8bf5e9 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:45:59 +0200
Subject: selftests: mptcp: join: specify host being checked

Instead of displaying 'invert' when looking at some events like MP_FAIL,
MP_FASTCLOSE, MP_RESET, RM_ADDR, which is a bit vague because they are
not traditionnaly sent from one side, the host being checked is now
printed.

For the ADD_ADDR, only display the host when it is the client sending
it, which is more unusual.

Also before, the 'invert' message was printed after a few checks, but it
was not clear which ones exactly.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-8-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 89 +++++++++++++------------
 1 file changed, 45 insertions(+), 44 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 7993e0e0029e..321197d8977e 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1180,6 +1180,8 @@ chk_fail_nr()
 	local count
 	local ns_tx=$ns1
 	local ns_rx=$ns2
+	local tx="server"
+	local rx="client"
 	local extra_msg=""
 	local allow_tx_lost=0
 	local allow_rx_lost=0
@@ -1187,7 +1189,8 @@ chk_fail_nr()
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns2
 		ns_rx=$ns1
-		extra_msg="invert"
+		tx="client"
+		rx="server"
 	fi
 
 	if [[ "${fail_tx}" = "-"* ]]; then
@@ -1199,10 +1202,10 @@ chk_fail_nr()
 		fail_rx=${fail_rx:1}
 	fi
 
-	print_check "fail tx"
+	print_check "fail tx ${tx}"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx")
 	if [ -n "$count" ] && [ "$count" != "$fail_tx" ]; then
-		extra_msg+=",tx=$count"
+		extra_msg+=" tx=$count"
 	fi
 	if [ -z "$count" ]; then
 		print_skip
@@ -1213,10 +1216,10 @@ chk_fail_nr()
 		print_ok
 	fi
 
-	print_check "fail rx"
+	print_check "fail rx ${rx}"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx")
 	if [ -n "$count" ] && [ "$count" != "$fail_rx" ]; then
-		extra_msg+=",rx=$count"
+		extra_msg+=" rx=$count"
 	fi
 	if [ -z "$count" ]; then
 		print_skip
@@ -1238,37 +1241,35 @@ chk_fclose_nr()
 	local count
 	local ns_tx=$ns2
 	local ns_rx=$ns1
-	local extra_msg=""
+	local tx="client"
+	local rx="server"
 
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns1
 		ns_rx=$ns2
-		extra_msg="invert"
+		tx="server"
+		rx="client"
 	fi
 
-	print_check "fast close tx"
+	print_check "fast close tx ${tx}"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFastcloseTx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$fclose_tx" ]; then
-		extra_msg+=",tx=$count"
 		fail_test "got $count MP_FASTCLOSE[s] TX expected $fclose_tx"
 	else
 		print_ok
 	fi
 
-	print_check "fast close rx"
+	print_check "fast close rx ${rx}"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFastcloseRx")
 	if [ -z "$count" ]; then
 		print_skip
 	elif [ "$count" != "$fclose_rx" ]; then
-		extra_msg+=",rx=$count"
 		fail_test "got $count MP_FASTCLOSE[s] RX expected $fclose_rx"
 	else
 		print_ok
 	fi
-
-	print_info "$extra_msg"
 }
 
 chk_rst_nr()
@@ -1279,15 +1280,17 @@ chk_rst_nr()
 	local count
 	local ns_tx=$ns1
 	local ns_rx=$ns2
-	local extra_msg=""
+	local tx="server"
+	local rx="client"
 
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns2
 		ns_rx=$ns1
-		extra_msg="invert"
+		tx="client"
+		rx="server"
 	fi
 
-	print_check "reset tx"
+	print_check "reset tx ${tx}"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPRstTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1299,7 +1302,7 @@ chk_rst_nr()
 		print_ok
 	fi
 
-	print_check "reset rx"
+	print_check "reset rx ${rx}"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPRstRx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1310,8 +1313,6 @@ chk_rst_nr()
 	else
 		print_ok
 	fi
-
-	print_info "$extra_msg"
 }
 
 chk_infi_nr()
@@ -1320,7 +1321,7 @@ chk_infi_nr()
 	local infi_rx=$2
 	local count
 
-	print_check "infi tx"
+	print_check "infi tx client"
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtInfiniteMapTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1330,7 +1331,7 @@ chk_infi_nr()
 		print_ok
 	fi
 
-	print_check "infi rx"
+	print_check "infi rx server"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtInfiniteMapRx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1506,19 +1507,21 @@ chk_add_nr()
 	local mis_ack_nr=0
 	local ns_tx=$ns1
 	local ns_rx=$ns2
-	local extra_msg=""
+	local tx=""
+	local rx=""
 	local count
 	local timeout
 
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns2
 		ns_rx=$ns1
-		extra_msg="invert"
+		tx=" client"
+		rx=" server"
 	fi
 
 	timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout)
 
-	print_check "add addr rx"
+	print_check "add addr rx${rx}"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1530,7 +1533,7 @@ chk_add_nr()
 		print_ok
 	fi
 
-	print_check "add addr echo rx"
+	print_check "add addr echo rx${tx}"
 	count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtEchoAdd")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1541,7 +1544,7 @@ chk_add_nr()
 	fi
 
 	if [ $port_nr -gt 0 ]; then
-		print_check "add addr rx with port"
+		print_check "add addr rx with port${rx}"
 		count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtPortAdd")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1551,7 +1554,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "syn rx port"
+		print_check "syn rx port${tx}"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortSynRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1562,7 +1565,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "synack rx port"
+		print_check "synack rx port${rx}"
 		count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPJoinPortSynAckRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1573,7 +1576,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "ack rx port"
+		print_check "ack rx port${tx}"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortAckRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1584,7 +1587,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "syn rx port mismatch"
+		print_check "syn rx port mismatch${tx}"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortSynRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1595,7 +1598,7 @@ chk_add_nr()
 			print_ok
 		fi
 
-		print_check "ack rx port mismatch"
+		print_check "ack rx port mismatch${tx}"
 		count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortAckRx")
 		if [ -z "$count" ]; then
 			print_skip
@@ -1606,8 +1609,6 @@ chk_add_nr()
 			print_ok
 		fi
 	fi
-
-	print_info "$extra_msg"
 }
 
 chk_add_tx_nr()
@@ -1651,6 +1652,8 @@ chk_rm_nr()
 	local count
 	local addr_ns=$ns1
 	local subflow_ns=$ns2
+	local addr="server"
+	local subflow="client"
 	local extra_msg=""
 
 	shift 2
@@ -1660,16 +1663,14 @@ chk_rm_nr()
 		shift
 	done
 
-	if [ -z $invert ]; then
-		addr_ns=$ns1
-		subflow_ns=$ns2
-	elif [ $invert = "true" ]; then
+	if [ "$invert" = "true" ]; then
 		addr_ns=$ns2
 		subflow_ns=$ns1
-		extra_msg="invert"
+		addr="client"
+		subflow="server"
 	fi
 
-	print_check "rm addr rx"
+	print_check "rm addr rx ${addr}"
 	count=$(mptcp_lib_get_counter ${addr_ns} "MPTcpExtRmAddr")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1679,7 +1680,7 @@ chk_rm_nr()
 		print_ok
 	fi
 
-	print_check "rm subflow"
+	print_check "rm subflow ${subflow}"
 	count=$(mptcp_lib_get_counter ${subflow_ns} "MPTcpExtRmSubflow")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1693,7 +1694,7 @@ chk_rm_nr()
 		count=$((count + cnt))
 		if [ "$count" != "$rm_subflow_nr" ]; then
 			suffix="$count in [$rm_subflow_nr:$((rm_subflow_nr*2))]"
-			extra_msg+=" simult"
+			extra_msg="simult"
 		fi
 		if [ $count -ge "$rm_subflow_nr" ] && \
 		   [ "$count" -le "$((rm_subflow_nr *2 ))" ]; then
@@ -1714,7 +1715,7 @@ chk_rm_tx_nr()
 {
 	local rm_addr_tx_nr=$1
 
-	print_check "rm addr tx"
+	print_check "rm addr tx client"
 	count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtRmAddrTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1733,7 +1734,7 @@ chk_prio_nr()
 	local mpj_syn_ack=$4
 	local count
 
-	print_check "mp_prio tx"
+	print_check "mp_prio tx server"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioTx")
 	if [ -z "$count" ]; then
 		print_skip
@@ -1743,7 +1744,7 @@ chk_prio_nr()
 		print_ok
 	fi
 
-	print_check "mp_prio rx"
+	print_check "mp_prio rx client"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPPrioRx")
 	if [ -z "$count" ]; then
 		print_skip
-- 
cgit v1.3-3-g829e


From 08eecd7e7fe79669ccab44dde518b10a2f7e48a7 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:46:00 +0200
Subject: selftests: mptcp: join: mute errors when ran in the background

The test is supposed to be killed before the end, which will likely
cause "Connection reset by peer" errors. It is confusing, especially
because in case of real transfer errors, the test will not be marked as
failed. But that's OK, there are many other tests checking that.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-9-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 36 ++++++++++++-------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 321197d8977e..5d164abc18e5 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3542,8 +3542,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns1
 		pm_nl_set_limits $ns2 2 2
-		speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 		wait_mpj $ns1
 		userspace_pm_add_addr $ns1 10.0.2.1 10
@@ -3575,8 +3575,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns2
 		pm_nl_set_limits $ns1 0 1
-		speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 		wait_mpj $ns2
 		userspace_pm_add_sf $ns2 10.0.3.2 20
@@ -3603,8 +3603,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns2
 		pm_nl_set_limits $ns1 0 1
-		speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 		wait_mpj $ns2
 		chk_mptcp_info subflows 0 subflows 0
@@ -3624,8 +3624,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns2
 		pm_nl_set_limits $ns1 0 1
-		speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 		wait_mpj $ns2
 		userspace_pm_add_sf $ns2 10.0.3.2 20
@@ -3648,8 +3648,8 @@ userspace_tests()
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
 		set_userspace_pm $ns1
 		pm_nl_set_limits $ns2 1 1
-		speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 		wait_mpj $ns1
 		userspace_pm_add_addr $ns1 10.0.2.1 10
@@ -3679,8 +3679,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns1 2 2
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
-		speed=slow \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 
 		wait_mpj $ns1
@@ -3706,8 +3706,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 0 3
 		pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
-		test_linkfail=4 speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ test_linkfail=4 speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 
 		wait_mpj $ns2
@@ -3783,8 +3783,8 @@ endpoint_tests()
 		# broadcast IP: no packet for this address will be received on ns1
 		pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
 		pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal
-		test_linkfail=4 speed=5 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ test_linkfail=4 speed=5 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 
 		wait_mpj $ns2
@@ -3856,8 +3856,8 @@ endpoint_tests()
 		# broadcast IP: no packet for this address will be received on ns1
 		pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
 		pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
-		test_linkfail=4 speed=20 \
-			run_tests $ns1 $ns2 10.0.1.1 &
+		{ test_linkfail=4 speed=20 \
+			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
 		local tests_pid=$!
 
 		wait_attempt_fail $ns2
-- 
cgit v1.3-3-g829e


From 0e2b4584d61abe8dc22db18e83c85429782793ee Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Mon, 2 Sep 2024 12:46:01 +0200
Subject: selftests: mptcp: join: simplify checksum_tests

The four checksum tests are similar, only one line is different. So
a for-loop can be used to simplify these tests.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-10-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 43 +++++++------------------
 1 file changed, 11 insertions(+), 32 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 5d164abc18e5..43f8a9bd84c4 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -363,7 +363,7 @@ reset_with_checksum()
 	local ns1_enable=$1
 	local ns2_enable=$2
 
-	reset "checksum test ${1} ${2}" || return 1
+	reset "checksum test ${ns1_enable} ${ns2_enable}" || return 1
 
 	ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable
 	ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable
@@ -3032,37 +3032,16 @@ syncookies_tests()
 
 checksum_tests()
 {
-	# checksum test 0 0
-	if reset_with_checksum 0 0; then
-		pm_nl_set_limits $ns1 0 1
-		pm_nl_set_limits $ns2 0 1
-		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
-	fi
-
-	# checksum test 1 1
-	if reset_with_checksum 1 1; then
-		pm_nl_set_limits $ns1 0 1
-		pm_nl_set_limits $ns2 0 1
-		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
-	fi
-
-	# checksum test 0 1
-	if reset_with_checksum 0 1; then
-		pm_nl_set_limits $ns1 0 1
-		pm_nl_set_limits $ns2 0 1
-		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
-	fi
-
-	# checksum test 1 0
-	if reset_with_checksum 1 0; then
-		pm_nl_set_limits $ns1 0 1
-		pm_nl_set_limits $ns2 0 1
-		run_tests $ns1 $ns2 10.0.1.1
-		chk_join_nr 0 0 0
-	fi
+	local checksum_enable
+	for checksum_enable in "0 0" "1 1" "0 1" "1 0"; do
+		# checksum test 0 0, 1 1, 0 1, 1 0
+		if reset_with_checksum ${checksum_enable}; then
+			pm_nl_set_limits $ns1 0 1
+			pm_nl_set_limits $ns2 0 1
+			run_tests $ns1 $ns2 10.0.1.1
+			chk_join_nr 0 0 0
+		fi
+	done
 }
 
 deny_join_id0_tests()
-- 
cgit v1.3-3-g829e


From 38dc0708bcc8d2ee9e0559a992fd6e91bf67e271 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 2 Sep 2024 12:46:02 +0200
Subject: selftests: mptcp: pm_nl_ctl: remove re-definition

'MPTCP_PM_NAME' is defined in 'linux/mptcp_pm.h', included in
'linux/mptcp.h', no need to re-define it.

'MPTCP_PM_EVENTS' is not defined in 'linux/mptcp.h', but
'MPTCP_PM_EV_GRP_NAME' is, with the same value. We can then use the
latter, and drop the other one.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240902-net-next-mptcp-mib-mpjtx-misc-v1-11-d3e0f3773b90@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 7ad5a59adff2..994a556f46c1 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -19,12 +19,6 @@
 
 #include "linux/mptcp.h"
 
-#ifndef MPTCP_PM_NAME
-#define MPTCP_PM_NAME		"mptcp_pm"
-#endif
-#ifndef MPTCP_PM_EVENTS
-#define MPTCP_PM_EVENTS		"mptcp_pm_events"
-#endif
 #ifndef IPPROTO_MPTCP
 #define IPPROTO_MPTCP 262
 #endif
@@ -116,7 +110,7 @@ static int capture_events(int fd, int event_group)
 
 	if (setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP,
 		       &event_group, sizeof(event_group)) < 0)
-		error(1, errno, "could not join the " MPTCP_PM_EVENTS " mcast group");
+		error(1, errno, "could not join the " MPTCP_PM_EV_GRP_NAME " mcast group");
 
 	do {
 		FD_ZERO(&rfds);
@@ -288,7 +282,7 @@ static int genl_parse_getfamily(struct nlmsghdr *nlh, int *pm_family,
 					if (grp->rta_type == CTRL_ATTR_MCAST_GRP_ID)
 						*events_mcast_grp = *(__u32 *)RTA_DATA(grp);
 					else if (grp->rta_type == CTRL_ATTR_MCAST_GRP_NAME &&
-						 !strcmp(RTA_DATA(grp), MPTCP_PM_EVENTS))
+						 !strcmp(RTA_DATA(grp), MPTCP_PM_EV_GRP_NAME))
 						got_events_grp = 1;
 
 					grp = RTA_NEXT(grp, grp_len);
-- 
cgit v1.3-3-g829e


From d2088ca85ebc38c3e8783442ba2c0f3e5100ac6d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 2 Sep 2024 23:41:06 +0200
Subject: netlink: specs: nftables: allow decode of default firewalld ruleset

This update allows listing default firewalld ruleset on Fedora 40 via
  tools/net/ynl/cli.py --spec \
     Documentation/netlink/specs/nftables.yaml --dump getrule

Default ruleset uses fib, reject and objref expressions which were
missing.

Other missing expressions can be added later.

Improve decoding while at it:
- add bitwise, ct and lookup attributes
- wire up the quota expression
- translate raw verdict codes to a human reable name, e.g.
  'code': 4294967293 becomes 'code': 'jump'.

v2: forgot fib addrtype in enum list (Donald Hunter)

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20240902214112.2549-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/nftables.yaml | 254 +++++++++++++++++++++++++++++-
 1 file changed, 250 insertions(+), 4 deletions(-)

diff --git a/Documentation/netlink/specs/nftables.yaml b/Documentation/netlink/specs/nftables.yaml
index dff2a18f3d90..4acf30cf8385 100644
--- a/Documentation/netlink/specs/nftables.yaml
+++ b/Documentation/netlink/specs/nftables.yaml
@@ -62,6 +62,13 @@ definitions:
       - sdif
       - sdifname
       - bri-broute
+  -
+    name: bitwise-ops
+    type: enum
+    entries:
+      - bool
+      - lshift
+      - rshift
   -
     name: cmp-ops
     type: enum
@@ -125,6 +132,99 @@ definitions:
       - object
       - concat
       - expr
+  -
+    name: lookup-flags
+    type: flags
+    entries:
+      - invert
+  -
+    name: ct-keys
+    type: enum
+    entries:
+      - state
+      - direction
+      - status
+      - mark
+      - secmark
+      - expiration
+      - helper
+      - l3protocol
+      - src
+      - dst
+      - protocol
+      - proto-src
+      - proto-dst
+      - labels
+      - pkts
+      - bytes
+      - avgpkt
+      - zone
+      - eventmask
+      - src-ip
+      - dst-ip
+      - src-ip6
+      - dst-ip6
+      - ct-id
+  -
+    name: ct-direction
+    type: enum
+    entries:
+      - original
+      - reply
+  -
+    name: quota-flags
+    type: flags
+    entries:
+      - invert
+      - depleted
+  -
+    name: verdict-code
+    type: enum
+    entries:
+      - name: continue
+        value: 0xffffffff
+      - name: break
+        value: 0xfffffffe
+      - name: jump
+        value: 0xfffffffd
+      - name: goto
+        value: 0xfffffffc
+      - name: return
+        value: 0xfffffffb
+      - name: drop
+        value: 0
+      - name: accept
+        value: 1
+      - name: stolen
+        value: 2
+      - name: queue
+        value: 3
+      - name: repeat
+        value: 4
+  -
+    name: fib-result
+    type: enum
+    entries:
+      - oif
+      - oifname
+      - addrtype
+  -
+    name: fib-flags
+    type: flags
+    entries:
+      - saddr
+      - daddr
+      - mark
+      - iif
+      - oif
+      - present
+  -
+    name: reject-types
+    type: enum
+    entries:
+      - icmp-unreach
+      - tcp-rst
+      - icmpx-unreach
 
 attribute-sets:
   -
@@ -611,9 +711,10 @@ attribute-sets:
         type: u64
         byte-order: big-endian
       -
-        name: flags # TODO
+        name: flags
         type: u32
         byte-order: big-endian
+        enum: quota-flags
       -
         name: pad
         type: pad
@@ -664,6 +765,38 @@ attribute-sets:
         name: devs
         type: nest
         nested-attributes: hook-dev-attrs
+  -
+    name: expr-bitwise-attrs
+    attributes:
+      -
+        name: sreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: dreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: len
+        type: u32
+        byte-order: big-endian
+      -
+        name: mask
+        type: nest
+        nested-attributes: data-attrs
+      -
+        name: xor
+        type: nest
+        nested-attributes: data-attrs
+      -
+        name: op
+        type: u32
+        byte-order: big-endian
+        enum: bitwise-ops
+      -
+        name: data
+        type: nest
+        nested-attributes: data-attrs
   -
     name: expr-cmp-attrs
     attributes:
@@ -698,6 +831,7 @@ attribute-sets:
         name: code
         type: u32
         byte-order: big-endian
+        enum: verdict-code
       -
         name: chain
         type: string
@@ -718,6 +852,43 @@ attribute-sets:
       -
         name: pad
         type: pad
+  -
+    name: expr-fib-attrs
+    attributes:
+      -
+        name: dreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: result
+        type: u32
+        byte-order: big-endian
+        enum: fib-result
+      -
+        name: flags
+        type: u32
+        byte-order: big-endian
+        enum: fib-flags
+  -
+    name: expr-ct-attrs
+    attributes:
+      -
+        name: dreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: key
+        type: u32
+        byte-order: big-endian
+        enum: ct-keys
+      -
+        name: direction
+        type: u8
+        enum: ct-direction
+      -
+        name: sreg
+        type: u32
+        byte-order: big-endian
   -
     name: expr-flow-offload-attrs
     attributes:
@@ -736,6 +907,31 @@ attribute-sets:
         name: data
         type: nest
         nested-attributes: data-attrs
+  -
+    name: expr-lookup-attrs
+    attributes:
+      -
+        name: set
+        type: string
+        doc: Name of set to use
+      -
+        name: set id
+        type: u32
+        byte-order: big-endian
+        doc: ID of set to use
+      -
+        name: sreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: dreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: flags
+        type: u32
+        byte-order: big-endian
+        enum: lookup-flags
   -
     name: expr-meta-attrs
     attributes:
@@ -820,6 +1016,17 @@ attribute-sets:
         name: csum-flags
         type: u32
         byte-order: big-endian
+  -
+    name: expr-reject-attrs
+    attributes:
+      -
+        name: type
+        type: u32
+        byte-order: big-endian
+        enum: reject-types
+      -
+        name: icmp-code
+        type: u8
   -
     name: expr-tproxy-attrs
     attributes:
@@ -835,13 +1042,38 @@ attribute-sets:
         name: reg-port
         type: u32
         byte-order: big-endian
+  -
+    name: expr-objref-attrs
+    attributes:
+      -
+        name: imm-type
+        type: u32
+        byte-order: big-endian
+      -
+        name: imm-name
+        type: string
+        doc: object name
+      -
+        name: set-sreg
+        type: u32
+        byte-order: big-endian
+      -
+        name: set-name
+        type: string
+        doc: name of object map
+      -
+        name: set-id
+        type: u32
+        byte-order: big-endian
+        doc: id of object map
 
 sub-messages:
   -
     name: expr-ops
     formats:
       -
-        value: bitwise # TODO
+        value: bitwise
+        attribute-set: expr-bitwise-attrs
       -
         value: cmp
         attribute-set: expr-cmp-attrs
@@ -849,7 +1081,11 @@ sub-messages:
         value: counter
         attribute-set: expr-counter-attrs
       -
-        value: ct # TODO
+        value: ct
+        attribute-set: expr-ct-attrs
+      -
+        value: fib
+        attribute-set: expr-fib-attrs
       -
         value: flow_offload
         attribute-set: expr-flow-offload-attrs
@@ -857,16 +1093,26 @@ sub-messages:
         value: immediate
         attribute-set: expr-immediate-attrs
       -
-        value: lookup # TODO
+        value: lookup
+        attribute-set: expr-lookup-attrs
       -
         value: meta
         attribute-set: expr-meta-attrs
       -
         value: nat
         attribute-set: expr-nat-attrs
+      -
+        value: objref
+        attribute-set: expr-objref-attrs
       -
         value: payload
         attribute-set: expr-payload-attrs
+      -
+        value: quota
+        attribute-set: quota-attrs
+      -
+        value: reject
+        attribute-set: expr-reject-attrs
       -
         value: tproxy
         attribute-set: expr-tproxy-attrs
-- 
cgit v1.3-3-g829e


From 9748229c90dc4974f56874a2a19e040cc86de67e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Mon, 2 Sep 2024 18:36:10 +0200
Subject: net: alacritech: Partially revert "net: alacritech: Switch to use
 dev_err_probe()"

This reverts commit bf4d87f884fe8a4b6b61fe4d0e05f293d08df61c because it
introduced dev_err_probe() in non-probe path, which is not desired.

In general, calling dev_err_probe() after successful probe in case of
handling -EPROBE_DEFER error, will set deferred status on the device
already probed.  This is however not a problem here now, because
dev_err_probe() in affected places is used for handling errors from
request_firmware(), which does not return -EPROBE_DEFER.  Still usage of
dev_err_probe() in such case is not correct, because request_firmware()
could once return -EPROBE_DEFER.

Fixes: bf4d87f884fe ("net: alacritech: Switch to use dev_err_probe()")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240902163610.17028-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/alacritech/slicoss.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 7f0c07c20be3..f62851708d4f 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -1051,9 +1051,11 @@ static int slic_load_rcvseq_firmware(struct slic_device *sdev)
 	file = (sdev->model == SLIC_MODEL_OASIS) ?  SLIC_RCV_FIRMWARE_OASIS :
 						    SLIC_RCV_FIRMWARE_MOJAVE;
 	err = request_firmware(&fw, file, &sdev->pdev->dev);
-	if (err)
-		return dev_err_probe(&sdev->pdev->dev, err,
+	if (err) {
+		dev_err(&sdev->pdev->dev,
 			"failed to load receive sequencer firmware %s\n", file);
+		return err;
+	}
 	/* Do an initial sanity check concerning firmware size now. A further
 	 * check follows below.
 	 */
@@ -1124,9 +1126,10 @@ static int slic_load_firmware(struct slic_device *sdev)
 	file = (sdev->model == SLIC_MODEL_OASIS) ?  SLIC_FIRMWARE_OASIS :
 						    SLIC_FIRMWARE_MOJAVE;
 	err = request_firmware(&fw, file, &sdev->pdev->dev);
-	if (err)
-		return dev_err_probe(&sdev->pdev->dev, err,
-				"failed to load firmware %s\n", file);
+	if (err) {
+		dev_err(&sdev->pdev->dev, "failed to load firmware %s\n", file);
+		return err;
+	}
 	/* Do an initial sanity check concerning firmware size now. A further
 	 * check follows below.
 	 */
-- 
cgit v1.3-3-g829e


From 6c76474fc1ceac25ee26b563954e48b6bb94fe77 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 2 Sep 2024 19:29:04 +0800
Subject: qlcnic: Remove unused declarations

There is no caller and implementation in tree.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240902112904.556577-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic.h         |  1 -
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h | 10 ----------
 2 files changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index b25102fded7b..3d0b5cd978cb 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1608,7 +1608,6 @@ void qlcnic_release_tx_buffers(struct qlcnic_adapter *,
 			       struct qlcnic_host_tx_ring *);
 
 int qlcnic_check_fw_status(struct qlcnic_adapter *adapter);
-void qlcnic_watchdog_task(struct work_struct *work);
 void qlcnic_post_rx_buffers(struct qlcnic_adapter *adapter,
 		struct qlcnic_host_rds_ring *rds_ring, u8 ring_id);
 void qlcnic_set_multi(struct net_device *netdev);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index 23cd47d588e5..a55fe6ac06c7 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -539,7 +539,6 @@ int qlcnic_83xx_setup_intr(struct qlcnic_adapter *);
 void qlcnic_83xx_get_func_no(struct qlcnic_adapter *);
 int qlcnic_83xx_cam_lock(struct qlcnic_adapter *);
 void qlcnic_83xx_cam_unlock(struct qlcnic_adapter *);
-int qlcnic_send_ctrl_op(struct qlcnic_adapter *, struct qlcnic_cmd_args *, u32);
 void qlcnic_83xx_add_sysfs(struct qlcnic_adapter *);
 void qlcnic_83xx_remove_sysfs(struct qlcnic_adapter *);
 void qlcnic_83xx_write_crb(struct qlcnic_adapter *, char *, loff_t, size_t);
@@ -577,8 +576,6 @@ int qlcnic_83xx_get_mac_address(struct qlcnic_adapter *, u8 *, u8);
 int qlcnic_83xx_alloc_mbx_args(struct qlcnic_cmd_args *,
 			       struct qlcnic_adapter *, u32);
 void qlcnic_free_mbx_args(struct qlcnic_cmd_args *);
-void qlcnic_set_npar_data(struct qlcnic_adapter *, const struct qlcnic_info *,
-			  struct qlcnic_info *);
 int qlcnic_83xx_config_intr_coal(struct qlcnic_adapter *,
 				 struct ethtool_coalesce *);
 int qlcnic_83xx_set_rx_tx_intr_coal(struct qlcnic_adapter *);
@@ -590,7 +587,6 @@ irqreturn_t qlcnic_83xx_intr(int, void *);
 irqreturn_t qlcnic_83xx_tmp_intr(int, void *);
 void qlcnic_83xx_check_vf(struct qlcnic_adapter *,
 			  const struct pci_device_id *);
-int qlcnic_83xx_config_default_opmode(struct qlcnic_adapter *);
 int qlcnic_83xx_setup_mbx_intr(struct qlcnic_adapter *);
 void qlcnic_83xx_free_mbx_intr(struct qlcnic_adapter *);
 void qlcnic_83xx_register_map(struct qlcnic_hardware_context *);
@@ -602,8 +598,6 @@ int qlcnic_83xx_flash_bulk_write(struct qlcnic_adapter *, u32, u32 *, int);
 int qlcnic_83xx_flash_write32(struct qlcnic_adapter *, u32, u32 *);
 int qlcnic_83xx_lock_flash(struct qlcnic_adapter *);
 void qlcnic_83xx_unlock_flash(struct qlcnic_adapter *);
-int qlcnic_83xx_save_flash_status(struct qlcnic_adapter *);
-int qlcnic_83xx_restore_flash_status(struct qlcnic_adapter *, int);
 int qlcnic_83xx_read_flash_mfg_id(struct qlcnic_adapter *);
 int qlcnic_83xx_read_flash_descriptor_table(struct qlcnic_adapter *);
 int qlcnic_83xx_flash_read32(struct qlcnic_adapter *, u32, u8 *, int);
@@ -616,13 +610,9 @@ void qlcnic_83xx_idc_exit(struct qlcnic_adapter *);
 void qlcnic_83xx_idc_request_reset(struct qlcnic_adapter *, u32);
 int qlcnic_83xx_lock_driver(struct qlcnic_adapter *);
 void qlcnic_83xx_unlock_driver(struct qlcnic_adapter *);
-int qlcnic_83xx_set_default_offload_settings(struct qlcnic_adapter *);
 int qlcnic_83xx_idc_vnic_pf_entry(struct qlcnic_adapter *);
 int qlcnic_83xx_disable_vnic_mode(struct qlcnic_adapter *, int);
 int qlcnic_83xx_config_vnic_opmode(struct qlcnic_adapter *);
-int qlcnic_83xx_get_vnic_vport_info(struct qlcnic_adapter *,
-				    struct qlcnic_info *, u8);
-int qlcnic_83xx_get_vnic_pf_info(struct qlcnic_adapter *, struct qlcnic_info *);
 int qlcnic_83xx_set_port_eswitch_status(struct qlcnic_adapter *, int, int *);
 
 void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *);
-- 
cgit v1.3-3-g829e


From 3d4d0fa4fc32f03f615bbf0ac384de06ce0005f5 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 2 Sep 2024 19:32:38 +0800
Subject: be2net: Remove unused declarations

Commit 6b7c5b947c67 ("net: Add be2net driver.") declared be_pci_fnum_get()
and be_cmd_reset() but never implemented. And commit 9fa465c0ce0d ("be2net:
remove code duplication relating to Lancer reset sequence") removed
lancer_test_and_set_rdy_state() but leave declaration.

Commit 76a9e08e33ce ("be2net: cleanup wake-on-lan code") left behind
be_is_wol_supported() declaration.
Commit baaa08d148ac ("be2net: do not call be_set/get_fw_log_level() on
Skyhawk-R") removed be_get_fw_log_level() but leave declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240902113238.557515-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/emulex/benet/be.h      | 2 --
 drivers/net/ethernet/emulex/benet/be_cmds.h | 3 ---
 2 files changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 61fe9625bed1..e48b861e4ce1 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -966,9 +966,7 @@ void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm,
 void be_link_status_update(struct be_adapter *adapter, u8 link_status);
 void be_parse_stats(struct be_adapter *adapter);
 int be_load_fw(struct be_adapter *adapter, u8 *func);
-bool be_is_wol_supported(struct be_adapter *adapter);
 bool be_pause_supported(struct be_adapter *adapter);
-u32 be_get_fw_log_level(struct be_adapter *adapter);
 int be_update_queues(struct be_adapter *adapter);
 int be_poll(struct napi_struct *napi, int budget);
 void be_eqd_update(struct be_adapter *adapter, bool force_update);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index e2085c68c0ee..d70818f06be7 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -2381,7 +2381,6 @@ struct be_cmd_req_manage_iface_filters {
 } __packed;
 
 u16 be_POST_stage_get(struct be_adapter *adapter);
-int be_pci_fnum_get(struct be_adapter *adapter);
 int be_fw_wait_ready(struct be_adapter *adapter);
 int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 			  bool permanent, u32 if_handle, u32 pmac_id);
@@ -2406,7 +2405,6 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q);
 int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 			     u8 *link_status, u32 dom);
-int be_cmd_reset(struct be_adapter *adapter);
 int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd);
 int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 			       struct be_dma_mem *nonemb_cmd);
@@ -2488,7 +2486,6 @@ int lancer_physdev_ctrl(struct be_adapter *adapter, u32 mask);
 int lancer_initiate_dump(struct be_adapter *adapter);
 int lancer_delete_dump(struct be_adapter *adapter);
 bool dump_present(struct be_adapter *adapter);
-int lancer_test_and_set_rdy_state(struct be_adapter *adapter);
 int be_cmd_query_port_name(struct be_adapter *adapter);
 int be_cmd_get_func_config(struct be_adapter *adapter,
 			   struct be_resources *res);
-- 
cgit v1.3-3-g829e


From 8b2f4d01f56c99491f6f107f7a03fedcfb9d2d52 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 13 Jul 2020 15:43:27 +0800
Subject: dt-bindings: can: rockchip_canfd: add rockchip CAN-FD controller

Add documentation for the rockchip rk3568 CAN-FD controller.

Co-developed-by: Elaine Zhang <zhangqing@rock-chips.com>
Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-1-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../bindings/net/can/rockchip,rk3568v2-canfd.yaml  | 74 ++++++++++++++++++++++
 MAINTAINERS                                        |  7 ++
 2 files changed, 81 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/can/rockchip,rk3568v2-canfd.yaml

diff --git a/Documentation/devicetree/bindings/net/can/rockchip,rk3568v2-canfd.yaml b/Documentation/devicetree/bindings/net/can/rockchip,rk3568v2-canfd.yaml
new file mode 100644
index 000000000000..a077c0330013
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/rockchip,rk3568v2-canfd.yaml
@@ -0,0 +1,74 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/can/rockchip,rk3568v2-canfd.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title:
+  Rockchip CAN-FD controller
+
+maintainers:
+  - Marc Kleine-Budde <mkl@pengutronix.de>
+
+allOf:
+  - $ref: can-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: rockchip,rk3568v2-canfd
+      - items:
+          - const: rockchip,rk3568v3-canfd
+          - const: rockchip,rk3568v2-canfd
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: baud
+      - const: pclk
+
+  resets:
+    maxItems: 2
+
+  reset-names:
+    items:
+      - const: core
+      - const: apb
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/rk3568-cru.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        can@fe570000 {
+            compatible = "rockchip,rk3568v2-canfd";
+            reg = <0x0 0xfe570000 0x0 0x1000>;
+            interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>;
+            clocks = <&cru CLK_CAN0>, <&cru PCLK_CAN0>;
+            clock-names = "baud", "pclk";
+            resets = <&cru SRST_CAN0>, <&cru SRST_P_CAN0>;
+            reset-names = "core", "apb";
+        };
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index baf88e74c907..aa0e023955cf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19730,6 +19730,13 @@ F:	Documentation/ABI/*/sysfs-driver-hid-roccat*
 F:	drivers/hid/hid-roccat*
 F:	include/linux/hid-roccat*
 
+ROCKCHIP CAN-FD DRIVER
+M:	Marc Kleine-Budde <mkl@pengutronix.de>
+R:	kernel@pengutronix.de
+L:	linux-can@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/can/rockchip,rk3568v2-canfd.yaml
+
 ROCKCHIP CRYPTO DRIVERS
 M:	Corentin Labbe <clabbe@baylibre.com>
 L:	linux-crypto@vger.kernel.org
-- 
cgit v1.3-3-g829e


From 30e48a75df9c6ead93866bdf1511ca6ecfe17fbe Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:06 +0200
Subject: net: microchip: add FDMA library
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new FDMA library for interacting with the FDMA engine on Microchip
Sparx5 and lan966x switch chips, in an effort to reduce duplicate code
and provide a common set of symbols and functions.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/Kconfig         |   1 +
 drivers/net/ethernet/microchip/Makefile        |   1 +
 drivers/net/ethernet/microchip/fdma/Kconfig    |  18 ++
 drivers/net/ethernet/microchip/fdma/Makefile   |   7 +
 drivers/net/ethernet/microchip/fdma/fdma_api.c | 146 +++++++++++++++
 drivers/net/ethernet/microchip/fdma/fdma_api.h | 243 +++++++++++++++++++++++++
 drivers/net/ethernet/microchip/sparx5/Kconfig  |   1 +
 7 files changed, 417 insertions(+)
 create mode 100644 drivers/net/ethernet/microchip/fdma/Kconfig
 create mode 100644 drivers/net/ethernet/microchip/fdma/Makefile
 create mode 100644 drivers/net/ethernet/microchip/fdma/fdma_api.c
 create mode 100644 drivers/net/ethernet/microchip/fdma/fdma_api.h

diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index 43ba71e82260..ce2435987fb6 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -59,5 +59,6 @@ config LAN743X
 source "drivers/net/ethernet/microchip/lan966x/Kconfig"
 source "drivers/net/ethernet/microchip/sparx5/Kconfig"
 source "drivers/net/ethernet/microchip/vcap/Kconfig"
+source "drivers/net/ethernet/microchip/fdma/Kconfig"
 
 endif # NET_VENDOR_MICROCHIP
diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index bbd349264e6f..94045537b643 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -12,3 +12,4 @@ lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o
 obj-$(CONFIG_LAN966X_SWITCH) += lan966x/
 obj-$(CONFIG_SPARX5_SWITCH) += sparx5/
 obj-$(CONFIG_VCAP) += vcap/
+obj-$(CONFIG_FDMA) += fdma/
diff --git a/drivers/net/ethernet/microchip/fdma/Kconfig b/drivers/net/ethernet/microchip/fdma/Kconfig
new file mode 100644
index 000000000000..59159ad6701a
--- /dev/null
+++ b/drivers/net/ethernet/microchip/fdma/Kconfig
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Microchip FDMA API configuration
+#
+
+if NET_VENDOR_MICROCHIP
+
+config FDMA
+	bool "FDMA API"
+	help
+	  Provides the basic FDMA functionality for multiple Microchip
+	  switchcores.
+
+	  Say Y here if you want to build the FDMA API that provides a common
+	  set of functions and data structures for interacting with the Frame
+	  DMA engine in multiple microchip switchcores.
+
+endif # NET_VENDOR_MICROCHIP
diff --git a/drivers/net/ethernet/microchip/fdma/Makefile b/drivers/net/ethernet/microchip/fdma/Makefile
new file mode 100644
index 000000000000..cc9a736be357
--- /dev/null
+++ b/drivers/net/ethernet/microchip/fdma/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for Microchip FDMA
+#
+
+obj-$(CONFIG_FDMA) += fdma.o
+fdma-y += fdma_api.o
diff --git a/drivers/net/ethernet/microchip/fdma/fdma_api.c b/drivers/net/ethernet/microchip/fdma/fdma_api.c
new file mode 100644
index 000000000000..e78c3590da9e
--- /dev/null
+++ b/drivers/net/ethernet/microchip/fdma/fdma_api.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include "fdma_api.h"
+
+#include <linux/bits.h>
+#include <linux/etherdevice.h>
+#include <linux/types.h>
+
+/* Add a DB to a DCB, providing a callback for getting the DB dataptr. */
+static int __fdma_db_add(struct fdma *fdma, int dcb_idx, int db_idx, u64 status,
+			 int (*cb)(struct fdma *fdma, int dcb_idx,
+				   int db_idx, u64 *dataptr))
+{
+	struct fdma_db *db = fdma_db_get(fdma, dcb_idx, db_idx);
+
+	db->status = status;
+
+	return cb(fdma, dcb_idx, db_idx, &db->dataptr);
+}
+
+/* Add a DB to a DCB, using the callback set in the fdma_ops struct. */
+int fdma_db_add(struct fdma *fdma, int dcb_idx, int db_idx, u64 status)
+{
+	return __fdma_db_add(fdma,
+			     dcb_idx,
+			     db_idx,
+			     status,
+			     fdma->ops.dataptr_cb);
+}
+
+/* Add a DCB with callbacks for getting the DB dataptr and the DCB nextptr. */
+int __fdma_dcb_add(struct fdma *fdma, int dcb_idx, u64 info, u64 status,
+		   int (*dcb_cb)(struct fdma *fdma, int dcb_idx, u64 *nextptr),
+		   int (*db_cb)(struct fdma *fdma, int dcb_idx, int db_idx,
+				u64 *dataptr))
+{
+	struct fdma_dcb *dcb = fdma_dcb_get(fdma, dcb_idx);
+	int i, err;
+
+	for (i = 0; i < fdma->n_dbs; i++) {
+		err = __fdma_db_add(fdma, dcb_idx, i, status, db_cb);
+		if (unlikely(err))
+			return err;
+	}
+
+	err = dcb_cb(fdma, dcb_idx, &fdma->last_dcb->nextptr);
+	if (unlikely(err))
+		return err;
+
+	fdma->last_dcb = dcb;
+
+	dcb->nextptr = FDMA_DCB_INVALID_DATA;
+	dcb->info = info;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__fdma_dcb_add);
+
+/* Add a DCB, using the preset callbacks in the fdma_ops struct. */
+int fdma_dcb_add(struct fdma *fdma, int dcb_idx, u64 info, u64 status)
+{
+	return __fdma_dcb_add(fdma,
+			      dcb_idx,
+			      info, status,
+			      fdma->ops.nextptr_cb,
+			      fdma->ops.dataptr_cb);
+}
+EXPORT_SYMBOL_GPL(fdma_dcb_add);
+
+/* Initialize the DCB's and DB's. */
+int fdma_dcbs_init(struct fdma *fdma, u64 info, u64 status)
+{
+	int i, err;
+
+	fdma->last_dcb = fdma->dcbs;
+	fdma->db_index = 0;
+	fdma->dcb_index = 0;
+
+	for (i = 0; i < fdma->n_dcbs; i++) {
+		err = fdma_dcb_add(fdma, i, info, status);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fdma_dcbs_init);
+
+/* Allocate coherent DMA memory for FDMA. */
+int fdma_alloc_coherent(struct device *dev, struct fdma *fdma)
+{
+	fdma->dcbs = dma_alloc_coherent(dev,
+					fdma->size,
+					&fdma->dma,
+					GFP_KERNEL);
+	if (!fdma->dcbs)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fdma_alloc_coherent);
+
+/* Allocate physical memory for FDMA. */
+int fdma_alloc_phys(struct fdma *fdma)
+{
+	fdma->dcbs = kzalloc(fdma->size, GFP_KERNEL);
+	if (!fdma->dcbs)
+		return -ENOMEM;
+
+	fdma->dma = virt_to_phys(fdma->dcbs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fdma_alloc_phys);
+
+/* Free coherent DMA memory. */
+void fdma_free_coherent(struct device *dev, struct fdma *fdma)
+{
+	dma_free_coherent(dev, fdma->size, fdma->dcbs, fdma->dma);
+}
+EXPORT_SYMBOL_GPL(fdma_free_coherent);
+
+/* Free virtual memory. */
+void fdma_free_phys(struct fdma *fdma)
+{
+	kfree(fdma->dcbs);
+}
+EXPORT_SYMBOL_GPL(fdma_free_phys);
+
+/* Get the size of the FDMA memory */
+u32 fdma_get_size(struct fdma *fdma)
+{
+	return ALIGN(sizeof(struct fdma_dcb) * fdma->n_dcbs, PAGE_SIZE);
+}
+EXPORT_SYMBOL_GPL(fdma_get_size);
+
+/* Get the size of the FDMA memory. This function is only applicable if the
+ * dataptr addresses and DCB's are in contiguous memory.
+ */
+u32 fdma_get_size_contiguous(struct fdma *fdma)
+{
+	return ALIGN(fdma->n_dcbs * sizeof(struct fdma_dcb) +
+		     fdma->n_dcbs * fdma->n_dbs * fdma->db_size,
+		     PAGE_SIZE);
+}
+EXPORT_SYMBOL_GPL(fdma_get_size_contiguous);
diff --git a/drivers/net/ethernet/microchip/fdma/fdma_api.h b/drivers/net/ethernet/microchip/fdma/fdma_api.h
new file mode 100644
index 000000000000..d91affe8bd98
--- /dev/null
+++ b/drivers/net/ethernet/microchip/fdma/fdma_api.h
@@ -0,0 +1,243 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _FDMA_API_H_
+#define _FDMA_API_H_
+
+#include <linux/bits.h>
+#include <linux/etherdevice.h>
+#include <linux/types.h>
+
+/* This provides a common set of functions and data structures for interacting
+ * with the Frame DMA engine on multiple Microchip switchcores.
+ *
+ * Frame DMA DCB format:
+ *
+ * +---------------------------+
+ * |         Next Ptr          |
+ * +---------------------------+
+ * |   Reserved  |    Info     |
+ * +---------------------------+
+ * |         Data0 Ptr         |
+ * +---------------------------+
+ * |   Reserved  |    Status0  |
+ * +---------------------------+
+ * |         Data1 Ptr         |
+ * +---------------------------+
+ * |   Reserved  |    Status1  |
+ * +---------------------------+
+ * |         Data2 Ptr         |
+ * +---------------------------+
+ * |   Reserved  |    Status2  |
+ * |-------------|-------------|
+ * |                           |
+ * |                           |
+ * |                           |
+ * |                           |
+ * |                           |
+ * |---------------------------|
+ * |         Data14 Ptr        |
+ * +-------------|-------------+
+ * |   Reserved  |    Status14 |
+ * +-------------|-------------+
+ *
+ * The data pointers points to the actual frame data to be received or sent. The
+ * addresses of the data pointers can, as of writing, be either a: DMA address,
+ * physical address or mapped address.
+ *
+ */
+
+#define FDMA_DCB_INFO_DATAL(x)		((x) & GENMASK(15, 0))
+#define FDMA_DCB_INFO_TOKEN		BIT(17)
+#define FDMA_DCB_INFO_INTR		BIT(18)
+#define FDMA_DCB_INFO_SW(x)		(((x) << 24) & GENMASK(31, 24))
+
+#define FDMA_DCB_STATUS_BLOCKL(x)	((x) & GENMASK(15, 0))
+#define FDMA_DCB_STATUS_SOF		BIT(16)
+#define FDMA_DCB_STATUS_EOF		BIT(17)
+#define FDMA_DCB_STATUS_INTR		BIT(18)
+#define FDMA_DCB_STATUS_DONE		BIT(19)
+#define FDMA_DCB_STATUS_BLOCKO(x)	(((x) << 20) & GENMASK(31, 20))
+#define FDMA_DCB_INVALID_DATA		0x1
+
+#define FDMA_DB_MAX			15 /* Max number of DB's on Sparx5 */
+
+struct fdma;
+
+struct fdma_db {
+	u64 dataptr;
+	u64 status;
+};
+
+struct fdma_dcb {
+	u64 nextptr;
+	u64 info;
+	struct fdma_db db[FDMA_DB_MAX];
+};
+
+struct fdma_ops {
+	/* User-provided callback to set the dataptr */
+	int (*dataptr_cb)(struct fdma *fdma, int dcb_idx, int db_idx, u64 *ptr);
+	/* User-provided callback to set the nextptr */
+	int (*nextptr_cb)(struct fdma *fdma, int dcb_idx, u64 *ptr);
+};
+
+struct fdma {
+	void *priv;
+
+	/* Virtual addresses */
+	struct fdma_dcb *dcbs;
+	struct fdma_dcb *last_dcb;
+
+	/* DMA address */
+	dma_addr_t dma;
+
+	/* Size of DCB + DB memory */
+	int size;
+
+	/* Indexes used to access the next-to-be-used DCB or DB */
+	int db_index;
+	int dcb_index;
+
+	/* Number of DCB's and DB's */
+	u32 n_dcbs;
+	u32 n_dbs;
+
+	/* Size of DB's */
+	u32 db_size;
+
+	/* Channel id this FDMA object operates on */
+	u32 channel_id;
+
+	struct fdma_ops ops;
+};
+
+/* Advance the DCB index and wrap if required. */
+static inline void fdma_dcb_advance(struct fdma *fdma)
+{
+	fdma->dcb_index++;
+	if (fdma->dcb_index >= fdma->n_dcbs)
+		fdma->dcb_index = 0;
+}
+
+/* Advance the DB index. */
+static inline void fdma_db_advance(struct fdma *fdma)
+{
+	fdma->db_index++;
+}
+
+/* Reset the db index to zero. */
+static inline void fdma_db_reset(struct fdma *fdma)
+{
+	fdma->db_index = 0;
+}
+
+/* Check if a DCB can be reused in case of multiple DB's per DCB. */
+static inline bool fdma_dcb_is_reusable(struct fdma *fdma)
+{
+	return fdma->db_index != fdma->n_dbs;
+}
+
+/* Check if the FDMA has marked this DB as done. */
+static inline bool fdma_db_is_done(struct fdma_db *db)
+{
+	return db->status & FDMA_DCB_STATUS_DONE;
+}
+
+/* Get the length of a DB. */
+static inline int fdma_db_len_get(struct fdma_db *db)
+{
+	return FDMA_DCB_STATUS_BLOCKL(db->status);
+}
+
+/* Set the length of a DB. */
+static inline void fdma_dcb_len_set(struct fdma_dcb *dcb, u32 len)
+{
+	dcb->info = FDMA_DCB_INFO_DATAL(len);
+}
+
+/* Get a DB by index. */
+static inline struct fdma_db *fdma_db_get(struct fdma *fdma, int dcb_idx,
+					  int db_idx)
+{
+	return &fdma->dcbs[dcb_idx].db[db_idx];
+}
+
+/* Get the next DB. */
+static inline struct fdma_db *fdma_db_next_get(struct fdma *fdma)
+{
+	return fdma_db_get(fdma, fdma->dcb_index, fdma->db_index);
+}
+
+/* Get a DCB by index. */
+static inline struct fdma_dcb *fdma_dcb_get(struct fdma *fdma, int dcb_idx)
+{
+	return &fdma->dcbs[dcb_idx];
+}
+
+/* Get the next DCB. */
+static inline struct fdma_dcb *fdma_dcb_next_get(struct fdma *fdma)
+{
+	return fdma_dcb_get(fdma, fdma->dcb_index);
+}
+
+/* Check if the FDMA has frames ready for extraction. */
+static inline bool fdma_has_frames(struct fdma *fdma)
+{
+	return fdma_db_is_done(fdma_db_next_get(fdma));
+}
+
+/* Get a nextptr by index */
+static inline int fdma_nextptr_cb(struct fdma *fdma, int dcb_idx, u64 *nextptr)
+{
+	*nextptr = fdma->dma + (sizeof(struct fdma_dcb) * dcb_idx);
+	return 0;
+}
+
+/* Get the DMA address of a dataptr, by index. This function is only applicable
+ * if the dataptr addresses and DCB's are in contiguous memory and the driver
+ * supports XDP.
+ */
+static inline u64 fdma_dataptr_get_contiguous(struct fdma *fdma, int dcb_idx,
+					      int db_idx)
+{
+	return fdma->dma + (sizeof(struct fdma_dcb) * fdma->n_dcbs) +
+	       (dcb_idx * fdma->n_dbs + db_idx) * fdma->db_size +
+	       XDP_PACKET_HEADROOM;
+}
+
+/* Get the virtual address of a dataptr, by index. This function is only
+ * applicable if the dataptr addresses and DCB's are in contiguous memory and
+ * the driver supports XDP.
+ */
+static inline void *fdma_dataptr_virt_get_contiguous(struct fdma *fdma,
+						     int dcb_idx, int db_idx)
+{
+	return (u8 *)fdma->dcbs + (sizeof(struct fdma_dcb) * fdma->n_dcbs) +
+	       (dcb_idx * fdma->n_dbs + db_idx) * fdma->db_size +
+	       XDP_PACKET_HEADROOM;
+}
+
+/* Check if this DCB is the last used DCB. */
+static inline bool fdma_is_last(struct fdma *fdma, struct fdma_dcb *dcb)
+{
+	return dcb == fdma->last_dcb;
+}
+
+int fdma_dcbs_init(struct fdma *fdma, u64 info, u64 status);
+int fdma_db_add(struct fdma *fdma, int dcb_idx, int db_idx, u64 status);
+int fdma_dcb_add(struct fdma *fdma, int dcb_idx, u64 info, u64 status);
+int __fdma_dcb_add(struct fdma *fdma, int dcb_idx, u64 info, u64 status,
+		   int (*dcb_cb)(struct fdma *fdma, int dcb_idx, u64 *nextptr),
+		   int (*db_cb)(struct fdma *fdma, int dcb_idx, int db_idx,
+				u64 *dataptr));
+
+int fdma_alloc_coherent(struct device *dev, struct fdma *fdma);
+int fdma_alloc_phys(struct fdma *fdma);
+
+void fdma_free_coherent(struct device *dev, struct fdma *fdma);
+void fdma_free_phys(struct fdma *fdma);
+
+u32 fdma_get_size(struct fdma *fdma);
+u32 fdma_get_size_contiguous(struct fdma *fdma);
+
+#endif
diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig
index f58c506bda22..3f04992eace6 100644
--- a/drivers/net/ethernet/microchip/sparx5/Kconfig
+++ b/drivers/net/ethernet/microchip/sparx5/Kconfig
@@ -10,6 +10,7 @@ config SPARX5_SWITCH
 	select PHY_SPARX5_SERDES
 	select RESET_CONTROLLER
 	select VCAP
+	select FDMA
 	help
 	  This driver supports the Sparx5 network switch device.
 
-- 
cgit v1.3-3-g829e


From 947a72f40f69fc0341cccf849e4e8a1e70fd4d3c Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:07 +0200
Subject: net: sparx5: use FDMA library symbols
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Include and use the new FDMA header, which now provides the required
masks and bit offsets for operating on the DCB's and DB's.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/Makefile     |  1 +
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 44 ----------------------
 .../net/ethernet/microchip/sparx5/sparx5_main.h    |  2 +
 3 files changed, 3 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile
index b68fe9c9a656..288de95add18 100644
--- a/drivers/net/ethernet/microchip/sparx5/Makefile
+++ b/drivers/net/ethernet/microchip/sparx5/Makefile
@@ -18,3 +18,4 @@ sparx5-switch-$(CONFIG_DEBUG_FS) += sparx5_vcap_debugfs.o
 
 # Provide include files
 ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap
+ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/fdma
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 1915998f6079..e7acf4ef291f 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -21,53 +21,9 @@
 #define FDMA_XTR_CHANNEL		6
 #define FDMA_INJ_CHANNEL		0
 
-#define FDMA_DCB_INFO_DATAL(x)		((x) & GENMASK(15, 0))
-#define FDMA_DCB_INFO_TOKEN		BIT(17)
-#define FDMA_DCB_INFO_INTR		BIT(18)
-#define FDMA_DCB_INFO_SW(x)		(((x) << 24) & GENMASK(31, 24))
-
-#define FDMA_DCB_STATUS_BLOCKL(x)	((x) & GENMASK(15, 0))
-#define FDMA_DCB_STATUS_SOF		BIT(16)
-#define FDMA_DCB_STATUS_EOF		BIT(17)
-#define FDMA_DCB_STATUS_INTR		BIT(18)
-#define FDMA_DCB_STATUS_DONE		BIT(19)
-#define FDMA_DCB_STATUS_BLOCKO(x)	(((x) << 20) & GENMASK(31, 20))
-#define FDMA_DCB_INVALID_DATA		0x1
-
 #define FDMA_XTR_BUFFER_SIZE		2048
 #define FDMA_WEIGHT			4
 
-/* Frame DMA DCB format
- *
- * +---------------------------+
- * |         Next Ptr          |
- * +---------------------------+
- * |   Reserved  |    Info     |
- * +---------------------------+
- * |         Data0 Ptr         |
- * +---------------------------+
- * |   Reserved  |    Status0  |
- * +---------------------------+
- * |         Data1 Ptr         |
- * +---------------------------+
- * |   Reserved  |    Status1  |
- * +---------------------------+
- * |         Data2 Ptr         |
- * +---------------------------+
- * |   Reserved  |    Status2  |
- * |-------------|-------------|
- * |                           |
- * |                           |
- * |                           |
- * |                           |
- * |                           |
- * |---------------------------|
- * |         Data14 Ptr        |
- * +-------------|-------------+
- * |   Reserved  |    Status14 |
- * +-------------|-------------+
- */
-
 /* For each hardware DB there is an entry in this list and when the HW DB
  * entry is used, this SW DB entry is moved to the back of the list
  */
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 1982ae03b4fe..f7ac47af58ce 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -20,6 +20,8 @@
 #include <linux/debugfs.h>
 #include <net/flow_offload.h>
 
+#include <fdma_api.h>
+
 #include "sparx5_main_regs.h"
 
 /* Target chip type */
-- 
cgit v1.3-3-g829e


From e8218f7a9f4425894048ad87f0064efd06fe19fc Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:08 +0200
Subject: net: sparx5: replace a few variables with new equivalent ones
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the old rx and tx variables: channel_id, FDMA_DCB_MAX,
FDMA_RX_DCB_MAX_DBS, FDMA_TX_DCB_MAX_DBS, dcb_index and db_index with
the equivalents from the FDMA rx and tx structs. These variables are not
entangled in any buffer allocation and can therefore be replaced in
advance.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 103 ++++++++++++---------
 .../net/ethernet/microchip/sparx5/sparx5_main.h    |   6 +-
 2 files changed, 63 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index e7acf4ef291f..5e058dbc734e 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -36,10 +36,11 @@ static void sparx5_fdma_rx_add_dcb(struct sparx5_rx *rx,
 				   struct sparx5_rx_dcb_hw *dcb,
 				   u64 nextptr)
 {
+	struct fdma *fdma = &rx->fdma;
 	int idx = 0;
 
 	/* Reset the status of the DB */
-	for (idx = 0; idx < FDMA_RX_DCB_MAX_DBS; ++idx) {
+	for (idx = 0; idx < fdma->n_dbs; ++idx) {
 		struct sparx5_db_hw *db = &dcb->db[idx];
 
 		db->status = FDMA_DCB_STATUS_INTR;
@@ -57,7 +58,7 @@ static void sparx5_fdma_tx_add_dcb(struct sparx5_tx *tx,
 	int idx = 0;
 
 	/* Reset the status of the DB */
-	for (idx = 0; idx < FDMA_TX_DCB_MAX_DBS; ++idx) {
+	for (idx = 0; idx < tx->fdma.n_dbs; ++idx) {
 		struct sparx5_db_hw *db = &dcb->db[idx];
 
 		db->status = FDMA_DCB_STATUS_DONE;
@@ -68,16 +69,18 @@ static void sparx5_fdma_tx_add_dcb(struct sparx5_tx *tx,
 
 static void sparx5_fdma_rx_activate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
+	struct fdma *fdma = &rx->fdma;
+
 	/* Write the buffer address in the LLP and LLP1 regs */
 	spx5_wr(((u64)rx->dma) & GENMASK(31, 0), sparx5,
-		FDMA_DCB_LLP(rx->channel_id));
-	spx5_wr(((u64)rx->dma) >> 32, sparx5, FDMA_DCB_LLP1(rx->channel_id));
+		FDMA_DCB_LLP(fdma->channel_id));
+	spx5_wr(((u64)rx->dma) >> 32, sparx5, FDMA_DCB_LLP1(fdma->channel_id));
 
 	/* Set the number of RX DBs to be used, and DB end-of-frame interrupt */
-	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(FDMA_RX_DCB_MAX_DBS) |
+	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
 		FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(1) |
 		FDMA_CH_CFG_CH_INJ_PORT_SET(XTR_QUEUE),
-		sparx5, FDMA_CH_CFG(rx->channel_id));
+		sparx5, FDMA_CH_CFG(fdma->channel_id));
 
 	/* Set the RX Watermark to max */
 	spx5_rmw(FDMA_XTR_CFG_XTR_FIFO_WM_SET(31), FDMA_XTR_CFG_XTR_FIFO_WM,
@@ -89,22 +92,24 @@ static void sparx5_fdma_rx_activate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 		 sparx5, FDMA_PORT_CTRL(0));
 
 	/* Enable RX channel DB interrupt */
-	spx5_rmw(BIT(rx->channel_id),
-		 BIT(rx->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
+	spx5_rmw(BIT(fdma->channel_id),
+		 BIT(fdma->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
 		 sparx5, FDMA_INTR_DB_ENA);
 
 	/* Activate the RX channel */
-	spx5_wr(BIT(rx->channel_id), sparx5, FDMA_CH_ACTIVATE);
+	spx5_wr(BIT(fdma->channel_id), sparx5, FDMA_CH_ACTIVATE);
 }
 
 static void sparx5_fdma_rx_deactivate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
+	struct fdma *fdma = &rx->fdma;
+
 	/* Deactivate the RX channel */
-	spx5_rmw(0, BIT(rx->channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
+	spx5_rmw(0, BIT(fdma->channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
 		 sparx5, FDMA_CH_ACTIVATE);
 
 	/* Disable RX channel DB interrupt */
-	spx5_rmw(0, BIT(rx->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
+	spx5_rmw(0, BIT(fdma->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
 		 sparx5, FDMA_INTR_DB_ENA);
 
 	/* Stop RX fdma */
@@ -114,42 +119,44 @@ static void sparx5_fdma_rx_deactivate(struct sparx5 *sparx5, struct sparx5_rx *r
 
 static void sparx5_fdma_tx_activate(struct sparx5 *sparx5, struct sparx5_tx *tx)
 {
+	struct fdma *fdma = &tx->fdma;
+
 	/* Write the buffer address in the LLP and LLP1 regs */
 	spx5_wr(((u64)tx->dma) & GENMASK(31, 0), sparx5,
-		FDMA_DCB_LLP(tx->channel_id));
-	spx5_wr(((u64)tx->dma) >> 32, sparx5, FDMA_DCB_LLP1(tx->channel_id));
+		FDMA_DCB_LLP(fdma->channel_id));
+	spx5_wr(((u64)tx->dma) >> 32, sparx5, FDMA_DCB_LLP1(fdma->channel_id));
 
 	/* Set the number of TX DBs to be used, and DB end-of-frame interrupt */
-	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(FDMA_TX_DCB_MAX_DBS) |
+	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
 		FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(1) |
 		FDMA_CH_CFG_CH_INJ_PORT_SET(INJ_QUEUE),
-		sparx5, FDMA_CH_CFG(tx->channel_id));
+		sparx5, FDMA_CH_CFG(fdma->channel_id));
 
 	/* Start TX fdma */
 	spx5_rmw(FDMA_PORT_CTRL_INJ_STOP_SET(0), FDMA_PORT_CTRL_INJ_STOP,
 		 sparx5, FDMA_PORT_CTRL(0));
 
 	/* Activate the channel */
-	spx5_wr(BIT(tx->channel_id), sparx5, FDMA_CH_ACTIVATE);
+	spx5_wr(BIT(fdma->channel_id), sparx5, FDMA_CH_ACTIVATE);
 }
 
 static void sparx5_fdma_tx_deactivate(struct sparx5 *sparx5, struct sparx5_tx *tx)
 {
 	/* Disable the channel */
-	spx5_rmw(0, BIT(tx->channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
+	spx5_rmw(0, BIT(tx->fdma.channel_id) & FDMA_CH_ACTIVATE_CH_ACTIVATE,
 		 sparx5, FDMA_CH_ACTIVATE);
 }
 
 static void sparx5_fdma_rx_reload(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
 	/* Reload the RX channel */
-	spx5_wr(BIT(rx->channel_id), sparx5, FDMA_CH_RELOAD);
+	spx5_wr(BIT(rx->fdma.channel_id), sparx5, FDMA_CH_RELOAD);
 }
 
 static void sparx5_fdma_tx_reload(struct sparx5 *sparx5, struct sparx5_tx *tx)
 {
 	/* Reload the TX channel */
-	spx5_wr(BIT(tx->channel_id), sparx5, FDMA_CH_RELOAD);
+	spx5_wr(BIT(tx->fdma.channel_id), sparx5, FDMA_CH_RELOAD);
 }
 
 static struct sk_buff *sparx5_fdma_rx_alloc_skb(struct sparx5_rx *rx)
@@ -160,6 +167,7 @@ static struct sk_buff *sparx5_fdma_rx_alloc_skb(struct sparx5_rx *rx)
 
 static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
+	struct fdma *fdma = &rx->fdma;
 	struct sparx5_db_hw *db_hw;
 	unsigned int packet_size;
 	struct sparx5_port *port;
@@ -169,17 +177,17 @@ static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx
 	dma_addr_t dma_addr;
 
 	/* Check if the DCB is done */
-	db_hw = &rx->dcb_entries[rx->dcb_index].db[rx->db_index];
+	db_hw = &rx->dcb_entries[fdma->dcb_index].db[fdma->db_index];
 	if (unlikely(!(db_hw->status & FDMA_DCB_STATUS_DONE)))
 		return false;
-	skb = rx->skb[rx->dcb_index][rx->db_index];
+	skb = rx->skb[fdma->dcb_index][fdma->db_index];
 	/* Replace the DB entry with a new SKB */
 	new_skb = sparx5_fdma_rx_alloc_skb(rx);
 	if (unlikely(!new_skb))
 		return false;
 	/* Map the new skb data and set the new skb */
 	dma_addr = virt_to_phys(new_skb->data);
-	rx->skb[rx->dcb_index][rx->db_index] = new_skb;
+	rx->skb[fdma->dcb_index][fdma->db_index] = new_skb;
 	db_hw->dataptr = dma_addr;
 	packet_size = FDMA_DCB_STATUS_BLOCKL(db_hw->status);
 	skb_put(skb, packet_size);
@@ -215,23 +223,24 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 {
 	struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi);
 	struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx);
+	struct fdma *fdma = &rx->fdma;
 	int counter = 0;
 
 	while (counter < weight && sparx5_fdma_rx_get_frame(sparx5, rx)) {
 		struct sparx5_rx_dcb_hw *old_dcb;
 
-		rx->db_index++;
+		fdma->db_index++;
 		counter++;
 		/* Check if the DCB can be reused */
-		if (rx->db_index != FDMA_RX_DCB_MAX_DBS)
+		if (fdma->db_index != fdma->n_dbs)
 			continue;
 		/* As the DCB  can be reused, just advance the dcb_index
 		 * pointer and set the nextptr in the DCB
 		 */
-		rx->db_index = 0;
-		old_dcb = &rx->dcb_entries[rx->dcb_index];
-		rx->dcb_index++;
-		rx->dcb_index &= FDMA_DCB_MAX - 1;
+		fdma->db_index = 0;
+		old_dcb = &rx->dcb_entries[fdma->dcb_index];
+		fdma->dcb_index++;
+		fdma->dcb_index &= fdma->n_dcbs - 1;
 		sparx5_fdma_rx_add_dcb(rx, old_dcb,
 				       rx->dma +
 				       ((unsigned long)old_dcb -
@@ -239,8 +248,8 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	}
 	if (counter < weight) {
 		napi_complete_done(&rx->napi, counter);
-		spx5_rmw(BIT(rx->channel_id),
-			 BIT(rx->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
+		spx5_rmw(BIT(fdma->channel_id),
+			 BIT(fdma->channel_id) & FDMA_INTR_DB_ENA_INTR_DB_ENA,
 			 sparx5, FDMA_INTR_DB_ENA);
 	}
 	if (counter)
@@ -252,12 +261,13 @@ static struct sparx5_tx_dcb_hw *sparx5_fdma_next_dcb(struct sparx5_tx *tx,
 						     struct sparx5_tx_dcb_hw *dcb)
 {
 	struct sparx5_tx_dcb_hw *next_dcb;
+	struct fdma *fdma = &tx->fdma;
 
 	next_dcb = dcb;
 	next_dcb++;
 	/* Handle wrap-around */
 	if ((unsigned long)next_dcb >=
-	    ((unsigned long)tx->first_entry + FDMA_DCB_MAX * sizeof(*dcb)))
+	    ((unsigned long)tx->first_entry + fdma->n_dcbs * sizeof(*dcb)))
 		next_dcb = tx->first_entry;
 	return next_dcb;
 }
@@ -300,28 +310,29 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
 static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5)
 {
 	struct sparx5_rx *rx = &sparx5->rx;
+	struct fdma *fdma = &rx->fdma;
 	struct sparx5_rx_dcb_hw *dcb;
 	int idx, jdx;
 	int size;
 
-	size = sizeof(struct sparx5_rx_dcb_hw) * FDMA_DCB_MAX;
+	size = sizeof(struct sparx5_rx_dcb_hw) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	rx->dcb_entries = devm_kzalloc(sparx5->dev, size, GFP_KERNEL);
 	if (!rx->dcb_entries)
 		return -ENOMEM;
 	rx->dma = virt_to_phys(rx->dcb_entries);
 	rx->last_entry = rx->dcb_entries;
-	rx->db_index = 0;
-	rx->dcb_index = 0;
+	fdma->db_index = 0;
+	fdma->dcb_index = 0;
 	/* Now for each dcb allocate the db */
-	for (idx = 0; idx < FDMA_DCB_MAX; ++idx) {
+	for (idx = 0; idx < fdma->n_dcbs; ++idx) {
 		dcb = &rx->dcb_entries[idx];
 		dcb->info = 0;
 		/* For each db allocate an skb and map skb data pointer to the DB
 		 * dataptr. In this way when the frame is received the skb->data
 		 * will contain the frame, so no memcpy is needed
 		 */
-		for (jdx = 0; jdx < FDMA_RX_DCB_MAX_DBS; ++jdx) {
+		for (jdx = 0; jdx < fdma->n_dbs; ++jdx) {
 			struct sparx5_db_hw *db_hw = &dcb->db[jdx];
 			dma_addr_t dma_addr;
 			struct sk_buff *skb;
@@ -348,10 +359,11 @@ static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 {
 	struct sparx5_tx *tx = &sparx5->tx;
 	struct sparx5_tx_dcb_hw *dcb;
+	struct fdma *fdma = &tx->fdma;
 	int idx, jdx;
 	int size;
 
-	size = sizeof(struct sparx5_tx_dcb_hw) * FDMA_DCB_MAX;
+	size = sizeof(struct sparx5_tx_dcb_hw) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	tx->curr_entry = devm_kzalloc(sparx5->dev, size, GFP_KERNEL);
 	if (!tx->curr_entry)
@@ -360,11 +372,11 @@ static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 	tx->first_entry = tx->curr_entry;
 	INIT_LIST_HEAD(&tx->db_list);
 	/* Now for each dcb allocate the db */
-	for (idx = 0; idx < FDMA_DCB_MAX; ++idx) {
+	for (idx = 0; idx < fdma->n_dcbs; ++idx) {
 		dcb = &tx->curr_entry[idx];
 		dcb->info = 0;
 		/* TX databuffers must be 16byte aligned */
-		for (jdx = 0; jdx < FDMA_TX_DCB_MAX_DBS; ++jdx) {
+		for (jdx = 0; jdx < fdma->n_dbs; ++jdx) {
 			struct sparx5_db_hw *db_hw = &dcb->db[jdx];
 			struct sparx5_db *db;
 			dma_addr_t phys;
@@ -386,7 +398,7 @@ static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 		}
 		sparx5_fdma_tx_add_dcb(tx, dcb, tx->dma + sizeof(*dcb) * idx);
 		/* Let the curr_entry to point to the last allocated entry */
-		if (idx == FDMA_DCB_MAX - 1)
+		if (idx == fdma->n_dcbs - 1)
 			tx->curr_entry = dcb;
 	}
 	return 0;
@@ -395,9 +407,12 @@ static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 static void sparx5_fdma_rx_init(struct sparx5 *sparx5,
 				struct sparx5_rx *rx, int channel)
 {
+	struct fdma *fdma = &rx->fdma;
 	int idx;
 
-	rx->channel_id = channel;
+	fdma->channel_id = channel;
+	fdma->n_dcbs = FDMA_DCB_MAX;
+	fdma->n_dbs = FDMA_RX_DCB_MAX_DBS;
 	/* Fetch a netdev for SKB and NAPI use, any will do */
 	for (idx = 0; idx < SPX5_PORTS; ++idx) {
 		struct sparx5_port *port = sparx5->ports[idx];
@@ -412,7 +427,11 @@ static void sparx5_fdma_rx_init(struct sparx5 *sparx5,
 static void sparx5_fdma_tx_init(struct sparx5 *sparx5,
 				struct sparx5_tx *tx, int channel)
 {
-	tx->channel_id = channel;
+	struct fdma *fdma = &tx->fdma;
+
+	fdma->channel_id = channel;
+	fdma->n_dcbs = FDMA_DCB_MAX;
+	fdma->n_dbs = FDMA_TX_DCB_MAX_DBS;
 }
 
 irqreturn_t sparx5_fdma_handler(int irq, void *args)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index f7ac47af58ce..542f57569c5f 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -126,14 +126,12 @@ struct sparx5_tx_dcb_hw {
  * When the db_index reached FDMA_RX_DCB_MAX_DBS the DB is reused.
  */
 struct sparx5_rx {
+	struct fdma fdma;
 	struct sparx5_rx_dcb_hw *dcb_entries;
 	struct sparx5_rx_dcb_hw *last_entry;
 	struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
-	int db_index;
-	int dcb_index;
 	dma_addr_t dma;
 	struct napi_struct napi;
-	u32 channel_id;
 	struct net_device *ndev;
 	u64 packets;
 };
@@ -142,11 +140,11 @@ struct sparx5_rx {
  * DCBs are chained using the DCBs nextptr field.
  */
 struct sparx5_tx {
+	struct fdma fdma;
 	struct sparx5_tx_dcb_hw *curr_entry;
 	struct sparx5_tx_dcb_hw *first_entry;
 	struct list_head db_list;
 	dma_addr_t dma;
-	u32 channel_id;
 	u64 packets;
 	u64 dropped;
 };
-- 
cgit v1.3-3-g829e


From 8fec1cea941d32b44bdaeded8ddb11dddcbf1412 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:09 +0200
Subject: net: sparx5: use the FDMA library for allocation of rx buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the two functions: fdma_alloc_phys() and fdma_dcb_init() for rx
buffer allocation and use the new buffers throughout.

In order to replace the old buffers with the new ones, we have to do the
following refactoring:

    - use fdma_alloc_phys() and fdma_dcb_init()

    - replace the variables: rx->dma, rx->dcb_entries and rx->last_entry
      with the equivalents from the FDMA struct.

    - replace uses of sparx5_db_hw and sparx5_rx_dcb_hw with fdma_db and
      fdma_dcb.

    - add sparx5_fdma_rx_dataptr_cb callback for obtaining the dataptr.

    - Initialize FDMA struct values.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 89 +++++++++++-----------
 .../net/ethernet/microchip/sparx5/sparx5_main.h    |  8 --
 2 files changed, 43 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 5e058dbc734e..675f8d5faa74 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -32,8 +32,26 @@ struct sparx5_db {
 	void *cpu_addr;
 };
 
+static int sparx5_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+				     u64 *dataptr)
+{
+	struct sparx5 *sparx5 = fdma->priv;
+	struct sparx5_rx *rx = &sparx5->rx;
+	struct sk_buff *skb;
+
+	skb = __netdev_alloc_skb(rx->ndev, fdma->db_size, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	*dataptr = virt_to_phys(skb->data);
+
+	rx->skb[dcb][db] = skb;
+
+	return 0;
+}
+
 static void sparx5_fdma_rx_add_dcb(struct sparx5_rx *rx,
-				   struct sparx5_rx_dcb_hw *dcb,
+				   struct fdma_dcb *dcb,
 				   u64 nextptr)
 {
 	struct fdma *fdma = &rx->fdma;
@@ -41,14 +59,15 @@ static void sparx5_fdma_rx_add_dcb(struct sparx5_rx *rx,
 
 	/* Reset the status of the DB */
 	for (idx = 0; idx < fdma->n_dbs; ++idx) {
-		struct sparx5_db_hw *db = &dcb->db[idx];
+		struct fdma_db *db = &dcb->db[idx];
 
 		db->status = FDMA_DCB_STATUS_INTR;
 	}
 	dcb->nextptr = FDMA_DCB_INVALID_DATA;
 	dcb->info = FDMA_DCB_INFO_DATAL(FDMA_XTR_BUFFER_SIZE);
-	rx->last_entry->nextptr = nextptr;
-	rx->last_entry = dcb;
+
+	fdma->last_dcb->nextptr = nextptr;
+	fdma->last_dcb = dcb;
 }
 
 static void sparx5_fdma_tx_add_dcb(struct sparx5_tx *tx,
@@ -72,9 +91,10 @@ static void sparx5_fdma_rx_activate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 	struct fdma *fdma = &rx->fdma;
 
 	/* Write the buffer address in the LLP and LLP1 regs */
-	spx5_wr(((u64)rx->dma) & GENMASK(31, 0), sparx5,
+	spx5_wr(((u64)fdma->dma) & GENMASK(31, 0), sparx5,
 		FDMA_DCB_LLP(fdma->channel_id));
-	spx5_wr(((u64)rx->dma) >> 32, sparx5, FDMA_DCB_LLP1(fdma->channel_id));
+	spx5_wr(((u64)fdma->dma) >> 32, sparx5,
+		FDMA_DCB_LLP1(fdma->channel_id));
 
 	/* Set the number of RX DBs to be used, and DB end-of-frame interrupt */
 	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
@@ -168,16 +188,16 @@ static struct sk_buff *sparx5_fdma_rx_alloc_skb(struct sparx5_rx *rx)
 static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
 	struct fdma *fdma = &rx->fdma;
-	struct sparx5_db_hw *db_hw;
 	unsigned int packet_size;
 	struct sparx5_port *port;
 	struct sk_buff *new_skb;
+	struct fdma_db *db_hw;
 	struct frame_info fi;
 	struct sk_buff *skb;
 	dma_addr_t dma_addr;
 
 	/* Check if the DCB is done */
-	db_hw = &rx->dcb_entries[fdma->dcb_index].db[fdma->db_index];
+	db_hw = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
 	if (unlikely(!(db_hw->status & FDMA_DCB_STATUS_DONE)))
 		return false;
 	skb = rx->skb[fdma->dcb_index][fdma->db_index];
@@ -227,7 +247,7 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	int counter = 0;
 
 	while (counter < weight && sparx5_fdma_rx_get_frame(sparx5, rx)) {
-		struct sparx5_rx_dcb_hw *old_dcb;
+		struct fdma_dcb *old_dcb;
 
 		fdma->db_index++;
 		counter++;
@@ -238,13 +258,13 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 		 * pointer and set the nextptr in the DCB
 		 */
 		fdma->db_index = 0;
-		old_dcb = &rx->dcb_entries[fdma->dcb_index];
+		old_dcb = &fdma->dcbs[fdma->dcb_index];
 		fdma->dcb_index++;
 		fdma->dcb_index &= fdma->n_dcbs - 1;
 		sparx5_fdma_rx_add_dcb(rx, old_dcb,
-				       rx->dma +
+				       fdma->dma +
 				       ((unsigned long)old_dcb -
-					(unsigned long)rx->dcb_entries));
+					(unsigned long)fdma->dcbs));
 	}
 	if (counter < weight) {
 		napi_complete_done(&rx->napi, counter);
@@ -311,43 +331,15 @@ static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5)
 {
 	struct sparx5_rx *rx = &sparx5->rx;
 	struct fdma *fdma = &rx->fdma;
-	struct sparx5_rx_dcb_hw *dcb;
-	int idx, jdx;
-	int size;
+	int err;
 
-	size = sizeof(struct sparx5_rx_dcb_hw) * fdma->n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-	rx->dcb_entries = devm_kzalloc(sparx5->dev, size, GFP_KERNEL);
-	if (!rx->dcb_entries)
-		return -ENOMEM;
-	rx->dma = virt_to_phys(rx->dcb_entries);
-	rx->last_entry = rx->dcb_entries;
-	fdma->db_index = 0;
-	fdma->dcb_index = 0;
-	/* Now for each dcb allocate the db */
-	for (idx = 0; idx < fdma->n_dcbs; ++idx) {
-		dcb = &rx->dcb_entries[idx];
-		dcb->info = 0;
-		/* For each db allocate an skb and map skb data pointer to the DB
-		 * dataptr. In this way when the frame is received the skb->data
-		 * will contain the frame, so no memcpy is needed
-		 */
-		for (jdx = 0; jdx < fdma->n_dbs; ++jdx) {
-			struct sparx5_db_hw *db_hw = &dcb->db[jdx];
-			dma_addr_t dma_addr;
-			struct sk_buff *skb;
+	err = fdma_alloc_phys(fdma);
+	if (err)
+		return err;
 
-			skb = sparx5_fdma_rx_alloc_skb(rx);
-			if (!skb)
-				return -ENOMEM;
+	fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size),
+		       FDMA_DCB_STATUS_INTR);
 
-			dma_addr = virt_to_phys(skb->data);
-			db_hw->dataptr = dma_addr;
-			db_hw->status = 0;
-			rx->skb[idx][jdx] = skb;
-		}
-		sparx5_fdma_rx_add_dcb(rx, dcb, rx->dma + sizeof(*dcb) * idx);
-	}
 	netif_napi_add_weight(rx->ndev, &rx->napi, sparx5_fdma_napi_callback,
 			      FDMA_WEIGHT);
 	napi_enable(&rx->napi);
@@ -413,6 +405,11 @@ static void sparx5_fdma_rx_init(struct sparx5 *sparx5,
 	fdma->channel_id = channel;
 	fdma->n_dcbs = FDMA_DCB_MAX;
 	fdma->n_dbs = FDMA_RX_DCB_MAX_DBS;
+	fdma->priv = sparx5;
+	fdma->db_size = ALIGN(FDMA_XTR_BUFFER_SIZE, PAGE_SIZE);
+	fdma->size = fdma_get_size(&sparx5->rx.fdma);
+	fdma->ops.dataptr_cb = &sparx5_fdma_rx_dataptr_cb;
+	fdma->ops.nextptr_cb = &fdma_nextptr_cb;
 	/* Fetch a netdev for SKB and NAPI use, any will do */
 	for (idx = 0; idx < SPX5_PORTS; ++idx) {
 		struct sparx5_port *port = sparx5->ports[idx];
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 542f57569c5f..1f57739b601c 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -107,12 +107,6 @@ struct sparx5_db_hw {
 	u64 status;
 };
 
-struct sparx5_rx_dcb_hw {
-	u64 nextptr;
-	u64 info;
-	struct sparx5_db_hw db[FDMA_RX_DCB_MAX_DBS];
-};
-
 struct sparx5_tx_dcb_hw {
 	u64 nextptr;
 	u64 info;
@@ -127,8 +121,6 @@ struct sparx5_tx_dcb_hw {
  */
 struct sparx5_rx {
 	struct fdma fdma;
-	struct sparx5_rx_dcb_hw *dcb_entries;
-	struct sparx5_rx_dcb_hw *last_entry;
 	struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
 	dma_addr_t dma;
 	struct napi_struct napi;
-- 
cgit v1.3-3-g829e


From 17b9521086818b1368a7fb2a9612554d6be8c795 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:10 +0200
Subject: net: sparx5: use FDMA library for adding DCB's in the rx path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the fdma_dcb_add() function to add DCB's in the rx path. This gets
rid of the open-coding of nextptr and dataptr handling and leaves it to
the library.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 49 ++--------------------
 1 file changed, 3 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 675f8d5faa74..122876136f75 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -50,26 +50,6 @@ static int sparx5_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
 	return 0;
 }
 
-static void sparx5_fdma_rx_add_dcb(struct sparx5_rx *rx,
-				   struct fdma_dcb *dcb,
-				   u64 nextptr)
-{
-	struct fdma *fdma = &rx->fdma;
-	int idx = 0;
-
-	/* Reset the status of the DB */
-	for (idx = 0; idx < fdma->n_dbs; ++idx) {
-		struct fdma_db *db = &dcb->db[idx];
-
-		db->status = FDMA_DCB_STATUS_INTR;
-	}
-	dcb->nextptr = FDMA_DCB_INVALID_DATA;
-	dcb->info = FDMA_DCB_INFO_DATAL(FDMA_XTR_BUFFER_SIZE);
-
-	fdma->last_dcb->nextptr = nextptr;
-	fdma->last_dcb = dcb;
-}
-
 static void sparx5_fdma_tx_add_dcb(struct sparx5_tx *tx,
 				   struct sparx5_tx_dcb_hw *dcb,
 				   u64 nextptr)
@@ -179,36 +159,20 @@ static void sparx5_fdma_tx_reload(struct sparx5 *sparx5, struct sparx5_tx *tx)
 	spx5_wr(BIT(tx->fdma.channel_id), sparx5, FDMA_CH_RELOAD);
 }
 
-static struct sk_buff *sparx5_fdma_rx_alloc_skb(struct sparx5_rx *rx)
-{
-	return __netdev_alloc_skb(rx->ndev, FDMA_XTR_BUFFER_SIZE,
-				  GFP_ATOMIC);
-}
-
 static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
 	struct fdma *fdma = &rx->fdma;
 	unsigned int packet_size;
 	struct sparx5_port *port;
-	struct sk_buff *new_skb;
 	struct fdma_db *db_hw;
 	struct frame_info fi;
 	struct sk_buff *skb;
-	dma_addr_t dma_addr;
 
 	/* Check if the DCB is done */
 	db_hw = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
 	if (unlikely(!(db_hw->status & FDMA_DCB_STATUS_DONE)))
 		return false;
 	skb = rx->skb[fdma->dcb_index][fdma->db_index];
-	/* Replace the DB entry with a new SKB */
-	new_skb = sparx5_fdma_rx_alloc_skb(rx);
-	if (unlikely(!new_skb))
-		return false;
-	/* Map the new skb data and set the new skb */
-	dma_addr = virt_to_phys(new_skb->data);
-	rx->skb[fdma->dcb_index][fdma->db_index] = new_skb;
-	db_hw->dataptr = dma_addr;
 	packet_size = FDMA_DCB_STATUS_BLOCKL(db_hw->status);
 	skb_put(skb, packet_size);
 	/* Now do the normal processing of the skb */
@@ -247,24 +211,17 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	int counter = 0;
 
 	while (counter < weight && sparx5_fdma_rx_get_frame(sparx5, rx)) {
-		struct fdma_dcb *old_dcb;
-
 		fdma->db_index++;
 		counter++;
 		/* Check if the DCB can be reused */
 		if (fdma->db_index != fdma->n_dbs)
 			continue;
-		/* As the DCB  can be reused, just advance the dcb_index
-		 * pointer and set the nextptr in the DCB
-		 */
+		fdma_dcb_add(fdma, fdma->dcb_index,
+			     FDMA_DCB_INFO_DATAL(fdma->db_size),
+			     FDMA_DCB_STATUS_INTR);
 		fdma->db_index = 0;
-		old_dcb = &fdma->dcbs[fdma->dcb_index];
 		fdma->dcb_index++;
 		fdma->dcb_index &= fdma->n_dcbs - 1;
-		sparx5_fdma_rx_add_dcb(rx, old_dcb,
-				       fdma->dma +
-				       ((unsigned long)old_dcb -
-					(unsigned long)fdma->dcbs));
 	}
 	if (counter < weight) {
 		napi_complete_done(&rx->napi, counter);
-- 
cgit v1.3-3-g829e


From 6647f2fd8df056d2bc7c74e25469388ad375d98d Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:11 +0200
Subject: net: sparx5: use library helper for freeing rx buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The library has the helper fdma_free_phys() for freeing physical FDMA
memory. Use it in the exit path.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 122876136f75..d01516f32d0c 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -523,5 +523,6 @@ int sparx5_fdma_stop(struct sparx5 *sparx5)
 	read_poll_timeout(sparx5_fdma_port_ctrl, val,
 			  FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_GET(val) == 0,
 			  500, 10000, 0, sparx5);
+	fdma_free_phys(&sparx5->rx.fdma);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 4ff58c394715ee0828fb82799d4176bfbe0721c9 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:12 +0200
Subject: net: sparx5: use a few FDMA helpers in the rx path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The library provides helpers for a number of DCB and DB operations. Use
these in the rx path.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index d01516f32d0c..c37718b99d67 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -162,19 +162,17 @@ static void sparx5_fdma_tx_reload(struct sparx5 *sparx5, struct sparx5_tx *tx)
 static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
 	struct fdma *fdma = &rx->fdma;
-	unsigned int packet_size;
 	struct sparx5_port *port;
 	struct fdma_db *db_hw;
 	struct frame_info fi;
 	struct sk_buff *skb;
 
 	/* Check if the DCB is done */
-	db_hw = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
-	if (unlikely(!(db_hw->status & FDMA_DCB_STATUS_DONE)))
+	db_hw = fdma_db_next_get(fdma);
+	if (unlikely(!fdma_db_is_done(db_hw)))
 		return false;
 	skb = rx->skb[fdma->dcb_index][fdma->db_index];
-	packet_size = FDMA_DCB_STATUS_BLOCKL(db_hw->status);
-	skb_put(skb, packet_size);
+	skb_put(skb, fdma_db_len_get(db_hw));
 	/* Now do the normal processing of the skb */
 	sparx5_ifh_parse((u32 *)skb->data, &fi);
 	/* Map to port netdev */
@@ -211,17 +209,16 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	int counter = 0;
 
 	while (counter < weight && sparx5_fdma_rx_get_frame(sparx5, rx)) {
-		fdma->db_index++;
+		fdma_db_advance(fdma);
 		counter++;
 		/* Check if the DCB can be reused */
-		if (fdma->db_index != fdma->n_dbs)
+		if (fdma_dcb_is_reusable(fdma))
 			continue;
 		fdma_dcb_add(fdma, fdma->dcb_index,
 			     FDMA_DCB_INFO_DATAL(fdma->db_size),
 			     FDMA_DCB_STATUS_INTR);
-		fdma->db_index = 0;
-		fdma->dcb_index++;
-		fdma->dcb_index &= fdma->n_dcbs - 1;
+		fdma_db_reset(fdma);
+		fdma_dcb_advance(fdma);
 	}
 	if (counter < weight) {
 		napi_complete_done(&rx->napi, counter);
-- 
cgit v1.3-3-g829e


From 0a5c440850896a0ae5a2cd637b3e84e442520f1d Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:13 +0200
Subject: net: sparx5: use the FDMA library for allocation of tx buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the two functions: fdma_alloc_phys() and fdma_dcb_init() for tx
buffer allocation and use the new buffers throughout.

In order to replace the old buffers with the new ones, we have to do the
following refactoring:

    - use fdma_alloc_phys() and fdma_dcb_init()

    - replace the variables: tx->dma, tx->first_entry and tx->curr_entry
      with the equivalents from the FDMA struct.

    - replace uses of sparx5_db_hw and sparx5_tx_dcb_hw with fdma_db and
      fdma_dcb.

    - add sparx5_fdma_tx_dataptr_cb callback for obtaining the dataptr.

    - Initialize FDMA struct values.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 94 ++++++++++------------
 .../net/ethernet/microchip/sparx5/sparx5_main.h    | 14 ----
 2 files changed, 44 insertions(+), 64 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index c37718b99d67..8f721f7671ce 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -32,6 +32,21 @@ struct sparx5_db {
 	void *cpu_addr;
 };
 
+static int sparx5_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+				     u64 *dataptr)
+{
+	struct sparx5 *sparx5 = fdma->priv;
+	struct sparx5_tx *tx = &sparx5->tx;
+	struct sparx5_db *db_buf;
+
+	db_buf = list_first_entry(&tx->db_list, struct sparx5_db, list);
+	list_move_tail(&db_buf->list, &tx->db_list);
+
+	*dataptr = virt_to_phys(db_buf->cpu_addr);
+
+	return 0;
+}
+
 static int sparx5_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
 				     u64 *dataptr)
 {
@@ -50,22 +65,6 @@ static int sparx5_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
 	return 0;
 }
 
-static void sparx5_fdma_tx_add_dcb(struct sparx5_tx *tx,
-				   struct sparx5_tx_dcb_hw *dcb,
-				   u64 nextptr)
-{
-	int idx = 0;
-
-	/* Reset the status of the DB */
-	for (idx = 0; idx < tx->fdma.n_dbs; ++idx) {
-		struct sparx5_db_hw *db = &dcb->db[idx];
-
-		db->status = FDMA_DCB_STATUS_DONE;
-	}
-	dcb->nextptr = FDMA_DCB_INVALID_DATA;
-	dcb->info = FDMA_DCB_INFO_DATAL(FDMA_XTR_BUFFER_SIZE);
-}
-
 static void sparx5_fdma_rx_activate(struct sparx5 *sparx5, struct sparx5_rx *rx)
 {
 	struct fdma *fdma = &rx->fdma;
@@ -122,9 +121,10 @@ static void sparx5_fdma_tx_activate(struct sparx5 *sparx5, struct sparx5_tx *tx)
 	struct fdma *fdma = &tx->fdma;
 
 	/* Write the buffer address in the LLP and LLP1 regs */
-	spx5_wr(((u64)tx->dma) & GENMASK(31, 0), sparx5,
+	spx5_wr(((u64)fdma->dma) & GENMASK(31, 0), sparx5,
 		FDMA_DCB_LLP(fdma->channel_id));
-	spx5_wr(((u64)tx->dma) >> 32, sparx5, FDMA_DCB_LLP1(fdma->channel_id));
+	spx5_wr(((u64)fdma->dma) >> 32, sparx5,
+		FDMA_DCB_LLP1(fdma->channel_id));
 
 	/* Set the number of TX DBs to be used, and DB end-of-frame interrupt */
 	spx5_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
@@ -231,40 +231,41 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	return counter;
 }
 
-static struct sparx5_tx_dcb_hw *sparx5_fdma_next_dcb(struct sparx5_tx *tx,
-						     struct sparx5_tx_dcb_hw *dcb)
+static struct fdma_dcb *sparx5_fdma_next_dcb(struct sparx5_tx *tx,
+					     struct fdma_dcb *dcb)
 {
-	struct sparx5_tx_dcb_hw *next_dcb;
+	struct fdma_dcb *next_dcb;
 	struct fdma *fdma = &tx->fdma;
 
 	next_dcb = dcb;
 	next_dcb++;
 	/* Handle wrap-around */
 	if ((unsigned long)next_dcb >=
-	    ((unsigned long)tx->first_entry + fdma->n_dcbs * sizeof(*dcb)))
-		next_dcb = tx->first_entry;
+	    ((unsigned long)fdma->dcbs + fdma->n_dcbs * sizeof(*dcb)))
+		next_dcb = fdma->dcbs;
 	return next_dcb;
 }
 
 int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
 {
-	struct sparx5_tx_dcb_hw *next_dcb_hw;
 	struct sparx5_tx *tx = &sparx5->tx;
+	struct fdma *fdma = &tx->fdma;
 	static bool first_time = true;
-	struct sparx5_db_hw *db_hw;
+	struct fdma_dcb *next_dcb_hw;
+	struct fdma_db *db_hw;
 	struct sparx5_db *db;
 
-	next_dcb_hw = sparx5_fdma_next_dcb(tx, tx->curr_entry);
+	next_dcb_hw = sparx5_fdma_next_dcb(tx, fdma->last_dcb);
 	db_hw = &next_dcb_hw->db[0];
 	if (!(db_hw->status & FDMA_DCB_STATUS_DONE))
 		return -EINVAL;
 	db = list_first_entry(&tx->db_list, struct sparx5_db, list);
 	list_move_tail(&db->list, &tx->db_list);
 	next_dcb_hw->nextptr = FDMA_DCB_INVALID_DATA;
-	tx->curr_entry->nextptr = tx->dma +
+	fdma->last_dcb->nextptr = fdma->dma +
 		((unsigned long)next_dcb_hw -
-		 (unsigned long)tx->first_entry);
-	tx->curr_entry = next_dcb_hw;
+		(unsigned long)fdma->dcbs);
+	fdma->last_dcb = next_dcb_hw;
 	memset(db->cpu_addr, 0, FDMA_XTR_BUFFER_SIZE);
 	memcpy(db->cpu_addr, ifh, IFH_LEN * 4);
 	memcpy(db->cpu_addr + IFH_LEN * 4, skb->data, skb->len);
@@ -304,28 +305,15 @@ static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5)
 static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 {
 	struct sparx5_tx *tx = &sparx5->tx;
-	struct sparx5_tx_dcb_hw *dcb;
 	struct fdma *fdma = &tx->fdma;
-	int idx, jdx;
-	int size;
+	int idx, jdx, err;
 
-	size = sizeof(struct sparx5_tx_dcb_hw) * fdma->n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-	tx->curr_entry = devm_kzalloc(sparx5->dev, size, GFP_KERNEL);
-	if (!tx->curr_entry)
-		return -ENOMEM;
-	tx->dma = virt_to_phys(tx->curr_entry);
-	tx->first_entry = tx->curr_entry;
 	INIT_LIST_HEAD(&tx->db_list);
 	/* Now for each dcb allocate the db */
 	for (idx = 0; idx < fdma->n_dcbs; ++idx) {
-		dcb = &tx->curr_entry[idx];
-		dcb->info = 0;
 		/* TX databuffers must be 16byte aligned */
 		for (jdx = 0; jdx < fdma->n_dbs; ++jdx) {
-			struct sparx5_db_hw *db_hw = &dcb->db[jdx];
 			struct sparx5_db *db;
-			dma_addr_t phys;
 			void *cpu_addr;
 
 			cpu_addr = devm_kzalloc(sparx5->dev,
@@ -333,20 +321,21 @@ static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 						GFP_KERNEL);
 			if (!cpu_addr)
 				return -ENOMEM;
-			phys = virt_to_phys(cpu_addr);
-			db_hw->dataptr = phys;
-			db_hw->status = 0;
 			db = devm_kzalloc(sparx5->dev, sizeof(*db), GFP_KERNEL);
 			if (!db)
 				return -ENOMEM;
 			db->cpu_addr = cpu_addr;
 			list_add_tail(&db->list, &tx->db_list);
 		}
-		sparx5_fdma_tx_add_dcb(tx, dcb, tx->dma + sizeof(*dcb) * idx);
-		/* Let the curr_entry to point to the last allocated entry */
-		if (idx == fdma->n_dcbs - 1)
-			tx->curr_entry = dcb;
 	}
+
+	err = fdma_alloc_phys(fdma);
+	if (err)
+		return err;
+
+	fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size),
+		       FDMA_DCB_STATUS_DONE);
+
 	return 0;
 }
 
@@ -383,6 +372,11 @@ static void sparx5_fdma_tx_init(struct sparx5 *sparx5,
 	fdma->channel_id = channel;
 	fdma->n_dcbs = FDMA_DCB_MAX;
 	fdma->n_dbs = FDMA_TX_DCB_MAX_DBS;
+	fdma->priv = sparx5;
+	fdma->db_size = ALIGN(FDMA_XTR_BUFFER_SIZE, PAGE_SIZE);
+	fdma->size = fdma_get_size(&sparx5->tx.fdma);
+	fdma->ops.dataptr_cb = &sparx5_fdma_tx_dataptr_cb;
+	fdma->ops.nextptr_cb = &fdma_nextptr_cb;
 }
 
 irqreturn_t sparx5_fdma_handler(int irq, void *args)
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 1f57739b601c..81c3f8f2f474 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -102,17 +102,6 @@ enum sparx5_vlan_port_type {
 
 struct sparx5;
 
-struct sparx5_db_hw {
-	u64 dataptr;
-	u64 status;
-};
-
-struct sparx5_tx_dcb_hw {
-	u64 nextptr;
-	u64 info;
-	struct sparx5_db_hw db[FDMA_TX_DCB_MAX_DBS];
-};
-
 /* Frame DMA receive state:
  * For each DB, there is a SKB, and the skb data pointer is mapped in
  * the DB. Once a frame is received the skb is given to the upper layers
@@ -133,10 +122,7 @@ struct sparx5_rx {
  */
 struct sparx5_tx {
 	struct fdma fdma;
-	struct sparx5_tx_dcb_hw *curr_entry;
-	struct sparx5_tx_dcb_hw *first_entry;
 	struct list_head db_list;
-	dma_addr_t dma;
 	u64 packets;
 	u64 dropped;
 };
-- 
cgit v1.3-3-g829e


From f4aa7e361ae2265ccdf2300f0a2ec531caed3f40 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:14 +0200
Subject: net: sparx5: use FDMA library for adding DCB's in the tx path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the fdma_dcb_add() function to add DCB's in the tx path. This gets
rid of the open-coding of nextptr and dataptr handling and leaves it to
the library.

Also, make sure the fdma indexes are advanced using: fdma_dcb_advance(),
so that the correct nextptr and dataptr offsets are retrieved.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 39 +++++-----------------
 1 file changed, 9 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 8f721f7671ce..4fc52140752a 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -231,48 +231,27 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 	return counter;
 }
 
-static struct fdma_dcb *sparx5_fdma_next_dcb(struct sparx5_tx *tx,
-					     struct fdma_dcb *dcb)
-{
-	struct fdma_dcb *next_dcb;
-	struct fdma *fdma = &tx->fdma;
-
-	next_dcb = dcb;
-	next_dcb++;
-	/* Handle wrap-around */
-	if ((unsigned long)next_dcb >=
-	    ((unsigned long)fdma->dcbs + fdma->n_dcbs * sizeof(*dcb)))
-		next_dcb = fdma->dcbs;
-	return next_dcb;
-}
-
 int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
 {
 	struct sparx5_tx *tx = &sparx5->tx;
 	struct fdma *fdma = &tx->fdma;
 	static bool first_time = true;
-	struct fdma_dcb *next_dcb_hw;
-	struct fdma_db *db_hw;
 	struct sparx5_db *db;
 
-	next_dcb_hw = sparx5_fdma_next_dcb(tx, fdma->last_dcb);
-	db_hw = &next_dcb_hw->db[0];
-	if (!(db_hw->status & FDMA_DCB_STATUS_DONE))
+	fdma_dcb_advance(fdma);
+	if (!fdma_db_is_done(fdma_db_get(fdma, fdma->dcb_index, 0)))
 		return -EINVAL;
 	db = list_first_entry(&tx->db_list, struct sparx5_db, list);
-	list_move_tail(&db->list, &tx->db_list);
-	next_dcb_hw->nextptr = FDMA_DCB_INVALID_DATA;
-	fdma->last_dcb->nextptr = fdma->dma +
-		((unsigned long)next_dcb_hw -
-		(unsigned long)fdma->dcbs);
-	fdma->last_dcb = next_dcb_hw;
 	memset(db->cpu_addr, 0, FDMA_XTR_BUFFER_SIZE);
 	memcpy(db->cpu_addr, ifh, IFH_LEN * 4);
 	memcpy(db->cpu_addr + IFH_LEN * 4, skb->data, skb->len);
-	db_hw->status = FDMA_DCB_STATUS_SOF |
-			FDMA_DCB_STATUS_EOF |
-			FDMA_DCB_STATUS_BLOCKO(0) |
-			FDMA_DCB_STATUS_BLOCKL(skb->len + IFH_LEN * 4 + 4);
+
+	fdma_dcb_add(fdma, fdma->dcb_index, 0,
+		     FDMA_DCB_STATUS_SOF |
+		     FDMA_DCB_STATUS_EOF |
+		     FDMA_DCB_STATUS_BLOCKO(0) |
+		     FDMA_DCB_STATUS_BLOCKL(skb->len + IFH_LEN * 4 + 4));
+
 	if (first_time) {
 		sparx5_fdma_tx_activate(sparx5, tx);
 		first_time = false;
-- 
cgit v1.3-3-g829e


From bb7a60dab43ba79df2c7795172f2c80894f25c50 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:15 +0200
Subject: net: sparx5: use library helper for freeing tx buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The library has the helper fdma_free_phys() for freeing physical FDMA
memory. Use it in the exit path.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 4fc52140752a..38735bac6482 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -494,5 +494,6 @@ int sparx5_fdma_stop(struct sparx5 *sparx5)
 			  FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_GET(val) == 0,
 			  500, 10000, 0, sparx5);
 	fdma_free_phys(&sparx5->rx.fdma);
+	fdma_free_phys(&sparx5->tx.fdma);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 55e84c3cfd06ae6806ff43fff6985ddf742a2a2a Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:16 +0200
Subject: net: sparx5: use contiguous memory for tx buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, the driver uses a linked list for storing the tx buffer
addresses. This requires a good amount of extra bookkeeping code. Ditch
the linked list in favor of tx buffers being in the same contiguous
memory space as the DCB's and the DB's. The FDMA library has a helper
for this - so use that.

The tx buffer addresses are now retrieved as an offset into the FDMA
memory space.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/microchip/sparx5/sparx5_fdma.c    | 57 +++++-----------------
 .../net/ethernet/microchip/sparx5/sparx5_main.h    |  1 -
 2 files changed, 13 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 38735bac6482..7e1bdd0344d0 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -24,25 +24,11 @@
 #define FDMA_XTR_BUFFER_SIZE		2048
 #define FDMA_WEIGHT			4
 
-/* For each hardware DB there is an entry in this list and when the HW DB
- * entry is used, this SW DB entry is moved to the back of the list
- */
-struct sparx5_db {
-	struct list_head list;
-	void *cpu_addr;
-};
-
 static int sparx5_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db,
 				     u64 *dataptr)
 {
-	struct sparx5 *sparx5 = fdma->priv;
-	struct sparx5_tx *tx = &sparx5->tx;
-	struct sparx5_db *db_buf;
-
-	db_buf = list_first_entry(&tx->db_list, struct sparx5_db, list);
-	list_move_tail(&db_buf->list, &tx->db_list);
-
-	*dataptr = virt_to_phys(db_buf->cpu_addr);
+	*dataptr = fdma->dma + (sizeof(struct fdma_dcb) * fdma->n_dcbs) +
+		   ((dcb * fdma->n_dbs + db) * fdma->db_size);
 
 	return 0;
 }
@@ -236,15 +222,19 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
 	struct sparx5_tx *tx = &sparx5->tx;
 	struct fdma *fdma = &tx->fdma;
 	static bool first_time = true;
-	struct sparx5_db *db;
+	void *virt_addr;
 
 	fdma_dcb_advance(fdma);
 	if (!fdma_db_is_done(fdma_db_get(fdma, fdma->dcb_index, 0)))
 		return -EINVAL;
-	db = list_first_entry(&tx->db_list, struct sparx5_db, list);
-	memset(db->cpu_addr, 0, FDMA_XTR_BUFFER_SIZE);
-	memcpy(db->cpu_addr, ifh, IFH_LEN * 4);
-	memcpy(db->cpu_addr + IFH_LEN * 4, skb->data, skb->len);
+
+	/* Get the virtual address of the dataptr for the next DB */
+	virt_addr = ((u8 *)fdma->dcbs +
+		     (sizeof(struct fdma_dcb) * fdma->n_dcbs) +
+		     ((fdma->dcb_index * fdma->n_dbs) * fdma->db_size));
+
+	memcpy(virt_addr, ifh, IFH_LEN * 4);
+	memcpy(virt_addr + IFH_LEN * 4, skb->data, skb->len);
 
 	fdma_dcb_add(fdma, fdma->dcb_index, 0,
 		     FDMA_DCB_STATUS_SOF |
@@ -285,28 +275,7 @@ static int sparx5_fdma_tx_alloc(struct sparx5 *sparx5)
 {
 	struct sparx5_tx *tx = &sparx5->tx;
 	struct fdma *fdma = &tx->fdma;
-	int idx, jdx, err;
-
-	INIT_LIST_HEAD(&tx->db_list);
-	/* Now for each dcb allocate the db */
-	for (idx = 0; idx < fdma->n_dcbs; ++idx) {
-		/* TX databuffers must be 16byte aligned */
-		for (jdx = 0; jdx < fdma->n_dbs; ++jdx) {
-			struct sparx5_db *db;
-			void *cpu_addr;
-
-			cpu_addr = devm_kzalloc(sparx5->dev,
-						FDMA_XTR_BUFFER_SIZE,
-						GFP_KERNEL);
-			if (!cpu_addr)
-				return -ENOMEM;
-			db = devm_kzalloc(sparx5->dev, sizeof(*db), GFP_KERNEL);
-			if (!db)
-				return -ENOMEM;
-			db->cpu_addr = cpu_addr;
-			list_add_tail(&db->list, &tx->db_list);
-		}
-	}
+	int err;
 
 	err = fdma_alloc_phys(fdma);
 	if (err)
@@ -353,7 +322,7 @@ static void sparx5_fdma_tx_init(struct sparx5 *sparx5,
 	fdma->n_dbs = FDMA_TX_DCB_MAX_DBS;
 	fdma->priv = sparx5;
 	fdma->db_size = ALIGN(FDMA_XTR_BUFFER_SIZE, PAGE_SIZE);
-	fdma->size = fdma_get_size(&sparx5->tx.fdma);
+	fdma->size = fdma_get_size_contiguous(&sparx5->tx.fdma);
 	fdma->ops.dataptr_cb = &sparx5_fdma_tx_dataptr_cb;
 	fdma->ops.nextptr_cb = &fdma_nextptr_cb;
 }
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
index 81c3f8f2f474..3309060b1e4c 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h
@@ -122,7 +122,6 @@ struct sparx5_rx {
  */
 struct sparx5_tx {
 	struct fdma fdma;
-	struct list_head db_list;
 	u64 packets;
 	u64 dropped;
 };
-- 
cgit v1.3-3-g829e


From 51152312dc99e2bb952d5bad7e81aefd3be3b97d Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Mon, 2 Sep 2024 16:54:17 +0200
Subject: net: sparx5: ditch sparx5_fdma_rx/tx_reload() functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These direction specific functions can be ditched in favor of a single
function: sparx5_fdma_reload(), which retrieves the channel id from the
fdma struct instead.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Steen Hegelund <Steen.Hegelund@microchip.com>
Reviewed-by: Jens Emil Schulz Østergaard <jensemil.schulzostergaard@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
index 7e1bdd0344d0..61df874b7623 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c
@@ -133,16 +133,10 @@ static void sparx5_fdma_tx_deactivate(struct sparx5 *sparx5, struct sparx5_tx *t
 		 sparx5, FDMA_CH_ACTIVATE);
 }
 
-static void sparx5_fdma_rx_reload(struct sparx5 *sparx5, struct sparx5_rx *rx)
+static void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma)
 {
 	/* Reload the RX channel */
-	spx5_wr(BIT(rx->fdma.channel_id), sparx5, FDMA_CH_RELOAD);
-}
-
-static void sparx5_fdma_tx_reload(struct sparx5 *sparx5, struct sparx5_tx *tx)
-{
-	/* Reload the TX channel */
-	spx5_wr(BIT(tx->fdma.channel_id), sparx5, FDMA_CH_RELOAD);
+	spx5_wr(BIT(fdma->channel_id), sparx5, FDMA_CH_RELOAD);
 }
 
 static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx)
@@ -213,7 +207,7 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight)
 			 sparx5, FDMA_INTR_DB_ENA);
 	}
 	if (counter)
-		sparx5_fdma_rx_reload(sparx5, rx);
+		sparx5_fdma_reload(sparx5, fdma);
 	return counter;
 }
 
@@ -246,7 +240,7 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb)
 		sparx5_fdma_tx_activate(sparx5, tx);
 		first_time = false;
 	} else {
-		sparx5_fdma_tx_reload(sparx5, tx);
+		sparx5_fdma_reload(sparx5, fdma);
 	}
 	return NETDEV_TX_OK;
 }
-- 
cgit v1.3-3-g829e


From 5c26516f090363b548c51ce892b8bcc46c7dcdbc Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Tue, 3 Sep 2024 00:06:10 +0800
Subject: selftests: add selftest for UDP SO_PEEK_OFF support

Add the SO_PEEK_OFF selftest for UDP. In this patch, I mainly do
three things:
1. rename tcp_so_peek_off.c
2. adjust for UDP protocol
3. add selftests into it

Suggested-by: Jon Maloy <jmaloy@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore        |   1 +
 tools/testing/selftests/net/Makefile          |   2 +-
 tools/testing/selftests/net/sk_so_peek_off.c  | 202 ++++++++++++++++++++++++++
 tools/testing/selftests/net/tcp_so_peek_off.c | 183 -----------------------
 4 files changed, 204 insertions(+), 184 deletions(-)
 create mode 100644 tools/testing/selftests/net/sk_so_peek_off.c
 delete mode 100644 tools/testing/selftests/net/tcp_so_peek_off.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 666ab7d9390b..923bf098e2eb 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -34,6 +34,7 @@ scm_pidfd
 scm_rights
 sk_bind_sendto_listen
 sk_connect_zero_addr
+sk_so_peek_off
 socket
 so_incoming_cpu
 so_netns_cookie
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 1179e3261bef..d5029f978aa9 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -80,7 +80,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh
 TEST_GEN_FILES += bind_bhash
 TEST_GEN_PROGS += sk_bind_sendto_listen
 TEST_GEN_PROGS += sk_connect_zero_addr
-TEST_GEN_PROGS += tcp_so_peek_off
+TEST_GEN_PROGS += sk_so_peek_off
 TEST_PROGS += test_ingress_egress_chaining.sh
 TEST_GEN_PROGS += so_incoming_cpu
 TEST_PROGS += sctp_vrf.sh
diff --git a/tools/testing/selftests/net/sk_so_peek_off.c b/tools/testing/selftests/net/sk_so_peek_off.c
new file mode 100644
index 000000000000..d87dd8d8d491
--- /dev/null
+++ b/tools/testing/selftests/net/sk_so_peek_off.c
@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include "../kselftest.h"
+
+static char *afstr(int af, int proto)
+{
+	if (proto == IPPROTO_TCP)
+		return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6";
+	else
+		return af == AF_INET ? "UDP/IPv4" : "UDP/IPv6";
+}
+
+int sk_peek_offset_probe(sa_family_t af, int proto)
+{
+	int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM);
+	int optv = 0;
+	int ret = 0;
+	int s;
+
+	s = socket(af, type, proto);
+	if (s < 0) {
+		ksft_perror("Temporary TCP socket creation failed");
+	} else {
+		if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int)))
+			ret = 1;
+		else
+			printf("%s does not support SO_PEEK_OFF\n", afstr(af, proto));
+		close(s);
+	}
+	return ret;
+}
+
+static void sk_peek_offset_set(int s, int offset)
+{
+	if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset)))
+		ksft_perror("Failed to set SO_PEEK_OFF value\n");
+}
+
+static int sk_peek_offset_get(int s)
+{
+	int offset;
+	socklen_t len = sizeof(offset);
+
+	if (getsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, &len))
+		ksft_perror("Failed to get SO_PEEK_OFF value\n");
+	return offset;
+}
+
+static int sk_peek_offset_test(sa_family_t af, int proto)
+{
+	int type = (proto == IPPROTO_TCP ? SOCK_STREAM : SOCK_DGRAM);
+	union {
+		struct sockaddr sa;
+		struct sockaddr_in a4;
+		struct sockaddr_in6 a6;
+	} a;
+	int res = 0;
+	int s[2] = {0, 0};
+	int recv_sock = 0;
+	int offset = 0;
+	ssize_t len;
+	char buf[2];
+
+	memset(&a, 0, sizeof(a));
+	a.sa.sa_family = af;
+
+	s[0] = recv_sock = socket(af, type, proto);
+	s[1] = socket(af, type, proto);
+
+	if (s[0] < 0 || s[1] < 0) {
+		ksft_perror("Temporary socket creation failed\n");
+		goto out;
+	}
+	if (bind(s[0], &a.sa, sizeof(a)) < 0) {
+		ksft_perror("Temporary socket bind() failed\n");
+		goto out;
+	}
+	if (getsockname(s[0], &a.sa, &((socklen_t) { sizeof(a) })) < 0) {
+		ksft_perror("Temporary socket getsockname() failed\n");
+		goto out;
+	}
+	if (proto == IPPROTO_TCP && listen(s[0], 0) < 0) {
+		ksft_perror("Temporary socket listen() failed\n");
+		goto out;
+	}
+	if (connect(s[1], &a.sa, sizeof(a)) < 0) {
+		ksft_perror("Temporary socket connect() failed\n");
+		goto out;
+	}
+	if (proto == IPPROTO_TCP) {
+		recv_sock = accept(s[0], NULL, NULL);
+		if (recv_sock <= 0) {
+			ksft_perror("Temporary socket accept() failed\n");
+			goto out;
+		}
+	}
+
+	/* Some basic tests of getting/setting offset */
+	offset = sk_peek_offset_get(recv_sock);
+	if (offset != -1) {
+		ksft_perror("Initial value of socket offset not -1\n");
+		goto out;
+	}
+	sk_peek_offset_set(recv_sock, 0);
+	offset = sk_peek_offset_get(recv_sock);
+	if (offset != 0) {
+		ksft_perror("Failed to set socket offset to 0\n");
+		goto out;
+	}
+
+	/* Transfer a message */
+	if (send(s[1], (char *)("ab"), 2, 0) != 2) {
+		ksft_perror("Temporary probe socket send() failed\n");
+		goto out;
+	}
+	/* Read first byte */
+	len = recv(recv_sock, buf, 1, MSG_PEEK);
+	if (len != 1 || buf[0] != 'a') {
+		ksft_perror("Failed to read first byte of message\n");
+		goto out;
+	}
+	offset = sk_peek_offset_get(recv_sock);
+	if (offset != 1) {
+		ksft_perror("Offset not forwarded correctly at first byte\n");
+		goto out;
+	}
+	/* Try to read beyond last byte */
+	len = recv(recv_sock, buf, 2, MSG_PEEK);
+	if (len != 1 || buf[0] != 'b') {
+		ksft_perror("Failed to read last byte of message\n");
+		goto out;
+	}
+	offset = sk_peek_offset_get(recv_sock);
+	if (offset != 2) {
+		ksft_perror("Offset not forwarded correctly at last byte\n");
+		goto out;
+	}
+	/* Flush message */
+	len = recv(recv_sock, buf, 2, MSG_TRUNC);
+	if (len != 2) {
+		ksft_perror("Failed to flush message\n");
+		goto out;
+	}
+	offset = sk_peek_offset_get(recv_sock);
+	if (offset != 0) {
+		ksft_perror("Offset not reverted correctly after flush\n");
+		goto out;
+	}
+
+	printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af, proto));
+	res = 1;
+out:
+	if (proto == IPPROTO_TCP && recv_sock >= 0)
+		close(recv_sock);
+	if (s[1] >= 0)
+		close(s[1]);
+	if (s[0] >= 0)
+		close(s[0]);
+	return res;
+}
+
+static int do_test(int proto)
+{
+	int res4, res6;
+
+	res4 = sk_peek_offset_probe(AF_INET, proto);
+	res6 = sk_peek_offset_probe(AF_INET6, proto);
+
+	if (!res4 && !res6)
+		return KSFT_SKIP;
+
+	if (res4)
+		res4 = sk_peek_offset_test(AF_INET, proto);
+
+	if (res6)
+		res6 = sk_peek_offset_test(AF_INET6, proto);
+
+	if (!res4 || !res6)
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+int main(void)
+{
+	int restcp, resudp;
+
+	restcp = do_test(IPPROTO_TCP);
+	resudp = do_test(IPPROTO_UDP);
+	if (restcp == KSFT_FAIL || resudp == KSFT_FAIL)
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/net/tcp_so_peek_off.c b/tools/testing/selftests/net/tcp_so_peek_off.c
deleted file mode 100644
index df8a39d9d3c3..000000000000
--- a/tools/testing/selftests/net/tcp_so_peek_off.c
+++ /dev/null
@@ -1,183 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <errno.h>
-#include <sys/types.h>
-#include <netinet/in.h>
-#include <arpa/inet.h>
-#include "../kselftest.h"
-
-static char *afstr(int af)
-{
-	return af == AF_INET ? "TCP/IPv4" : "TCP/IPv6";
-}
-
-int tcp_peek_offset_probe(sa_family_t af)
-{
-	int optv = 0;
-	int ret = 0;
-	int s;
-
-	s = socket(af, SOCK_STREAM | SOCK_CLOEXEC, IPPROTO_TCP);
-	if (s < 0) {
-		ksft_perror("Temporary TCP socket creation failed");
-	} else {
-		if (!setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &optv, sizeof(int)))
-			ret = 1;
-		else
-			printf("%s does not support SO_PEEK_OFF\n", afstr(af));
-		close(s);
-	}
-	return ret;
-}
-
-static void tcp_peek_offset_set(int s, int offset)
-{
-	if (setsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, sizeof(offset)))
-		ksft_perror("Failed to set SO_PEEK_OFF value\n");
-}
-
-static int tcp_peek_offset_get(int s)
-{
-	int offset;
-	socklen_t len = sizeof(offset);
-
-	if (getsockopt(s, SOL_SOCKET, SO_PEEK_OFF, &offset, &len))
-		ksft_perror("Failed to get SO_PEEK_OFF value\n");
-	return offset;
-}
-
-static int tcp_peek_offset_test(sa_family_t af)
-{
-	union {
-		struct sockaddr sa;
-		struct sockaddr_in a4;
-		struct sockaddr_in6 a6;
-	} a;
-	int res = 0;
-	int s[2] = {0, 0};
-	int recv_sock = 0;
-	int offset = 0;
-	ssize_t len;
-	char buf;
-
-	memset(&a, 0, sizeof(a));
-	a.sa.sa_family = af;
-
-	s[0] = socket(af, SOCK_STREAM, IPPROTO_TCP);
-	s[1] = socket(af, SOCK_STREAM | SOCK_NONBLOCK, IPPROTO_TCP);
-
-	if (s[0] < 0 || s[1] < 0) {
-		ksft_perror("Temporary socket creation failed\n");
-		goto out;
-	}
-	if (bind(s[0], &a.sa, sizeof(a)) < 0) {
-		ksft_perror("Temporary socket bind() failed\n");
-		goto out;
-	}
-	if (getsockname(s[0], &a.sa, &((socklen_t) { sizeof(a) })) < 0) {
-		ksft_perror("Temporary socket getsockname() failed\n");
-		goto out;
-	}
-	if (listen(s[0], 0) < 0) {
-		ksft_perror("Temporary socket listen() failed\n");
-		goto out;
-	}
-	if (connect(s[1], &a.sa, sizeof(a)) >= 0 || errno != EINPROGRESS) {
-		ksft_perror("Temporary socket connect() failed\n");
-		goto out;
-	}
-	recv_sock = accept(s[0], NULL, NULL);
-	if (recv_sock <= 0) {
-		ksft_perror("Temporary socket accept() failed\n");
-		goto out;
-	}
-
-	/* Some basic tests of getting/setting offset */
-	offset = tcp_peek_offset_get(recv_sock);
-	if (offset != -1) {
-		ksft_perror("Initial value of socket offset not -1\n");
-		goto out;
-	}
-	tcp_peek_offset_set(recv_sock, 0);
-	offset = tcp_peek_offset_get(recv_sock);
-	if (offset != 0) {
-		ksft_perror("Failed to set socket offset to 0\n");
-		goto out;
-	}
-
-	/* Transfer a message */
-	if (send(s[1], (char *)("ab"), 2, 0) <= 0 || errno != EINPROGRESS) {
-		ksft_perror("Temporary probe socket send() failed\n");
-		goto out;
-	}
-	/* Read first byte */
-	len = recv(recv_sock, &buf, 1, MSG_PEEK);
-	if (len != 1 || buf != 'a') {
-		ksft_perror("Failed to read first byte of message\n");
-		goto out;
-	}
-	offset = tcp_peek_offset_get(recv_sock);
-	if (offset != 1) {
-		ksft_perror("Offset not forwarded correctly at first byte\n");
-		goto out;
-	}
-	/* Try to read beyond last byte */
-	len = recv(recv_sock, &buf, 2, MSG_PEEK);
-	if (len != 1 || buf != 'b') {
-		ksft_perror("Failed to read last byte of message\n");
-		goto out;
-	}
-	offset = tcp_peek_offset_get(recv_sock);
-	if (offset != 2) {
-		ksft_perror("Offset not forwarded correctly at last byte\n");
-		goto out;
-	}
-	/* Flush message */
-	len = recv(recv_sock, NULL, 2, MSG_TRUNC);
-	if (len != 2) {
-		ksft_perror("Failed to flush message\n");
-		goto out;
-	}
-	offset = tcp_peek_offset_get(recv_sock);
-	if (offset != 0) {
-		ksft_perror("Offset not reverted correctly after flush\n");
-		goto out;
-	}
-
-	printf("%s with MSG_PEEK_OFF works correctly\n", afstr(af));
-	res = 1;
-out:
-	if (recv_sock >= 0)
-		close(recv_sock);
-	if (s[1] >= 0)
-		close(s[1]);
-	if (s[0] >= 0)
-		close(s[0]);
-	return res;
-}
-
-int main(void)
-{
-	int res4, res6;
-
-	res4 = tcp_peek_offset_probe(AF_INET);
-	res6 = tcp_peek_offset_probe(AF_INET6);
-
-	if (!res4 && !res6)
-		return KSFT_SKIP;
-
-	if (res4)
-		res4 = tcp_peek_offset_test(AF_INET);
-
-	if (res6)
-		res6 = tcp_peek_offset_test(AF_INET6);
-
-	if (!res4 || !res6)
-		return KSFT_FAIL;
-
-	return KSFT_PASS;
-}
-- 
cgit v1.3-3-g829e


From bd2557a554a0d61c81ef0c1aee2c16d02e225770 Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Mon, 2 Sep 2024 10:39:06 -0700
Subject: eth: fbnic: Add ethtool support for fbnic

Add ethtool ops support and enable 'get_drvinfo' for fbnic. The driver
provides firmware version information while the driver name and bus
information is provided by ethtool_get_drvinfo().

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/meta/fbnic/Makefile        |  1 +
 drivers/net/ethernet/meta/fbnic/fbnic.h         |  3 +++
 drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c | 26 +++++++++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c      | 13 +++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_fw.h      |  6 +++---
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.c  |  2 ++
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.h  |  1 +
 7 files changed, 49 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c

diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile
index 9373b558fdc9..37cfc34a5118 100644
--- a/drivers/net/ethernet/meta/fbnic/Makefile
+++ b/drivers/net/ethernet/meta/fbnic/Makefile
@@ -8,6 +8,7 @@
 obj-$(CONFIG_FBNIC) += fbnic.o
 
 fbnic-y := fbnic_devlink.o \
+	   fbnic_ethtool.o \
 	   fbnic_fw.o \
 	   fbnic_irq.o \
 	   fbnic_mac.o \
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index ad2689bfd6cb..28d970f81bfc 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -132,6 +132,9 @@ void fbnic_free_irq(struct fbnic_dev *dev, int nr, void *data);
 void fbnic_free_irqs(struct fbnic_dev *fbd);
 int fbnic_alloc_irqs(struct fbnic_dev *fbd);
 
+void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
+				 const size_t str_sz);
+
 enum fbnic_boards {
 	fbnic_board_asic
 };
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
new file mode 100644
index 000000000000..7064dfc9f5b0
--- /dev/null
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -0,0 +1,26 @@
+#include <linux/ethtool.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+
+#include "fbnic.h"
+#include "fbnic_netdev.h"
+#include "fbnic_tlv.h"
+
+static void
+fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	fbnic_get_fw_ver_commit_str(fbd, drvinfo->fw_version,
+				    sizeof(drvinfo->fw_version));
+}
+
+static const struct ethtool_ops fbnic_ethtool_ops = {
+	.get_drvinfo		= fbnic_get_drvinfo,
+};
+
+void fbnic_set_ethtool_ops(struct net_device *dev)
+{
+	dev->ethtool_ops = &fbnic_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 0c6e1b4c119b..8f7a2a19ddf8 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -789,3 +789,16 @@ void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
 		count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
 	} while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
 }
+
+void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
+				 const size_t str_sz)
+{
+	struct fbnic_fw_ver *mgmt = &fbd->fw_cap.running.mgmt;
+	const char *delim = "";
+
+	if (mgmt->commit[0])
+		delim = "_";
+
+	fbnic_mk_full_fw_ver_str(mgmt->version, delim, mgmt->commit,
+				 fw_version, str_sz);
+}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index c65bca613665..221faf8c6756 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -53,10 +53,10 @@ int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership);
 int fbnic_fw_init_heartbeat(struct fbnic_dev *fbd, bool poll);
 void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd);
 
-#define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str)	\
+#define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str, _str_sz) \
 do {									\
 	const u32 __rev_id = _rev_id;					\
-	snprintf(_str, sizeof(_str), "%02lu.%02lu.%02lu-%03lu%s%s",	\
+	snprintf(_str, _str_sz, "%02lu.%02lu.%02lu-%03lu%s%s",	\
 		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_MAJOR, __rev_id),	\
 		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_MINOR, __rev_id),	\
 		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_PATCH, __rev_id),	\
@@ -65,7 +65,7 @@ do {									\
 } while (0)
 
 #define fbnic_mk_fw_ver_str(_rev_id, _str) \
-	fbnic_mk_full_fw_ver_str(_rev_id, "", "", _str)
+	fbnic_mk_full_fw_ver_str(_rev_id, "", "", _str, sizeof(_str))
 
 #define FW_HEARTBEAT_PERIOD		(10 * HZ)
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 571374361259..a400616a24d4 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -521,6 +521,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	netdev->netdev_ops = &fbnic_netdev_ops;
 	netdev->stat_ops = &fbnic_stat_ops;
 
+	fbnic_set_ethtool_ops(netdev);
+
 	fbn = netdev_priv(netdev);
 
 	fbn->netdev = netdev;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
index 60199e634468..6c27da09a612 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
@@ -58,6 +58,7 @@ int fbnic_netdev_register(struct net_device *netdev);
 void fbnic_netdev_unregister(struct net_device *netdev);
 void fbnic_reset_queues(struct fbnic_net *fbn,
 			unsigned int tx, unsigned int rx);
+void fbnic_set_ethtool_ops(struct net_device *dev);
 
 void __fbnic_set_rx_mode(struct net_device *netdev);
 void fbnic_clear_rx_mode(struct net_device *netdev);
-- 
cgit v1.3-3-g829e


From 4eb7f20bcf0614fef744af88a2ba3c1c8bfcf189 Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Mon, 2 Sep 2024 10:39:07 -0700
Subject: eth: fbnic: Add support to fetch group stats

Add support for group stats for mac. The fbnic_set_counter help preserve
the default values for counters which are not touched by the driver.

The 'reset' flag in 'get_eth_mac_stats' allows to choose between
resetting the counter to recent most value or fetching the aggregated
values of the counter.

The 'fbnic_stat_rd64' read 64b stats counters in an atomic fashion using
read-read-read approach. This allows to isolate cases where counter is
moving too fast making accuracy of the counter questionable.

Command: ethtool -S eth0 --groups eth-mac
Example Output:
eth-mac-FramesTransmittedOK: 421644
eth-mac-FramesReceivedOK: 3849708
eth-mac-FrameCheckSequenceErrors: 0
eth-mac-AlignmentErrors: 0
eth-mac-OctetsTransmittedOK: 64799060
eth-mac-FramesLostDueToIntMACXmitError: 0
eth-mac-OctetsReceivedOK: 5134513531
eth-mac-FramesLostDueToIntMACRcvError: 0
eth-mac-MulticastFramesXmittedOK: 568
eth-mac-BroadcastFramesXmittedOK: 454
eth-mac-MulticastFramesReceivedOK: 276106
eth-mac-BroadcastFramesReceivedOK: 26119
eth-mac-FrameTooLongErrors: 0

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/meta/fbnic/Makefile         |  1 +
 drivers/net/ethernet/meta/fbnic/fbnic.h          |  4 ++
 drivers/net/ethernet/meta/fbnic/fbnic_csr.h      | 37 ++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c  | 49 +++++++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c | 27 +++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h | 40 +++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_mac.c      | 50 ++++++++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_mac.h      |  3 ++
 8 files changed, 211 insertions(+)
 create mode 100644 drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
 create mode 100644 drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h

diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile
index 37cfc34a5118..ed4533a73c57 100644
--- a/drivers/net/ethernet/meta/fbnic/Makefile
+++ b/drivers/net/ethernet/meta/fbnic/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_FBNIC) += fbnic.o
 fbnic-y := fbnic_devlink.o \
 	   fbnic_ethtool.o \
 	   fbnic_fw.o \
+	   fbnic_hw_stats.o \
 	   fbnic_irq.o \
 	   fbnic_mac.o \
 	   fbnic_netdev.o \
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 28d970f81bfc..0f9e8d79461c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -11,6 +11,7 @@
 
 #include "fbnic_csr.h"
 #include "fbnic_fw.h"
+#include "fbnic_hw_stats.h"
 #include "fbnic_mac.h"
 #include "fbnic_rpc.h"
 
@@ -47,6 +48,9 @@ struct fbnic_dev {
 
 	/* Number of TCQs/RCQs available on hardware */
 	u16 max_num_queues;
+
+	/* Local copy of hardware statistics */
+	struct fbnic_hw_stats hw_stats;
 };
 
 /* Reserve entry 0 in the MSI-X "others" array until we have filled all
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index a64360de0552..21db509acbc1 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -660,6 +660,43 @@ enum {
 #define FBNIC_SIG_PCS_INTR_MASK		0x11816		/* 0x46058 */
 #define FBNIC_CSR_END_SIG		0x1184e /* CSR section delimiter */
 
+#define FBNIC_CSR_START_MAC_STAT	0x11a00
+#define FBNIC_MAC_STAT_RX_BYTE_COUNT_L	0x11a08		/* 0x46820 */
+#define FBNIC_MAC_STAT_RX_BYTE_COUNT_H	0x11a09		/* 0x46824 */
+#define FBNIC_MAC_STAT_RX_ALIGN_ERROR_L \
+					0x11a0a		/* 0x46828 */
+#define FBNIC_MAC_STAT_RX_ALIGN_ERROR_H \
+					0x11a0b		/* 0x4682c */
+#define FBNIC_MAC_STAT_RX_TOOLONG_L	0x11a0e		/* 0x46838 */
+#define FBNIC_MAC_STAT_RX_TOOLONG_H	0x11a0f		/* 0x4683c */
+#define FBNIC_MAC_STAT_RX_RECEIVED_OK_L	\
+					0x11a12		/* 0x46848 */
+#define FBNIC_MAC_STAT_RX_RECEIVED_OK_H	\
+					0x11a13		/* 0x4684c */
+#define FBNIC_MAC_STAT_RX_PACKET_BAD_FCS_L \
+					0x11a14		/* 0x46850 */
+#define FBNIC_MAC_STAT_RX_PACKET_BAD_FCS_H \
+					0x11a15		/* 0x46854 */
+#define FBNIC_MAC_STAT_RX_IFINERRORS_L	0x11a18		/* 0x46860 */
+#define FBNIC_MAC_STAT_RX_IFINERRORS_H	0x11a19		/* 0x46864 */
+#define FBNIC_MAC_STAT_RX_MULTICAST_L	0x11a1c		/* 0x46870 */
+#define FBNIC_MAC_STAT_RX_MULTICAST_H	0x11a1d		/* 0x46874 */
+#define FBNIC_MAC_STAT_RX_BROADCAST_L	0x11a1e		/* 0x46878 */
+#define FBNIC_MAC_STAT_RX_BROADCAST_H	0x11a1f		/* 0x4687c */
+#define FBNIC_MAC_STAT_TX_BYTE_COUNT_L	0x11a3e		/* 0x468f8 */
+#define FBNIC_MAC_STAT_TX_BYTE_COUNT_H	0x11a3f		/* 0x468fc */
+#define FBNIC_MAC_STAT_TX_TRANSMITTED_OK_L \
+					0x11a42		/* 0x46908 */
+#define FBNIC_MAC_STAT_TX_TRANSMITTED_OK_H \
+					0x11a43		/* 0x4690c */
+#define FBNIC_MAC_STAT_TX_IFOUTERRORS_L \
+					0x11a46		/* 0x46918 */
+#define FBNIC_MAC_STAT_TX_IFOUTERRORS_H \
+					0x11a47		/* 0x4691c */
+#define FBNIC_MAC_STAT_TX_MULTICAST_L	0x11a4a		/* 0x46928 */
+#define FBNIC_MAC_STAT_TX_MULTICAST_H	0x11a4b		/* 0x4692c */
+#define FBNIC_MAC_STAT_TX_BROADCAST_L	0x11a4c		/* 0x46930 */
+#define FBNIC_MAC_STAT_TX_BROADCAST_H	0x11a4d		/* 0x46934 */
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index 7064dfc9f5b0..5d980e178941 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -16,8 +16,57 @@ fbnic_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 				    sizeof(drvinfo->fw_version));
 }
 
+static void fbnic_set_counter(u64 *stat, struct fbnic_stat_counter *counter)
+{
+	if (counter->reported)
+		*stat = counter->value;
+}
+
+static void
+fbnic_get_eth_mac_stats(struct net_device *netdev,
+			struct ethtool_eth_mac_stats *eth_mac_stats)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_mac_stats *mac_stats;
+	struct fbnic_dev *fbd = fbn->fbd;
+	const struct fbnic_mac *mac;
+
+	mac_stats = &fbd->hw_stats.mac;
+	mac = fbd->mac;
+
+	mac->get_eth_mac_stats(fbd, false, &mac_stats->eth_mac);
+
+	fbnic_set_counter(&eth_mac_stats->FramesTransmittedOK,
+			  &mac_stats->eth_mac.FramesTransmittedOK);
+	fbnic_set_counter(&eth_mac_stats->FramesReceivedOK,
+			  &mac_stats->eth_mac.FramesReceivedOK);
+	fbnic_set_counter(&eth_mac_stats->FrameCheckSequenceErrors,
+			  &mac_stats->eth_mac.FrameCheckSequenceErrors);
+	fbnic_set_counter(&eth_mac_stats->AlignmentErrors,
+			  &mac_stats->eth_mac.AlignmentErrors);
+	fbnic_set_counter(&eth_mac_stats->OctetsTransmittedOK,
+			  &mac_stats->eth_mac.OctetsTransmittedOK);
+	fbnic_set_counter(&eth_mac_stats->FramesLostDueToIntMACXmitError,
+			  &mac_stats->eth_mac.FramesLostDueToIntMACXmitError);
+	fbnic_set_counter(&eth_mac_stats->OctetsReceivedOK,
+			  &mac_stats->eth_mac.OctetsReceivedOK);
+	fbnic_set_counter(&eth_mac_stats->FramesLostDueToIntMACRcvError,
+			  &mac_stats->eth_mac.FramesLostDueToIntMACRcvError);
+	fbnic_set_counter(&eth_mac_stats->MulticastFramesXmittedOK,
+			  &mac_stats->eth_mac.MulticastFramesXmittedOK);
+	fbnic_set_counter(&eth_mac_stats->BroadcastFramesXmittedOK,
+			  &mac_stats->eth_mac.BroadcastFramesXmittedOK);
+	fbnic_set_counter(&eth_mac_stats->MulticastFramesReceivedOK,
+			  &mac_stats->eth_mac.MulticastFramesReceivedOK);
+	fbnic_set_counter(&eth_mac_stats->BroadcastFramesReceivedOK,
+			  &mac_stats->eth_mac.BroadcastFramesReceivedOK);
+	fbnic_set_counter(&eth_mac_stats->FrameTooLongErrors,
+			  &mac_stats->eth_mac.FrameTooLongErrors);
+}
+
 static const struct ethtool_ops fbnic_ethtool_ops = {
 	.get_drvinfo		= fbnic_get_drvinfo,
+	.get_eth_mac_stats	= fbnic_get_eth_mac_stats,
 };
 
 void fbnic_set_ethtool_ops(struct net_device *dev)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
new file mode 100644
index 000000000000..a0acc7606aa1
--- /dev/null
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c
@@ -0,0 +1,27 @@
+#include "fbnic.h"
+
+u64 fbnic_stat_rd64(struct fbnic_dev *fbd, u32 reg, u32 offset)
+{
+	u32 prev_upper, upper, lower, diff;
+
+	prev_upper = rd32(fbd, reg + offset);
+	lower = rd32(fbd, reg);
+	upper = rd32(fbd, reg + offset);
+
+	diff = upper - prev_upper;
+	if (!diff)
+		return ((u64)upper << 32) | lower;
+
+	if (diff > 1)
+		dev_warn_once(fbd->dev,
+			      "Stats inconsistent, upper 32b of %#010x updating too quickly\n",
+			      reg * 4);
+
+	/* Return only the upper bits as we cannot guarantee
+	 * the accuracy of the lower bits. We will add them in
+	 * when the counter slows down enough that we can get
+	 * a snapshot with both upper values being the same
+	 * between reads.
+	 */
+	return ((u64)upper << 32);
+}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
new file mode 100644
index 000000000000..30348904b510
--- /dev/null
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h
@@ -0,0 +1,40 @@
+#include <linux/ethtool.h>
+
+#include "fbnic_csr.h"
+
+struct fbnic_stat_counter {
+	u64 value;
+	union {
+		u32 old_reg_value_32;
+		u64 old_reg_value_64;
+	} u;
+	bool reported;
+};
+
+struct fbnic_eth_mac_stats {
+	struct fbnic_stat_counter FramesTransmittedOK;
+	struct fbnic_stat_counter FramesReceivedOK;
+	struct fbnic_stat_counter FrameCheckSequenceErrors;
+	struct fbnic_stat_counter AlignmentErrors;
+	struct fbnic_stat_counter OctetsTransmittedOK;
+	struct fbnic_stat_counter FramesLostDueToIntMACXmitError;
+	struct fbnic_stat_counter OctetsReceivedOK;
+	struct fbnic_stat_counter FramesLostDueToIntMACRcvError;
+	struct fbnic_stat_counter MulticastFramesXmittedOK;
+	struct fbnic_stat_counter BroadcastFramesXmittedOK;
+	struct fbnic_stat_counter MulticastFramesReceivedOK;
+	struct fbnic_stat_counter BroadcastFramesReceivedOK;
+	struct fbnic_stat_counter FrameTooLongErrors;
+};
+
+struct fbnic_mac_stats {
+	struct fbnic_eth_mac_stats eth_mac;
+};
+
+struct fbnic_hw_stats {
+	struct fbnic_mac_stats mac;
+};
+
+u64 fbnic_stat_rd64(struct fbnic_dev *fbd, u32 reg, u32 offset);
+
+void fbnic_get_hw_stats(struct fbnic_dev *fbd);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 7920e7af82d9..7b654d0a6dac 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -403,6 +403,21 @@ static void fbnic_mac_init_regs(struct fbnic_dev *fbd)
 	fbnic_mac_init_txb(fbd);
 }
 
+static void __fbnic_mac_stat_rd64(struct fbnic_dev *fbd, bool reset, u32 reg,
+				  struct fbnic_stat_counter *stat)
+{
+	u64 new_reg_value;
+
+	new_reg_value = fbnic_stat_rd64(fbd, reg, 1);
+	if (!reset)
+		stat->value += new_reg_value - stat->u.old_reg_value_64;
+	stat->u.old_reg_value_64 = new_reg_value;
+	stat->reported = true;
+}
+
+#define fbnic_mac_stat_rd64(fbd, reset, __stat, __CSR) \
+	__fbnic_mac_stat_rd64(fbd, reset, FBNIC_##__CSR##_L, &(__stat))
+
 static void fbnic_mac_tx_pause_config(struct fbnic_dev *fbd, bool tx_pause)
 {
 	u32 rxb_pause_ctrl;
@@ -637,12 +652,47 @@ static void fbnic_mac_link_up_asic(struct fbnic_dev *fbd,
 	wr32(fbd, FBNIC_MAC_COMMAND_CONFIG, cmd_cfg);
 }
 
+static void
+fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset,
+			    struct fbnic_eth_mac_stats *mac_stats)
+{
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->OctetsReceivedOK,
+			    MAC_STAT_RX_BYTE_COUNT);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->AlignmentErrors,
+			    MAC_STAT_RX_ALIGN_ERROR);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->FrameTooLongErrors,
+			    MAC_STAT_RX_TOOLONG);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->FramesReceivedOK,
+			    MAC_STAT_RX_RECEIVED_OK);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->FrameCheckSequenceErrors,
+			    MAC_STAT_RX_PACKET_BAD_FCS);
+	fbnic_mac_stat_rd64(fbd, reset,
+			    mac_stats->FramesLostDueToIntMACRcvError,
+			    MAC_STAT_RX_IFINERRORS);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->MulticastFramesReceivedOK,
+			    MAC_STAT_RX_MULTICAST);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->BroadcastFramesReceivedOK,
+			    MAC_STAT_RX_BROADCAST);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->OctetsTransmittedOK,
+			    MAC_STAT_TX_BYTE_COUNT);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->FramesTransmittedOK,
+			    MAC_STAT_TX_TRANSMITTED_OK);
+	fbnic_mac_stat_rd64(fbd, reset,
+			    mac_stats->FramesLostDueToIntMACXmitError,
+			    MAC_STAT_TX_IFOUTERRORS);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->MulticastFramesXmittedOK,
+			    MAC_STAT_TX_MULTICAST);
+	fbnic_mac_stat_rd64(fbd, reset, mac_stats->BroadcastFramesXmittedOK,
+			    MAC_STAT_TX_BROADCAST);
+}
+
 static const struct fbnic_mac fbnic_mac_asic = {
 	.init_regs = fbnic_mac_init_regs,
 	.pcs_enable = fbnic_pcs_enable_asic,
 	.pcs_disable = fbnic_pcs_disable_asic,
 	.pcs_get_link = fbnic_pcs_get_link_asic,
 	.pcs_get_link_event = fbnic_pcs_get_link_event_asic,
+	.get_eth_mac_stats = fbnic_mac_get_eth_mac_stats,
 	.link_down = fbnic_mac_link_down_asic,
 	.link_up = fbnic_mac_link_up_asic,
 };
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h
index f53be6e6aef9..476239a9d381 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h
@@ -78,6 +78,9 @@ struct fbnic_mac {
 	bool (*pcs_get_link)(struct fbnic_dev *fbd);
 	int (*pcs_get_link_event)(struct fbnic_dev *fbd);
 
+	void (*get_eth_mac_stats)(struct fbnic_dev *fbd, bool reset,
+				  struct fbnic_eth_mac_stats *mac_stats);
+
 	void (*link_down)(struct fbnic_dev *fbd);
 	void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause);
 };
-- 
cgit v1.3-3-g829e


From ff60bfbaf67f219c634cfe89a52250efe8e600d0 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 11 Oct 2023 16:02:32 +0200
Subject: can: rockchip_canfd: add driver for Rockchip CAN-FD controller

Add driver for the Rockchip CAN-FD controller.

The IP core on the rk3568v2 SoC has 12 documented errata. Corrections
for these errata will be added in the upcoming patches.

Since several workarounds are required for the TX path, only add the
base driver that only implements the RX path.

Although the RX path implements CAN-FD support, it's not activated in
ctrlmode_supported, as the IP core in the rk3568v2 has problems with
receiving or sending certain CAN-FD frames.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-4-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 MAINTAINERS                                        |   1 +
 drivers/net/can/Kconfig                            |   1 +
 drivers/net/can/Makefile                           |   1 +
 drivers/net/can/rockchip/Kconfig                   |   9 +
 drivers/net/can/rockchip/Makefile                  |   9 +
 drivers/net/can/rockchip/rockchip_canfd-core.c     | 868 +++++++++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd-rx.c       | 118 +++
 .../net/can/rockchip/rockchip_canfd-timestamp.c    |  15 +
 drivers/net/can/rockchip/rockchip_canfd-tx.c       |  12 +
 drivers/net/can/rockchip/rockchip_canfd.h          | 361 +++++++++
 10 files changed, 1395 insertions(+)
 create mode 100644 drivers/net/can/rockchip/Kconfig
 create mode 100644 drivers/net/can/rockchip/Makefile
 create mode 100644 drivers/net/can/rockchip/rockchip_canfd-core.c
 create mode 100644 drivers/net/can/rockchip/rockchip_canfd-rx.c
 create mode 100644 drivers/net/can/rockchip/rockchip_canfd-timestamp.c
 create mode 100644 drivers/net/can/rockchip/rockchip_canfd-tx.c
 create mode 100644 drivers/net/can/rockchip/rockchip_canfd.h

diff --git a/MAINTAINERS b/MAINTAINERS
index aa0e023955cf..47e8de644b58 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19736,6 +19736,7 @@ R:	kernel@pengutronix.de
 L:	linux-can@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/can/rockchip,rk3568v2-canfd.yaml
+F:	drivers/net/can/rockchip/
 
 ROCKCHIP CRYPTO DRIVERS
 M:	Corentin Labbe <clabbe@baylibre.com>
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 7f9b60a42d29..cf989bea9aa3 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -225,6 +225,7 @@ source "drivers/net/can/m_can/Kconfig"
 source "drivers/net/can/mscan/Kconfig"
 source "drivers/net/can/peak_canfd/Kconfig"
 source "drivers/net/can/rcar/Kconfig"
+source "drivers/net/can/rockchip/Kconfig"
 source "drivers/net/can/sja1000/Kconfig"
 source "drivers/net/can/softing/Kconfig"
 source "drivers/net/can/spi/Kconfig"
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index 4669cd51e7bf..a71db2cfe990 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_CAN_SLCAN)		+= slcan/
 obj-y				+= dev/
 obj-y				+= esd/
 obj-y				+= rcar/
+obj-y				+= rockchip/
 obj-y				+= spi/
 obj-y				+= usb/
 obj-y				+= softing/
diff --git a/drivers/net/can/rockchip/Kconfig b/drivers/net/can/rockchip/Kconfig
new file mode 100644
index 000000000000..e029e2a3ca4b
--- /dev/null
+++ b/drivers/net/can/rockchip/Kconfig
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config CAN_ROCKCHIP_CANFD
+	tristate "Rockchip CAN-FD controller"
+	depends on OF || COMPILE_TEST
+	select CAN_RX_OFFLOAD
+	help
+	  Say Y here if you want to use CAN-FD controller found on
+	  Rockchip SoCs.
diff --git a/drivers/net/can/rockchip/Makefile b/drivers/net/can/rockchip/Makefile
new file mode 100644
index 000000000000..4eb7c50d8d5b
--- /dev/null
+++ b/drivers/net/can/rockchip/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_CAN_ROCKCHIP_CANFD) += rockchip_canfd.o
+
+rockchip_canfd-objs :=
+rockchip_canfd-objs += rockchip_canfd-core.o
+rockchip_canfd-objs += rockchip_canfd-rx.o
+rockchip_canfd-objs += rockchip_canfd-timestamp.o
+rockchip_canfd-objs += rockchip_canfd-tx.o
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
new file mode 100644
index 000000000000..f1b2bad04bf4
--- /dev/null
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -0,0 +1,868 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2023, 2024 Pengutronix,
+//               Marc Kleine-Budde <kernel@pengutronix.de>
+//
+// Based on:
+//
+// Rockchip CANFD driver
+//
+// Copyright (c) 2020 Rockchip Electronics Co. Ltd.
+//
+
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/string.h>
+
+#include "rockchip_canfd.h"
+
+static const struct rkcanfd_devtype_data rkcanfd_devtype_data_rk3568v2 = {
+	.model = RKCANFD_MODEL_RK3568V2,
+};
+
+static const char *__rkcanfd_get_model_str(enum rkcanfd_model model)
+{
+	switch (model) {
+	case RKCANFD_MODEL_RK3568V2:
+		return "rk3568v2";
+	}
+
+	return "<unknown>";
+}
+
+static inline const char *
+rkcanfd_get_model_str(const struct rkcanfd_priv *priv)
+{
+	return __rkcanfd_get_model_str(priv->devtype_data.model);
+}
+
+/* Note:
+ *
+ * The formula to calculate the CAN System Clock is:
+ *
+ * Tsclk = 2 x Tclk x (brp + 1)
+ *
+ * Double the data sheet's brp_min, brp_max and brp_inc values (both
+ * for the arbitration and data bit timing) to take the "2 x" into
+ * account.
+ */
+static const struct can_bittiming_const rkcanfd_bittiming_const = {
+	.name = DEVICE_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 256,
+	.tseg2_min = 1,
+	.tseg2_max = 128,
+	.sjw_max = 128,
+	.brp_min = 2,	/* value from data sheet x2 */
+	.brp_max = 512,	/* value from data sheet x2 */
+	.brp_inc = 2,	/* value from data sheet x2 */
+};
+
+static const struct can_bittiming_const rkcanfd_data_bittiming_const = {
+	.name = DEVICE_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 32,
+	.tseg2_min = 1,
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 2,	/* value from data sheet x2 */
+	.brp_max = 512,	/* value from data sheet x2 */
+	.brp_inc = 2,	/* value from data sheet x2 */
+};
+
+static void rkcanfd_chip_set_reset_mode(const struct rkcanfd_priv *priv)
+{
+	reset_control_assert(priv->reset);
+	udelay(2);
+	reset_control_deassert(priv->reset);
+
+	rkcanfd_write(priv, RKCANFD_REG_MODE, 0x0);
+}
+
+static void rkcanfd_chip_set_work_mode(const struct rkcanfd_priv *priv)
+{
+	rkcanfd_write(priv, RKCANFD_REG_MODE, priv->reg_mode_default);
+}
+
+static int rkcanfd_set_bittiming(struct rkcanfd_priv *priv)
+{
+	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *bt = &priv->can.bittiming;
+	u32 reg_nbt, reg_dbt, reg_tdc;
+	u32 tdco;
+
+	reg_nbt = FIELD_PREP(RKCANFD_REG_FD_NOMINAL_BITTIMING_SJW,
+			     bt->sjw - 1) |
+		FIELD_PREP(RKCANFD_REG_FD_NOMINAL_BITTIMING_BRP,
+			   (bt->brp / 2) - 1) |
+		FIELD_PREP(RKCANFD_REG_FD_NOMINAL_BITTIMING_TSEG2,
+			   bt->phase_seg2 - 1) |
+		FIELD_PREP(RKCANFD_REG_FD_NOMINAL_BITTIMING_TSEG1,
+			   bt->prop_seg + bt->phase_seg1 - 1);
+
+	rkcanfd_write(priv, RKCANFD_REG_FD_NOMINAL_BITTIMING, reg_nbt);
+
+	if (!(priv->can.ctrlmode & CAN_CTRLMODE_FD))
+		return 0;
+
+	reg_dbt = FIELD_PREP(RKCANFD_REG_FD_DATA_BITTIMING_SJW,
+			     dbt->sjw - 1) |
+		FIELD_PREP(RKCANFD_REG_FD_DATA_BITTIMING_BRP,
+			   (dbt->brp / 2) - 1) |
+		FIELD_PREP(RKCANFD_REG_FD_DATA_BITTIMING_TSEG2,
+			   dbt->phase_seg2 - 1) |
+		FIELD_PREP(RKCANFD_REG_FD_DATA_BITTIMING_TSEG1,
+			   dbt->prop_seg + dbt->phase_seg1 - 1);
+
+	rkcanfd_write(priv, RKCANFD_REG_FD_DATA_BITTIMING, reg_dbt);
+
+	tdco = (priv->can.clock.freq / dbt->bitrate) * 2 / 3;
+	tdco = min(tdco, FIELD_MAX(RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION_TDC_OFFSET));
+
+	reg_tdc = FIELD_PREP(RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION_TDC_OFFSET, tdco) |
+		RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION_TDC_ENABLE;
+	rkcanfd_write(priv, RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION,
+		      reg_tdc);
+
+	return 0;
+}
+
+static void rkcanfd_get_berr_counter_raw(struct rkcanfd_priv *priv,
+					 struct can_berr_counter *bec)
+{
+	bec->rxerr = rkcanfd_read(priv, RKCANFD_REG_RXERRORCNT);
+	bec->txerr = rkcanfd_read(priv, RKCANFD_REG_TXERRORCNT);
+}
+
+static int rkcanfd_get_berr_counter(const struct net_device *ndev,
+				    struct can_berr_counter *bec)
+{
+	struct rkcanfd_priv *priv = netdev_priv(ndev);
+	int err;
+
+	err = pm_runtime_resume_and_get(ndev->dev.parent);
+	if (err)
+		return err;
+
+	rkcanfd_get_berr_counter_raw(priv, bec);
+
+	pm_runtime_put(ndev->dev.parent);
+
+	return 0;
+}
+
+static void rkcanfd_chip_interrupts_enable(const struct rkcanfd_priv *priv)
+{
+	rkcanfd_write(priv, RKCANFD_REG_INT_MASK, priv->reg_int_mask_default);
+
+	netdev_dbg(priv->ndev, "%s: reg_int_mask=0x%08x\n", __func__,
+		   rkcanfd_read(priv, RKCANFD_REG_INT_MASK));
+}
+
+static void rkcanfd_chip_interrupts_disable(const struct rkcanfd_priv *priv)
+{
+	rkcanfd_write(priv, RKCANFD_REG_INT_MASK, RKCANFD_REG_INT_ALL);
+}
+
+static void rkcanfd_chip_fifo_setup(struct rkcanfd_priv *priv)
+{
+	u32 reg;
+
+	/* TXE FIFO */
+	reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
+	reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE;
+	rkcanfd_write(priv, RKCANFD_REG_RX_FIFO_CTRL, reg);
+
+	/* RX FIFO */
+	reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
+	reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE;
+	rkcanfd_write(priv, RKCANFD_REG_RX_FIFO_CTRL, reg);
+
+	WRITE_ONCE(priv->tx_head, 0);
+	WRITE_ONCE(priv->tx_tail, 0);
+	netdev_reset_queue(priv->ndev);
+}
+
+static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
+{
+	u32 reg;
+
+	rkcanfd_chip_set_reset_mode(priv);
+
+	/* Receiving Filter: accept all */
+	rkcanfd_write(priv, RKCANFD_REG_IDCODE, 0x0);
+	rkcanfd_write(priv, RKCANFD_REG_IDMASK, RKCANFD_REG_IDCODE_EXTENDED_FRAME_ID);
+
+	/* enable:
+	 * - CAN_FD: enable CAN-FD
+	 * - AUTO_RETX_MODE: auto retransmission on TX error
+	 * - COVER_MODE: RX-FIFO overwrite mode, do not send OVERLOAD frames
+	 * - WORK_MODE: transition from reset to working mode
+	 */
+	reg = rkcanfd_read(priv, RKCANFD_REG_MODE);
+	priv->reg_mode_default = reg |
+		RKCANFD_REG_MODE_CAN_FD_MODE_ENABLE |
+		RKCANFD_REG_MODE_AUTO_RETX_MODE |
+		RKCANFD_REG_MODE_COVER_MODE |
+		RKCANFD_REG_MODE_WORK_MODE;
+
+	/* mask, i.e. ignore:
+	 * - TIMESTAMP_COUNTER_OVERFLOW_INT - timestamp counter overflow interrupt
+	 * - TX_ARBIT_FAIL_INT - TX arbitration fail interrupt
+	 * - OVERLOAD_INT - CAN bus overload interrupt
+	 */
+	priv->reg_int_mask_default =
+		RKCANFD_REG_INT_TIMESTAMP_COUNTER_OVERFLOW_INT |
+		RKCANFD_REG_INT_TX_ARBIT_FAIL_INT |
+		RKCANFD_REG_INT_OVERLOAD_INT;
+
+	rkcanfd_chip_fifo_setup(priv);
+	rkcanfd_timestamp_init(priv);
+	rkcanfd_set_bittiming(priv);
+
+	rkcanfd_chip_interrupts_disable(priv);
+	rkcanfd_chip_set_work_mode(priv);
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	netdev_dbg(priv->ndev, "%s: reg_mode=0x%08x\n", __func__,
+		   rkcanfd_read(priv, RKCANFD_REG_MODE));
+}
+
+static void __rkcanfd_chip_stop(struct rkcanfd_priv *priv, const enum can_state state)
+{
+	priv->can.state = state;
+
+	rkcanfd_chip_set_reset_mode(priv);
+	rkcanfd_chip_interrupts_disable(priv);
+}
+
+static void rkcanfd_chip_stop(struct rkcanfd_priv *priv, const enum can_state state)
+{
+	priv->can.state = state;
+
+	__rkcanfd_chip_stop(priv, state);
+}
+
+static void rkcanfd_chip_stop_sync(struct rkcanfd_priv *priv, const enum can_state state)
+{
+	priv->can.state = state;
+
+	__rkcanfd_chip_stop(priv, state);
+}
+
+static int rkcanfd_set_mode(struct net_device *ndev,
+			    enum can_mode mode)
+{
+	struct rkcanfd_priv *priv = netdev_priv(ndev);
+
+	switch (mode) {
+	case CAN_MODE_START:
+		rkcanfd_chip_start(priv);
+		rkcanfd_chip_interrupts_enable(priv);
+		netif_wake_queue(ndev);
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static struct sk_buff *
+rkcanfd_alloc_can_err_skb(struct rkcanfd_priv *priv,
+			  struct can_frame **cf, u32 *timestamp)
+{
+	struct sk_buff *skb;
+
+	*timestamp = rkcanfd_get_timestamp(priv);
+
+	skb = alloc_can_err_skb(priv->ndev, cf);
+
+	return skb;
+}
+
+static const char *rkcanfd_get_error_type_str(unsigned int type)
+{
+	switch (type) {
+	case RKCANFD_REG_ERROR_CODE_TYPE_BIT:
+		return "Bit";
+	case RKCANFD_REG_ERROR_CODE_TYPE_STUFF:
+		return "Stuff";
+	case RKCANFD_REG_ERROR_CODE_TYPE_FORM:
+		return "Form";
+	case RKCANFD_REG_ERROR_CODE_TYPE_ACK:
+		return "ACK";
+	case RKCANFD_REG_ERROR_CODE_TYPE_CRC:
+		return "CRC";
+	}
+
+	return "<unknown>";
+}
+
+#define RKCAN_ERROR_CODE(reg_ec, code) \
+	((reg_ec) & RKCANFD_REG_ERROR_CODE_##code ? __stringify(code) " " : "")
+
+static void
+rkcanfd_handle_error_int_reg_ec(struct rkcanfd_priv *priv, struct can_frame *cf,
+				const u32 reg_ec)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	unsigned int type;
+	u32 reg_state, reg_cmd;
+
+	type = FIELD_GET(RKCANFD_REG_ERROR_CODE_TYPE, reg_ec);
+	reg_cmd = rkcanfd_read(priv, RKCANFD_REG_CMD);
+	reg_state = rkcanfd_read(priv, RKCANFD_REG_STATE);
+
+	netdev_dbg(priv->ndev, "%s Error in %s %s Phase: %s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s(0x%08x) CMD=%u RX=%u TX=%u Error-Warning=%u Bus-Off=%u\n",
+		   rkcanfd_get_error_type_str(type),
+		   reg_ec & RKCANFD_REG_ERROR_CODE_DIRECTION_RX ? "RX" : "TX",
+		   reg_ec & RKCANFD_REG_ERROR_CODE_PHASE ? "Data" : "Arbitration",
+		   RKCAN_ERROR_CODE(reg_ec, TX_OVERLOAD),
+		   RKCAN_ERROR_CODE(reg_ec, TX_ERROR),
+		   RKCAN_ERROR_CODE(reg_ec, TX_ACK),
+		   RKCAN_ERROR_CODE(reg_ec, TX_ACK_EOF),
+		   RKCAN_ERROR_CODE(reg_ec, TX_CRC),
+		   RKCAN_ERROR_CODE(reg_ec, TX_STUFF_COUNT),
+		   RKCAN_ERROR_CODE(reg_ec, TX_DATA),
+		   RKCAN_ERROR_CODE(reg_ec, TX_SOF_DLC),
+		   RKCAN_ERROR_CODE(reg_ec, TX_IDLE),
+		   RKCAN_ERROR_CODE(reg_ec, RX_BUF_INT),
+		   RKCAN_ERROR_CODE(reg_ec, RX_SPACE),
+		   RKCAN_ERROR_CODE(reg_ec, RX_EOF),
+		   RKCAN_ERROR_CODE(reg_ec, RX_ACK_LIM),
+		   RKCAN_ERROR_CODE(reg_ec, RX_ACK),
+		   RKCAN_ERROR_CODE(reg_ec, RX_CRC_LIM),
+		   RKCAN_ERROR_CODE(reg_ec, RX_CRC),
+		   RKCAN_ERROR_CODE(reg_ec, RX_STUFF_COUNT),
+		   RKCAN_ERROR_CODE(reg_ec, RX_DATA),
+		   RKCAN_ERROR_CODE(reg_ec, RX_DLC),
+		   RKCAN_ERROR_CODE(reg_ec, RX_BRS_ESI),
+		   RKCAN_ERROR_CODE(reg_ec, RX_RES),
+		   RKCAN_ERROR_CODE(reg_ec, RX_FDF),
+		   RKCAN_ERROR_CODE(reg_ec, RX_ID2_RTR),
+		   RKCAN_ERROR_CODE(reg_ec, RX_SOF_IDE),
+		   RKCAN_ERROR_CODE(reg_ec, RX_IDLE),
+		   reg_ec, reg_cmd,
+		   !!(reg_state & RKCANFD_REG_STATE_RX_PERIOD),
+		   !!(reg_state & RKCANFD_REG_STATE_TX_PERIOD),
+		   !!(reg_state & RKCANFD_REG_STATE_ERROR_WARNING_STATE),
+		   !!(reg_state & RKCANFD_REG_STATE_BUS_OFF_STATE));
+
+	priv->can.can_stats.bus_error++;
+
+	if (reg_ec & RKCANFD_REG_ERROR_CODE_DIRECTION_RX)
+		stats->rx_errors++;
+	else
+		stats->tx_errors++;
+
+	if (!cf)
+		return;
+
+	if (reg_ec & RKCANFD_REG_ERROR_CODE_DIRECTION_RX) {
+		if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_SOF_IDE)
+			cf->data[3] = CAN_ERR_PROT_LOC_SOF;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_ID2_RTR)
+			cf->data[3] = CAN_ERR_PROT_LOC_RTR;
+		/* RKCANFD_REG_ERROR_CODE_RX_FDF */
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_RES)
+			cf->data[3] = CAN_ERR_PROT_LOC_RES0;
+		/* RKCANFD_REG_ERROR_CODE_RX_BRS_ESI */
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_DLC)
+			cf->data[3] = CAN_ERR_PROT_LOC_DLC;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_DATA)
+			cf->data[3] = CAN_ERR_PROT_LOC_DATA;
+		/* RKCANFD_REG_ERROR_CODE_RX_STUFF_COUNT */
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_CRC)
+			cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_CRC_LIM)
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_ACK)
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_ACK_LIM)
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_EOF)
+			cf->data[3] = CAN_ERR_PROT_LOC_EOF;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_SPACE)
+			cf->data[3] = CAN_ERR_PROT_LOC_EOF;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_RX_BUF_INT)
+			cf->data[3] = CAN_ERR_PROT_LOC_INTERM;
+	} else {
+		cf->data[2] |= CAN_ERR_PROT_TX;
+
+		if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_SOF_DLC)
+			cf->data[3] = CAN_ERR_PROT_LOC_SOF;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_DATA)
+			cf->data[3] = CAN_ERR_PROT_LOC_DATA;
+		/* RKCANFD_REG_ERROR_CODE_TX_STUFF_COUNT */
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_CRC)
+			cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_ACK_EOF)
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_ACK)
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_ACK_EOF)
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
+		/* RKCANFD_REG_ERROR_CODE_TX_ERROR */
+		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_OVERLOAD)
+			cf->data[2] |= CAN_ERR_PROT_OVERLOAD;
+	}
+
+	switch (reg_ec & RKCANFD_REG_ERROR_CODE_TYPE) {
+	case FIELD_PREP_CONST(RKCANFD_REG_ERROR_CODE_TYPE,
+			      RKCANFD_REG_ERROR_CODE_TYPE_BIT):
+
+		cf->data[2] |= CAN_ERR_PROT_BIT;
+		break;
+	case FIELD_PREP_CONST(RKCANFD_REG_ERROR_CODE_TYPE,
+			      RKCANFD_REG_ERROR_CODE_TYPE_STUFF):
+		cf->data[2] |= CAN_ERR_PROT_STUFF;
+		break;
+	case FIELD_PREP_CONST(RKCANFD_REG_ERROR_CODE_TYPE,
+			      RKCANFD_REG_ERROR_CODE_TYPE_FORM):
+		cf->data[2] |= CAN_ERR_PROT_FORM;
+		break;
+	case FIELD_PREP_CONST(RKCANFD_REG_ERROR_CODE_TYPE,
+			      RKCANFD_REG_ERROR_CODE_TYPE_ACK):
+		cf->can_id |= CAN_ERR_ACK;
+		break;
+	case FIELD_PREP_CONST(RKCANFD_REG_ERROR_CODE_TYPE,
+			      RKCANFD_REG_ERROR_CODE_TYPE_CRC):
+		cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
+		break;
+	}
+}
+
+static int rkcanfd_handle_error_int(struct rkcanfd_priv *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct can_frame *cf = NULL;
+	u32 reg_ec, timestamp;
+	struct sk_buff *skb;
+	int err;
+
+	reg_ec = rkcanfd_read(priv, RKCANFD_REG_ERROR_CODE);
+
+	if (!reg_ec)
+		return 0;
+
+	skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
+	if (cf) {
+		struct can_berr_counter bec;
+
+		rkcanfd_get_berr_counter_raw(priv, &bec);
+		cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR | CAN_ERR_CNT;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+	}
+
+	rkcanfd_handle_error_int_reg_ec(priv, cf, reg_ec);
+
+	if (!cf)
+		return 0;
+
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
+	if (err)
+		stats->rx_fifo_errors++;
+
+	return 0;
+}
+
+static int rkcanfd_handle_state_error_int(struct rkcanfd_priv *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	enum can_state new_state, rx_state, tx_state;
+	struct net_device *ndev = priv->ndev;
+	struct can_berr_counter bec;
+	struct can_frame *cf = NULL;
+	struct sk_buff *skb;
+	u32 timestamp;
+	int err;
+
+	rkcanfd_get_berr_counter_raw(priv, &bec);
+	can_state_get_by_berr_counter(ndev, &bec, &tx_state, &rx_state);
+
+	new_state = max(tx_state, rx_state);
+	if (new_state == priv->can.state)
+		return 0;
+
+	/* The skb allocation might fail, but can_change_state()
+	 * handles cf == NULL.
+	 */
+	skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
+	can_change_state(ndev, cf, tx_state, rx_state);
+
+	if (new_state == CAN_STATE_BUS_OFF) {
+		rkcanfd_chip_stop(priv, CAN_STATE_BUS_OFF);
+		can_bus_off(ndev);
+	}
+
+	if (!skb)
+		return 0;
+
+	if (new_state != CAN_STATE_BUS_OFF) {
+		cf->can_id |= CAN_ERR_CNT;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+	}
+
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
+	if (err)
+		stats->rx_fifo_errors++;
+
+	return 0;
+}
+
+static int
+rkcanfd_handle_rx_fifo_overflow_int(struct rkcanfd_priv *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct can_berr_counter bec;
+	struct can_frame *cf = NULL;
+	struct sk_buff *skb;
+	u32 timestamp;
+	int err;
+
+	stats->rx_over_errors++;
+	stats->rx_errors++;
+
+	netdev_dbg(priv->ndev, "RX-FIFO overflow\n");
+
+	skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
+	if (skb)
+		return 0;
+
+	rkcanfd_get_berr_counter_raw(priv, &bec);
+
+	cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT;
+	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+	cf->data[6] = bec.txerr;
+	cf->data[7] = bec.rxerr;
+
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
+	if (err)
+		stats->rx_fifo_errors++;
+
+	return 0;
+}
+
+#define rkcanfd_handle(priv, irq, ...) \
+({ \
+	struct rkcanfd_priv *_priv = (priv); \
+	int err; \
+\
+	err = rkcanfd_handle_##irq(_priv, ## __VA_ARGS__); \
+	if (err) \
+		netdev_err(_priv->ndev, \
+			"IRQ handler rkcanfd_handle_%s() returned error: %pe\n", \
+			   __stringify(irq), ERR_PTR(err)); \
+	err; \
+})
+
+static irqreturn_t rkcanfd_irq(int irq, void *dev_id)
+{
+	struct rkcanfd_priv *priv = dev_id;
+	u32 reg_int_unmasked, reg_int;
+
+	reg_int_unmasked = rkcanfd_read(priv, RKCANFD_REG_INT);
+	reg_int = reg_int_unmasked & ~priv->reg_int_mask_default;
+
+	if (!reg_int)
+		return IRQ_NONE;
+
+	/* First ACK then handle, to avoid lost-IRQ race condition on
+	 * fast re-occurring interrupts.
+	 */
+	rkcanfd_write(priv, RKCANFD_REG_INT, reg_int);
+
+	if (reg_int & RKCANFD_REG_INT_RX_FINISH_INT)
+		rkcanfd_handle(priv, rx_int);
+
+	if (reg_int & RKCANFD_REG_INT_ERROR_INT)
+		rkcanfd_handle(priv, error_int);
+
+	if (reg_int & (RKCANFD_REG_INT_BUS_OFF_INT |
+		       RKCANFD_REG_INT_PASSIVE_ERROR_INT |
+		       RKCANFD_REG_INT_ERROR_WARNING_INT) ||
+	    priv->can.state > CAN_STATE_ERROR_ACTIVE)
+		rkcanfd_handle(priv, state_error_int);
+
+	if (reg_int & RKCANFD_REG_INT_RX_FIFO_OVERFLOW_INT)
+		rkcanfd_handle(priv, rx_fifo_overflow_int);
+
+	if (reg_int & ~(RKCANFD_REG_INT_ALL_ERROR |
+			RKCANFD_REG_INT_RX_FIFO_OVERFLOW_INT |
+			RKCANFD_REG_INT_RX_FINISH_INT))
+		netdev_err(priv->ndev, "%s: int=0x%08x\n", __func__, reg_int);
+
+	if (reg_int & RKCANFD_REG_INT_WAKEUP_INT)
+		netdev_info(priv->ndev, "%s: WAKEUP_INT\n", __func__);
+
+	if (reg_int & RKCANFD_REG_INT_TXE_FIFO_FULL_INT)
+		netdev_info(priv->ndev, "%s: TXE_FIFO_FULL_INT\n", __func__);
+
+	if (reg_int & RKCANFD_REG_INT_TXE_FIFO_OV_INT)
+		netdev_info(priv->ndev, "%s: TXE_FIFO_OV_INT\n", __func__);
+
+	if (reg_int & RKCANFD_REG_INT_BUS_OFF_RECOVERY_INT)
+		netdev_info(priv->ndev, "%s: BUS_OFF_RECOVERY_INT\n", __func__);
+
+	if (reg_int & RKCANFD_REG_INT_RX_FIFO_FULL_INT)
+		netdev_info(priv->ndev, "%s: RX_FIFO_FULL_INT\n", __func__);
+
+	if (reg_int & RKCANFD_REG_INT_OVERLOAD_INT)
+		netdev_info(priv->ndev, "%s: OVERLOAD_INT\n", __func__);
+
+	can_rx_offload_irq_finish(&priv->offload);
+
+	return IRQ_HANDLED;
+}
+
+static int rkcanfd_open(struct net_device *ndev)
+{
+	struct rkcanfd_priv *priv = netdev_priv(ndev);
+	int err;
+
+	err = open_candev(ndev);
+	if (err)
+		return err;
+
+	err = pm_runtime_resume_and_get(ndev->dev.parent);
+	if (err)
+		goto out_close_candev;
+
+	rkcanfd_chip_start(priv);
+	can_rx_offload_enable(&priv->offload);
+
+	err = request_irq(ndev->irq, rkcanfd_irq, IRQF_SHARED, ndev->name, priv);
+	if (err)
+		goto out_rkcanfd_chip_stop;
+
+	rkcanfd_chip_interrupts_enable(priv);
+
+	netif_start_queue(ndev);
+
+	return 0;
+
+out_rkcanfd_chip_stop:
+	rkcanfd_chip_stop_sync(priv, CAN_STATE_STOPPED);
+	pm_runtime_put(ndev->dev.parent);
+out_close_candev:
+	close_candev(ndev);
+	return err;
+}
+
+static int rkcanfd_stop(struct net_device *ndev)
+{
+	struct rkcanfd_priv *priv = netdev_priv(ndev);
+
+	netif_stop_queue(ndev);
+
+	rkcanfd_chip_interrupts_disable(priv);
+	free_irq(ndev->irq, priv);
+	can_rx_offload_disable(&priv->offload);
+	rkcanfd_chip_stop_sync(priv, CAN_STATE_STOPPED);
+	close_candev(ndev);
+
+	pm_runtime_put(ndev->dev.parent);
+
+	return 0;
+}
+
+static const struct net_device_ops rkcanfd_netdev_ops = {
+	.ndo_open = rkcanfd_open,
+	.ndo_stop = rkcanfd_stop,
+	.ndo_start_xmit = rkcanfd_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+static int __maybe_unused rkcanfd_runtime_suspend(struct device *dev)
+{
+	struct rkcanfd_priv *priv = dev_get_drvdata(dev);
+
+	clk_bulk_disable_unprepare(priv->clks_num, priv->clks);
+
+	return 0;
+}
+
+static int __maybe_unused rkcanfd_runtime_resume(struct device *dev)
+{
+	struct rkcanfd_priv *priv = dev_get_drvdata(dev);
+
+	return clk_bulk_prepare_enable(priv->clks_num, priv->clks);
+}
+
+static void rkcanfd_register_done(const struct rkcanfd_priv *priv)
+{
+	u32 dev_id;
+
+	dev_id = rkcanfd_read(priv, RKCANFD_REG_RTL_VERSION);
+
+	netdev_info(priv->ndev,
+		    "Rockchip-CANFD %s rev%lu.%lu found\n",
+		    rkcanfd_get_model_str(priv),
+		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MAJOR, dev_id),
+		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MINOR, dev_id));
+}
+
+static int rkcanfd_register(struct rkcanfd_priv *priv)
+{
+	struct net_device *ndev = priv->ndev;
+	int err;
+
+	pm_runtime_enable(ndev->dev.parent);
+
+	err = pm_runtime_resume_and_get(ndev->dev.parent);
+	if (err)
+		goto out_pm_runtime_disable;
+
+	err = register_candev(ndev);
+	if (err)
+		goto out_pm_runtime_put_sync;
+
+	rkcanfd_register_done(priv);
+
+	pm_runtime_put(ndev->dev.parent);
+
+	return 0;
+
+out_pm_runtime_put_sync:
+	pm_runtime_put_sync(ndev->dev.parent);
+out_pm_runtime_disable:
+	pm_runtime_disable(ndev->dev.parent);
+
+	return err;
+}
+
+static inline void rkcanfd_unregister(struct rkcanfd_priv *priv)
+{
+	struct net_device *ndev	= priv->ndev;
+
+	unregister_candev(ndev);
+	pm_runtime_disable(ndev->dev.parent);
+}
+
+static const struct of_device_id rkcanfd_of_match[] = {
+	{
+		.compatible = "rockchip,rk3568v2-canfd",
+		.data = &rkcanfd_devtype_data_rk3568v2,
+	}, {
+		/* sentinel */
+	},
+};
+MODULE_DEVICE_TABLE(of, rkcanfd_of_match);
+
+static int rkcanfd_probe(struct platform_device *pdev)
+{
+	struct rkcanfd_priv *priv;
+	struct net_device *ndev;
+	const void *match;
+	int err;
+
+	ndev = alloc_candev(sizeof(struct rkcanfd_priv), RKCANFD_TXFIFO_DEPTH);
+	if (!ndev)
+		return -ENOMEM;
+
+	priv = netdev_priv(ndev);
+
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq < 0) {
+		err = ndev->irq;
+		goto out_free_candev;
+	}
+
+	priv->clks_num = devm_clk_bulk_get_all(&pdev->dev, &priv->clks);
+	if (priv->clks_num < 0) {
+		err = priv->clks_num;
+		goto out_free_candev;
+	}
+
+	priv->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->regs)) {
+		err = PTR_ERR(priv->regs);
+		goto out_free_candev;
+	}
+
+	priv->reset = devm_reset_control_array_get_exclusive(&pdev->dev);
+	if (IS_ERR(priv->reset)) {
+		err = dev_err_probe(&pdev->dev, PTR_ERR(priv->reset),
+				    "Failed to get reset line\n");
+		goto out_free_candev;
+	}
+
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+
+	ndev->netdev_ops = &rkcanfd_netdev_ops;
+	ndev->flags |= IFF_ECHO;
+
+	platform_set_drvdata(pdev, priv);
+	priv->can.clock.freq = clk_get_rate(priv->clks[0].clk);
+	priv->can.bittiming_const = &rkcanfd_bittiming_const;
+	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
+	priv->can.ctrlmode_supported = 0;
+	priv->can.do_set_mode = rkcanfd_set_mode;
+	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
+	priv->ndev = ndev;
+
+	match = device_get_match_data(&pdev->dev);
+	if (match)
+		priv->devtype_data = *(struct rkcanfd_devtype_data *)match;
+
+	err = can_rx_offload_add_manual(ndev, &priv->offload,
+					RKCANFD_NAPI_WEIGHT);
+	if (err)
+		goto out_free_candev;
+
+	err = rkcanfd_register(priv);
+	if (err)
+		goto out_can_rx_offload_del;
+
+	return 0;
+
+out_can_rx_offload_del:
+	can_rx_offload_del(&priv->offload);
+out_free_candev:
+	free_candev(ndev);
+
+	return err;
+}
+
+static void rkcanfd_remove(struct platform_device *pdev)
+{
+	struct rkcanfd_priv *priv = platform_get_drvdata(pdev);
+	struct net_device *ndev = priv->ndev;
+
+	can_rx_offload_del(&priv->offload);
+	rkcanfd_unregister(priv);
+	free_candev(ndev);
+}
+
+static const struct dev_pm_ops rkcanfd_pm_ops = {
+	SET_RUNTIME_PM_OPS(rkcanfd_runtime_suspend,
+			   rkcanfd_runtime_resume, NULL)
+};
+
+static struct platform_driver rkcanfd_driver = {
+	.driver = {
+		.name = DEVICE_NAME,
+		.pm = &rkcanfd_pm_ops,
+		.of_match_table = rkcanfd_of_match,
+	},
+	.probe = rkcanfd_probe,
+	.remove = rkcanfd_remove,
+};
+module_platform_driver(rkcanfd_driver);
+
+MODULE_AUTHOR("Marc Kleine-Budde <mkl@pengutronix.de>");
+MODULE_DESCRIPTION("Rockchip CAN-FD Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
new file mode 100644
index 000000000000..5398aff0d180
--- /dev/null
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2023, 2024 Pengutronix,
+//               Marc Kleine-Budde <kernel@pengutronix.de>
+//
+
+#include "rockchip_canfd.h"
+
+static unsigned int
+rkcanfd_fifo_header_to_cfd_header(const struct rkcanfd_priv *priv,
+				  const struct rkcanfd_fifo_header *header,
+				  struct canfd_frame *cfd)
+{
+	unsigned int len = sizeof(*cfd) - sizeof(cfd->data);
+	u8 dlc;
+
+	if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_FRAME_FORMAT)
+		cfd->can_id = FIELD_GET(RKCANFD_REG_FD_ID_EFF, header->id) |
+			CAN_EFF_FLAG;
+	else
+		cfd->can_id = FIELD_GET(RKCANFD_REG_FD_ID_SFF, header->id);
+
+	dlc = FIELD_GET(RKCANFD_REG_FD_FRAMEINFO_DATA_LENGTH,
+			header->frameinfo);
+
+	/* CAN-FD */
+	if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_FDF) {
+		cfd->len = can_fd_dlc2len(dlc);
+
+		/* The cfd is not allocated by alloc_canfd_skb(), so
+		 * set CANFD_FDF here.
+		 */
+		cfd->flags |= CANFD_FDF;
+
+		if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_BRS)
+			cfd->flags |= CANFD_BRS;
+	} else {
+		cfd->len = can_cc_dlc2len(dlc);
+
+		if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_RTR) {
+			cfd->can_id |= CAN_RTR_FLAG;
+
+			return len;
+		}
+	}
+
+	return len + cfd->len;
+}
+
+static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	struct canfd_frame cfd[1] = { }, *skb_cfd;
+	struct rkcanfd_fifo_header header[1] = { };
+	struct sk_buff *skb;
+	unsigned int len;
+	int err;
+
+	/* read header into separate struct and convert it later */
+	rkcanfd_read_rep(priv, RKCANFD_REG_RX_FIFO_RDATA,
+			 header, sizeof(*header));
+	/* read data directly into cfd */
+	rkcanfd_read_rep(priv, RKCANFD_REG_RX_FIFO_RDATA,
+			 cfd->data, sizeof(cfd->data));
+
+	len = rkcanfd_fifo_header_to_cfd_header(priv, header, cfd);
+
+	/* Drop any received CAN-FD frames if CAN-FD mode is not
+	 * requested.
+	 */
+	if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_FDF &&
+	    !(priv->can.ctrlmode & CAN_CTRLMODE_FD)) {
+		stats->rx_dropped++;
+
+		return 0;
+	}
+
+	if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_FDF)
+		skb = alloc_canfd_skb(priv->ndev, &skb_cfd);
+	else
+		skb = alloc_can_skb(priv->ndev, (struct can_frame **)&skb_cfd);
+
+	if (!skb) {
+		stats->rx_dropped++;
+
+		return 0;
+	}
+
+	memcpy(skb_cfd, cfd, len);
+
+	err = can_rx_offload_queue_timestamp(&priv->offload, skb, header->ts);
+	if (err)
+		stats->rx_fifo_errors++;
+
+	return 0;
+}
+
+static inline unsigned int
+rkcanfd_rx_fifo_get_len(const struct rkcanfd_priv *priv)
+{
+	const u32 reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
+
+	return FIELD_GET(RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_CNT, reg);
+}
+
+int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv)
+{
+	unsigned int len;
+	int err;
+
+	while ((len = rkcanfd_rx_fifo_get_len(priv))) {
+		err = rkcanfd_handle_rx_int_one(priv);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
new file mode 100644
index 000000000000..9301b3ceceb0
--- /dev/null
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2023, 2024 Pengutronix,
+//               Marc Kleine-Budde <kernel@pengutronix.de>
+//
+
+#include "rockchip_canfd.h"
+
+void rkcanfd_timestamp_init(struct rkcanfd_priv *priv)
+{
+	u32 reg;
+
+	reg = RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_ENABLE;
+	rkcanfd_write(priv, RKCANFD_REG_TIMESTAMP_CTRL, reg);
+}
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
new file mode 100644
index 000000000000..89c65db3b2dc
--- /dev/null
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2023, 2024 Pengutronix,
+//               Marc Kleine-Budde <kernel@pengutronix.de>
+//
+
+#include "rockchip_canfd.h"
+
+int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	return NETDEV_TX_OK;
+}
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
new file mode 100644
index 000000000000..0848b1900baa
--- /dev/null
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -0,0 +1,361 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (c) 2023, 2024 Pengutronix,
+ *               Marc Kleine-Budde <kernel@pengutronix.de>
+ */
+
+#ifndef _ROCKCHIP_CANFD_H
+#define _ROCKCHIP_CANFD_H
+
+#include <linux/bitfield.h>
+#include <linux/can/dev.h>
+#include <linux/can/rx-offload.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/reset.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/units.h>
+
+#define RKCANFD_REG_MODE 0x000
+#define RKCANFD_REG_MODE_CAN_FD_MODE_ENABLE BIT(15)
+#define RKCANFD_REG_MODE_DPEE BIT(14)
+#define RKCANFD_REG_MODE_BRSD BIT(13)
+#define RKCANFD_REG_MODE_SPACE_RX_MODE BIT(12)
+#define RKCANFD_REG_MODE_AUTO_BUS_ON BIT(11)
+#define RKCANFD_REG_MODE_AUTO_RETX_MODE BIT(10)
+#define RKCANFD_REG_MODE_OVLD_MODE BIT(9)
+#define RKCANFD_REG_MODE_COVER_MODE BIT(8)
+#define RKCANFD_REG_MODE_RXSORT_MODE BIT(7)
+#define RKCANFD_REG_MODE_TXORDER_MODE BIT(6)
+#define RKCANFD_REG_MODE_RXSTX_MODE BIT(5)
+#define RKCANFD_REG_MODE_LBACK_MODE BIT(4)
+#define RKCANFD_REG_MODE_SILENT_MODE BIT(3)
+#define RKCANFD_REG_MODE_SELF_TEST BIT(2)
+#define RKCANFD_REG_MODE_SLEEP_MODE BIT(1)
+#define RKCANFD_REG_MODE_WORK_MODE BIT(0)
+
+#define RKCANFD_REG_CMD 0x004
+#define RKCANFD_REG_CMD_TX1_REQ BIT(1)
+#define RKCANFD_REG_CMD_TX0_REQ BIT(0)
+#define RKCANFD_REG_CMD_TX_REQ(i) (RKCANFD_REG_CMD_TX0_REQ << (i))
+
+#define RKCANFD_REG_STATE 0x008
+#define RKCANFD_REG_STATE_SLEEP_STATE BIT(6)
+#define RKCANFD_REG_STATE_BUS_OFF_STATE BIT(5)
+#define RKCANFD_REG_STATE_ERROR_WARNING_STATE BIT(4)
+#define RKCANFD_REG_STATE_TX_PERIOD BIT(3)
+#define RKCANFD_REG_STATE_RX_PERIOD BIT(2)
+#define RKCANFD_REG_STATE_TX_BUFFER_FULL BIT(1)
+#define RKCANFD_REG_STATE_RX_BUFFER_FULL BIT(0)
+
+#define RKCANFD_REG_INT 0x00c
+#define RKCANFD_REG_INT_WAKEUP_INT BIT(14)
+#define RKCANFD_REG_INT_TXE_FIFO_FULL_INT BIT(13)
+#define RKCANFD_REG_INT_TXE_FIFO_OV_INT BIT(12)
+#define RKCANFD_REG_INT_TIMESTAMP_COUNTER_OVERFLOW_INT BIT(11)
+#define RKCANFD_REG_INT_BUS_OFF_RECOVERY_INT BIT(10)
+#define RKCANFD_REG_INT_BUS_OFF_INT BIT(9)
+#define RKCANFD_REG_INT_RX_FIFO_OVERFLOW_INT BIT(8)
+#define RKCANFD_REG_INT_RX_FIFO_FULL_INT BIT(7)
+#define RKCANFD_REG_INT_ERROR_INT BIT(6)
+#define RKCANFD_REG_INT_TX_ARBIT_FAIL_INT BIT(5)
+#define RKCANFD_REG_INT_PASSIVE_ERROR_INT BIT(4)
+#define RKCANFD_REG_INT_OVERLOAD_INT BIT(3)
+#define RKCANFD_REG_INT_ERROR_WARNING_INT BIT(2)
+#define RKCANFD_REG_INT_TX_FINISH_INT BIT(1)
+#define RKCANFD_REG_INT_RX_FINISH_INT BIT(0)
+
+#define RKCANFD_REG_INT_ALL \
+	(RKCANFD_REG_INT_WAKEUP_INT | \
+	 RKCANFD_REG_INT_TXE_FIFO_FULL_INT | \
+	 RKCANFD_REG_INT_TXE_FIFO_OV_INT | \
+	 RKCANFD_REG_INT_TIMESTAMP_COUNTER_OVERFLOW_INT | \
+	 RKCANFD_REG_INT_BUS_OFF_RECOVERY_INT | \
+	 RKCANFD_REG_INT_BUS_OFF_INT | \
+	 RKCANFD_REG_INT_RX_FIFO_OVERFLOW_INT | \
+	 RKCANFD_REG_INT_RX_FIFO_FULL_INT | \
+	 RKCANFD_REG_INT_ERROR_INT | \
+	 RKCANFD_REG_INT_TX_ARBIT_FAIL_INT | \
+	 RKCANFD_REG_INT_PASSIVE_ERROR_INT | \
+	 RKCANFD_REG_INT_OVERLOAD_INT | \
+	 RKCANFD_REG_INT_ERROR_WARNING_INT | \
+	 RKCANFD_REG_INT_TX_FINISH_INT | \
+	 RKCANFD_REG_INT_RX_FINISH_INT)
+
+#define RKCANFD_REG_INT_ALL_ERROR \
+	(RKCANFD_REG_INT_BUS_OFF_INT | \
+	 RKCANFD_REG_INT_ERROR_INT | \
+	 RKCANFD_REG_INT_PASSIVE_ERROR_INT | \
+	 RKCANFD_REG_INT_ERROR_WARNING_INT)
+
+#define RKCANFD_REG_INT_MASK 0x010
+
+#define RKCANFD_REG_DMA_CTL 0x014
+#define RKCANFD_REG_DMA_CTL_DMA_RX_MODE BIT(1)
+#define RKCANFD_REG_DMA_CTL_DMA_TX_MODE BIT(9)
+
+#define RKCANFD_REG_BITTIMING 0x018
+#define RKCANFD_REG_BITTIMING_SAMPLE_MODE BIT(16)
+#define RKCANFD_REG_BITTIMING_SJW GENMASK(15, 14)
+#define RKCANFD_REG_BITTIMING_BRP GENMASK(13, 8)
+#define RKCANFD_REG_BITTIMING_TSEG2 GENMASK(6, 4)
+#define RKCANFD_REG_BITTIMING_TSEG1 GENMASK(3, 0)
+
+#define RKCANFD_REG_ARBITFAIL 0x028
+#define RKCANFD_REG_ARBITFAIL_ARBIT_FAIL_CODE GENMASK(6, 0)
+
+/* Register seems to be clear or read */
+#define RKCANFD_REG_ERROR_CODE 0x02c
+#define RKCANFD_REG_ERROR_CODE_PHASE BIT(29)
+#define RKCANFD_REG_ERROR_CODE_TYPE GENMASK(28, 26)
+#define RKCANFD_REG_ERROR_CODE_TYPE_BIT 0x0
+#define RKCANFD_REG_ERROR_CODE_TYPE_STUFF 0x1
+#define RKCANFD_REG_ERROR_CODE_TYPE_FORM 0x2
+#define RKCANFD_REG_ERROR_CODE_TYPE_ACK 0x3
+#define RKCANFD_REG_ERROR_CODE_TYPE_CRC 0x4
+#define RKCANFD_REG_ERROR_CODE_DIRECTION_RX BIT(25)
+#define RKCANFD_REG_ERROR_CODE_TX GENMASK(24, 16)
+#define RKCANFD_REG_ERROR_CODE_TX_OVERLOAD BIT(24)
+#define RKCANFD_REG_ERROR_CODE_TX_ERROR BIT(23)
+#define RKCANFD_REG_ERROR_CODE_TX_ACK BIT(22)
+#define RKCANFD_REG_ERROR_CODE_TX_ACK_EOF BIT(21)
+#define RKCANFD_REG_ERROR_CODE_TX_CRC BIT(20)
+#define RKCANFD_REG_ERROR_CODE_TX_STUFF_COUNT BIT(19)
+#define RKCANFD_REG_ERROR_CODE_TX_DATA BIT(18)
+#define RKCANFD_REG_ERROR_CODE_TX_SOF_DLC BIT(17)
+#define RKCANFD_REG_ERROR_CODE_TX_IDLE BIT(16)
+#define RKCANFD_REG_ERROR_CODE_RX GENMASK(15, 0)
+#define RKCANFD_REG_ERROR_CODE_RX_BUF_INT BIT(15)
+#define RKCANFD_REG_ERROR_CODE_RX_SPACE BIT(14)
+#define RKCANFD_REG_ERROR_CODE_RX_EOF BIT(13)
+#define RKCANFD_REG_ERROR_CODE_RX_ACK_LIM BIT(12)
+#define RKCANFD_REG_ERROR_CODE_RX_ACK BIT(11)
+#define RKCANFD_REG_ERROR_CODE_RX_CRC_LIM BIT(10)
+#define RKCANFD_REG_ERROR_CODE_RX_CRC BIT(9)
+#define RKCANFD_REG_ERROR_CODE_RX_STUFF_COUNT BIT(8)
+#define RKCANFD_REG_ERROR_CODE_RX_DATA BIT(7)
+#define RKCANFD_REG_ERROR_CODE_RX_DLC BIT(6)
+#define RKCANFD_REG_ERROR_CODE_RX_BRS_ESI BIT(5)
+#define RKCANFD_REG_ERROR_CODE_RX_RES BIT(4)
+#define RKCANFD_REG_ERROR_CODE_RX_FDF BIT(3)
+#define RKCANFD_REG_ERROR_CODE_RX_ID2_RTR BIT(2)
+#define RKCANFD_REG_ERROR_CODE_RX_SOF_IDE BIT(1)
+#define RKCANFD_REG_ERROR_CODE_RX_IDLE BIT(0)
+
+#define RKCANFD_REG_ERROR_CODE_NOACK \
+	(FIELD_PREP(RKCANFD_REG_ERROR_CODE_TYPE, \
+		    RKCANFD_REG_ERROR_CODE_TYPE_ACK) | \
+	 RKCANFD_REG_ERROR_CODE_TX_ACK_EOF | \
+	 RKCANFD_REG_ERROR_CODE_RX_ACK)
+
+#define RKCANFD_REG_RXERRORCNT 0x034
+#define RKCANFD_REG_RXERRORCNT_RX_ERR_CNT GENMASK(7, 0)
+
+#define RKCANFD_REG_TXERRORCNT 0x038
+#define RKCANFD_REG_TXERRORCNT_TX_ERR_CNT GENMASK(8, 0)
+
+#define RKCANFD_REG_IDCODE 0x03c
+#define RKCANFD_REG_IDCODE_STANDARD_FRAME_ID GENMASK(10, 0)
+#define RKCANFD_REG_IDCODE_EXTENDED_FRAME_ID GENMASK(28, 0)
+
+#define RKCANFD_REG_IDMASK 0x040
+
+#define RKCANFD_REG_TXFRAMEINFO 0x050
+#define RKCANFD_REG_FRAMEINFO_FRAME_FORMAT BIT(7)
+#define RKCANFD_REG_FRAMEINFO_RTR BIT(6)
+#define RKCANFD_REG_FRAMEINFO_DATA_LENGTH GENMASK(3, 0)
+
+#define RKCANFD_REG_TXID 0x054
+#define RKCANFD_REG_TXID_TX_ID GENMASK(28, 0)
+
+#define RKCANFD_REG_TXDATA0 0x058
+#define RKCANFD_REG_TXDATA1 0x05C
+#define RKCANFD_REG_RXFRAMEINFO 0x060
+#define RKCANFD_REG_RXID 0x064
+#define RKCANFD_REG_RXDATA0 0x068
+#define RKCANFD_REG_RXDATA1 0x06c
+
+#define RKCANFD_REG_RTL_VERSION 0x070
+#define RKCANFD_REG_RTL_VERSION_MAJOR GENMASK(7, 4)
+#define RKCANFD_REG_RTL_VERSION_MINOR GENMASK(3, 0)
+
+#define RKCANFD_REG_FD_NOMINAL_BITTIMING 0x100
+#define RKCANFD_REG_FD_NOMINAL_BITTIMING_SAMPLE_MODE BIT(31)
+#define RKCANFD_REG_FD_NOMINAL_BITTIMING_SJW GENMASK(30, 24)
+#define RKCANFD_REG_FD_NOMINAL_BITTIMING_BRP GENMASK(23, 16)
+#define RKCANFD_REG_FD_NOMINAL_BITTIMING_TSEG2 GENMASK(14, 8)
+#define RKCANFD_REG_FD_NOMINAL_BITTIMING_TSEG1 GENMASK(7, 0)
+
+#define RKCANFD_REG_FD_DATA_BITTIMING 0x104
+#define RKCANFD_REG_FD_DATA_BITTIMING_SAMPLE_MODE BIT(21)
+#define RKCANFD_REG_FD_DATA_BITTIMING_SJW GENMASK(20, 17)
+#define RKCANFD_REG_FD_DATA_BITTIMING_BRP GENMASK(16, 9)
+#define RKCANFD_REG_FD_DATA_BITTIMING_TSEG2 GENMASK(8, 5)
+#define RKCANFD_REG_FD_DATA_BITTIMING_TSEG1 GENMASK(4, 0)
+
+#define RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION 0x108
+#define RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION_TDC_OFFSET GENMASK(6, 1)
+#define RKCANFD_REG_TRANSMIT_DELAY_COMPENSATION_TDC_ENABLE BIT(0)
+
+#define RKCANFD_REG_TIMESTAMP_CTRL 0x10c
+/* datasheet says 6:1, which is wrong */
+#define RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_PRESCALE GENMASK(5, 1)
+#define RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_ENABLE BIT(0)
+
+#define RKCANFD_REG_TIMESTAMP 0x110
+
+#define RKCANFD_REG_TXEVENT_FIFO_CTRL 0x114
+#define RKCANFD_REG_TXEVENT_FIFO_CTRL_TXE_FIFO_CNT GENMASK(8, 5)
+#define RKCANFD_REG_TXEVENT_FIFO_CTRL_TXE_FIFO_WATERMARK GENMASK(4, 1)
+#define RKCANFD_REG_TXEVENT_FIFO_CTRL_TXE_FIFO_ENABLE BIT(0)
+
+#define RKCANFD_REG_RX_FIFO_CTRL 0x118
+#define RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_CNT GENMASK(6, 4)
+#define RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_FULL_WATERMARK GENMASK(3, 1)
+#define RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE BIT(0)
+
+#define RKCANFD_REG_AFC_CTRL 0x11c
+#define RKCANFD_REG_AFC_CTRL_UAF5 BIT(4)
+#define RKCANFD_REG_AFC_CTRL_UAF4 BIT(3)
+#define RKCANFD_REG_AFC_CTRL_UAF3 BIT(2)
+#define RKCANFD_REG_AFC_CTRL_UAF2 BIT(1)
+#define RKCANFD_REG_AFC_CTRL_UAF1 BIT(0)
+
+#define RKCANFD_REG_IDCODE0 0x120
+#define RKCANFD_REG_IDMASK0 0x124
+#define RKCANFD_REG_IDCODE1 0x128
+#define RKCANFD_REG_IDMASK1 0x12c
+#define RKCANFD_REG_IDCODE2 0x130
+#define RKCANFD_REG_IDMASK2 0x134
+#define RKCANFD_REG_IDCODE3 0x138
+#define RKCANFD_REG_IDMASK3 0x13c
+#define RKCANFD_REG_IDCODE4 0x140
+#define RKCANFD_REG_IDMASK4 0x144
+
+#define RKCANFD_REG_FD_TXFRAMEINFO 0x200
+#define RKCANFD_REG_FD_FRAMEINFO_FRAME_FORMAT BIT(7)
+#define RKCANFD_REG_FD_FRAMEINFO_RTR BIT(6)
+#define RKCANFD_REG_FD_FRAMEINFO_FDF BIT(5)
+#define RKCANFD_REG_FD_FRAMEINFO_BRS BIT(4)
+#define RKCANFD_REG_FD_FRAMEINFO_DATA_LENGTH GENMASK(3, 0)
+
+#define RKCANFD_REG_FD_TXID 0x204
+#define RKCANFD_REG_FD_ID_EFF GENMASK(28, 0)
+#define RKCANFD_REG_FD_ID_SFF GENMASK(11, 0)
+
+#define RKCANFD_REG_FD_TXDATA0 0x208
+#define RKCANFD_REG_FD_TXDATA1 0x20c
+#define RKCANFD_REG_FD_TXDATA2 0x210
+#define RKCANFD_REG_FD_TXDATA3 0x214
+#define RKCANFD_REG_FD_TXDATA4 0x218
+#define RKCANFD_REG_FD_TXDATA5 0x21c
+#define RKCANFD_REG_FD_TXDATA6 0x220
+#define RKCANFD_REG_FD_TXDATA7 0x224
+#define RKCANFD_REG_FD_TXDATA8 0x228
+#define RKCANFD_REG_FD_TXDATA9 0x22c
+#define RKCANFD_REG_FD_TXDATA10 0x230
+#define RKCANFD_REG_FD_TXDATA11 0x234
+#define RKCANFD_REG_FD_TXDATA12 0x238
+#define RKCANFD_REG_FD_TXDATA13 0x23c
+#define RKCANFD_REG_FD_TXDATA14 0x240
+#define RKCANFD_REG_FD_TXDATA15 0x244
+
+#define RKCANFD_REG_FD_RXFRAMEINFO 0x300
+#define RKCANFD_REG_FD_RXID 0x304
+#define RKCANFD_REG_FD_RXTIMESTAMP 0x308
+#define RKCANFD_REG_FD_RXDATA0 0x30c
+#define RKCANFD_REG_FD_RXDATA1 0x310
+#define RKCANFD_REG_FD_RXDATA2 0x314
+#define RKCANFD_REG_FD_RXDATA3 0x318
+#define RKCANFD_REG_FD_RXDATA4 0x31c
+#define RKCANFD_REG_FD_RXDATA5 0x320
+#define RKCANFD_REG_FD_RXDATA6 0x320
+#define RKCANFD_REG_FD_RXDATA7 0x328
+#define RKCANFD_REG_FD_RXDATA8 0x32c
+#define RKCANFD_REG_FD_RXDATA9 0x330
+#define RKCANFD_REG_FD_RXDATA10 0x334
+#define RKCANFD_REG_FD_RXDATA11 0x338
+#define RKCANFD_REG_FD_RXDATA12 0x33c
+#define RKCANFD_REG_FD_RXDATA13 0x340
+#define RKCANFD_REG_FD_RXDATA14 0x344
+#define RKCANFD_REG_FD_RXDATA15 0x348
+
+#define RKCANFD_REG_RX_FIFO_RDATA 0x400
+#define RKCANFD_REG_TXE_FIFO_RDATA 0x500
+
+#define DEVICE_NAME "rockchip_canfd"
+#define RKCANFD_NAPI_WEIGHT 32
+#define RKCANFD_TXFIFO_DEPTH 1
+#define RKCANFD_TX_STOP_THRESHOLD 1
+#define RKCANFD_TX_START_THRESHOLD 1
+
+#define RKCANFD_TIMESTAMP_WORK_MAX_DELAY_SEC 60
+#define RKCANFD_ERRATUM_5_SYSCLOCK_HZ_MIN (300 * MEGA)
+
+enum rkcanfd_model {
+	RKCANFD_MODEL_RK3568V2 = 0x35682,
+};
+
+struct rkcanfd_devtype_data {
+	enum rkcanfd_model model;
+};
+
+struct rkcanfd_fifo_header {
+	u32 frameinfo;
+	u32 id;
+	u32 ts;
+};
+
+struct rkcanfd_priv {
+	struct can_priv can;
+	struct can_rx_offload offload;
+	struct net_device *ndev;
+
+	void __iomem *regs;
+	unsigned int tx_head;
+	unsigned int tx_tail;
+
+	u32 reg_mode_default;
+	u32 reg_int_mask_default;
+	struct rkcanfd_devtype_data devtype_data;
+
+	struct reset_control *reset;
+	struct clk_bulk_data *clks;
+	int clks_num;
+};
+
+static inline u32
+rkcanfd_read(const struct rkcanfd_priv *priv, u32 reg)
+{
+	return readl(priv->regs + reg);
+}
+
+static inline void
+rkcanfd_read_rep(const struct rkcanfd_priv *priv, u32 reg,
+		 void *buf, unsigned int len)
+{
+	readsl(priv->regs + reg, buf, len / sizeof(u32));
+}
+
+static inline void
+rkcanfd_write(const struct rkcanfd_priv *priv, u32 reg, u32 val)
+{
+	writel(val, priv->regs + reg);
+}
+
+static inline u32
+rkcanfd_get_timestamp(const struct rkcanfd_priv *priv)
+{
+	return rkcanfd_read(priv, RKCANFD_REG_TIMESTAMP);
+}
+
+int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv);
+
+void rkcanfd_timestamp_init(struct rkcanfd_priv *priv);
+
+int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+
+#endif
-- 
cgit v1.3-3-g829e


From bbc783bb7142dc58e6cef27f0308670a7d0ebcce Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 24 Nov 2023 08:54:01 +0100
Subject: can: rockchip_canfd: add quirks for errata workarounds

Add a basic infrastructure for quirks for the 12 documented errata.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-5-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 11 +++++-
 drivers/net/can/rockchip/rockchip_canfd.h      | 55 ++++++++++++++++++++++++++
 2 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index f1b2bad04bf4..18957769b3d3 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -26,6 +26,12 @@
 
 static const struct rkcanfd_devtype_data rkcanfd_devtype_data_rk3568v2 = {
 	.model = RKCANFD_MODEL_RK3568V2,
+	.quirks = RKCANFD_QUIRK_RK3568_ERRATUM_1 | RKCANFD_QUIRK_RK3568_ERRATUM_2 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_3 | RKCANFD_QUIRK_RK3568_ERRATUM_4 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_5 | RKCANFD_QUIRK_RK3568_ERRATUM_6 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_7 | RKCANFD_QUIRK_RK3568_ERRATUM_8 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_9 | RKCANFD_QUIRK_RK3568_ERRATUM_10 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_11 | RKCANFD_QUIRK_RK3568_ERRATUM_12,
 };
 
 static const char *__rkcanfd_get_model_str(enum rkcanfd_model model)
@@ -709,10 +715,11 @@ static void rkcanfd_register_done(const struct rkcanfd_priv *priv)
 	dev_id = rkcanfd_read(priv, RKCANFD_REG_RTL_VERSION);
 
 	netdev_info(priv->ndev,
-		    "Rockchip-CANFD %s rev%lu.%lu found\n",
+		    "Rockchip-CANFD %s rev%lu.%lu (errata 0x%04x) found\n",
 		    rkcanfd_get_model_str(priv),
 		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MAJOR, dev_id),
-		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MINOR, dev_id));
+		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MINOR, dev_id),
+		    priv->devtype_data.quirks);
 }
 
 static int rkcanfd_register(struct rkcanfd_priv *priv)
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 0848b1900baa..09626ca174a8 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -295,12 +295,67 @@
 #define RKCANFD_TIMESTAMP_WORK_MAX_DELAY_SEC 60
 #define RKCANFD_ERRATUM_5_SYSCLOCK_HZ_MIN (300 * MEGA)
 
+/* rk3568 CAN-FD Errata, as of Tue 07 Nov 2023 11:25:31 +08:00 */
+
+/* Erratum 1: The error frame sent by the CAN controller has an
+ * abnormal format.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_1 BIT(0)
+
+/* Erratum 2: The error frame sent after detecting a CRC error has an
+ * abnormal position.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_2 BIT(1)
+
+/* Erratum 3: Intermittent CRC calculation errors. */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_3 BIT(2)
+
+/* Erratum 4: Intermittent occurrence of stuffing errors. */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_4 BIT(3)
+
+/* Erratum 5: Counters related to the TXFIFO and RXFIFO exhibit
+ * abnormal counting behavior.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_5 BIT(4)
+
+/* Erratum 6: The CAN controller's transmission of extended frames may
+ * intermittently change into standard frames
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_6 BIT(5)
+
+/* Erratum 7: In the passive error state, the CAN controller's
+ * interframe space segment counting is inaccurate.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_7 BIT(6)
+
+/* Erratum 8: The Format-Error error flag is transmitted one bit
+ * later.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_8 BIT(7)
+
+/* Erratum 9: In the arbitration segment, the CAN controller will
+ * identify stuffing errors as arbitration failures.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_9 BIT(8)
+
+/* Erratum 10: Does not support the BUSOFF slow recovery mechanism. */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_10 BIT(9)
+
+/* Erratum 11: Arbitration error. */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_11 BIT(10)
+
+/* Erratum 12: A dominant bit at the third bit of the intermission may
+ * cause a transmission error.
+ */
+#define RKCANFD_QUIRK_RK3568_ERRATUM_12 BIT(11)
+
 enum rkcanfd_model {
 	RKCANFD_MODEL_RK3568V2 = 0x35682,
 };
 
 struct rkcanfd_devtype_data {
 	enum rkcanfd_model model;
+	u32 quirks;
 };
 
 struct rkcanfd_fifo_header {
-- 
cgit v1.3-3-g829e


From bbdffb341498431ed5e8d97f1f6af49704eeb3e3 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 19 Dec 2023 12:33:30 +0100
Subject: can: rockchip_canfd: add quirk for broken CAN-FD support

The errata sheets doesn't say anything about CAN-FD, but tests on the
rk3568v2 and rk3568v3 show that receiving certain CAN-FD frames
triggers an Error Interrupt.

Mark the CAN-FD support as broken.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-6-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c |  5 ++++-
 drivers/net/can/rockchip/rockchip_canfd.h      | 21 +++++++++++++++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 18957769b3d3..61de6f89cf16 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -31,7 +31,8 @@ static const struct rkcanfd_devtype_data rkcanfd_devtype_data_rk3568v2 = {
 		RKCANFD_QUIRK_RK3568_ERRATUM_5 | RKCANFD_QUIRK_RK3568_ERRATUM_6 |
 		RKCANFD_QUIRK_RK3568_ERRATUM_7 | RKCANFD_QUIRK_RK3568_ERRATUM_8 |
 		RKCANFD_QUIRK_RK3568_ERRATUM_9 | RKCANFD_QUIRK_RK3568_ERRATUM_10 |
-		RKCANFD_QUIRK_RK3568_ERRATUM_11 | RKCANFD_QUIRK_RK3568_ERRATUM_12,
+		RKCANFD_QUIRK_RK3568_ERRATUM_11 | RKCANFD_QUIRK_RK3568_ERRATUM_12 |
+		RKCANFD_QUIRK_CANFD_BROKEN,
 };
 
 static const char *__rkcanfd_get_model_str(enum rkcanfd_model model)
@@ -817,6 +818,8 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	priv->can.bittiming_const = &rkcanfd_bittiming_const;
 	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
 	priv->can.ctrlmode_supported = 0;
+	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
+		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 	priv->can.do_set_mode = rkcanfd_set_mode;
 	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
 	priv->ndev = ndev;
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 09626ca174a8..7321027534fb 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -349,6 +349,27 @@
  */
 #define RKCANFD_QUIRK_RK3568_ERRATUM_12 BIT(11)
 
+/* Tests on the rk3568v2 and rk3568v3 show that receiving certain
+ * CAN-FD frames trigger an Error Interrupt.
+ *
+ * - Form Error in RX Arbitration Phase: TX_IDLE RX_STUFF_COUNT (0x0a010100) CMD=0 RX=0 TX=0
+ *   Error-Warning=1 Bus-Off=0
+ *   To reproduce:
+ *   host:
+ *     cansend can0 002##01f
+ *   DUT:
+ *     candump any,0:0,#FFFFFFFF -cexdHtA
+ *
+ * - Form Error in RX Arbitration Phase: TX_IDLE RX_CRC (0x0a010200) CMD=0 RX=0 TX=0
+ *   Error-Warning=1 Bus-Off=0
+ *   To reproduce:
+ *   host:
+ *     cansend can0 002##07217010000000000
+ *   DUT:
+ *     candump any,0:0,#FFFFFFFF -cexdHtA
+ */
+#define RKCANFD_QUIRK_CANFD_BROKEN BIT(12)
+
 enum rkcanfd_model {
 	RKCANFD_MODEL_RK3568V2 = 0x35682,
 };
-- 
cgit v1.3-3-g829e


From c158f22fe5562f416bcec4d6a75ae0f9f6661910 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sun, 19 May 2024 15:25:25 +0200
Subject: can: rockchip_canfd: add support for rk3568v3

Add the support for the rk3568v3 SoC, the CAN-FD IP core has 7
documented errata.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-7-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 20 ++++++++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd.h      |  1 +
 2 files changed, 21 insertions(+)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 61de6f89cf16..40911bb63623 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -35,11 +35,28 @@ static const struct rkcanfd_devtype_data rkcanfd_devtype_data_rk3568v2 = {
 		RKCANFD_QUIRK_CANFD_BROKEN,
 };
 
+/* The rk3568 CAN-FD errata sheet as of Tue 07 Nov 2023 11:25:31 +08:00
+ * states that only the rk3568v2 is affected by erratum 5, but tests
+ * with the rk3568v2 and rk3568v3 show that the RX_FIFO_CNT is
+ * sometimes too high. In contrast to the errata sheet mark rk3568v3
+ * as effected by erratum 5, too.
+ */
+static const struct rkcanfd_devtype_data rkcanfd_devtype_data_rk3568v3 = {
+	.model = RKCANFD_MODEL_RK3568V3,
+	.quirks = RKCANFD_QUIRK_RK3568_ERRATUM_1 | RKCANFD_QUIRK_RK3568_ERRATUM_2 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_5 | RKCANFD_QUIRK_RK3568_ERRATUM_7 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_8 | RKCANFD_QUIRK_RK3568_ERRATUM_10 |
+		RKCANFD_QUIRK_RK3568_ERRATUM_11 | RKCANFD_QUIRK_RK3568_ERRATUM_12 |
+		RKCANFD_QUIRK_CANFD_BROKEN,
+};
+
 static const char *__rkcanfd_get_model_str(enum rkcanfd_model model)
 {
 	switch (model) {
 	case RKCANFD_MODEL_RK3568V2:
 		return "rk3568v2";
+	case RKCANFD_MODEL_RK3568V3:
+		return "rk3568v3";
 	}
 
 	return "<unknown>";
@@ -764,6 +781,9 @@ static const struct of_device_id rkcanfd_of_match[] = {
 	{
 		.compatible = "rockchip,rk3568v2-canfd",
 		.data = &rkcanfd_devtype_data_rk3568v2,
+	}, {
+		.compatible = "rockchip,rk3568v3-canfd",
+		.data = &rkcanfd_devtype_data_rk3568v3,
 	}, {
 		/* sentinel */
 	},
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 7321027534fb..9b446331fbd0 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -372,6 +372,7 @@
 
 enum rkcanfd_model {
 	RKCANFD_MODEL_RK3568V2 = 0x35682,
+	RKCANFD_MODEL_RK3568V3 = 0x35683,
 };
 
 struct rkcanfd_devtype_data {
-- 
cgit v1.3-3-g829e


From fb999a5f990605fa4876525c9f73fc0a37844a2d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sun, 28 Jul 2024 14:53:27 +0200
Subject: can: rockchip_canfd: add notes about known issues

Even the rk3568v3 has some known issues. Document them together with a
reproducer.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-8-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 9b446331fbd0..3dafb5e68dc5 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -370,6 +370,26 @@
  */
 #define RKCANFD_QUIRK_CANFD_BROKEN BIT(12)
 
+/* known issues with rk3568v3:
+ *
+ * - Overload situation during high bus load
+ *   To reproduce:
+ *   host:
+ *     # add a 2nd CAN adapter to the CAN bus
+ *     cangen can0 -I 1 -Li -Di -p10 -g 0.3
+ *     cansequence -rve
+ *   DUT:
+ *     cangen can0 -I2 -L1 -Di -p10 -c10 -g 1 -e
+ *     cansequence -rv -i 1
+ *
+ * - TX starvation after repeated Bus-Off
+ *   To reproduce:
+ *   host:
+ *     sleep 3 && cangen can0 -I2 -Li -Di -p10 -g 0.0
+ *   DUT:
+ *     cangen can0 -I2 -Li -Di -p10 -g 0.05
+ */
+
 enum rkcanfd_model {
 	RKCANFD_MODEL_RK3568V2 = 0x35682,
 	RKCANFD_MODEL_RK3568V3 = 0x35683,
-- 
cgit v1.3-3-g829e


From 6571354269f87ddbe0d0b8c890119326145b08d0 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 4 Jan 2024 10:45:38 +0100
Subject: can: rockchip_canfd: rkcanfd_handle_rx_int_one(): implement
 workaround for erratum 5: check for empty FIFO

The rk3568 CAN-FD errata sheet as of Tue 07 Nov 2023 11:25:31 +08:00
says:

| Erratum 5: Counters related to the TXFIFO and RXFIFO exhibit
| abnormal counting behavior.
|
| Due to a bug in the cross-asynchronous logic of the enable signals
| for rx_fifo_cnt and txe_fifo_frame_cnt counters, the counts of these
| two counters become inaccurate. This issue has resulted in the
| inability to use the TXFIFO and RXFIFO functions.

The errata sheet mentioned above states that only the rk3568v2 is
affected by this erratum, but tests with the rk3568v2 and rk3568v3
show that the RX_FIFO_CNT is sometimes too high. This leads to CAN
frames being read from the FIFO, which is then already empty.

Further tests on the rk3568v2 and rk3568v3 show that in this
situation (i.e. empty FIFO) all elements of the FIFO
header (frameinfo, id, ts) contain the same data.

On the rk3568v2 and rk3568v3, this problem only occurs extremely
rarely with the standard clock of 300 MHz, but almost immediately at
80 MHz.

To workaround this problem, check for empty FIFO with
rkcanfd_fifo_header_empty() in rkcanfd_handle_rx_int_one() and exit
early.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-9-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-rx.c | 14 ++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd.h    | 22 ++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 5398aff0d180..609282359bca 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -47,6 +47,16 @@ rkcanfd_fifo_header_to_cfd_header(const struct rkcanfd_priv *priv,
 	return len + cfd->len;
 }
 
+static inline bool
+rkcanfd_fifo_header_empty(const struct rkcanfd_fifo_header *header)
+{
+	/* Erratum 5: If the FIFO is empty, we read the same value for
+	 * all elements.
+	 */
+	return header->frameinfo == header->id &&
+		header->frameinfo == header->ts;
+}
+
 static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
@@ -63,6 +73,10 @@ static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 	rkcanfd_read_rep(priv, RKCANFD_REG_RX_FIFO_RDATA,
 			 cfd->data, sizeof(cfd->data));
 
+	/* Erratum 5: Counters for TXEFIFO and RXFIFO may be wrong */
+	if (rkcanfd_fifo_header_empty(header))
+		return 0;
+
 	len = rkcanfd_fifo_header_to_cfd_header(priv, header, cfd);
 
 	/* Drop any received CAN-FD frames if CAN-FD mode is not
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 3dafb5e68dc5..c775e75a2740 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -315,6 +315,28 @@
 
 /* Erratum 5: Counters related to the TXFIFO and RXFIFO exhibit
  * abnormal counting behavior.
+ *
+ * The rk3568 CAN-FD errata sheet as of Tue 07 Nov 2023 11:25:31 +08:00
+ * states that only the rk3568v2 is affected by this erratum, but
+ * tests with the rk3568v2 and rk3568v3 show that the RX_FIFO_CNT is
+ * sometimes too high. This leads to CAN frames being read from the
+ * FIFO, which is then already empty.
+ *
+ * Further tests on the rk3568v2 and rk3568v3 show that in this
+ * situation (i.e. empty FIFO) all elements of the FIFO header
+ * (frameinfo, id, ts) contain the same data.
+ *
+ * On the rk3568v2 and rk3568v3, this problem only occurs extremely
+ * rarely with the standard clock of 300 MHz, but almost immediately
+ * at 80 MHz.
+ *
+ * To workaround this problem, check for empty FIFO with
+ * rkcanfd_fifo_header_empty() in rkcanfd_handle_rx_int_one() and exit
+ * early.
+ *
+ * To reproduce:
+ * assigned-clocks = <&cru CLK_CANx>;
+ * assigned-clock-rates = <80000000>;
  */
 #define RKCANFD_QUIRK_RK3568_ERRATUM_5 BIT(4)
 
-- 
cgit v1.3-3-g829e


From 25e024c3491cba0e22135720c7adaf52c0f1f019 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 12 Dec 2023 13:57:55 +0100
Subject: can: rockchip_canfd: rkcanfd_register_done(): add warning for erratum
 5

Tests on the rk3568v2 and rk3568v3 show that a reduced "baudclk" (e.g.
80MHz, compared to the standard 300MHz) significantly increases the
possibility of incorrect FIFO counters, i.e. erratum 5.

Print an info message if the clock is below the known good value of
300MHz.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-10-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 40911bb63623..d6c0f2fe8d2b 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -738,6 +738,13 @@ static void rkcanfd_register_done(const struct rkcanfd_priv *priv)
 		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MAJOR, dev_id),
 		    FIELD_GET(RKCANFD_REG_RTL_VERSION_MINOR, dev_id),
 		    priv->devtype_data.quirks);
+
+	if (priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_5 &&
+	    priv->can.clock.freq < RKCANFD_ERRATUM_5_SYSCLOCK_HZ_MIN)
+		netdev_info(priv->ndev,
+			    "Erratum 5: CAN clock frequency (%luMHz) lower than known good (%luMHz), expect degraded performance\n",
+			    priv->can.clock.freq / MEGA,
+			    RKCANFD_ERRATUM_5_SYSCLOCK_HZ_MIN / MEGA);
 }
 
 static int rkcanfd_register(struct rkcanfd_priv *priv)
-- 
cgit v1.3-3-g829e


From b6661d73290c572645ebdf7119974927444f4a7d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 24 Nov 2023 21:37:36 +0100
Subject: can: rockchip_canfd: add TX PATH

The IP core has a TX event FIFO. In other IP cores, this type of FIFO
usually contains the events that a CAN frame has been successfully
sent. However, the IP core on the rk3568v2 the FIFO also holds events
of unsuccessful transmission attempts.

It turned out that the best way to work around this problem is to set
the IP core to self-receive mode (RXSTX), filter out the self-received
frames and insert them into the complete TX path.

Add a pair new functions to check if 2 struct canfd_frame are equal.
The 1st checks if the header of the CAN frames are equal, the 2nd
checks if the data portion are equal:

- rkcanfd_can_frame_header_equal()
- rkcanfd_can_frame_data_equal()

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-11-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c |  6 +-
 drivers/net/can/rockchip/rockchip_canfd-rx.c   | 96 ++++++++++++++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd-tx.c   | 94 +++++++++++++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd.h      | 26 +++++++
 4 files changed, 221 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index d6c0f2fe8d2b..700702e4d2ed 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -229,6 +229,7 @@ static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
 	 * - CAN_FD: enable CAN-FD
 	 * - AUTO_RETX_MODE: auto retransmission on TX error
 	 * - COVER_MODE: RX-FIFO overwrite mode, do not send OVERLOAD frames
+	 * - RXSTX_MODE: Receive Self Transmit data mode
 	 * - WORK_MODE: transition from reset to working mode
 	 */
 	reg = rkcanfd_read(priv, RKCANFD_REG_MODE);
@@ -236,17 +237,20 @@ static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
 		RKCANFD_REG_MODE_CAN_FD_MODE_ENABLE |
 		RKCANFD_REG_MODE_AUTO_RETX_MODE |
 		RKCANFD_REG_MODE_COVER_MODE |
+		RKCANFD_REG_MODE_RXSTX_MODE |
 		RKCANFD_REG_MODE_WORK_MODE;
 
 	/* mask, i.e. ignore:
 	 * - TIMESTAMP_COUNTER_OVERFLOW_INT - timestamp counter overflow interrupt
 	 * - TX_ARBIT_FAIL_INT - TX arbitration fail interrupt
 	 * - OVERLOAD_INT - CAN bus overload interrupt
+	 * - TX_FINISH_INT - Transmit finish interrupt
 	 */
 	priv->reg_int_mask_default =
 		RKCANFD_REG_INT_TIMESTAMP_COUNTER_OVERFLOW_INT |
 		RKCANFD_REG_INT_TX_ARBIT_FAIL_INT |
-		RKCANFD_REG_INT_OVERLOAD_INT;
+		RKCANFD_REG_INT_OVERLOAD_INT |
+		RKCANFD_REG_INT_TX_FINISH_INT;
 
 	rkcanfd_chip_fifo_setup(priv);
 	rkcanfd_timestamp_init(priv);
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 609282359bca..650dfd41e0a0 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -4,8 +4,52 @@
 //               Marc Kleine-Budde <kernel@pengutronix.de>
 //
 
+#include <net/netdev_queues.h>
+
 #include "rockchip_canfd.h"
 
+static bool rkcanfd_can_frame_header_equal(const struct canfd_frame *const cfd1,
+					   const struct canfd_frame *const cfd2,
+					   const bool is_canfd)
+{
+	const u8 mask_flags = CANFD_BRS | CANFD_ESI | CANFD_FDF;
+	canid_t mask = CAN_EFF_FLAG;
+
+	if (canfd_sanitize_len(cfd1->len) != canfd_sanitize_len(cfd2->len))
+		return false;
+
+	if (!is_canfd)
+		mask |= CAN_RTR_FLAG;
+
+	if (cfd1->can_id & CAN_EFF_FLAG)
+		mask |= CAN_EFF_MASK;
+	else
+		mask |= CAN_SFF_MASK;
+
+	if ((cfd1->can_id & mask) != (cfd2->can_id & mask))
+		return false;
+
+	if (is_canfd &&
+	    (cfd1->flags & mask_flags) != (cfd2->flags & mask_flags))
+		return false;
+
+	return true;
+}
+
+static bool rkcanfd_can_frame_data_equal(const struct canfd_frame *cfd1,
+					 const struct canfd_frame *cfd2,
+					 const bool is_canfd)
+{
+	u8 len;
+
+	if (!is_canfd && (cfd1->can_id & CAN_RTR_FLAG))
+		return true;
+
+	len = canfd_sanitize_len(cfd1->len);
+
+	return !memcmp(cfd1->data, cfd2->data, len);
+}
+
 static unsigned int
 rkcanfd_fifo_header_to_cfd_header(const struct rkcanfd_priv *priv,
 				  const struct rkcanfd_fifo_header *header,
@@ -47,6 +91,48 @@ rkcanfd_fifo_header_to_cfd_header(const struct rkcanfd_priv *priv,
 	return len + cfd->len;
 }
 
+static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
+				const struct canfd_frame *cfd_rx, const u32 ts,
+				bool *tx_done)
+{
+	const struct canfd_frame *cfd_nominal;
+	const struct sk_buff *skb;
+	unsigned int tx_tail;
+
+	tx_tail = rkcanfd_get_tx_tail(priv);
+	skb = priv->can.echo_skb[tx_tail];
+	if (!skb) {
+		netdev_err(priv->ndev,
+			   "%s: echo_skb[%u]=NULL tx_head=0x%08x tx_tail=0x%08x\n",
+			   __func__, tx_tail,
+			   priv->tx_head, priv->tx_tail);
+
+		return -ENOMSG;
+	}
+	cfd_nominal = (struct canfd_frame *)skb->data;
+
+	/* We RX'ed a frame identical to our pending TX frame. */
+	if (rkcanfd_can_frame_header_equal(cfd_rx, cfd_nominal,
+					   cfd_rx->flags & CANFD_FDF) &&
+	    rkcanfd_can_frame_data_equal(cfd_rx, cfd_nominal,
+					 cfd_rx->flags & CANFD_FDF)) {
+		unsigned int frame_len;
+
+		rkcanfd_handle_tx_done_one(priv, ts, &frame_len);
+
+		WRITE_ONCE(priv->tx_tail, priv->tx_tail + 1);
+		netif_subqueue_completed_wake(priv->ndev, 0, 1, frame_len,
+					      rkcanfd_get_tx_free(priv),
+					      RKCANFD_TX_START_THRESHOLD);
+
+		*tx_done = true;
+
+		return 0;
+	}
+
+	return 0;
+}
+
 static inline bool
 rkcanfd_fifo_header_empty(const struct rkcanfd_fifo_header *header)
 {
@@ -89,6 +175,16 @@ static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 		return 0;
 	}
 
+	if (rkcanfd_get_tx_pending(priv)) {
+		bool tx_done = false;
+
+		err = rkcanfd_rxstx_filter(priv, cfd, header->ts, &tx_done);
+		if (err)
+			return err;
+		if (tx_done)
+			return 0;
+	}
+
 	if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_FDF)
 		skb = alloc_canfd_skb(priv->ndev, &skb_cfd);
 	else
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 89c65db3b2dc..668a902f4c2a 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -4,9 +4,103 @@
 //               Marc Kleine-Budde <kernel@pengutronix.de>
 //
 
+#include <net/netdev_queues.h>
+
 #include "rockchip_canfd.h"
 
+static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
+					 const u32 reg_cmd)
+{
+	rkcanfd_write(priv, RKCANFD_REG_CMD, reg_cmd);
+}
+
 int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
+	struct rkcanfd_priv *priv = netdev_priv(ndev);
+	u32 reg_frameinfo, reg_id, reg_cmd;
+	unsigned int tx_head, frame_len;
+	const struct canfd_frame *cfd;
+	int err;
+	u8 i;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	if (!netif_subqueue_maybe_stop(priv->ndev, 0,
+				       rkcanfd_get_tx_free(priv),
+				       RKCANFD_TX_STOP_THRESHOLD,
+				       RKCANFD_TX_START_THRESHOLD)) {
+		if (net_ratelimit())
+			netdev_info(priv->ndev,
+				    "Stopping tx-queue (tx_head=0x%08x, tx_tail=0x%08x, tx_pending=%d)\n",
+				    priv->tx_head, priv->tx_tail,
+				    rkcanfd_get_tx_pending(priv));
+
+		return NETDEV_TX_BUSY;
+	}
+
+	cfd = (struct canfd_frame *)skb->data;
+
+	if (cfd->can_id & CAN_EFF_FLAG) {
+		reg_frameinfo = RKCANFD_REG_FD_FRAMEINFO_FRAME_FORMAT;
+		reg_id = FIELD_PREP(RKCANFD_REG_FD_ID_EFF, cfd->can_id);
+	} else {
+		reg_frameinfo = 0;
+		reg_id = FIELD_PREP(RKCANFD_REG_FD_ID_SFF, cfd->can_id);
+	}
+
+	if (cfd->can_id & CAN_RTR_FLAG)
+		reg_frameinfo |= RKCANFD_REG_FD_FRAMEINFO_RTR;
+
+	if (can_is_canfd_skb(skb)) {
+		reg_frameinfo |= RKCANFD_REG_FD_FRAMEINFO_FDF;
+
+		if (cfd->flags & CANFD_BRS)
+			reg_frameinfo |= RKCANFD_REG_FD_FRAMEINFO_BRS;
+
+		reg_frameinfo |= FIELD_PREP(RKCANFD_REG_FD_FRAMEINFO_DATA_LENGTH,
+					    can_fd_len2dlc(cfd->len));
+	} else {
+		reg_frameinfo |= FIELD_PREP(RKCANFD_REG_FD_FRAMEINFO_DATA_LENGTH,
+					    cfd->len);
+	}
+
+	tx_head = rkcanfd_get_tx_head(priv);
+	reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
+
+	rkcanfd_write(priv, RKCANFD_REG_FD_TXFRAMEINFO, reg_frameinfo);
+	rkcanfd_write(priv, RKCANFD_REG_FD_TXID, reg_id);
+	for (i = 0; i < cfd->len; i += 4)
+		rkcanfd_write(priv, RKCANFD_REG_FD_TXDATA0 + i,
+			      *(u32 *)(cfd->data + i));
+
+	frame_len = can_skb_get_frame_len(skb);
+	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
+	if (!err)
+		netdev_sent_queue(priv->ndev, frame_len);
+
+	WRITE_ONCE(priv->tx_head, priv->tx_head + 1);
+
+	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
+
+	netif_subqueue_maybe_stop(priv->ndev, 0,
+				  rkcanfd_get_tx_free(priv),
+				  RKCANFD_TX_STOP_THRESHOLD,
+				  RKCANFD_TX_START_THRESHOLD);
+
 	return NETDEV_TX_OK;
 }
+
+void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
+				unsigned int *frame_len_p)
+{
+	struct net_device_stats *stats = &priv->ndev->stats;
+	unsigned int tx_tail;
+
+	tx_tail = rkcanfd_get_tx_tail(priv);
+	stats->tx_bytes +=
+		can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload,
+							    tx_tail, ts,
+							    frame_len_p);
+	stats->tx_packets++;
+}
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index c775e75a2740..a4688411e586 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -471,10 +471,36 @@ rkcanfd_get_timestamp(const struct rkcanfd_priv *priv)
 	return rkcanfd_read(priv, RKCANFD_REG_TIMESTAMP);
 }
 
+static inline unsigned int
+rkcanfd_get_tx_head(const struct rkcanfd_priv *priv)
+{
+	return READ_ONCE(priv->tx_head) & (RKCANFD_TXFIFO_DEPTH - 1);
+}
+
+static inline unsigned int
+rkcanfd_get_tx_tail(const struct rkcanfd_priv *priv)
+{
+	return READ_ONCE(priv->tx_tail) & (RKCANFD_TXFIFO_DEPTH - 1);
+}
+
+static inline unsigned int
+rkcanfd_get_tx_pending(const struct rkcanfd_priv *priv)
+{
+	return READ_ONCE(priv->tx_head) - READ_ONCE(priv->tx_tail);
+}
+
+static inline unsigned int
+rkcanfd_get_tx_free(const struct rkcanfd_priv *priv)
+{
+	return RKCANFD_TXFIFO_DEPTH - rkcanfd_get_tx_pending(priv);
+}
+
 int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv);
 
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv);
 
 int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
+				unsigned int *frame_len_p);
 
 #endif
-- 
cgit v1.3-3-g829e


From 58d3cc65a241953d40490329fb7638a93f95dd78 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 24 Nov 2023 09:27:00 +0100
Subject: can: rockchip_canfd: implement workaround for erratum 6

The rk3568 CAN-FD errata sheet as of Tue 07 Nov 2023 11:25:31 +08:00
says:

| The CAN controller's transmission of extended frames may
| intermittently change into standard frames.
|
| When using the CAN controller to send extended frames, if the
| 'tx_req' is configured as 1 and coincides with the internal
| transmission point, the extended frame will be transmitted onto the
| bus in the format of a standard frame.

To work around Erratum 6, the driver is in self-receiving mode (RXSTX)
and all received CAN frames are passed through rkcanfd_rxstx_filter().

Add a check in rkcanfd_rxstx_filter() whether the received frame
corresponds to the current outgoing frame, but the extended CAN ID has
been mangled to a standard ID. In this case re-send the original CAN
frame.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-12-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-rx.c | 44 ++++++++++++++++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd-tx.c |  8 +++++
 drivers/net/can/rockchip/rockchip_canfd.h    | 19 ++++++++++++
 3 files changed, 71 insertions(+)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 650dfd41e0a0..31cee3362f1e 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -95,6 +95,7 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 				const struct canfd_frame *cfd_rx, const u32 ts,
 				bool *tx_done)
 {
+	struct net_device_stats *stats = &priv->ndev->stats;
 	const struct canfd_frame *cfd_nominal;
 	const struct sk_buff *skb;
 	unsigned int tx_tail;
@@ -130,6 +131,49 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 		return 0;
 	}
 
+	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_6))
+		return 0;
+
+	/* Erratum 6: Extended frames may be send as standard frames.
+	 *
+	 * Not affected if:
+	 * - TX'ed a standard frame -or-
+	 * - RX'ed an extended frame
+	 */
+	if (!(cfd_nominal->can_id & CAN_EFF_FLAG) ||
+	    (cfd_rx->can_id & CAN_EFF_FLAG))
+		return 0;
+
+	/* Not affected if:
+	 * - standard part and RTR flag of the TX'ed frame
+	 *   is not equal the CAN-ID and RTR flag of the RX'ed frame.
+	 */
+	if ((cfd_nominal->can_id & (CAN_RTR_FLAG | CAN_SFF_MASK)) !=
+	    (cfd_rx->can_id & (CAN_RTR_FLAG | CAN_SFF_MASK)))
+		return 0;
+
+	/* Not affected if:
+	 * - length is not the same
+	 */
+	if (cfd_nominal->len != cfd_rx->len)
+		return 0;
+
+	/* Not affected if:
+	 * - the data of non RTR frames is different
+	 */
+	if (!(cfd_nominal->can_id & CAN_RTR_FLAG) &&
+	    memcmp(cfd_nominal->data, cfd_rx->data, cfd_nominal->len))
+		return 0;
+
+	/* Affected by Erratum 6 */
+
+	*tx_done = true;
+
+	stats->tx_packets++;
+	stats->tx_errors++;
+
+	rkcanfd_xmit_retry(priv);
+
 	return 0;
 }
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 668a902f4c2a..e98e7a836b83 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -14,6 +14,14 @@ static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
 	rkcanfd_write(priv, RKCANFD_REG_CMD, reg_cmd);
 }
 
+void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
+{
+	const unsigned int tx_head = rkcanfd_get_tx_head(priv);
+	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
+
+	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
+}
+
 int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct rkcanfd_priv *priv = netdev_priv(ndev);
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index a4688411e586..3fe6ddcdd8ac 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -342,6 +342,24 @@
 
 /* Erratum 6: The CAN controller's transmission of extended frames may
  * intermittently change into standard frames
+ *
+ * Work around this issue by activating self reception (RXSTX). If we
+ * have pending TX CAN frames, check all RX'ed CAN frames in
+ * rkcanfd_rxstx_filter().
+ *
+ * If it's a frame we've send and it's OK, call the TX complete
+ * handler: rkcanfd_handle_tx_done_one(). Mask the TX complete IRQ.
+ *
+ * If it's a frame we've send, but the CAN-ID is mangled, resend the
+ * original extended frame.
+ *
+ * To reproduce:
+ * host:
+ *   canfdtest -evx -g can0
+ *   candump any,0:80000000 -cexdtA
+ * dut:
+ *   canfdtest -evx can0
+ *   ethtool -S can0
  */
 #define RKCANFD_QUIRK_RK3568_ERRATUM_6 BIT(5)
 
@@ -499,6 +517,7 @@ int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv);
 
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv);
 
+void rkcanfd_xmit_retry(struct rkcanfd_priv *priv);
 int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 				unsigned int *frame_len_p);
-- 
cgit v1.3-3-g829e


From 83f9bd6bf39de5865372d45edbe0cf7b19c285c5 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 24 Nov 2023 08:54:32 +0100
Subject: can: rockchip_canfd: implement workaround for erratum 12

The rk3568 CAN-FD errata sheet as of Tue 07 Nov 2023 11:25:31 +08:00
says:

| A dominant bit at the third bit of the intermission may cause a
| transmission error.
|
| When sampling the third bit of the intermission as a dominant bit, if
| tx_req is configured to transmit extended frames at this time, the
| extended frame may be sent to the bus in the format of a standard
| frame. The extended frame will be sent as a standard frame and will not
| result in error frames

Turn on "Interframe Spaceing RX Mode" only during TX to work around
erratum 12, according to rock-chip:

| Spaceing RX Mode = 1, the third Bit between frames cannot receive
| and send, and the fourth Bit begins to receive and send.
|
| Spaceing RX Mode = 0, allowing the third Bit between frames to
| receive and send.

Message-ID: <be72939f-0a9e-0608-dfff-7b0096a26eba@rock-chips.com>
Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-13-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index e98e7a836b83..9db6d90a4e7f 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -11,7 +11,14 @@
 static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
 					 const u32 reg_cmd)
 {
+	if (priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_12)
+		rkcanfd_write(priv, RKCANFD_REG_MODE, priv->reg_mode_default |
+			      RKCANFD_REG_MODE_SPACE_RX_MODE);
+
 	rkcanfd_write(priv, RKCANFD_REG_CMD, reg_cmd);
+
+	if (priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_12)
+		rkcanfd_write(priv, RKCANFD_REG_MODE, priv->reg_mode_default);
 }
 
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
-- 
cgit v1.3-3-g829e


From 7ba7111b5f9e754e21ea508754c43238c5528c3d Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sun, 10 Dec 2023 14:43:14 +0100
Subject: can: rockchip_canfd: rkcanfd_get_berr_counter_corrected(): work
 around broken {RX,TX}ERRORCNT register

Tests show that sometimes both CAN bus error counters read 0x0, even
if the controller is in warning mode
(RKCANFD_REG_STATE_ERROR_WARNING_STATE in RKCANFD_REG_STATE
set).

To work around this issue, if both error counters read from hardware
are 0x0, use the structure priv->bec, otherwise save the read value in
priv->bec.

In rkcanfd_handle_rx_int_one() decrement the priv->bec.rxerr for
successfully RX'ed CAN frames.

In rkcanfd_handle_tx_done_one() decrement the priv->bec.txerr for
successfully TX'ed CAN frames.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-14-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 50 ++++++++++++++++++++++----
 drivers/net/can/rockchip/rockchip_canfd-rx.c   | 15 ++++++++
 drivers/net/can/rockchip/rockchip_canfd-tx.c   |  8 +++++
 drivers/net/can/rockchip/rockchip_canfd.h      |  2 ++
 4 files changed, 69 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 700702e4d2ed..cf176180a282 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -159,11 +159,47 @@ static int rkcanfd_set_bittiming(struct rkcanfd_priv *priv)
 	return 0;
 }
 
-static void rkcanfd_get_berr_counter_raw(struct rkcanfd_priv *priv,
-					 struct can_berr_counter *bec)
+static void rkcanfd_get_berr_counter_corrected(struct rkcanfd_priv *priv,
+					       struct can_berr_counter *bec)
 {
+	struct can_berr_counter bec_raw;
+	u32 reg_state;
+
 	bec->rxerr = rkcanfd_read(priv, RKCANFD_REG_RXERRORCNT);
 	bec->txerr = rkcanfd_read(priv, RKCANFD_REG_TXERRORCNT);
+	bec_raw = *bec;
+
+	/* Tests show that sometimes both CAN bus error counters read
+	 * 0x0, even if the controller is in warning mode
+	 * (RKCANFD_REG_STATE_ERROR_WARNING_STATE in RKCANFD_REG_STATE
+	 * set).
+	 *
+	 * In case both error counters read 0x0, use the struct
+	 * priv->bec, otherwise save the read value to priv->bec.
+	 *
+	 * rkcanfd_handle_rx_int_one() handles the decrementing of
+	 * priv->bec.rxerr for successfully RX'ed CAN frames.
+	 *
+	 * Luckily the controller doesn't decrement the RX CAN bus
+	 * error counter in hardware for self received TX'ed CAN
+	 * frames (RKCANFD_REG_MODE_RXSTX_MODE), so RXSTX doesn't
+	 * interfere with proper RX CAN bus error counters.
+	 *
+	 * rkcanfd_handle_tx_done_one() handles the decrementing of
+	 * priv->bec.txerr for successfully TX'ed CAN frames.
+	 */
+	if (!bec->rxerr && !bec->txerr)
+		*bec = priv->bec;
+	else
+		priv->bec = *bec;
+
+	reg_state = rkcanfd_read(priv, RKCANFD_REG_STATE);
+	netdev_vdbg(priv->ndev,
+		    "%s: Raw/Cor: txerr=%3u/%3u rxerr=%3u/%3u Bus Off=%u Warning=%u\n",
+		    __func__,
+		    bec_raw.txerr, bec->txerr, bec_raw.rxerr, bec->rxerr,
+		    !!(reg_state & RKCANFD_REG_STATE_BUS_OFF_STATE),
+		    !!(reg_state & RKCANFD_REG_STATE_ERROR_WARNING_STATE));
 }
 
 static int rkcanfd_get_berr_counter(const struct net_device *ndev,
@@ -176,7 +212,7 @@ static int rkcanfd_get_berr_counter(const struct net_device *ndev,
 	if (err)
 		return err;
 
-	rkcanfd_get_berr_counter_raw(priv, bec);
+	rkcanfd_get_berr_counter_corrected(priv, bec);
 
 	pm_runtime_put(ndev->dev.parent);
 
@@ -252,6 +288,8 @@ static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
 		RKCANFD_REG_INT_OVERLOAD_INT |
 		RKCANFD_REG_INT_TX_FINISH_INT;
 
+	memset(&priv->bec, 0x0, sizeof(priv->bec));
+
 	rkcanfd_chip_fifo_setup(priv);
 	rkcanfd_timestamp_init(priv);
 	rkcanfd_set_bittiming(priv);
@@ -488,7 +526,7 @@ static int rkcanfd_handle_error_int(struct rkcanfd_priv *priv)
 	if (cf) {
 		struct can_berr_counter bec;
 
-		rkcanfd_get_berr_counter_raw(priv, &bec);
+		rkcanfd_get_berr_counter_corrected(priv, &bec);
 		cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR | CAN_ERR_CNT;
 		cf->data[6] = bec.txerr;
 		cf->data[7] = bec.rxerr;
@@ -517,7 +555,7 @@ static int rkcanfd_handle_state_error_int(struct rkcanfd_priv *priv)
 	u32 timestamp;
 	int err;
 
-	rkcanfd_get_berr_counter_raw(priv, &bec);
+	rkcanfd_get_berr_counter_corrected(priv, &bec);
 	can_state_get_by_berr_counter(ndev, &bec, &tx_state, &rx_state);
 
 	new_state = max(tx_state, rx_state);
@@ -570,7 +608,7 @@ rkcanfd_handle_rx_fifo_overflow_int(struct rkcanfd_priv *priv)
 	if (skb)
 		return 0;
 
-	rkcanfd_get_berr_counter_raw(priv, &bec);
+	rkcanfd_get_berr_counter_corrected(priv, &bec);
 
 	cf->can_id |= CAN_ERR_CRTL | CAN_ERR_CNT;
 	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 31cee3362f1e..eff08948840c 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -167,6 +167,13 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 
 	/* Affected by Erratum 6 */
 
+	/* Manual handling of CAN Bus Error counters. See
+	 * rkcanfd_get_corrected_berr_counter() for detailed
+	 * explanation.
+	 */
+	if (priv->bec.txerr)
+		priv->bec.txerr--;
+
 	*tx_done = true;
 
 	stats->tx_packets++;
@@ -229,6 +236,14 @@ static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 			return 0;
 	}
 
+	/* Manual handling of CAN Bus Error counters. See
+	 * rkcanfd_get_corrected_berr_counter() for detailed
+	 * explanation.
+	 */
+	if (priv->bec.rxerr)
+		priv->bec.rxerr = min(CAN_ERROR_PASSIVE_THRESHOLD,
+				      priv->bec.rxerr) - 1;
+
 	if (header->frameinfo & RKCANFD_REG_FD_FRAMEINFO_FDF)
 		skb = alloc_canfd_skb(priv->ndev, &skb_cfd);
 	else
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 9db6d90a4e7f..f8e74e814b3b 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -113,6 +113,14 @@ void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 	unsigned int tx_tail;
 
 	tx_tail = rkcanfd_get_tx_tail(priv);
+
+	/* Manual handling of CAN Bus Error counters. See
+	 * rkcanfd_get_corrected_berr_counter() for detailed
+	 * explanation.
+	 */
+	if (priv->bec.txerr)
+		priv->bec.txerr--;
+
 	stats->tx_bytes +=
 		can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload,
 							    tx_tail, ts,
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 3fe6ddcdd8ac..67f135fbcfb9 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -459,6 +459,8 @@ struct rkcanfd_priv {
 	u32 reg_int_mask_default;
 	struct rkcanfd_devtype_data devtype_data;
 
+	struct can_berr_counter bec;
+
 	struct reset_control *reset;
 	struct clk_bulk_data *clks;
 	int clks_num;
-- 
cgit v1.3-3-g829e


From 669904d14609352b5c46b898b8560ffe46bcab78 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 14 Dec 2023 14:45:09 +0100
Subject: can: rockchip_canfd: add stats support for errata workarounds

The driver contains workarounds for some of the rk3568v2 errata. Add
ethtool-based statistics ("ethtool -S") to track how often an erratum
workaround was needed.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-15-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/Makefile                 |  1 +
 drivers/net/can/rockchip/rockchip_canfd-core.c    |  2 +
 drivers/net/can/rockchip/rockchip_canfd-ethtool.c | 73 +++++++++++++++++++++++
 drivers/net/can/rockchip/rockchip_canfd-rx.c      | 13 +++-
 drivers/net/can/rockchip/rockchip_canfd.h         | 14 +++++
 5 files changed, 102 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/can/rockchip/rockchip_canfd-ethtool.c

diff --git a/drivers/net/can/rockchip/Makefile b/drivers/net/can/rockchip/Makefile
index 4eb7c50d8d5b..3760d3e1baa3 100644
--- a/drivers/net/can/rockchip/Makefile
+++ b/drivers/net/can/rockchip/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_CAN_ROCKCHIP_CANFD) += rockchip_canfd.o
 
 rockchip_canfd-objs :=
 rockchip_canfd-objs += rockchip_canfd-core.o
+rockchip_canfd-objs += rockchip_canfd-ethtool.o
 rockchip_canfd-objs += rockchip_canfd-rx.o
 rockchip_canfd-objs += rockchip_canfd-timestamp.o
 rockchip_canfd-objs += rockchip_canfd-tx.o
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index cf176180a282..4db552bfc4db 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -800,6 +800,8 @@ static int rkcanfd_register(struct rkcanfd_priv *priv)
 	if (err)
 		goto out_pm_runtime_disable;
 
+	rkcanfd_ethtool_init(priv);
+
 	err = register_candev(ndev);
 	if (err)
 		goto out_pm_runtime_put_sync;
diff --git a/drivers/net/can/rockchip/rockchip_canfd-ethtool.c b/drivers/net/can/rockchip/rockchip_canfd-ethtool.c
new file mode 100644
index 000000000000..0084f37b2b9f
--- /dev/null
+++ b/drivers/net/can/rockchip/rockchip_canfd-ethtool.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2023, 2024 Pengutronix,
+//               Marc Kleine-Budde <kernel@pengutronix.de>
+//
+
+#include <linux/ethtool.h>
+
+#include "rockchip_canfd.h"
+
+enum rkcanfd_stats_type {
+	RKCANFD_STATS_TYPE_RX_FIFO_EMPTY_ERRORS,
+	RKCANFD_STATS_TYPE_TX_EXTENDED_AS_STANDARD_ERRORS,
+};
+
+static const char rkcanfd_stats_strings[][ETH_GSTRING_LEN] = {
+	[RKCANFD_STATS_TYPE_RX_FIFO_EMPTY_ERRORS] = "rx_fifo_empty_errors",
+	[RKCANFD_STATS_TYPE_TX_EXTENDED_AS_STANDARD_ERRORS] = "tx_extended_as_standard_errors",
+};
+
+static void
+rkcanfd_ethtool_get_strings(struct net_device *ndev, u32 stringset, u8 *buf)
+{
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(buf, rkcanfd_stats_strings,
+		       sizeof(rkcanfd_stats_strings));
+	}
+}
+
+static int rkcanfd_ethtool_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return ARRAY_SIZE(rkcanfd_stats_strings);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static void
+rkcanfd_ethtool_get_ethtool_stats(struct net_device *ndev,
+				  struct ethtool_stats *stats, u64 *data)
+{
+	struct rkcanfd_priv *priv = netdev_priv(ndev);
+	struct rkcanfd_stats *rkcanfd_stats;
+	unsigned int start;
+
+	rkcanfd_stats = &priv->stats;
+
+	do {
+		start = u64_stats_fetch_begin(&rkcanfd_stats->syncp);
+
+		data[RKCANFD_STATS_TYPE_RX_FIFO_EMPTY_ERRORS] =
+			u64_stats_read(&rkcanfd_stats->rx_fifo_empty_errors);
+		data[RKCANFD_STATS_TYPE_TX_EXTENDED_AS_STANDARD_ERRORS] =
+			u64_stats_read(&rkcanfd_stats->tx_extended_as_standard_errors);
+	} while (u64_stats_fetch_retry(&rkcanfd_stats->syncp, start));
+}
+
+static const struct ethtool_ops rkcanfd_ethtool_ops = {
+	.get_ts_info = ethtool_op_get_ts_info,
+	.get_strings = rkcanfd_ethtool_get_strings,
+	.get_sset_count = rkcanfd_ethtool_get_sset_count,
+	.get_ethtool_stats = rkcanfd_ethtool_get_ethtool_stats,
+};
+
+void rkcanfd_ethtool_init(struct rkcanfd_priv *priv)
+{
+	priv->ndev->ethtool_ops = &rkcanfd_ethtool_ops;
+
+	u64_stats_init(&priv->stats.syncp);
+}
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index eff08948840c..9f72483dab18 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -96,6 +96,7 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 				bool *tx_done)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
+	struct rkcanfd_stats *rkcanfd_stats = &priv->stats;
 	const struct canfd_frame *cfd_nominal;
 	const struct sk_buff *skb;
 	unsigned int tx_tail;
@@ -166,6 +167,9 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 		return 0;
 
 	/* Affected by Erratum 6 */
+	u64_stats_update_begin(&rkcanfd_stats->syncp);
+	u64_stats_inc(&rkcanfd_stats->tx_extended_as_standard_errors);
+	u64_stats_update_end(&rkcanfd_stats->syncp);
 
 	/* Manual handling of CAN Bus Error counters. See
 	 * rkcanfd_get_corrected_berr_counter() for detailed
@@ -211,8 +215,15 @@ static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 			 cfd->data, sizeof(cfd->data));
 
 	/* Erratum 5: Counters for TXEFIFO and RXFIFO may be wrong */
-	if (rkcanfd_fifo_header_empty(header))
+	if (rkcanfd_fifo_header_empty(header)) {
+		struct rkcanfd_stats *rkcanfd_stats = &priv->stats;
+
+		u64_stats_update_begin(&rkcanfd_stats->syncp);
+		u64_stats_inc(&rkcanfd_stats->rx_fifo_empty_errors);
+		u64_stats_update_end(&rkcanfd_stats->syncp);
+
 		return 0;
+	}
 
 	len = rkcanfd_fifo_header_to_cfd_header(priv, header, cfd);
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 67f135fbcfb9..f24a1d18be66 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -446,6 +446,16 @@ struct rkcanfd_fifo_header {
 	u32 ts;
 };
 
+struct rkcanfd_stats {
+	struct u64_stats_sync syncp;
+
+	/* Erratum 5 */
+	u64_stats_t rx_fifo_empty_errors;
+
+	/* Erratum 6 */
+	u64_stats_t tx_extended_as_standard_errors;
+};
+
 struct rkcanfd_priv {
 	struct can_priv can;
 	struct can_rx_offload offload;
@@ -461,6 +471,8 @@ struct rkcanfd_priv {
 
 	struct can_berr_counter bec;
 
+	struct rkcanfd_stats stats;
+
 	struct reset_control *reset;
 	struct clk_bulk_data *clks;
 	int clks_num;
@@ -515,6 +527,8 @@ rkcanfd_get_tx_free(const struct rkcanfd_priv *priv)
 	return RKCANFD_TXFIFO_DEPTH - rkcanfd_get_tx_pending(priv);
 }
 
+void rkcanfd_ethtool_init(struct rkcanfd_priv *priv);
+
 int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv);
 
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv);
-- 
cgit v1.3-3-g829e


From ae002cc32ec49d9845cf361a81cd4a7a91a0384e Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 17 Jan 2024 18:56:35 +0100
Subject: can: rockchip_canfd: prepare to use full TX-FIFO depth

So far the TX-FIFO is only used with a depth of 1, although the
hardware offers a depth of 2.

The workaround for the chips that are affected by erratum 6, i.e. EFF
frames may be send as standard frames, is to re-send the EFF frame.
This means the driver cannot queue the next frame for sending, as long
ad the EFF frame has not been successfully send out.

Introduce rkcanfd_get_effective_tx_free() that returns "0" space in
the TX-FIFO if an EFF frame is pending and the actual free space in
the TX-FIFO otherwise. Then replace rkcanfd_get_tx_free() with
rkcanfd_get_effective_tx_free() everywhere.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-16-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-rx.c |  2 +-
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 38 ++++++++++++++++++++++++++--
 drivers/net/can/rockchip/rockchip_canfd.h    |  1 +
 3 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 9f72483dab18..bacef5e5dc39 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -124,7 +124,7 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 
 		WRITE_ONCE(priv->tx_tail, priv->tx_tail + 1);
 		netif_subqueue_completed_wake(priv->ndev, 0, 1, frame_len,
-					      rkcanfd_get_tx_free(priv),
+					      rkcanfd_get_effective_tx_free(priv),
 					      RKCANFD_TX_START_THRESHOLD);
 
 		*tx_done = true;
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index f8e74e814b3b..d10da548ba71 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -8,6 +8,40 @@
 
 #include "rockchip_canfd.h"
 
+static bool rkcanfd_tx_tail_is_eff(const struct rkcanfd_priv *priv)
+{
+	const struct canfd_frame *cfd;
+	const struct sk_buff *skb;
+	unsigned int tx_tail;
+
+	if (!rkcanfd_get_tx_pending(priv))
+		return false;
+
+	tx_tail = rkcanfd_get_tx_tail(priv);
+	skb = priv->can.echo_skb[tx_tail];
+	if (!skb) {
+		netdev_err(priv->ndev,
+			   "%s: echo_skb[%u]=NULL tx_head=0x%08x tx_tail=0x%08x\n",
+			   __func__, tx_tail,
+			   priv->tx_head, priv->tx_tail);
+
+		return false;
+	}
+
+	cfd = (struct canfd_frame *)skb->data;
+
+	return cfd->can_id & CAN_EFF_FLAG;
+}
+
+unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv)
+{
+	if (priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_6 &&
+	    rkcanfd_tx_tail_is_eff(priv))
+		return 0;
+
+	return rkcanfd_get_tx_free(priv);
+}
+
 static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
 					 const u32 reg_cmd)
 {
@@ -42,7 +76,7 @@ int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_OK;
 
 	if (!netif_subqueue_maybe_stop(priv->ndev, 0,
-				       rkcanfd_get_tx_free(priv),
+				       rkcanfd_get_effective_tx_free(priv),
 				       RKCANFD_TX_STOP_THRESHOLD,
 				       RKCANFD_TX_START_THRESHOLD)) {
 		if (net_ratelimit())
@@ -99,7 +133,7 @@ int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
 
 	netif_subqueue_maybe_stop(priv->ndev, 0,
-				  rkcanfd_get_tx_free(priv),
+				  rkcanfd_get_effective_tx_free(priv),
 				  RKCANFD_TX_STOP_THRESHOLD,
 				  RKCANFD_TX_START_THRESHOLD);
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index f24a1d18be66..37d90400429f 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -533,6 +533,7 @@ int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv);
 
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv);
 
+unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv);
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv);
 int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
-- 
cgit v1.3-3-g829e


From a5605d61c7dd9473498d402a725ca49c915b0ac4 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 18 Jan 2024 08:54:23 +0100
Subject: can: rockchip_canfd: enable full TX-FIFO depth of 2

The previous commit prepared the TX path to make use of the full
TX-FIFO depth as much as possible. Increase the available TX-FIFO
depth to the hardware maximum of 2.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-17-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 37d90400429f..6be2865ec95a 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -288,7 +288,7 @@
 
 #define DEVICE_NAME "rockchip_canfd"
 #define RKCANFD_NAPI_WEIGHT 32
-#define RKCANFD_TXFIFO_DEPTH 1
+#define RKCANFD_TXFIFO_DEPTH 2
 #define RKCANFD_TX_STOP_THRESHOLD 1
 #define RKCANFD_TX_START_THRESHOLD 1
 
-- 
cgit v1.3-3-g829e


From 4e1a18bab1244204f873103eef1c0c88f794be85 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 22 Nov 2023 17:44:34 +0100
Subject: can: rockchip_canfd: add hardware timestamping support

Add support for hardware based timestamping.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-18-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c     |  6 ++
 drivers/net/can/rockchip/rockchip_canfd-ethtool.c  |  2 +-
 drivers/net/can/rockchip/rockchip_canfd-rx.c       |  1 +
 .../net/can/rockchip/rockchip_canfd-timestamp.c    | 94 +++++++++++++++++++++-
 drivers/net/can/rockchip/rockchip_canfd-tx.c       |  4 +
 drivers/net/can/rockchip/rockchip_canfd.h          | 11 +++
 6 files changed, 115 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 4db552bfc4db..015623314e88 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -292,6 +292,8 @@ static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
 
 	rkcanfd_chip_fifo_setup(priv);
 	rkcanfd_timestamp_init(priv);
+	rkcanfd_timestamp_start(priv);
+
 	rkcanfd_set_bittiming(priv);
 
 	rkcanfd_chip_interrupts_disable(priv);
@@ -315,6 +317,7 @@ static void rkcanfd_chip_stop(struct rkcanfd_priv *priv, const enum can_state st
 {
 	priv->can.state = state;
 
+	rkcanfd_timestamp_stop(priv);
 	__rkcanfd_chip_stop(priv, state);
 }
 
@@ -322,6 +325,7 @@ static void rkcanfd_chip_stop_sync(struct rkcanfd_priv *priv, const enum can_sta
 {
 	priv->can.state = state;
 
+	rkcanfd_timestamp_stop_sync(priv);
 	__rkcanfd_chip_stop(priv, state);
 }
 
@@ -353,6 +357,8 @@ rkcanfd_alloc_can_err_skb(struct rkcanfd_priv *priv,
 	*timestamp = rkcanfd_get_timestamp(priv);
 
 	skb = alloc_can_err_skb(priv->ndev, cf);
+	if (skb)
+		rkcanfd_skb_set_timestamp(priv, skb, *timestamp);
 
 	return skb;
 }
diff --git a/drivers/net/can/rockchip/rockchip_canfd-ethtool.c b/drivers/net/can/rockchip/rockchip_canfd-ethtool.c
index 0084f37b2b9f..5aeeef64a67a 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-ethtool.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-ethtool.c
@@ -59,7 +59,7 @@ rkcanfd_ethtool_get_ethtool_stats(struct net_device *ndev,
 }
 
 static const struct ethtool_ops rkcanfd_ethtool_ops = {
-	.get_ts_info = ethtool_op_get_ts_info,
+	.get_ts_info = can_ethtool_op_get_ts_info_hwts,
 	.get_strings = rkcanfd_ethtool_get_strings,
 	.get_sset_count = rkcanfd_ethtool_get_sset_count,
 	.get_ethtool_stats = rkcanfd_ethtool_get_ethtool_stats,
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index bacef5e5dc39..d862116840eb 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -267,6 +267,7 @@ static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 	}
 
 	memcpy(skb_cfd, cfd, len);
+	rkcanfd_skb_set_timestamp(priv, skb, header->ts);
 
 	err = can_rx_offload_queue_timestamp(&priv->offload, skb, header->ts);
 	if (err)
diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
index 9301b3ceceb0..81cccc5fd838 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -4,12 +4,102 @@
 //               Marc Kleine-Budde <kernel@pengutronix.de>
 //
 
+#include <linux/clocksource.h>
+
 #include "rockchip_canfd.h"
 
+static u64 rkcanfd_timestamp_read(const struct cyclecounter *cc)
+{
+	const struct rkcanfd_priv *priv = container_of(cc, struct rkcanfd_priv, cc);
+
+	return rkcanfd_get_timestamp(priv);
+}
+
+void rkcanfd_skb_set_timestamp(const struct rkcanfd_priv *priv,
+			       struct sk_buff *skb, const u32 timestamp)
+{
+	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
+	u64 ns;
+
+	ns = timecounter_cyc2time(&priv->tc, timestamp);
+
+	hwtstamps->hwtstamp = ns_to_ktime(ns);
+}
+
+static void rkcanfd_timestamp_work(struct work_struct *work)
+{
+	const struct delayed_work *delayed_work = to_delayed_work(work);
+	struct rkcanfd_priv *priv;
+
+	priv = container_of(delayed_work, struct rkcanfd_priv, timestamp);
+	timecounter_read(&priv->tc);
+
+	schedule_delayed_work(&priv->timestamp, priv->work_delay_jiffies);
+}
+
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv)
 {
-	u32 reg;
+	const struct can_bittiming *dbt = &priv->can.data_bittiming;
+	const struct can_bittiming *bt = &priv->can.bittiming;
+	struct cyclecounter *cc = &priv->cc;
+	u32 bitrate, div, reg, rate;
+	u64 work_delay_ns;
+	u64 max_cycles;
 
-	reg = RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_ENABLE;
+	/* At the standard clock rate of 300Mhz on the rk3658, the 32
+	 * bit timer overflows every 14s. This means that we have to
+	 * poll it quite often to avoid missing a wrap around.
+	 *
+	 * Divide it down to a reasonable rate, at least twice the bit
+	 * rate.
+	 */
+	bitrate = max(bt->bitrate, dbt->bitrate);
+	div = min(DIV_ROUND_UP(priv->can.clock.freq, bitrate * 2),
+		  FIELD_MAX(RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_PRESCALE) + 1);
+
+	reg = FIELD_PREP(RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_PRESCALE,
+			 div - 1) |
+		RKCANFD_REG_TIMESTAMP_CTRL_TIME_BASE_COUNTER_ENABLE;
 	rkcanfd_write(priv, RKCANFD_REG_TIMESTAMP_CTRL, reg);
+
+	cc->read = rkcanfd_timestamp_read;
+	cc->mask = CYCLECOUNTER_MASK(32);
+
+	rate = priv->can.clock.freq / div;
+	clocks_calc_mult_shift(&cc->mult, &cc->shift, rate, NSEC_PER_SEC,
+			       RKCANFD_TIMESTAMP_WORK_MAX_DELAY_SEC);
+
+	max_cycles = div_u64(ULLONG_MAX, cc->mult);
+	max_cycles = min(max_cycles, cc->mask);
+	work_delay_ns = clocksource_cyc2ns(max_cycles, cc->mult, cc->shift) / 3;
+	priv->work_delay_jiffies = nsecs_to_jiffies(work_delay_ns);
+	INIT_DELAYED_WORK(&priv->timestamp, rkcanfd_timestamp_work);
+
+	netdev_dbg(priv->ndev, "clock=%lu.%02luMHz bitrate=%lu.%02luMBit/s div=%u rate=%lu.%02luMHz mult=%u shift=%u delay=%lus\n",
+		   priv->can.clock.freq / MEGA,
+		   priv->can.clock.freq % MEGA / KILO / 10,
+		   bitrate / MEGA,
+		   bitrate % MEGA / KILO / 100,
+		   div,
+		   rate / MEGA,
+		   rate % MEGA / KILO / 10,
+		   cc->mult, cc->shift,
+		   priv->work_delay_jiffies / HZ);
+}
+
+void rkcanfd_timestamp_start(struct rkcanfd_priv *priv)
+{
+	timecounter_init(&priv->tc, &priv->cc, ktime_get_real_ns());
+
+	schedule_delayed_work(&priv->timestamp, priv->work_delay_jiffies);
+}
+
+void rkcanfd_timestamp_stop(struct rkcanfd_priv *priv)
+{
+	cancel_delayed_work(&priv->timestamp);
+}
+
+void rkcanfd_timestamp_stop_sync(struct rkcanfd_priv *priv)
+{
+	cancel_delayed_work_sync(&priv->timestamp);
 }
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index d10da548ba71..f954f38b955f 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -145,8 +145,10 @@ void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
 	unsigned int tx_tail;
+	struct sk_buff *skb;
 
 	tx_tail = rkcanfd_get_tx_tail(priv);
+	skb = priv->can.echo_skb[tx_tail];
 
 	/* Manual handling of CAN Bus Error counters. See
 	 * rkcanfd_get_corrected_berr_counter() for detailed
@@ -155,6 +157,8 @@ void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 	if (priv->bec.txerr)
 		priv->bec.txerr--;
 
+	if (skb)
+		rkcanfd_skb_set_timestamp(priv, skb, ts);
 	stats->tx_bytes +=
 		can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload,
 							    tx_tail, ts,
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 6be2865ec95a..3efd7f174e14 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -15,6 +15,7 @@
 #include <linux/netdevice.h>
 #include <linux/reset.h>
 #include <linux/skbuff.h>
+#include <linux/timecounter.h>
 #include <linux/types.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/units.h>
@@ -469,6 +470,11 @@ struct rkcanfd_priv {
 	u32 reg_int_mask_default;
 	struct rkcanfd_devtype_data devtype_data;
 
+	struct cyclecounter cc;
+	struct timecounter tc;
+	struct delayed_work timestamp;
+	unsigned long work_delay_jiffies;
+
 	struct can_berr_counter bec;
 
 	struct rkcanfd_stats stats;
@@ -531,7 +537,12 @@ void rkcanfd_ethtool_init(struct rkcanfd_priv *priv);
 
 int rkcanfd_handle_rx_int(struct rkcanfd_priv *priv);
 
+void rkcanfd_skb_set_timestamp(const struct rkcanfd_priv *priv,
+			       struct sk_buff *skb, const u32 timestamp);
 void rkcanfd_timestamp_init(struct rkcanfd_priv *priv);
+void rkcanfd_timestamp_start(struct rkcanfd_priv *priv);
+void rkcanfd_timestamp_stop(struct rkcanfd_priv *priv);
+void rkcanfd_timestamp_stop_sync(struct rkcanfd_priv *priv);
 
 unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv);
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv);
-- 
cgit v1.3-3-g829e


From edf1dd18c8f9c7ef01c6e0e934a9526f9acae873 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 25 Dec 2023 18:51:11 +0100
Subject: can: rockchip_canfd: add support for CAN_CTRLMODE_LOOPBACK

Add support for loopback mode.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-19-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 7 ++++++-
 drivers/net/can/rockchip/rockchip_canfd-rx.c   | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 015623314e88..8853f6a135da 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -276,6 +276,11 @@ static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
 		RKCANFD_REG_MODE_RXSTX_MODE |
 		RKCANFD_REG_MODE_WORK_MODE;
 
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		priv->reg_mode_default |= RKCANFD_REG_MODE_LBACK_MODE |
+			RKCANFD_REG_MODE_SILENT_MODE |
+			RKCANFD_REG_MODE_SELF_TEST;
+
 	/* mask, i.e. ignore:
 	 * - TIMESTAMP_COUNTER_OVERFLOW_INT - timestamp counter overflow interrupt
 	 * - TX_ARBIT_FAIL_INT - TX arbitration fail interrupt
@@ -894,7 +899,7 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	priv->can.clock.freq = clk_get_rate(priv->clks[0].clk);
 	priv->can.bittiming_const = &rkcanfd_bittiming_const;
 	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
-	priv->can.ctrlmode_supported = 0;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK;
 	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 	priv->can.do_set_mode = rkcanfd_set_mode;
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index d862116840eb..475c0409e215 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -243,7 +243,7 @@ static int rkcanfd_handle_rx_int_one(struct rkcanfd_priv *priv)
 		err = rkcanfd_rxstx_filter(priv, cfd, header->ts, &tx_done);
 		if (err)
 			return err;
-		if (tx_done)
+		if (tx_done && !(priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK))
 			return 0;
 	}
 
-- 
cgit v1.3-3-g829e


From e3b5fa0f081b1eca1e5b6771a524e1c633e9a788 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Tue, 19 Dec 2023 12:33:30 +0100
Subject: can: rockchip_canfd: add support for CAN_CTRLMODE_BERR_REPORTING

Add support for Bus Error Reporting.

Tested-by: Alibek Omarov <a1ba.omarov@gmail.com>
Acked-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20240904-rockchip-canfd-v5-20-8ae22bcb27cc@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 8853f6a135da..6883153e8fc1 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -293,6 +293,12 @@ static void rkcanfd_chip_start(struct rkcanfd_priv *priv)
 		RKCANFD_REG_INT_OVERLOAD_INT |
 		RKCANFD_REG_INT_TX_FINISH_INT;
 
+	/* Do not mask the bus error interrupt if the bus error
+	 * reporting is requested.
+	 */
+	if (!(priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING))
+		priv->reg_int_mask_default |= RKCANFD_REG_INT_ERROR_INT;
+
 	memset(&priv->bec, 0x0, sizeof(priv->bec));
 
 	rkcanfd_chip_fifo_setup(priv);
@@ -533,14 +539,16 @@ static int rkcanfd_handle_error_int(struct rkcanfd_priv *priv)
 	if (!reg_ec)
 		return 0;
 
-	skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
-	if (cf) {
-		struct can_berr_counter bec;
+	if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) {
+		skb = rkcanfd_alloc_can_err_skb(priv, &cf, &timestamp);
+		if (cf) {
+			struct can_berr_counter bec;
 
-		rkcanfd_get_berr_counter_corrected(priv, &bec);
-		cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR | CAN_ERR_CNT;
-		cf->data[6] = bec.txerr;
-		cf->data[7] = bec.rxerr;
+			rkcanfd_get_berr_counter_corrected(priv, &bec);
+			cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR | CAN_ERR_CNT;
+			cf->data[6] = bec.txerr;
+			cf->data[7] = bec.rxerr;
+		}
 	}
 
 	rkcanfd_handle_error_int_reg_ec(priv, cf, reg_ec);
@@ -899,7 +907,8 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	priv->can.clock.freq = clk_get_rate(priv->clks[0].clk);
 	priv->can.bittiming_const = &rkcanfd_bittiming_const;
 	priv->can.data_bittiming_const = &rkcanfd_data_bittiming_const;
-	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
+		CAN_CTRLMODE_BERR_REPORTING;
 	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_CANFD_BROKEN))
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 	priv->can.do_set_mode = rkcanfd_set_mode;
-- 
cgit v1.3-3-g829e


From 1705341485ff1eec097dfa26891d03afe5907e16 Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Sun, 1 Sep 2024 20:45:34 -0700
Subject: net: mana: Improve mana_set_channels() in low mem conditions

The mana_set_channels() function requires detaching the mana
driver and reattaching it with changed channel values.
During this operation if the system is low on memory, the reattach
might fail, causing the network device being down.
To avoid this we pre-allocate buffers at the beginning of set operation,
to prevent complete network loss

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/1725248734-21760-1-git-send-email-shradhagupta@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c      |  6 ++---
 drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 28 ++++++++++++----------
 include/net/mana/mana.h                            |  2 +-
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 3e865985340e..a174ca719aba 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -608,7 +608,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
 	*datasize = mtu + ETH_HLEN;
 }
 
-int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
+int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_queues)
 {
 	struct device *dev;
 	struct page *page;
@@ -622,7 +622,7 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
 
 	dev = mpc->ac->gdma_dev->gdma_context->dev;
 
-	num_rxb = mpc->num_queues * mpc->rx_queue_size;
+	num_rxb = num_queues * mpc->rx_queue_size;
 
 	WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n");
 	mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL);
@@ -682,7 +682,7 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu)
 	int err;
 
 	/* Pre-allocate buffers to prevent failure in mana_attach later */
-	err = mana_pre_alloc_rxbufs(mpc, new_mtu);
+	err = mana_pre_alloc_rxbufs(mpc, new_mtu, mpc->num_queues);
 	if (err) {
 		netdev_err(ndev, "Insufficient memory for new MTU\n");
 		return err;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index d6a35fbda447..dc3864377538 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -345,27 +345,29 @@ static int mana_set_channels(struct net_device *ndev,
 	struct mana_port_context *apc = netdev_priv(ndev);
 	unsigned int new_count = channels->combined_count;
 	unsigned int old_count = apc->num_queues;
-	int err, err2;
+	int err;
+
+	err = mana_pre_alloc_rxbufs(apc, ndev->mtu, new_count);
+	if (err) {
+		netdev_err(ndev, "Insufficient memory for new allocations");
+		return err;
+	}
 
 	err = mana_detach(ndev, false);
 	if (err) {
 		netdev_err(ndev, "mana_detach failed: %d\n", err);
-		return err;
+		goto out;
 	}
 
 	apc->num_queues = new_count;
 	err = mana_attach(ndev);
-	if (!err)
-		return 0;
-
-	netdev_err(ndev, "mana_attach failed: %d\n", err);
-
-	/* Try to roll it back to the old configuration. */
-	apc->num_queues = old_count;
-	err2 = mana_attach(ndev);
-	if (err2)
-		netdev_err(ndev, "mana re-attach failed: %d\n", err2);
+	if (err) {
+		apc->num_queues = old_count;
+		netdev_err(ndev, "mana_attach failed: %d\n", err);
+	}
 
+out:
+	mana_pre_dealloc_rxbufs(apc);
 	return err;
 }
 
@@ -414,7 +416,7 @@ static int mana_set_ringparam(struct net_device *ndev,
 
 	/* pre-allocating new buffers to prevent failures in mana_attach() later */
 	apc->rx_queue_size = new_rx;
-	err = mana_pre_alloc_rxbufs(apc, ndev->mtu);
+	err = mana_pre_alloc_rxbufs(apc, ndev->mtu, apc->num_queues);
 	apc->rx_queue_size = old_rx;
 	if (err) {
 		netdev_err(ndev, "Insufficient memory for new allocations\n");
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 1f869624811d..dfbf78d4e557 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -488,7 +488,7 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
 void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 void mana_query_gf_stats(struct mana_port_context *apc);
-int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu);
+int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
 void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
 
 extern const struct ethtool_ops mana_ethtool_ops;
-- 
cgit v1.3-3-g829e


From 510c0732fc8cabe7bca8de291c74d3f3cc36df48 Mon Sep 17 00:00:00 2001
From: James Chapman <jchapman@katalix.com>
Date: Tue, 3 Sep 2024 12:35:47 +0100
Subject: l2tp: remove unneeded null check in l2tp_v2_session_get_next

Commit aa92c1cec92b ("l2tp: add tunnel/session get_next helpers") uses
idr_get_next APIs to iterate over l2tp session IDR lists.  Sessions in
l2tp_v2_session_idr always have a non-null session->tunnel pointer
since l2tp_session_register sets it before inserting the session into
the IDR. Therefore the null check on session->tunnel in
l2tp_v2_session_get_next is redundant and can be removed. Removing the
check avoids a warning from lkp.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/r/202408111407.HtON8jqa-lkp@intel.com/
CC: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: James Chapman <jchapman@katalix.com>
Acked-by: Tom Parkin <tparkin@katalix.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240903113547.1261048-1-jchapman@katalix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 32102d1ed4cd..3eec23ac5ab1 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -345,7 +345,7 @@ again:
 			goto again;
 		}
 
-		if (tunnel && tunnel->tunnel_id == tid &&
+		if (tunnel->tunnel_id == tid &&
 		    refcount_inc_not_zero(&session->ref_count)) {
 			rcu_read_unlock_bh();
 			return session;
-- 
cgit v1.3-3-g829e


From 1083d733eb2624837753046924a9248555a1bfbf Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 3 Sep 2024 16:35:54 +0300
Subject: ipv4: Fix user space build failure due to header change
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RT_TOS() from include/uapi/linux/in_route.h is defined using
IPTOS_TOS_MASK from include/uapi/linux/ip.h. This is problematic for
files such as include/net/ip_fib.h that want to use RT_TOS() as without
including both header files kernel compilation fails:

In file included from ./include/net/ip_fib.h:25,
                 from ./include/net/route.h:27,
                 from ./include/net/lwtunnel.h:9,
                 from net/core/dst.c:24:
./include/net/ip_fib.h: In function ‘fib_dscp_masked_match’:
./include/uapi/linux/in_route.h:31:32: error: ‘IPTOS_TOS_MASK’ undeclared (first use in this function)
   31 | #define RT_TOS(tos)     ((tos)&IPTOS_TOS_MASK)
      |                                ^~~~~~~~~~~~~~
./include/net/ip_fib.h:440:45: note: in expansion of macro ‘RT_TOS’
  440 |         return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos));

Therefore, cited commit changed linux/in_route.h to include linux/ip.h.
However, as reported by David, this breaks iproute2 compilation due
overlapping definitions between linux/ip.h and
/usr/include/netinet/ip.h:

In file included from ../include/uapi/linux/in_route.h:5,
                 from iproute.c:19:
../include/uapi/linux/ip.h:25:9: warning: "IPTOS_TOS" redefined
   25 | #define IPTOS_TOS(tos)          ((tos)&IPTOS_TOS_MASK)
      |         ^~~~~~~~~
In file included from iproute.c:17:
/usr/include/netinet/ip.h:222:9: note: this is the location of the previous definition
  222 | #define IPTOS_TOS(tos)          ((tos) & IPTOS_TOS_MASK)

Fix by changing include/net/ip_fib.h to include linux/ip.h. Note that
usage of RT_TOS() should not spread further in the kernel due to recent
work in this area.

Fixes: 1fa3314c14c6 ("ipv4: Centralize TOS matching")
Reported-by: David Ahern <dsahern@kernel.org>
Closes: https://lore.kernel.org/netdev/2f5146ff-507d-4cab-a195-b28c0c9e654e@kernel.org/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20240903133554.2807343-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_fib.h          | 1 +
 include/uapi/linux/in_route.h | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 269ec10f63e4..967e4dc555fa 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -22,6 +22,7 @@
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/refcount.h>
+#include <linux/ip.h>
 #include <linux/in_route.h>
 
 struct fib_config {
diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h
index 10bdd7e7107f..0cc2c23b47f8 100644
--- a/include/uapi/linux/in_route.h
+++ b/include/uapi/linux/in_route.h
@@ -2,8 +2,6 @@
 #ifndef _LINUX_IN_ROUTE_H
 #define _LINUX_IN_ROUTE_H
 
-#include <linux/ip.h>
-
 /* IPv4 routing cache flags */
 
 #define RTCF_DEAD	RTNH_F_DEAD
-- 
cgit v1.3-3-g829e


From 6ffa72acc9c933a065782cb49afde1130ca722f7 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 09:44:41 +0800
Subject: selftests: net: convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240904014441.1065753-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/psock_fanout.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 1a736f700be4..4f31e92ebd96 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -165,9 +165,9 @@ static void sock_fanout_set_ebpf(int fd)
 	attr.insns = (unsigned long) prog;
 	attr.insn_cnt = ARRAY_SIZE(prog);
 	attr.license = (unsigned long) "GPL";
-	attr.log_buf = (unsigned long) log_buf,
-	attr.log_size = sizeof(log_buf),
-	attr.log_level = 1,
+	attr.log_buf = (unsigned long) log_buf;
+	attr.log_size = sizeof(log_buf);
+	attr.log_level = 1;
 
 	pfd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
 	if (pfd < 0) {
-- 
cgit v1.3-3-g829e


From 71f1fea4f65deeb0e1a4442fe661cfc5a541a036 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 3 Sep 2024 16:53:24 +0300
Subject: ipv4: Unmask upper DSCP bits in __ip_queue_xmit()

The function is passed the full DS field in its 'tos' argument by its
two callers. It then masks the upper DSCP bits using RT_TOS() when
passing it to ip_route_output_ports().

Unmask the upper DSCP bits when passing 'tos' to ip_route_output_ports()
so that in the future it could perform the FIB lookup according to the
full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240903135327.2810535-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index eea443b7f65e..49811c9281d4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -494,7 +494,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 					   inet->inet_dport,
 					   inet->inet_sport,
 					   sk->sk_protocol,
-					   RT_TOS(tos),
+					   tos & INET_DSCP_MASK,
 					   sk->sk_bound_dev_if);
 		if (IS_ERR(rt))
 			goto no_route;
-- 
cgit v1.3-3-g829e


From 97edbbaad30368c2e0219d21987ceba5a303ba5f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 3 Sep 2024 16:53:25 +0300
Subject: ipv4: ipmr: Unmask upper DSCP bits in ipmr_queue_xmit()

Unmask the upper DSCP bits when calling ip_route_output_ports() so that
in the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240903135327.2810535-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ipmr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index f1a43199551b..089864c6a35e 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1869,7 +1869,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 					   vif->remote, vif->local,
 					   0, 0,
 					   IPPROTO_IPIP,
-					   RT_TOS(iph->tos), vif->link);
+					   iph->tos & INET_DSCP_MASK, vif->link);
 		if (IS_ERR(rt))
 			goto out_free;
 		encap = sizeof(struct iphdr);
@@ -1877,7 +1877,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
 		rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0,
 					   0, 0,
 					   IPPROTO_IPIP,
-					   RT_TOS(iph->tos), vif->link);
+					   iph->tos & INET_DSCP_MASK, vif->link);
 		if (IS_ERR(rt))
 			goto out_free;
 	}
-- 
cgit v1.3-3-g829e


From de1fb3e8b053bf29ab366ae56b43659e87985928 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 3 Sep 2024 16:53:26 +0300
Subject: ip6_tunnel: Unmask upper DSCP bits in ip4ip6_err()

Unmask the upper DSCP bits when calling ip_route_output_ports() so that
in the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240903135327.2810535-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_tunnel.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index ec51ab5063e8..b60e13c42bca 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -53,6 +53,7 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/dst_metadata.h>
+#include <net/inet_dscp.h>
 
 MODULE_AUTHOR("Ville Nuorvala");
 MODULE_DESCRIPTION("IPv6 tunneling device");
@@ -608,7 +609,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	/* Try to guess incoming interface */
 	rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr,
-				   0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
+				   0, 0, 0, IPPROTO_IPIP,
+				   eiph->tos & INET_DSCP_MASK, 0);
 	if (IS_ERR(rt))
 		goto out;
 
@@ -619,7 +621,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (rt->rt_flags & RTCF_LOCAL) {
 		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 					   eiph->daddr, eiph->saddr, 0, 0,
-					   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
+					   IPPROTO_IPIP,
+					   eiph->tos & INET_DSCP_MASK, 0);
 		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
-- 
cgit v1.3-3-g829e


From c9a1e2629d10669e86b772add4fdea84252442da Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 3 Sep 2024 16:53:27 +0300
Subject: ipv6: sit: Unmask upper DSCP bits in ipip6_tunnel_bind_dev()

Unmask the upper DSCP bits when calling ip_route_output_ports() so that
in the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240903135327.2810535-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/sit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 16b90a24c9ba..39bd8951bfca 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1112,7 +1112,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 							  iph->daddr, iph->saddr,
 							  0, 0,
 							  IPPROTO_IPV6,
-							  RT_TOS(iph->tos),
+							  iph->tos & INET_DSCP_MASK,
 							  tunnel->parms.link);
 
 		if (!IS_ERR(rt)) {
-- 
cgit v1.3-3-g829e


From 4614ac219e3f441c64d98d684edbdc8945d49dcc Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 3 Sep 2024 22:31:49 +0800
Subject: ionic: Remove redundant null pointer checks in
 ionic_debugfs_add_qcq()

Since the debugfs_create_dir() never returns a null pointer, checking
the return value for a null pointer is redundant, and using IS_ERR is
safe enough.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Link: https://patch.msgid.link/20240903143149.2004530-1-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
index 59e5a9f21105..c98b4e75e288 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c
@@ -123,7 +123,7 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	struct ionic_cq *cq = &qcq->cq;
 
 	qcq_dentry = debugfs_create_dir(q->name, lif->dentry);
-	if (IS_ERR_OR_NULL(qcq_dentry))
+	if (IS_ERR(qcq_dentry))
 		return;
 	qcq->dentry = qcq_dentry;
 
-- 
cgit v1.3-3-g829e


From 8ed6e71219a3571a5583db6f839e80eebaa2853d Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 3 Sep 2024 22:33:43 +0800
Subject: pds_core: Remove redundant null pointer checks

Since the debugfs_create_dir() never returns a null pointer, checking
the return value for a null pointer is redundant, and using IS_ERR is
safe enough.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Link: https://patch.msgid.link/20240903143343.2004652-1-lizetao1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/debugfs.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c
index 6bdd02b7aa6d..ac37a4e738ae 100644
--- a/drivers/net/ethernet/amd/pds_core/debugfs.c
+++ b/drivers/net/ethernet/amd/pds_core/debugfs.c
@@ -112,7 +112,7 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 	struct pdsc_cq *cq = &qcq->cq;
 
 	qcq_dentry = debugfs_create_dir(q->name, pdsc->dentry);
-	if (IS_ERR_OR_NULL(qcq_dentry))
+	if (IS_ERR(qcq_dentry))
 		return;
 	qcq->dentry = qcq_dentry;
 
@@ -123,7 +123,7 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 	debugfs_create_x32("accum_work", 0400, qcq_dentry, &qcq->accum_work);
 
 	q_dentry = debugfs_create_dir("q", qcq->dentry);
-	if (IS_ERR_OR_NULL(q_dentry))
+	if (IS_ERR(q_dentry))
 		return;
 
 	debugfs_create_u32("index", 0400, q_dentry, &q->index);
@@ -135,7 +135,7 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 	debugfs_create_u16("head", 0400, q_dentry, &q->head_idx);
 
 	cq_dentry = debugfs_create_dir("cq", qcq->dentry);
-	if (IS_ERR_OR_NULL(cq_dentry))
+	if (IS_ERR(cq_dentry))
 		return;
 
 	debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa);
@@ -148,7 +148,7 @@ void pdsc_debugfs_add_qcq(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 		struct pdsc_intr_info *intr = &pdsc->intr_info[qcq->intx];
 
 		intr_dentry = debugfs_create_dir("intr", qcq->dentry);
-		if (IS_ERR_OR_NULL(intr_dentry))
+		if (IS_ERR(intr_dentry))
 			return;
 
 		debugfs_create_u32("index", 0400, intr_dentry, &intr->index);
-- 
cgit v1.3-3-g829e


From 569bf6d481b0b823c3c9c3b8be77908fd7caf66b Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Tue, 3 Sep 2024 19:15:36 +0200
Subject: net: phy: Check for read errors in SIOCGMIIREG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When reading registers from the PHY using the SIOCGMIIREG IOCTL any
errors returned from either mdiobus_read() or mdiobus_c45_read() are
ignored, and parts of the returned error is passed as the register value
back to user-space.

For example, if mdiobus_c45_read() is used with a bus that do not
implement the read_c45() callback -EOPNOTSUPP is returned. This is
however directly stored in mii_data->val_out and returned as the
registers content. As val_out is a u16 the error code is truncated and
returned as a plausible register value.

Fix this by first checking the return value for errors before returning
it as the register content.

Before this patch,

    # phytool read eth0/0:1/0
    0xffa1

After this change,

    $ phytool read eth0/0:1/0
    error: phy_read (-95)

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20240903171536.628930-1-niklas.soderlund+renesas@ragnatech.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index cba3af926429..4f3e742907cb 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -342,14 +342,19 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 		if (mdio_phy_id_is_c45(mii_data->phy_id)) {
 			prtad = mdio_phy_id_prtad(mii_data->phy_id);
 			devad = mdio_phy_id_devad(mii_data->phy_id);
-			mii_data->val_out = mdiobus_c45_read(
-				phydev->mdio.bus, prtad, devad,
-				mii_data->reg_num);
+			ret = mdiobus_c45_read(phydev->mdio.bus, prtad, devad,
+					       mii_data->reg_num);
+
 		} else {
-			mii_data->val_out = mdiobus_read(
-				phydev->mdio.bus, mii_data->phy_id,
-				mii_data->reg_num);
+			ret = mdiobus_read(phydev->mdio.bus, mii_data->phy_id,
+					   mii_data->reg_num);
 		}
+
+		if (ret < 0)
+			return ret;
+
+		mii_data->val_out = ret;
+
 		return 0;
 
 	case SIOCSMIIREG:
-- 
cgit v1.3-3-g829e


From d57f7b45945ac0517ff8ea50655f00db6e8d637c Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Tue, 3 Sep 2024 14:49:12 -0400
Subject: net: cadence: macb: Enable software IRQ coalescing by default

This NIC doesn't have hardware IRQ coalescing. Under high load,
interrupts can adversely affect performance. To mitigate this, enable
software IRQ coalescing by default. On my system this increases receive
throughput with iperf3 from 853 MBit/sec to 934 MBit/s, decreases
interrupts from 69489/sec to 2016/sec, and decreases CPU utilization
from 27% (4x Cortex-A53) to 14%. Latency is not affected (as far as I
can tell).

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240903184912.4151926-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 127bb3208034..8e1e4b2b2386 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4184,6 +4184,8 @@ static int macb_init(struct platform_device *pdev)
 		dev->ethtool_ops = &macb_ethtool_ops;
 	}
 
+	netdev_sw_irq_coalesce_default_on(dev);
+
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	/* Set features */
-- 
cgit v1.3-3-g829e


From 9ecb64ed07efda833608d1095a5c0ee92179f035 Mon Sep 17 00:00:00 2001
From: Eric Huang <echuang@realtek.com>
Date: Wed, 28 Aug 2024 13:52:16 +0800
Subject: wifi: rtw89: adjust DIG threshold to reduce false alarm

Use RSSI without subtracting offset as packet detection lower bound and
set an absolute minimal threshold. It's equivalent to setting a higher
noise floor, thereby reducing false alarm and improving interference
endurance.

Signed-off-by: Eric Huang <echuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240828055217.10263-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/phy.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 59b98aa876dd..c7165e757842 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -5401,7 +5401,7 @@ static void rtw89_phy_dig_update_para(struct rtw89_dev *rtwdev)
 	memcpy(dig->igi_rssi_th, igi_rssi_th, sizeof(dig->igi_rssi_th));
 }
 
-static const u8 pd_low_th_offset = 20, dynamic_igi_min = 0x20;
+static const u8 pd_low_th_offset = 16, dynamic_igi_min = 0x20;
 static const u8 igi_max_performance_mode = 0x5a;
 static const u8 dynamic_pd_threshold_max;
 
@@ -5699,38 +5699,47 @@ void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev)
 }
 
 #define IGI_RSSI_MIN 10
+#define ABS_IGI_MIN 0xc
 void rtw89_phy_dig(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_dig_info *dig = &rtwdev->dig;
 	bool is_linked = rtwdev->total_sta_assoc > 0;
+	u8 igi_min;
 
 	if (unlikely(dig->bypass_dig)) {
 		dig->bypass_dig = false;
 		return;
 	}
 
+	rtw89_phy_dig_update_rssi_info(rtwdev);
+
 	if (!dig->is_linked_pre && is_linked) {
 		rtw89_debug(rtwdev, RTW89_DBG_DIG, "First connected\n");
 		rtw89_phy_dig_update_para(rtwdev);
+		dig->igi_fa_rssi = dig->igi_rssi;
 	} else if (dig->is_linked_pre && !is_linked) {
 		rtw89_debug(rtwdev, RTW89_DBG_DIG, "First disconnected\n");
 		rtw89_phy_dig_update_para(rtwdev);
+		dig->igi_fa_rssi = dig->igi_rssi;
 	}
 	dig->is_linked_pre = is_linked;
 
 	rtw89_phy_dig_igi_offset_by_env(rtwdev);
-	rtw89_phy_dig_update_rssi_info(rtwdev);
 
-	dig->dyn_igi_min = (dig->igi_rssi > IGI_RSSI_MIN) ?
-			    dig->igi_rssi - IGI_RSSI_MIN : 0;
-	dig->dyn_igi_max = dig->dyn_igi_min + IGI_OFFSET_MAX;
-	dig->igi_fa_rssi = dig->dyn_igi_min + dig->fa_rssi_ofst;
+	igi_min = max_t(int, dig->igi_rssi - IGI_RSSI_MIN, 0);
+	dig->dyn_igi_max = min(igi_min + IGI_OFFSET_MAX, igi_max_performance_mode);
+	dig->dyn_igi_min = max(igi_min, ABS_IGI_MIN);
 
-	dig->igi_fa_rssi = clamp(dig->igi_fa_rssi, dig->dyn_igi_min,
-				 dig->dyn_igi_max);
+	if (dig->dyn_igi_max >= dig->dyn_igi_min) {
+		dig->igi_fa_rssi += dig->fa_rssi_ofst;
+		dig->igi_fa_rssi = clamp(dig->igi_fa_rssi, dig->dyn_igi_min,
+					 dig->dyn_igi_max);
+	} else {
+		dig->igi_fa_rssi = dig->dyn_igi_max;
+	}
 
 	rtw89_debug(rtwdev, RTW89_DBG_DIG,
-		    "rssi=%03d, dyn(max,min)=(%d,%d), final_rssi=%d\n",
+		    "rssi=%03d, dyn_joint(max,min)=(%d,%d), final_rssi=%d\n",
 		    dig->igi_rssi, dig->dyn_igi_max, dig->dyn_igi_min,
 		    dig->igi_fa_rssi);
 
-- 
cgit v1.3-3-g829e


From c9ac071e30ba4f2e770a0705564790502a7b931f Mon Sep 17 00:00:00 2001
From: Eric Huang <echuang@realtek.com>
Date: Wed, 28 Aug 2024 13:52:17 +0800
Subject: wifi: rtw89: use frequency domain RSSI

To get more accurate RSSI, this commit includes frequency domain RSSI
info in RSSI calculation. Add correspond physts parsing and macro to
get frequency domain RSSI information for supported IC.

Signed-off-by: Eric Huang <echuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240828055217.10263-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c          | 73 +++++++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/core.h          | 17 +++++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c      |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c      |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c      |  1 +
 .../net/wireless/realtek/rtw89/rtw8852b_common.c   | 14 +++++
 .../net/wireless/realtek/rtw89/rtw8852b_common.h   |  9 +++
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c     |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c      |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c      | 33 ++++++++++
 drivers/net/wireless/realtek/rtw89/txrx.h          | 59 ++++++++++++++++-
 11 files changed, 208 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index f3db1a199b24..4553810634c6 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -1583,11 +1583,27 @@ static u16 rtw89_core_get_phy_status_ie_len(struct rtw89_dev *rtwdev,
 	return ie_len;
 }
 
+static void rtw89_core_parse_phy_status_ie01_v2(struct rtw89_dev *rtwdev,
+						const struct rtw89_phy_sts_iehdr *iehdr,
+						struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	const struct rtw89_phy_sts_ie01_v2 *ie;
+	u8 *rpl_fd = phy_ppdu->rpl_fd;
+
+	ie = (const struct rtw89_phy_sts_ie01_v2 *)iehdr;
+	rpl_fd[RF_PATH_A] = le32_get_bits(ie->w8, RTW89_PHY_STS_IE01_V2_W8_RPL_FD_A);
+	rpl_fd[RF_PATH_B] = le32_get_bits(ie->w8, RTW89_PHY_STS_IE01_V2_W8_RPL_FD_B);
+	rpl_fd[RF_PATH_C] = le32_get_bits(ie->w9, RTW89_PHY_STS_IE01_V2_W9_RPL_FD_C);
+	rpl_fd[RF_PATH_D] = le32_get_bits(ie->w9, RTW89_PHY_STS_IE01_V2_W9_RPL_FD_D);
+
+	phy_ppdu->bw_idx = le32_get_bits(ie->w5, RTW89_PHY_STS_IE01_V2_W5_BW_IDX);
+}
+
 static void rtw89_core_parse_phy_status_ie01(struct rtw89_dev *rtwdev,
 					     const struct rtw89_phy_sts_iehdr *iehdr,
 					     struct rtw89_rx_phy_ppdu *phy_ppdu)
 {
-	const struct rtw89_phy_sts_ie0 *ie = (const struct rtw89_phy_sts_ie0 *)iehdr;
+	const struct rtw89_phy_sts_ie01 *ie = (const struct rtw89_phy_sts_ie01 *)iehdr;
 	s16 cfo;
 	u32 t;
 
@@ -1598,12 +1614,17 @@ static void rtw89_core_parse_phy_status_ie01(struct rtw89_dev *rtwdev,
 		phy_ppdu->stbc = le32_get_bits(ie->w2, RTW89_PHY_STS_IE01_W2_STBC);
 	}
 
+	if (!phy_ppdu->hdr_2_en)
+		phy_ppdu->rx_path_en =
+			le32_get_bits(ie->w0, RTW89_PHY_STS_IE01_W0_RX_PATH_EN);
+
 	if (phy_ppdu->rate < RTW89_HW_RATE_OFDM6)
 		return;
 
 	if (!phy_ppdu->to_self)
 		return;
 
+	phy_ppdu->rpl_avg = le32_get_bits(ie->w0, RTW89_PHY_STS_IE01_W0_RSSI_AVG_FD);
 	phy_ppdu->ofdm.avg_snr = le32_get_bits(ie->w2, RTW89_PHY_STS_IE01_W2_AVG_SNR);
 	phy_ppdu->ofdm.evm_max = le32_get_bits(ie->w2, RTW89_PHY_STS_IE01_W2_EVM_MAX);
 	phy_ppdu->ofdm.evm_min = le32_get_bits(ie->w2, RTW89_PHY_STS_IE01_W2_EVM_MIN);
@@ -1619,6 +1640,39 @@ static void rtw89_core_parse_phy_status_ie01(struct rtw89_dev *rtwdev,
 	}
 
 	rtw89_phy_cfo_parse(rtwdev, cfo, phy_ppdu);
+
+	if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+		rtw89_core_parse_phy_status_ie01_v2(rtwdev, iehdr, phy_ppdu);
+}
+
+static void rtw89_core_parse_phy_status_ie00(struct rtw89_dev *rtwdev,
+					     const struct rtw89_phy_sts_iehdr *iehdr,
+					     struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	const struct rtw89_phy_sts_ie00 *ie = (const struct rtw89_phy_sts_ie00 *)iehdr;
+	u16 tmp_rpl;
+
+	tmp_rpl = le32_get_bits(ie->w0, RTW89_PHY_STS_IE00_W0_RPL);
+	phy_ppdu->rpl_avg = tmp_rpl >> 1;
+}
+
+static void rtw89_core_parse_phy_status_ie00_v2(struct rtw89_dev *rtwdev,
+						const struct rtw89_phy_sts_iehdr *iehdr,
+						struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	const struct rtw89_phy_sts_ie00_v2 *ie;
+	u8 *rpl_path = phy_ppdu->rpl_path;
+	u16 tmp_rpl[RF_PATH_MAX];
+	u8 i;
+
+	ie = (const struct rtw89_phy_sts_ie00_v2 *)iehdr;
+	tmp_rpl[RF_PATH_A] = le32_get_bits(ie->w4, RTW89_PHY_STS_IE00_V2_W4_RPL_TD_A);
+	tmp_rpl[RF_PATH_B] = le32_get_bits(ie->w4, RTW89_PHY_STS_IE00_V2_W4_RPL_TD_B);
+	tmp_rpl[RF_PATH_C] = le32_get_bits(ie->w4, RTW89_PHY_STS_IE00_V2_W4_RPL_TD_C);
+	tmp_rpl[RF_PATH_D] = le32_get_bits(ie->w5, RTW89_PHY_STS_IE00_V2_W5_RPL_TD_D);
+
+	for (i = 0; i < RF_PATH_MAX; i++)
+		rpl_path[i] = tmp_rpl[i] >> 1;
 }
 
 static int rtw89_core_process_phy_status_ie(struct rtw89_dev *rtwdev,
@@ -1630,6 +1684,11 @@ static int rtw89_core_process_phy_status_ie(struct rtw89_dev *rtwdev,
 	ie = le32_get_bits(iehdr->w0, RTW89_PHY_STS_IEHDR_TYPE);
 
 	switch (ie) {
+	case RTW89_PHYSTS_IE00_CMN_CCK:
+		rtw89_core_parse_phy_status_ie00(rtwdev, iehdr, phy_ppdu);
+		if (rtwdev->chip->chip_gen == RTW89_CHIP_BE)
+			rtw89_core_parse_phy_status_ie00_v2(rtwdev, iehdr, phy_ppdu);
+		break;
 	case RTW89_PHYSTS_IE01_CMN_OFDM:
 		rtw89_core_parse_phy_status_ie01(rtwdev, iehdr, phy_ppdu);
 		break;
@@ -1640,6 +1699,13 @@ static int rtw89_core_process_phy_status_ie(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static void rtw89_core_update_phy_ppdu_hdr_v2(struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	const struct rtw89_phy_sts_hdr_v2 *hdr = phy_ppdu->buf + PHY_STS_HDR_LEN;
+
+	phy_ppdu->rx_path_en = le32_get_bits(hdr->w0, RTW89_PHY_STS_HDR_V2_W0_PATH_EN);
+}
+
 static void rtw89_core_update_phy_ppdu(struct rtw89_rx_phy_ppdu *phy_ppdu)
 {
 	const struct rtw89_phy_sts_hdr *hdr = phy_ppdu->buf;
@@ -1651,6 +1717,10 @@ static void rtw89_core_update_phy_ppdu(struct rtw89_rx_phy_ppdu *phy_ppdu)
 	rssi[RF_PATH_B] = le32_get_bits(hdr->w1, RTW89_PHY_STS_HDR_W1_RSSI_B);
 	rssi[RF_PATH_C] = le32_get_bits(hdr->w1, RTW89_PHY_STS_HDR_W1_RSSI_C);
 	rssi[RF_PATH_D] = le32_get_bits(hdr->w1, RTW89_PHY_STS_HDR_W1_RSSI_D);
+
+	phy_ppdu->hdr_2_en = le32_get_bits(hdr->w0, RTW89_PHY_STS_HDR_W0_HDR_2_EN);
+	if (phy_ppdu->hdr_2_en)
+		rtw89_core_update_phy_ppdu_hdr_v2(phy_ppdu);
 }
 
 static int rtw89_core_rx_process_phy_ppdu(struct rtw89_dev *rtwdev,
@@ -1703,6 +1773,7 @@ static int rtw89_core_rx_parse_phy_sts(struct rtw89_dev *rtwdev,
 		}
 	}
 
+	rtw89_chip_convert_rpl_to_rssi(rtwdev, phy_ppdu);
 	rtw89_phy_antdiv_parse(rtwdev, phy_ppdu);
 
 	return 0;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 7c3aeedfd93a..4091c8838bc5 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -797,6 +797,11 @@ struct rtw89_rx_phy_ppdu {
 	u8 chan_idx;
 	u8 ie;
 	u16 rate;
+	u8 rpl_avg;
+	u8 rpl_path[RF_PATH_MAX];
+	u8 rpl_fd[RF_PATH_MAX];
+	u8 bw_idx;
+	u8 rx_path_en;
 	struct {
 		bool has;
 		u8 avg_snr;
@@ -809,6 +814,7 @@ struct rtw89_rx_phy_ppdu {
 	bool stbc;
 	bool to_self;
 	bool valid;
+	bool hdr_2_en;
 };
 
 enum rtw89_mac_idx {
@@ -3613,6 +3619,8 @@ struct rtw89_chip_ops {
 	void (*query_ppdu)(struct rtw89_dev *rtwdev,
 			   struct rtw89_rx_phy_ppdu *phy_ppdu,
 			   struct ieee80211_rx_status *status);
+	void (*convert_rpl_to_rssi)(struct rtw89_dev *rtwdev,
+				    struct rtw89_rx_phy_ppdu *phy_ppdu);
 	void (*ctrl_nbtg_bt_tx)(struct rtw89_dev *rtwdev, bool en,
 				enum rtw89_phy_idx phy_idx);
 	void (*cfg_txrx_path)(struct rtw89_dev *rtwdev);
@@ -6307,6 +6315,15 @@ static inline void rtw89_chip_query_ppdu(struct rtw89_dev *rtwdev,
 		chip->ops->query_ppdu(rtwdev, phy_ppdu, status);
 }
 
+static inline void rtw89_chip_convert_rpl_to_rssi(struct rtw89_dev *rtwdev,
+						  struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	if (chip->ops->convert_rpl_to_rssi)
+		chip->ops->convert_rpl_to_rssi(rtwdev, phy_ppdu);
+}
+
 static inline void rtw89_ctrl_nbtg_bt_tx(struct rtw89_dev *rtwdev, bool en,
 					 enum rtw89_phy_idx phy_idx)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 6dc07edd18a2..1679bd408ef3 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2387,6 +2387,7 @@ static const struct rtw89_chip_ops rtw8851b_chip_ops = {
 	.get_thermal		= rtw8851b_get_thermal,
 	.ctrl_btg_bt_rx		= rtw8851b_ctrl_btg_bt_rx,
 	.query_ppdu		= rtw8851b_query_ppdu,
+	.convert_rpl_to_rssi	= NULL,
 	.ctrl_nbtg_bt_tx	= rtw8851b_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8851b_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8851b_set_txpwr_ul_tb_offset,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 5eadb0cba29c..dde96bd63021 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2113,6 +2113,7 @@ static const struct rtw89_chip_ops rtw8852a_chip_ops = {
 	.get_thermal		= rtw8852a_get_thermal,
 	.ctrl_btg_bt_rx		= rtw8852a_ctrl_btg_bt_rx,
 	.query_ppdu		= rtw8852a_query_ppdu,
+	.convert_rpl_to_rssi	= NULL,
 	.ctrl_nbtg_bt_tx	= rtw8852a_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= NULL,
 	.set_txpwr_ul_tb_offset	= rtw8852a_set_txpwr_ul_tb_offset,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index b7e92ce9256b..12be52f76427 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -741,6 +741,7 @@ static const struct rtw89_chip_ops rtw8852b_chip_ops = {
 	.get_thermal		= rtw8852bx_get_thermal,
 	.ctrl_btg_bt_rx		= rtw8852bx_ctrl_btg_bt_rx,
 	.query_ppdu		= rtw8852bx_query_ppdu,
+	.convert_rpl_to_rssi	= rtw8852bx_convert_rpl_to_rssi,
 	.ctrl_nbtg_bt_tx	= rtw8852bx_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8852bx_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8852bx_set_txpwr_ul_tb_offset,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
index bd05880cfe8f..ede0ca5426ae 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
@@ -1947,6 +1947,19 @@ static void __rtw8852bx_query_ppdu(struct rtw89_dev *rtwdev,
 		rtw8852bx_fill_freq_with_ppdu(rtwdev, phy_ppdu, status);
 }
 
+static void __rtw8852bx_convert_rpl_to_rssi(struct rtw89_dev *rtwdev,
+					    struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	u8 delta = phy_ppdu->rpl_avg - phy_ppdu->rssi_avg;
+	u8 *rssi = phy_ppdu->rssi;
+	u8 i;
+
+	for (i = 0; i < RF_PATH_NUM_8852BX; i++)
+		rssi[i] += delta;
+
+	phy_ppdu->rssi_avg = phy_ppdu->rpl_avg;
+}
+
 static int __rtw8852bx_mac_enable_bb_rf(struct rtw89_dev *rtwdev)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;
@@ -2029,6 +2042,7 @@ const struct rtw8852bx_info rtw8852bx_info = {
 	.ctrl_nbtg_bt_tx = __rtw8852bx_ctrl_nbtg_bt_tx,
 	.ctrl_btg_bt_rx = __rtw8852bx_ctrl_btg_bt_rx,
 	.query_ppdu = __rtw8852bx_query_ppdu,
+	.convert_rpl_to_rssi = __rtw8852bx_convert_rpl_to_rssi,
 	.read_efuse = __rtw8852bx_read_efuse,
 	.read_phycap = __rtw8852bx_read_phycap,
 	.power_trim = __rtw8852bx_power_trim,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h
index a916e38c76c1..3dce5422f41e 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.h
@@ -146,6 +146,8 @@ struct rtw8852bx_info {
 	void (*query_ppdu)(struct rtw89_dev *rtwdev,
 			   struct rtw89_rx_phy_ppdu *phy_ppdu,
 			   struct ieee80211_rx_status *status);
+	void (*convert_rpl_to_rssi)(struct rtw89_dev *rtwdev,
+				    struct rtw89_rx_phy_ppdu *phy_ppdu);
 	int (*read_efuse)(struct rtw89_dev *rtwdev, u8 *log_map,
 			  enum rtw89_efuse_block block);
 	int (*read_phycap)(struct rtw89_dev *rtwdev, u8 *phycap_map);
@@ -293,6 +295,13 @@ void rtw8852bx_query_ppdu(struct rtw89_dev *rtwdev,
 	rtw8852bx_info.query_ppdu(rtwdev, phy_ppdu, status);
 }
 
+static inline
+void rtw8852bx_convert_rpl_to_rssi(struct rtw89_dev *rtwdev,
+				   struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	rtw8852bx_info.convert_rpl_to_rssi(rtwdev, phy_ppdu);
+}
+
 static inline
 int rtw8852bx_read_efuse(struct rtw89_dev *rtwdev, u8 *log_map,
 			 enum rtw89_efuse_block block)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 52a76d2646e9..7dfdcb5964e1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -675,6 +675,7 @@ static const struct rtw89_chip_ops rtw8852bt_chip_ops = {
 	.get_thermal		= rtw8852bx_get_thermal,
 	.ctrl_btg_bt_rx		= rtw8852bx_ctrl_btg_bt_rx,
 	.query_ppdu		= rtw8852bx_query_ppdu,
+	.convert_rpl_to_rssi	= rtw8852bx_convert_rpl_to_rssi,
 	.ctrl_nbtg_bt_tx	= rtw8852bx_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8852bx_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8852bx_set_txpwr_ul_tb_offset,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 4a7eaebcdddc..1c6e89ab0f4b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2890,6 +2890,7 @@ static const struct rtw89_chip_ops rtw8852c_chip_ops = {
 	.get_thermal		= rtw8852c_get_thermal,
 	.ctrl_btg_bt_rx		= rtw8852c_ctrl_btg_bt_rx,
 	.query_ppdu		= rtw8852c_query_ppdu,
+	.convert_rpl_to_rssi	= NULL,
 	.ctrl_nbtg_bt_tx	= rtw8852c_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8852c_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= rtw8852c_set_txpwr_ul_tb_offset,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 0ff9c9b275f8..63b1ff2f98ed 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2497,6 +2497,38 @@ static void rtw8922a_query_ppdu(struct rtw89_dev *rtwdev,
 		rtw8922a_fill_freq_with_ppdu(rtwdev, phy_ppdu, status);
 }
 
+static void rtw8922a_convert_rpl_to_rssi(struct rtw89_dev *rtwdev,
+					 struct rtw89_rx_phy_ppdu *phy_ppdu)
+{
+	/* Mapping to BW: 5, 10, 20, 40, 80, 160, 80_80 */
+	static const u8 bw_compensate[] = {0, 0, 0, 6, 12, 18, 0};
+	u8 *rssi = phy_ppdu->rssi;
+	u8 compensate = 0;
+	u16 rpl_tmp;
+	u8 i;
+
+	if (phy_ppdu->bw_idx < ARRAY_SIZE(bw_compensate))
+		compensate = bw_compensate[phy_ppdu->bw_idx];
+
+	for (i = 0; i < RF_PATH_NUM_8922A; i++) {
+		if (!(phy_ppdu->rx_path_en & BIT(i))) {
+			rssi[i] = 0;
+			phy_ppdu->rpl_path[i] = 0;
+			phy_ppdu->rpl_fd[i] = 0;
+		}
+		if (phy_ppdu->rate >= RTW89_HW_RATE_OFDM6) {
+			rpl_tmp = phy_ppdu->rpl_fd[i];
+			if (rpl_tmp)
+				rpl_tmp += compensate;
+
+			phy_ppdu->rpl_path[i] = rpl_tmp;
+		}
+		rssi[i] = phy_ppdu->rpl_path[i];
+	}
+
+	phy_ppdu->rssi_avg = phy_ppdu->rpl_avg;
+}
+
 static int rtw8922a_mac_enable_bb_rf(struct rtw89_dev *rtwdev)
 {
 	rtw89_write8_set(rtwdev, R_BE_FEN_RST_ENABLE,
@@ -2554,6 +2586,7 @@ static const struct rtw89_chip_ops rtw8922a_chip_ops = {
 	.get_thermal		= rtw8922a_get_thermal,
 	.ctrl_btg_bt_rx		= rtw8922a_ctrl_btg_bt_rx,
 	.query_ppdu		= rtw8922a_query_ppdu,
+	.convert_rpl_to_rssi	= rtw8922a_convert_rpl_to_rssi,
 	.ctrl_nbtg_bt_tx	= rtw8922a_ctrl_nbtg_bt_tx,
 	.cfg_txrx_path		= rtw8922a_bb_cfg_txrx_path,
 	.set_txpwr_ul_tb_offset	= NULL,
diff --git a/drivers/net/wireless/realtek/rtw89/txrx.h b/drivers/net/wireless/realtek/rtw89/txrx.h
index a33280ec2a25..b2e47829983f 100644
--- a/drivers/net/wireless/realtek/rtw89/txrx.h
+++ b/drivers/net/wireless/realtek/rtw89/txrx.h
@@ -441,6 +441,7 @@ struct rtw89_phy_sts_hdr {
 } __packed;
 
 #define RTW89_PHY_STS_HDR_W0_IE_MAP GENMASK(4, 0)
+#define RTW89_PHY_STS_HDR_W0_HDR_2_EN BIT(5)
 #define RTW89_PHY_STS_HDR_W0_VALID BIT(7)
 #define RTW89_PHY_STS_HDR_W0_LEN GENMASK(15, 8)
 #define RTW89_PHY_STS_HDR_W0_RSSI_AVG GENMASK(31, 24)
@@ -449,6 +450,13 @@ struct rtw89_phy_sts_hdr {
 #define RTW89_PHY_STS_HDR_W1_RSSI_C GENMASK(23, 16)
 #define RTW89_PHY_STS_HDR_W1_RSSI_D GENMASK(31, 24)
 
+struct rtw89_phy_sts_hdr_v2 {
+	__le32 w0;
+	__le32 w1;
+} __packed;
+
+#define RTW89_PHY_STS_HDR_V2_W0_PATH_EN GENMASK(20, 16)
+
 struct rtw89_phy_sts_iehdr {
 	__le32 w0;
 };
@@ -552,13 +560,43 @@ struct rtw89_phy_sts_iehdr {
 #define BE_RXD_HDR_OFFSET_MASK GENMASK(20, 16)
 #define BE_RXD_WL_HD_IV_LEN_MASK GENMASK(26, 21)
 
-struct rtw89_phy_sts_ie0 {
+struct rtw89_phy_sts_ie00 {
+	__le32 w0;
+	__le32 w1;
+	__le32 w2;
+	__le32 w3;
+} __packed;
+
+#define RTW89_PHY_STS_IE00_W0_RPL GENMASK(15, 7)
+
+struct rtw89_phy_sts_ie00_v2 {
 	__le32 w0;
 	__le32 w1;
 	__le32 w2;
+	__le32 w3;
+	__le32 w4;
+	__le32 w5;
+	__le32 w6;
+	__le32 w7;
+} __packed;
+
+#define RTW89_PHY_STS_IE00_V2_W4_RPL_TD_A GENMASK(8, 0)
+#define RTW89_PHY_STS_IE00_V2_W4_RPL_TD_B GENMASK(17, 9)
+#define RTW89_PHY_STS_IE00_V2_W4_RPL_TD_C GENMASK(26, 18)
+#define RTW89_PHY_STS_IE00_V2_W5_RPL_TD_D GENMASK(8, 0)
+
+struct rtw89_phy_sts_ie01 {
+	__le32 w0;
+	__le32 w1;
+	__le32 w2;
+	__le32 w3;
+	__le32 w4;
+	__le32 w5;
 } __packed;
 
 #define RTW89_PHY_STS_IE01_W0_CH_IDX GENMASK(23, 16)
+#define RTW89_PHY_STS_IE01_W0_RSSI_AVG_FD GENMASK(15, 8)
+#define RTW89_PHY_STS_IE01_W0_RX_PATH_EN GENMASK(31, 28)
 #define RTW89_PHY_STS_IE01_W1_FD_CFO GENMASK(19, 8)
 #define RTW89_PHY_STS_IE01_W1_PREMB_CFO GENMASK(31, 20)
 #define RTW89_PHY_STS_IE01_W2_AVG_SNR GENMASK(5, 0)
@@ -567,6 +605,25 @@ struct rtw89_phy_sts_ie0 {
 #define RTW89_PHY_STS_IE01_W2_LDPC BIT(28)
 #define RTW89_PHY_STS_IE01_W2_STBC BIT(30)
 
+struct rtw89_phy_sts_ie01_v2 {
+	__le32 w0;
+	__le32 w1;
+	__le32 w2;
+	__le32 w3;
+	__le32 w4;
+	__le32 w5;
+	__le32 w6;
+	__le32 w7;
+	__le32 w8;
+	__le32 w9;
+} __packed;
+
+#define RTW89_PHY_STS_IE01_V2_W5_BW_IDX GENMASK(31, 29)
+#define RTW89_PHY_STS_IE01_V2_W8_RPL_FD_A GENMASK(11, 4)
+#define RTW89_PHY_STS_IE01_V2_W8_RPL_FD_B GENMASK(23, 16)
+#define RTW89_PHY_STS_IE01_V2_W9_RPL_FD_C GENMASK(11, 4)
+#define RTW89_PHY_STS_IE01_V2_W9_RPL_FD_D GENMASK(23, 16)
+
 enum rtw89_tx_channel {
 	RTW89_TXCH_ACH0	= 0,
 	RTW89_TXCH_ACH1	= 1,
-- 
cgit v1.3-3-g829e


From ed2e4bb17a4884cf29c3347353d8aabb7265b46c Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 2 Sep 2024 09:58:03 +0800
Subject: wifi: rtw89: avoid reading out of bounds when loading TX power FW
 elements

Because the loop-expression will do one more time before getting false from
cond-expression, the original code copied one more entry size beyond valid
region.

Fix it by moving the entry copy to loop-body.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20240902015803.20420-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 4091c8838bc5..4ed9034fdb46 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3978,16 +3978,22 @@ struct rtw89_txpwr_conf {
 	const void *data;
 };
 
+static inline bool rtw89_txpwr_entcpy(void *entry, const void *cursor, u8 size,
+				      const struct rtw89_txpwr_conf *conf)
+{
+	u8 valid_size = min(size, conf->ent_sz);
+
+	memcpy(entry, cursor, valid_size);
+	return true;
+}
+
 #define rtw89_txpwr_conf_valid(conf) (!!(conf)->data)
 
 #define rtw89_for_each_in_txpwr_conf(entry, cursor, conf) \
-	for (typecheck(const void *, cursor), (cursor) = (conf)->data, \
-	     memcpy(&(entry), cursor, \
-		    min_t(u8, sizeof(entry), (conf)->ent_sz)); \
+	for (typecheck(const void *, cursor), (cursor) = (conf)->data; \
 	     (cursor) < (conf)->data + (conf)->num_ents * (conf)->ent_sz; \
-	     (cursor) += (conf)->ent_sz, \
-	     memcpy(&(entry), cursor, \
-		    min_t(u8, sizeof(entry), (conf)->ent_sz)))
+	     (cursor) += (conf)->ent_sz) \
+		if (rtw89_txpwr_entcpy(&(entry), cursor, sizeof(entry), conf))
 
 struct rtw89_txpwr_byrate_data {
 	struct rtw89_txpwr_conf conf;
-- 
cgit v1.3-3-g829e


From d2095989943b88a4ab98d01d912c6c45925f2dcf Mon Sep 17 00:00:00 2001
From: Tan En De <ende.tan@starfivetech.com>
Date: Sat, 31 Aug 2024 09:11:14 +0800
Subject: net: stmmac: Batch set RX OWN flag and other flags

Minimize access to the RX descriptor by collecting all the flags in a
local variable and then updating the descriptor at once.

Signed-off-by: Tan En De <ende.tan@starfivetech.com>
Link: https://patch.msgid.link/20240831011114.2065912-1-ende.tan@starfivetech.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c   | 6 ++++--
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 1c5802e0d7f4..e99401bcc1f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -186,10 +186,12 @@ static void dwmac4_set_tx_owner(struct dma_desc *p)
 
 static void dwmac4_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
 {
-	p->des3 |= cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
+	u32 flags = (RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
 
 	if (!disable_rx_ic)
-		p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
+		flags |= RDES3_INT_ON_COMPLETION_EN;
+
+	p->des3 |= cpu_to_le32(flags);
 }
 
 static int dwmac4_get_tx_ls(struct dma_desc *p)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index fc82862a612c..389aad7b5c1e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -56,10 +56,12 @@ static void dwxgmac2_set_tx_owner(struct dma_desc *p)
 
 static void dwxgmac2_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
 {
-	p->des3 |= cpu_to_le32(XGMAC_RDES3_OWN);
+	u32 flags = XGMAC_RDES3_OWN;
 
 	if (!disable_rx_ic)
-		p->des3 |= cpu_to_le32(XGMAC_RDES3_IOC);
+		flags |= XGMAC_RDES3_IOC;
+
+	p->des3 |= cpu_to_le32(flags);
 }
 
 static int dwxgmac2_get_tx_ls(struct dma_desc *p)
-- 
cgit v1.3-3-g829e


From 1ddec5d0eec4b79461347cd9eaa880b9e4dd0567 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Sep 2024 08:34:55 +0800
Subject: bonding: add common function to check ipsec device

This patch adds a common function to check the status of IPSec devices.
This function will be useful for future implementations, such as IPSec ESN
and state offload callbacks.

Suggested-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 50 ++++++++++++++++++++++++++++++-----------
 1 file changed, 37 insertions(+), 13 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f13d413ad26c..46f46fea9152 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -418,6 +418,41 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev,
 /*---------------------------------- XFRM -----------------------------------*/
 
 #ifdef CONFIG_XFRM_OFFLOAD
+/**
+ * bond_ipsec_dev - Get active device for IPsec offload
+ * @xs: pointer to transformer state struct
+ *
+ * Context: caller must hold rcu_read_lock.
+ *
+ * Return: the device for ipsec offload, or NULL if not exist.
+ **/
+static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
+{
+	struct net_device *bond_dev = xs->xso.dev;
+	struct bonding *bond;
+	struct slave *slave;
+
+	if (!bond_dev)
+		return NULL;
+
+	bond = netdev_priv(bond_dev);
+	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
+		return NULL;
+
+	slave = rcu_dereference(bond->curr_active_slave);
+	if (!slave)
+		return NULL;
+
+	if (!xs->xso.real_dev)
+		return NULL;
+
+	if (xs->xso.real_dev != slave->dev)
+		pr_warn_ratelimited("%s: (slave %s): not same with IPsec offload real dev %s\n",
+				    bond_dev->name, slave->dev->name, xs->xso.real_dev->name);
+
+	return slave->dev;
+}
+
 /**
  * bond_ipsec_add_sa - program device with a security association
  * @xs: pointer to transformer state struct
@@ -640,23 +675,12 @@ out:
  **/
 static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 {
-	struct net_device *bond_dev = xs->xso.dev;
 	struct net_device *real_dev;
-	struct slave *curr_active;
-	struct bonding *bond;
 	bool ok = false;
 
-	bond = netdev_priv(bond_dev);
 	rcu_read_lock();
-	curr_active = rcu_dereference(bond->curr_active_slave);
-	if (!curr_active)
-		goto out;
-	real_dev = curr_active->dev;
-
-	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
-		goto out;
-
-	if (!xs->xso.real_dev)
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev)
 		goto out;
 
 	if (!real_dev->xfrmdev_ops ||
-- 
cgit v1.3-3-g829e


From 96d30bf9410954526106ea78659ba18ab9ce9ab5 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Sep 2024 08:34:56 +0800
Subject: bonding: Add ESN support to IPSec HW offload

Currently, users can see that bonding supports IPSec HW offload via ethtool.
However, this functionality does not work with NICs like Mellanox cards when
ESN (Extended Sequence Numbers) is enabled, as ESN functions are not yet
supported. This patch adds ESN support to the bonding IPSec device offload,
ensuring proper functionality with NICs that support ESN.

Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 46f46fea9152..a6628b1f33a7 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -694,11 +694,36 @@ out:
 	return ok;
 }
 
+/**
+ * bond_advance_esn_state - ESN support for IPSec HW offload
+ * @xs: pointer to transformer state struct
+ **/
+static void bond_advance_esn_state(struct xfrm_state *xs)
+{
+	struct net_device *real_dev;
+
+	rcu_read_lock();
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev)
+		goto out;
+
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_advance_esn) {
+		pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_advance_esn\n", __func__, real_dev->name);
+		goto out;
+	}
+
+	real_dev->xfrmdev_ops->xdo_dev_state_advance_esn(xs);
+out:
+	rcu_read_unlock();
+}
+
 static const struct xfrmdev_ops bond_xfrmdev_ops = {
 	.xdo_dev_state_add = bond_ipsec_add_sa,
 	.xdo_dev_state_delete = bond_ipsec_del_sa,
 	.xdo_dev_state_free = bond_ipsec_free_sa,
 	.xdo_dev_offload_ok = bond_ipsec_offload_ok,
+	.xdo_dev_state_advance_esn = bond_advance_esn_state,
 };
 #endif /* CONFIG_XFRM_OFFLOAD */
 
-- 
cgit v1.3-3-g829e


From 68db604e16d56f50de48cdd0c47f510394c1fbe9 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 4 Sep 2024 08:34:57 +0800
Subject: bonding: support xfrm state update

The patch add xfrm statistics update for bonding IPsec offload.

Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index a6628b1f33a7..47ab4ccd6fc1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -718,12 +718,37 @@ out:
 	rcu_read_unlock();
 }
 
+/**
+ * bond_xfrm_update_stats - Update xfrm state
+ * @xs: pointer to transformer state struct
+ **/
+static void bond_xfrm_update_stats(struct xfrm_state *xs)
+{
+	struct net_device *real_dev;
+
+	rcu_read_lock();
+	real_dev = bond_ipsec_dev(xs);
+	if (!real_dev)
+		goto out;
+
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_update_stats) {
+		pr_warn_ratelimited("%s: %s doesn't support xdo_dev_state_update_stats\n", __func__, real_dev->name);
+		goto out;
+	}
+
+	real_dev->xfrmdev_ops->xdo_dev_state_update_stats(xs);
+out:
+	rcu_read_unlock();
+}
+
 static const struct xfrmdev_ops bond_xfrmdev_ops = {
 	.xdo_dev_state_add = bond_ipsec_add_sa,
 	.xdo_dev_state_delete = bond_ipsec_del_sa,
 	.xdo_dev_state_free = bond_ipsec_free_sa,
 	.xdo_dev_offload_ok = bond_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = bond_advance_esn_state,
+	.xdo_dev_state_update_stats = bond_xfrm_update_stats,
 };
 #endif /* CONFIG_XFRM_OFFLOAD */
 
-- 
cgit v1.3-3-g829e


From 50ddaedeae7562b25e8eeca04f581d7c815be1db Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 4 Sep 2024 09:49:56 +0800
Subject: net: dsa: felix: Annotate struct action_gate_entry with __counted_by

Add the __counted_by compiler attribute to the flexible array member
entries to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and
CONFIG_FORTIFY_SOURCE.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240904014956.2035117-1-lihongbo22@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/ocelot/felix_vsc9959.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
index ba37a566da39..73d053501fb1 100644
--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
+++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
@@ -1733,7 +1733,7 @@ struct felix_stream_gate {
 	u64 cycletime;
 	u64 cycletime_ext;
 	u32 num_entries;
-	struct action_gate_entry entries[];
+	struct action_gate_entry entries[] __counted_by(num_entries);
 };
 
 struct felix_stream_gate_entry {
-- 
cgit v1.3-3-g829e


From 862bf7cbd772c2bad570ef0c5b5556a1330656dd Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Sat, 13 Jul 2024 15:00:10 +0200
Subject: wifi: mt76: mt7915: fix oops on non-dbdc mt7986
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

mt7915_band_config() sets band_idx = 1 on the main phy for mt7986
with MT7975_ONE_ADIE or MT7976_ONE_ADIE.

Commit 0335c034e726 ("wifi: mt76: fix race condition related to
checking tx queue fill status") introduced a dereference of the
phys array indirectly indexed by band_idx via wcid->phy_idx in
mt76_wcid_cleanup(). This caused the following Oops on affected
mt7986 devices:

 Unable to handle kernel read from unreadable memory at virtual address 0000000000000024
 Mem abort info:
   ESR = 0x0000000096000005
   EC = 0x25: DABT (current EL), IL = 32 bits
   SET = 0, FnV = 0
   EA = 0, S1PTW = 0
   FSC = 0x05: level 1 translation fault
 Data abort info:
   ISV = 0, ISS = 0x00000005
   CM = 0, WnR = 0
 user pgtable: 4k pages, 39-bit VAs, pgdp=0000000042545000
 [0000000000000024] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
 Internal error: Oops: 0000000096000005 [#1] SMP
 Modules linked in: ... mt7915e mt76_connac_lib mt76 mac80211 cfg80211 ...
 CPU: 2 PID: 1631 Comm: hostapd Not tainted 5.15.150 #0
 Hardware name: ZyXEL EX5700 (Telenor) (DT)
 pstate: 80400005 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : mt76_wcid_cleanup+0x84/0x22c [mt76]
 lr : mt76_wcid_cleanup+0x64/0x22c [mt76]
 sp : ffffffc00a803700
 x29: ffffffc00a803700 x28: ffffff80008f7300 x27: ffffff80003f3c00
 x26: ffffff80000a7880 x25: ffffffc008c26e00 x24: 0000000000000001
 x23: ffffffc000a68114 x22: 0000000000000000 x21: ffffff8004172cc8
 x20: ffffffc00a803748 x19: ffffff8004152020 x18: 0000000000000000
 x17: 00000000000017c0 x16: ffffffc008ef5000 x15: 0000000000000be0
 x14: ffffff8004172e28 x13: ffffff8004172e28 x12: 0000000000000000
 x11: 0000000000000000 x10: ffffff8004172e30 x9 : ffffff8004172e28
 x8 : 0000000000000000 x7 : ffffff8004156020 x6 : 0000000000000000
 x5 : 0000000000000031 x4 : 0000000000000000 x3 : 0000000000000001
 x2 : 0000000000000000 x1 : ffffff80008f7300 x0 : 0000000000000024
 Call trace:
  mt76_wcid_cleanup+0x84/0x22c [mt76]
  __mt76_sta_remove+0x70/0xbc [mt76]
  mt76_sta_state+0x8c/0x1a4 [mt76]
  mt7915_eeprom_get_power_delta+0x11e4/0x23a0 [mt7915e]
  drv_sta_state+0x144/0x274 [mac80211]
  sta_info_move_state+0x1cc/0x2a4 [mac80211]
  sta_set_sinfo+0xaf8/0xc24 [mac80211]
  sta_info_destroy_addr_bss+0x4c/0x6c [mac80211]

  ieee80211_color_change_finish+0x1c08/0x1e70 [mac80211]
  cfg80211_check_station_change+0x1360/0x4710 [cfg80211]
  genl_family_rcv_msg_doit+0xb4/0x110
  genl_rcv_msg+0xd0/0x1bc
  netlink_rcv_skb+0x58/0x120
  genl_rcv+0x34/0x50
  netlink_unicast+0x1f0/0x2ec
  netlink_sendmsg+0x198/0x3d0
  ____sys_sendmsg+0x1b0/0x210
  ___sys_sendmsg+0x80/0xf0
  __sys_sendmsg+0x44/0xa0
  __arm64_sys_sendmsg+0x20/0x30
  invoke_syscall.constprop.0+0x4c/0xe0
  do_el0_svc+0x40/0xd0
  el0_svc+0x14/0x4c
  el0t_64_sync_handler+0x100/0x110
  el0t_64_sync+0x15c/0x160
 Code: d2800002 910092c0 52800023 f9800011 (885f7c01)
 ---[ end trace 7e42dd9a39ed2281 ]---

Fix by using mt76_dev_phy() which will map band_idx to the correct phy
for all hardware combinations.

Fixes: 0335c034e726 ("wifi: mt76: fix race condition related to checking tx queue fill status")
Link: https://github.com/openwrt/openwrt/issues/14548
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Link: https://patch.msgid.link/20240713130010.516037-1-bjorn@mork.no
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index bb291fe314fb..d96ee759828e 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1529,7 +1529,7 @@ EXPORT_SYMBOL_GPL(mt76_wcid_init);
 
 void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid)
 {
-	struct mt76_phy *phy = dev->phys[wcid->phy_idx];
+	struct mt76_phy *phy = mt76_dev_phy(dev, wcid->phy_idx);
 	struct ieee80211_hw *hw;
 	struct sk_buff_head list;
 	struct sk_buff *skb;
-- 
cgit v1.3-3-g829e


From 723762a7a7e6fdb3cc6953f127a3fe9c5162beb7 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 6 Aug 2024 09:34:08 +0800
Subject: wifi: mt76: mt7921: fix wrong UNII-4 freq range check for the channel
 usage

The check should start from 5845 to 5925, which includes
channels 169, 173, and 177.

Fixes: 09382d8f8641 ("wifi: mt76: mt7921: update the channel usage when the regd domain changed")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20240806013408.17874-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index ef0c721d26e3..57672c69150e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -83,7 +83,7 @@ mt7921_regd_channel_update(struct wiphy *wiphy, struct mt792x_dev *dev)
 		}
 
 		/* UNII-4 */
-		if (IS_UNII_INVALID(0, 5850, 5925))
+		if (IS_UNII_INVALID(0, 5845, 5925))
 			ch->flags |= IEEE80211_CHAN_DISABLED;
 	}
 
-- 
cgit v1.3-3-g829e


From f98c3de92bb05dac4a4969df8a4595ed380b4604 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:25 +0800
Subject: wifi: mt76: mt7996: use hweight16 to get correct tx antenna

The chainmask is u16 so using hweight8 cannot get correct tx_ant.
Without this patch, the tx_ant of band 2 would be -1 and lead to the
following issue:
BUG: KASAN: stack-out-of-bounds in mt7996_mcu_add_sta+0x12e0/0x16e0 [mt7996e]

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-1-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 2e4fa9f48dfb..e68724e54013 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1653,7 +1653,7 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_phy *phy = mvif->phy;
-	int tx_ant = hweight8(phy->mt76->chainmask) - 1;
+	int tx_ant = hweight16(phy->mt76->chainmask) - 1;
 	struct sta_rec_bf *bf;
 	struct tlv *tlv;
 	static const u8 matrix[4][4] = {
-- 
cgit v1.3-3-g829e


From 376200f095d0c3a7096199b336204698d7086279 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:26 +0800
Subject: wifi: mt76: mt7996: fix traffic delay when switching back to working
 channel

During scanning, UNI_CHANNEL_RX_PATH tag is necessary for the firmware to
properly stop and resume MAC TX queue. Without this tag, HW needs more time
to resume traffic when switching back to working channel.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-2-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index bce082038219..f3f78e11a65f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -307,6 +307,10 @@ int mt7996_set_channel(struct mt7996_phy *phy)
 	if (ret)
 		goto out;
 
+	ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_RX_PATH);
+	if (ret)
+		goto out;
+
 	ret = mt7996_dfs_init_radar_detector(phy);
 	mt7996_mac_cca_stats_reset(phy);
 
-- 
cgit v1.3-3-g829e


From 9265397caacf5c0c2d10c40b2958a474664ebd9e Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:27 +0800
Subject: wifi: mt76: mt7996: fix wmm set of station interface to 3

According to connac3 HW design, the WMM index of AP and STA interface
should be 0 and 3, respectively.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-3-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index f3f78e11a65f..1ab2fb292266 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -206,7 +206,7 @@ static int mt7996_add_interface(struct ieee80211_hw *hw,
 	mvif->mt76.omac_idx = idx;
 	mvif->phy = phy;
 	mvif->mt76.band_idx = band_idx;
-	mvif->mt76.wmm_idx = vif->type != NL80211_IFTYPE_AP;
+	mvif->mt76.wmm_idx = vif->type == NL80211_IFTYPE_AP ? 0 : 3;
 
 	ret = mt7996_mcu_add_dev_info(phy, vif, true);
 	if (ret)
-- 
cgit v1.3-3-g829e


From 948f652498686a4ddcd9501d7d6418f0682e7e61 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:28 +0800
Subject: wifi: mt76: mt7996: advertize beacon_int_min_gcd

Advertize beacon_int_min_gcd as 100 to allow setting different beacon
intervals on different interfaces.

Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-4-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/init.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 283df84f1b43..4d6157e49b16 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -42,6 +42,7 @@ static const struct ieee80211_iface_combination if_comb[] = {
 				       BIT(NL80211_CHAN_WIDTH_40) |
 				       BIT(NL80211_CHAN_WIDTH_80) |
 				       BIT(NL80211_CHAN_WIDTH_160),
+		.beacon_int_min_gcd = 100,
 	}
 };
 
-- 
cgit v1.3-3-g829e


From e1f4847fdbdf5d44ae60e035c131920e5ab88598 Mon Sep 17 00:00:00 2001
From: Howard Hsu <howard-yh.hsu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:29 +0800
Subject: wifi: mt76: mt7996: fix HE and EHT beamforming capabilities

Fix HE and EHT beamforming capabilities for different bands and
interface types.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Fixes: 348533eb968d ("wifi: mt76: mt7996: add EHT capability init")
Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-5-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/init.c | 65 ++++++++++++++++--------
 1 file changed, 43 insertions(+), 22 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 4d6157e49b16..7e7e42b54c2e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -1012,8 +1012,6 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy,
 		return;
 
 	elem->phy_cap_info[3] |= IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER;
-	if (vif == NL80211_IFTYPE_AP)
-		elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER;
 
 	c = FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK,
 		       sts - 1) |
@@ -1021,6 +1019,11 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy,
 		       sts - 1);
 	elem->phy_cap_info[5] |= c;
 
+	if (vif != NL80211_IFTYPE_AP)
+		return;
+
+	elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER;
+
 	c = IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB |
 	    IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB;
 	elem->phy_cap_info[6] |= c;
@@ -1180,7 +1183,6 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 		IEEE80211_EHT_MAC_CAP0_OM_CONTROL;
 
 	eht_cap_elem->phy_cap_info[0] =
-		IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ |
 		IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI |
 		IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER |
 		IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE;
@@ -1194,30 +1196,36 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 		u8_encode_bits(u8_get_bits(val, GENMASK(2, 1)),
 			       IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK) |
 		u8_encode_bits(val,
-			       IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK) |
-		u8_encode_bits(val,
-			       IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK);
+			       IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK);
 
 	eht_cap_elem->phy_cap_info[2] =
 		u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK) |
-		u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK) |
-		u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK);
+		u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK);
+
+	if (band == NL80211_BAND_6GHZ) {
+		eht_cap_elem->phy_cap_info[0] |=
+			IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
+
+		eht_cap_elem->phy_cap_info[1] |=
+			u8_encode_bits(val,
+				       IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK);
+
+		eht_cap_elem->phy_cap_info[2] |=
+			u8_encode_bits(sts - 1,
+				       IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK);
+	}
 
 	eht_cap_elem->phy_cap_info[3] =
 		IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK |
 		IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK |
 		IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK |
-		IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK |
-		IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK |
-		IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK |
-		IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK;
+		IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK;
 
 	eht_cap_elem->phy_cap_info[4] =
 		u8_encode_bits(min_t(int, sts - 1, 2),
 			       IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK);
 
 	eht_cap_elem->phy_cap_info[5] =
-		IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK |
 		u8_encode_bits(IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US,
 			       IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK) |
 		u8_encode_bits(u8_get_bits(0x11, GENMASK(1, 0)),
@@ -1231,14 +1239,6 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 			       IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK) |
 		u8_encode_bits(val, IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK);
 
-	eht_cap_elem->phy_cap_info[7] =
-		IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
-		IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
-		IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ |
-		IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ |
-		IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ |
-		IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ;
-
 	val = u8_encode_bits(nss, IEEE80211_EHT_MCS_NSS_RX) |
 	      u8_encode_bits(nss, IEEE80211_EHT_MCS_NSS_TX);
 #define SET_EHT_MAX_NSS(_bw, _val) do {				\
@@ -1249,8 +1249,29 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 
 	SET_EHT_MAX_NSS(80, val);
 	SET_EHT_MAX_NSS(160, val);
-	SET_EHT_MAX_NSS(320, val);
+	if (band == NL80211_BAND_6GHZ)
+		SET_EHT_MAX_NSS(320, val);
 #undef SET_EHT_MAX_NSS
+
+	if (iftype != NL80211_IFTYPE_AP)
+		return;
+
+	eht_cap_elem->phy_cap_info[3] |=
+		IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK |
+		IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK;
+
+	eht_cap_elem->phy_cap_info[7] =
+		IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
+		IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
+		IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ |
+		IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ;
+
+	if (band != NL80211_BAND_6GHZ)
+		return;
+
+	eht_cap_elem->phy_cap_info[7] |=
+		IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ |
+		IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ;
 }
 
 static void
-- 
cgit v1.3-3-g829e


From 0cca3fe7453189b983eb68baea939192b58af8f0 Mon Sep 17 00:00:00 2001
From: Howard Hsu <howard-yh.hsu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:30 +0800
Subject: wifi: mt76: mt7996: set correct beamformee SS capability

According to IEEE P802.11be/D6.0 Table 9-417n, beamformee SS field stands
for the maximum number of spatial streams that the STA can receive in an
EHT sounding NDP minus 1, and the minimum value of this field is 3.

This value indicates the decoding capability of a beamformee, which is
independent of current antenna settings. Correct the value for mt7996
and mt7992 chipsets based on their HW capability.

Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-6-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/init.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
index 7e7e42b54c2e..5e96973226bb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
@@ -942,8 +942,12 @@ void mt7996_set_stream_vht_txbf_caps(struct mt7996_phy *phy)
 	cap = &phy->mt76->sband_5g.sband.vht_cap.cap;
 
 	*cap |= IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
-		IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE |
-		FIELD_PREP(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, sts - 1);
+		IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE;
+
+	if (is_mt7996(phy->mt76->dev))
+		*cap |= FIELD_PREP(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, 3);
+	else
+		*cap |= FIELD_PREP(IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK, 4);
 
 	*cap &= ~(IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK |
 		  IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE |
@@ -988,9 +992,15 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy,
 	    IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO;
 	elem->phy_cap_info[2] |= c;
 
-	c = IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
-	    IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 |
-	    IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4;
+	c = IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE;
+
+	if (is_mt7996(phy->mt76->dev))
+		c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 |
+		     IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4;
+	else
+		c |= IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 |
+		     IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5;
+
 	elem->phy_cap_info[4] |= c;
 
 	/* do not support NG16 due to spec D4.0 changes subcarrier idx */
@@ -1187,7 +1197,8 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
 		IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER |
 		IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE;
 
-	val = max_t(u8, sts - 1, 3);
+	/* Set the maximum capability regardless of the antenna configuration. */
+	val = is_mt7992(phy->mt76->dev) ? 4 : 3;
 	eht_cap_elem->phy_cap_info[0] |=
 		u8_encode_bits(u8_get_bits(val, BIT(0)),
 			       IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK);
-- 
cgit v1.3-3-g829e


From 9ca65757f0a5b393a7737d37f377d5daf91716af Mon Sep 17 00:00:00 2001
From: Howard Hsu <howard-yh.hsu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:31 +0800
Subject: wifi: mt76: mt7996: fix EHT beamforming capability check

If a VIF acts as a beamformer, it should check peer's beamformee
capability, and vice versa.

Fixes: ba01944adee9 ("wifi: mt76: mt7996: add EHT beamforming support")
Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-7-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index e68724e54013..daef014954d0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1429,10 +1429,10 @@ mt7996_is_ebf_supported(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 
 		if (bfee)
 			return vif->bss_conf.eht_su_beamformee &&
-			       EHT_PHY(CAP0_SU_BEAMFORMEE, pe->phy_cap_info[0]);
+			       EHT_PHY(CAP0_SU_BEAMFORMER, pe->phy_cap_info[0]);
 		else
 			return vif->bss_conf.eht_su_beamformer &&
-			       EHT_PHY(CAP0_SU_BEAMFORMER, pe->phy_cap_info[0]);
+			       EHT_PHY(CAP0_SU_BEAMFORMEE, pe->phy_cap_info[0]);
 	}
 
 	if (sta->deflink.he_cap.has_he) {
-- 
cgit v1.3-3-g829e


From 5dae5d09feebb2e305d825b3a5a4e4dae286ae20 Mon Sep 17 00:00:00 2001
From: Howard Hsu <howard-yh.hsu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:32 +0800
Subject: wifi: mt76: mt7996: set correct value in beamforming mcu command for
 mt7992

Configure correct bf number and bitmap in beamforming mcu command for
mt7992 chipsets, which only support dual-band.

Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-8-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index daef014954d0..238b1f78ff7c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -3923,8 +3923,9 @@ int mt7996_mcu_set_txbf(struct mt7996_dev *dev, u8 action)
 
 		tlv = mt7996_mcu_add_uni_tlv(skb, action, sizeof(*req_mod_en));
 		req_mod_en = (struct bf_mod_en_ctrl *)tlv;
-		req_mod_en->bf_num = 3;
-		req_mod_en->bf_bitmap = GENMASK(2, 0);
+		req_mod_en->bf_num = mt7996_band_valid(dev, MT_BAND2) ? 3 : 2;
+		req_mod_en->bf_bitmap = mt7996_band_valid(dev, MT_BAND2) ?
+					GENMASK(2, 0) : GENMASK(1, 0);
 		break;
 	}
 	default:
-- 
cgit v1.3-3-g829e


From 335cc75ce3d8ba27023bc4365b6f2cd25f0e0d25 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 09:50:03 +0800
Subject: ptp: ptp_idt82p33: Convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240904015003.1065872-1-nichen@iscas.ac.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/ptp/ptp_idt82p33.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c
index 92bb42c43fb2..d5732490ed9d 100644
--- a/drivers/ptp/ptp_idt82p33.c
+++ b/drivers/ptp/ptp_idt82p33.c
@@ -1171,10 +1171,10 @@ static void idt82p33_caps_init(u32 index, struct ptp_clock_info *caps,
 	caps->owner = THIS_MODULE;
 	caps->max_adj = DCO_MAX_PPB;
 	caps->n_per_out = MAX_PER_OUT;
-	caps->n_ext_ts = MAX_PHC_PLL,
-	caps->n_pins = max_pins,
-	caps->adjphase = idt82p33_adjwritephase,
-	caps->getmaxphase = idt82p33_getmaxphase,
+	caps->n_ext_ts = MAX_PHC_PLL;
+	caps->n_pins = max_pins;
+	caps->adjphase = idt82p33_adjwritephase;
+	caps->getmaxphase = idt82p33_getmaxphase;
 	caps->adjfine = idt82p33_adjfine;
 	caps->adjtime = idt82p33_adjtime;
 	caps->gettime64 = idt82p33_gettime;
-- 
cgit v1.3-3-g829e


From 8d878c87b5c45ae64b0aecd4aac71e210d19173f Mon Sep 17 00:00:00 2001
From: Frank Sae <Frank.Sae@motor-comm.com>
Date: Sun, 1 Sep 2024 01:35:25 -0700
Subject: net: phy: Optimize phy speed mask to be compatible to yt8821

yt8521 and yt8531s as Gigabit transceiver use bit15:14(bit9 reserved
default 0) as phy speed mask, yt8821 as 2.5G transceiver uses bit9 bit15:14
as phy speed mask.

Be compatible to yt8821, reform phy speed mask and phy speed macro.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Frank Sae <Frank.Sae@motor-comm.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/motorcomm.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c
index 7a11fdb687cc..fe0aabe12622 100644
--- a/drivers/net/phy/motorcomm.c
+++ b/drivers/net/phy/motorcomm.c
@@ -46,12 +46,10 @@
 
 /* Specific Status Register */
 #define YTPHY_SPECIFIC_STATUS_REG		0x11
-#define YTPHY_SSR_SPEED_MODE_OFFSET		14
-
-#define YTPHY_SSR_SPEED_MODE_MASK		(BIT(15) | BIT(14))
-#define YTPHY_SSR_SPEED_10M			0x0
-#define YTPHY_SSR_SPEED_100M			0x1
-#define YTPHY_SSR_SPEED_1000M			0x2
+#define YTPHY_SSR_SPEED_MASK			((0x3 << 14) | BIT(9))
+#define YTPHY_SSR_SPEED_10M			((0x0 << 14))
+#define YTPHY_SSR_SPEED_100M			((0x1 << 14))
+#define YTPHY_SSR_SPEED_1000M			((0x2 << 14))
 #define YTPHY_SSR_DUPLEX_OFFSET			13
 #define YTPHY_SSR_DUPLEX			BIT(13)
 #define YTPHY_SSR_PAGE_RECEIVED			BIT(12)
@@ -1187,8 +1185,7 @@ static int yt8521_adjust_status(struct phy_device *phydev, int status,
 	else
 		duplex = DUPLEX_FULL;	/* for fiber, it always DUPLEX_FULL */
 
-	speed_mode = (status & YTPHY_SSR_SPEED_MODE_MASK) >>
-		     YTPHY_SSR_SPEED_MODE_OFFSET;
+	speed_mode = status & YTPHY_SSR_SPEED_MASK;
 
 	switch (speed_mode) {
 	case YTPHY_SSR_SPEED_10M:
-- 
cgit v1.3-3-g829e


From b671105b88c3bb9acc1fb61a3ee2ca0ece60cb8d Mon Sep 17 00:00:00 2001
From: Frank Sae <Frank.Sae@motor-comm.com>
Date: Sun, 1 Sep 2024 01:35:26 -0700
Subject: net: phy: Add driver for Motorcomm yt8821 2.5G ethernet phy

Add a driver for the motorcomm yt8821 2.5G ethernet phy. Verified the
driver on BPI-R3(with MediaTek MT7986(Filogic 830) SoC) development board,
which is developed by Guangdong Bipai Technology Co., Ltd..

yt8821 2.5G ethernet phy works in AUTO_BX2500_SGMII or FORCE_BX2500
interface, supports 2.5G/1000M/100M/10M speeds, and wol(magic package).

Signed-off-by: Frank Sae <Frank.Sae@motor-comm.com>
Reviewed-by: Sai Krishna <saikrishnag@marvell.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/motorcomm.c | 671 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 667 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c
index fe0aabe12622..0e91f5d1a4fd 100644
--- a/drivers/net/phy/motorcomm.c
+++ b/drivers/net/phy/motorcomm.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * Motorcomm 8511/8521/8531/8531S PHY driver.
+ * Motorcomm 8511/8521/8531/8531S/8821 PHY driver.
  *
  * Author: Peter Geis <pgwipeout@gmail.com>
  * Author: Frank <Frank.Sae@motor-comm.com>
@@ -16,8 +16,8 @@
 #define PHY_ID_YT8521		0x0000011a
 #define PHY_ID_YT8531		0x4f51e91b
 #define PHY_ID_YT8531S		0x4f51e91a
-
-/* YT8521/YT8531S Register Overview
+#define PHY_ID_YT8821		0x4f51ea19
+/* YT8521/YT8531S/YT8821 Register Overview
  *	UTP Register space	|	FIBER Register space
  *  ------------------------------------------------------------
  * |	UTP MII			|	FIBER MII		|
@@ -50,6 +50,8 @@
 #define YTPHY_SSR_SPEED_10M			((0x0 << 14))
 #define YTPHY_SSR_SPEED_100M			((0x1 << 14))
 #define YTPHY_SSR_SPEED_1000M			((0x2 << 14))
+#define YTPHY_SSR_SPEED_10G			((0x3 << 14))
+#define YTPHY_SSR_SPEED_2500M			((0x0 << 14) | BIT(9))
 #define YTPHY_SSR_DUPLEX_OFFSET			13
 #define YTPHY_SSR_DUPLEX			BIT(13)
 #define YTPHY_SSR_PAGE_RECEIVED			BIT(12)
@@ -268,12 +270,89 @@
 #define YT8531_SCR_CLK_SRC_REF_25M		4
 #define YT8531_SCR_CLK_SRC_SSC_25M		5
 
+#define YT8821_SDS_EXT_CSR_CTRL_REG			0x23
+#define YT8821_SDS_EXT_CSR_VCO_LDO_EN			BIT(15)
+#define YT8821_SDS_EXT_CSR_VCO_BIAS_LPF_EN		BIT(8)
+
+#define YT8821_UTP_EXT_PI_CTRL_REG			0x56
+#define YT8821_UTP_EXT_PI_RST_N_FIFO			BIT(5)
+#define YT8821_UTP_EXT_PI_TX_CLK_SEL_AFE		BIT(4)
+#define YT8821_UTP_EXT_PI_RX_CLK_3_SEL_AFE		BIT(3)
+#define YT8821_UTP_EXT_PI_RX_CLK_2_SEL_AFE		BIT(2)
+#define YT8821_UTP_EXT_PI_RX_CLK_1_SEL_AFE		BIT(1)
+#define YT8821_UTP_EXT_PI_RX_CLK_0_SEL_AFE		BIT(0)
+
+#define YT8821_UTP_EXT_VCT_CFG6_CTRL_REG		0x97
+#define YT8821_UTP_EXT_FECHO_AMP_TH_HUGE		GENMASK(15, 8)
+
+#define YT8821_UTP_EXT_ECHO_CTRL_REG			0x336
+#define YT8821_UTP_EXT_TRACE_LNG_GAIN_THR_1000		GENMASK(14, 8)
+
+#define YT8821_UTP_EXT_GAIN_CTRL_REG			0x340
+#define YT8821_UTP_EXT_TRACE_MED_GAIN_THR_1000		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_RPDN_CTRL_REG			0x34E
+#define YT8821_UTP_EXT_RPDN_BP_FFE_LNG_2500		BIT(15)
+#define YT8821_UTP_EXT_RPDN_BP_FFE_SHT_2500		BIT(7)
+#define YT8821_UTP_EXT_RPDN_IPR_SHT_2500		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_TH_20DB_2500_CTRL_REG		0x36A
+#define YT8821_UTP_EXT_TH_20DB_2500			GENMASK(15, 0)
+
+#define YT8821_UTP_EXT_TRACE_CTRL_REG			0x372
+#define YT8821_UTP_EXT_TRACE_LNG_GAIN_THE_2500		GENMASK(14, 8)
+#define YT8821_UTP_EXT_TRACE_MED_GAIN_THE_2500		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_ALPHA_IPR_CTRL_REG		0x374
+#define YT8821_UTP_EXT_ALPHA_SHT_2500			GENMASK(14, 8)
+#define YT8821_UTP_EXT_IPR_LNG_2500			GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_PLL_CTRL_REG			0x450
+#define YT8821_UTP_EXT_PLL_SPARE_CFG			GENMASK(7, 0)
+
+#define YT8821_UTP_EXT_DAC_IMID_CH_2_3_CTRL_REG		0x466
+#define YT8821_UTP_EXT_DAC_IMID_CH_3_10_ORG		GENMASK(14, 8)
+#define YT8821_UTP_EXT_DAC_IMID_CH_2_10_ORG		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_DAC_IMID_CH_0_1_CTRL_REG		0x467
+#define YT8821_UTP_EXT_DAC_IMID_CH_1_10_ORG		GENMASK(14, 8)
+#define YT8821_UTP_EXT_DAC_IMID_CH_0_10_ORG		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_DAC_IMSB_CH_2_3_CTRL_REG		0x468
+#define YT8821_UTP_EXT_DAC_IMSB_CH_3_10_ORG		GENMASK(14, 8)
+#define YT8821_UTP_EXT_DAC_IMSB_CH_2_10_ORG		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_DAC_IMSB_CH_0_1_CTRL_REG		0x469
+#define YT8821_UTP_EXT_DAC_IMSB_CH_1_10_ORG		GENMASK(14, 8)
+#define YT8821_UTP_EXT_DAC_IMSB_CH_0_10_ORG		GENMASK(6, 0)
+
+#define YT8821_UTP_EXT_MU_COARSE_FR_CTRL_REG		0x4B3
+#define YT8821_UTP_EXT_MU_COARSE_FR_F_FFE		GENMASK(14, 12)
+#define YT8821_UTP_EXT_MU_COARSE_FR_F_FBE		GENMASK(10, 8)
+
+#define YT8821_UTP_EXT_MU_FINE_FR_CTRL_REG		0x4B5
+#define YT8821_UTP_EXT_MU_FINE_FR_F_FFE			GENMASK(14, 12)
+#define YT8821_UTP_EXT_MU_FINE_FR_F_FBE			GENMASK(10, 8)
+
+#define YT8821_UTP_EXT_VGA_LPF1_CAP_CTRL_REG		0x4D2
+#define YT8821_UTP_EXT_VGA_LPF1_CAP_OTHER		GENMASK(7, 4)
+#define YT8821_UTP_EXT_VGA_LPF1_CAP_2500		GENMASK(3, 0)
+
+#define YT8821_UTP_EXT_VGA_LPF2_CAP_CTRL_REG		0x4D3
+#define YT8821_UTP_EXT_VGA_LPF2_CAP_OTHER		GENMASK(7, 4)
+#define YT8821_UTP_EXT_VGA_LPF2_CAP_2500		GENMASK(3, 0)
+
+#define YT8821_UTP_EXT_TXGE_NFR_FR_THP_CTRL_REG		0x660
+#define YT8821_UTP_EXT_NFR_TX_ABILITY			BIT(3)
 /* Extended Register  end */
 
 #define YTPHY_DTS_OUTPUT_CLK_DIS		0
 #define YTPHY_DTS_OUTPUT_CLK_25M		25000000
 #define YTPHY_DTS_OUTPUT_CLK_125M		125000000
 
+#define YT8821_CHIP_MODE_AUTO_BX2500_SGMII	0
+#define YT8821_CHIP_MODE_FORCE_BX2500		1
+
 struct yt8521_priv {
 	/* combo_advertising is used for case of YT8521 in combo mode,
 	 * this means that yt8521 may work in utp or fiber mode which depends
@@ -2249,6 +2328,572 @@ static int yt8521_get_features(struct phy_device *phydev)
 	return ret;
 }
 
+/**
+ * yt8821_get_features - read mmd register to get 2.5G capability
+ * @phydev: target phy_device struct
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_get_features(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_c45_pma_read_ext_abilities(phydev);
+	if (ret < 0)
+		return ret;
+
+	return genphy_read_abilities(phydev);
+}
+
+/**
+ * yt8821_get_rate_matching - read register to get phy chip mode
+ * @phydev: target phy_device struct
+ * @iface: PHY data interface type
+ *
+ * Returns: rate matching type or negative errno code
+ */
+static int yt8821_get_rate_matching(struct phy_device *phydev,
+				    phy_interface_t iface)
+{
+	int val;
+
+	val = ytphy_read_ext_with_lock(phydev, YT8521_CHIP_CONFIG_REG);
+	if (val < 0)
+		return val;
+
+	if (FIELD_GET(YT8521_CCR_MODE_SEL_MASK, val) ==
+	    YT8821_CHIP_MODE_FORCE_BX2500)
+		return RATE_MATCH_PAUSE;
+
+	return RATE_MATCH_NONE;
+}
+
+/**
+ * yt8821_aneg_done() - determines the auto negotiation result
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0(no link)or 1(utp link) or negative errno code
+ */
+static int yt8821_aneg_done(struct phy_device *phydev)
+{
+	return yt8521_aneg_done_paged(phydev, YT8521_RSSR_UTP_SPACE);
+}
+
+/**
+ * yt8821_serdes_init() - serdes init
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_serdes_init(struct phy_device *phydev)
+{
+	int old_page;
+	int ret = 0;
+	u16 mask;
+	u16 set;
+
+	old_page = phy_select_page(phydev, YT8521_RSSR_FIBER_SPACE);
+	if (old_page < 0) {
+		phydev_err(phydev, "Failed to select page: %d\n",
+			   old_page);
+		goto err_restore_page;
+	}
+
+	ret = __phy_modify(phydev, MII_BMCR, BMCR_ANENABLE, 0);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_SDS_EXT_CSR_VCO_LDO_EN |
+		YT8821_SDS_EXT_CSR_VCO_BIAS_LPF_EN;
+	set = YT8821_SDS_EXT_CSR_VCO_LDO_EN;
+	ret = ytphy_modify_ext(phydev, YT8821_SDS_EXT_CSR_CTRL_REG, mask,
+			       set);
+
+err_restore_page:
+	return phy_restore_page(phydev, old_page, ret);
+}
+
+/**
+ * yt8821_utp_init() - utp init
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_utp_init(struct phy_device *phydev)
+{
+	int old_page;
+	int ret = 0;
+	u16 mask;
+	u16 save;
+	u16 set;
+
+	old_page = phy_select_page(phydev, YT8521_RSSR_UTP_SPACE);
+	if (old_page < 0) {
+		phydev_err(phydev, "Failed to select page: %d\n",
+			   old_page);
+		goto err_restore_page;
+	}
+
+	mask = YT8821_UTP_EXT_RPDN_BP_FFE_LNG_2500 |
+		YT8821_UTP_EXT_RPDN_BP_FFE_SHT_2500 |
+		YT8821_UTP_EXT_RPDN_IPR_SHT_2500;
+	set = YT8821_UTP_EXT_RPDN_BP_FFE_LNG_2500 |
+		YT8821_UTP_EXT_RPDN_BP_FFE_SHT_2500;
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_RPDN_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_VGA_LPF1_CAP_OTHER |
+		YT8821_UTP_EXT_VGA_LPF1_CAP_2500;
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_VGA_LPF1_CAP_CTRL_REG,
+			       mask, 0);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_VGA_LPF2_CAP_OTHER |
+		YT8821_UTP_EXT_VGA_LPF2_CAP_2500;
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_VGA_LPF2_CAP_CTRL_REG,
+			       mask, 0);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_TRACE_LNG_GAIN_THE_2500 |
+		YT8821_UTP_EXT_TRACE_MED_GAIN_THE_2500;
+	set = FIELD_PREP(YT8821_UTP_EXT_TRACE_LNG_GAIN_THE_2500, 0x5a) |
+		FIELD_PREP(YT8821_UTP_EXT_TRACE_MED_GAIN_THE_2500, 0x3c);
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_TRACE_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_IPR_LNG_2500;
+	set = FIELD_PREP(YT8821_UTP_EXT_IPR_LNG_2500, 0x6c);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_ALPHA_IPR_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_TRACE_LNG_GAIN_THR_1000;
+	set = FIELD_PREP(YT8821_UTP_EXT_TRACE_LNG_GAIN_THR_1000, 0x2a);
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_ECHO_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_TRACE_MED_GAIN_THR_1000;
+	set = FIELD_PREP(YT8821_UTP_EXT_TRACE_MED_GAIN_THR_1000, 0x22);
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_GAIN_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_TH_20DB_2500;
+	set = FIELD_PREP(YT8821_UTP_EXT_TH_20DB_2500, 0x8000);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_TH_20DB_2500_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_MU_COARSE_FR_F_FFE |
+		YT8821_UTP_EXT_MU_COARSE_FR_F_FBE;
+	set = FIELD_PREP(YT8821_UTP_EXT_MU_COARSE_FR_F_FFE, 0x7) |
+		FIELD_PREP(YT8821_UTP_EXT_MU_COARSE_FR_F_FBE, 0x7);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_MU_COARSE_FR_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_MU_FINE_FR_F_FFE |
+		YT8821_UTP_EXT_MU_FINE_FR_F_FBE;
+	set = FIELD_PREP(YT8821_UTP_EXT_MU_FINE_FR_F_FFE, 0x2) |
+		FIELD_PREP(YT8821_UTP_EXT_MU_FINE_FR_F_FBE, 0x2);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_MU_FINE_FR_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	/* save YT8821_UTP_EXT_PI_CTRL_REG's val for use later */
+	ret = ytphy_read_ext(phydev, YT8821_UTP_EXT_PI_CTRL_REG);
+	if (ret < 0)
+		goto err_restore_page;
+
+	save = ret;
+
+	mask = YT8821_UTP_EXT_PI_TX_CLK_SEL_AFE |
+		YT8821_UTP_EXT_PI_RX_CLK_3_SEL_AFE |
+		YT8821_UTP_EXT_PI_RX_CLK_2_SEL_AFE |
+		YT8821_UTP_EXT_PI_RX_CLK_1_SEL_AFE |
+		YT8821_UTP_EXT_PI_RX_CLK_0_SEL_AFE;
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_PI_CTRL_REG,
+			       mask, 0);
+	if (ret < 0)
+		goto err_restore_page;
+
+	/* restore YT8821_UTP_EXT_PI_CTRL_REG's val */
+	ret = ytphy_write_ext(phydev, YT8821_UTP_EXT_PI_CTRL_REG, save);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_FECHO_AMP_TH_HUGE;
+	set = FIELD_PREP(YT8821_UTP_EXT_FECHO_AMP_TH_HUGE, 0x38);
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_VCT_CFG6_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_NFR_TX_ABILITY;
+	set = YT8821_UTP_EXT_NFR_TX_ABILITY;
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_TXGE_NFR_FR_THP_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_PLL_SPARE_CFG;
+	set = FIELD_PREP(YT8821_UTP_EXT_PLL_SPARE_CFG, 0xe9);
+	ret = ytphy_modify_ext(phydev, YT8821_UTP_EXT_PLL_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_DAC_IMID_CH_3_10_ORG |
+		YT8821_UTP_EXT_DAC_IMID_CH_2_10_ORG;
+	set = FIELD_PREP(YT8821_UTP_EXT_DAC_IMID_CH_3_10_ORG, 0x64) |
+		FIELD_PREP(YT8821_UTP_EXT_DAC_IMID_CH_2_10_ORG, 0x64);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_DAC_IMID_CH_2_3_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_DAC_IMID_CH_1_10_ORG |
+		YT8821_UTP_EXT_DAC_IMID_CH_0_10_ORG;
+	set = FIELD_PREP(YT8821_UTP_EXT_DAC_IMID_CH_1_10_ORG, 0x64) |
+		FIELD_PREP(YT8821_UTP_EXT_DAC_IMID_CH_0_10_ORG, 0x64);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_DAC_IMID_CH_0_1_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_DAC_IMSB_CH_3_10_ORG |
+		YT8821_UTP_EXT_DAC_IMSB_CH_2_10_ORG;
+	set = FIELD_PREP(YT8821_UTP_EXT_DAC_IMSB_CH_3_10_ORG, 0x64) |
+		FIELD_PREP(YT8821_UTP_EXT_DAC_IMSB_CH_2_10_ORG, 0x64);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_DAC_IMSB_CH_2_3_CTRL_REG,
+			       mask, set);
+	if (ret < 0)
+		goto err_restore_page;
+
+	mask = YT8821_UTP_EXT_DAC_IMSB_CH_1_10_ORG |
+		YT8821_UTP_EXT_DAC_IMSB_CH_0_10_ORG;
+	set = FIELD_PREP(YT8821_UTP_EXT_DAC_IMSB_CH_1_10_ORG, 0x64) |
+		FIELD_PREP(YT8821_UTP_EXT_DAC_IMSB_CH_0_10_ORG, 0x64);
+	ret = ytphy_modify_ext(phydev,
+			       YT8821_UTP_EXT_DAC_IMSB_CH_0_1_CTRL_REG,
+			       mask, set);
+
+err_restore_page:
+	return phy_restore_page(phydev, old_page, ret);
+}
+
+/**
+ * yt8821_auto_sleep_config() - phy auto sleep config
+ * @phydev: a pointer to a &struct phy_device
+ * @enable: true enable auto sleep, false disable auto sleep
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_auto_sleep_config(struct phy_device *phydev,
+				    bool enable)
+{
+	int old_page;
+	int ret = 0;
+
+	old_page = phy_select_page(phydev, YT8521_RSSR_UTP_SPACE);
+	if (old_page < 0) {
+		phydev_err(phydev, "Failed to select page: %d\n",
+			   old_page);
+		goto err_restore_page;
+	}
+
+	ret = ytphy_modify_ext(phydev,
+			       YT8521_EXTREG_SLEEP_CONTROL1_REG,
+			       YT8521_ESC1R_SLEEP_SW,
+			       enable ? 1 : 0);
+
+err_restore_page:
+	return phy_restore_page(phydev, old_page, ret);
+}
+
+/**
+ * yt8821_soft_reset() - soft reset utp and serdes
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_soft_reset(struct phy_device *phydev)
+{
+	return ytphy_modify_ext_with_lock(phydev, YT8521_CHIP_CONFIG_REG,
+					  YT8521_CCR_SW_RST, 0);
+}
+
+/**
+ * yt8821_config_init() - phy initializatioin
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_config_init(struct phy_device *phydev)
+{
+	u8 mode = YT8821_CHIP_MODE_AUTO_BX2500_SGMII;
+	int ret;
+	u16 set;
+
+	if (phydev->interface == PHY_INTERFACE_MODE_2500BASEX)
+		mode = YT8821_CHIP_MODE_FORCE_BX2500;
+
+	set = FIELD_PREP(YT8521_CCR_MODE_SEL_MASK, mode);
+	ret = ytphy_modify_ext_with_lock(phydev,
+					 YT8521_CHIP_CONFIG_REG,
+					 YT8521_CCR_MODE_SEL_MASK,
+					 set);
+	if (ret < 0)
+		return ret;
+
+	__set_bit(PHY_INTERFACE_MODE_2500BASEX,
+		  phydev->possible_interfaces);
+
+	if (mode == YT8821_CHIP_MODE_AUTO_BX2500_SGMII) {
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  phydev->possible_interfaces);
+
+		phydev->rate_matching = RATE_MATCH_NONE;
+	} else if (mode == YT8821_CHIP_MODE_FORCE_BX2500) {
+		phydev->rate_matching = RATE_MATCH_PAUSE;
+	}
+
+	ret = yt8821_serdes_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	ret = yt8821_utp_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* disable auto sleep */
+	ret = yt8821_auto_sleep_config(phydev, false);
+	if (ret < 0)
+		return ret;
+
+	/* soft reset */
+	return yt8821_soft_reset(phydev);
+}
+
+/**
+ * yt8821_adjust_status() - update speed and duplex to phydev
+ * @phydev: a pointer to a &struct phy_device
+ * @val: read from YTPHY_SPECIFIC_STATUS_REG
+ */
+static void yt8821_adjust_status(struct phy_device *phydev, int val)
+{
+	int speed, duplex;
+	int speed_mode;
+
+	duplex = FIELD_GET(YTPHY_SSR_DUPLEX, val);
+	speed_mode = val & YTPHY_SSR_SPEED_MASK;
+	switch (speed_mode) {
+	case YTPHY_SSR_SPEED_10M:
+		speed = SPEED_10;
+		break;
+	case YTPHY_SSR_SPEED_100M:
+		speed = SPEED_100;
+		break;
+	case YTPHY_SSR_SPEED_1000M:
+		speed = SPEED_1000;
+		break;
+	case YTPHY_SSR_SPEED_2500M:
+		speed = SPEED_2500;
+		break;
+	default:
+		speed = SPEED_UNKNOWN;
+		break;
+	}
+
+	phydev->speed = speed;
+	phydev->duplex = duplex;
+}
+
+/**
+ * yt8821_update_interface() - update interface per current speed
+ * @phydev: a pointer to a &struct phy_device
+ */
+static void yt8821_update_interface(struct phy_device *phydev)
+{
+	if (!phydev->link)
+		return;
+
+	switch (phydev->speed) {
+	case SPEED_2500:
+		phydev->interface = PHY_INTERFACE_MODE_2500BASEX;
+		break;
+	case SPEED_1000:
+	case SPEED_100:
+	case SPEED_10:
+		phydev->interface = PHY_INTERFACE_MODE_SGMII;
+		break;
+	default:
+		phydev_warn(phydev, "phy speed err :%d\n", phydev->speed);
+		break;
+	}
+}
+
+/**
+ * yt8821_read_status() -  determines the negotiated speed and duplex
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_read_status(struct phy_device *phydev)
+{
+	int link;
+	int ret;
+	int val;
+
+	ret = ytphy_write_ext_with_lock(phydev,
+					YT8521_REG_SPACE_SELECT_REG,
+					YT8521_RSSR_UTP_SPACE);
+	if (ret < 0)
+		return ret;
+
+	ret = genphy_read_status(phydev);
+	if (ret < 0)
+		return ret;
+
+	if (phydev->autoneg_complete) {
+		ret = genphy_c45_read_lpa(phydev);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = phy_read(phydev, YTPHY_SPECIFIC_STATUS_REG);
+	if (ret < 0)
+		return ret;
+
+	val = ret;
+
+	link = val & YTPHY_SSR_LINK;
+	if (link)
+		yt8821_adjust_status(phydev, val);
+
+	if (link) {
+		if (phydev->link == 0)
+			phydev_dbg(phydev,
+				   "%s, phy addr: %d, link up\n",
+				   __func__, phydev->mdio.addr);
+		phydev->link = 1;
+	} else {
+		if (phydev->link == 1)
+			phydev_dbg(phydev,
+				   "%s, phy addr: %d, link down\n",
+				   __func__, phydev->mdio.addr);
+		phydev->link = 0;
+	}
+
+	val = ytphy_read_ext_with_lock(phydev, YT8521_CHIP_CONFIG_REG);
+	if (val < 0)
+		return val;
+
+	if (FIELD_GET(YT8521_CCR_MODE_SEL_MASK, val) ==
+	    YT8821_CHIP_MODE_AUTO_BX2500_SGMII)
+		yt8821_update_interface(phydev);
+
+	return 0;
+}
+
+/**
+ * yt8821_modify_utp_fiber_bmcr - bits modify a PHY's BMCR register
+ * @phydev: the phy_device struct
+ * @mask: bit mask of bits to clear
+ * @set: bit mask of bits to set
+ *
+ * NOTE: Convenience function which allows a PHY's BMCR register to be
+ * modified as new register value = (old register value & ~mask) | set.
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_modify_utp_fiber_bmcr(struct phy_device *phydev,
+					u16 mask, u16 set)
+{
+	int ret;
+
+	ret = yt8521_modify_bmcr_paged(phydev, YT8521_RSSR_UTP_SPACE,
+				       mask, set);
+	if (ret < 0)
+		return ret;
+
+	return yt8521_modify_bmcr_paged(phydev, YT8521_RSSR_FIBER_SPACE,
+					mask, set);
+}
+
+/**
+ * yt8821_suspend() - suspend the hardware
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_suspend(struct phy_device *phydev)
+{
+	int wol_config;
+
+	wol_config = ytphy_read_ext_with_lock(phydev,
+					      YTPHY_WOL_CONFIG_REG);
+	if (wol_config < 0)
+		return wol_config;
+
+	/* if wol enable, do nothing */
+	if (wol_config & YTPHY_WCR_ENABLE)
+		return 0;
+
+	return yt8821_modify_utp_fiber_bmcr(phydev, 0, BMCR_PDOWN);
+}
+
+/**
+ * yt8821_resume() - resume the hardware
+ * @phydev: a pointer to a &struct phy_device
+ *
+ * Returns: 0 or negative errno code
+ */
+static int yt8821_resume(struct phy_device *phydev)
+{
+	int wol_config;
+	int ret;
+
+	/* disable auto sleep */
+	ret = yt8821_auto_sleep_config(phydev, false);
+	if (ret < 0)
+		return ret;
+
+	wol_config = ytphy_read_ext_with_lock(phydev,
+					      YTPHY_WOL_CONFIG_REG);
+	if (wol_config < 0)
+		return wol_config;
+
+	/* if wol enable, do nothing */
+	if (wol_config & YTPHY_WCR_ENABLE)
+		return 0;
+
+	return yt8821_modify_utp_fiber_bmcr(phydev, BMCR_PDOWN, 0);
+}
+
 static struct phy_driver motorcomm_phy_drvs[] = {
 	{
 		PHY_ID_MATCH_EXACT(PHY_ID_YT8511),
@@ -2304,11 +2949,28 @@ static struct phy_driver motorcomm_phy_drvs[] = {
 		.suspend	= yt8521_suspend,
 		.resume		= yt8521_resume,
 	},
+	{
+		PHY_ID_MATCH_EXACT(PHY_ID_YT8821),
+		.name			= "YT8821 2.5Gbps PHY",
+		.get_features		= yt8821_get_features,
+		.read_page		= yt8521_read_page,
+		.write_page		= yt8521_write_page,
+		.get_wol		= ytphy_get_wol,
+		.set_wol		= ytphy_set_wol,
+		.config_aneg		= genphy_config_aneg,
+		.aneg_done		= yt8821_aneg_done,
+		.config_init		= yt8821_config_init,
+		.get_rate_matching	= yt8821_get_rate_matching,
+		.read_status		= yt8821_read_status,
+		.soft_reset		= yt8821_soft_reset,
+		.suspend		= yt8821_suspend,
+		.resume			= yt8821_resume,
+	},
 };
 
 module_phy_driver(motorcomm_phy_drvs);
 
-MODULE_DESCRIPTION("Motorcomm 8511/8521/8531/8531S PHY driver");
+MODULE_DESCRIPTION("Motorcomm 8511/8521/8531/8531S/8821 PHY driver");
 MODULE_AUTHOR("Peter Geis");
 MODULE_AUTHOR("Frank");
 MODULE_LICENSE("GPL");
@@ -2318,6 +2980,7 @@ static const struct mdio_device_id __maybe_unused motorcomm_tbl[] = {
 	{ PHY_ID_MATCH_EXACT(PHY_ID_YT8521) },
 	{ PHY_ID_MATCH_EXACT(PHY_ID_YT8531) },
 	{ PHY_ID_MATCH_EXACT(PHY_ID_YT8531S) },
+	{ PHY_ID_MATCH_EXACT(PHY_ID_YT8821) },
 	{ /* sentinel */ }
 };
 
-- 
cgit v1.3-3-g829e


From 6b083650a37318112fb60c65fbb6070584f53d93 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 4 Sep 2024 18:28:08 +0200
Subject: xsk: Bump xsk_queue::queue_empty_descs in xp_can_alloc()

We have STAT_FILL_EMPTY test case in xskxceiver that tries to process
traffic with fill queue being empty which currently fails for zero copy
ice driver after it started to use xsk_buff_can_alloc() API. That is
because xsk_queue::queue_empty_descs is currently only increased from
alloc APIs and right now if driver sees that xsk_buff_pool will be
unable to provide the requested count of buffers, it bails out early,
skipping calls to xsk_buff_alloc{_batch}().

Mentioned statistic should be handled in xsk_buff_can_alloc() from the
very beginning, so let's add this logic now. Do it by open coding
xskq_cons_has_entries() and bumping queue_empty_descs in the middle when
fill queue currently has no entries.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20240904162808.249160-1-maciej.fijalkowski@intel.com
---
 net/xdp/xsk_buff_pool.c | 10 +++++++++-
 net/xdp/xsk_queue.h     |  5 -----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index c0e0204b9630..dad7849c1b75 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -656,9 +656,17 @@ EXPORT_SYMBOL(xp_alloc_batch);
 
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count)
 {
+	u32 req_count, avail_count;
+
 	if (pool->free_list_cnt >= count)
 		return true;
-	return xskq_cons_has_entries(pool->fq, count - pool->free_list_cnt);
+
+	req_count = count - pool->free_list_cnt;
+	avail_count = xskq_cons_nb_entries(pool->fq, req_count);
+	if (!avail_count)
+		pool->fq->queue_empty_descs++;
+
+	return avail_count >= req_count;
 }
 EXPORT_SYMBOL(xp_can_alloc);
 
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 6f2d1621c992..406b20dfee8d 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -306,11 +306,6 @@ static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max)
 	return entries >= max ? max : entries;
 }
 
-static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt)
-{
-	return xskq_cons_nb_entries(q, cnt) >= cnt;
-}
-
 static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
 {
 	if (q->cached_prod == q->cached_cons)
-- 
cgit v1.3-3-g829e


From 820aa897837ff6c156f60423f82c0cb1d9b18103 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 16 Aug 2024 13:12:39 +0300
Subject: wifi: ath11k: Avoid -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Move the conflicting declaration to the end of the structure. Notice
that `struct ieee80211_chanctx_conf` is a flexible structure --a
structure that contains a flexible-array member.

Also, remove a couple of unused structures.

Fix the following warnings:
drivers/net/wireless/ath/ath11k/core.h:409:39: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/ath/ath11k/dp.h:1309:24: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/ath/ath11k/dp.h:1368:24: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/ZrZB3Rjswe0ZXtug@cute
---
 drivers/net/wireless/ath/ath11k/core.h |  8 +++++++-
 drivers/net/wireless/ath/ath11k/dp.h   | 23 -----------------------
 2 files changed, 7 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 7122176dd91e..018cff520c87 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -407,11 +407,17 @@ struct ath11k_vif {
 	bool wpaie_present;
 	bool bcca_zero_sent;
 	bool do_not_send_tmpl;
-	struct ieee80211_chanctx_conf chanctx;
 	struct ath11k_arp_ns_offload arp_ns_offload;
 	struct ath11k_rekey_data rekey_data;
 
 	struct ath11k_reg_tpc_power_info reg_tpc_info;
+
+	/* Must be last - ends in a flexible-array member.
+	 *
+	 * FIXME: Driver should not copy struct ieee80211_chanctx_conf,
+	 * especially because it has a flexible array. Find a better way.
+	 */
+	struct ieee80211_chanctx_conf chanctx;
 };
 
 struct ath11k_vif_iter {
diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h
index 2f6dd69d3be2..65d2bc0687c8 100644
--- a/drivers/net/wireless/ath/ath11k/dp.h
+++ b/drivers/net/wireless/ath/ath11k/dp.h
@@ -1305,18 +1305,6 @@ struct htt_ppdu_stats_user_rate {
 #define HTT_TX_INFO_PEERID(_flags) \
 			FIELD_GET(HTT_PPDU_STATS_TX_INFO_FLAGS_PEERID_M, _flags)
 
-struct htt_tx_ppdu_stats_info {
-	struct htt_tlv tlv_hdr;
-	u32 tx_success_bytes;
-	u32 tx_retry_bytes;
-	u32 tx_failed_bytes;
-	u32 flags; /* %HTT_PPDU_STATS_TX_INFO_FLAGS_ */
-	u16 tx_success_msdus;
-	u16 tx_retry_msdus;
-	u16 tx_failed_msdus;
-	u16 tx_duration; /* united in us */
-} __packed;
-
 enum  htt_ppdu_stats_usr_compln_status {
 	HTT_PPDU_STATS_USER_STATUS_OK,
 	HTT_PPDU_STATS_USER_STATUS_FILTERED,
@@ -1364,17 +1352,6 @@ struct htt_ppdu_stats_usr_cmpltn_ack_ba_status {
 	u32 success_bytes;
 } __packed;
 
-struct htt_ppdu_stats_usr_cmn_array {
-	struct htt_tlv tlv_hdr;
-	u32 num_ppdu_stats;
-	/* tx_ppdu_stats_info is filled by multiple struct htt_tx_ppdu_stats_info
-	 * elements.
-	 * tx_ppdu_stats_info is variable length, with length =
-	 *     number_of_ppdu_stats * sizeof (struct htt_tx_ppdu_stats_info)
-	 */
-	struct htt_tx_ppdu_stats_info tx_ppdu_info[];
-} __packed;
-
 struct htt_ppdu_user_stats {
 	u16 peer_id;
 	u32 tlv_flags;
-- 
cgit v1.3-3-g829e


From 02f454f9aa6255d99611d6a4e37edd08812878df Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 16 Aug 2024 13:12:39 +0300
Subject: wifi: ath12k: Avoid -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Move the conflicting declaration to the end of the structure. Notice
that `struct ieee80211_chanctx_conf` is a flexible structure --a
structure that contains a flexible-array member.

Also, remove an unused structure.

Fix the following warnings:
drivers/net/wireless/ath/ath12k/core.h:290:39: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/ath/ath12k/dp.h:1499:24: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: Kalle Valo <quic_kvalo@quicinc.com>
Link: https://patch.msgid.link/ZrZEuxJihMzAaTVh@cute
---
 drivers/net/wireless/ath/ath12k/core.h |  8 +++++++-
 drivers/net/wireless/ath/ath12k/dp.h   | 12 ------------
 2 files changed, 7 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index cdfd43a7321a..7f2e9a9b4097 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -287,7 +287,6 @@ struct ath12k_vif {
 	int txpower;
 	bool rsnie_present;
 	bool wpaie_present;
-	struct ieee80211_chanctx_conf chanctx;
 	u32 key_cipher;
 	u8 tx_encap_type;
 	u8 vdev_stats_id;
@@ -295,6 +294,13 @@ struct ath12k_vif {
 	bool ps;
 	struct ath12k_vif_cache *cache;
 	struct ath12k_rekey_data rekey_data;
+
+	/* Must be last - ends in a flexible-array member.
+	 *
+	 * FIXME: Driver should not copy struct ieee80211_chanctx_conf,
+	 * especially because it has a flexible array. Find a better way.
+	 */
+	struct ieee80211_chanctx_conf chanctx;
 };
 
 struct ath12k_vif_iter {
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index b77497c14ac4..2fb18b83b3ee 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -1495,18 +1495,6 @@ struct htt_ppdu_stats_user_rate {
 #define HTT_TX_INFO_PEERID(_flags) \
 			u32_get_bits(_flags, HTT_PPDU_STATS_TX_INFO_FLAGS_PEERID_M)
 
-struct htt_tx_ppdu_stats_info {
-	struct htt_tlv tlv_hdr;
-	__le32 tx_success_bytes;
-	__le32 tx_retry_bytes;
-	__le32 tx_failed_bytes;
-	__le32 flags; /* %HTT_PPDU_STATS_TX_INFO_FLAGS_ */
-	__le16 tx_success_msdus;
-	__le16 tx_retry_msdus;
-	__le16 tx_failed_msdus;
-	__le16 tx_duration; /* united in us */
-} __packed;
-
 enum  htt_ppdu_stats_usr_compln_status {
 	HTT_PPDU_STATS_USER_STATUS_OK,
 	HTT_PPDU_STATS_USER_STATUS_FILTERED,
-- 
cgit v1.3-3-g829e


From 08062af0a52107a243f7608fd972edb54ca5b7f8 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Wed, 4 Sep 2024 15:34:30 +0000
Subject: net: napi: Prevent overflow of napi_defer_hard_irqs

In commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature")
napi_defer_irqs was added to net_device and napi_defer_irqs_count was
added to napi_struct, both as type int.

This value never goes below zero, so there is not reason for it to be a
signed int. Change the type for both from int to u32, and add an
overflow check to sysfs to limit the value to S32_MAX.

The limit of S32_MAX was chosen because the practical limit before this
patch was S32_MAX (anything larger was an overflow) and thus there are
no behavioral changes introduced. If the extra bit is needed in the
future, the limit can be raised.

Before this patch:

$ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs'
$ cat /sys/class/net/eth4/napi_defer_hard_irqs
-2147483647

After this patch:

$ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs'
bash: line 0: echo: write error: Numerical result out of range

Similarly, /sys/class/net/XXXXX/tx_queue_len is defined as unsigned:

include/linux/netdevice.h:      unsigned int            tx_queue_len;

And has an overflow check:

dev_change_tx_queue_len(..., unsigned long new_len):

  if (new_len != (unsigned int)new_len)
          return -ERANGE;

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240904153431.307932-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/net_cachelines/net_device.rst | 2 +-
 include/linux/netdevice.h                              | 4 ++--
 net/core/net-sysfs.c                                   | 6 +++++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 56d4bbaf8a2c..22b07c814f4a 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -99,7 +99,7 @@ unsigned_int                        num_rx_queues
 unsigned_int                        real_num_rx_queues      -                   read_mostly         get_rps_cpu
 struct_bpf_prog*                    xdp_prog                -                   read_mostly         netif_elide_gro()
 unsigned_long                       gro_flush_timeout       -                   read_mostly         napi_complete_done
-int                                 napi_defer_hard_irqs    -                   read_mostly         napi_complete_done
+u32                                 napi_defer_hard_irqs    -                   read_mostly         napi_complete_done
 unsigned_int                        gro_max_size            -                   read_mostly         skb_gro_receive
 unsigned_int                        gro_ipv4_max_size       -                   read_mostly         skb_gro_receive
 rx_handler_func_t*                  rx_handler              read_mostly         -                   __netif_receive_skb_core
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ca5f0dda733b..b47c00657bd0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -356,7 +356,7 @@ struct napi_struct {
 
 	unsigned long		state;
 	int			weight;
-	int			defer_hard_irqs_count;
+	u32			defer_hard_irqs_count;
 	unsigned long		gro_bitmask;
 	int			(*poll)(struct napi_struct *, int);
 #ifdef CONFIG_NETPOLL
@@ -2075,7 +2075,7 @@ struct net_device {
 	unsigned int		real_num_rx_queues;
 	struct netdev_rx_queue	*_rx;
 	unsigned long		gro_flush_timeout;
-	int			napi_defer_hard_irqs;
+	u32			napi_defer_hard_irqs;
 	unsigned int		gro_max_size;
 	unsigned int		gro_ipv4_max_size;
 	rx_handler_func_t __rcu	*rx_handler;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 01a9fb54ef42..146a271a74e0 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -32,6 +32,7 @@
 #ifdef CONFIG_SYSFS
 static const char fmt_hex[] = "%#x\n";
 static const char fmt_dec[] = "%d\n";
+static const char fmt_uint[] = "%u\n";
 static const char fmt_ulong[] = "%lu\n";
 static const char fmt_u64[] = "%llu\n";
 
@@ -425,6 +426,9 @@ NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong);
 
 static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val)
 {
+	if (val > S32_MAX)
+		return -ERANGE;
+
 	WRITE_ONCE(dev->napi_defer_hard_irqs, val);
 	return 0;
 }
@@ -438,7 +442,7 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev,
 
 	return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs);
 }
-NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec);
+NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint);
 
 static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t len)
-- 
cgit v1.3-3-g829e


From e10034e38e9da2a644f2aa73f2f46bb7beb8620b Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Wed, 4 Sep 2024 10:10:24 +0100
Subject: netlink: specs: nftables: allow decode of tailscale ruleset

Fill another small gap in the nftables spec so that it is possible to
dump a tailscale ruleset with:

  tools/net/ynl/cli.py --spec \
     Documentation/netlink/specs/nftables.yaml --dump getrule

This adds support for the 'target' expression.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20240904091024.3138-1-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/nftables.yaml | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/Documentation/netlink/specs/nftables.yaml b/Documentation/netlink/specs/nftables.yaml
index 4acf30cf8385..bd938bd01b6b 100644
--- a/Documentation/netlink/specs/nftables.yaml
+++ b/Documentation/netlink/specs/nftables.yaml
@@ -1027,6 +1027,19 @@ attribute-sets:
       -
         name: icmp-code
         type: u8
+  -
+    name: expr-target-attrs
+    attributes:
+      -
+        name: name
+        type: string
+      -
+        name: rev
+        type: u32
+        byte-order: big-endian
+      -
+        name: info
+        type: binary
   -
     name: expr-tproxy-attrs
     attributes:
@@ -1113,6 +1126,9 @@ sub-messages:
       -
         value: reject
         attribute-set: expr-reject-attrs
+      -
+        value: target
+        attribute-set: expr-target-attrs
       -
         value: tproxy
         attribute-set: expr-tproxy-attrs
-- 
cgit v1.3-3-g829e


From a36e9f5cfe9eb3a1dce8769c7058251c42705357 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:02 +0800
Subject: rtase: Add support for a pci table in this module

Add support for a pci table in this module, and implement pci_driver
function to initialize this driver, remove this driver, or shutdown
this driver.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-2-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase.h      | 340 +++++++++++++
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 638 ++++++++++++++++++++++++
 2 files changed, 978 insertions(+)
 create mode 100644 drivers/net/ethernet/realtek/rtase/rtase.h
 create mode 100644 drivers/net/ethernet/realtek/rtase/rtase_main.c

diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h
new file mode 100644
index 000000000000..583c33930f88
--- /dev/null
+++ b/drivers/net/ethernet/realtek/rtase/rtase.h
@@ -0,0 +1,340 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ *  rtase is the Linux device driver released for Realtek Automotive Switch
+ *  controllers with PCI-Express interface.
+ *
+ *  Copyright(c) 2024 Realtek Semiconductor Corp.
+ */
+
+#ifndef RTASE_H
+#define RTASE_H
+
+#define RTASE_HW_VER_MASK 0x7C800000
+
+#define RTASE_RX_DMA_BURST_256       4
+#define RTASE_TX_DMA_BURST_UNLIMITED 7
+
+#define RTASE_RX_BUF_SIZE    (PAGE_SIZE - \
+			      SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define RTASE_MAX_JUMBO_SIZE (RTASE_RX_BUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN)
+
+/* 3 means InterFrameGap = the shortest one */
+#define RTASE_INTERFRAMEGAP 0x03
+
+#define RTASE_REGS_SIZE     256
+#define RTASE_PCI_REGS_SIZE 0x100
+
+#define RTASE_MULTICAST_FILTER_MASK GENMASK(30, 26)
+
+#define RTASE_VLAN_FILTER_ENTRY_NUM 32
+#define RTASE_NUM_TX_QUEUE 8
+#define RTASE_NUM_RX_QUEUE 4
+
+#define RTASE_TXQ_CTRL      1
+#define RTASE_FUNC_TXQ_NUM  1
+#define RTASE_FUNC_RXQ_NUM  1
+#define RTASE_INTERRUPT_NUM 1
+
+#define RTASE_MITI_TIME_COUNT_MASK    GENMASK(3, 0)
+#define RTASE_MITI_TIME_UNIT_MASK     GENMASK(7, 4)
+#define RTASE_MITI_DEFAULT_TIME       128
+#define RTASE_MITI_MAX_TIME           491520
+#define RTASE_MITI_PKT_NUM_COUNT_MASK GENMASK(11, 8)
+#define RTASE_MITI_PKT_NUM_UNIT_MASK  GENMASK(13, 12)
+#define RTASE_MITI_DEFAULT_PKT_NUM    64
+#define RTASE_MITI_MAX_PKT_NUM_IDX    3
+#define RTASE_MITI_MAX_PKT_NUM_UNIT   16
+#define RTASE_MITI_MAX_PKT_NUM        240
+#define RTASE_MITI_COUNT_BIT_NUM      4
+
+#define RTASE_NUM_MSIX 4
+
+#define RTASE_DWORD_MOD 16
+
+/*****************************************************************************/
+enum rtase_registers {
+	RTASE_MAC0   = 0x0000,
+	RTASE_MAC4   = 0x0004,
+	RTASE_MAR0   = 0x0008,
+	RTASE_MAR1   = 0x000C,
+	RTASE_DTCCR0 = 0x0010,
+	RTASE_DTCCR4 = 0x0014,
+#define RTASE_COUNTER_RESET BIT(0)
+#define RTASE_COUNTER_DUMP  BIT(3)
+
+	RTASE_FCR = 0x0018,
+#define RTASE_FCR_RXQ_MASK GENMASK(5, 4)
+
+	RTASE_LBK_CTRL = 0x001A,
+#define RTASE_LBK_ATLD BIT(1)
+#define RTASE_LBK_CLR  BIT(0)
+
+	RTASE_TX_DESC_ADDR0   = 0x0020,
+	RTASE_TX_DESC_ADDR4   = 0x0024,
+	RTASE_TX_DESC_COMMAND = 0x0028,
+#define RTASE_TX_DESC_CMD_CS BIT(15)
+#define RTASE_TX_DESC_CMD_WE BIT(14)
+
+	RTASE_BOOT_CTL  = 0x6004,
+	RTASE_CLKSW_SET = 0x6018,
+
+	RTASE_CHIP_CMD = 0x0037,
+#define RTASE_STOP_REQ      BIT(7)
+#define RTASE_STOP_REQ_DONE BIT(6)
+#define RTASE_RE            BIT(3)
+#define RTASE_TE            BIT(2)
+
+	RTASE_IMR0 = 0x0038,
+	RTASE_ISR0 = 0x003C,
+#define RTASE_TOK7 BIT(30)
+#define RTASE_TOK6 BIT(28)
+#define RTASE_TOK5 BIT(26)
+#define RTASE_TOK4 BIT(24)
+#define RTASE_FOVW BIT(6)
+#define RTASE_RDU  BIT(4)
+#define RTASE_TOK  BIT(2)
+#define RTASE_ROK  BIT(0)
+
+	RTASE_IMR1 = 0x0800,
+	RTASE_ISR1 = 0x0802,
+#define RTASE_Q_TOK BIT(4)
+#define RTASE_Q_RDU BIT(1)
+#define RTASE_Q_ROK BIT(0)
+
+	RTASE_EPHY_ISR = 0x6014,
+	RTASE_EPHY_IMR = 0x6016,
+
+	RTASE_TX_CONFIG_0 = 0x0040,
+#define RTASE_TX_INTER_FRAME_GAP_MASK GENMASK(25, 24)
+	/* DMA burst value (0-7) is shift this many bits */
+#define RTASE_TX_DMA_MASK             GENMASK(10, 8)
+
+	RTASE_RX_CONFIG_0 = 0x0044,
+#define RTASE_RX_SINGLE_FETCH  BIT(14)
+#define RTASE_RX_SINGLE_TAG    BIT(13)
+#define RTASE_RX_MX_DMA_MASK   GENMASK(10, 8)
+#define RTASE_ACPT_FLOW        BIT(7)
+#define RTASE_ACCEPT_ERR       BIT(5)
+#define RTASE_ACCEPT_RUNT      BIT(4)
+#define RTASE_ACCEPT_BROADCAST BIT(3)
+#define RTASE_ACCEPT_MULTICAST BIT(2)
+#define RTASE_ACCEPT_MYPHYS    BIT(1)
+#define RTASE_ACCEPT_ALLPHYS   BIT(0)
+#define RTASE_ACCEPT_MASK      (RTASE_ACPT_FLOW | RTASE_ACCEPT_ERR | \
+				RTASE_ACCEPT_RUNT | RTASE_ACCEPT_BROADCAST | \
+				RTASE_ACCEPT_MULTICAST | RTASE_ACCEPT_MYPHYS | \
+				RTASE_ACCEPT_ALLPHYS)
+
+	RTASE_RX_CONFIG_1 = 0x0046,
+#define RTASE_RX_MAX_FETCH_DESC_MASK GENMASK(15, 11)
+#define RTASE_RX_NEW_DESC_FORMAT_EN  BIT(8)
+#define RTASE_OUTER_VLAN_DETAG_EN    BIT(7)
+#define RTASE_INNER_VLAN_DETAG_EN    BIT(6)
+#define RTASE_PCIE_NEW_FLOW          BIT(2)
+#define RTASE_PCIE_RELOAD_EN         BIT(0)
+
+	RTASE_EEM = 0x0050,
+#define RTASE_EEM_UNLOCK 0xC0
+
+	RTASE_TDFNR  = 0x0057,
+	RTASE_TPPOLL = 0x0090,
+	RTASE_PDR    = 0x00B0,
+	RTASE_FIFOR  = 0x00D3,
+#define RTASE_TX_FIFO_EMPTY BIT(5)
+#define RTASE_RX_FIFO_EMPTY BIT(4)
+
+	RTASE_RMS       = 0x00DA,
+	RTASE_CPLUS_CMD = 0x00E0,
+#define RTASE_FORCE_RXFLOW_EN BIT(11)
+#define RTASE_FORCE_TXFLOW_EN BIT(10)
+#define RTASE_RX_CHKSUM       BIT(5)
+
+	RTASE_Q0_RX_DESC_ADDR0 = 0x00E4,
+	RTASE_Q0_RX_DESC_ADDR4 = 0x00E8,
+	RTASE_Q1_RX_DESC_ADDR0 = 0x4000,
+	RTASE_Q1_RX_DESC_ADDR4 = 0x4004,
+	RTASE_MTPS             = 0x00EC,
+#define RTASE_TAG_NUM_SEL_MASK GENMASK(10, 8)
+
+	RTASE_MISC = 0x00F2,
+#define RTASE_RX_DV_GATE_EN BIT(3)
+
+	RTASE_TFUN_CTRL = 0x0400,
+#define RTASE_TX_NEW_DESC_FORMAT_EN BIT(0)
+
+	RTASE_TX_CONFIG_1 = 0x203E,
+#define RTASE_TC_MODE_MASK GENMASK(11, 10)
+
+	RTASE_TOKSEL      = 0x2046,
+	RTASE_RFIFONFULL  = 0x4406,
+	RTASE_INT_MITI_TX = 0x0A00,
+	RTASE_INT_MITI_RX = 0x0A80,
+
+	RTASE_VLAN_ENTRY_0     = 0xAC80,
+};
+
+enum rtase_desc_status_bit {
+	RTASE_DESC_OWN = BIT(31), /* Descriptor is owned by NIC */
+	RTASE_RING_END = BIT(30), /* End of descriptor ring */
+};
+
+enum rtase_sw_flag_content {
+	RTASE_SWF_MSI_ENABLED  = BIT(1),
+	RTASE_SWF_MSIX_ENABLED = BIT(2),
+};
+
+#define RSVD_MASK 0x3FFFC000
+
+struct rtase_tx_desc {
+	__le32 opts1;
+	__le32 opts2;
+	__le64 addr;
+	__le32 opts3;
+	__le32 reserved1;
+	__le32 reserved2;
+	__le32 reserved3;
+} __packed;
+
+/*------ offset 0 of tx descriptor ------*/
+#define RTASE_TX_FIRST_FRAG BIT(29) /* Tx First segment of a packet */
+#define RTASE_TX_LAST_FRAG  BIT(28) /* Tx Final segment of a packet */
+#define RTASE_GIANT_SEND_V4 BIT(26) /* TCP Giant Send Offload V4 (GSOv4) */
+#define RTASE_GIANT_SEND_V6 BIT(25) /* TCP Giant Send Offload V6 (GSOv6) */
+#define RTASE_TX_VLAN_TAG   BIT(17) /* Add VLAN tag */
+
+/*------ offset 4 of tx descriptor ------*/
+#define RTASE_TX_UDPCS_C BIT(31) /* Calculate UDP/IP checksum */
+#define RTASE_TX_TCPCS_C BIT(30) /* Calculate TCP/IP checksum */
+#define RTASE_TX_IPCS_C  BIT(29) /* Calculate IP checksum */
+#define RTASE_TX_IPV6F_C BIT(28) /* Indicate it is an IPv6 packet */
+
+union rtase_rx_desc {
+	struct {
+		__le64 header_buf_addr;
+		__le32 reserved1;
+		__le32 opts_header_len;
+		__le64 addr;
+		__le32 reserved2;
+		__le32 opts1;
+	} __packed desc_cmd;
+
+	struct {
+		__le32 reserved1;
+		__le32 reserved2;
+		__le32 rss;
+		__le32 opts4;
+		__le32 reserved3;
+		__le32 opts3;
+		__le32 opts2;
+		__le32 opts1;
+	} __packed desc_status;
+} __packed;
+
+/*------ offset 28 of rx descriptor ------*/
+#define RTASE_RX_FIRST_FRAG BIT(25) /* Rx First segment of a packet */
+#define RTASE_RX_LAST_FRAG  BIT(24) /* Rx Final segment of a packet */
+#define RTASE_RX_RES        BIT(20)
+#define RTASE_RX_RUNT       BIT(19)
+#define RTASE_RX_RWT        BIT(18)
+#define RTASE_RX_CRC        BIT(16)
+#define RTASE_RX_V6F        BIT(31)
+#define RTASE_RX_V4F        BIT(30)
+#define RTASE_RX_UDPT       BIT(29)
+#define RTASE_RX_TCPT       BIT(28)
+#define RTASE_RX_IPF        BIT(26) /* IP checksum failed */
+#define RTASE_RX_UDPF       BIT(25) /* UDP/IP checksum failed */
+#define RTASE_RX_TCPF       BIT(24) /* TCP/IP checksum failed */
+#define RTASE_RX_VLAN_TAG   BIT(16) /* VLAN tag available */
+
+#define RTASE_NUM_DESC          1024
+#define RTASE_TX_BUDGET_DEFAULT 256
+#define RTASE_TX_RING_DESC_SIZE (RTASE_NUM_DESC * sizeof(struct rtase_tx_desc))
+#define RTASE_RX_RING_DESC_SIZE (RTASE_NUM_DESC * sizeof(union rtase_rx_desc))
+#define RTASE_TX_STOP_THRS      (MAX_SKB_FRAGS + 1)
+#define RTASE_TX_START_THRS     (2 * RTASE_TX_STOP_THRS)
+#define RTASE_VLAN_TAG_MASK     GENMASK(15, 0)
+#define RTASE_RX_PKT_SIZE_MASK  GENMASK(13, 0)
+
+#define RTASE_IVEC_NAME_SIZE (IFNAMSIZ + 10)
+
+struct rtase_int_vector {
+	struct rtase_private *tp;
+	unsigned int irq;
+	char name[RTASE_IVEC_NAME_SIZE];
+	u16 index;
+	u16 imr_addr;
+	u16 isr_addr;
+	u32 imr;
+	struct list_head ring_list;
+	struct napi_struct napi;
+	int (*poll)(struct napi_struct *napi, int budget);
+};
+
+struct rtase_ring {
+	struct rtase_int_vector *ivec;
+	void *desc;
+	dma_addr_t phy_addr;
+	u32 cur_idx;
+	u32 dirty_idx;
+	u16 index;
+
+	struct sk_buff *skbuff[RTASE_NUM_DESC];
+	void *data_buf[RTASE_NUM_DESC];
+	union {
+		u32 len[RTASE_NUM_DESC];
+		dma_addr_t data_phy_addr[RTASE_NUM_DESC];
+	} mis;
+
+	struct list_head ring_entry;
+	int (*ring_handler)(struct rtase_ring *ring, int budget);
+	u64 alloc_fail;
+};
+
+struct rtase_stats {
+	u64 tx_dropped;
+	u64 rx_dropped;
+	u64 multicast;
+	u64 rx_errors;
+	u64 rx_length_errors;
+	u64 rx_crc_errors;
+};
+
+struct rtase_private {
+	void __iomem *mmio_addr;
+	u32 sw_flag;
+
+	struct pci_dev *pdev;
+	struct net_device *dev;
+	u32 rx_buf_sz;
+
+	struct page_pool *page_pool;
+	struct rtase_ring tx_ring[RTASE_NUM_TX_QUEUE];
+	struct rtase_ring rx_ring[RTASE_NUM_RX_QUEUE];
+	struct rtase_counters *tally_vaddr;
+	dma_addr_t tally_paddr;
+
+	u32 vlan_filter_ctrl;
+	u16 vlan_filter_vid[RTASE_VLAN_FILTER_ENTRY_NUM];
+
+	struct msix_entry msix_entry[RTASE_NUM_MSIX];
+	struct rtase_int_vector int_vector[RTASE_NUM_MSIX];
+
+	struct rtase_stats stats;
+
+	u16 tx_queue_ctrl;
+	u16 func_tx_queue_num;
+	u16 func_rx_queue_num;
+	u16 int_nums;
+	u16 tx_int_mit;
+	u16 rx_int_mit;
+};
+
+#define RTASE_LSO_64K 64000
+
+#define RTASE_NIC_MAX_PHYS_BUF_COUNT_LSO2 (16 * 4)
+
+#define RTASE_TCPHO_MASK GENMASK(24, 18)
+
+#define RTASE_MSS_MASK GENMASK(28, 18)
+
+#endif /* RTASE_H */
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
new file mode 100644
index 000000000000..2aa472d4212a
--- /dev/null
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -0,0 +1,638 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ *  rtase is the Linux device driver released for Realtek Automotive Switch
+ *  controllers with PCI-Express interface.
+ *
+ *  Copyright(c) 2024 Realtek Semiconductor Corp.
+ *
+ *  Below is a simplified block diagram of the chip and its relevant interfaces.
+ *
+ *               *************************
+ *               *                       *
+ *               *  CPU network device   *
+ *               *                       *
+ *               *   +-------------+     *
+ *               *   |  PCIE Host  |     *
+ *               ***********++************
+ *                          ||
+ *                         PCIE
+ *                          ||
+ *      ********************++**********************
+ *      *            | PCIE Endpoint |             *
+ *      *            +---------------+             *
+ *      *                | GMAC |                  *
+ *      *                +--++--+  Realtek         *
+ *      *                   ||     RTL90xx Series  *
+ *      *                   ||                     *
+ *      *     +-------------++----------------+    *
+ *      *     |           | MAC |             |    *
+ *      *     |           +-----+             |    *
+ *      *     |                               |    *
+ *      *     |     Ethernet Switch Core      |    *
+ *      *     |                               |    *
+ *      *     |   +-----+           +-----+   |    *
+ *      *     |   | MAC |...........| MAC |   |    *
+ *      *     +---+-----+-----------+-----+---+    *
+ *      *         | PHY |...........| PHY |        *
+ *      *         +--++-+           +--++-+        *
+ *      *************||****************||***********
+ *
+ *  The block of the Realtek RTL90xx series is our entire chip architecture,
+ *  the GMAC is connected to the switch core, and there is no PHY in between.
+ *  In addition, this driver is mainly used to control GMAC, but does not
+ *  control the switch core, so it is not the same as DSA. Linux only plays
+ *  the role of a normal leaf node in this model.
+ */
+
+#include <linux/crc32.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/mdio.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+#include <linux/pm_runtime.h>
+#include <linux/prefetch.h>
+#include <linux/rtnetlink.h>
+#include <linux/tcp.h>
+#include <asm/irq.h>
+#include <net/ip6_checksum.h>
+#include <net/netdev_queues.h>
+#include <net/page_pool/helpers.h>
+#include <net/pkt_cls.h>
+
+#include "rtase.h"
+
+#define RTK_OPTS1_DEBUG_VALUE 0x0BADBEEF
+#define RTK_MAGIC_NUMBER      0x0BADBADBADBADBAD
+
+static const struct pci_device_id rtase_pci_tbl[] = {
+	{PCI_VDEVICE(REALTEK, 0x906A)},
+	{}
+};
+
+MODULE_DEVICE_TABLE(pci, rtase_pci_tbl);
+
+MODULE_AUTHOR("Realtek ARD Software Team");
+MODULE_DESCRIPTION("Network Driver for the PCIe interface of Realtek Automotive Ethernet Switch");
+MODULE_LICENSE("Dual BSD/GPL");
+
+struct rtase_counters {
+	__le64 tx_packets;
+	__le64 rx_packets;
+	__le64 tx_errors;
+	__le32 rx_errors;
+	__le16 rx_missed;
+	__le16 align_errors;
+	__le32 tx_one_collision;
+	__le32 tx_multi_collision;
+	__le64 rx_unicast;
+	__le64 rx_broadcast;
+	__le32 rx_multicast;
+	__le16 tx_aborted;
+	__le16 tx_underun;
+} __packed;
+
+static void rtase_w8(const struct rtase_private *tp, u16 reg, u8 val8)
+{
+	writeb(val8, tp->mmio_addr + reg);
+}
+
+static void rtase_w16(const struct rtase_private *tp, u16 reg, u16 val16)
+{
+	writew(val16, tp->mmio_addr + reg);
+}
+
+static void rtase_w32(const struct rtase_private *tp, u16 reg, u32 val32)
+{
+	writel(val32, tp->mmio_addr + reg);
+}
+
+static u8 rtase_r8(const struct rtase_private *tp, u16 reg)
+{
+	return readb(tp->mmio_addr + reg);
+}
+
+static u16 rtase_r16(const struct rtase_private *tp, u16 reg)
+{
+	return readw(tp->mmio_addr + reg);
+}
+
+static u32 rtase_r32(const struct rtase_private *tp, u16 reg)
+{
+	return readl(tp->mmio_addr + reg);
+}
+
+static void rtase_tally_counter_clear(const struct rtase_private *tp)
+{
+	u32 cmd = lower_32_bits(tp->tally_paddr);
+
+	rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(tp->tally_paddr));
+	rtase_w32(tp, RTASE_DTCCR0, cmd | RTASE_COUNTER_RESET);
+}
+
+static void rtase_enable_eem_write(const struct rtase_private *tp)
+{
+	u8 val;
+
+	val = rtase_r8(tp, RTASE_EEM);
+	rtase_w8(tp, RTASE_EEM, val | RTASE_EEM_UNLOCK);
+}
+
+static void rtase_disable_eem_write(const struct rtase_private *tp)
+{
+	u8 val;
+
+	val = rtase_r8(tp, RTASE_EEM);
+	rtase_w8(tp, RTASE_EEM, val & ~RTASE_EEM_UNLOCK);
+}
+
+static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr)
+{
+	u32 rar_low, rar_high;
+
+	rar_low = (u32)addr[0] | ((u32)addr[1] << 8) |
+		  ((u32)addr[2] << 16) | ((u32)addr[3] << 24);
+
+	rar_high = (u32)addr[4] | ((u32)addr[5] << 8);
+
+	rtase_enable_eem_write(tp);
+	rtase_w32(tp, RTASE_MAC0, rar_low);
+	rtase_w32(tp, RTASE_MAC4, rar_high);
+	rtase_disable_eem_write(tp);
+	rtase_w16(tp, RTASE_LBK_CTRL, RTASE_LBK_ATLD | RTASE_LBK_CLR);
+}
+
+static void rtase_get_mac_address(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	u8 mac_addr[ETH_ALEN] __aligned(2) = {};
+	u32 i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		mac_addr[i] = rtase_r8(tp, RTASE_MAC0 + i);
+
+	if (!is_valid_ether_addr(mac_addr)) {
+		eth_hw_addr_random(dev);
+		netdev_warn(dev, "Random ether addr %pM\n", dev->dev_addr);
+	} else {
+		eth_hw_addr_set(dev, mac_addr);
+		ether_addr_copy(dev->perm_addr, dev->dev_addr);
+	}
+
+	rtase_rar_set(tp, dev->dev_addr);
+}
+
+static void rtase_reset_interrupt(struct pci_dev *pdev,
+				  const struct rtase_private *tp)
+{
+	if (tp->sw_flag & RTASE_SWF_MSIX_ENABLED)
+		pci_disable_msix(pdev);
+	else
+		pci_disable_msi(pdev);
+}
+
+static int rtase_alloc_msix(struct pci_dev *pdev, struct rtase_private *tp)
+{
+	int ret, irq;
+	u16 i;
+
+	memset(tp->msix_entry, 0x0, RTASE_NUM_MSIX *
+	       sizeof(struct msix_entry));
+
+	for (i = 0; i < RTASE_NUM_MSIX; i++)
+		tp->msix_entry[i].entry = i;
+
+	ret = pci_enable_msix_exact(pdev, tp->msix_entry, tp->int_nums);
+
+	if (ret)
+		return ret;
+
+	for (i = 0; i < tp->int_nums; i++) {
+		irq = pci_irq_vector(pdev, i);
+		if (!irq) {
+			pci_disable_msix(pdev);
+			return irq;
+		}
+
+		tp->int_vector[i].irq = irq;
+	}
+
+	return 0;
+}
+
+static int rtase_alloc_interrupt(struct pci_dev *pdev,
+				 struct rtase_private *tp)
+{
+	int ret;
+
+	ret = rtase_alloc_msix(pdev, tp);
+	if (ret) {
+		ret = pci_enable_msi(pdev);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"unable to alloc interrupt.(MSI)\n");
+			return ret;
+		}
+
+		tp->sw_flag |= RTASE_SWF_MSI_ENABLED;
+	} else {
+		tp->sw_flag |= RTASE_SWF_MSIX_ENABLED;
+	}
+
+	return 0;
+}
+
+static void rtase_init_hardware(const struct rtase_private *tp)
+{
+	u16 i;
+
+	for (i = 0; i < RTASE_VLAN_FILTER_ENTRY_NUM; i++)
+		rtase_w32(tp, RTASE_VLAN_ENTRY_0 + i * 4, 0);
+}
+
+static void rtase_init_int_vector(struct rtase_private *tp)
+{
+	u16 i;
+
+	/* interrupt vector 0 */
+	tp->int_vector[0].tp = tp;
+	tp->int_vector[0].index = 0;
+	tp->int_vector[0].imr_addr = RTASE_IMR0;
+	tp->int_vector[0].isr_addr = RTASE_ISR0;
+	tp->int_vector[0].imr = RTASE_ROK | RTASE_RDU | RTASE_TOK |
+				RTASE_TOK4 | RTASE_TOK5 | RTASE_TOK6 |
+				RTASE_TOK7;
+	tp->int_vector[0].poll = rtase_poll;
+
+	memset(tp->int_vector[0].name, 0x0, sizeof(tp->int_vector[0].name));
+	INIT_LIST_HEAD(&tp->int_vector[0].ring_list);
+
+	netif_napi_add(tp->dev, &tp->int_vector[0].napi,
+		       tp->int_vector[0].poll);
+
+	/* interrupt vector 1 ~ 3 */
+	for (i = 1; i < tp->int_nums; i++) {
+		tp->int_vector[i].tp = tp;
+		tp->int_vector[i].index = i;
+		tp->int_vector[i].imr_addr = RTASE_IMR1 + (i - 1) * 4;
+		tp->int_vector[i].isr_addr = RTASE_ISR1 + (i - 1) * 4;
+		tp->int_vector[i].imr = RTASE_Q_ROK | RTASE_Q_RDU |
+					RTASE_Q_TOK;
+		tp->int_vector[i].poll = rtase_poll;
+
+		memset(tp->int_vector[i].name, 0x0,
+		       sizeof(tp->int_vector[0].name));
+		INIT_LIST_HEAD(&tp->int_vector[i].ring_list);
+
+		netif_napi_add(tp->dev, &tp->int_vector[i].napi,
+			       tp->int_vector[i].poll);
+	}
+}
+
+static u16 rtase_calc_time_mitigation(u32 time_us)
+{
+	u8 msb, time_count, time_unit;
+	u16 int_miti;
+
+	time_us = min_t(int, time_us, RTASE_MITI_MAX_TIME);
+
+	msb = fls(time_us);
+	if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+		time_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
+		time_count = time_us >> (msb - RTASE_MITI_COUNT_BIT_NUM);
+	} else {
+		time_unit = 0;
+		time_count = time_us;
+	}
+
+	int_miti = u16_encode_bits(time_count, RTASE_MITI_TIME_COUNT_MASK) |
+		   u16_encode_bits(time_unit, RTASE_MITI_TIME_UNIT_MASK);
+
+	return int_miti;
+}
+
+static u16 rtase_calc_packet_num_mitigation(u16 pkt_num)
+{
+	u8 msb, pkt_num_count, pkt_num_unit;
+	u16 int_miti;
+
+	pkt_num = min_t(int, pkt_num, RTASE_MITI_MAX_PKT_NUM);
+
+	if (pkt_num > 60) {
+		pkt_num_unit = RTASE_MITI_MAX_PKT_NUM_IDX;
+		pkt_num_count = pkt_num / RTASE_MITI_MAX_PKT_NUM_UNIT;
+	} else {
+		msb = fls(pkt_num);
+		if (msb >= RTASE_MITI_COUNT_BIT_NUM) {
+			pkt_num_unit = msb - RTASE_MITI_COUNT_BIT_NUM;
+			pkt_num_count = pkt_num >> (msb -
+						    RTASE_MITI_COUNT_BIT_NUM);
+		} else {
+			pkt_num_unit = 0;
+			pkt_num_count = pkt_num;
+		}
+	}
+
+	int_miti = u16_encode_bits(pkt_num_count,
+				   RTASE_MITI_PKT_NUM_COUNT_MASK) |
+		   u16_encode_bits(pkt_num_unit,
+				   RTASE_MITI_PKT_NUM_UNIT_MASK);
+
+	return int_miti;
+}
+
+static void rtase_init_software_variable(struct pci_dev *pdev,
+					 struct rtase_private *tp)
+{
+	u16 int_miti;
+
+	tp->tx_queue_ctrl = RTASE_TXQ_CTRL;
+	tp->func_tx_queue_num = RTASE_FUNC_TXQ_NUM;
+	tp->func_rx_queue_num = RTASE_FUNC_RXQ_NUM;
+	tp->int_nums = RTASE_INTERRUPT_NUM;
+
+	int_miti = rtase_calc_time_mitigation(RTASE_MITI_DEFAULT_TIME) |
+		   rtase_calc_packet_num_mitigation(RTASE_MITI_DEFAULT_PKT_NUM);
+	tp->tx_int_mit = int_miti;
+	tp->rx_int_mit = int_miti;
+
+	tp->sw_flag = 0;
+
+	rtase_init_int_vector(tp);
+
+	/* MTU range: 60 - hw-specific max */
+	tp->dev->min_mtu = ETH_ZLEN;
+	tp->dev->max_mtu = RTASE_MAX_JUMBO_SIZE;
+}
+
+static bool rtase_check_mac_version_valid(struct rtase_private *tp)
+{
+	u32 hw_ver = rtase_r32(tp, RTASE_TX_CONFIG_0) & RTASE_HW_VER_MASK;
+	bool known_ver = false;
+
+	switch (hw_ver) {
+	case 0x00800000:
+	case 0x04000000:
+	case 0x04800000:
+		known_ver = true;
+		break;
+	}
+
+	return known_ver;
+}
+
+static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out,
+			    void __iomem **ioaddr_out)
+{
+	struct net_device *dev;
+	void __iomem *ioaddr;
+	int ret = -ENOMEM;
+
+	/* dev zeroed in alloc_etherdev */
+	dev = alloc_etherdev_mq(sizeof(struct rtase_private),
+				RTASE_FUNC_TXQ_NUM);
+	if (!dev)
+		goto err_out;
+
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	ret = pci_enable_device(pdev);
+	if (ret < 0)
+		goto err_out_free_dev;
+
+	/* make sure PCI base addr 1 is MMIO */
+	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) {
+		ret = -ENODEV;
+		goto err_out_disable;
+	}
+
+	/* check for weird/broken PCI region reporting */
+	if (pci_resource_len(pdev, 2) < RTASE_REGS_SIZE) {
+		ret = -ENODEV;
+		goto err_out_disable;
+	}
+
+	ret = pci_request_regions(pdev, KBUILD_MODNAME);
+	if (ret < 0)
+		goto err_out_disable;
+
+	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
+		dev_err(&pdev->dev, "no usable dma addressing method\n");
+		goto err_out_free_res;
+	}
+
+	pci_set_master(pdev);
+
+	/* ioremap MMIO region */
+	ioaddr = ioremap(pci_resource_start(pdev, 2),
+			 pci_resource_len(pdev, 2));
+	if (!ioaddr) {
+		ret = -EIO;
+		goto err_out_free_res;
+	}
+
+	*ioaddr_out = ioaddr;
+	*dev_out = dev;
+
+	return ret;
+
+err_out_free_res:
+	pci_release_regions(pdev);
+
+err_out_disable:
+	pci_disable_device(pdev);
+
+err_out_free_dev:
+	free_netdev(dev);
+
+err_out:
+	*ioaddr_out = NULL;
+	*dev_out = NULL;
+
+	return ret;
+}
+
+static void rtase_release_board(struct pci_dev *pdev, struct net_device *dev,
+				void __iomem *ioaddr)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+
+	rtase_rar_set(tp, tp->dev->perm_addr);
+	iounmap(ioaddr);
+
+	if (tp->sw_flag & RTASE_SWF_MSIX_ENABLED)
+		pci_disable_msix(pdev);
+	else
+		pci_disable_msi(pdev);
+
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	free_netdev(dev);
+}
+
+static int rtase_init_one(struct pci_dev *pdev,
+			  const struct pci_device_id *ent)
+{
+	struct net_device *dev = NULL;
+	struct rtase_int_vector *ivec;
+	void __iomem *ioaddr = NULL;
+	struct rtase_private *tp;
+	int ret, i;
+
+	if (!pdev->is_physfn && pdev->is_virtfn) {
+		dev_err(&pdev->dev,
+			"This module does not support a virtual function.");
+		return -EINVAL;
+	}
+
+	dev_dbg(&pdev->dev, "Automotive Switch Ethernet driver loaded\n");
+
+	ret = rtase_init_board(pdev, &dev, &ioaddr);
+	if (ret != 0)
+		return ret;
+
+	tp = netdev_priv(dev);
+	tp->mmio_addr = ioaddr;
+	tp->dev = dev;
+	tp->pdev = pdev;
+
+	/* identify chip attached to board */
+	if (!rtase_check_mac_version_valid(tp))
+		return dev_err_probe(&pdev->dev, -ENODEV,
+				     "unknown chip version, contact rtase maintainers (see MAINTAINERS file)\n");
+
+	rtase_init_software_variable(pdev, tp);
+	rtase_init_hardware(tp);
+
+	ret = rtase_alloc_interrupt(pdev, tp);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "unable to alloc MSIX/MSI\n");
+		goto err_out_1;
+	}
+
+	rtase_init_netdev_ops(dev);
+
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
+
+	dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+			 NETIF_F_IP_CSUM | NETIF_F_HIGHDMA |
+			 NETIF_F_RXCSUM | NETIF_F_SG |
+			 NETIF_F_TSO | NETIF_F_IPV6_CSUM |
+			 NETIF_F_TSO6;
+
+	dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM |
+			   NETIF_F_TSO | NETIF_F_RXCSUM |
+			   NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+			   NETIF_F_RXALL | NETIF_F_RXFCS |
+			   NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
+
+	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
+			     NETIF_F_HIGHDMA;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+	netif_set_tso_max_size(dev, RTASE_LSO_64K);
+	netif_set_tso_max_segs(dev, RTASE_NIC_MAX_PHYS_BUF_COUNT_LSO2);
+
+	rtase_get_mac_address(dev);
+
+	tp->tally_vaddr = dma_alloc_coherent(&pdev->dev,
+					     sizeof(*tp->tally_vaddr),
+					     &tp->tally_paddr,
+					     GFP_KERNEL);
+	if (!tp->tally_vaddr) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
+	rtase_tally_counter_clear(tp);
+
+	pci_set_drvdata(pdev, dev);
+
+	netif_carrier_off(dev);
+
+	ret = register_netdev(dev);
+	if (ret != 0)
+		goto err_out;
+
+	netdev_dbg(dev, "%pM, IRQ %d\n", dev->dev_addr, dev->irq);
+
+	return 0;
+
+err_out:
+	if (tp->tally_vaddr) {
+		dma_free_coherent(&pdev->dev,
+				  sizeof(*tp->tally_vaddr),
+				  tp->tally_vaddr,
+				  tp->tally_paddr);
+
+		tp->tally_vaddr = NULL;
+	}
+
+err_out_1:
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		netif_napi_del(&ivec->napi);
+	}
+
+	rtase_release_board(pdev, dev, ioaddr);
+
+	return ret;
+}
+
+static void rtase_remove_one(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_int_vector *ivec;
+	u32 i;
+
+	unregister_netdev(dev);
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		netif_napi_del(&ivec->napi);
+	}
+
+	rtase_reset_interrupt(pdev, tp);
+	if (tp->tally_vaddr) {
+		dma_free_coherent(&pdev->dev,
+				  sizeof(*tp->tally_vaddr),
+				  tp->tally_vaddr,
+				  tp->tally_paddr);
+		tp->tally_vaddr = NULL;
+	}
+
+	rtase_release_board(pdev, dev, tp->mmio_addr);
+	pci_set_drvdata(pdev, NULL);
+}
+
+static void rtase_shutdown(struct pci_dev *pdev)
+{
+	struct net_device *dev = pci_get_drvdata(pdev);
+	const struct rtase_private *tp;
+
+	tp = netdev_priv(dev);
+
+	if (netif_running(dev))
+		rtase_close(dev);
+
+	rtase_reset_interrupt(pdev, tp);
+}
+
+static struct pci_driver rtase_pci_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = rtase_pci_tbl,
+	.probe = rtase_init_one,
+	.remove = rtase_remove_one,
+	.shutdown = rtase_shutdown,
+};
+
+module_pci_driver(rtase_pci_driver);
-- 
cgit v1.3-3-g829e


From ea244d7d8dce074e8a38e658ecd2e96abed288af Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:03 +0800
Subject: rtase: Implement the .ndo_open function

Implement the .ndo_open function to set default hardware settings
and initialize the descriptor ring and interrupts. Among them,
when requesting interrupt, because the first group of interrupts
needs to process more events, the overall structure and interrupt
handler will be different from other groups of interrupts, so it
needs to be handled separately. The first set of interrupt handlers
need to handle the interrupt status of RXQ0 and TXQ0, TXQ4~7,
while other groups of interrupt handlers will handle the interrupt
status of RXQ1&TXQ1 or RXQ2&TXQ2 or RXQ3&TXQ3 according to the
interrupt vector.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-3-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 405 ++++++++++++++++++++++++
 1 file changed, 405 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 2aa472d4212a..a7e8b4f50c5b 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -131,6 +131,277 @@ static u32 rtase_r32(const struct rtase_private *tp, u16 reg)
 	return readl(tp->mmio_addr + reg);
 }
 
+static void rtase_free_desc(struct rtase_private *tp)
+{
+	struct pci_dev *pdev = tp->pdev;
+	u32 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		if (!tp->tx_ring[i].desc)
+			continue;
+
+		dma_free_coherent(&pdev->dev, RTASE_TX_RING_DESC_SIZE,
+				  tp->tx_ring[i].desc,
+				  tp->tx_ring[i].phy_addr);
+		tp->tx_ring[i].desc = NULL;
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		if (!tp->rx_ring[i].desc)
+			continue;
+
+		dma_free_coherent(&pdev->dev, RTASE_RX_RING_DESC_SIZE,
+				  tp->rx_ring[i].desc,
+				  tp->rx_ring[i].phy_addr);
+		tp->rx_ring[i].desc = NULL;
+	}
+}
+
+static int rtase_alloc_desc(struct rtase_private *tp)
+{
+	struct pci_dev *pdev = tp->pdev;
+	u32 i;
+
+	/* rx and tx descriptors needs 256 bytes alignment.
+	 * dma_alloc_coherent provides more.
+	 */
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		tp->tx_ring[i].desc =
+				dma_alloc_coherent(&pdev->dev,
+						   RTASE_TX_RING_DESC_SIZE,
+						   &tp->tx_ring[i].phy_addr,
+						   GFP_KERNEL);
+		if (!tp->tx_ring[i].desc)
+			goto err_out;
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		tp->rx_ring[i].desc =
+				dma_alloc_coherent(&pdev->dev,
+						   RTASE_RX_RING_DESC_SIZE,
+						   &tp->rx_ring[i].phy_addr,
+						   GFP_KERNEL);
+		if (!tp->rx_ring[i].desc)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	rtase_free_desc(tp);
+	return -ENOMEM;
+}
+
+static void rtase_mark_to_asic(union rtase_rx_desc *desc, u32 rx_buf_sz)
+{
+	u32 eor = le32_to_cpu(desc->desc_cmd.opts1) & RTASE_RING_END;
+
+	desc->desc_status.opts2 = 0;
+	/* force memory writes to complete before releasing descriptor */
+	dma_wmb();
+	WRITE_ONCE(desc->desc_cmd.opts1,
+		   cpu_to_le32(RTASE_DESC_OWN | eor | rx_buf_sz));
+}
+
+static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx)
+{
+	struct rtase_ring *ring = &tp->tx_ring[idx];
+	struct rtase_tx_desc *desc;
+	u32 i;
+
+	memset(ring->desc, 0x0, RTASE_TX_RING_DESC_SIZE);
+	memset(ring->skbuff, 0x0, sizeof(ring->skbuff));
+	ring->cur_idx = 0;
+	ring->dirty_idx = 0;
+	ring->index = idx;
+	ring->alloc_fail = 0;
+
+	for (i = 0; i < RTASE_NUM_DESC; i++) {
+		ring->mis.len[i] = 0;
+		if ((RTASE_NUM_DESC - 1) == i) {
+			desc = ring->desc + sizeof(struct rtase_tx_desc) * i;
+			desc->opts1 = cpu_to_le32(RTASE_RING_END);
+		}
+	}
+
+	ring->ring_handler = tx_handler;
+	if (idx < 4) {
+		ring->ivec = &tp->int_vector[idx];
+		list_add_tail(&ring->ring_entry,
+			      &tp->int_vector[idx].ring_list);
+	} else {
+		ring->ivec = &tp->int_vector[0];
+		list_add_tail(&ring->ring_entry, &tp->int_vector[0].ring_list);
+	}
+}
+
+static void rtase_map_to_asic(union rtase_rx_desc *desc, dma_addr_t mapping,
+			      u32 rx_buf_sz)
+{
+	desc->desc_cmd.addr = cpu_to_le64(mapping);
+
+	rtase_mark_to_asic(desc, rx_buf_sz);
+}
+
+static void rtase_make_unusable_by_asic(union rtase_rx_desc *desc)
+{
+	desc->desc_cmd.addr = cpu_to_le64(RTK_MAGIC_NUMBER);
+	desc->desc_cmd.opts1 &= ~cpu_to_le32(RTASE_DESC_OWN | RSVD_MASK);
+}
+
+static int rtase_alloc_rx_data_buf(struct rtase_ring *ring,
+				   void **p_data_buf,
+				   union rtase_rx_desc *desc,
+				   dma_addr_t *rx_phy_addr)
+{
+	struct rtase_int_vector *ivec = ring->ivec;
+	const struct rtase_private *tp = ivec->tp;
+	dma_addr_t mapping;
+	struct page *page;
+
+	page = page_pool_dev_alloc_pages(tp->page_pool);
+	if (!page) {
+		ring->alloc_fail++;
+		goto err_out;
+	}
+
+	*p_data_buf = page_address(page);
+	mapping = page_pool_get_dma_addr(page);
+	*rx_phy_addr = mapping;
+	rtase_map_to_asic(desc, mapping, tp->rx_buf_sz);
+
+	return 0;
+
+err_out:
+	rtase_make_unusable_by_asic(desc);
+
+	return -ENOMEM;
+}
+
+static u32 rtase_rx_ring_fill(struct rtase_ring *ring, u32 ring_start,
+			      u32 ring_end)
+{
+	union rtase_rx_desc *desc_base = ring->desc;
+	u32 cur;
+
+	for (cur = ring_start; ring_end - cur > 0; cur++) {
+		u32 i = cur % RTASE_NUM_DESC;
+		union rtase_rx_desc *desc = desc_base + i;
+		int ret;
+
+		if (ring->data_buf[i])
+			continue;
+
+		ret = rtase_alloc_rx_data_buf(ring, &ring->data_buf[i], desc,
+					      &ring->mis.data_phy_addr[i]);
+		if (ret)
+			break;
+	}
+
+	return cur - ring_start;
+}
+
+static void rtase_mark_as_last_descriptor(union rtase_rx_desc *desc)
+{
+	desc->desc_cmd.opts1 |= cpu_to_le32(RTASE_RING_END);
+}
+
+static void rtase_rx_ring_clear(struct page_pool *page_pool,
+				struct rtase_ring *ring)
+{
+	union rtase_rx_desc *desc;
+	struct page *page;
+	u32 i;
+
+	for (i = 0; i < RTASE_NUM_DESC; i++) {
+		desc = ring->desc + sizeof(union rtase_rx_desc) * i;
+		page = virt_to_head_page(ring->data_buf[i]);
+
+		if (ring->data_buf[i])
+			page_pool_put_full_page(page_pool, page, true);
+
+		rtase_make_unusable_by_asic(desc);
+	}
+}
+
+static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx)
+{
+	struct rtase_ring *ring = &tp->rx_ring[idx];
+	u16 i;
+
+	memset(ring->desc, 0x0, RTASE_RX_RING_DESC_SIZE);
+	memset(ring->data_buf, 0x0, sizeof(ring->data_buf));
+	ring->cur_idx = 0;
+	ring->dirty_idx = 0;
+	ring->index = idx;
+	ring->alloc_fail = 0;
+
+	for (i = 0; i < RTASE_NUM_DESC; i++)
+		ring->mis.data_phy_addr[i] = 0;
+
+	ring->ring_handler = rx_handler;
+	ring->ivec = &tp->int_vector[idx];
+	list_add_tail(&ring->ring_entry, &tp->int_vector[idx].ring_list);
+}
+
+static void rtase_rx_clear(struct rtase_private *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->func_rx_queue_num; i++)
+		rtase_rx_ring_clear(tp->page_pool, &tp->rx_ring[i]);
+
+	page_pool_destroy(tp->page_pool);
+	tp->page_pool = NULL;
+}
+
+static int rtase_init_ring(const struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	struct page_pool_params pp_params = { 0 };
+	struct page_pool *page_pool;
+	u32 num;
+	u16 i;
+
+	pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp_params.order = 0;
+	pp_params.pool_size = RTASE_NUM_DESC * tp->func_rx_queue_num;
+	pp_params.nid = dev_to_node(&tp->pdev->dev);
+	pp_params.dev = &tp->pdev->dev;
+	pp_params.dma_dir = DMA_FROM_DEVICE;
+	pp_params.max_len = PAGE_SIZE;
+	pp_params.offset = 0;
+
+	page_pool = page_pool_create(&pp_params);
+	if (IS_ERR(page_pool)) {
+		netdev_err(tp->dev, "failed to create page pool\n");
+		return -ENOMEM;
+	}
+
+	tp->page_pool = page_pool;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++)
+		rtase_tx_desc_init(tp, i);
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		rtase_rx_desc_init(tp, i);
+
+		num = rtase_rx_ring_fill(&tp->rx_ring[i], 0, RTASE_NUM_DESC);
+		if (num != RTASE_NUM_DESC)
+			goto err_out;
+
+		rtase_mark_as_last_descriptor(tp->rx_ring[i].desc +
+					      sizeof(union rtase_rx_desc) *
+					      (RTASE_NUM_DESC - 1));
+	}
+
+	return 0;
+
+err_out:
+	rtase_rx_clear(tp);
+	return -ENOMEM;
+}
+
 static void rtase_tally_counter_clear(const struct rtase_private *tp)
 {
 	u32 cmd = lower_32_bits(tp->tally_paddr);
@@ -139,6 +410,130 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp)
 	rtase_w32(tp, RTASE_DTCCR0, cmd | RTASE_COUNTER_RESET);
 }
 
+static void rtase_nic_enable(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 rcr = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	u8 val;
+
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rcr & ~RTASE_PCIE_RELOAD_EN);
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rcr | RTASE_PCIE_RELOAD_EN);
+
+	val = rtase_r8(tp, RTASE_CHIP_CMD);
+	rtase_w8(tp, RTASE_CHIP_CMD, val | RTASE_TE | RTASE_RE);
+
+	val = rtase_r8(tp, RTASE_MISC);
+	rtase_w8(tp, RTASE_MISC, val & ~RTASE_RX_DV_GATE_EN);
+}
+
+static void rtase_enable_hw_interrupt(const struct rtase_private *tp)
+{
+	const struct rtase_int_vector *ivec = &tp->int_vector[0];
+	u32 i;
+
+	rtase_w32(tp, ivec->imr_addr, ivec->imr);
+
+	for (i = 1; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		rtase_w16(tp, ivec->imr_addr, ivec->imr);
+	}
+}
+
+static void rtase_hw_start(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+
+	rtase_nic_enable(dev);
+	rtase_enable_hw_interrupt(tp);
+}
+
+static int rtase_open(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	const struct pci_dev *pdev = tp->pdev;
+	struct rtase_int_vector *ivec;
+	u16 i = 0, j;
+	int ret;
+
+	ivec = &tp->int_vector[0];
+	tp->rx_buf_sz = RTASE_RX_BUF_SIZE;
+
+	ret = rtase_alloc_desc(tp);
+	if (ret)
+		return ret;
+
+	ret = rtase_init_ring(dev);
+	if (ret)
+		goto err_free_all_allocated_mem;
+
+	rtase_hw_config(dev);
+
+	if (tp->sw_flag & RTASE_SWF_MSIX_ENABLED) {
+		ret = request_irq(ivec->irq, rtase_interrupt, 0,
+				  dev->name, ivec);
+		if (ret)
+			goto err_free_all_allocated_irq;
+
+		/* request other interrupts to handle multiqueue */
+		for (i = 1; i < tp->int_nums; i++) {
+			ivec = &tp->int_vector[i];
+			snprintf(ivec->name, sizeof(ivec->name), "%s_int%i",
+				 tp->dev->name, i);
+			ret = request_irq(ivec->irq, rtase_q_interrupt, 0,
+					  ivec->name, ivec);
+			if (ret)
+				goto err_free_all_allocated_irq;
+		}
+	} else {
+		ret = request_irq(pdev->irq, rtase_interrupt, 0, dev->name,
+				  ivec);
+		if (ret)
+			goto err_free_all_allocated_mem;
+	}
+
+	rtase_hw_start(dev);
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		napi_enable(&ivec->napi);
+	}
+
+	netif_carrier_on(dev);
+	netif_wake_queue(dev);
+
+	return 0;
+
+err_free_all_allocated_irq:
+	for (j = 0; j < i; j++)
+		free_irq(tp->int_vector[j].irq, &tp->int_vector[j]);
+
+err_free_all_allocated_mem:
+	rtase_free_desc(tp);
+
+	return ret;
+}
+
+static int rtase_close(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	const struct pci_dev *pdev = tp->pdev;
+	u32 i;
+
+	rtase_down(dev);
+
+	if (tp->sw_flag & RTASE_SWF_MSIX_ENABLED) {
+		for (i = 0; i < tp->int_nums; i++)
+			free_irq(tp->int_vector[i].irq, &tp->int_vector[i]);
+
+	} else {
+		free_irq(pdev->irq, &tp->int_vector[0]);
+	}
+
+	rtase_free_desc(tp);
+
+	return 0;
+}
+
 static void rtase_enable_eem_write(const struct rtase_private *tp)
 {
 	u8 val;
@@ -171,6 +566,11 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr)
 	rtase_w16(tp, RTASE_LBK_CTRL, RTASE_LBK_ATLD | RTASE_LBK_CLR);
 }
 
+static const struct net_device_ops rtase_netdev_ops = {
+	.ndo_open = rtase_open,
+	.ndo_stop = rtase_close,
+};
+
 static void rtase_get_mac_address(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
@@ -191,6 +591,11 @@ static void rtase_get_mac_address(struct net_device *dev)
 	rtase_rar_set(tp, dev->dev_addr);
 }
 
+static void rtase_init_netdev_ops(struct net_device *dev)
+{
+	dev->netdev_ops = &rtase_netdev_ops;
+}
+
 static void rtase_reset_interrupt(struct pci_dev *pdev,
 				  const struct rtase_private *tp)
 {
-- 
cgit v1.3-3-g829e


From 5a2a2f15244cd3c0de396ec8bf7121ef6121994b Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:04 +0800
Subject: rtase: Implement the rtase_down function

Implement the rtase_down function to disable hardware setting
and interrupt and clear descriptor ring.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-4-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 150 ++++++++++++++++++++++++
 1 file changed, 150 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index a7e8b4f50c5b..7f683c246003 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -192,6 +192,56 @@ err_out:
 	return -ENOMEM;
 }
 
+static void rtase_unmap_tx_skb(struct pci_dev *pdev, u32 len,
+			       struct rtase_tx_desc *desc)
+{
+	dma_unmap_single(&pdev->dev, le64_to_cpu(desc->addr), len,
+			 DMA_TO_DEVICE);
+	desc->opts1 = cpu_to_le32(RTK_OPTS1_DEBUG_VALUE);
+	desc->opts2 = 0x00;
+	desc->addr = cpu_to_le64(RTK_MAGIC_NUMBER);
+}
+
+static void rtase_tx_clear_range(struct rtase_ring *ring, u32 start, u32 n)
+{
+	struct rtase_tx_desc *desc_base = ring->desc;
+	struct rtase_private *tp = ring->ivec->tp;
+	u32 i;
+
+	for (i = 0; i < n; i++) {
+		u32 entry = (start + i) % RTASE_NUM_DESC;
+		struct rtase_tx_desc *desc = desc_base + entry;
+		u32 len = ring->mis.len[entry];
+		struct sk_buff *skb;
+
+		if (len == 0)
+			continue;
+
+		rtase_unmap_tx_skb(tp->pdev, len, desc);
+		ring->mis.len[entry] = 0;
+		skb = ring->skbuff[entry];
+		if (!skb)
+			continue;
+
+		tp->stats.tx_dropped++;
+		dev_kfree_skb_any(skb);
+		ring->skbuff[entry] = NULL;
+	}
+}
+
+static void rtase_tx_clear(struct rtase_private *tp)
+{
+	struct rtase_ring *ring;
+	u16 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		ring = &tp->tx_ring[i];
+		rtase_tx_clear_range(ring, ring->dirty_idx, RTASE_NUM_DESC);
+		ring->cur_idx = 0;
+		ring->dirty_idx = 0;
+	}
+}
+
 static void rtase_mark_to_asic(union rtase_rx_desc *desc, u32 rx_buf_sz)
 {
 	u32 eor = le32_to_cpu(desc->desc_cmd.opts1) & RTASE_RING_END;
@@ -410,6 +460,80 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp)
 	rtase_w32(tp, RTASE_DTCCR0, cmd | RTASE_COUNTER_RESET);
 }
 
+static void rtase_irq_dis_and_clear(const struct rtase_private *tp)
+{
+	const struct rtase_int_vector *ivec = &tp->int_vector[0];
+	u32 val1;
+	u16 val2;
+	u8 i;
+
+	rtase_w32(tp, ivec->imr_addr, 0);
+	val1 = rtase_r32(tp, ivec->isr_addr);
+	rtase_w32(tp, ivec->isr_addr, val1);
+
+	for (i = 1; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		rtase_w16(tp, ivec->imr_addr, 0);
+		val2 = rtase_r16(tp, ivec->isr_addr);
+		rtase_w16(tp, ivec->isr_addr, val2);
+	}
+}
+
+static void rtase_poll_timeout(const struct rtase_private *tp, u32 cond,
+			       u32 sleep_us, u64 timeout_us, u16 reg)
+{
+	int err;
+	u8 val;
+
+	err = read_poll_timeout(rtase_r8, val, val & cond, sleep_us,
+				timeout_us, false, tp, reg);
+
+	if (err == -ETIMEDOUT)
+		netdev_err(tp->dev, "poll reg 0x00%x timeout\n", reg);
+}
+
+static void rtase_nic_reset(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_config;
+	u8 val;
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config & ~RTASE_ACCEPT_MASK);
+
+	val = rtase_r8(tp, RTASE_MISC);
+	rtase_w8(tp, RTASE_MISC, val | RTASE_RX_DV_GATE_EN);
+
+	val = rtase_r8(tp, RTASE_CHIP_CMD);
+	rtase_w8(tp, RTASE_CHIP_CMD, val | RTASE_STOP_REQ);
+	mdelay(2);
+
+	rtase_poll_timeout(tp, RTASE_STOP_REQ_DONE, 100, 150000,
+			   RTASE_CHIP_CMD);
+
+	rtase_poll_timeout(tp, RTASE_TX_FIFO_EMPTY, 100, 100000,
+			   RTASE_FIFOR);
+
+	rtase_poll_timeout(tp, RTASE_RX_FIFO_EMPTY, 100, 100000,
+			   RTASE_FIFOR);
+
+	val = rtase_r8(tp, RTASE_CHIP_CMD);
+	rtase_w8(tp, RTASE_CHIP_CMD, val & ~(RTASE_TE | RTASE_RE));
+	val = rtase_r8(tp, RTASE_CHIP_CMD);
+	rtase_w8(tp, RTASE_CHIP_CMD, val & ~RTASE_STOP_REQ);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config);
+}
+
+static void rtase_hw_reset(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+
+	rtase_irq_dis_and_clear(tp);
+
+	rtase_nic_reset(dev);
+}
+
 static void rtase_nic_enable(const struct net_device *dev)
 {
 	const struct rtase_private *tp = netdev_priv(dev);
@@ -513,6 +637,32 @@ err_free_all_allocated_mem:
 	return ret;
 }
 
+static void rtase_down(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_int_vector *ivec;
+	struct rtase_ring *ring, *tmp;
+	u32 i;
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		napi_disable(&ivec->napi);
+		list_for_each_entry_safe(ring, tmp, &ivec->ring_list,
+					 ring_entry)
+			list_del(&ring->ring_entry);
+	}
+
+	netif_tx_disable(dev);
+
+	netif_carrier_off(dev);
+
+	rtase_hw_reset(dev);
+
+	rtase_tx_clear(tp);
+
+	rtase_rx_clear(tp);
+}
+
 static int rtase_close(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
-- 
cgit v1.3-3-g829e


From 2bbba79e348d872510cadb9783a11896634062ec Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:05 +0800
Subject: rtase: Implement the interrupt routine and rtase_poll

1. Implement rtase_interrupt to handle txQ0/rxQ0, txQ4~txQ7 interrupts,
and implement rtase_q_interrupt to handle txQ1/rxQ1, txQ2/rxQ2 and
txQ3/rxQ3 interrupts.
2. Implement rtase_poll to call ring_handler to process the tx or
rx packet of each ring. If the returned value is budget,it means that
there is still work of a certain ring that has not yet been completed.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-5-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 69 +++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 7f683c246003..6e7f30b015eb 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -571,6 +571,75 @@ static void rtase_hw_start(const struct net_device *dev)
 	rtase_enable_hw_interrupt(tp);
 }
 
+/*  the interrupt handler does RXQ0 and TXQ0, TXQ4~7 interrutp status
+ */
+static irqreturn_t rtase_interrupt(int irq, void *dev_instance)
+{
+	const struct rtase_private *tp;
+	struct rtase_int_vector *ivec;
+	u32 status;
+
+	ivec = dev_instance;
+	tp = ivec->tp;
+	status = rtase_r32(tp, ivec->isr_addr);
+
+	rtase_w32(tp, ivec->imr_addr, 0x0);
+	rtase_w32(tp, ivec->isr_addr, status & ~RTASE_FOVW);
+
+	if (napi_schedule_prep(&ivec->napi))
+		__napi_schedule(&ivec->napi);
+
+	return IRQ_HANDLED;
+}
+
+/*  the interrupt handler does RXQ1&TXQ1 or RXQ2&TXQ2 or RXQ3&TXQ3 interrupt
+ *  status according to interrupt vector
+ */
+static irqreturn_t rtase_q_interrupt(int irq, void *dev_instance)
+{
+	const struct rtase_private *tp;
+	struct rtase_int_vector *ivec;
+	u16 status;
+
+	ivec = dev_instance;
+	tp = ivec->tp;
+	status = rtase_r16(tp, ivec->isr_addr);
+
+	rtase_w16(tp, ivec->imr_addr, 0x0);
+	rtase_w16(tp, ivec->isr_addr, status);
+
+	if (napi_schedule_prep(&ivec->napi))
+		__napi_schedule(&ivec->napi);
+
+	return IRQ_HANDLED;
+}
+
+static int rtase_poll(struct napi_struct *napi, int budget)
+{
+	const struct rtase_int_vector *ivec;
+	const struct rtase_private *tp;
+	struct rtase_ring *ring;
+	int total_workdone = 0;
+
+	ivec = container_of(napi, struct rtase_int_vector, napi);
+	tp = ivec->tp;
+
+	list_for_each_entry(ring, &ivec->ring_list, ring_entry)
+		total_workdone += ring->ring_handler(ring, budget);
+
+	if (total_workdone >= budget)
+		return budget;
+
+	if (napi_complete_done(napi, total_workdone)) {
+		if (!ivec->index)
+			rtase_w32(tp, ivec->imr_addr, ivec->imr);
+		else
+			rtase_w16(tp, ivec->imr_addr, ivec->imr);
+	}
+
+	return total_workdone;
+}
+
 static int rtase_open(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
-- 
cgit v1.3-3-g829e


From 85dd839ad1e52b2d32499b8ee3861fd958bfa96b Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:06 +0800
Subject: rtase: Implement hardware configuration function

Implement rtase_hw_config to set default hardware settings, including
setting interrupt mitigation, tx/rx DMA burst, interframe gap time,
rx packet filter, near fifo threshold and fill descriptor ring and
tally counter address, and enable flow control. When filling the
rx descriptor ring, the first group of queues needs to be processed
separately because the positions of the first group of queues are not
regular with other subsequent groups. The other queues are all newly
added features, but we want to retain the original design. So they were
not put together.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-6-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 238 ++++++++++++++++++++++++
 1 file changed, 238 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 6e7f30b015eb..ce40aa84588f 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -452,6 +452,23 @@ err_out:
 	return -ENOMEM;
 }
 
+static void rtase_interrupt_mitigation(const struct rtase_private *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++)
+		rtase_w16(tp, RTASE_INT_MITI_TX + i * 2, tp->tx_int_mit);
+
+	for (i = 0; i < tp->func_rx_queue_num; i++)
+		rtase_w16(tp, RTASE_INT_MITI_RX + i * 2, tp->rx_int_mit);
+}
+
+static void rtase_tally_counter_addr_fill(const struct rtase_private *tp)
+{
+	rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(tp->tally_paddr));
+	rtase_w32(tp, RTASE_DTCCR0, lower_32_bits(tp->tally_paddr));
+}
+
 static void rtase_tally_counter_clear(const struct rtase_private *tp)
 {
 	u32 cmd = lower_32_bits(tp->tally_paddr);
@@ -460,6 +477,119 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp)
 	rtase_w32(tp, RTASE_DTCCR0, cmd | RTASE_COUNTER_RESET);
 }
 
+static void rtase_desc_addr_fill(const struct rtase_private *tp)
+{
+	const struct rtase_ring *ring;
+	u16 i, cmd, val;
+	int err;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		ring = &tp->tx_ring[i];
+
+		rtase_w32(tp, RTASE_TX_DESC_ADDR0,
+			  lower_32_bits(ring->phy_addr));
+		rtase_w32(tp, RTASE_TX_DESC_ADDR4,
+			  upper_32_bits(ring->phy_addr));
+
+		cmd = i | RTASE_TX_DESC_CMD_WE | RTASE_TX_DESC_CMD_CS;
+		rtase_w16(tp, RTASE_TX_DESC_COMMAND, cmd);
+
+		err = read_poll_timeout(rtase_r16, val,
+					!(val & RTASE_TX_DESC_CMD_CS), 10,
+					1000, false, tp,
+					RTASE_TX_DESC_COMMAND);
+
+		if (err == -ETIMEDOUT)
+			netdev_err(tp->dev,
+				   "error occurred in fill tx descriptor\n");
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		ring = &tp->rx_ring[i];
+
+		if (i == 0) {
+			rtase_w32(tp, RTASE_Q0_RX_DESC_ADDR0,
+				  lower_32_bits(ring->phy_addr));
+			rtase_w32(tp, RTASE_Q0_RX_DESC_ADDR4,
+				  upper_32_bits(ring->phy_addr));
+		} else {
+			rtase_w32(tp, (RTASE_Q1_RX_DESC_ADDR0 + ((i - 1) * 8)),
+				  lower_32_bits(ring->phy_addr));
+			rtase_w32(tp, (RTASE_Q1_RX_DESC_ADDR4 + ((i - 1) * 8)),
+				  upper_32_bits(ring->phy_addr));
+		}
+	}
+}
+
+static void rtase_hw_set_features(const struct net_device *dev,
+				  netdev_features_t features)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_config, val;
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	if (features & NETIF_F_RXALL)
+		rx_config |= (RTASE_ACCEPT_ERR | RTASE_ACCEPT_RUNT);
+	else
+		rx_config &= ~(RTASE_ACCEPT_ERR | RTASE_ACCEPT_RUNT);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config);
+
+	val = rtase_r16(tp, RTASE_CPLUS_CMD);
+	if (features & NETIF_F_RXCSUM)
+		rtase_w16(tp, RTASE_CPLUS_CMD, val | RTASE_RX_CHKSUM);
+	else
+		rtase_w16(tp, RTASE_CPLUS_CMD, val & ~RTASE_RX_CHKSUM);
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		rx_config |= (RTASE_INNER_VLAN_DETAG_EN |
+			      RTASE_OUTER_VLAN_DETAG_EN);
+	else
+		rx_config &= ~(RTASE_INNER_VLAN_DETAG_EN |
+			       RTASE_OUTER_VLAN_DETAG_EN);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rx_config);
+}
+
+static void rtase_hw_set_rx_packet_filter(struct net_device *dev)
+{
+	u32 mc_filter[2] = { 0xFFFFFFFF, 0xFFFFFFFF };
+	struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_mode;
+
+	rx_mode = rtase_r16(tp, RTASE_RX_CONFIG_0) & ~RTASE_ACCEPT_MASK;
+	rx_mode |= RTASE_ACCEPT_BROADCAST | RTASE_ACCEPT_MYPHYS;
+
+	if (dev->flags & IFF_PROMISC) {
+		rx_mode |= RTASE_ACCEPT_MULTICAST | RTASE_ACCEPT_ALLPHYS;
+	} else if (dev->flags & IFF_ALLMULTI) {
+		rx_mode |= RTASE_ACCEPT_MULTICAST;
+	} else {
+		struct netdev_hw_addr *hw_addr;
+
+		mc_filter[0] = 0;
+		mc_filter[1] = 0;
+
+		netdev_for_each_mc_addr(hw_addr, dev) {
+			u32 bit_nr = eth_hw_addr_crc(hw_addr);
+			u32 idx = u32_get_bits(bit_nr, BIT(31));
+			u32 bit = u32_get_bits(bit_nr,
+					       RTASE_MULTICAST_FILTER_MASK);
+
+			mc_filter[idx] |= BIT(bit);
+			rx_mode |= RTASE_ACCEPT_MULTICAST;
+		}
+	}
+
+	if (dev->features & NETIF_F_RXALL)
+		rx_mode |= RTASE_ACCEPT_ERR | RTASE_ACCEPT_RUNT;
+
+	rtase_w32(tp, RTASE_MAR0, swab32(mc_filter[1]));
+	rtase_w32(tp, RTASE_MAR1, swab32(mc_filter[0]));
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_mode);
+}
+
 static void rtase_irq_dis_and_clear(const struct rtase_private *tp)
 {
 	const struct rtase_int_vector *ivec = &tp->int_vector[0];
@@ -534,6 +664,114 @@ static void rtase_hw_reset(const struct net_device *dev)
 	rtase_nic_reset(dev);
 }
 
+static void rtase_set_rx_queue(const struct rtase_private *tp)
+{
+	u16 reg_data;
+
+	reg_data = rtase_r16(tp, RTASE_FCR);
+	switch (tp->func_rx_queue_num) {
+	case 1:
+		u16p_replace_bits(&reg_data, 0x1, RTASE_FCR_RXQ_MASK);
+		break;
+	case 2:
+		u16p_replace_bits(&reg_data, 0x2, RTASE_FCR_RXQ_MASK);
+		break;
+	case 4:
+		u16p_replace_bits(&reg_data, 0x3, RTASE_FCR_RXQ_MASK);
+		break;
+	}
+	rtase_w16(tp, RTASE_FCR, reg_data);
+}
+
+static void rtase_set_tx_queue(const struct rtase_private *tp)
+{
+	u16 reg_data;
+
+	reg_data = rtase_r16(tp, RTASE_TX_CONFIG_1);
+	switch (tp->tx_queue_ctrl) {
+	case 1:
+		u16p_replace_bits(&reg_data, 0x0, RTASE_TC_MODE_MASK);
+		break;
+	case 2:
+		u16p_replace_bits(&reg_data, 0x1, RTASE_TC_MODE_MASK);
+		break;
+	case 3:
+	case 4:
+		u16p_replace_bits(&reg_data, 0x2, RTASE_TC_MODE_MASK);
+		break;
+	default:
+		u16p_replace_bits(&reg_data, 0x3, RTASE_TC_MODE_MASK);
+		break;
+	}
+	rtase_w16(tp, RTASE_TX_CONFIG_1, reg_data);
+}
+
+static void rtase_hw_config(struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u32 reg_data32;
+	u16 reg_data16;
+
+	rtase_hw_reset(dev);
+
+	/* set rx dma burst */
+	reg_data16 = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	reg_data16 &= ~(RTASE_RX_SINGLE_TAG | RTASE_RX_SINGLE_FETCH);
+	u16p_replace_bits(&reg_data16, RTASE_RX_DMA_BURST_256,
+			  RTASE_RX_MX_DMA_MASK);
+	rtase_w16(tp, RTASE_RX_CONFIG_0, reg_data16);
+
+	/* new rx descritpor */
+	reg_data16 = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	reg_data16 |= RTASE_RX_NEW_DESC_FORMAT_EN | RTASE_PCIE_NEW_FLOW;
+	u16p_replace_bits(&reg_data16, 0xF, RTASE_RX_MAX_FETCH_DESC_MASK);
+	rtase_w16(tp, RTASE_RX_CONFIG_1, reg_data16);
+
+	rtase_set_rx_queue(tp);
+
+	rtase_interrupt_mitigation(tp);
+
+	/* set tx dma burst size and interframe gap time */
+	reg_data32 = rtase_r32(tp, RTASE_TX_CONFIG_0);
+	u32p_replace_bits(&reg_data32, RTASE_TX_DMA_BURST_UNLIMITED,
+			  RTASE_TX_DMA_MASK);
+	u32p_replace_bits(&reg_data32, RTASE_INTERFRAMEGAP,
+			  RTASE_TX_INTER_FRAME_GAP_MASK);
+	rtase_w32(tp, RTASE_TX_CONFIG_0, reg_data32);
+
+	/* new tx descriptor */
+	reg_data16 = rtase_r16(tp, RTASE_TFUN_CTRL);
+	rtase_w16(tp, RTASE_TFUN_CTRL, reg_data16 |
+		  RTASE_TX_NEW_DESC_FORMAT_EN);
+
+	/* tx fetch desc number */
+	rtase_w8(tp, RTASE_TDFNR, 0x10);
+
+	/* tag num select */
+	reg_data16 = rtase_r16(tp, RTASE_MTPS);
+	u16p_replace_bits(&reg_data16, 0x4, RTASE_TAG_NUM_SEL_MASK);
+	rtase_w16(tp, RTASE_MTPS, reg_data16);
+
+	rtase_set_tx_queue(tp);
+
+	rtase_w16(tp, RTASE_TOKSEL, 0x5555);
+
+	rtase_tally_counter_addr_fill(tp);
+	rtase_desc_addr_fill(tp);
+	rtase_hw_set_features(dev, dev->features);
+
+	/* enable flow control */
+	reg_data16 = rtase_r16(tp, RTASE_CPLUS_CMD);
+	reg_data16 |= (RTASE_FORCE_TXFLOW_EN | RTASE_FORCE_RXFLOW_EN);
+	rtase_w16(tp, RTASE_CPLUS_CMD, reg_data16);
+	/* set near fifo threshold - rx missed issue. */
+	rtase_w16(tp, RTASE_RFIFONFULL, 0x190);
+
+	rtase_w16(tp, RTASE_RMS, tp->rx_buf_sz);
+
+	rtase_hw_set_rx_packet_filter(dev);
+}
+
 static void rtase_nic_enable(const struct net_device *dev)
 {
 	const struct rtase_private *tp = netdev_priv(dev);
-- 
cgit v1.3-3-g829e


From d6e882b89fdf80be0ab4f914ec10f75215e49495 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:07 +0800
Subject: rtase: Implement .ndo_start_xmit function

Implement .ndo_start_xmit function to fill the information of the packet
to be transmitted into the tx descriptor, and then the hardware will
transmit the packet using the information in the tx descriptor.
In addition, we also implemented the tx_handler function to enable the
tx descriptor to be reused.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-7-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 283 ++++++++++++++++++++++++
 1 file changed, 283 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index ce40aa84588f..bef5a944df59 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -253,6 +253,68 @@ static void rtase_mark_to_asic(union rtase_rx_desc *desc, u32 rx_buf_sz)
 		   cpu_to_le32(RTASE_DESC_OWN | eor | rx_buf_sz));
 }
 
+static u32 rtase_tx_avail(struct rtase_ring *ring)
+{
+	return READ_ONCE(ring->dirty_idx) + RTASE_NUM_DESC -
+	       READ_ONCE(ring->cur_idx);
+}
+
+static int tx_handler(struct rtase_ring *ring, int budget)
+{
+	const struct rtase_private *tp = ring->ivec->tp;
+	struct net_device *dev = tp->dev;
+	u32 dirty_tx, tx_left;
+	u32 bytes_compl = 0;
+	u32 pkts_compl = 0;
+	int workdone = 0;
+
+	dirty_tx = ring->dirty_idx;
+	tx_left = READ_ONCE(ring->cur_idx) - dirty_tx;
+
+	while (tx_left > 0) {
+		u32 entry = dirty_tx % RTASE_NUM_DESC;
+		struct rtase_tx_desc *desc = ring->desc +
+				       sizeof(struct rtase_tx_desc) * entry;
+		u32 status;
+
+		status = le32_to_cpu(desc->opts1);
+
+		if (status & RTASE_DESC_OWN)
+			break;
+
+		rtase_unmap_tx_skb(tp->pdev, ring->mis.len[entry], desc);
+		ring->mis.len[entry] = 0;
+		if (ring->skbuff[entry]) {
+			pkts_compl++;
+			bytes_compl += ring->skbuff[entry]->len;
+			napi_consume_skb(ring->skbuff[entry], budget);
+			ring->skbuff[entry] = NULL;
+		}
+
+		dirty_tx++;
+		tx_left--;
+		workdone++;
+
+		if (workdone == RTASE_TX_BUDGET_DEFAULT)
+			break;
+	}
+
+	if (ring->dirty_idx != dirty_tx) {
+		dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl);
+		WRITE_ONCE(ring->dirty_idx, dirty_tx);
+
+		netif_subqueue_completed_wake(dev, ring->index, pkts_compl,
+					      bytes_compl,
+					      rtase_tx_avail(ring),
+					      RTASE_TX_START_THRS);
+
+		if (ring->cur_idx != dirty_tx)
+			rtase_w8(tp, RTASE_TPPOLL, BIT(ring->index));
+	}
+
+	return 0;
+}
+
 static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx)
 {
 	struct rtase_ring *ring = &tp->tx_ring[idx];
@@ -991,6 +1053,226 @@ static int rtase_close(struct net_device *dev)
 	return 0;
 }
 
+static u32 rtase_tx_vlan_tag(const struct rtase_private *tp,
+			     const struct sk_buff *skb)
+{
+	return (skb_vlan_tag_present(skb)) ?
+		(RTASE_TX_VLAN_TAG | swab16(skb_vlan_tag_get(skb))) : 0x00;
+}
+
+static u32 rtase_tx_csum(struct sk_buff *skb, const struct net_device *dev)
+{
+	u32 csum_cmd = 0;
+	u8 ip_protocol;
+
+	switch (vlan_get_protocol(skb)) {
+	case htons(ETH_P_IP):
+		csum_cmd = RTASE_TX_IPCS_C;
+		ip_protocol = ip_hdr(skb)->protocol;
+		break;
+
+	case htons(ETH_P_IPV6):
+		csum_cmd = RTASE_TX_IPV6F_C;
+		ip_protocol = ipv6_hdr(skb)->nexthdr;
+		break;
+
+	default:
+		ip_protocol = IPPROTO_RAW;
+		break;
+	}
+
+	if (ip_protocol == IPPROTO_TCP)
+		csum_cmd |= RTASE_TX_TCPCS_C;
+	else if (ip_protocol == IPPROTO_UDP)
+		csum_cmd |= RTASE_TX_UDPCS_C;
+
+	csum_cmd |= u32_encode_bits(skb_transport_offset(skb),
+				    RTASE_TCPHO_MASK);
+
+	return csum_cmd;
+}
+
+static int rtase_xmit_frags(struct rtase_ring *ring, struct sk_buff *skb,
+			    u32 opts1, u32 opts2)
+{
+	const struct skb_shared_info *info = skb_shinfo(skb);
+	const struct rtase_private *tp = ring->ivec->tp;
+	const u8 nr_frags = info->nr_frags;
+	struct rtase_tx_desc *txd = NULL;
+	u32 cur_frag, entry;
+
+	entry = ring->cur_idx;
+	for (cur_frag = 0; cur_frag < nr_frags; cur_frag++) {
+		const skb_frag_t *frag = &info->frags[cur_frag];
+		dma_addr_t mapping;
+		u32 status, len;
+		void *addr;
+
+		entry = (entry + 1) % RTASE_NUM_DESC;
+
+		txd = ring->desc + sizeof(struct rtase_tx_desc) * entry;
+		len = skb_frag_size(frag);
+		addr = skb_frag_address(frag);
+		mapping = dma_map_single(&tp->pdev->dev, addr, len,
+					 DMA_TO_DEVICE);
+
+		if (unlikely(dma_mapping_error(&tp->pdev->dev, mapping))) {
+			if (unlikely(net_ratelimit()))
+				netdev_err(tp->dev,
+					   "Failed to map TX fragments DMA!\n");
+
+			goto err_out;
+		}
+
+		if (((entry + 1) % RTASE_NUM_DESC) == 0)
+			status = (opts1 | len | RTASE_RING_END);
+		else
+			status = opts1 | len;
+
+		if (cur_frag == (nr_frags - 1)) {
+			ring->skbuff[entry] = skb;
+			status |= RTASE_TX_LAST_FRAG;
+		}
+
+		ring->mis.len[entry] = len;
+		txd->addr = cpu_to_le64(mapping);
+		txd->opts2 = cpu_to_le32(opts2);
+
+		/* make sure the operating fields have been updated */
+		dma_wmb();
+		txd->opts1 = cpu_to_le32(status);
+	}
+
+	return cur_frag;
+
+err_out:
+	rtase_tx_clear_range(ring, ring->cur_idx + 1, cur_frag);
+	return -EIO;
+}
+
+static netdev_tx_t rtase_start_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	struct rtase_private *tp = netdev_priv(dev);
+	u32 q_idx, entry, len, opts1, opts2;
+	struct netdev_queue *tx_queue;
+	bool stop_queue, door_bell;
+	u32 mss = shinfo->gso_size;
+	struct rtase_tx_desc *txd;
+	struct rtase_ring *ring;
+	dma_addr_t mapping;
+	int frags;
+
+	/* multiqueues */
+	q_idx = skb_get_queue_mapping(skb);
+	ring = &tp->tx_ring[q_idx];
+	tx_queue = netdev_get_tx_queue(dev, q_idx);
+
+	if (unlikely(!rtase_tx_avail(ring))) {
+		if (net_ratelimit())
+			netdev_err(dev,
+				   "BUG! Tx Ring full when queue awake!\n");
+
+		netif_stop_queue(dev);
+		return NETDEV_TX_BUSY;
+	}
+
+	entry = ring->cur_idx % RTASE_NUM_DESC;
+	txd = ring->desc + sizeof(struct rtase_tx_desc) * entry;
+
+	opts1 = RTASE_DESC_OWN;
+	opts2 = rtase_tx_vlan_tag(tp, skb);
+
+	/* tcp segmentation offload (or tcp large send) */
+	if (mss) {
+		if (shinfo->gso_type & SKB_GSO_TCPV4) {
+			opts1 |= RTASE_GIANT_SEND_V4;
+		} else if (shinfo->gso_type & SKB_GSO_TCPV6) {
+			if (skb_cow_head(skb, 0))
+				goto err_dma_0;
+
+			tcp_v6_gso_csum_prep(skb);
+			opts1 |= RTASE_GIANT_SEND_V6;
+		} else {
+			WARN_ON_ONCE(1);
+		}
+
+		opts1 |= u32_encode_bits(skb_transport_offset(skb),
+					 RTASE_TCPHO_MASK);
+		opts2 |= u32_encode_bits(mss, RTASE_MSS_MASK);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		opts2 |= rtase_tx_csum(skb, dev);
+	}
+
+	frags = rtase_xmit_frags(ring, skb, opts1, opts2);
+	if (unlikely(frags < 0))
+		goto err_dma_0;
+
+	if (frags) {
+		len = skb_headlen(skb);
+		opts1 |= RTASE_TX_FIRST_FRAG;
+	} else {
+		len = skb->len;
+		ring->skbuff[entry] = skb;
+		opts1 |= RTASE_TX_FIRST_FRAG | RTASE_TX_LAST_FRAG;
+	}
+
+	if (((entry + 1) % RTASE_NUM_DESC) == 0)
+		opts1 |= (len | RTASE_RING_END);
+	else
+		opts1 |= len;
+
+	mapping = dma_map_single(&tp->pdev->dev, skb->data, len,
+				 DMA_TO_DEVICE);
+
+	if (unlikely(dma_mapping_error(&tp->pdev->dev, mapping))) {
+		if (unlikely(net_ratelimit()))
+			netdev_err(dev, "Failed to map TX DMA!\n");
+
+		goto err_dma_1;
+	}
+
+	ring->mis.len[entry] = len;
+	txd->addr = cpu_to_le64(mapping);
+	txd->opts2 = cpu_to_le32(opts2);
+	txd->opts1 = cpu_to_le32(opts1 & ~RTASE_DESC_OWN);
+
+	/* make sure the operating fields have been updated */
+	dma_wmb();
+
+	door_bell = __netdev_tx_sent_queue(tx_queue, skb->len,
+					   netdev_xmit_more());
+
+	txd->opts1 = cpu_to_le32(opts1);
+
+	skb_tx_timestamp(skb);
+
+	/* tx needs to see descriptor changes before updated cur_idx */
+	smp_wmb();
+
+	WRITE_ONCE(ring->cur_idx, ring->cur_idx + frags + 1);
+
+	stop_queue = !netif_subqueue_maybe_stop(dev, ring->index,
+						rtase_tx_avail(ring),
+						RTASE_TX_STOP_THRS,
+						RTASE_TX_START_THRS);
+
+	if (door_bell || stop_queue)
+		rtase_w8(tp, RTASE_TPPOLL, BIT(ring->index));
+
+	return NETDEV_TX_OK;
+
+err_dma_1:
+	ring->skbuff[entry] = NULL;
+	rtase_tx_clear_range(ring, ring->cur_idx + 1, frags);
+
+err_dma_0:
+	tp->stats.tx_dropped++;
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
 static void rtase_enable_eem_write(const struct rtase_private *tp)
 {
 	u8 val;
@@ -1026,6 +1308,7 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr)
 static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_open = rtase_open,
 	.ndo_stop = rtase_close,
+	.ndo_start_xmit = rtase_start_xmit,
 };
 
 static void rtase_get_mac_address(struct net_device *dev)
-- 
cgit v1.3-3-g829e


From cf7226c808452aa5d2597fe23b864d7d2045cd70 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:08 +0800
Subject: rtase: Implement a function to receive packets

Implement rx_handler to read the information of the rx descriptor,
thereby checking the packet accordingly and storing the packet
in the socket buffer to complete the reception of the packet.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-8-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 144 ++++++++++++++++++++++++
 1 file changed, 144 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index bef5a944df59..361e9f2a02b8 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -436,6 +436,150 @@ static void rtase_rx_ring_clear(struct page_pool *page_pool,
 	}
 }
 
+static int rtase_fragmented_frame(u32 status)
+{
+	return (status & (RTASE_RX_FIRST_FRAG | RTASE_RX_LAST_FRAG)) !=
+	       (RTASE_RX_FIRST_FRAG | RTASE_RX_LAST_FRAG);
+}
+
+static void rtase_rx_csum(const struct rtase_private *tp, struct sk_buff *skb,
+			  const union rtase_rx_desc *desc)
+{
+	u32 opts2 = le32_to_cpu(desc->desc_status.opts2);
+
+	/* rx csum offload */
+	if (((opts2 & RTASE_RX_V4F) && !(opts2 & RTASE_RX_IPF)) ||
+	    (opts2 & RTASE_RX_V6F)) {
+		if (((opts2 & RTASE_RX_TCPT) && !(opts2 & RTASE_RX_TCPF)) ||
+		    ((opts2 & RTASE_RX_UDPT) && !(opts2 & RTASE_RX_UDPF)))
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		else
+			skb->ip_summed = CHECKSUM_NONE;
+	} else {
+		skb->ip_summed = CHECKSUM_NONE;
+	}
+}
+
+static void rtase_rx_vlan_skb(union rtase_rx_desc *desc, struct sk_buff *skb)
+{
+	u32 opts2 = le32_to_cpu(desc->desc_status.opts2);
+
+	if (!(opts2 & RTASE_RX_VLAN_TAG))
+		return;
+
+	__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+			       swab16(opts2 & RTASE_VLAN_TAG_MASK));
+}
+
+static void rtase_rx_skb(const struct rtase_ring *ring, struct sk_buff *skb)
+{
+	struct rtase_int_vector *ivec = ring->ivec;
+
+	napi_gro_receive(&ivec->napi, skb);
+}
+
+static int rx_handler(struct rtase_ring *ring, int budget)
+{
+	union rtase_rx_desc *desc_base = ring->desc;
+	u32 pkt_size, cur_rx, delta, entry, status;
+	struct rtase_private *tp = ring->ivec->tp;
+	struct net_device *dev = tp->dev;
+	union rtase_rx_desc *desc;
+	struct sk_buff *skb;
+	int workdone = 0;
+
+	cur_rx = ring->cur_idx;
+	entry = cur_rx % RTASE_NUM_DESC;
+	desc = &desc_base[entry];
+
+	while (workdone < budget) {
+		status = le32_to_cpu(desc->desc_status.opts1);
+
+		if (status & RTASE_DESC_OWN)
+			break;
+
+		/* This barrier is needed to keep us from reading
+		 * any other fields out of the rx descriptor until
+		 * we know the status of RTASE_DESC_OWN
+		 */
+		dma_rmb();
+
+		if (unlikely(status & RTASE_RX_RES)) {
+			if (net_ratelimit())
+				netdev_warn(dev, "Rx ERROR. status = %08x\n",
+					    status);
+
+			tp->stats.rx_errors++;
+
+			if (status & (RTASE_RX_RWT | RTASE_RX_RUNT))
+				tp->stats.rx_length_errors++;
+
+			if (status & RTASE_RX_CRC)
+				tp->stats.rx_crc_errors++;
+
+			if (dev->features & NETIF_F_RXALL)
+				goto process_pkt;
+
+			rtase_mark_to_asic(desc, tp->rx_buf_sz);
+			goto skip_process_pkt;
+		}
+
+process_pkt:
+		pkt_size = status & RTASE_RX_PKT_SIZE_MASK;
+		if (likely(!(dev->features & NETIF_F_RXFCS)))
+			pkt_size -= ETH_FCS_LEN;
+
+		/* The driver does not support incoming fragmented frames.
+		 * They are seen as a symptom of over-mtu sized frames.
+		 */
+		if (unlikely(rtase_fragmented_frame(status))) {
+			tp->stats.rx_dropped++;
+			tp->stats.rx_length_errors++;
+			rtase_mark_to_asic(desc, tp->rx_buf_sz);
+			goto skip_process_pkt;
+		}
+
+		dma_sync_single_for_cpu(&tp->pdev->dev,
+					ring->mis.data_phy_addr[entry],
+					tp->rx_buf_sz, DMA_FROM_DEVICE);
+
+		skb = build_skb(ring->data_buf[entry], PAGE_SIZE);
+		if (!skb) {
+			tp->stats.rx_dropped++;
+			rtase_mark_to_asic(desc, tp->rx_buf_sz);
+			goto skip_process_pkt;
+		}
+		ring->data_buf[entry] = NULL;
+
+		if (dev->features & NETIF_F_RXCSUM)
+			rtase_rx_csum(tp, skb, desc);
+
+		skb_put(skb, pkt_size);
+		skb_mark_for_recycle(skb);
+		skb->protocol = eth_type_trans(skb, dev);
+
+		if (skb->pkt_type == PACKET_MULTICAST)
+			tp->stats.multicast++;
+
+		rtase_rx_vlan_skb(desc, skb);
+		rtase_rx_skb(ring, skb);
+
+		dev_sw_netstats_rx_add(dev, pkt_size);
+
+skip_process_pkt:
+		workdone++;
+		cur_rx++;
+		entry = cur_rx % RTASE_NUM_DESC;
+		desc = ring->desc + sizeof(union rtase_rx_desc) * entry;
+	}
+
+	ring->cur_idx = cur_rx;
+	delta = rtase_rx_ring_fill(ring, ring->dirty_idx, ring->cur_idx);
+	ring->dirty_idx += delta;
+
+	return workdone;
+}
+
 static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx)
 {
 	struct rtase_ring *ring = &tp->rx_ring[idx];
-- 
cgit v1.3-3-g829e


From 0796004899601249e26c3fa474e7c248e4d2568f Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:09 +0800
Subject: rtase: Implement net_device_ops

1. Implement .ndo_set_rx_mode so that the device can change address
list filtering.
2. Implement .ndo_set_mac_address so that mac address can be changed.
3. Implement .ndo_change_mtu so that mtu can be changed.
4. Implement .ndo_tx_timeout to perform related processing when the
transmitter does not make any progress.
5. Implement .ndo_get_stats64 to provide statistics that are called
when the user wants to get network device usage.
6. Implement .ndo_vlan_rx_add_vid to register VLAN ID when the device
supports VLAN filtering.
7. Implement .ndo_vlan_rx_kill_vid to unregister VLAN ID when the device
supports VLAN filtering.
8. Implement the .ndo_setup_tc to enable setting any "tc" scheduler,
classifier or action on dev.
9. Implement .ndo_fix_features enables adjusting requested feature flags
based on device-specific constraints.
10. Implement .ndo_set_features enables updating device configuration to
new features.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-9-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 235 ++++++++++++++++++++++++
 1 file changed, 235 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 361e9f2a02b8..ea569a2d8b8b 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1417,6 +1417,11 @@ err_dma_0:
 	return NETDEV_TX_OK;
 }
 
+static void rtase_set_rx_mode(struct net_device *dev)
+{
+	rtase_hw_set_rx_packet_filter(dev);
+}
+
 static void rtase_enable_eem_write(const struct rtase_private *tp)
 {
 	u8 val;
@@ -1449,10 +1454,240 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr)
 	rtase_w16(tp, RTASE_LBK_CTRL, RTASE_LBK_ATLD | RTASE_LBK_CLR);
 }
 
+static int rtase_set_mac_address(struct net_device *dev, void *p)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	int ret;
+
+	ret = eth_mac_addr(dev, p);
+	if (ret)
+		return ret;
+
+	rtase_rar_set(tp, dev->dev_addr);
+
+	return 0;
+}
+
+static int rtase_change_mtu(struct net_device *dev, int new_mtu)
+{
+	dev->mtu = new_mtu;
+
+	netdev_update_features(dev);
+
+	return 0;
+}
+
+static void rtase_wait_for_quiescence(const struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_int_vector *ivec;
+	u32 i;
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		synchronize_irq(ivec->irq);
+		/* wait for any pending NAPI task to complete */
+		napi_disable(&ivec->napi);
+	}
+
+	rtase_irq_dis_and_clear(tp);
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		napi_enable(&ivec->napi);
+	}
+}
+
+static void rtase_sw_reset(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	int ret;
+
+	netif_stop_queue(dev);
+	netif_carrier_off(dev);
+	rtase_hw_reset(dev);
+
+	/* let's wait a bit while any (async) irq lands on */
+	rtase_wait_for_quiescence(dev);
+	rtase_tx_clear(tp);
+	rtase_rx_clear(tp);
+
+	ret = rtase_init_ring(dev);
+	if (ret) {
+		netdev_err(dev, "unable to init ring\n");
+		rtase_free_desc(tp);
+		return;
+	}
+
+	rtase_hw_config(dev);
+	/* always link, so start to transmit & receive */
+	rtase_hw_start(dev);
+
+	netif_carrier_on(dev);
+	netif_wake_queue(dev);
+}
+
+static void rtase_dump_tally_counter(const struct rtase_private *tp)
+{
+	dma_addr_t paddr = tp->tally_paddr;
+	u32 cmd = lower_32_bits(paddr);
+	u32 val;
+	int err;
+
+	rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(paddr));
+	rtase_w32(tp, RTASE_DTCCR0, cmd);
+	rtase_w32(tp, RTASE_DTCCR0, cmd | RTASE_COUNTER_DUMP);
+
+	err = read_poll_timeout(rtase_r32, val, !(val & RTASE_COUNTER_DUMP),
+				10, 250, false, tp, RTASE_DTCCR0);
+
+	if (err == -ETIMEDOUT)
+		netdev_err(tp->dev, "error occurred in dump tally counter\n");
+}
+
+static void rtase_dump_state(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	int max_reg_size = RTASE_PCI_REGS_SIZE;
+	const struct rtase_counters *counters;
+	const struct rtase_ring *ring;
+	u32 dword_rd;
+	int n = 0;
+
+	ring = &tp->tx_ring[0];
+	netdev_err(dev, "Tx descriptor info:\n");
+	netdev_err(dev, "Tx curIdx = 0x%x\n", ring->cur_idx);
+	netdev_err(dev, "Tx dirtyIdx = 0x%x\n", ring->dirty_idx);
+	netdev_err(dev, "Tx phyAddr = %pad\n", &ring->phy_addr);
+
+	ring = &tp->rx_ring[0];
+	netdev_err(dev, "Rx descriptor info:\n");
+	netdev_err(dev, "Rx curIdx = 0x%x\n", ring->cur_idx);
+	netdev_err(dev, "Rx dirtyIdx = 0x%x\n", ring->dirty_idx);
+	netdev_err(dev, "Rx phyAddr = %pad\n", &ring->phy_addr);
+
+	netdev_err(dev, "Device Registers:\n");
+	netdev_err(dev, "Chip Command = 0x%02x\n",
+		   rtase_r8(tp, RTASE_CHIP_CMD));
+	netdev_err(dev, "IMR = %08x\n", rtase_r32(tp, RTASE_IMR0));
+	netdev_err(dev, "ISR = %08x\n", rtase_r32(tp, RTASE_ISR0));
+	netdev_err(dev, "Boot Ctrl Reg(0xE004) = %04x\n",
+		   rtase_r16(tp, RTASE_BOOT_CTL));
+	netdev_err(dev, "EPHY ISR(0xE014) = %04x\n",
+		   rtase_r16(tp, RTASE_EPHY_ISR));
+	netdev_err(dev, "EPHY IMR(0xE016) = %04x\n",
+		   rtase_r16(tp, RTASE_EPHY_IMR));
+	netdev_err(dev, "CLKSW SET REG(0xE018) = %04x\n",
+		   rtase_r16(tp, RTASE_CLKSW_SET));
+
+	netdev_err(dev, "Dump PCI Registers:\n");
+
+	while (n < max_reg_size) {
+		if ((n % RTASE_DWORD_MOD) == 0)
+			netdev_err(tp->dev, "0x%03x:\n", n);
+
+		pci_read_config_dword(tp->pdev, n, &dword_rd);
+		netdev_err(tp->dev, "%08x\n", dword_rd);
+		n += 4;
+	}
+
+	netdev_err(dev, "Dump tally counter:\n");
+	counters = tp->tally_vaddr;
+	rtase_dump_tally_counter(tp);
+
+	netdev_err(dev, "tx_packets %lld\n",
+		   le64_to_cpu(counters->tx_packets));
+	netdev_err(dev, "rx_packets %lld\n",
+		   le64_to_cpu(counters->rx_packets));
+	netdev_err(dev, "tx_errors %lld\n",
+		   le64_to_cpu(counters->tx_errors));
+	netdev_err(dev, "rx_errors %d\n",
+		   le32_to_cpu(counters->rx_errors));
+	netdev_err(dev, "rx_missed %d\n",
+		   le16_to_cpu(counters->rx_missed));
+	netdev_err(dev, "align_errors %d\n",
+		   le16_to_cpu(counters->align_errors));
+	netdev_err(dev, "tx_one_collision %d\n",
+		   le32_to_cpu(counters->tx_one_collision));
+	netdev_err(dev, "tx_multi_collision %d\n",
+		   le32_to_cpu(counters->tx_multi_collision));
+	netdev_err(dev, "rx_unicast %lld\n",
+		   le64_to_cpu(counters->rx_unicast));
+	netdev_err(dev, "rx_broadcast %lld\n",
+		   le64_to_cpu(counters->rx_broadcast));
+	netdev_err(dev, "rx_multicast %d\n",
+		   le32_to_cpu(counters->rx_multicast));
+	netdev_err(dev, "tx_aborted %d\n",
+		   le16_to_cpu(counters->tx_aborted));
+	netdev_err(dev, "tx_underun %d\n",
+		   le16_to_cpu(counters->tx_underun));
+}
+
+static void rtase_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	rtase_dump_state(dev);
+	rtase_sw_reset(dev);
+}
+
+static void rtase_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *stats)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	const struct rtase_counters *counters;
+
+	counters = tp->tally_vaddr;
+
+	dev_fetch_sw_netstats(stats, dev->tstats);
+
+	/* fetch additional counter values missing in stats collected by driver
+	 * from tally counter
+	 */
+	rtase_dump_tally_counter(tp);
+	stats->rx_errors = tp->stats.rx_errors;
+	stats->tx_errors = le64_to_cpu(counters->tx_errors);
+	stats->rx_dropped = tp->stats.rx_dropped;
+	stats->tx_dropped = tp->stats.tx_dropped;
+	stats->multicast = tp->stats.multicast;
+	stats->rx_length_errors = tp->stats.rx_length_errors;
+}
+
+static netdev_features_t rtase_fix_features(struct net_device *dev,
+					    netdev_features_t features)
+{
+	netdev_features_t features_fix = features;
+
+	/* not support TSO for jumbo frames */
+	if (dev->mtu > ETH_DATA_LEN)
+		features_fix &= ~NETIF_F_ALL_TSO;
+
+	return features_fix;
+}
+
+static int rtase_set_features(struct net_device *dev,
+			      netdev_features_t features)
+{
+	netdev_features_t features_set = features;
+
+	features_set &= NETIF_F_RXALL | NETIF_F_RXCSUM |
+			NETIF_F_HW_VLAN_CTAG_RX;
+
+	if (features_set ^ dev->features)
+		rtase_hw_set_features(dev, features_set);
+
+	return 0;
+}
+
 static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_open = rtase_open,
 	.ndo_stop = rtase_close,
 	.ndo_start_xmit = rtase_start_xmit,
+	.ndo_set_rx_mode = rtase_set_rx_mode,
+	.ndo_set_mac_address = rtase_set_mac_address,
+	.ndo_change_mtu = rtase_change_mtu,
+	.ndo_tx_timeout = rtase_tx_timeout,
+	.ndo_get_stats64 = rtase_get_stats64,
+	.ndo_fix_features = rtase_fix_features,
+	.ndo_set_features = rtase_set_features,
 };
 
 static void rtase_get_mac_address(struct net_device *dev)
-- 
cgit v1.3-3-g829e


From a25a0b070c5160b44707fa1dfbf32d3d84e4224f Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:10 +0800
Subject: rtase: Implement pci_driver suspend and resume function

Implement the pci_driver suspend function to enable the device
to sleep, and implement the resume function to enable the device
to resume operation.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-10-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 51 +++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index ea569a2d8b8b..7a31bef0576a 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -2151,12 +2151,63 @@ static void rtase_shutdown(struct pci_dev *pdev)
 	rtase_reset_interrupt(pdev, tp);
 }
 
+static int rtase_suspend(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+
+	if (netif_running(dev)) {
+		netif_device_detach(dev);
+		rtase_hw_reset(dev);
+	}
+
+	return 0;
+}
+
+static int rtase_resume(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+	struct rtase_private *tp = netdev_priv(dev);
+	int ret;
+
+	/* restore last modified mac address */
+	rtase_rar_set(tp, dev->dev_addr);
+
+	if (!netif_running(dev))
+		goto out;
+
+	rtase_wait_for_quiescence(dev);
+
+	rtase_tx_clear(tp);
+	rtase_rx_clear(tp);
+
+	ret = rtase_init_ring(dev);
+	if (ret) {
+		netdev_err(dev, "unable to init ring\n");
+		rtase_free_desc(tp);
+		return -ENOMEM;
+	}
+
+	rtase_hw_config(dev);
+	/* always link, so start to transmit & receive */
+	rtase_hw_start(dev);
+
+	netif_device_attach(dev);
+out:
+
+	return 0;
+}
+
+static const struct dev_pm_ops rtase_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(rtase_suspend, rtase_resume)
+};
+
 static struct pci_driver rtase_pci_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = rtase_pci_tbl,
 	.probe = rtase_init_one,
 	.remove = rtase_remove_one,
 	.shutdown = rtase_shutdown,
+	.driver.pm = pm_ptr(&rtase_pm_ops),
 };
 
 module_pci_driver(rtase_pci_driver);
-- 
cgit v1.3-3-g829e


From dd7f17c40fd1cec1db2b8e693832a5ce852433ba Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:11 +0800
Subject: rtase: Implement ethtool function

Implement the ethtool function to support users to obtain network card
information, including obtaining various device settings, Report whether
physical link is up, Report pause parameters, Set pause parameters,
Return extended statistics about the device.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-11-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 74 +++++++++++++++++++++++++
 1 file changed, 74 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 7a31bef0576a..7882f2c0e1a4 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1710,9 +1710,83 @@ static void rtase_get_mac_address(struct net_device *dev)
 	rtase_rar_set(tp, dev->dev_addr);
 }
 
+static int rtase_get_settings(struct net_device *dev,
+			      struct ethtool_link_ksettings *cmd)
+{
+	u32 supported = SUPPORTED_MII | SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+
+	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
+						supported);
+	cmd->base.speed = SPEED_5000;
+	cmd->base.duplex = DUPLEX_FULL;
+	cmd->base.port = PORT_MII;
+	cmd->base.autoneg = AUTONEG_DISABLE;
+
+	return 0;
+}
+
+static void rtase_get_pauseparam(struct net_device *dev,
+				 struct ethtool_pauseparam *pause)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 value = rtase_r16(tp, RTASE_CPLUS_CMD);
+
+	pause->autoneg = AUTONEG_DISABLE;
+	pause->tx_pause = !!(value & RTASE_FORCE_TXFLOW_EN);
+	pause->rx_pause = !!(value & RTASE_FORCE_RXFLOW_EN);
+}
+
+static int rtase_set_pauseparam(struct net_device *dev,
+				struct ethtool_pauseparam *pause)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 value = rtase_r16(tp, RTASE_CPLUS_CMD);
+
+	if (pause->autoneg)
+		return -EOPNOTSUPP;
+
+	value &= ~(RTASE_FORCE_TXFLOW_EN | RTASE_FORCE_RXFLOW_EN);
+
+	if (pause->tx_pause)
+		value |= RTASE_FORCE_TXFLOW_EN;
+
+	if (pause->rx_pause)
+		value |= RTASE_FORCE_RXFLOW_EN;
+
+	rtase_w16(tp, RTASE_CPLUS_CMD, value);
+	return 0;
+}
+
+static void rtase_get_eth_mac_stats(struct net_device *dev,
+				    struct ethtool_eth_mac_stats *stats)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	const struct rtase_counters *counters;
+
+	counters = tp->tally_vaddr;
+
+	rtase_dump_tally_counter(tp);
+
+	stats->FramesTransmittedOK = le64_to_cpu(counters->tx_packets);
+	stats->FramesReceivedOK = le64_to_cpu(counters->rx_packets);
+	stats->FramesLostDueToIntMACXmitError =
+		le64_to_cpu(counters->tx_errors);
+	stats->BroadcastFramesReceivedOK = le64_to_cpu(counters->rx_broadcast);
+}
+
+static const struct ethtool_ops rtase_ethtool_ops = {
+	.get_link = ethtool_op_get_link,
+	.get_link_ksettings = rtase_get_settings,
+	.get_pauseparam = rtase_get_pauseparam,
+	.set_pauseparam = rtase_set_pauseparam,
+	.get_eth_mac_stats = rtase_get_eth_mac_stats,
+	.get_ts_info = ethtool_op_get_ts_info,
+};
+
 static void rtase_init_netdev_ops(struct net_device *dev)
 {
 	dev->netdev_ops = &rtase_netdev_ops;
+	dev->ethtool_ops = &rtase_ethtool_ops;
 }
 
 static void rtase_reset_interrupt(struct pci_dev *pdev,
-- 
cgit v1.3-3-g829e


From 14cb81d1359e2bf4e0a48ed74f66d12f06a21a8f Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:12 +0800
Subject: rtase: Add a Makefile in the rtase folder

Add a Makefile in the rtase folder to build rtase driver.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-12-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/Makefile | 10 ++++++++++
 1 file changed, 10 insertions(+)
 create mode 100644 drivers/net/ethernet/realtek/rtase/Makefile

diff --git a/drivers/net/ethernet/realtek/rtase/Makefile b/drivers/net/ethernet/realtek/rtase/Makefile
new file mode 100644
index 000000000000..ba3d8550f9e6
--- /dev/null
+++ b/drivers/net/ethernet/realtek/rtase/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+# Copyright(c) 2024 Realtek Semiconductor Corp. All rights reserved.
+
+#
+# Makefile for the Realtek PCIe driver
+#
+
+obj-$(CONFIG_RTASE) += rtase.o
+
+rtase-objs := rtase_main.o
-- 
cgit v1.3-3-g829e


From ad61903add56561b72b49d717c01563cf1535781 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:13 +0800
Subject: realtek: Update the Makefile and Kconfig in the realtek folder

1. Add the RTASE entry in the Kconfig.
2. Add the CONFIG_RTASE entry in the Makefile.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-13-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/Kconfig  | 19 +++++++++++++++++++
 drivers/net/ethernet/realtek/Makefile |  1 +
 2 files changed, 20 insertions(+)

diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 03015b665f4e..8a8ea51c639e 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -120,4 +120,23 @@ config R8169_LEDS
 	  Optional support for controlling the NIC LED's with the netdev
 	  LED trigger.
 
+config RTASE
+	tristate "Realtek Automotive Switch 9054/9068/9072/9075/9068/9071 PCIe Interface support"
+	depends on PCI
+	select CRC32
+	select PAGE_POOL
+	help
+	  Say Y here and it will be compiled and linked with the kernel
+	  if you have a Realtek Ethernet adapter belonging to the
+	  following families:
+	  RTL9054 5GBit Ethernet
+	  RTL9068 5GBit Ethernet
+	  RTL9072 5GBit Ethernet
+	  RTL9075 5GBit Ethernet
+	  RTL9068 5GBit Ethernet
+	  RTL9071 5GBit Ethernet
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called rtase. This is recommended.
+
 endif # NET_VENDOR_REALTEK
diff --git a/drivers/net/ethernet/realtek/Makefile b/drivers/net/ethernet/realtek/Makefile
index 635491d8826e..046adf503ff4 100644
--- a/drivers/net/ethernet/realtek/Makefile
+++ b/drivers/net/ethernet/realtek/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_ATP) += atp.o
 r8169-y += r8169_main.o r8169_firmware.o r8169_phy_config.o
 r8169-$(CONFIG_R8169_LEDS) += r8169_leds.o
 obj-$(CONFIG_R8169) += r8169.o
+obj-$(CONFIG_RTASE) += rtase/
-- 
cgit v1.3-3-g829e


From b0613ba1cd9364a8ed4689cabd4b53bd0f865ae0 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Wed, 4 Sep 2024 11:21:14 +0800
Subject: MAINTAINERS: Add the rtase ethernet driver entry

Add myself and Larry Chiu as the maintainer for the rtase ethernet driver.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Link: https://patch.msgid.link/20240904032114.247117-14-justinlai0215@realtek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 312bf63b5a0d..ca1469d52076 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19906,6 +19906,13 @@ L:	linux-remoteproc@vger.kernel.org
 S:	Maintained
 F:	drivers/tty/rpmsg_tty.c
 
+RTASE ETHERNET DRIVER
+M:	Justin Lai <justinlai0215@realtek.com>
+M:	Larry Chiu <larry.chiu@realtek.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/realtek/rtase/
+
 RTL2830 MEDIA DRIVER
 L:	linux-media@vger.kernel.org
 S:	Orphan
-- 
cgit v1.3-3-g829e


From 6e65f5f55b7e9d6a335606bcfb0424844d43a7c5 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Wed, 4 Sep 2024 08:27:40 +0200
Subject: net: dsa: microchip: rename ksz8 series files

The first KSZ8 series implementation was done for a KSZ8795 device but
since several other KSZ8 devices have been added. Rename these files
to adhere to the ksz8 naming convention as already used in most
functions and the existing ksz8.h; add an explanatory note.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/Kconfig       |    9 +-
 drivers/net/dsa/microchip/Makefile      |    2 +-
 drivers/net/dsa/microchip/ksz8.c        | 1975 +++++++++++++++++++++++++++++++
 drivers/net/dsa/microchip/ksz8795.c     | 1968 ------------------------------
 drivers/net/dsa/microchip/ksz8795_reg.h |  798 -------------
 drivers/net/dsa/microchip/ksz8_reg.h    |  803 +++++++++++++
 6 files changed, 2785 insertions(+), 2770 deletions(-)
 create mode 100644 drivers/net/dsa/microchip/ksz8.c
 delete mode 100644 drivers/net/dsa/microchip/ksz8795.c
 delete mode 100644 drivers/net/dsa/microchip/ksz8795_reg.h
 create mode 100644 drivers/net/dsa/microchip/ksz8_reg.h

diff --git a/drivers/net/dsa/microchip/Kconfig b/drivers/net/dsa/microchip/Kconfig
index c1b906c05a02..12a86585a77f 100644
--- a/drivers/net/dsa/microchip/Kconfig
+++ b/drivers/net/dsa/microchip/Kconfig
@@ -1,14 +1,17 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menuconfig NET_DSA_MICROCHIP_KSZ_COMMON
-	tristate "Microchip KSZ8795/KSZ9477/LAN937x series switch support"
+	tristate "Microchip KSZ8XXX/KSZ9XXX/LAN937X series switch support"
 	depends on NET_DSA
 	select NET_DSA_TAG_KSZ
 	select NET_DSA_TAG_NONE
 	select NET_IEEE8021Q_HELPERS
 	select DCB
 	help
-	  This driver adds support for Microchip KSZ9477 series switch and
-	  KSZ8795/KSZ88x3 switch chips.
+	  This driver adds support for Microchip KSZ8, KSZ9 and
+	  LAN937X series switch chips, being KSZ8863/8873,
+	  KSZ8895/8864, KSZ8794/8795/8765,
+	  KSZ9477/9897/9896/9567/8567, KSZ9893/9563/8563 and
+	  LAN9370/9371/9372/9373/9374.
 
 config NET_DSA_MICROCHIP_KSZ9477_I2C
 	tristate "KSZ series I2C connected switch driver"
diff --git a/drivers/net/dsa/microchip/Makefile b/drivers/net/dsa/microchip/Makefile
index 1cfba1ec9355..9347cfb3d0b5 100644
--- a/drivers/net/dsa/microchip/Makefile
+++ b/drivers/net/dsa/microchip/Makefile
@@ -2,7 +2,7 @@
 obj-$(CONFIG_NET_DSA_MICROCHIP_KSZ_COMMON)	+= ksz_switch.o
 ksz_switch-objs := ksz_common.o ksz_dcb.o
 ksz_switch-objs += ksz9477.o ksz9477_acl.o ksz9477_tc_flower.o
-ksz_switch-objs += ksz8795.o
+ksz_switch-objs += ksz8.o
 ksz_switch-objs += lan937x_main.o
 
 ifdef CONFIG_NET_DSA_MICROCHIP_KSZ_PTP
diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
new file mode 100644
index 000000000000..7af3c0853505
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -0,0 +1,1975 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Microchip KSZ8XXX series switch driver
+ *
+ * It supports the following switches:
+ * - KSZ8863, KSZ8873 aka KSZ88X3
+ * - KSZ8895, KSZ8864 aka KSZ8895 family
+ * - KSZ8794, KSZ8795, KSZ8765 aka KSZ87XX
+ * Note that it does NOT support:
+ * - KSZ8563, KSZ8567 - see KSZ9477 driver
+ *
+ * Copyright (C) 2017 Microchip Technology Inc.
+ *	Tristram Ha <Tristram.Ha@microchip.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gpio.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_data/microchip-ksz.h>
+#include <linux/phy.h>
+#include <linux/etherdevice.h>
+#include <linux/if_bridge.h>
+#include <linux/micrel_phy.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+#include <linux/phylink.h>
+
+#include "ksz_common.h"
+#include "ksz8_reg.h"
+#include "ksz8.h"
+
+static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
+{
+	regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0);
+}
+
+static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
+			 bool set)
+{
+	regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset),
+			   bits, set ? bits : 0);
+}
+
+/**
+ * ksz8_ind_write8 - EEE/ACL/PME indirect register write
+ * @dev: The device structure.
+ * @table: Function & table select, register 110.
+ * @addr: Indirect access control, register 111.
+ * @data: The data to be written.
+ *
+ * This function performs an indirect register write for EEE, ACL or
+ * PME switch functionalities. Both 8-bit registers 110 and 111 are
+ * written at once with ksz_write16, using the serial multiple write
+ * functionality.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data)
+{
+	const u16 *regs;
+	u16 ctrl_addr;
+	int ret = 0;
+
+	regs = dev->info->regs;
+
+	mutex_lock(&dev->alu_mutex);
+
+	ctrl_addr = IND_ACC_TABLE(table) | addr;
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+	if (!ret)
+		ret = ksz_write8(dev, regs[REG_IND_BYTE], data);
+
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+/**
+ * ksz8_ind_read8 - EEE/ACL/PME indirect register read
+ * @dev: The device structure.
+ * @table: Function & table select, register 110.
+ * @addr: Indirect access control, register 111.
+ * @val: The value read.
+ *
+ * This function performs an indirect register read for EEE, ACL or
+ * PME switch functionalities. Both 8-bit registers 110 and 111 are
+ * written at once with ksz_write16, using the serial multiple write
+ * functionality.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
+static int ksz8_ind_read8(struct ksz_device *dev, u8 table, u16 addr, u8 *val)
+{
+	const u16 *regs;
+	u16 ctrl_addr;
+	int ret = 0;
+
+	regs = dev->info->regs;
+
+	mutex_lock(&dev->alu_mutex);
+
+	ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr;
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+	if (!ret)
+		ret = ksz_read8(dev, regs[REG_IND_BYTE], val);
+
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value)
+{
+	return ksz8_ind_write8(dev, (u8)(reg >> 8), (u8)(reg), value);
+}
+
+int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data)
+{
+	u8 table = (u8)(offset >> 8 | (port + 1));
+
+	return ksz8_ind_read8(dev, table, (u8)(offset), data);
+}
+
+int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data)
+{
+	u8 table = (u8)(offset >> 8 | (port + 1));
+
+	return ksz8_ind_write8(dev, table, (u8)(offset), data);
+}
+
+int ksz8_reset_switch(struct ksz_device *dev)
+{
+	if (ksz_is_ksz88x3(dev)) {
+		/* reset switch */
+		ksz_cfg(dev, KSZ8863_REG_SW_RESET,
+			KSZ8863_GLOBAL_SOFTWARE_RESET | KSZ8863_PCS_RESET, true);
+		ksz_cfg(dev, KSZ8863_REG_SW_RESET,
+			KSZ8863_GLOBAL_SOFTWARE_RESET | KSZ8863_PCS_RESET, false);
+	} else {
+		/* reset switch */
+		ksz_write8(dev, REG_POWER_MANAGEMENT_1,
+			   SW_SOFTWARE_POWER_DOWN << SW_POWER_MANAGEMENT_MODE_S);
+		ksz_write8(dev, REG_POWER_MANAGEMENT_1, 0);
+	}
+
+	return 0;
+}
+
+static int ksz8863_change_mtu(struct ksz_device *dev, int frame_size)
+{
+	u8 ctrl2 = 0;
+
+	if (frame_size <= KSZ8_LEGAL_PACKET_SIZE)
+		ctrl2 |= KSZ8863_LEGAL_PACKET_ENABLE;
+	else if (frame_size > KSZ8863_NORMAL_PACKET_SIZE)
+		ctrl2 |= KSZ8863_HUGE_PACKET_ENABLE;
+
+	return ksz_rmw8(dev, REG_SW_CTRL_2, KSZ8863_LEGAL_PACKET_ENABLE |
+			KSZ8863_HUGE_PACKET_ENABLE, ctrl2);
+}
+
+static int ksz8795_change_mtu(struct ksz_device *dev, int frame_size)
+{
+	u8 ctrl1 = 0, ctrl2 = 0;
+	int ret;
+
+	if (frame_size > KSZ8_LEGAL_PACKET_SIZE)
+		ctrl2 |= SW_LEGAL_PACKET_DISABLE;
+	if (frame_size > KSZ8863_NORMAL_PACKET_SIZE)
+		ctrl1 |= SW_HUGE_PACKET;
+
+	ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_HUGE_PACKET, ctrl1);
+	if (ret)
+		return ret;
+
+	return ksz_rmw8(dev, REG_SW_CTRL_2, SW_LEGAL_PACKET_DISABLE, ctrl2);
+}
+
+int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu)
+{
+	u16 frame_size;
+
+	if (!dsa_is_cpu_port(dev->ds, port))
+		return 0;
+
+	frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
+
+	switch (dev->chip_id) {
+	case KSZ8795_CHIP_ID:
+	case KSZ8794_CHIP_ID:
+	case KSZ8765_CHIP_ID:
+		return ksz8795_change_mtu(dev, frame_size);
+	case KSZ8830_CHIP_ID:
+	case KSZ8864_CHIP_ID:
+	case KSZ8895_CHIP_ID:
+		return ksz8863_change_mtu(dev, frame_size);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int ksz8_port_queue_split(struct ksz_device *dev, int port, int queues)
+{
+	u8 mask_4q, mask_2q;
+	u8 reg_4q, reg_2q;
+	u8 data_4q = 0;
+	u8 data_2q = 0;
+	int ret;
+
+	if (ksz_is_ksz88x3(dev)) {
+		mask_4q = KSZ8873_PORT_4QUEUE_SPLIT_EN;
+		mask_2q = KSZ8873_PORT_2QUEUE_SPLIT_EN;
+		reg_4q = REG_PORT_CTRL_0;
+		reg_2q = REG_PORT_CTRL_2;
+
+		/* KSZ8795 family switches have Weighted Fair Queueing (WFQ)
+		 * enabled by default. Enable it for KSZ8873 family switches
+		 * too. Default value for KSZ8873 family is strict priority,
+		 * which should be enabled by using TC_SETUP_QDISC_ETS, not
+		 * by default.
+		 */
+		ret = ksz_rmw8(dev, REG_SW_CTRL_3, WEIGHTED_FAIR_QUEUE_ENABLE,
+			       WEIGHTED_FAIR_QUEUE_ENABLE);
+		if (ret)
+			return ret;
+	} else {
+		mask_4q = KSZ8795_PORT_4QUEUE_SPLIT_EN;
+		mask_2q = KSZ8795_PORT_2QUEUE_SPLIT_EN;
+		reg_4q = REG_PORT_CTRL_13;
+		reg_2q = REG_PORT_CTRL_0;
+
+		/* TODO: this is legacy from initial KSZ8795 driver, should be
+		 * moved to appropriate place in the future.
+		 */
+		ret = ksz_rmw8(dev, REG_SW_CTRL_19,
+			       SW_OUT_RATE_LIMIT_QUEUE_BASED,
+			       SW_OUT_RATE_LIMIT_QUEUE_BASED);
+		if (ret)
+			return ret;
+	}
+
+	if (queues == 4)
+		data_4q = mask_4q;
+	else if (queues == 2)
+		data_2q = mask_2q;
+
+	ret = ksz_prmw8(dev, port, reg_4q, mask_4q, data_4q);
+	if (ret)
+		return ret;
+
+	return ksz_prmw8(dev, port, reg_2q, mask_2q, data_2q);
+}
+
+int ksz8_all_queues_split(struct ksz_device *dev, int queues)
+{
+	struct dsa_switch *ds = dev->ds;
+	const struct dsa_port *dp;
+
+	dsa_switch_for_each_port(dp, ds) {
+		int ret = ksz8_port_queue_split(dev, dp->index, queues);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+void ksz8_r_mib_cnt(struct ksz_device *dev, int port, u16 addr, u64 *cnt)
+{
+	const u32 *masks;
+	const u16 *regs;
+	u16 ctrl_addr;
+	u32 data;
+	u8 check;
+	int loop;
+
+	masks = dev->info->masks;
+	regs = dev->info->regs;
+
+	ctrl_addr = addr + dev->info->reg_mib_cnt * port;
+	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
+
+	mutex_lock(&dev->alu_mutex);
+	ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+
+	/* It is almost guaranteed to always read the valid bit because of
+	 * slow SPI speed.
+	 */
+	for (loop = 2; loop > 0; loop--) {
+		ksz_read8(dev, regs[REG_IND_MIB_CHECK], &check);
+
+		if (check & masks[MIB_COUNTER_VALID]) {
+			ksz_read32(dev, regs[REG_IND_DATA_LO], &data);
+			if (check & masks[MIB_COUNTER_OVERFLOW])
+				*cnt += MIB_COUNTER_VALUE + 1;
+			*cnt += data & MIB_COUNTER_VALUE;
+			break;
+		}
+	}
+	mutex_unlock(&dev->alu_mutex);
+}
+
+static void ksz8795_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
+			      u64 *dropped, u64 *cnt)
+{
+	const u32 *masks;
+	const u16 *regs;
+	u16 ctrl_addr;
+	u32 data;
+	u8 check;
+	int loop;
+
+	masks = dev->info->masks;
+	regs = dev->info->regs;
+
+	addr -= dev->info->reg_mib_cnt;
+	ctrl_addr = (KSZ8795_MIB_TOTAL_RX_1 - KSZ8795_MIB_TOTAL_RX_0) * port;
+	ctrl_addr += addr + KSZ8795_MIB_TOTAL_RX_0;
+	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
+
+	mutex_lock(&dev->alu_mutex);
+	ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+
+	/* It is almost guaranteed to always read the valid bit because of
+	 * slow SPI speed.
+	 */
+	for (loop = 2; loop > 0; loop--) {
+		ksz_read8(dev, regs[REG_IND_MIB_CHECK], &check);
+
+		if (check & masks[MIB_COUNTER_VALID]) {
+			ksz_read32(dev, regs[REG_IND_DATA_LO], &data);
+			if (addr < 2) {
+				u64 total;
+
+				total = check & MIB_TOTAL_BYTES_H;
+				total <<= 32;
+				*cnt += total;
+				*cnt += data;
+				if (check & masks[MIB_COUNTER_OVERFLOW]) {
+					total = MIB_TOTAL_BYTES_H + 1;
+					total <<= 32;
+					*cnt += total;
+				}
+			} else {
+				if (check & masks[MIB_COUNTER_OVERFLOW])
+					*cnt += MIB_PACKET_DROPPED + 1;
+				*cnt += data & MIB_PACKET_DROPPED;
+			}
+			break;
+		}
+	}
+	mutex_unlock(&dev->alu_mutex);
+}
+
+static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
+			      u64 *dropped, u64 *cnt)
+{
+	u32 *last = (u32 *)dropped;
+	const u16 *regs;
+	u16 ctrl_addr;
+	u32 data;
+	u32 cur;
+
+	regs = dev->info->regs;
+
+	addr -= dev->info->reg_mib_cnt;
+	ctrl_addr = addr ? KSZ8863_MIB_PACKET_DROPPED_TX_0 :
+			   KSZ8863_MIB_PACKET_DROPPED_RX_0;
+	ctrl_addr += port;
+	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
+
+	mutex_lock(&dev->alu_mutex);
+	ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+	ksz_read32(dev, regs[REG_IND_DATA_LO], &data);
+	mutex_unlock(&dev->alu_mutex);
+
+	data &= MIB_PACKET_DROPPED;
+	cur = last[addr];
+	if (data != cur) {
+		last[addr] = data;
+		if (data < cur)
+			data += MIB_PACKET_DROPPED + 1;
+		data -= cur;
+		*cnt += data;
+	}
+}
+
+void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
+		    u64 *dropped, u64 *cnt)
+{
+	if (is_ksz88xx(dev))
+		ksz8863_r_mib_pkt(dev, port, addr, dropped, cnt);
+	else
+		ksz8795_r_mib_pkt(dev, port, addr, dropped, cnt);
+}
+
+void ksz8_freeze_mib(struct ksz_device *dev, int port, bool freeze)
+{
+	if (is_ksz88xx(dev))
+		return;
+
+	/* enable the port for flush/freeze function */
+	if (freeze)
+		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true);
+	ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FREEZE, freeze);
+
+	/* disable the port after freeze is done */
+	if (!freeze)
+		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), false);
+}
+
+void ksz8_port_init_cnt(struct ksz_device *dev, int port)
+{
+	struct ksz_port_mib *mib = &dev->ports[port].mib;
+	u64 *dropped;
+
+	/* For KSZ8795 family. */
+	if (ksz_is_ksz87xx(dev)) {
+		/* flush all enabled port MIB counters */
+		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true);
+		ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FLUSH, true);
+		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), false);
+	}
+
+	mib->cnt_ptr = 0;
+
+	/* Some ports may not have MIB counters before SWITCH_COUNTER_NUM. */
+	while (mib->cnt_ptr < dev->info->reg_mib_cnt) {
+		dev->dev_ops->r_mib_cnt(dev, port, mib->cnt_ptr,
+					&mib->counters[mib->cnt_ptr]);
+		++mib->cnt_ptr;
+	}
+
+	/* last one in storage */
+	dropped = &mib->counters[dev->info->mib_cnt];
+
+	/* Some ports may not have MIB counters after SWITCH_COUNTER_NUM. */
+	while (mib->cnt_ptr < dev->info->mib_cnt) {
+		dev->dev_ops->r_mib_pkt(dev, port, mib->cnt_ptr,
+					dropped, &mib->counters[mib->cnt_ptr]);
+		++mib->cnt_ptr;
+	}
+}
+
+static int ksz8_r_table(struct ksz_device *dev, int table, u16 addr, u64 *data)
+{
+	const u16 *regs;
+	u16 ctrl_addr;
+	int ret;
+
+	regs = dev->info->regs;
+
+	ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr;
+
+	mutex_lock(&dev->alu_mutex);
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+	if (ret)
+		goto unlock_alu;
+
+	ret = ksz_read64(dev, regs[REG_IND_DATA_HI], data);
+unlock_alu:
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static int ksz8_w_table(struct ksz_device *dev, int table, u16 addr, u64 data)
+{
+	const u16 *regs;
+	u16 ctrl_addr;
+	int ret;
+
+	regs = dev->info->regs;
+
+	ctrl_addr = IND_ACC_TABLE(table) | addr;
+
+	mutex_lock(&dev->alu_mutex);
+	ret = ksz_write64(dev, regs[REG_IND_DATA_HI], data);
+	if (ret)
+		goto unlock_alu;
+
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+unlock_alu:
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static int ksz8_valid_dyn_entry(struct ksz_device *dev, u8 *data)
+{
+	int timeout = 100;
+	const u32 *masks;
+	const u16 *regs;
+	int ret;
+
+	masks = dev->info->masks;
+	regs = dev->info->regs;
+
+	do {
+		ret = ksz_read8(dev, regs[REG_IND_DATA_CHECK], data);
+		if (ret)
+			return ret;
+
+		timeout--;
+	} while ((*data & masks[DYNAMIC_MAC_TABLE_NOT_READY]) && timeout);
+
+	/* Entry is not ready for accessing. */
+	if (*data & masks[DYNAMIC_MAC_TABLE_NOT_READY])
+		return -ETIMEDOUT;
+
+	/* Entry is ready for accessing. */
+	return ksz_read8(dev, regs[REG_IND_DATA_8], data);
+}
+
+static int ksz8_r_dyn_mac_table(struct ksz_device *dev, u16 addr, u8 *mac_addr,
+				u8 *fid, u8 *src_port, u16 *entries)
+{
+	u32 data_hi, data_lo;
+	const u8 *shifts;
+	const u32 *masks;
+	const u16 *regs;
+	u16 ctrl_addr;
+	u64 buf = 0;
+	u8 data;
+	int cnt;
+	int ret;
+
+	shifts = dev->info->shifts;
+	masks = dev->info->masks;
+	regs = dev->info->regs;
+
+	ctrl_addr = IND_ACC_TABLE(TABLE_DYNAMIC_MAC | TABLE_READ) | addr;
+
+	mutex_lock(&dev->alu_mutex);
+	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
+	if (ret)
+		goto unlock_alu;
+
+	ret = ksz8_valid_dyn_entry(dev, &data);
+	if (ret)
+		goto unlock_alu;
+
+	if (data & masks[DYNAMIC_MAC_TABLE_MAC_EMPTY]) {
+		*entries = 0;
+		goto unlock_alu;
+	}
+
+	ret = ksz_read64(dev, regs[REG_IND_DATA_HI], &buf);
+	if (ret)
+		goto unlock_alu;
+
+	data_hi = (u32)(buf >> 32);
+	data_lo = (u32)buf;
+
+	/* Check out how many valid entry in the table. */
+	cnt = data & masks[DYNAMIC_MAC_TABLE_ENTRIES_H];
+	cnt <<= shifts[DYNAMIC_MAC_ENTRIES_H];
+	cnt |= (data_hi & masks[DYNAMIC_MAC_TABLE_ENTRIES]) >>
+		shifts[DYNAMIC_MAC_ENTRIES];
+	*entries = cnt + 1;
+
+	*fid = (data_hi & masks[DYNAMIC_MAC_TABLE_FID]) >>
+		shifts[DYNAMIC_MAC_FID];
+	*src_port = (data_hi & masks[DYNAMIC_MAC_TABLE_SRC_PORT]) >>
+		shifts[DYNAMIC_MAC_SRC_PORT];
+
+	mac_addr[5] = (u8)data_lo;
+	mac_addr[4] = (u8)(data_lo >> 8);
+	mac_addr[3] = (u8)(data_lo >> 16);
+	mac_addr[2] = (u8)(data_lo >> 24);
+
+	mac_addr[1] = (u8)data_hi;
+	mac_addr[0] = (u8)(data_hi >> 8);
+
+unlock_alu:
+	mutex_unlock(&dev->alu_mutex);
+
+	return ret;
+}
+
+static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr,
+				struct alu_struct *alu, bool *valid)
+{
+	u32 data_hi, data_lo;
+	const u8 *shifts;
+	const u32 *masks;
+	u64 data;
+	int ret;
+
+	shifts = dev->info->shifts;
+	masks = dev->info->masks;
+
+	ret = ksz8_r_table(dev, TABLE_STATIC_MAC, addr, &data);
+	if (ret)
+		return ret;
+
+	data_hi = data >> 32;
+	data_lo = (u32)data;
+
+	if (!(data_hi & (masks[STATIC_MAC_TABLE_VALID] |
+			 masks[STATIC_MAC_TABLE_OVERRIDE]))) {
+		*valid = false;
+		return 0;
+	}
+
+	alu->mac[5] = (u8)data_lo;
+	alu->mac[4] = (u8)(data_lo >> 8);
+	alu->mac[3] = (u8)(data_lo >> 16);
+	alu->mac[2] = (u8)(data_lo >> 24);
+	alu->mac[1] = (u8)data_hi;
+	alu->mac[0] = (u8)(data_hi >> 8);
+	alu->port_forward =
+		(data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >>
+			shifts[STATIC_MAC_FWD_PORTS];
+	alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0;
+
+	/* KSZ8795/KSZ8895 family switches have STATIC_MAC_TABLE_USE_FID and
+	 * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the
+	 * static MAC table compared to doing write.
+	 */
+	if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev))
+		data_hi >>= 1;
+	alu->is_static = true;
+	alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0;
+	alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >>
+		shifts[STATIC_MAC_FID];
+
+	*valid = true;
+
+	return 0;
+}
+
+static int ksz8_w_sta_mac_table(struct ksz_device *dev, u16 addr,
+				struct alu_struct *alu)
+{
+	u32 data_hi, data_lo;
+	const u8 *shifts;
+	const u32 *masks;
+	u64 data;
+
+	shifts = dev->info->shifts;
+	masks = dev->info->masks;
+
+	data_lo = ((u32)alu->mac[2] << 24) |
+		((u32)alu->mac[3] << 16) |
+		((u32)alu->mac[4] << 8) | alu->mac[5];
+	data_hi = ((u32)alu->mac[0] << 8) | alu->mac[1];
+	data_hi |= (u32)alu->port_forward << shifts[STATIC_MAC_FWD_PORTS];
+
+	if (alu->is_override)
+		data_hi |= masks[STATIC_MAC_TABLE_OVERRIDE];
+	if (alu->is_use_fid) {
+		data_hi |= masks[STATIC_MAC_TABLE_USE_FID];
+		data_hi |= (u32)alu->fid << shifts[STATIC_MAC_FID];
+	}
+	if (alu->is_static)
+		data_hi |= masks[STATIC_MAC_TABLE_VALID];
+	else
+		data_hi &= ~masks[STATIC_MAC_TABLE_OVERRIDE];
+
+	data = (u64)data_hi << 32 | data_lo;
+
+	return ksz8_w_table(dev, TABLE_STATIC_MAC, addr, data);
+}
+
+static void ksz8_from_vlan(struct ksz_device *dev, u32 vlan, u8 *fid,
+			   u8 *member, u8 *valid)
+{
+	const u8 *shifts;
+	const u32 *masks;
+
+	shifts = dev->info->shifts;
+	masks = dev->info->masks;
+
+	*fid = vlan & masks[VLAN_TABLE_FID];
+	*member = (vlan & masks[VLAN_TABLE_MEMBERSHIP]) >>
+			shifts[VLAN_TABLE_MEMBERSHIP_S];
+	*valid = !!(vlan & masks[VLAN_TABLE_VALID]);
+}
+
+static void ksz8_to_vlan(struct ksz_device *dev, u8 fid, u8 member, u8 valid,
+			 u16 *vlan)
+{
+	const u8 *shifts;
+	const u32 *masks;
+
+	shifts = dev->info->shifts;
+	masks = dev->info->masks;
+
+	*vlan = fid;
+	*vlan |= (u16)member << shifts[VLAN_TABLE_MEMBERSHIP_S];
+	if (valid)
+		*vlan |= masks[VLAN_TABLE_VALID];
+}
+
+static void ksz8_r_vlan_entries(struct ksz_device *dev, u16 addr)
+{
+	const u8 *shifts;
+	u64 data;
+	int i;
+
+	shifts = dev->info->shifts;
+
+	ksz8_r_table(dev, TABLE_VLAN, addr, &data);
+	addr *= 4;
+	for (i = 0; i < 4; i++) {
+		dev->vlan_cache[addr + i].table[0] = (u16)data;
+		data >>= shifts[VLAN_TABLE];
+	}
+}
+
+static void ksz8_r_vlan_table(struct ksz_device *dev, u16 vid, u16 *vlan)
+{
+	int index;
+	u16 *data;
+	u16 addr;
+	u64 buf;
+
+	data = (u16 *)&buf;
+	addr = vid / 4;
+	index = vid & 3;
+	ksz8_r_table(dev, TABLE_VLAN, addr, &buf);
+	*vlan = data[index];
+}
+
+static void ksz8_w_vlan_table(struct ksz_device *dev, u16 vid, u16 vlan)
+{
+	int index;
+	u16 *data;
+	u16 addr;
+	u64 buf;
+
+	data = (u16 *)&buf;
+	addr = vid / 4;
+	index = vid & 3;
+	ksz8_r_table(dev, TABLE_VLAN, addr, &buf);
+	data[index] = vlan;
+	dev->vlan_cache[vid].table[0] = vlan;
+	ksz8_w_table(dev, TABLE_VLAN, addr, buf);
+}
+
+/**
+ * ksz879x_get_loopback - KSZ879x specific function to get loopback
+ *                        configuration status for a specific port
+ * @dev: Pointer to the device structure
+ * @port: Port number to query
+ * @val: Pointer to store the result
+ *
+ * This function reads the SMI registers to determine whether loopback mode
+ * is enabled for a specific port.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+static int ksz879x_get_loopback(struct ksz_device *dev, u16 port,
+				u16 *val)
+{
+	u8 stat3;
+	int ret;
+
+	ret = ksz_pread8(dev, port, REG_PORT_STATUS_3, &stat3);
+	if (ret)
+		return ret;
+
+	if (stat3 & PORT_PHY_LOOPBACK)
+		*val |= BMCR_LOOPBACK;
+
+	return 0;
+}
+
+/**
+ * ksz879x_set_loopback - KSZ879x specific function  to set loopback mode for
+ *			  a specific port
+ * @dev: Pointer to the device structure.
+ * @port: Port number to modify.
+ * @val: Value indicating whether to enable or disable loopback mode.
+ *
+ * This function translates loopback bit of the BMCR register into the
+ * corresponding hardware register bit value and writes it to the SMI interface.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+static int ksz879x_set_loopback(struct ksz_device *dev, u16 port, u16 val)
+{
+	u8 stat3 = 0;
+
+	if (val & BMCR_LOOPBACK)
+		stat3 |= PORT_PHY_LOOPBACK;
+
+	return ksz_prmw8(dev, port, REG_PORT_STATUS_3, PORT_PHY_LOOPBACK,
+			 stat3);
+}
+
+/**
+ * ksz8_r_phy_ctrl - Translates and reads from the SMI interface to a MIIM PHY
+ *		     Control register (Reg. 31).
+ * @dev: The KSZ device instance.
+ * @port: The port number to be read.
+ * @val: The value read from the SMI interface.
+ *
+ * This function reads the SMI interface and translates the hardware register
+ * bit values into their corresponding control settings for a MIIM PHY Control
+ * register.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+static int ksz8_r_phy_ctrl(struct ksz_device *dev, int port, u16 *val)
+{
+	const u16 *regs = dev->info->regs;
+	u8 reg_val;
+	int ret;
+
+	*val = 0;
+
+	ret = ksz_pread8(dev, port, regs[P_LINK_STATUS], &reg_val);
+	if (ret < 0)
+		return ret;
+
+	if (reg_val & PORT_MDIX_STATUS)
+		*val |= KSZ886X_CTRL_MDIX_STAT;
+
+	ret = ksz_pread8(dev, port, REG_PORT_LINK_MD_CTRL, &reg_val);
+	if (ret < 0)
+		return ret;
+
+	if (reg_val & PORT_FORCE_LINK)
+		*val |= KSZ886X_CTRL_FORCE_LINK;
+
+	if (reg_val & PORT_POWER_SAVING)
+		*val |= KSZ886X_CTRL_PWRSAVE;
+
+	if (reg_val & PORT_PHY_REMOTE_LOOPBACK)
+		*val |= KSZ886X_CTRL_REMOTE_LOOPBACK;
+
+	return 0;
+}
+
+/**
+ * ksz8_r_phy_bmcr - Translates and reads from the SMI interface to a MIIM PHY
+ *		     Basic mode control register (Reg. 0).
+ * @dev: The KSZ device instance.
+ * @port: The port number to be read.
+ * @val: The value read from the SMI interface.
+ *
+ * This function reads the SMI interface and translates the hardware register
+ * bit values into their corresponding control settings for a MIIM PHY Basic
+ * mode control register.
+ *
+ * MIIM Bit Mapping Comparison between KSZ8794 and KSZ8873
+ * -------------------------------------------------------------------
+ * MIIM Bit                    | KSZ8794 Reg/Bit             | KSZ8873 Reg/Bit
+ * ----------------------------+-----------------------------+----------------
+ * Bit 15 - Soft Reset         | 0xF/4                       | Not supported
+ * Bit 14 - Loopback           | 0xD/0 (MAC), 0xF/7 (PHY)    ~ 0xD/0 (PHY)
+ * Bit 13 - Force 100          | 0xC/6                       = 0xC/6
+ * Bit 12 - AN Enable          | 0xC/7 (reverse logic)       ~ 0xC/7
+ * Bit 11 - Power Down         | 0xD/3                       = 0xD/3
+ * Bit 10 - PHY Isolate        | 0xF/5                       | Not supported
+ * Bit 9 - Restart AN          | 0xD/5                       = 0xD/5
+ * Bit 8 - Force Full-Duplex   | 0xC/5                       = 0xC/5
+ * Bit 7 - Collision Test/Res. | Not supported               | Not supported
+ * Bit 6 - Reserved            | Not supported               | Not supported
+ * Bit 5 - Hp_mdix             | 0x9/7                       ~ 0xF/7
+ * Bit 4 - Force MDI           | 0xD/1                       = 0xD/1
+ * Bit 3 - Disable MDIX        | 0xD/2                       = 0xD/2
+ * Bit 2 - Disable Far-End F.  | ????                        | 0xD/4
+ * Bit 1 - Disable Transmit    | 0xD/6                       = 0xD/6
+ * Bit 0 - Disable LED         | 0xD/7                       = 0xD/7
+ * -------------------------------------------------------------------
+ *
+ * Return: 0 on success, error code on failure.
+ */
+static int ksz8_r_phy_bmcr(struct ksz_device *dev, u16 port, u16 *val)
+{
+	const u16 *regs = dev->info->regs;
+	u8 restart, speed, ctrl;
+	int ret;
+
+	*val = 0;
+
+	ret = ksz_pread8(dev, port, regs[P_NEG_RESTART_CTRL], &restart);
+	if (ret)
+		return ret;
+
+	ret = ksz_pread8(dev, port, regs[P_SPEED_STATUS], &speed);
+	if (ret)
+		return ret;
+
+	ret = ksz_pread8(dev, port, regs[P_FORCE_CTRL], &ctrl);
+	if (ret)
+		return ret;
+
+	if (ctrl & PORT_FORCE_100_MBIT)
+		*val |= BMCR_SPEED100;
+
+	if (ksz_is_ksz88x3(dev)) {
+		if (restart & KSZ8873_PORT_PHY_LOOPBACK)
+			*val |= BMCR_LOOPBACK;
+
+		if ((ctrl & PORT_AUTO_NEG_ENABLE))
+			*val |= BMCR_ANENABLE;
+	} else {
+		ret = ksz879x_get_loopback(dev, port, val);
+		if (ret)
+			return ret;
+
+		if (!(ctrl & PORT_AUTO_NEG_DISABLE))
+			*val |= BMCR_ANENABLE;
+	}
+
+	if (restart & PORT_POWER_DOWN)
+		*val |= BMCR_PDOWN;
+
+	if (restart & PORT_AUTO_NEG_RESTART)
+		*val |= BMCR_ANRESTART;
+
+	if (ctrl & PORT_FORCE_FULL_DUPLEX)
+		*val |= BMCR_FULLDPLX;
+
+	if (speed & PORT_HP_MDIX)
+		*val |= KSZ886X_BMCR_HP_MDIX;
+
+	if (restart & PORT_FORCE_MDIX)
+		*val |= KSZ886X_BMCR_FORCE_MDI;
+
+	if (restart & PORT_AUTO_MDIX_DISABLE)
+		*val |= KSZ886X_BMCR_DISABLE_AUTO_MDIX;
+
+	if (restart & PORT_TX_DISABLE)
+		*val |= KSZ886X_BMCR_DISABLE_TRANSMIT;
+
+	if (restart & PORT_LED_OFF)
+		*val |= KSZ886X_BMCR_DISABLE_LED;
+
+	return 0;
+}
+
+int ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val)
+{
+	u8 ctrl, link, val1, val2;
+	int processed = true;
+	const u16 *regs;
+	u16 data = 0;
+	u16 p = phy;
+	int ret;
+
+	regs = dev->info->regs;
+
+	switch (reg) {
+	case MII_BMCR:
+		ret = ksz8_r_phy_bmcr(dev, p, &data);
+		if (ret)
+			return ret;
+		break;
+	case MII_BMSR:
+		ret = ksz_pread8(dev, p, regs[P_LINK_STATUS], &link);
+		if (ret)
+			return ret;
+
+		data = BMSR_100FULL |
+		       BMSR_100HALF |
+		       BMSR_10FULL |
+		       BMSR_10HALF |
+		       BMSR_ANEGCAPABLE;
+		if (link & PORT_AUTO_NEG_COMPLETE)
+			data |= BMSR_ANEGCOMPLETE;
+		if (link & PORT_STAT_LINK_GOOD)
+			data |= BMSR_LSTATUS;
+		break;
+	case MII_PHYSID1:
+		data = KSZ8795_ID_HI;
+		break;
+	case MII_PHYSID2:
+		if (ksz_is_ksz88x3(dev))
+			data = KSZ8863_ID_LO;
+		else
+			data = KSZ8795_ID_LO;
+		break;
+	case MII_ADVERTISE:
+		ret = ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl);
+		if (ret)
+			return ret;
+
+		data = ADVERTISE_CSMA;
+		if (ctrl & PORT_AUTO_NEG_SYM_PAUSE)
+			data |= ADVERTISE_PAUSE_CAP;
+		if (ctrl & PORT_AUTO_NEG_100BTX_FD)
+			data |= ADVERTISE_100FULL;
+		if (ctrl & PORT_AUTO_NEG_100BTX)
+			data |= ADVERTISE_100HALF;
+		if (ctrl & PORT_AUTO_NEG_10BT_FD)
+			data |= ADVERTISE_10FULL;
+		if (ctrl & PORT_AUTO_NEG_10BT)
+			data |= ADVERTISE_10HALF;
+		break;
+	case MII_LPA:
+		ret = ksz_pread8(dev, p, regs[P_REMOTE_STATUS], &link);
+		if (ret)
+			return ret;
+
+		data = LPA_SLCT;
+		if (link & PORT_REMOTE_SYM_PAUSE)
+			data |= LPA_PAUSE_CAP;
+		if (link & PORT_REMOTE_100BTX_FD)
+			data |= LPA_100FULL;
+		if (link & PORT_REMOTE_100BTX)
+			data |= LPA_100HALF;
+		if (link & PORT_REMOTE_10BT_FD)
+			data |= LPA_10FULL;
+		if (link & PORT_REMOTE_10BT)
+			data |= LPA_10HALF;
+		if (data & ~LPA_SLCT)
+			data |= LPA_LPACK;
+		break;
+	case PHY_REG_LINK_MD:
+		ret = ksz_pread8(dev, p, REG_PORT_LINK_MD_CTRL, &val1);
+		if (ret)
+			return ret;
+
+		ret = ksz_pread8(dev, p, REG_PORT_LINK_MD_RESULT, &val2);
+		if (ret)
+			return ret;
+
+		if (val1 & PORT_START_CABLE_DIAG)
+			data |= PHY_START_CABLE_DIAG;
+
+		if (val1 & PORT_CABLE_10M_SHORT)
+			data |= PHY_CABLE_10M_SHORT;
+
+		data |= FIELD_PREP(PHY_CABLE_DIAG_RESULT_M,
+				FIELD_GET(PORT_CABLE_DIAG_RESULT_M, val1));
+
+		data |= FIELD_PREP(PHY_CABLE_FAULT_COUNTER_M,
+				(FIELD_GET(PORT_CABLE_FAULT_COUNTER_H, val1) << 8) |
+				FIELD_GET(PORT_CABLE_FAULT_COUNTER_L, val2));
+		break;
+	case PHY_REG_PHY_CTRL:
+		ret = ksz8_r_phy_ctrl(dev, p, &data);
+		if (ret)
+			return ret;
+
+		break;
+	default:
+		processed = false;
+		break;
+	}
+	if (processed)
+		*val = data;
+
+	return 0;
+}
+
+/**
+ * ksz8_w_phy_ctrl - Translates and writes to the SMI interface from a MIIM PHY
+ *		     Control register (Reg. 31).
+ * @dev: The KSZ device instance.
+ * @port: The port number to be configured.
+ * @val: The register value to be written.
+ *
+ * This function translates control settings from a MIIM PHY Control register
+ * into their corresponding hardware register bit values for the SMI
+ * interface.
+ *
+ * Return: 0 on success, error code on failure.
+ */
+static int ksz8_w_phy_ctrl(struct ksz_device *dev, int port, u16 val)
+{
+	u8 reg_val = 0;
+	int ret;
+
+	if (val & KSZ886X_CTRL_FORCE_LINK)
+		reg_val |= PORT_FORCE_LINK;
+
+	if (val & KSZ886X_CTRL_PWRSAVE)
+		reg_val |= PORT_POWER_SAVING;
+
+	if (val & KSZ886X_CTRL_REMOTE_LOOPBACK)
+		reg_val |= PORT_PHY_REMOTE_LOOPBACK;
+
+	ret = ksz_prmw8(dev, port, REG_PORT_LINK_MD_CTRL, PORT_FORCE_LINK |
+			PORT_POWER_SAVING | PORT_PHY_REMOTE_LOOPBACK, reg_val);
+	return ret;
+}
+
+/**
+ * ksz8_w_phy_bmcr - Translates and writes to the SMI interface from a MIIM PHY
+ *		     Basic mode control register (Reg. 0).
+ * @dev: The KSZ device instance.
+ * @port: The port number to be configured.
+ * @val: The register value to be written.
+ *
+ * This function translates control settings from a MIIM PHY Basic mode control
+ * register into their corresponding hardware register bit values for the SMI
+ * interface.
+ *
+ * MIIM Bit Mapping Comparison between KSZ8794 and KSZ8873
+ * -------------------------------------------------------------------
+ * MIIM Bit                    | KSZ8794 Reg/Bit             | KSZ8873 Reg/Bit
+ * ----------------------------+-----------------------------+----------------
+ * Bit 15 - Soft Reset         | 0xF/4                       | Not supported
+ * Bit 14 - Loopback           | 0xD/0 (MAC), 0xF/7 (PHY)    ~ 0xD/0 (PHY)
+ * Bit 13 - Force 100          | 0xC/6                       = 0xC/6
+ * Bit 12 - AN Enable          | 0xC/7 (reverse logic)       ~ 0xC/7
+ * Bit 11 - Power Down         | 0xD/3                       = 0xD/3
+ * Bit 10 - PHY Isolate        | 0xF/5                       | Not supported
+ * Bit 9 - Restart AN          | 0xD/5                       = 0xD/5
+ * Bit 8 - Force Full-Duplex   | 0xC/5                       = 0xC/5
+ * Bit 7 - Collision Test/Res. | Not supported               | Not supported
+ * Bit 6 - Reserved            | Not supported               | Not supported
+ * Bit 5 - Hp_mdix             | 0x9/7                       ~ 0xF/7
+ * Bit 4 - Force MDI           | 0xD/1                       = 0xD/1
+ * Bit 3 - Disable MDIX        | 0xD/2                       = 0xD/2
+ * Bit 2 - Disable Far-End F.  | ????                        | 0xD/4
+ * Bit 1 - Disable Transmit    | 0xD/6                       = 0xD/6
+ * Bit 0 - Disable LED         | 0xD/7                       = 0xD/7
+ * -------------------------------------------------------------------
+ *
+ * Return: 0 on success, error code on failure.
+ */
+static int ksz8_w_phy_bmcr(struct ksz_device *dev, u16 port, u16 val)
+{
+	u8 restart, speed, ctrl, restart_mask;
+	const u16 *regs = dev->info->regs;
+	int ret;
+
+	/* Do not support PHY reset function. */
+	if (val & BMCR_RESET)
+		return 0;
+
+	speed = 0;
+	if (val & KSZ886X_BMCR_HP_MDIX)
+		speed |= PORT_HP_MDIX;
+
+	ret = ksz_prmw8(dev, port, regs[P_SPEED_STATUS], PORT_HP_MDIX, speed);
+	if (ret)
+		return ret;
+
+	ctrl = 0;
+	if (ksz_is_ksz88x3(dev)) {
+		if ((val & BMCR_ANENABLE))
+			ctrl |= PORT_AUTO_NEG_ENABLE;
+	} else {
+		if (!(val & BMCR_ANENABLE))
+			ctrl |= PORT_AUTO_NEG_DISABLE;
+
+		/* Fiber port does not support auto-negotiation. */
+		if (dev->ports[port].fiber)
+			ctrl |= PORT_AUTO_NEG_DISABLE;
+	}
+
+	if (val & BMCR_SPEED100)
+		ctrl |= PORT_FORCE_100_MBIT;
+
+	if (val & BMCR_FULLDPLX)
+		ctrl |= PORT_FORCE_FULL_DUPLEX;
+
+	ret = ksz_prmw8(dev, port, regs[P_FORCE_CTRL], PORT_FORCE_100_MBIT |
+		 /* PORT_AUTO_NEG_ENABLE and PORT_AUTO_NEG_DISABLE are the same
+		  * bits
+		  */
+		 PORT_FORCE_FULL_DUPLEX | PORT_AUTO_NEG_ENABLE, ctrl);
+	if (ret)
+		return ret;
+
+	restart = 0;
+	restart_mask = PORT_LED_OFF | PORT_TX_DISABLE | PORT_AUTO_NEG_RESTART |
+		PORT_POWER_DOWN | PORT_AUTO_MDIX_DISABLE | PORT_FORCE_MDIX;
+
+	if (val & KSZ886X_BMCR_DISABLE_LED)
+		restart |= PORT_LED_OFF;
+
+	if (val & KSZ886X_BMCR_DISABLE_TRANSMIT)
+		restart |= PORT_TX_DISABLE;
+
+	if (val & BMCR_ANRESTART)
+		restart |= PORT_AUTO_NEG_RESTART;
+
+	if (val & BMCR_PDOWN)
+		restart |= PORT_POWER_DOWN;
+
+	if (val & KSZ886X_BMCR_DISABLE_AUTO_MDIX)
+		restart |= PORT_AUTO_MDIX_DISABLE;
+
+	if (val & KSZ886X_BMCR_FORCE_MDI)
+		restart |= PORT_FORCE_MDIX;
+
+	if (ksz_is_ksz88x3(dev)) {
+		restart_mask |= KSZ8873_PORT_PHY_LOOPBACK;
+
+		if (val & BMCR_LOOPBACK)
+			restart |= KSZ8873_PORT_PHY_LOOPBACK;
+	} else {
+		ret = ksz879x_set_loopback(dev, port, val);
+		if (ret)
+			return ret;
+	}
+
+	return ksz_prmw8(dev, port, regs[P_NEG_RESTART_CTRL], restart_mask,
+			 restart);
+}
+
+int ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
+{
+	const u16 *regs;
+	u8 ctrl, data;
+	u16 p = phy;
+	int ret;
+
+	regs = dev->info->regs;
+
+	switch (reg) {
+	case MII_BMCR:
+		ret = ksz8_w_phy_bmcr(dev, p, val);
+		if (ret)
+			return ret;
+		break;
+	case MII_ADVERTISE:
+		ret = ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl);
+		if (ret)
+			return ret;
+
+		data = ctrl;
+		data &= ~(PORT_AUTO_NEG_SYM_PAUSE |
+			  PORT_AUTO_NEG_100BTX_FD |
+			  PORT_AUTO_NEG_100BTX |
+			  PORT_AUTO_NEG_10BT_FD |
+			  PORT_AUTO_NEG_10BT);
+		if (val & ADVERTISE_PAUSE_CAP)
+			data |= PORT_AUTO_NEG_SYM_PAUSE;
+		if (val & ADVERTISE_100FULL)
+			data |= PORT_AUTO_NEG_100BTX_FD;
+		if (val & ADVERTISE_100HALF)
+			data |= PORT_AUTO_NEG_100BTX;
+		if (val & ADVERTISE_10FULL)
+			data |= PORT_AUTO_NEG_10BT_FD;
+		if (val & ADVERTISE_10HALF)
+			data |= PORT_AUTO_NEG_10BT;
+
+		if (data != ctrl) {
+			ret = ksz_pwrite8(dev, p, regs[P_LOCAL_CTRL], data);
+			if (ret)
+				return ret;
+		}
+		break;
+	case PHY_REG_LINK_MD:
+		if (val & PHY_START_CABLE_DIAG)
+			ksz_port_cfg(dev, p, REG_PORT_LINK_MD_CTRL, PORT_START_CABLE_DIAG, true);
+		break;
+
+	case PHY_REG_PHY_CTRL:
+		ret = ksz8_w_phy_ctrl(dev, p, val);
+		if (ret)
+			return ret;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member)
+{
+	u8 data;
+
+	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
+	data &= ~PORT_VLAN_MEMBERSHIP;
+	data |= (member & dev->port_mask);
+	ksz_pwrite8(dev, port, P_MIRROR_CTRL, data);
+}
+
+void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port)
+{
+	u8 learn[DSA_MAX_PORTS];
+	int first, index, cnt;
+	const u16 *regs;
+
+	regs = dev->info->regs;
+
+	if ((uint)port < dev->info->port_cnt) {
+		first = port;
+		cnt = port + 1;
+	} else {
+		/* Flush all ports. */
+		first = 0;
+		cnt = dev->info->port_cnt;
+	}
+	for (index = first; index < cnt; index++) {
+		ksz_pread8(dev, index, regs[P_STP_CTRL], &learn[index]);
+		if (!(learn[index] & PORT_LEARN_DISABLE))
+			ksz_pwrite8(dev, index, regs[P_STP_CTRL],
+				    learn[index] | PORT_LEARN_DISABLE);
+	}
+	ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_DYN_MAC_TABLE, true);
+	for (index = first; index < cnt; index++) {
+		if (!(learn[index] & PORT_LEARN_DISABLE))
+			ksz_pwrite8(dev, index, regs[P_STP_CTRL], learn[index]);
+	}
+}
+
+int ksz8_fdb_dump(struct ksz_device *dev, int port,
+		  dsa_fdb_dump_cb_t *cb, void *data)
+{
+	u8 mac[ETH_ALEN];
+	u8 src_port, fid;
+	u16 entries = 0;
+	int ret, i;
+
+	for (i = 0; i < KSZ8_DYN_MAC_ENTRIES; i++) {
+		ret = ksz8_r_dyn_mac_table(dev, i, mac, &fid, &src_port,
+					   &entries);
+		if (ret)
+			return ret;
+
+		if (i >= entries)
+			return 0;
+
+		if (port == src_port) {
+			ret = cb(mac, fid, false, data);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int ksz8_add_sta_mac(struct ksz_device *dev, int port,
+			    const unsigned char *addr, u16 vid)
+{
+	struct alu_struct alu;
+	int index, ret;
+	int empty = 0;
+
+	alu.port_forward = 0;
+	for (index = 0; index < dev->info->num_statics; index++) {
+		bool valid;
+
+		ret = ksz8_r_sta_mac_table(dev, index, &alu, &valid);
+		if (ret)
+			return ret;
+		if (!valid) {
+			/* Remember the first empty entry. */
+			if (!empty)
+				empty = index + 1;
+			continue;
+		}
+
+		if (!memcmp(alu.mac, addr, ETH_ALEN) && alu.fid == vid)
+			break;
+	}
+
+	/* no available entry */
+	if (index == dev->info->num_statics && !empty)
+		return -ENOSPC;
+
+	/* add entry */
+	if (index == dev->info->num_statics) {
+		index = empty - 1;
+		memset(&alu, 0, sizeof(alu));
+		memcpy(alu.mac, addr, ETH_ALEN);
+		alu.is_static = true;
+	}
+	alu.port_forward |= BIT(port);
+	if (vid) {
+		alu.is_use_fid = true;
+
+		/* Need a way to map VID to FID. */
+		alu.fid = vid;
+	}
+
+	return ksz8_w_sta_mac_table(dev, index, &alu);
+}
+
+static int ksz8_del_sta_mac(struct ksz_device *dev, int port,
+			    const unsigned char *addr, u16 vid)
+{
+	struct alu_struct alu;
+	int index, ret;
+
+	for (index = 0; index < dev->info->num_statics; index++) {
+		bool valid;
+
+		ret = ksz8_r_sta_mac_table(dev, index, &alu, &valid);
+		if (ret)
+			return ret;
+		if (!valid)
+			continue;
+
+		if (!memcmp(alu.mac, addr, ETH_ALEN) && alu.fid == vid)
+			break;
+	}
+
+	/* no available entry */
+	if (index == dev->info->num_statics)
+		return 0;
+
+	/* clear port */
+	alu.port_forward &= ~BIT(port);
+	if (!alu.port_forward)
+		alu.is_static = false;
+
+	return ksz8_w_sta_mac_table(dev, index, &alu);
+}
+
+int ksz8_mdb_add(struct ksz_device *dev, int port,
+		 const struct switchdev_obj_port_mdb *mdb, struct dsa_db db)
+{
+	return ksz8_add_sta_mac(dev, port, mdb->addr, mdb->vid);
+}
+
+int ksz8_mdb_del(struct ksz_device *dev, int port,
+		 const struct switchdev_obj_port_mdb *mdb, struct dsa_db db)
+{
+	return ksz8_del_sta_mac(dev, port, mdb->addr, mdb->vid);
+}
+
+int ksz8_fdb_add(struct ksz_device *dev, int port, const unsigned char *addr,
+		 u16 vid, struct dsa_db db)
+{
+	return ksz8_add_sta_mac(dev, port, addr, vid);
+}
+
+int ksz8_fdb_del(struct ksz_device *dev, int port, const unsigned char *addr,
+		 u16 vid, struct dsa_db db)
+{
+	return ksz8_del_sta_mac(dev, port, addr, vid);
+}
+
+int ksz8_port_vlan_filtering(struct ksz_device *dev, int port, bool flag,
+			     struct netlink_ext_ack *extack)
+{
+	if (ksz_is_ksz88x3(dev))
+		return -ENOTSUPP;
+
+	/* Discard packets with VID not enabled on the switch */
+	ksz_cfg(dev, S_MIRROR_CTRL, SW_VLAN_ENABLE, flag);
+
+	/* Discard packets with VID not enabled on the ingress port */
+	for (port = 0; port < dev->phy_port_cnt; ++port)
+		ksz_port_cfg(dev, port, REG_PORT_CTRL_2, PORT_INGRESS_FILTER,
+			     flag);
+
+	return 0;
+}
+
+static void ksz8_port_enable_pvid(struct ksz_device *dev, int port, bool state)
+{
+	if (ksz_is_ksz88x3(dev)) {
+		ksz_cfg(dev, REG_SW_INSERT_SRC_PVID,
+			0x03 << (4 - 2 * port), state);
+	} else {
+		ksz_pwrite8(dev, port, REG_PORT_CTRL_12, state ? 0x0f : 0x00);
+	}
+}
+
+int ksz8_port_vlan_add(struct ksz_device *dev, int port,
+		       const struct switchdev_obj_port_vlan *vlan,
+		       struct netlink_ext_ack *extack)
+{
+	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	struct ksz_port *p = &dev->ports[port];
+	u16 data, new_pvid = 0;
+	u8 fid, member, valid;
+
+	if (ksz_is_ksz88x3(dev))
+		return -ENOTSUPP;
+
+	/* If a VLAN is added with untagged flag different from the
+	 * port's Remove Tag flag, we need to change the latter.
+	 * Ignore VID 0, which is always untagged.
+	 * Ignore CPU port, which will always be tagged.
+	 */
+	if (untagged != p->remove_tag && vlan->vid != 0 &&
+	    port != dev->cpu_port) {
+		unsigned int vid;
+
+		/* Reject attempts to add a VLAN that requires the
+		 * Remove Tag flag to be changed, unless there are no
+		 * other VLANs currently configured.
+		 */
+		for (vid = 1; vid < dev->info->num_vlans; ++vid) {
+			/* Skip the VID we are going to add or reconfigure */
+			if (vid == vlan->vid)
+				continue;
+
+			ksz8_from_vlan(dev, dev->vlan_cache[vid].table[0],
+				       &fid, &member, &valid);
+			if (valid && (member & BIT(port)))
+				return -EINVAL;
+		}
+
+		ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged);
+		p->remove_tag = untagged;
+	}
+
+	ksz8_r_vlan_table(dev, vlan->vid, &data);
+	ksz8_from_vlan(dev, data, &fid, &member, &valid);
+
+	/* First time to setup the VLAN entry. */
+	if (!valid) {
+		/* Need to find a way to map VID to FID. */
+		fid = 1;
+		valid = 1;
+	}
+	member |= BIT(port);
+
+	ksz8_to_vlan(dev, fid, member, valid, &data);
+	ksz8_w_vlan_table(dev, vlan->vid, data);
+
+	/* change PVID */
+	if (vlan->flags & BRIDGE_VLAN_INFO_PVID)
+		new_pvid = vlan->vid;
+
+	if (new_pvid) {
+		u16 vid;
+
+		ksz_pread16(dev, port, REG_PORT_CTRL_VID, &vid);
+		vid &= ~VLAN_VID_MASK;
+		vid |= new_pvid;
+		ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, vid);
+
+		ksz8_port_enable_pvid(dev, port, true);
+	}
+
+	return 0;
+}
+
+int ksz8_port_vlan_del(struct ksz_device *dev, int port,
+		       const struct switchdev_obj_port_vlan *vlan)
+{
+	u16 data, pvid;
+	u8 fid, member, valid;
+
+	if (ksz_is_ksz88x3(dev))
+		return -ENOTSUPP;
+
+	ksz_pread16(dev, port, REG_PORT_CTRL_VID, &pvid);
+	pvid = pvid & 0xFFF;
+
+	ksz8_r_vlan_table(dev, vlan->vid, &data);
+	ksz8_from_vlan(dev, data, &fid, &member, &valid);
+
+	member &= ~BIT(port);
+
+	/* Invalidate the entry if no more member. */
+	if (!member) {
+		fid = 0;
+		valid = 0;
+	}
+
+	ksz8_to_vlan(dev, fid, member, valid, &data);
+	ksz8_w_vlan_table(dev, vlan->vid, data);
+
+	if (pvid == vlan->vid)
+		ksz8_port_enable_pvid(dev, port, false);
+
+	return 0;
+}
+
+int ksz8_port_mirror_add(struct ksz_device *dev, int port,
+			 struct dsa_mall_mirror_tc_entry *mirror,
+			 bool ingress, struct netlink_ext_ack *extack)
+{
+	if (ingress) {
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true);
+		dev->mirror_rx |= BIT(port);
+	} else {
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true);
+		dev->mirror_tx |= BIT(port);
+	}
+
+	ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false);
+
+	/* configure mirror port */
+	if (dev->mirror_rx || dev->mirror_tx)
+		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
+			     PORT_MIRROR_SNIFFER, true);
+
+	return 0;
+}
+
+void ksz8_port_mirror_del(struct ksz_device *dev, int port,
+			  struct dsa_mall_mirror_tc_entry *mirror)
+{
+	u8 data;
+
+	if (mirror->ingress) {
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false);
+		dev->mirror_rx &= ~BIT(port);
+	} else {
+		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false);
+		dev->mirror_tx &= ~BIT(port);
+	}
+
+	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
+
+	if (!dev->mirror_rx && !dev->mirror_tx)
+		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
+			     PORT_MIRROR_SNIFFER, false);
+}
+
+static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port)
+{
+	struct ksz_port *p = &dev->ports[port];
+
+	if (!ksz_is_ksz87xx(dev))
+		return;
+
+	if (!p->interface && dev->compat_interface) {
+		dev_warn(dev->dev,
+			 "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. "
+			 "Please update your device tree.\n",
+			 port);
+		p->interface = dev->compat_interface;
+	}
+}
+
+void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
+{
+	const u16 *regs = dev->info->regs;
+	struct dsa_switch *ds = dev->ds;
+	const u32 *masks;
+	int queues;
+	u8 member;
+
+	masks = dev->info->masks;
+
+	/* enable broadcast storm limit */
+	ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true);
+
+	/* For KSZ88x3 enable only one queue by default, otherwise we won't
+	 * be able to get rid of PCP prios on Port 2.
+	 */
+	if (ksz_is_ksz88x3(dev))
+		queues = 1;
+	else
+		queues = dev->info->num_tx_queues;
+
+	ksz8_port_queue_split(dev, port, queues);
+
+	/* replace priority */
+	ksz_port_cfg(dev, port, P_802_1P_CTRL,
+		     masks[PORT_802_1P_REMAPPING], false);
+
+	if (cpu_port)
+		member = dsa_user_ports(ds);
+	else
+		member = BIT(dsa_upstream_port(ds, port));
+
+	ksz8_cfg_port_member(dev, port, member);
+
+	/* Disable all WoL options by default. Otherwise
+	 * ksz_switch_macaddr_get/put logic will not work properly.
+	 * CPU port 4 has no WoL functionality.
+	 */
+	if (ksz_is_ksz87xx(dev) && !cpu_port)
+		ksz8_pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0);
+}
+
+static void ksz88x3_config_rmii_clk(struct ksz_device *dev)
+{
+	struct dsa_port *cpu_dp = dsa_to_port(dev->ds, dev->cpu_port);
+	bool rmii_clk_internal;
+
+	if (!ksz_is_ksz88x3(dev))
+		return;
+
+	rmii_clk_internal = of_property_read_bool(cpu_dp->dn,
+						  "microchip,rmii-clk-internal");
+
+	ksz_cfg(dev, KSZ88X3_REG_FVID_AND_HOST_MODE,
+		KSZ88X3_PORT3_RMII_CLK_INTERNAL, rmii_clk_internal);
+}
+
+void ksz8_config_cpu_port(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	struct ksz_port *p;
+	const u32 *masks;
+	const u16 *regs;
+	u8 remote;
+	int i;
+
+	masks = dev->info->masks;
+	regs = dev->info->regs;
+
+	ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true);
+
+	ksz8_port_setup(dev, dev->cpu_port, true);
+
+	ksz8795_cpu_interface_select(dev, dev->cpu_port);
+	ksz88x3_config_rmii_clk(dev);
+
+	for (i = 0; i < dev->phy_port_cnt; i++) {
+		ksz_port_stp_state_set(ds, i, BR_STATE_DISABLED);
+	}
+	for (i = 0; i < dev->phy_port_cnt; i++) {
+		p = &dev->ports[i];
+
+		/* For KSZ8795 family. */
+		if (ksz_is_ksz87xx(dev)) {
+			ksz_pread8(dev, i, regs[P_REMOTE_STATUS], &remote);
+			if (remote & KSZ8_PORT_FIBER_MODE)
+				p->fiber = 1;
+		}
+		if (p->fiber)
+			ksz_port_cfg(dev, i, regs[P_STP_CTRL],
+				     PORT_FORCE_FLOW_CTRL, true);
+		else
+			ksz_port_cfg(dev, i, regs[P_STP_CTRL],
+				     PORT_FORCE_FLOW_CTRL, false);
+	}
+}
+
+/**
+ * ksz8_phy_port_link_up - Configures ports with integrated PHYs
+ * @dev: The KSZ device instance.
+ * @port: The port number to configure.
+ * @duplex: The desired duplex mode.
+ * @tx_pause: If true, enables transmit pause.
+ * @rx_pause: If true, enables receive pause.
+ *
+ * Description:
+ * The function configures flow control settings for a given port based on the
+ * desired settings and current duplex mode.
+ *
+ * According to the KSZ8873 datasheet, the PORT_FORCE_FLOW_CTRL bit in the
+ * Port Control 2 register (0x1A for Port 1, 0x22 for Port 2, 0x32 for Port 3)
+ * determines how flow control is handled on the port:
+ *    "1 = will always enable full-duplex flow control on the port, regardless
+ *         of AN result.
+ *     0 = full-duplex flow control is enabled based on AN result."
+ *
+ * This means that the flow control behavior depends on the state of this bit:
+ * - If PORT_FORCE_FLOW_CTRL is set to 1, the switch will ignore AN results and
+ *   force flow control on the port.
+ * - If PORT_FORCE_FLOW_CTRL is set to 0, the switch will enable or disable
+ *   flow control based on the AN results.
+ *
+ * However, there is a potential limitation in this configuration. It is
+ * currently not possible to force disable flow control on a port if we still
+ * advertise pause support. While such a configuration is not currently
+ * supported by Linux, and may not make practical sense, it's important to be
+ * aware of this limitation when working with the KSZ8873 and similar devices.
+ */
+static void ksz8_phy_port_link_up(struct ksz_device *dev, int port, int duplex,
+				  bool tx_pause, bool rx_pause)
+{
+	const u16 *regs = dev->info->regs;
+	u8 sctrl = 0;
+
+	/* The KSZ8795 switch differs from the KSZ8873 by supporting
+	 * asymmetric pause control. However, since a single bit is used to
+	 * control both RX and TX pause, we can't enforce asymmetric pause
+	 * control - both TX and RX pause will be either enabled or disabled
+	 * together.
+	 *
+	 * If auto-negotiation is enabled, we usually allow the flow control to
+	 * be determined by the auto-negotiation process based on the
+	 * capabilities of both link partners. However, for KSZ8873, the
+	 * PORT_FORCE_FLOW_CTRL bit may be set by the hardware bootstrap,
+	 * ignoring the auto-negotiation result. Thus, even in auto-negotiation
+	 * mode, we need to ensure that the PORT_FORCE_FLOW_CTRL bit is
+	 * properly cleared.
+	 *
+	 * In the absence of pause auto-negotiation, we will enforce symmetric
+	 * pause control for both variants of switches - KSZ8873 and KSZ8795.
+	 *
+	 * Autoneg Pause Autoneg      rx,tx	PORT_FORCE_FLOW_CTRL
+	 * 1		1		x	0
+	 * 0		1		x	0 (flow control probably disabled)
+	 * x		0		1	1 (flow control force enabled)
+	 * 1		0		0	0 (flow control still depends on
+	 *					   aneg result due to hardware)
+	 * 0		0		0	0 (flow control probably disabled)
+	 */
+	if (dev->ports[port].manual_flow && tx_pause)
+		sctrl |= PORT_FORCE_FLOW_CTRL;
+
+	ksz_prmw8(dev, port, regs[P_STP_CTRL], PORT_FORCE_FLOW_CTRL, sctrl);
+}
+
+/**
+ * ksz8_cpu_port_link_up - Configures the CPU port of the switch.
+ * @dev: The KSZ device instance.
+ * @speed: The desired link speed.
+ * @duplex: The desired duplex mode.
+ * @tx_pause: If true, enables transmit pause.
+ * @rx_pause: If true, enables receive pause.
+ *
+ * Description:
+ * The function configures flow control and speed settings for the CPU
+ * port of the switch based on the desired settings, current duplex mode, and
+ * speed.
+ */
+static void ksz8_cpu_port_link_up(struct ksz_device *dev, int speed, int duplex,
+				  bool tx_pause, bool rx_pause)
+{
+	const u16 *regs = dev->info->regs;
+	u8 ctrl = 0;
+
+	/* SW_FLOW_CTRL, SW_HALF_DUPLEX, and SW_10_MBIT bits are bootstrappable
+	 * at least on KSZ8873. They can have different values depending on your
+	 * board setup.
+	 */
+	if (tx_pause || rx_pause)
+		ctrl |= SW_FLOW_CTRL;
+
+	if (duplex == DUPLEX_HALF)
+		ctrl |= SW_HALF_DUPLEX;
+
+	/* This hardware only supports SPEED_10 and SPEED_100. For SPEED_10
+	 * we need to set the SW_10_MBIT bit. Otherwise, we can leave it 0.
+	 */
+	if (speed == SPEED_10)
+		ctrl |= SW_10_MBIT;
+
+	ksz_rmw8(dev, regs[S_BROADCAST_CTRL], SW_HALF_DUPLEX | SW_FLOW_CTRL |
+		 SW_10_MBIT, ctrl);
+}
+
+void ksz8_phylink_mac_link_up(struct phylink_config *config,
+			      struct phy_device *phydev, unsigned int mode,
+			      phy_interface_t interface, int speed, int duplex,
+			      bool tx_pause, bool rx_pause)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct ksz_device *dev = dp->ds->priv;
+	int port = dp->index;
+
+	/* If the port is the CPU port, apply special handling. Only the CPU
+	 * port is configured via global registers.
+	 */
+	if (dev->cpu_port == port)
+		ksz8_cpu_port_link_up(dev, speed, duplex, tx_pause, rx_pause);
+	else if (dev->info->internal_phy[port])
+		ksz8_phy_port_link_up(dev, port, duplex, tx_pause, rx_pause);
+}
+
+static int ksz8_handle_global_errata(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	int ret = 0;
+
+	/* KSZ87xx Errata DS80000687C.
+	 * Module 2: Link drops with some EEE link partners.
+	 *   An issue with the EEE next page exchange between the
+	 *   KSZ879x/KSZ877x/KSZ876x and some EEE link partners may result in
+	 *   the link dropping.
+	 */
+	if (dev->info->ksz87xx_eee_link_erratum)
+		ret = ksz8_ind_write8(dev, TABLE_EEE, REG_IND_EEE_GLOB2_HI, 0);
+
+	return ret;
+}
+
+int ksz8_enable_stp_addr(struct ksz_device *dev)
+{
+	struct alu_struct alu;
+
+	/* Setup STP address for STP operation. */
+	memset(&alu, 0, sizeof(alu));
+	ether_addr_copy(alu.mac, eth_stp_addr);
+	alu.is_static = true;
+	alu.is_override = true;
+	alu.port_forward = dev->info->cpu_ports;
+
+	return ksz8_w_sta_mac_table(dev, 0, &alu);
+}
+
+int ksz8_setup(struct dsa_switch *ds)
+{
+	struct ksz_device *dev = ds->priv;
+	const u16 *regs = dev->info->regs;
+	int i, ret = 0;
+
+	ds->mtu_enforcement_ingress = true;
+
+	/* We rely on software untagging on the CPU port, so that we
+	 * can support both tagged and untagged VLANs
+	 */
+	ds->untag_bridge_pvid = true;
+
+	/* VLAN filtering is partly controlled by the global VLAN
+	 * Enable flag
+	 */
+	ds->vlan_filtering_is_global = true;
+
+	/* Enable automatic fast aging when link changed detected. */
+	ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true);
+
+	/* Enable aggressive back off algorithm in half duplex mode. */
+	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1,
+			   SW_AGGR_BACKOFF, SW_AGGR_BACKOFF);
+
+	/*
+	 * Make sure unicast VLAN boundary is set as default and
+	 * enable no excessive collision drop.
+	 */
+	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2,
+			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP,
+			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP);
+
+	ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false);
+
+	ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false);
+
+	if (!ksz_is_ksz88x3(dev))
+		ksz_cfg(dev, REG_SW_CTRL_19, SW_INS_TAG_ENABLE, true);
+
+	for (i = 0; i < (dev->info->num_vlans / 4); i++)
+		ksz8_r_vlan_entries(dev, i);
+
+	/* Make sure PME (WoL) is not enabled. If requested, it will
+	 * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs
+	 * do not like PME events changes before shutdown. PME only
+	 * available on KSZ87xx family.
+	 */
+	if (ksz_is_ksz87xx(dev)) {
+		ret = ksz8_pme_write8(dev, regs[REG_SW_PME_CTRL], 0);
+		if (!ret)
+			ret = ksz_rmw8(dev, REG_INT_ENABLE, INT_PME, 0);
+	}
+
+	if (!ret)
+		return ksz8_handle_global_errata(ds);
+	else
+		return ret;
+}
+
+void ksz8_get_caps(struct ksz_device *dev, int port,
+		   struct phylink_config *config)
+{
+	config->mac_capabilities = MAC_10 | MAC_100;
+
+	/* Silicon Errata Sheet (DS80000830A):
+	 * "Port 1 does not respond to received flow control PAUSE frames"
+	 * So, disable Pause support on "Port 1" (port == 0) for all ksz88x3
+	 * switches.
+	 */
+	if (!ksz_is_ksz88x3(dev) || port)
+		config->mac_capabilities |= MAC_SYM_PAUSE;
+
+	/* Asym pause is not supported on KSZ8863 and KSZ8873 */
+	if (!ksz_is_ksz88x3(dev))
+		config->mac_capabilities |= MAC_ASYM_PAUSE;
+}
+
+u32 ksz8_get_port_addr(int port, int offset)
+{
+	return PORT_CTRL_ADDR(port, offset);
+}
+
+int ksz8_switch_init(struct ksz_device *dev)
+{
+	dev->cpu_port = fls(dev->info->cpu_ports) - 1;
+	dev->phy_port_cnt = dev->info->port_cnt - 1;
+	dev->port_mask = (BIT(dev->phy_port_cnt) - 1) | dev->info->cpu_ports;
+
+	return 0;
+}
+
+void ksz8_switch_exit(struct ksz_device *dev)
+{
+	ksz8_reset_switch(dev);
+}
+
+MODULE_AUTHOR("Tristram Ha <Tristram.Ha@microchip.com>");
+MODULE_DESCRIPTION("Microchip KSZ8795 Series Switch DSA Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
deleted file mode 100644
index aa09d89debf0..000000000000
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ /dev/null
@@ -1,1968 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Microchip KSZ8795 switch driver
- *
- * Copyright (C) 2017 Microchip Technology Inc.
- *	Tristram Ha <Tristram.Ha@microchip.com>
- */
-
-#include <linux/bitfield.h>
-#include <linux/delay.h>
-#include <linux/export.h>
-#include <linux/gpio.h>
-#include <linux/if_vlan.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_data/microchip-ksz.h>
-#include <linux/phy.h>
-#include <linux/etherdevice.h>
-#include <linux/if_bridge.h>
-#include <linux/micrel_phy.h>
-#include <net/dsa.h>
-#include <net/switchdev.h>
-#include <linux/phylink.h>
-
-#include "ksz_common.h"
-#include "ksz8795_reg.h"
-#include "ksz8.h"
-
-static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
-{
-	regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0);
-}
-
-static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
-			 bool set)
-{
-	regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset),
-			   bits, set ? bits : 0);
-}
-
-/**
- * ksz8_ind_write8 - EEE/ACL/PME indirect register write
- * @dev: The device structure.
- * @table: Function & table select, register 110.
- * @addr: Indirect access control, register 111.
- * @data: The data to be written.
- *
- * This function performs an indirect register write for EEE, ACL or
- * PME switch functionalities. Both 8-bit registers 110 and 111 are
- * written at once with ksz_write16, using the serial multiple write
- * functionality.
- *
- * Return: 0 on success, or an error code on failure.
- */
-static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data)
-{
-	const u16 *regs;
-	u16 ctrl_addr;
-	int ret = 0;
-
-	regs = dev->info->regs;
-
-	mutex_lock(&dev->alu_mutex);
-
-	ctrl_addr = IND_ACC_TABLE(table) | addr;
-	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-	if (!ret)
-		ret = ksz_write8(dev, regs[REG_IND_BYTE], data);
-
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-/**
- * ksz8_ind_read8 - EEE/ACL/PME indirect register read
- * @dev: The device structure.
- * @table: Function & table select, register 110.
- * @addr: Indirect access control, register 111.
- * @val: The value read.
- *
- * This function performs an indirect register read for EEE, ACL or
- * PME switch functionalities. Both 8-bit registers 110 and 111 are
- * written at once with ksz_write16, using the serial multiple write
- * functionality.
- *
- * Return: 0 on success, or an error code on failure.
- */
-static int ksz8_ind_read8(struct ksz_device *dev, u8 table, u16 addr, u8 *val)
-{
-	const u16 *regs;
-	u16 ctrl_addr;
-	int ret = 0;
-
-	regs = dev->info->regs;
-
-	mutex_lock(&dev->alu_mutex);
-
-	ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr;
-	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-	if (!ret)
-		ret = ksz_read8(dev, regs[REG_IND_BYTE], val);
-
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value)
-{
-	return ksz8_ind_write8(dev, (u8)(reg >> 8), (u8)(reg), value);
-}
-
-int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data)
-{
-	u8 table = (u8)(offset >> 8 | (port + 1));
-
-	return ksz8_ind_read8(dev, table, (u8)(offset), data);
-}
-
-int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data)
-{
-	u8 table = (u8)(offset >> 8 | (port + 1));
-
-	return ksz8_ind_write8(dev, table, (u8)(offset), data);
-}
-
-int ksz8_reset_switch(struct ksz_device *dev)
-{
-	if (ksz_is_ksz88x3(dev)) {
-		/* reset switch */
-		ksz_cfg(dev, KSZ8863_REG_SW_RESET,
-			KSZ8863_GLOBAL_SOFTWARE_RESET | KSZ8863_PCS_RESET, true);
-		ksz_cfg(dev, KSZ8863_REG_SW_RESET,
-			KSZ8863_GLOBAL_SOFTWARE_RESET | KSZ8863_PCS_RESET, false);
-	} else {
-		/* reset switch */
-		ksz_write8(dev, REG_POWER_MANAGEMENT_1,
-			   SW_SOFTWARE_POWER_DOWN << SW_POWER_MANAGEMENT_MODE_S);
-		ksz_write8(dev, REG_POWER_MANAGEMENT_1, 0);
-	}
-
-	return 0;
-}
-
-static int ksz8863_change_mtu(struct ksz_device *dev, int frame_size)
-{
-	u8 ctrl2 = 0;
-
-	if (frame_size <= KSZ8_LEGAL_PACKET_SIZE)
-		ctrl2 |= KSZ8863_LEGAL_PACKET_ENABLE;
-	else if (frame_size > KSZ8863_NORMAL_PACKET_SIZE)
-		ctrl2 |= KSZ8863_HUGE_PACKET_ENABLE;
-
-	return ksz_rmw8(dev, REG_SW_CTRL_2, KSZ8863_LEGAL_PACKET_ENABLE |
-			KSZ8863_HUGE_PACKET_ENABLE, ctrl2);
-}
-
-static int ksz8795_change_mtu(struct ksz_device *dev, int frame_size)
-{
-	u8 ctrl1 = 0, ctrl2 = 0;
-	int ret;
-
-	if (frame_size > KSZ8_LEGAL_PACKET_SIZE)
-		ctrl2 |= SW_LEGAL_PACKET_DISABLE;
-	if (frame_size > KSZ8863_NORMAL_PACKET_SIZE)
-		ctrl1 |= SW_HUGE_PACKET;
-
-	ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_HUGE_PACKET, ctrl1);
-	if (ret)
-		return ret;
-
-	return ksz_rmw8(dev, REG_SW_CTRL_2, SW_LEGAL_PACKET_DISABLE, ctrl2);
-}
-
-int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu)
-{
-	u16 frame_size;
-
-	if (!dsa_is_cpu_port(dev->ds, port))
-		return 0;
-
-	frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
-
-	switch (dev->chip_id) {
-	case KSZ8795_CHIP_ID:
-	case KSZ8794_CHIP_ID:
-	case KSZ8765_CHIP_ID:
-		return ksz8795_change_mtu(dev, frame_size);
-	case KSZ8830_CHIP_ID:
-	case KSZ8864_CHIP_ID:
-	case KSZ8895_CHIP_ID:
-		return ksz8863_change_mtu(dev, frame_size);
-	}
-
-	return -EOPNOTSUPP;
-}
-
-static int ksz8_port_queue_split(struct ksz_device *dev, int port, int queues)
-{
-	u8 mask_4q, mask_2q;
-	u8 reg_4q, reg_2q;
-	u8 data_4q = 0;
-	u8 data_2q = 0;
-	int ret;
-
-	if (ksz_is_ksz88x3(dev)) {
-		mask_4q = KSZ8873_PORT_4QUEUE_SPLIT_EN;
-		mask_2q = KSZ8873_PORT_2QUEUE_SPLIT_EN;
-		reg_4q = REG_PORT_CTRL_0;
-		reg_2q = REG_PORT_CTRL_2;
-
-		/* KSZ8795 family switches have Weighted Fair Queueing (WFQ)
-		 * enabled by default. Enable it for KSZ8873 family switches
-		 * too. Default value for KSZ8873 family is strict priority,
-		 * which should be enabled by using TC_SETUP_QDISC_ETS, not
-		 * by default.
-		 */
-		ret = ksz_rmw8(dev, REG_SW_CTRL_3, WEIGHTED_FAIR_QUEUE_ENABLE,
-			       WEIGHTED_FAIR_QUEUE_ENABLE);
-		if (ret)
-			return ret;
-	} else {
-		mask_4q = KSZ8795_PORT_4QUEUE_SPLIT_EN;
-		mask_2q = KSZ8795_PORT_2QUEUE_SPLIT_EN;
-		reg_4q = REG_PORT_CTRL_13;
-		reg_2q = REG_PORT_CTRL_0;
-
-		/* TODO: this is legacy from initial KSZ8795 driver, should be
-		 * moved to appropriate place in the future.
-		 */
-		ret = ksz_rmw8(dev, REG_SW_CTRL_19,
-			       SW_OUT_RATE_LIMIT_QUEUE_BASED,
-			       SW_OUT_RATE_LIMIT_QUEUE_BASED);
-		if (ret)
-			return ret;
-	}
-
-	if (queues == 4)
-		data_4q = mask_4q;
-	else if (queues == 2)
-		data_2q = mask_2q;
-
-	ret = ksz_prmw8(dev, port, reg_4q, mask_4q, data_4q);
-	if (ret)
-		return ret;
-
-	return ksz_prmw8(dev, port, reg_2q, mask_2q, data_2q);
-}
-
-int ksz8_all_queues_split(struct ksz_device *dev, int queues)
-{
-	struct dsa_switch *ds = dev->ds;
-	const struct dsa_port *dp;
-
-	dsa_switch_for_each_port(dp, ds) {
-		int ret = ksz8_port_queue_split(dev, dp->index, queues);
-
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-void ksz8_r_mib_cnt(struct ksz_device *dev, int port, u16 addr, u64 *cnt)
-{
-	const u32 *masks;
-	const u16 *regs;
-	u16 ctrl_addr;
-	u32 data;
-	u8 check;
-	int loop;
-
-	masks = dev->info->masks;
-	regs = dev->info->regs;
-
-	ctrl_addr = addr + dev->info->reg_mib_cnt * port;
-	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
-
-	mutex_lock(&dev->alu_mutex);
-	ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-
-	/* It is almost guaranteed to always read the valid bit because of
-	 * slow SPI speed.
-	 */
-	for (loop = 2; loop > 0; loop--) {
-		ksz_read8(dev, regs[REG_IND_MIB_CHECK], &check);
-
-		if (check & masks[MIB_COUNTER_VALID]) {
-			ksz_read32(dev, regs[REG_IND_DATA_LO], &data);
-			if (check & masks[MIB_COUNTER_OVERFLOW])
-				*cnt += MIB_COUNTER_VALUE + 1;
-			*cnt += data & MIB_COUNTER_VALUE;
-			break;
-		}
-	}
-	mutex_unlock(&dev->alu_mutex);
-}
-
-static void ksz8795_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
-			      u64 *dropped, u64 *cnt)
-{
-	const u32 *masks;
-	const u16 *regs;
-	u16 ctrl_addr;
-	u32 data;
-	u8 check;
-	int loop;
-
-	masks = dev->info->masks;
-	regs = dev->info->regs;
-
-	addr -= dev->info->reg_mib_cnt;
-	ctrl_addr = (KSZ8795_MIB_TOTAL_RX_1 - KSZ8795_MIB_TOTAL_RX_0) * port;
-	ctrl_addr += addr + KSZ8795_MIB_TOTAL_RX_0;
-	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
-
-	mutex_lock(&dev->alu_mutex);
-	ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-
-	/* It is almost guaranteed to always read the valid bit because of
-	 * slow SPI speed.
-	 */
-	for (loop = 2; loop > 0; loop--) {
-		ksz_read8(dev, regs[REG_IND_MIB_CHECK], &check);
-
-		if (check & masks[MIB_COUNTER_VALID]) {
-			ksz_read32(dev, regs[REG_IND_DATA_LO], &data);
-			if (addr < 2) {
-				u64 total;
-
-				total = check & MIB_TOTAL_BYTES_H;
-				total <<= 32;
-				*cnt += total;
-				*cnt += data;
-				if (check & masks[MIB_COUNTER_OVERFLOW]) {
-					total = MIB_TOTAL_BYTES_H + 1;
-					total <<= 32;
-					*cnt += total;
-				}
-			} else {
-				if (check & masks[MIB_COUNTER_OVERFLOW])
-					*cnt += MIB_PACKET_DROPPED + 1;
-				*cnt += data & MIB_PACKET_DROPPED;
-			}
-			break;
-		}
-	}
-	mutex_unlock(&dev->alu_mutex);
-}
-
-static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
-			      u64 *dropped, u64 *cnt)
-{
-	u32 *last = (u32 *)dropped;
-	const u16 *regs;
-	u16 ctrl_addr;
-	u32 data;
-	u32 cur;
-
-	regs = dev->info->regs;
-
-	addr -= dev->info->reg_mib_cnt;
-	ctrl_addr = addr ? KSZ8863_MIB_PACKET_DROPPED_TX_0 :
-			   KSZ8863_MIB_PACKET_DROPPED_RX_0;
-	ctrl_addr += port;
-	ctrl_addr |= IND_ACC_TABLE(TABLE_MIB | TABLE_READ);
-
-	mutex_lock(&dev->alu_mutex);
-	ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-	ksz_read32(dev, regs[REG_IND_DATA_LO], &data);
-	mutex_unlock(&dev->alu_mutex);
-
-	data &= MIB_PACKET_DROPPED;
-	cur = last[addr];
-	if (data != cur) {
-		last[addr] = data;
-		if (data < cur)
-			data += MIB_PACKET_DROPPED + 1;
-		data -= cur;
-		*cnt += data;
-	}
-}
-
-void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr,
-		    u64 *dropped, u64 *cnt)
-{
-	if (is_ksz88xx(dev))
-		ksz8863_r_mib_pkt(dev, port, addr, dropped, cnt);
-	else
-		ksz8795_r_mib_pkt(dev, port, addr, dropped, cnt);
-}
-
-void ksz8_freeze_mib(struct ksz_device *dev, int port, bool freeze)
-{
-	if (is_ksz88xx(dev))
-		return;
-
-	/* enable the port for flush/freeze function */
-	if (freeze)
-		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true);
-	ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FREEZE, freeze);
-
-	/* disable the port after freeze is done */
-	if (!freeze)
-		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), false);
-}
-
-void ksz8_port_init_cnt(struct ksz_device *dev, int port)
-{
-	struct ksz_port_mib *mib = &dev->ports[port].mib;
-	u64 *dropped;
-
-	/* For KSZ8795 family. */
-	if (ksz_is_ksz87xx(dev)) {
-		/* flush all enabled port MIB counters */
-		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true);
-		ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FLUSH, true);
-		ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), false);
-	}
-
-	mib->cnt_ptr = 0;
-
-	/* Some ports may not have MIB counters before SWITCH_COUNTER_NUM. */
-	while (mib->cnt_ptr < dev->info->reg_mib_cnt) {
-		dev->dev_ops->r_mib_cnt(dev, port, mib->cnt_ptr,
-					&mib->counters[mib->cnt_ptr]);
-		++mib->cnt_ptr;
-	}
-
-	/* last one in storage */
-	dropped = &mib->counters[dev->info->mib_cnt];
-
-	/* Some ports may not have MIB counters after SWITCH_COUNTER_NUM. */
-	while (mib->cnt_ptr < dev->info->mib_cnt) {
-		dev->dev_ops->r_mib_pkt(dev, port, mib->cnt_ptr,
-					dropped, &mib->counters[mib->cnt_ptr]);
-		++mib->cnt_ptr;
-	}
-}
-
-static int ksz8_r_table(struct ksz_device *dev, int table, u16 addr, u64 *data)
-{
-	const u16 *regs;
-	u16 ctrl_addr;
-	int ret;
-
-	regs = dev->info->regs;
-
-	ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr;
-
-	mutex_lock(&dev->alu_mutex);
-	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-	if (ret)
-		goto unlock_alu;
-
-	ret = ksz_read64(dev, regs[REG_IND_DATA_HI], data);
-unlock_alu:
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-static int ksz8_w_table(struct ksz_device *dev, int table, u16 addr, u64 data)
-{
-	const u16 *regs;
-	u16 ctrl_addr;
-	int ret;
-
-	regs = dev->info->regs;
-
-	ctrl_addr = IND_ACC_TABLE(table) | addr;
-
-	mutex_lock(&dev->alu_mutex);
-	ret = ksz_write64(dev, regs[REG_IND_DATA_HI], data);
-	if (ret)
-		goto unlock_alu;
-
-	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-unlock_alu:
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-static int ksz8_valid_dyn_entry(struct ksz_device *dev, u8 *data)
-{
-	int timeout = 100;
-	const u32 *masks;
-	const u16 *regs;
-	int ret;
-
-	masks = dev->info->masks;
-	regs = dev->info->regs;
-
-	do {
-		ret = ksz_read8(dev, regs[REG_IND_DATA_CHECK], data);
-		if (ret)
-			return ret;
-
-		timeout--;
-	} while ((*data & masks[DYNAMIC_MAC_TABLE_NOT_READY]) && timeout);
-
-	/* Entry is not ready for accessing. */
-	if (*data & masks[DYNAMIC_MAC_TABLE_NOT_READY])
-		return -ETIMEDOUT;
-
-	/* Entry is ready for accessing. */
-	return ksz_read8(dev, regs[REG_IND_DATA_8], data);
-}
-
-static int ksz8_r_dyn_mac_table(struct ksz_device *dev, u16 addr, u8 *mac_addr,
-				u8 *fid, u8 *src_port, u16 *entries)
-{
-	u32 data_hi, data_lo;
-	const u8 *shifts;
-	const u32 *masks;
-	const u16 *regs;
-	u16 ctrl_addr;
-	u64 buf = 0;
-	u8 data;
-	int cnt;
-	int ret;
-
-	shifts = dev->info->shifts;
-	masks = dev->info->masks;
-	regs = dev->info->regs;
-
-	ctrl_addr = IND_ACC_TABLE(TABLE_DYNAMIC_MAC | TABLE_READ) | addr;
-
-	mutex_lock(&dev->alu_mutex);
-	ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr);
-	if (ret)
-		goto unlock_alu;
-
-	ret = ksz8_valid_dyn_entry(dev, &data);
-	if (ret)
-		goto unlock_alu;
-
-	if (data & masks[DYNAMIC_MAC_TABLE_MAC_EMPTY]) {
-		*entries = 0;
-		goto unlock_alu;
-	}
-
-	ret = ksz_read64(dev, regs[REG_IND_DATA_HI], &buf);
-	if (ret)
-		goto unlock_alu;
-
-	data_hi = (u32)(buf >> 32);
-	data_lo = (u32)buf;
-
-	/* Check out how many valid entry in the table. */
-	cnt = data & masks[DYNAMIC_MAC_TABLE_ENTRIES_H];
-	cnt <<= shifts[DYNAMIC_MAC_ENTRIES_H];
-	cnt |= (data_hi & masks[DYNAMIC_MAC_TABLE_ENTRIES]) >>
-		shifts[DYNAMIC_MAC_ENTRIES];
-	*entries = cnt + 1;
-
-	*fid = (data_hi & masks[DYNAMIC_MAC_TABLE_FID]) >>
-		shifts[DYNAMIC_MAC_FID];
-	*src_port = (data_hi & masks[DYNAMIC_MAC_TABLE_SRC_PORT]) >>
-		shifts[DYNAMIC_MAC_SRC_PORT];
-
-	mac_addr[5] = (u8)data_lo;
-	mac_addr[4] = (u8)(data_lo >> 8);
-	mac_addr[3] = (u8)(data_lo >> 16);
-	mac_addr[2] = (u8)(data_lo >> 24);
-
-	mac_addr[1] = (u8)data_hi;
-	mac_addr[0] = (u8)(data_hi >> 8);
-
-unlock_alu:
-	mutex_unlock(&dev->alu_mutex);
-
-	return ret;
-}
-
-static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr,
-				struct alu_struct *alu, bool *valid)
-{
-	u32 data_hi, data_lo;
-	const u8 *shifts;
-	const u32 *masks;
-	u64 data;
-	int ret;
-
-	shifts = dev->info->shifts;
-	masks = dev->info->masks;
-
-	ret = ksz8_r_table(dev, TABLE_STATIC_MAC, addr, &data);
-	if (ret)
-		return ret;
-
-	data_hi = data >> 32;
-	data_lo = (u32)data;
-
-	if (!(data_hi & (masks[STATIC_MAC_TABLE_VALID] |
-			 masks[STATIC_MAC_TABLE_OVERRIDE]))) {
-		*valid = false;
-		return 0;
-	}
-
-	alu->mac[5] = (u8)data_lo;
-	alu->mac[4] = (u8)(data_lo >> 8);
-	alu->mac[3] = (u8)(data_lo >> 16);
-	alu->mac[2] = (u8)(data_lo >> 24);
-	alu->mac[1] = (u8)data_hi;
-	alu->mac[0] = (u8)(data_hi >> 8);
-	alu->port_forward =
-		(data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >>
-			shifts[STATIC_MAC_FWD_PORTS];
-	alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0;
-
-	/* KSZ8795/KSZ8895 family switches have STATIC_MAC_TABLE_USE_FID and
-	 * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the
-	 * static MAC table compared to doing write.
-	 */
-	if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev))
-		data_hi >>= 1;
-	alu->is_static = true;
-	alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0;
-	alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >>
-		shifts[STATIC_MAC_FID];
-
-	*valid = true;
-
-	return 0;
-}
-
-static int ksz8_w_sta_mac_table(struct ksz_device *dev, u16 addr,
-				struct alu_struct *alu)
-{
-	u32 data_hi, data_lo;
-	const u8 *shifts;
-	const u32 *masks;
-	u64 data;
-
-	shifts = dev->info->shifts;
-	masks = dev->info->masks;
-
-	data_lo = ((u32)alu->mac[2] << 24) |
-		((u32)alu->mac[3] << 16) |
-		((u32)alu->mac[4] << 8) | alu->mac[5];
-	data_hi = ((u32)alu->mac[0] << 8) | alu->mac[1];
-	data_hi |= (u32)alu->port_forward << shifts[STATIC_MAC_FWD_PORTS];
-
-	if (alu->is_override)
-		data_hi |= masks[STATIC_MAC_TABLE_OVERRIDE];
-	if (alu->is_use_fid) {
-		data_hi |= masks[STATIC_MAC_TABLE_USE_FID];
-		data_hi |= (u32)alu->fid << shifts[STATIC_MAC_FID];
-	}
-	if (alu->is_static)
-		data_hi |= masks[STATIC_MAC_TABLE_VALID];
-	else
-		data_hi &= ~masks[STATIC_MAC_TABLE_OVERRIDE];
-
-	data = (u64)data_hi << 32 | data_lo;
-
-	return ksz8_w_table(dev, TABLE_STATIC_MAC, addr, data);
-}
-
-static void ksz8_from_vlan(struct ksz_device *dev, u32 vlan, u8 *fid,
-			   u8 *member, u8 *valid)
-{
-	const u8 *shifts;
-	const u32 *masks;
-
-	shifts = dev->info->shifts;
-	masks = dev->info->masks;
-
-	*fid = vlan & masks[VLAN_TABLE_FID];
-	*member = (vlan & masks[VLAN_TABLE_MEMBERSHIP]) >>
-			shifts[VLAN_TABLE_MEMBERSHIP_S];
-	*valid = !!(vlan & masks[VLAN_TABLE_VALID]);
-}
-
-static void ksz8_to_vlan(struct ksz_device *dev, u8 fid, u8 member, u8 valid,
-			 u16 *vlan)
-{
-	const u8 *shifts;
-	const u32 *masks;
-
-	shifts = dev->info->shifts;
-	masks = dev->info->masks;
-
-	*vlan = fid;
-	*vlan |= (u16)member << shifts[VLAN_TABLE_MEMBERSHIP_S];
-	if (valid)
-		*vlan |= masks[VLAN_TABLE_VALID];
-}
-
-static void ksz8_r_vlan_entries(struct ksz_device *dev, u16 addr)
-{
-	const u8 *shifts;
-	u64 data;
-	int i;
-
-	shifts = dev->info->shifts;
-
-	ksz8_r_table(dev, TABLE_VLAN, addr, &data);
-	addr *= 4;
-	for (i = 0; i < 4; i++) {
-		dev->vlan_cache[addr + i].table[0] = (u16)data;
-		data >>= shifts[VLAN_TABLE];
-	}
-}
-
-static void ksz8_r_vlan_table(struct ksz_device *dev, u16 vid, u16 *vlan)
-{
-	int index;
-	u16 *data;
-	u16 addr;
-	u64 buf;
-
-	data = (u16 *)&buf;
-	addr = vid / 4;
-	index = vid & 3;
-	ksz8_r_table(dev, TABLE_VLAN, addr, &buf);
-	*vlan = data[index];
-}
-
-static void ksz8_w_vlan_table(struct ksz_device *dev, u16 vid, u16 vlan)
-{
-	int index;
-	u16 *data;
-	u16 addr;
-	u64 buf;
-
-	data = (u16 *)&buf;
-	addr = vid / 4;
-	index = vid & 3;
-	ksz8_r_table(dev, TABLE_VLAN, addr, &buf);
-	data[index] = vlan;
-	dev->vlan_cache[vid].table[0] = vlan;
-	ksz8_w_table(dev, TABLE_VLAN, addr, buf);
-}
-
-/**
- * ksz879x_get_loopback - KSZ879x specific function to get loopback
- *                        configuration status for a specific port
- * @dev: Pointer to the device structure
- * @port: Port number to query
- * @val: Pointer to store the result
- *
- * This function reads the SMI registers to determine whether loopback mode
- * is enabled for a specific port.
- *
- * Return: 0 on success, error code on failure.
- */
-static int ksz879x_get_loopback(struct ksz_device *dev, u16 port,
-				u16 *val)
-{
-	u8 stat3;
-	int ret;
-
-	ret = ksz_pread8(dev, port, REG_PORT_STATUS_3, &stat3);
-	if (ret)
-		return ret;
-
-	if (stat3 & PORT_PHY_LOOPBACK)
-		*val |= BMCR_LOOPBACK;
-
-	return 0;
-}
-
-/**
- * ksz879x_set_loopback - KSZ879x specific function  to set loopback mode for
- *			  a specific port
- * @dev: Pointer to the device structure.
- * @port: Port number to modify.
- * @val: Value indicating whether to enable or disable loopback mode.
- *
- * This function translates loopback bit of the BMCR register into the
- * corresponding hardware register bit value and writes it to the SMI interface.
- *
- * Return: 0 on success, error code on failure.
- */
-static int ksz879x_set_loopback(struct ksz_device *dev, u16 port, u16 val)
-{
-	u8 stat3 = 0;
-
-	if (val & BMCR_LOOPBACK)
-		stat3 |= PORT_PHY_LOOPBACK;
-
-	return ksz_prmw8(dev, port, REG_PORT_STATUS_3, PORT_PHY_LOOPBACK,
-			 stat3);
-}
-
-/**
- * ksz8_r_phy_ctrl - Translates and reads from the SMI interface to a MIIM PHY
- *		     Control register (Reg. 31).
- * @dev: The KSZ device instance.
- * @port: The port number to be read.
- * @val: The value read from the SMI interface.
- *
- * This function reads the SMI interface and translates the hardware register
- * bit values into their corresponding control settings for a MIIM PHY Control
- * register.
- *
- * Return: 0 on success, error code on failure.
- */
-static int ksz8_r_phy_ctrl(struct ksz_device *dev, int port, u16 *val)
-{
-	const u16 *regs = dev->info->regs;
-	u8 reg_val;
-	int ret;
-
-	*val = 0;
-
-	ret = ksz_pread8(dev, port, regs[P_LINK_STATUS], &reg_val);
-	if (ret < 0)
-		return ret;
-
-	if (reg_val & PORT_MDIX_STATUS)
-		*val |= KSZ886X_CTRL_MDIX_STAT;
-
-	ret = ksz_pread8(dev, port, REG_PORT_LINK_MD_CTRL, &reg_val);
-	if (ret < 0)
-		return ret;
-
-	if (reg_val & PORT_FORCE_LINK)
-		*val |= KSZ886X_CTRL_FORCE_LINK;
-
-	if (reg_val & PORT_POWER_SAVING)
-		*val |= KSZ886X_CTRL_PWRSAVE;
-
-	if (reg_val & PORT_PHY_REMOTE_LOOPBACK)
-		*val |= KSZ886X_CTRL_REMOTE_LOOPBACK;
-
-	return 0;
-}
-
-/**
- * ksz8_r_phy_bmcr - Translates and reads from the SMI interface to a MIIM PHY
- *		     Basic mode control register (Reg. 0).
- * @dev: The KSZ device instance.
- * @port: The port number to be read.
- * @val: The value read from the SMI interface.
- *
- * This function reads the SMI interface and translates the hardware register
- * bit values into their corresponding control settings for a MIIM PHY Basic
- * mode control register.
- *
- * MIIM Bit Mapping Comparison between KSZ8794 and KSZ8873
- * -------------------------------------------------------------------
- * MIIM Bit                    | KSZ8794 Reg/Bit             | KSZ8873 Reg/Bit
- * ----------------------------+-----------------------------+----------------
- * Bit 15 - Soft Reset         | 0xF/4                       | Not supported
- * Bit 14 - Loopback           | 0xD/0 (MAC), 0xF/7 (PHY)    ~ 0xD/0 (PHY)
- * Bit 13 - Force 100          | 0xC/6                       = 0xC/6
- * Bit 12 - AN Enable          | 0xC/7 (reverse logic)       ~ 0xC/7
- * Bit 11 - Power Down         | 0xD/3                       = 0xD/3
- * Bit 10 - PHY Isolate        | 0xF/5                       | Not supported
- * Bit 9 - Restart AN          | 0xD/5                       = 0xD/5
- * Bit 8 - Force Full-Duplex   | 0xC/5                       = 0xC/5
- * Bit 7 - Collision Test/Res. | Not supported               | Not supported
- * Bit 6 - Reserved            | Not supported               | Not supported
- * Bit 5 - Hp_mdix             | 0x9/7                       ~ 0xF/7
- * Bit 4 - Force MDI           | 0xD/1                       = 0xD/1
- * Bit 3 - Disable MDIX        | 0xD/2                       = 0xD/2
- * Bit 2 - Disable Far-End F.  | ????                        | 0xD/4
- * Bit 1 - Disable Transmit    | 0xD/6                       = 0xD/6
- * Bit 0 - Disable LED         | 0xD/7                       = 0xD/7
- * -------------------------------------------------------------------
- *
- * Return: 0 on success, error code on failure.
- */
-static int ksz8_r_phy_bmcr(struct ksz_device *dev, u16 port, u16 *val)
-{
-	const u16 *regs = dev->info->regs;
-	u8 restart, speed, ctrl;
-	int ret;
-
-	*val = 0;
-
-	ret = ksz_pread8(dev, port, regs[P_NEG_RESTART_CTRL], &restart);
-	if (ret)
-		return ret;
-
-	ret = ksz_pread8(dev, port, regs[P_SPEED_STATUS], &speed);
-	if (ret)
-		return ret;
-
-	ret = ksz_pread8(dev, port, regs[P_FORCE_CTRL], &ctrl);
-	if (ret)
-		return ret;
-
-	if (ctrl & PORT_FORCE_100_MBIT)
-		*val |= BMCR_SPEED100;
-
-	if (ksz_is_ksz88x3(dev)) {
-		if (restart & KSZ8873_PORT_PHY_LOOPBACK)
-			*val |= BMCR_LOOPBACK;
-
-		if ((ctrl & PORT_AUTO_NEG_ENABLE))
-			*val |= BMCR_ANENABLE;
-	} else {
-		ret = ksz879x_get_loopback(dev, port, val);
-		if (ret)
-			return ret;
-
-		if (!(ctrl & PORT_AUTO_NEG_DISABLE))
-			*val |= BMCR_ANENABLE;
-	}
-
-	if (restart & PORT_POWER_DOWN)
-		*val |= BMCR_PDOWN;
-
-	if (restart & PORT_AUTO_NEG_RESTART)
-		*val |= BMCR_ANRESTART;
-
-	if (ctrl & PORT_FORCE_FULL_DUPLEX)
-		*val |= BMCR_FULLDPLX;
-
-	if (speed & PORT_HP_MDIX)
-		*val |= KSZ886X_BMCR_HP_MDIX;
-
-	if (restart & PORT_FORCE_MDIX)
-		*val |= KSZ886X_BMCR_FORCE_MDI;
-
-	if (restart & PORT_AUTO_MDIX_DISABLE)
-		*val |= KSZ886X_BMCR_DISABLE_AUTO_MDIX;
-
-	if (restart & PORT_TX_DISABLE)
-		*val |= KSZ886X_BMCR_DISABLE_TRANSMIT;
-
-	if (restart & PORT_LED_OFF)
-		*val |= KSZ886X_BMCR_DISABLE_LED;
-
-	return 0;
-}
-
-int ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val)
-{
-	u8 ctrl, link, val1, val2;
-	int processed = true;
-	const u16 *regs;
-	u16 data = 0;
-	u16 p = phy;
-	int ret;
-
-	regs = dev->info->regs;
-
-	switch (reg) {
-	case MII_BMCR:
-		ret = ksz8_r_phy_bmcr(dev, p, &data);
-		if (ret)
-			return ret;
-		break;
-	case MII_BMSR:
-		ret = ksz_pread8(dev, p, regs[P_LINK_STATUS], &link);
-		if (ret)
-			return ret;
-
-		data = BMSR_100FULL |
-		       BMSR_100HALF |
-		       BMSR_10FULL |
-		       BMSR_10HALF |
-		       BMSR_ANEGCAPABLE;
-		if (link & PORT_AUTO_NEG_COMPLETE)
-			data |= BMSR_ANEGCOMPLETE;
-		if (link & PORT_STAT_LINK_GOOD)
-			data |= BMSR_LSTATUS;
-		break;
-	case MII_PHYSID1:
-		data = KSZ8795_ID_HI;
-		break;
-	case MII_PHYSID2:
-		if (ksz_is_ksz88x3(dev))
-			data = KSZ8863_ID_LO;
-		else
-			data = KSZ8795_ID_LO;
-		break;
-	case MII_ADVERTISE:
-		ret = ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl);
-		if (ret)
-			return ret;
-
-		data = ADVERTISE_CSMA;
-		if (ctrl & PORT_AUTO_NEG_SYM_PAUSE)
-			data |= ADVERTISE_PAUSE_CAP;
-		if (ctrl & PORT_AUTO_NEG_100BTX_FD)
-			data |= ADVERTISE_100FULL;
-		if (ctrl & PORT_AUTO_NEG_100BTX)
-			data |= ADVERTISE_100HALF;
-		if (ctrl & PORT_AUTO_NEG_10BT_FD)
-			data |= ADVERTISE_10FULL;
-		if (ctrl & PORT_AUTO_NEG_10BT)
-			data |= ADVERTISE_10HALF;
-		break;
-	case MII_LPA:
-		ret = ksz_pread8(dev, p, regs[P_REMOTE_STATUS], &link);
-		if (ret)
-			return ret;
-
-		data = LPA_SLCT;
-		if (link & PORT_REMOTE_SYM_PAUSE)
-			data |= LPA_PAUSE_CAP;
-		if (link & PORT_REMOTE_100BTX_FD)
-			data |= LPA_100FULL;
-		if (link & PORT_REMOTE_100BTX)
-			data |= LPA_100HALF;
-		if (link & PORT_REMOTE_10BT_FD)
-			data |= LPA_10FULL;
-		if (link & PORT_REMOTE_10BT)
-			data |= LPA_10HALF;
-		if (data & ~LPA_SLCT)
-			data |= LPA_LPACK;
-		break;
-	case PHY_REG_LINK_MD:
-		ret = ksz_pread8(dev, p, REG_PORT_LINK_MD_CTRL, &val1);
-		if (ret)
-			return ret;
-
-		ret = ksz_pread8(dev, p, REG_PORT_LINK_MD_RESULT, &val2);
-		if (ret)
-			return ret;
-
-		if (val1 & PORT_START_CABLE_DIAG)
-			data |= PHY_START_CABLE_DIAG;
-
-		if (val1 & PORT_CABLE_10M_SHORT)
-			data |= PHY_CABLE_10M_SHORT;
-
-		data |= FIELD_PREP(PHY_CABLE_DIAG_RESULT_M,
-				FIELD_GET(PORT_CABLE_DIAG_RESULT_M, val1));
-
-		data |= FIELD_PREP(PHY_CABLE_FAULT_COUNTER_M,
-				(FIELD_GET(PORT_CABLE_FAULT_COUNTER_H, val1) << 8) |
-				FIELD_GET(PORT_CABLE_FAULT_COUNTER_L, val2));
-		break;
-	case PHY_REG_PHY_CTRL:
-		ret = ksz8_r_phy_ctrl(dev, p, &data);
-		if (ret)
-			return ret;
-
-		break;
-	default:
-		processed = false;
-		break;
-	}
-	if (processed)
-		*val = data;
-
-	return 0;
-}
-
-/**
- * ksz8_w_phy_ctrl - Translates and writes to the SMI interface from a MIIM PHY
- *		     Control register (Reg. 31).
- * @dev: The KSZ device instance.
- * @port: The port number to be configured.
- * @val: The register value to be written.
- *
- * This function translates control settings from a MIIM PHY Control register
- * into their corresponding hardware register bit values for the SMI
- * interface.
- *
- * Return: 0 on success, error code on failure.
- */
-static int ksz8_w_phy_ctrl(struct ksz_device *dev, int port, u16 val)
-{
-	u8 reg_val = 0;
-	int ret;
-
-	if (val & KSZ886X_CTRL_FORCE_LINK)
-		reg_val |= PORT_FORCE_LINK;
-
-	if (val & KSZ886X_CTRL_PWRSAVE)
-		reg_val |= PORT_POWER_SAVING;
-
-	if (val & KSZ886X_CTRL_REMOTE_LOOPBACK)
-		reg_val |= PORT_PHY_REMOTE_LOOPBACK;
-
-	ret = ksz_prmw8(dev, port, REG_PORT_LINK_MD_CTRL, PORT_FORCE_LINK |
-			PORT_POWER_SAVING | PORT_PHY_REMOTE_LOOPBACK, reg_val);
-	return ret;
-}
-
-/**
- * ksz8_w_phy_bmcr - Translates and writes to the SMI interface from a MIIM PHY
- *		     Basic mode control register (Reg. 0).
- * @dev: The KSZ device instance.
- * @port: The port number to be configured.
- * @val: The register value to be written.
- *
- * This function translates control settings from a MIIM PHY Basic mode control
- * register into their corresponding hardware register bit values for the SMI
- * interface.
- *
- * MIIM Bit Mapping Comparison between KSZ8794 and KSZ8873
- * -------------------------------------------------------------------
- * MIIM Bit                    | KSZ8794 Reg/Bit             | KSZ8873 Reg/Bit
- * ----------------------------+-----------------------------+----------------
- * Bit 15 - Soft Reset         | 0xF/4                       | Not supported
- * Bit 14 - Loopback           | 0xD/0 (MAC), 0xF/7 (PHY)    ~ 0xD/0 (PHY)
- * Bit 13 - Force 100          | 0xC/6                       = 0xC/6
- * Bit 12 - AN Enable          | 0xC/7 (reverse logic)       ~ 0xC/7
- * Bit 11 - Power Down         | 0xD/3                       = 0xD/3
- * Bit 10 - PHY Isolate        | 0xF/5                       | Not supported
- * Bit 9 - Restart AN          | 0xD/5                       = 0xD/5
- * Bit 8 - Force Full-Duplex   | 0xC/5                       = 0xC/5
- * Bit 7 - Collision Test/Res. | Not supported               | Not supported
- * Bit 6 - Reserved            | Not supported               | Not supported
- * Bit 5 - Hp_mdix             | 0x9/7                       ~ 0xF/7
- * Bit 4 - Force MDI           | 0xD/1                       = 0xD/1
- * Bit 3 - Disable MDIX        | 0xD/2                       = 0xD/2
- * Bit 2 - Disable Far-End F.  | ????                        | 0xD/4
- * Bit 1 - Disable Transmit    | 0xD/6                       = 0xD/6
- * Bit 0 - Disable LED         | 0xD/7                       = 0xD/7
- * -------------------------------------------------------------------
- *
- * Return: 0 on success, error code on failure.
- */
-static int ksz8_w_phy_bmcr(struct ksz_device *dev, u16 port, u16 val)
-{
-	u8 restart, speed, ctrl, restart_mask;
-	const u16 *regs = dev->info->regs;
-	int ret;
-
-	/* Do not support PHY reset function. */
-	if (val & BMCR_RESET)
-		return 0;
-
-	speed = 0;
-	if (val & KSZ886X_BMCR_HP_MDIX)
-		speed |= PORT_HP_MDIX;
-
-	ret = ksz_prmw8(dev, port, regs[P_SPEED_STATUS], PORT_HP_MDIX, speed);
-	if (ret)
-		return ret;
-
-	ctrl = 0;
-	if (ksz_is_ksz88x3(dev)) {
-		if ((val & BMCR_ANENABLE))
-			ctrl |= PORT_AUTO_NEG_ENABLE;
-	} else {
-		if (!(val & BMCR_ANENABLE))
-			ctrl |= PORT_AUTO_NEG_DISABLE;
-
-		/* Fiber port does not support auto-negotiation. */
-		if (dev->ports[port].fiber)
-			ctrl |= PORT_AUTO_NEG_DISABLE;
-	}
-
-	if (val & BMCR_SPEED100)
-		ctrl |= PORT_FORCE_100_MBIT;
-
-	if (val & BMCR_FULLDPLX)
-		ctrl |= PORT_FORCE_FULL_DUPLEX;
-
-	ret = ksz_prmw8(dev, port, regs[P_FORCE_CTRL], PORT_FORCE_100_MBIT |
-		 /* PORT_AUTO_NEG_ENABLE and PORT_AUTO_NEG_DISABLE are the same
-		  * bits
-		  */
-		 PORT_FORCE_FULL_DUPLEX | PORT_AUTO_NEG_ENABLE, ctrl);
-	if (ret)
-		return ret;
-
-	restart = 0;
-	restart_mask = PORT_LED_OFF | PORT_TX_DISABLE | PORT_AUTO_NEG_RESTART |
-		PORT_POWER_DOWN | PORT_AUTO_MDIX_DISABLE | PORT_FORCE_MDIX;
-
-	if (val & KSZ886X_BMCR_DISABLE_LED)
-		restart |= PORT_LED_OFF;
-
-	if (val & KSZ886X_BMCR_DISABLE_TRANSMIT)
-		restart |= PORT_TX_DISABLE;
-
-	if (val & BMCR_ANRESTART)
-		restart |= PORT_AUTO_NEG_RESTART;
-
-	if (val & BMCR_PDOWN)
-		restart |= PORT_POWER_DOWN;
-
-	if (val & KSZ886X_BMCR_DISABLE_AUTO_MDIX)
-		restart |= PORT_AUTO_MDIX_DISABLE;
-
-	if (val & KSZ886X_BMCR_FORCE_MDI)
-		restart |= PORT_FORCE_MDIX;
-
-	if (ksz_is_ksz88x3(dev)) {
-		restart_mask |= KSZ8873_PORT_PHY_LOOPBACK;
-
-		if (val & BMCR_LOOPBACK)
-			restart |= KSZ8873_PORT_PHY_LOOPBACK;
-	} else {
-		ret = ksz879x_set_loopback(dev, port, val);
-		if (ret)
-			return ret;
-	}
-
-	return ksz_prmw8(dev, port, regs[P_NEG_RESTART_CTRL], restart_mask,
-			 restart);
-}
-
-int ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
-{
-	const u16 *regs;
-	u8 ctrl, data;
-	u16 p = phy;
-	int ret;
-
-	regs = dev->info->regs;
-
-	switch (reg) {
-	case MII_BMCR:
-		ret = ksz8_w_phy_bmcr(dev, p, val);
-		if (ret)
-			return ret;
-		break;
-	case MII_ADVERTISE:
-		ret = ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl);
-		if (ret)
-			return ret;
-
-		data = ctrl;
-		data &= ~(PORT_AUTO_NEG_SYM_PAUSE |
-			  PORT_AUTO_NEG_100BTX_FD |
-			  PORT_AUTO_NEG_100BTX |
-			  PORT_AUTO_NEG_10BT_FD |
-			  PORT_AUTO_NEG_10BT);
-		if (val & ADVERTISE_PAUSE_CAP)
-			data |= PORT_AUTO_NEG_SYM_PAUSE;
-		if (val & ADVERTISE_100FULL)
-			data |= PORT_AUTO_NEG_100BTX_FD;
-		if (val & ADVERTISE_100HALF)
-			data |= PORT_AUTO_NEG_100BTX;
-		if (val & ADVERTISE_10FULL)
-			data |= PORT_AUTO_NEG_10BT_FD;
-		if (val & ADVERTISE_10HALF)
-			data |= PORT_AUTO_NEG_10BT;
-
-		if (data != ctrl) {
-			ret = ksz_pwrite8(dev, p, regs[P_LOCAL_CTRL], data);
-			if (ret)
-				return ret;
-		}
-		break;
-	case PHY_REG_LINK_MD:
-		if (val & PHY_START_CABLE_DIAG)
-			ksz_port_cfg(dev, p, REG_PORT_LINK_MD_CTRL, PORT_START_CABLE_DIAG, true);
-		break;
-
-	case PHY_REG_PHY_CTRL:
-		ret = ksz8_w_phy_ctrl(dev, p, val);
-		if (ret)
-			return ret;
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member)
-{
-	u8 data;
-
-	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
-	data &= ~PORT_VLAN_MEMBERSHIP;
-	data |= (member & dev->port_mask);
-	ksz_pwrite8(dev, port, P_MIRROR_CTRL, data);
-}
-
-void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port)
-{
-	u8 learn[DSA_MAX_PORTS];
-	int first, index, cnt;
-	const u16 *regs;
-
-	regs = dev->info->regs;
-
-	if ((uint)port < dev->info->port_cnt) {
-		first = port;
-		cnt = port + 1;
-	} else {
-		/* Flush all ports. */
-		first = 0;
-		cnt = dev->info->port_cnt;
-	}
-	for (index = first; index < cnt; index++) {
-		ksz_pread8(dev, index, regs[P_STP_CTRL], &learn[index]);
-		if (!(learn[index] & PORT_LEARN_DISABLE))
-			ksz_pwrite8(dev, index, regs[P_STP_CTRL],
-				    learn[index] | PORT_LEARN_DISABLE);
-	}
-	ksz_cfg(dev, S_FLUSH_TABLE_CTRL, SW_FLUSH_DYN_MAC_TABLE, true);
-	for (index = first; index < cnt; index++) {
-		if (!(learn[index] & PORT_LEARN_DISABLE))
-			ksz_pwrite8(dev, index, regs[P_STP_CTRL], learn[index]);
-	}
-}
-
-int ksz8_fdb_dump(struct ksz_device *dev, int port,
-		  dsa_fdb_dump_cb_t *cb, void *data)
-{
-	u8 mac[ETH_ALEN];
-	u8 src_port, fid;
-	u16 entries = 0;
-	int ret, i;
-
-	for (i = 0; i < KSZ8_DYN_MAC_ENTRIES; i++) {
-		ret = ksz8_r_dyn_mac_table(dev, i, mac, &fid, &src_port,
-					   &entries);
-		if (ret)
-			return ret;
-
-		if (i >= entries)
-			return 0;
-
-		if (port == src_port) {
-			ret = cb(mac, fid, false, data);
-			if (ret)
-				return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int ksz8_add_sta_mac(struct ksz_device *dev, int port,
-			    const unsigned char *addr, u16 vid)
-{
-	struct alu_struct alu;
-	int index, ret;
-	int empty = 0;
-
-	alu.port_forward = 0;
-	for (index = 0; index < dev->info->num_statics; index++) {
-		bool valid;
-
-		ret = ksz8_r_sta_mac_table(dev, index, &alu, &valid);
-		if (ret)
-			return ret;
-		if (!valid) {
-			/* Remember the first empty entry. */
-			if (!empty)
-				empty = index + 1;
-			continue;
-		}
-
-		if (!memcmp(alu.mac, addr, ETH_ALEN) && alu.fid == vid)
-			break;
-	}
-
-	/* no available entry */
-	if (index == dev->info->num_statics && !empty)
-		return -ENOSPC;
-
-	/* add entry */
-	if (index == dev->info->num_statics) {
-		index = empty - 1;
-		memset(&alu, 0, sizeof(alu));
-		memcpy(alu.mac, addr, ETH_ALEN);
-		alu.is_static = true;
-	}
-	alu.port_forward |= BIT(port);
-	if (vid) {
-		alu.is_use_fid = true;
-
-		/* Need a way to map VID to FID. */
-		alu.fid = vid;
-	}
-
-	return ksz8_w_sta_mac_table(dev, index, &alu);
-}
-
-static int ksz8_del_sta_mac(struct ksz_device *dev, int port,
-			    const unsigned char *addr, u16 vid)
-{
-	struct alu_struct alu;
-	int index, ret;
-
-	for (index = 0; index < dev->info->num_statics; index++) {
-		bool valid;
-
-		ret = ksz8_r_sta_mac_table(dev, index, &alu, &valid);
-		if (ret)
-			return ret;
-		if (!valid)
-			continue;
-
-		if (!memcmp(alu.mac, addr, ETH_ALEN) && alu.fid == vid)
-			break;
-	}
-
-	/* no available entry */
-	if (index == dev->info->num_statics)
-		return 0;
-
-	/* clear port */
-	alu.port_forward &= ~BIT(port);
-	if (!alu.port_forward)
-		alu.is_static = false;
-
-	return ksz8_w_sta_mac_table(dev, index, &alu);
-}
-
-int ksz8_mdb_add(struct ksz_device *dev, int port,
-		 const struct switchdev_obj_port_mdb *mdb, struct dsa_db db)
-{
-	return ksz8_add_sta_mac(dev, port, mdb->addr, mdb->vid);
-}
-
-int ksz8_mdb_del(struct ksz_device *dev, int port,
-		 const struct switchdev_obj_port_mdb *mdb, struct dsa_db db)
-{
-	return ksz8_del_sta_mac(dev, port, mdb->addr, mdb->vid);
-}
-
-int ksz8_fdb_add(struct ksz_device *dev, int port, const unsigned char *addr,
-		 u16 vid, struct dsa_db db)
-{
-	return ksz8_add_sta_mac(dev, port, addr, vid);
-}
-
-int ksz8_fdb_del(struct ksz_device *dev, int port, const unsigned char *addr,
-		 u16 vid, struct dsa_db db)
-{
-	return ksz8_del_sta_mac(dev, port, addr, vid);
-}
-
-int ksz8_port_vlan_filtering(struct ksz_device *dev, int port, bool flag,
-			     struct netlink_ext_ack *extack)
-{
-	if (ksz_is_ksz88x3(dev))
-		return -ENOTSUPP;
-
-	/* Discard packets with VID not enabled on the switch */
-	ksz_cfg(dev, S_MIRROR_CTRL, SW_VLAN_ENABLE, flag);
-
-	/* Discard packets with VID not enabled on the ingress port */
-	for (port = 0; port < dev->phy_port_cnt; ++port)
-		ksz_port_cfg(dev, port, REG_PORT_CTRL_2, PORT_INGRESS_FILTER,
-			     flag);
-
-	return 0;
-}
-
-static void ksz8_port_enable_pvid(struct ksz_device *dev, int port, bool state)
-{
-	if (ksz_is_ksz88x3(dev)) {
-		ksz_cfg(dev, REG_SW_INSERT_SRC_PVID,
-			0x03 << (4 - 2 * port), state);
-	} else {
-		ksz_pwrite8(dev, port, REG_PORT_CTRL_12, state ? 0x0f : 0x00);
-	}
-}
-
-int ksz8_port_vlan_add(struct ksz_device *dev, int port,
-		       const struct switchdev_obj_port_vlan *vlan,
-		       struct netlink_ext_ack *extack)
-{
-	bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
-	struct ksz_port *p = &dev->ports[port];
-	u16 data, new_pvid = 0;
-	u8 fid, member, valid;
-
-	if (ksz_is_ksz88x3(dev))
-		return -ENOTSUPP;
-
-	/* If a VLAN is added with untagged flag different from the
-	 * port's Remove Tag flag, we need to change the latter.
-	 * Ignore VID 0, which is always untagged.
-	 * Ignore CPU port, which will always be tagged.
-	 */
-	if (untagged != p->remove_tag && vlan->vid != 0 &&
-	    port != dev->cpu_port) {
-		unsigned int vid;
-
-		/* Reject attempts to add a VLAN that requires the
-		 * Remove Tag flag to be changed, unless there are no
-		 * other VLANs currently configured.
-		 */
-		for (vid = 1; vid < dev->info->num_vlans; ++vid) {
-			/* Skip the VID we are going to add or reconfigure */
-			if (vid == vlan->vid)
-				continue;
-
-			ksz8_from_vlan(dev, dev->vlan_cache[vid].table[0],
-				       &fid, &member, &valid);
-			if (valid && (member & BIT(port)))
-				return -EINVAL;
-		}
-
-		ksz_port_cfg(dev, port, P_TAG_CTRL, PORT_REMOVE_TAG, untagged);
-		p->remove_tag = untagged;
-	}
-
-	ksz8_r_vlan_table(dev, vlan->vid, &data);
-	ksz8_from_vlan(dev, data, &fid, &member, &valid);
-
-	/* First time to setup the VLAN entry. */
-	if (!valid) {
-		/* Need to find a way to map VID to FID. */
-		fid = 1;
-		valid = 1;
-	}
-	member |= BIT(port);
-
-	ksz8_to_vlan(dev, fid, member, valid, &data);
-	ksz8_w_vlan_table(dev, vlan->vid, data);
-
-	/* change PVID */
-	if (vlan->flags & BRIDGE_VLAN_INFO_PVID)
-		new_pvid = vlan->vid;
-
-	if (new_pvid) {
-		u16 vid;
-
-		ksz_pread16(dev, port, REG_PORT_CTRL_VID, &vid);
-		vid &= ~VLAN_VID_MASK;
-		vid |= new_pvid;
-		ksz_pwrite16(dev, port, REG_PORT_CTRL_VID, vid);
-
-		ksz8_port_enable_pvid(dev, port, true);
-	}
-
-	return 0;
-}
-
-int ksz8_port_vlan_del(struct ksz_device *dev, int port,
-		       const struct switchdev_obj_port_vlan *vlan)
-{
-	u16 data, pvid;
-	u8 fid, member, valid;
-
-	if (ksz_is_ksz88x3(dev))
-		return -ENOTSUPP;
-
-	ksz_pread16(dev, port, REG_PORT_CTRL_VID, &pvid);
-	pvid = pvid & 0xFFF;
-
-	ksz8_r_vlan_table(dev, vlan->vid, &data);
-	ksz8_from_vlan(dev, data, &fid, &member, &valid);
-
-	member &= ~BIT(port);
-
-	/* Invalidate the entry if no more member. */
-	if (!member) {
-		fid = 0;
-		valid = 0;
-	}
-
-	ksz8_to_vlan(dev, fid, member, valid, &data);
-	ksz8_w_vlan_table(dev, vlan->vid, data);
-
-	if (pvid == vlan->vid)
-		ksz8_port_enable_pvid(dev, port, false);
-
-	return 0;
-}
-
-int ksz8_port_mirror_add(struct ksz_device *dev, int port,
-			 struct dsa_mall_mirror_tc_entry *mirror,
-			 bool ingress, struct netlink_ext_ack *extack)
-{
-	if (ingress) {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, true);
-		dev->mirror_rx |= BIT(port);
-	} else {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, true);
-		dev->mirror_tx |= BIT(port);
-	}
-
-	ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_SNIFFER, false);
-
-	/* configure mirror port */
-	if (dev->mirror_rx || dev->mirror_tx)
-		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
-			     PORT_MIRROR_SNIFFER, true);
-
-	return 0;
-}
-
-void ksz8_port_mirror_del(struct ksz_device *dev, int port,
-			  struct dsa_mall_mirror_tc_entry *mirror)
-{
-	u8 data;
-
-	if (mirror->ingress) {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_RX, false);
-		dev->mirror_rx &= ~BIT(port);
-	} else {
-		ksz_port_cfg(dev, port, P_MIRROR_CTRL, PORT_MIRROR_TX, false);
-		dev->mirror_tx &= ~BIT(port);
-	}
-
-	ksz_pread8(dev, port, P_MIRROR_CTRL, &data);
-
-	if (!dev->mirror_rx && !dev->mirror_tx)
-		ksz_port_cfg(dev, mirror->to_local_port, P_MIRROR_CTRL,
-			     PORT_MIRROR_SNIFFER, false);
-}
-
-static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port)
-{
-	struct ksz_port *p = &dev->ports[port];
-
-	if (!ksz_is_ksz87xx(dev))
-		return;
-
-	if (!p->interface && dev->compat_interface) {
-		dev_warn(dev->dev,
-			 "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. "
-			 "Please update your device tree.\n",
-			 port);
-		p->interface = dev->compat_interface;
-	}
-}
-
-void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
-{
-	const u16 *regs = dev->info->regs;
-	struct dsa_switch *ds = dev->ds;
-	const u32 *masks;
-	int queues;
-	u8 member;
-
-	masks = dev->info->masks;
-
-	/* enable broadcast storm limit */
-	ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true);
-
-	/* For KSZ88x3 enable only one queue by default, otherwise we won't
-	 * be able to get rid of PCP prios on Port 2.
-	 */
-	if (ksz_is_ksz88x3(dev))
-		queues = 1;
-	else
-		queues = dev->info->num_tx_queues;
-
-	ksz8_port_queue_split(dev, port, queues);
-
-	/* replace priority */
-	ksz_port_cfg(dev, port, P_802_1P_CTRL,
-		     masks[PORT_802_1P_REMAPPING], false);
-
-	if (cpu_port)
-		member = dsa_user_ports(ds);
-	else
-		member = BIT(dsa_upstream_port(ds, port));
-
-	ksz8_cfg_port_member(dev, port, member);
-
-	/* Disable all WoL options by default. Otherwise
-	 * ksz_switch_macaddr_get/put logic will not work properly.
-	 * CPU port 4 has no WoL functionality.
-	 */
-	if (ksz_is_ksz87xx(dev) && !cpu_port)
-		ksz8_pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0);
-}
-
-static void ksz88x3_config_rmii_clk(struct ksz_device *dev)
-{
-	struct dsa_port *cpu_dp = dsa_to_port(dev->ds, dev->cpu_port);
-	bool rmii_clk_internal;
-
-	if (!ksz_is_ksz88x3(dev))
-		return;
-
-	rmii_clk_internal = of_property_read_bool(cpu_dp->dn,
-						  "microchip,rmii-clk-internal");
-
-	ksz_cfg(dev, KSZ88X3_REG_FVID_AND_HOST_MODE,
-		KSZ88X3_PORT3_RMII_CLK_INTERNAL, rmii_clk_internal);
-}
-
-void ksz8_config_cpu_port(struct dsa_switch *ds)
-{
-	struct ksz_device *dev = ds->priv;
-	struct ksz_port *p;
-	const u32 *masks;
-	const u16 *regs;
-	u8 remote;
-	int i;
-
-	masks = dev->info->masks;
-	regs = dev->info->regs;
-
-	ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true);
-
-	ksz8_port_setup(dev, dev->cpu_port, true);
-
-	ksz8795_cpu_interface_select(dev, dev->cpu_port);
-	ksz88x3_config_rmii_clk(dev);
-
-	for (i = 0; i < dev->phy_port_cnt; i++) {
-		ksz_port_stp_state_set(ds, i, BR_STATE_DISABLED);
-	}
-	for (i = 0; i < dev->phy_port_cnt; i++) {
-		p = &dev->ports[i];
-
-		/* For KSZ8795 family. */
-		if (ksz_is_ksz87xx(dev)) {
-			ksz_pread8(dev, i, regs[P_REMOTE_STATUS], &remote);
-			if (remote & KSZ8_PORT_FIBER_MODE)
-				p->fiber = 1;
-		}
-		if (p->fiber)
-			ksz_port_cfg(dev, i, regs[P_STP_CTRL],
-				     PORT_FORCE_FLOW_CTRL, true);
-		else
-			ksz_port_cfg(dev, i, regs[P_STP_CTRL],
-				     PORT_FORCE_FLOW_CTRL, false);
-	}
-}
-
-/**
- * ksz8_phy_port_link_up - Configures ports with integrated PHYs
- * @dev: The KSZ device instance.
- * @port: The port number to configure.
- * @duplex: The desired duplex mode.
- * @tx_pause: If true, enables transmit pause.
- * @rx_pause: If true, enables receive pause.
- *
- * Description:
- * The function configures flow control settings for a given port based on the
- * desired settings and current duplex mode.
- *
- * According to the KSZ8873 datasheet, the PORT_FORCE_FLOW_CTRL bit in the
- * Port Control 2 register (0x1A for Port 1, 0x22 for Port 2, 0x32 for Port 3)
- * determines how flow control is handled on the port:
- *    "1 = will always enable full-duplex flow control on the port, regardless
- *         of AN result.
- *     0 = full-duplex flow control is enabled based on AN result."
- *
- * This means that the flow control behavior depends on the state of this bit:
- * - If PORT_FORCE_FLOW_CTRL is set to 1, the switch will ignore AN results and
- *   force flow control on the port.
- * - If PORT_FORCE_FLOW_CTRL is set to 0, the switch will enable or disable
- *   flow control based on the AN results.
- *
- * However, there is a potential limitation in this configuration. It is
- * currently not possible to force disable flow control on a port if we still
- * advertise pause support. While such a configuration is not currently
- * supported by Linux, and may not make practical sense, it's important to be
- * aware of this limitation when working with the KSZ8873 and similar devices.
- */
-static void ksz8_phy_port_link_up(struct ksz_device *dev, int port, int duplex,
-				  bool tx_pause, bool rx_pause)
-{
-	const u16 *regs = dev->info->regs;
-	u8 sctrl = 0;
-
-	/* The KSZ8795 switch differs from the KSZ8873 by supporting
-	 * asymmetric pause control. However, since a single bit is used to
-	 * control both RX and TX pause, we can't enforce asymmetric pause
-	 * control - both TX and RX pause will be either enabled or disabled
-	 * together.
-	 *
-	 * If auto-negotiation is enabled, we usually allow the flow control to
-	 * be determined by the auto-negotiation process based on the
-	 * capabilities of both link partners. However, for KSZ8873, the
-	 * PORT_FORCE_FLOW_CTRL bit may be set by the hardware bootstrap,
-	 * ignoring the auto-negotiation result. Thus, even in auto-negotiation
-	 * mode, we need to ensure that the PORT_FORCE_FLOW_CTRL bit is
-	 * properly cleared.
-	 *
-	 * In the absence of pause auto-negotiation, we will enforce symmetric
-	 * pause control for both variants of switches - KSZ8873 and KSZ8795.
-	 *
-	 * Autoneg Pause Autoneg      rx,tx	PORT_FORCE_FLOW_CTRL
-	 * 1		1		x	0
-	 * 0		1		x	0 (flow control probably disabled)
-	 * x		0		1	1 (flow control force enabled)
-	 * 1		0		0	0 (flow control still depends on
-	 *					   aneg result due to hardware)
-	 * 0		0		0	0 (flow control probably disabled)
-	 */
-	if (dev->ports[port].manual_flow && tx_pause)
-		sctrl |= PORT_FORCE_FLOW_CTRL;
-
-	ksz_prmw8(dev, port, regs[P_STP_CTRL], PORT_FORCE_FLOW_CTRL, sctrl);
-}
-
-/**
- * ksz8_cpu_port_link_up - Configures the CPU port of the switch.
- * @dev: The KSZ device instance.
- * @speed: The desired link speed.
- * @duplex: The desired duplex mode.
- * @tx_pause: If true, enables transmit pause.
- * @rx_pause: If true, enables receive pause.
- *
- * Description:
- * The function configures flow control and speed settings for the CPU
- * port of the switch based on the desired settings, current duplex mode, and
- * speed.
- */
-static void ksz8_cpu_port_link_up(struct ksz_device *dev, int speed, int duplex,
-				  bool tx_pause, bool rx_pause)
-{
-	const u16 *regs = dev->info->regs;
-	u8 ctrl = 0;
-
-	/* SW_FLOW_CTRL, SW_HALF_DUPLEX, and SW_10_MBIT bits are bootstrappable
-	 * at least on KSZ8873. They can have different values depending on your
-	 * board setup.
-	 */
-	if (tx_pause || rx_pause)
-		ctrl |= SW_FLOW_CTRL;
-
-	if (duplex == DUPLEX_HALF)
-		ctrl |= SW_HALF_DUPLEX;
-
-	/* This hardware only supports SPEED_10 and SPEED_100. For SPEED_10
-	 * we need to set the SW_10_MBIT bit. Otherwise, we can leave it 0.
-	 */
-	if (speed == SPEED_10)
-		ctrl |= SW_10_MBIT;
-
-	ksz_rmw8(dev, regs[S_BROADCAST_CTRL], SW_HALF_DUPLEX | SW_FLOW_CTRL |
-		 SW_10_MBIT, ctrl);
-}
-
-void ksz8_phylink_mac_link_up(struct phylink_config *config,
-			      struct phy_device *phydev, unsigned int mode,
-			      phy_interface_t interface, int speed, int duplex,
-			      bool tx_pause, bool rx_pause)
-{
-	struct dsa_port *dp = dsa_phylink_to_port(config);
-	struct ksz_device *dev = dp->ds->priv;
-	int port = dp->index;
-
-	/* If the port is the CPU port, apply special handling. Only the CPU
-	 * port is configured via global registers.
-	 */
-	if (dev->cpu_port == port)
-		ksz8_cpu_port_link_up(dev, speed, duplex, tx_pause, rx_pause);
-	else if (dev->info->internal_phy[port])
-		ksz8_phy_port_link_up(dev, port, duplex, tx_pause, rx_pause);
-}
-
-static int ksz8_handle_global_errata(struct dsa_switch *ds)
-{
-	struct ksz_device *dev = ds->priv;
-	int ret = 0;
-
-	/* KSZ87xx Errata DS80000687C.
-	 * Module 2: Link drops with some EEE link partners.
-	 *   An issue with the EEE next page exchange between the
-	 *   KSZ879x/KSZ877x/KSZ876x and some EEE link partners may result in
-	 *   the link dropping.
-	 */
-	if (dev->info->ksz87xx_eee_link_erratum)
-		ret = ksz8_ind_write8(dev, TABLE_EEE, REG_IND_EEE_GLOB2_HI, 0);
-
-	return ret;
-}
-
-int ksz8_enable_stp_addr(struct ksz_device *dev)
-{
-	struct alu_struct alu;
-
-	/* Setup STP address for STP operation. */
-	memset(&alu, 0, sizeof(alu));
-	ether_addr_copy(alu.mac, eth_stp_addr);
-	alu.is_static = true;
-	alu.is_override = true;
-	alu.port_forward = dev->info->cpu_ports;
-
-	return ksz8_w_sta_mac_table(dev, 0, &alu);
-}
-
-int ksz8_setup(struct dsa_switch *ds)
-{
-	struct ksz_device *dev = ds->priv;
-	const u16 *regs = dev->info->regs;
-	int i, ret = 0;
-
-	ds->mtu_enforcement_ingress = true;
-
-	/* We rely on software untagging on the CPU port, so that we
-	 * can support both tagged and untagged VLANs
-	 */
-	ds->untag_bridge_pvid = true;
-
-	/* VLAN filtering is partly controlled by the global VLAN
-	 * Enable flag
-	 */
-	ds->vlan_filtering_is_global = true;
-
-	/* Enable automatic fast aging when link changed detected. */
-	ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true);
-
-	/* Enable aggressive back off algorithm in half duplex mode. */
-	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1,
-			   SW_AGGR_BACKOFF, SW_AGGR_BACKOFF);
-
-	/*
-	 * Make sure unicast VLAN boundary is set as default and
-	 * enable no excessive collision drop.
-	 */
-	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2,
-			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP,
-			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP);
-
-	ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false);
-
-	ksz_cfg(dev, S_MIRROR_CTRL, SW_MIRROR_RX_TX, false);
-
-	if (!ksz_is_ksz88x3(dev))
-		ksz_cfg(dev, REG_SW_CTRL_19, SW_INS_TAG_ENABLE, true);
-
-	for (i = 0; i < (dev->info->num_vlans / 4); i++)
-		ksz8_r_vlan_entries(dev, i);
-
-	/* Make sure PME (WoL) is not enabled. If requested, it will
-	 * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs
-	 * do not like PME events changes before shutdown. PME only
-	 * available on KSZ87xx family.
-	 */
-	if (ksz_is_ksz87xx(dev)) {
-		ret = ksz8_pme_write8(dev, regs[REG_SW_PME_CTRL], 0);
-		if (!ret)
-			ret = ksz_rmw8(dev, REG_INT_ENABLE, INT_PME, 0);
-	}
-
-	if (!ret)
-		return ksz8_handle_global_errata(ds);
-	else
-		return ret;
-}
-
-void ksz8_get_caps(struct ksz_device *dev, int port,
-		   struct phylink_config *config)
-{
-	config->mac_capabilities = MAC_10 | MAC_100;
-
-	/* Silicon Errata Sheet (DS80000830A):
-	 * "Port 1 does not respond to received flow control PAUSE frames"
-	 * So, disable Pause support on "Port 1" (port == 0) for all ksz88x3
-	 * switches.
-	 */
-	if (!ksz_is_ksz88x3(dev) || port)
-		config->mac_capabilities |= MAC_SYM_PAUSE;
-
-	/* Asym pause is not supported on KSZ8863 and KSZ8873 */
-	if (!ksz_is_ksz88x3(dev))
-		config->mac_capabilities |= MAC_ASYM_PAUSE;
-}
-
-u32 ksz8_get_port_addr(int port, int offset)
-{
-	return PORT_CTRL_ADDR(port, offset);
-}
-
-int ksz8_switch_init(struct ksz_device *dev)
-{
-	dev->cpu_port = fls(dev->info->cpu_ports) - 1;
-	dev->phy_port_cnt = dev->info->port_cnt - 1;
-	dev->port_mask = (BIT(dev->phy_port_cnt) - 1) | dev->info->cpu_ports;
-
-	return 0;
-}
-
-void ksz8_switch_exit(struct ksz_device *dev)
-{
-	ksz8_reset_switch(dev);
-}
-
-MODULE_AUTHOR("Tristram Ha <Tristram.Ha@microchip.com>");
-MODULE_DESCRIPTION("Microchip KSZ8795 Series Switch DSA Driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h
deleted file mode 100644
index 69566a5d9cda..000000000000
--- a/drivers/net/dsa/microchip/ksz8795_reg.h
+++ /dev/null
@@ -1,798 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Microchip KSZ8795 register definitions
- *
- * Copyright (c) 2017 Microchip Technology Inc.
- *	Tristram Ha <Tristram.Ha@microchip.com>
- */
-
-#ifndef __KSZ8795_REG_H
-#define __KSZ8795_REG_H
-
-#define KS_PORT_M			0x1F
-
-#define KS_PRIO_M			0x3
-#define KS_PRIO_S			2
-
-#define SW_REVISION_M			0x0E
-#define SW_REVISION_S			1
-
-#define KSZ8863_REG_SW_RESET		0x43
-
-#define KSZ8863_GLOBAL_SOFTWARE_RESET	BIT(4)
-#define KSZ8863_PCS_RESET		BIT(0)
-
-#define KSZ88X3_REG_FVID_AND_HOST_MODE  0xC6
-#define KSZ88X3_PORT3_RMII_CLK_INTERNAL BIT(3)
-
-#define REG_SW_CTRL_0			0x02
-
-#define SW_NEW_BACKOFF			BIT(7)
-#define SW_GLOBAL_RESET			BIT(6)
-#define SW_FLUSH_DYN_MAC_TABLE		BIT(5)
-#define SW_FLUSH_STA_MAC_TABLE		BIT(4)
-#define SW_LINK_AUTO_AGING		BIT(0)
-
-#define REG_SW_CTRL_1			0x03
-
-#define SW_HUGE_PACKET			BIT(6)
-#define SW_TX_FLOW_CTRL_DISABLE		BIT(5)
-#define SW_RX_FLOW_CTRL_DISABLE		BIT(4)
-#define SW_CHECK_LENGTH			BIT(3)
-#define SW_AGING_ENABLE			BIT(2)
-#define SW_FAST_AGING			BIT(1)
-#define SW_AGGR_BACKOFF			BIT(0)
-
-#define REG_SW_CTRL_2			0x04
-
-#define UNICAST_VLAN_BOUNDARY		BIT(7)
-#define SW_BACK_PRESSURE		BIT(5)
-#define FAIR_FLOW_CTRL			BIT(4)
-#define NO_EXC_COLLISION_DROP		BIT(3)
-#define SW_LEGAL_PACKET_DISABLE		BIT(1)
-
-#define KSZ8863_HUGE_PACKET_ENABLE	BIT(2)
-#define KSZ8863_LEGAL_PACKET_ENABLE	BIT(1)
-
-#define REG_SW_CTRL_3			0x05
- #define WEIGHTED_FAIR_QUEUE_ENABLE	BIT(3)
-
-#define SW_VLAN_ENABLE			BIT(7)
-#define SW_IGMP_SNOOP			BIT(6)
-#define SW_MIRROR_RX_TX			BIT(0)
-
-#define REG_SW_CTRL_4			0x06
-
-#define SW_HALF_DUPLEX_FLOW_CTRL	BIT(7)
-#define SW_HALF_DUPLEX			BIT(6)
-#define SW_FLOW_CTRL			BIT(5)
-#define SW_10_MBIT			BIT(4)
-#define SW_REPLACE_VID			BIT(3)
-
-#define REG_SW_CTRL_5			0x07
-
-#define REG_SW_CTRL_6			0x08
-
-#define SW_MIB_COUNTER_FLUSH		BIT(7)
-#define SW_MIB_COUNTER_FREEZE		BIT(6)
-#define SW_MIB_COUNTER_CTRL_ENABLE	KS_PORT_M
-
-#define REG_SW_CTRL_9			0x0B
-
-#define SPI_CLK_125_MHZ			0x80
-#define SPI_CLK_62_5_MHZ		0x40
-#define SPI_CLK_31_25_MHZ		0x00
-
-#define SW_LED_MODE_M			0x3
-#define SW_LED_MODE_S			4
-#define SW_LED_LINK_ACT_SPEED		0
-#define SW_LED_LINK_ACT			1
-#define SW_LED_LINK_ACT_DUPLEX		2
-#define SW_LED_LINK_DUPLEX		3
-
-#define REG_SW_CTRL_10			0x0C
-
-#define SW_PASS_PAUSE			BIT(0)
-
-#define REG_SW_CTRL_11			0x0D
-
-#define REG_POWER_MANAGEMENT_1		0x0E
-
-#define SW_PLL_POWER_DOWN		BIT(5)
-#define SW_POWER_MANAGEMENT_MODE_M	0x3
-#define SW_POWER_MANAGEMENT_MODE_S	3
-#define SW_POWER_NORMAL			0
-#define SW_ENERGY_DETECTION		1
-#define SW_SOFTWARE_POWER_DOWN		2
-
-#define REG_POWER_MANAGEMENT_2		0x0F
-
-#define REG_PORT_1_CTRL_0		0x10
-#define REG_PORT_2_CTRL_0		0x20
-#define REG_PORT_3_CTRL_0		0x30
-#define REG_PORT_4_CTRL_0		0x40
-#define REG_PORT_5_CTRL_0		0x50
-
-#define PORT_BROADCAST_STORM		BIT(7)
-#define PORT_DIFFSERV_ENABLE		BIT(6)
-#define PORT_802_1P_ENABLE		BIT(5)
-#define PORT_BASED_PRIO_S		3
-#define PORT_BASED_PRIO_M		KS_PRIO_M
-#define PORT_BASED_PRIO_0		0
-#define PORT_BASED_PRIO_1		1
-#define PORT_BASED_PRIO_2		2
-#define PORT_BASED_PRIO_3		3
-#define PORT_INSERT_TAG			BIT(2)
-#define PORT_REMOVE_TAG			BIT(1)
-#define KSZ8795_PORT_2QUEUE_SPLIT_EN	BIT(0)
-#define KSZ8873_PORT_4QUEUE_SPLIT_EN	BIT(0)
-
-#define REG_PORT_1_CTRL_1		0x11
-#define REG_PORT_2_CTRL_1		0x21
-#define REG_PORT_3_CTRL_1		0x31
-#define REG_PORT_4_CTRL_1		0x41
-#define REG_PORT_5_CTRL_1		0x51
-
-#define PORT_MIRROR_SNIFFER		BIT(7)
-#define PORT_MIRROR_RX			BIT(6)
-#define PORT_MIRROR_TX			BIT(5)
-#define PORT_VLAN_MEMBERSHIP		KS_PORT_M
-
-#define REG_PORT_1_CTRL_2		0x12
-#define REG_PORT_2_CTRL_2		0x22
-#define REG_PORT_3_CTRL_2		0x32
-#define REG_PORT_4_CTRL_2		0x42
-#define REG_PORT_5_CTRL_2		0x52
-
-#define KSZ8873_PORT_2QUEUE_SPLIT_EN	BIT(7)
-#define PORT_INGRESS_FILTER		BIT(6)
-#define PORT_DISCARD_NON_VID		BIT(5)
-#define PORT_FORCE_FLOW_CTRL		BIT(4)
-#define PORT_BACK_PRESSURE		BIT(3)
-
-#define REG_PORT_1_CTRL_3		0x13
-#define REG_PORT_2_CTRL_3		0x23
-#define REG_PORT_3_CTRL_3		0x33
-#define REG_PORT_4_CTRL_3		0x43
-#define REG_PORT_5_CTRL_3		0x53
-#define REG_PORT_1_CTRL_4		0x14
-#define REG_PORT_2_CTRL_4		0x24
-#define REG_PORT_3_CTRL_4		0x34
-#define REG_PORT_4_CTRL_4		0x44
-#define REG_PORT_5_CTRL_4		0x54
-
-#define PORT_DEFAULT_VID		0x0001
-
-#define REG_PORT_1_CTRL_5		0x15
-#define REG_PORT_2_CTRL_5		0x25
-#define REG_PORT_3_CTRL_5		0x35
-#define REG_PORT_4_CTRL_5		0x45
-#define REG_PORT_5_CTRL_5		0x55
-
-#define PORT_ACL_ENABLE			BIT(2)
-#define PORT_AUTHEN_MODE		0x3
-#define PORT_AUTHEN_PASS		0
-#define PORT_AUTHEN_BLOCK		1
-#define PORT_AUTHEN_TRAP		2
-
-#define REG_PORT_5_CTRL_6		0x56
-
-#define PORT_MII_INTERNAL_CLOCK		BIT(7)
-#define PORT_GMII_MAC_MODE		BIT(2)
-
-#define REG_PORT_1_CTRL_7		0x17
-#define REG_PORT_2_CTRL_7		0x27
-#define REG_PORT_3_CTRL_7		0x37
-#define REG_PORT_4_CTRL_7		0x47
-
-#define PORT_AUTO_NEG_ASYM_PAUSE	BIT(5)
-#define PORT_AUTO_NEG_SYM_PAUSE		BIT(4)
-#define PORT_AUTO_NEG_100BTX_FD		BIT(3)
-#define PORT_AUTO_NEG_100BTX		BIT(2)
-#define PORT_AUTO_NEG_10BT_FD		BIT(1)
-#define PORT_AUTO_NEG_10BT		BIT(0)
-
-#define REG_PORT_1_STATUS_0		0x18
-#define REG_PORT_2_STATUS_0		0x28
-#define REG_PORT_3_STATUS_0		0x38
-#define REG_PORT_4_STATUS_0		0x48
-
-/* For KSZ8765. */
-#define PORT_REMOTE_ASYM_PAUSE		BIT(5)
-#define PORT_REMOTE_SYM_PAUSE		BIT(4)
-#define PORT_REMOTE_100BTX_FD		BIT(3)
-#define PORT_REMOTE_100BTX		BIT(2)
-#define PORT_REMOTE_10BT_FD		BIT(1)
-#define PORT_REMOTE_10BT		BIT(0)
-
-#define REG_PORT_1_STATUS_1		0x19
-#define REG_PORT_2_STATUS_1		0x29
-#define REG_PORT_3_STATUS_1		0x39
-#define REG_PORT_4_STATUS_1		0x49
-
-#define PORT_HP_MDIX			BIT(7)
-#define PORT_REVERSED_POLARITY		BIT(5)
-#define PORT_TX_FLOW_CTRL		BIT(4)
-#define PORT_RX_FLOW_CTRL		BIT(3)
-#define PORT_STAT_SPEED_100MBIT		BIT(2)
-#define PORT_STAT_FULL_DUPLEX		BIT(1)
-
-#define PORT_REMOTE_FAULT		BIT(0)
-
-#define REG_PORT_1_LINK_MD_CTRL		0x1A
-#define REG_PORT_2_LINK_MD_CTRL		0x2A
-#define REG_PORT_3_LINK_MD_CTRL		0x3A
-#define REG_PORT_4_LINK_MD_CTRL		0x4A
-
-#define PORT_CABLE_10M_SHORT		BIT(7)
-#define PORT_CABLE_DIAG_RESULT_M	GENMASK(6, 5)
-#define PORT_CABLE_DIAG_RESULT_S	5
-#define PORT_CABLE_STAT_NORMAL		0
-#define PORT_CABLE_STAT_OPEN		1
-#define PORT_CABLE_STAT_SHORT		2
-#define PORT_CABLE_STAT_FAILED		3
-#define PORT_START_CABLE_DIAG		BIT(4)
-#define PORT_FORCE_LINK			BIT(3)
-#define PORT_POWER_SAVING		BIT(2)
-#define PORT_PHY_REMOTE_LOOPBACK	BIT(1)
-#define PORT_CABLE_FAULT_COUNTER_H	0x01
-
-#define REG_PORT_1_LINK_MD_RESULT	0x1B
-#define REG_PORT_2_LINK_MD_RESULT	0x2B
-#define REG_PORT_3_LINK_MD_RESULT	0x3B
-#define REG_PORT_4_LINK_MD_RESULT	0x4B
-
-#define PORT_CABLE_FAULT_COUNTER_L	0xFF
-#define PORT_CABLE_FAULT_COUNTER	0x1FF
-
-#define REG_PORT_1_CTRL_9		0x1C
-#define REG_PORT_2_CTRL_9		0x2C
-#define REG_PORT_3_CTRL_9		0x3C
-#define REG_PORT_4_CTRL_9		0x4C
-
-#define PORT_AUTO_NEG_ENABLE		BIT(7)
-#define PORT_AUTO_NEG_DISABLE		BIT(7)
-#define PORT_FORCE_100_MBIT		BIT(6)
-#define PORT_FORCE_FULL_DUPLEX		BIT(5)
-
-#define REG_PORT_1_CTRL_10		0x1D
-#define REG_PORT_2_CTRL_10		0x2D
-#define REG_PORT_3_CTRL_10		0x3D
-#define REG_PORT_4_CTRL_10		0x4D
-
-#define PORT_LED_OFF			BIT(7)
-#define PORT_TX_DISABLE			BIT(6)
-#define PORT_AUTO_NEG_RESTART		BIT(5)
-#define PORT_POWER_DOWN			BIT(3)
-#define PORT_AUTO_MDIX_DISABLE		BIT(2)
-#define PORT_FORCE_MDIX			BIT(1)
-#define PORT_MAC_LOOPBACK		BIT(0)
-#define KSZ8873_PORT_PHY_LOOPBACK	BIT(0)
-
-#define REG_PORT_1_STATUS_2		0x1E
-#define REG_PORT_2_STATUS_2		0x2E
-#define REG_PORT_3_STATUS_2		0x3E
-#define REG_PORT_4_STATUS_2		0x4E
-
-#define PORT_MDIX_STATUS		BIT(7)
-#define PORT_AUTO_NEG_COMPLETE		BIT(6)
-#define PORT_STAT_LINK_GOOD		BIT(5)
-
-#define REG_PORT_1_STATUS_3		0x1F
-#define REG_PORT_2_STATUS_3		0x2F
-#define REG_PORT_3_STATUS_3		0x3F
-#define REG_PORT_4_STATUS_3		0x4F
-
-#define PORT_PHY_LOOPBACK		BIT(7)
-#define PORT_PHY_ISOLATE		BIT(5)
-#define PORT_PHY_SOFT_RESET		BIT(4)
-#define PORT_PHY_FORCE_LINK		BIT(3)
-#define PORT_PHY_MODE_M			0x7
-#define PHY_MODE_IN_AUTO_NEG		1
-#define PHY_MODE_10BT_HALF		2
-#define PHY_MODE_100BT_HALF		3
-#define PHY_MODE_10BT_FULL		5
-#define PHY_MODE_100BT_FULL		6
-#define PHY_MODE_ISOLDATE		7
-
-#define REG_PORT_CTRL_0			0x00
-#define REG_PORT_CTRL_1			0x01
-#define REG_PORT_CTRL_2			0x02
-#define REG_PORT_CTRL_VID		0x03
-
-#define REG_PORT_CTRL_5			0x05
-
-#define REG_PORT_STATUS_1		0x09
-#define REG_PORT_LINK_MD_CTRL		0x0A
-#define REG_PORT_LINK_MD_RESULT		0x0B
-#define REG_PORT_CTRL_9			0x0C
-#define REG_PORT_CTRL_10		0x0D
-#define REG_PORT_STATUS_3		0x0F
-
-#define REG_PORT_CTRL_12		0xA0
-#define REG_PORT_CTRL_13		0xA1
-#define REG_PORT_RATE_CTRL_3		0xA2
-#define REG_PORT_RATE_CTRL_2		0xA3
-#define REG_PORT_RATE_CTRL_1		0xA4
-#define REG_PORT_RATE_CTRL_0		0xA5
-#define REG_PORT_RATE_LIMIT		0xA6
-#define REG_PORT_IN_RATE_0		0xA7
-#define REG_PORT_IN_RATE_1		0xA8
-#define REG_PORT_IN_RATE_2		0xA9
-#define REG_PORT_IN_RATE_3		0xAA
-#define REG_PORT_OUT_RATE_0		0xAB
-#define REG_PORT_OUT_RATE_1		0xAC
-#define REG_PORT_OUT_RATE_2		0xAD
-#define REG_PORT_OUT_RATE_3		0xAE
-
-#define PORT_CTRL_ADDR(port, addr)		\
-	((addr) + REG_PORT_1_CTRL_0 + (port) *	\
-		(REG_PORT_2_CTRL_0 - REG_PORT_1_CTRL_0))
-
-#define TABLE_EXT_SELECT_S		5
-#define TABLE_EEE_V			1
-#define TABLE_ACL_V			2
-#define TABLE_PME_V			4
-#define TABLE_LINK_MD_V			5
-#define TABLE_EEE			(TABLE_EEE_V << TABLE_EXT_SELECT_S)
-#define TABLE_ACL			(TABLE_ACL_V << TABLE_EXT_SELECT_S)
-#define TABLE_PME			(TABLE_PME_V << TABLE_EXT_SELECT_S)
-#define TABLE_LINK_MD			(TABLE_LINK_MD << TABLE_EXT_SELECT_S)
-#define TABLE_READ			BIT(4)
-#define TABLE_SELECT_S			2
-#define TABLE_STATIC_MAC_V		0
-#define TABLE_VLAN_V			1
-#define TABLE_DYNAMIC_MAC_V		2
-#define TABLE_MIB_V			3
-#define TABLE_STATIC_MAC		(TABLE_STATIC_MAC_V << TABLE_SELECT_S)
-#define TABLE_VLAN			(TABLE_VLAN_V << TABLE_SELECT_S)
-#define TABLE_DYNAMIC_MAC		(TABLE_DYNAMIC_MAC_V << TABLE_SELECT_S)
-#define TABLE_MIB			(TABLE_MIB_V << TABLE_SELECT_S)
-
-#define REG_IND_CTRL_1			0x6F
-
-#define TABLE_ENTRY_MASK		0x03FF
-#define TABLE_EXT_ENTRY_MASK		0x0FFF
-
-#define REG_IND_DATA_5			0x73
-#define REG_IND_DATA_2			0x76
-#define REG_IND_DATA_1			0x77
-#define REG_IND_DATA_0			0x78
-
-#define REG_IND_DATA_PME_EEE_ACL	0xA0
-
-#define REG_INT_STATUS			0x7C
-#define REG_INT_ENABLE			0x7D
-
-#define INT_PME				BIT(4)
-
-#define REG_ACL_INT_STATUS		0x7E
-#define REG_ACL_INT_ENABLE		0x7F
-
-#define INT_PORT_5			BIT(4)
-#define INT_PORT_4			BIT(3)
-#define INT_PORT_3			BIT(2)
-#define INT_PORT_2			BIT(1)
-#define INT_PORT_1			BIT(0)
-
-#define INT_PORT_ALL			\
-	(INT_PORT_5 | INT_PORT_4 | INT_PORT_3 | INT_PORT_2 | INT_PORT_1)
-
-#define REG_SW_CTRL_12			0x80
-#define REG_SW_CTRL_13			0x81
-
-#define SWITCH_802_1P_MASK		3
-#define SWITCH_802_1P_BASE		3
-#define SWITCH_802_1P_SHIFT		2
-
-#define SW_802_1P_MAP_M			KS_PRIO_M
-#define SW_802_1P_MAP_S			KS_PRIO_S
-
-#define REG_SWITCH_CTRL_14		0x82
-
-#define SW_PRIO_MAPPING_M		KS_PRIO_M
-#define SW_PRIO_MAPPING_S		6
-#define SW_PRIO_MAP_3_HI		0
-#define SW_PRIO_MAP_2_HI		2
-#define SW_PRIO_MAP_0_LO		3
-
-#define REG_SW_CTRL_15			0x83
-#define REG_SW_CTRL_16			0x84
-#define REG_SW_CTRL_17			0x85
-#define REG_SW_CTRL_18			0x86
-
-#define SW_SELF_ADDR_FILTER_ENABLE	BIT(6)
-
-#define REG_SW_UNK_UCAST_CTRL		0x83
-#define REG_SW_UNK_MCAST_CTRL		0x84
-#define REG_SW_UNK_VID_CTRL		0x85
-#define REG_SW_UNK_IP_MCAST_CTRL	0x86
-
-#define SW_UNK_FWD_ENABLE		BIT(5)
-#define SW_UNK_FWD_MAP			KS_PORT_M
-
-#define REG_SW_CTRL_19			0x87
-
-#define SW_IN_RATE_LIMIT_PERIOD_M	0x3
-#define SW_IN_RATE_LIMIT_PERIOD_S	4
-#define SW_IN_RATE_LIMIT_16_MS		0
-#define SW_IN_RATE_LIMIT_64_MS		1
-#define SW_IN_RATE_LIMIT_256_MS		2
-#define SW_OUT_RATE_LIMIT_QUEUE_BASED	BIT(3)
-#define SW_INS_TAG_ENABLE		BIT(2)
-
-#define REG_TOS_PRIO_CTRL_0		0x90
-#define REG_TOS_PRIO_CTRL_1		0x91
-#define REG_TOS_PRIO_CTRL_2		0x92
-#define REG_TOS_PRIO_CTRL_3		0x93
-#define REG_TOS_PRIO_CTRL_4		0x94
-#define REG_TOS_PRIO_CTRL_5		0x95
-#define REG_TOS_PRIO_CTRL_6		0x96
-#define REG_TOS_PRIO_CTRL_7		0x97
-#define REG_TOS_PRIO_CTRL_8		0x98
-#define REG_TOS_PRIO_CTRL_9		0x99
-#define REG_TOS_PRIO_CTRL_10		0x9A
-#define REG_TOS_PRIO_CTRL_11		0x9B
-#define REG_TOS_PRIO_CTRL_12		0x9C
-#define REG_TOS_PRIO_CTRL_13		0x9D
-#define REG_TOS_PRIO_CTRL_14		0x9E
-#define REG_TOS_PRIO_CTRL_15		0x9F
-
-#define TOS_PRIO_M			KS_PRIO_M
-#define TOS_PRIO_S			KS_PRIO_S
-
-#define REG_SW_CTRL_21			0xA4
-
-#define SW_IPV6_MLD_OPTION		BIT(3)
-#define SW_IPV6_MLD_SNOOP		BIT(2)
-
-#define REG_PORT_1_CTRL_12		0xB0
-#define REG_PORT_2_CTRL_12		0xC0
-#define REG_PORT_3_CTRL_12		0xD0
-#define REG_PORT_4_CTRL_12		0xE0
-#define REG_PORT_5_CTRL_12		0xF0
-
-#define PORT_PASS_ALL			BIT(6)
-#define PORT_INS_TAG_FOR_PORT_5_S	3
-#define PORT_INS_TAG_FOR_PORT_5		BIT(3)
-#define PORT_INS_TAG_FOR_PORT_4		BIT(2)
-#define PORT_INS_TAG_FOR_PORT_3		BIT(1)
-#define PORT_INS_TAG_FOR_PORT_2		BIT(0)
-
-#define REG_PORT_1_CTRL_13		0xB1
-#define REG_PORT_2_CTRL_13		0xC1
-#define REG_PORT_3_CTRL_13		0xD1
-#define REG_PORT_4_CTRL_13		0xE1
-#define REG_PORT_5_CTRL_13		0xF1
-
-#define KSZ8795_PORT_4QUEUE_SPLIT_EN	BIT(1)
-#define PORT_DROP_TAG			BIT(0)
-
-#define REG_PORT_1_CTRL_14		0xB2
-#define REG_PORT_2_CTRL_14		0xC2
-#define REG_PORT_3_CTRL_14		0xD2
-#define REG_PORT_4_CTRL_14		0xE2
-#define REG_PORT_5_CTRL_14		0xF2
-#define REG_PORT_1_CTRL_15		0xB3
-#define REG_PORT_2_CTRL_15		0xC3
-#define REG_PORT_3_CTRL_15		0xD3
-#define REG_PORT_4_CTRL_15		0xE3
-#define REG_PORT_5_CTRL_15		0xF3
-#define REG_PORT_1_CTRL_16		0xB4
-#define REG_PORT_2_CTRL_16		0xC4
-#define REG_PORT_3_CTRL_16		0xD4
-#define REG_PORT_4_CTRL_16		0xE4
-#define REG_PORT_5_CTRL_16		0xF4
-#define REG_PORT_1_CTRL_17		0xB5
-#define REG_PORT_2_CTRL_17		0xC5
-#define REG_PORT_3_CTRL_17		0xD5
-#define REG_PORT_4_CTRL_17		0xE5
-#define REG_PORT_5_CTRL_17		0xF5
-
-#define REG_PORT_1_RATE_CTRL_3		0xB2
-#define REG_PORT_1_RATE_CTRL_2		0xB3
-#define REG_PORT_1_RATE_CTRL_1		0xB4
-#define REG_PORT_1_RATE_CTRL_0		0xB5
-#define REG_PORT_2_RATE_CTRL_3		0xC2
-#define REG_PORT_2_RATE_CTRL_2		0xC3
-#define REG_PORT_2_RATE_CTRL_1		0xC4
-#define REG_PORT_2_RATE_CTRL_0		0xC5
-#define REG_PORT_3_RATE_CTRL_3		0xD2
-#define REG_PORT_3_RATE_CTRL_2		0xD3
-#define REG_PORT_3_RATE_CTRL_1		0xD4
-#define REG_PORT_3_RATE_CTRL_0		0xD5
-#define REG_PORT_4_RATE_CTRL_3		0xE2
-#define REG_PORT_4_RATE_CTRL_2		0xE3
-#define REG_PORT_4_RATE_CTRL_1		0xE4
-#define REG_PORT_4_RATE_CTRL_0		0xE5
-#define REG_PORT_5_RATE_CTRL_3		0xF2
-#define REG_PORT_5_RATE_CTRL_2		0xF3
-#define REG_PORT_5_RATE_CTRL_1		0xF4
-#define REG_PORT_5_RATE_CTRL_0		0xF5
-
-#define RATE_CTRL_ENABLE		BIT(7)
-#define RATE_RATIO_M			(BIT(7) - 1)
-
-#define PORT_OUT_RATE_ENABLE		BIT(7)
-
-#define REG_PORT_1_RATE_LIMIT		0xB6
-#define REG_PORT_2_RATE_LIMIT		0xC6
-#define REG_PORT_3_RATE_LIMIT		0xD6
-#define REG_PORT_4_RATE_LIMIT		0xE6
-#define REG_PORT_5_RATE_LIMIT		0xF6
-
-#define PORT_IN_PORT_BASED_S		6
-#define PORT_RATE_PACKET_BASED_S	5
-#define PORT_IN_FLOW_CTRL_S		4
-#define PORT_IN_LIMIT_MODE_M		0x3
-#define PORT_IN_LIMIT_MODE_S		2
-#define PORT_COUNT_IFG_S		1
-#define PORT_COUNT_PREAMBLE_S		0
-#define PORT_IN_PORT_BASED		BIT(PORT_IN_PORT_BASED_S)
-#define PORT_RATE_PACKET_BASED		BIT(PORT_RATE_PACKET_BASED_S)
-#define PORT_IN_FLOW_CTRL		BIT(PORT_IN_FLOW_CTRL_S)
-#define PORT_IN_ALL			0
-#define PORT_IN_UNICAST			1
-#define PORT_IN_MULTICAST		2
-#define PORT_IN_BROADCAST		3
-#define PORT_COUNT_IFG			BIT(PORT_COUNT_IFG_S)
-#define PORT_COUNT_PREAMBLE		BIT(PORT_COUNT_PREAMBLE_S)
-
-#define REG_PORT_1_IN_RATE_0		0xB7
-#define REG_PORT_2_IN_RATE_0		0xC7
-#define REG_PORT_3_IN_RATE_0		0xD7
-#define REG_PORT_4_IN_RATE_0		0xE7
-#define REG_PORT_5_IN_RATE_0		0xF7
-#define REG_PORT_1_IN_RATE_1		0xB8
-#define REG_PORT_2_IN_RATE_1		0xC8
-#define REG_PORT_3_IN_RATE_1		0xD8
-#define REG_PORT_4_IN_RATE_1		0xE8
-#define REG_PORT_5_IN_RATE_1		0xF8
-#define REG_PORT_1_IN_RATE_2		0xB9
-#define REG_PORT_2_IN_RATE_2		0xC9
-#define REG_PORT_3_IN_RATE_2		0xD9
-#define REG_PORT_4_IN_RATE_2		0xE9
-#define REG_PORT_5_IN_RATE_2		0xF9
-#define REG_PORT_1_IN_RATE_3		0xBA
-#define REG_PORT_2_IN_RATE_3		0xCA
-#define REG_PORT_3_IN_RATE_3		0xDA
-#define REG_PORT_4_IN_RATE_3		0xEA
-#define REG_PORT_5_IN_RATE_3		0xFA
-
-#define PORT_IN_RATE_ENABLE		BIT(7)
-#define PORT_RATE_LIMIT_M		(BIT(7) - 1)
-
-#define REG_PORT_1_OUT_RATE_0		0xBB
-#define REG_PORT_2_OUT_RATE_0		0xCB
-#define REG_PORT_3_OUT_RATE_0		0xDB
-#define REG_PORT_4_OUT_RATE_0		0xEB
-#define REG_PORT_5_OUT_RATE_0		0xFB
-#define REG_PORT_1_OUT_RATE_1		0xBC
-#define REG_PORT_2_OUT_RATE_1		0xCC
-#define REG_PORT_3_OUT_RATE_1		0xDC
-#define REG_PORT_4_OUT_RATE_1		0xEC
-#define REG_PORT_5_OUT_RATE_1		0xFC
-#define REG_PORT_1_OUT_RATE_2		0xBD
-#define REG_PORT_2_OUT_RATE_2		0xCD
-#define REG_PORT_3_OUT_RATE_2		0xDD
-#define REG_PORT_4_OUT_RATE_2		0xED
-#define REG_PORT_5_OUT_RATE_2		0xFD
-#define REG_PORT_1_OUT_RATE_3		0xBE
-#define REG_PORT_2_OUT_RATE_3		0xCE
-#define REG_PORT_3_OUT_RATE_3		0xDE
-#define REG_PORT_4_OUT_RATE_3		0xEE
-#define REG_PORT_5_OUT_RATE_3		0xFE
-
-/* 88x3 specific */
-
-#define REG_SW_INSERT_SRC_PVID		0xC2
-
-/* PME */
-
-#define SW_PME_OUTPUT_ENABLE		BIT(1)
-#define SW_PME_ACTIVE_HIGH		BIT(0)
-
-#define PORT_MAGIC_PACKET_DETECT	BIT(2)
-#define PORT_LINK_UP_DETECT		BIT(1)
-#define PORT_ENERGY_DETECT		BIT(0)
-
-/* ACL */
-
-#define ACL_FIRST_RULE_M		0xF
-
-#define ACL_MODE_M			0x3
-#define ACL_MODE_S			4
-#define ACL_MODE_DISABLE		0
-#define ACL_MODE_LAYER_2		1
-#define ACL_MODE_LAYER_3		2
-#define ACL_MODE_LAYER_4		3
-#define ACL_ENABLE_M			0x3
-#define ACL_ENABLE_S			2
-#define ACL_ENABLE_2_COUNT		0
-#define ACL_ENABLE_2_TYPE		1
-#define ACL_ENABLE_2_MAC		2
-#define ACL_ENABLE_2_BOTH		3
-#define ACL_ENABLE_3_IP			1
-#define ACL_ENABLE_3_SRC_DST_COMP	2
-#define ACL_ENABLE_4_PROTOCOL		0
-#define ACL_ENABLE_4_TCP_PORT_COMP	1
-#define ACL_ENABLE_4_UDP_PORT_COMP	2
-#define ACL_ENABLE_4_TCP_SEQN_COMP	3
-#define ACL_SRC				BIT(1)
-#define ACL_EQUAL			BIT(0)
-
-#define ACL_MAX_PORT			0xFFFF
-
-#define ACL_MIN_PORT			0xFFFF
-#define ACL_IP_ADDR			0xFFFFFFFF
-#define ACL_TCP_SEQNUM			0xFFFFFFFF
-
-#define ACL_RESERVED			0xF8
-#define ACL_PORT_MODE_M			0x3
-#define ACL_PORT_MODE_S			1
-#define ACL_PORT_MODE_DISABLE		0
-#define ACL_PORT_MODE_EITHER		1
-#define ACL_PORT_MODE_IN_RANGE		2
-#define ACL_PORT_MODE_OUT_OF_RANGE	3
-
-#define ACL_TCP_FLAG_ENABLE		BIT(0)
-
-#define ACL_TCP_FLAG_M			0xFF
-
-#define ACL_TCP_FLAG			0xFF
-#define ACL_ETH_TYPE			0xFFFF
-#define ACL_IP_M			0xFFFFFFFF
-
-#define ACL_PRIO_MODE_M			0x3
-#define ACL_PRIO_MODE_S			6
-#define ACL_PRIO_MODE_DISABLE		0
-#define ACL_PRIO_MODE_HIGHER		1
-#define ACL_PRIO_MODE_LOWER		2
-#define ACL_PRIO_MODE_REPLACE		3
-#define ACL_PRIO_M			0x7
-#define ACL_PRIO_S			3
-#define ACL_VLAN_PRIO_REPLACE		BIT(2)
-#define ACL_VLAN_PRIO_M			0x7
-#define ACL_VLAN_PRIO_HI_M		0x3
-
-#define ACL_VLAN_PRIO_LO_M		0x8
-#define ACL_VLAN_PRIO_S			7
-#define ACL_MAP_MODE_M			0x3
-#define ACL_MAP_MODE_S			5
-#define ACL_MAP_MODE_DISABLE		0
-#define ACL_MAP_MODE_OR			1
-#define ACL_MAP_MODE_AND		2
-#define ACL_MAP_MODE_REPLACE		3
-#define ACL_MAP_PORT_M			0x1F
-
-#define ACL_CNT_M			(BIT(11) - 1)
-#define ACL_CNT_S			5
-#define ACL_MSEC_UNIT			BIT(4)
-#define ACL_INTR_MODE			BIT(3)
-
-#define REG_PORT_ACL_BYTE_EN_MSB	0x10
-
-#define ACL_BYTE_EN_MSB_M		0x3F
-
-#define REG_PORT_ACL_BYTE_EN_LSB	0x11
-
-#define ACL_ACTION_START		0xA
-#define ACL_ACTION_LEN			2
-#define ACL_INTR_CNT_START		0xB
-#define ACL_RULESET_START		0xC
-#define ACL_RULESET_LEN			2
-#define ACL_TABLE_LEN			14
-
-#define ACL_ACTION_ENABLE		0x000C
-#define ACL_MATCH_ENABLE		0x1FF0
-#define ACL_RULESET_ENABLE		0x2003
-#define ACL_BYTE_ENABLE			((ACL_BYTE_EN_MSB_M << 8) | 0xFF)
-#define ACL_MODE_ENABLE			(0x10 << 8)
-
-#define REG_PORT_ACL_CTRL_0		0x12
-
-#define PORT_ACL_WRITE_DONE		BIT(6)
-#define PORT_ACL_READ_DONE		BIT(5)
-#define PORT_ACL_WRITE			BIT(4)
-#define PORT_ACL_INDEX_M		0xF
-
-#define REG_PORT_ACL_CTRL_1		0x13
-
-#define PORT_ACL_FORCE_DLR_MISS		BIT(0)
-
-#define KSZ8795_ID_HI			0x0022
-#define KSZ8795_ID_LO			0x1550
-#define KSZ8863_ID_LO			0x1430
-
-#define KSZ8795_SW_ID			0x8795
-
-#define PHY_REG_LINK_MD			0x1D
-
-#define PHY_START_CABLE_DIAG		BIT(15)
-#define PHY_CABLE_DIAG_RESULT_M		GENMASK(14, 13)
-#define PHY_CABLE_DIAG_RESULT		0x6000
-#define PHY_CABLE_STAT_NORMAL		0x0000
-#define PHY_CABLE_STAT_OPEN		0x2000
-#define PHY_CABLE_STAT_SHORT		0x4000
-#define PHY_CABLE_STAT_FAILED		0x6000
-#define PHY_CABLE_10M_SHORT		BIT(12)
-#define PHY_CABLE_FAULT_COUNTER_M	GENMASK(8, 0)
-
-#define PHY_REG_PHY_CTRL		0x1F
-
-#define PHY_MODE_M			0x7
-#define PHY_MODE_S			8
-#define PHY_STAT_REVERSED_POLARITY	BIT(5)
-#define PHY_STAT_MDIX			BIT(4)
-#define PHY_FORCE_LINK			BIT(3)
-#define PHY_POWER_SAVING_ENABLE		BIT(2)
-#define PHY_REMOTE_LOOPBACK		BIT(1)
-
-/* Chip resource */
-
-#define PRIO_QUEUES			4
-
-#define KS_PRIO_IN_REG			4
-
-#define MIB_COUNTER_NUM		0x20
-
-/* Common names used by other drivers */
-
-#define P_BCAST_STORM_CTRL		REG_PORT_CTRL_0
-#define P_PRIO_CTRL			REG_PORT_CTRL_0
-#define P_TAG_CTRL			REG_PORT_CTRL_0
-#define P_MIRROR_CTRL			REG_PORT_CTRL_1
-#define P_802_1P_CTRL			REG_PORT_CTRL_2
-#define P_PASS_ALL_CTRL			REG_PORT_CTRL_12
-#define P_INS_SRC_PVID_CTRL		REG_PORT_CTRL_12
-#define P_DROP_TAG_CTRL			REG_PORT_CTRL_13
-#define P_RATE_LIMIT_CTRL		REG_PORT_RATE_LIMIT
-
-#define S_UNKNOWN_DA_CTRL		REG_SWITCH_CTRL_12
-#define S_FORWARD_INVALID_VID_CTRL	REG_FORWARD_INVALID_VID
-
-#define S_FLUSH_TABLE_CTRL		REG_SW_CTRL_0
-#define S_LINK_AGING_CTRL		REG_SW_CTRL_0
-#define S_HUGE_PACKET_CTRL		REG_SW_CTRL_1
-#define S_MIRROR_CTRL			REG_SW_CTRL_3
-#define S_REPLACE_VID_CTRL		REG_SW_CTRL_4
-#define S_PASS_PAUSE_CTRL		REG_SW_CTRL_10
-#define S_802_1P_PRIO_CTRL		REG_SW_CTRL_12
-#define S_TOS_PRIO_CTRL			REG_TOS_PRIO_CTRL_0
-#define S_IPV6_MLD_CTRL			REG_SW_CTRL_21
-
-#define IND_ACC_TABLE(table)		((table) << 8)
-
-/* */
-#define REG_IND_EEE_GLOB2_LO		0x34
-#define REG_IND_EEE_GLOB2_HI		0x35
-
-/**
- * MIB_COUNTER_VALUE			00-00000000-3FFFFFFF
- * MIB_TOTAL_BYTES			00-0000000F-FFFFFFFF
- * MIB_PACKET_DROPPED			00-00000000-0000FFFF
- * MIB_COUNTER_VALID			00-00000020-00000000
- * MIB_COUNTER_OVERFLOW			00-00000040-00000000
- */
-
-#define MIB_COUNTER_VALUE		0x3FFFFFFF
-
-#define KSZ8795_MIB_TOTAL_RX_0		0x100
-#define KSZ8795_MIB_TOTAL_TX_0		0x101
-#define KSZ8795_MIB_TOTAL_RX_1		0x104
-#define KSZ8795_MIB_TOTAL_TX_1		0x105
-
-#define KSZ8863_MIB_PACKET_DROPPED_TX_0 0x100
-#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x105
-
-#define MIB_PACKET_DROPPED		0x0000FFFF
-
-#define MIB_TOTAL_BYTES_H		0x0000000F
-
-#define TAIL_TAG_OVERRIDE		BIT(6)
-#define TAIL_TAG_LOOKUP			BIT(7)
-
-#define FID_ENTRIES			128
-#define KSZ8_DYN_MAC_ENTRIES		1024
-
-#endif
diff --git a/drivers/net/dsa/microchip/ksz8_reg.h b/drivers/net/dsa/microchip/ksz8_reg.h
new file mode 100644
index 000000000000..ff264d57594f
--- /dev/null
+++ b/drivers/net/dsa/microchip/ksz8_reg.h
@@ -0,0 +1,803 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Microchip KSZ8XXX series register definitions
+ *
+ * The base for these definitions is KSZ8795 but unless indicated
+ * differently by their prefix, they apply to all KSZ8 series
+ * devices. Registers and masks that do change are defined in
+ * dedicated structures in ksz_common.c.
+ *
+ * Copyright (c) 2017 Microchip Technology Inc.
+ *	Tristram Ha <Tristram.Ha@microchip.com>
+ */
+
+#ifndef __KSZ8_REG_H
+#define __KSZ8_REG_H
+
+#define KS_PORT_M			0x1F
+
+#define KS_PRIO_M			0x3
+#define KS_PRIO_S			2
+
+#define SW_REVISION_M			0x0E
+#define SW_REVISION_S			1
+
+#define KSZ8863_REG_SW_RESET		0x43
+
+#define KSZ8863_GLOBAL_SOFTWARE_RESET	BIT(4)
+#define KSZ8863_PCS_RESET		BIT(0)
+
+#define KSZ88X3_REG_FVID_AND_HOST_MODE  0xC6
+#define KSZ88X3_PORT3_RMII_CLK_INTERNAL BIT(3)
+
+#define REG_SW_CTRL_0			0x02
+
+#define SW_NEW_BACKOFF			BIT(7)
+#define SW_GLOBAL_RESET			BIT(6)
+#define SW_FLUSH_DYN_MAC_TABLE		BIT(5)
+#define SW_FLUSH_STA_MAC_TABLE		BIT(4)
+#define SW_LINK_AUTO_AGING		BIT(0)
+
+#define REG_SW_CTRL_1			0x03
+
+#define SW_HUGE_PACKET			BIT(6)
+#define SW_TX_FLOW_CTRL_DISABLE		BIT(5)
+#define SW_RX_FLOW_CTRL_DISABLE		BIT(4)
+#define SW_CHECK_LENGTH			BIT(3)
+#define SW_AGING_ENABLE			BIT(2)
+#define SW_FAST_AGING			BIT(1)
+#define SW_AGGR_BACKOFF			BIT(0)
+
+#define REG_SW_CTRL_2			0x04
+
+#define UNICAST_VLAN_BOUNDARY		BIT(7)
+#define SW_BACK_PRESSURE		BIT(5)
+#define FAIR_FLOW_CTRL			BIT(4)
+#define NO_EXC_COLLISION_DROP		BIT(3)
+#define SW_LEGAL_PACKET_DISABLE		BIT(1)
+
+#define KSZ8863_HUGE_PACKET_ENABLE	BIT(2)
+#define KSZ8863_LEGAL_PACKET_ENABLE	BIT(1)
+
+#define REG_SW_CTRL_3			0x05
+ #define WEIGHTED_FAIR_QUEUE_ENABLE	BIT(3)
+
+#define SW_VLAN_ENABLE			BIT(7)
+#define SW_IGMP_SNOOP			BIT(6)
+#define SW_MIRROR_RX_TX			BIT(0)
+
+#define REG_SW_CTRL_4			0x06
+
+#define SW_HALF_DUPLEX_FLOW_CTRL	BIT(7)
+#define SW_HALF_DUPLEX			BIT(6)
+#define SW_FLOW_CTRL			BIT(5)
+#define SW_10_MBIT			BIT(4)
+#define SW_REPLACE_VID			BIT(3)
+
+#define REG_SW_CTRL_5			0x07
+
+#define REG_SW_CTRL_6			0x08
+
+#define SW_MIB_COUNTER_FLUSH		BIT(7)
+#define SW_MIB_COUNTER_FREEZE		BIT(6)
+#define SW_MIB_COUNTER_CTRL_ENABLE	KS_PORT_M
+
+#define REG_SW_CTRL_9			0x0B
+
+#define SPI_CLK_125_MHZ			0x80
+#define SPI_CLK_62_5_MHZ		0x40
+#define SPI_CLK_31_25_MHZ		0x00
+
+#define SW_LED_MODE_M			0x3
+#define SW_LED_MODE_S			4
+#define SW_LED_LINK_ACT_SPEED		0
+#define SW_LED_LINK_ACT			1
+#define SW_LED_LINK_ACT_DUPLEX		2
+#define SW_LED_LINK_DUPLEX		3
+
+#define REG_SW_CTRL_10			0x0C
+
+#define SW_PASS_PAUSE			BIT(0)
+
+#define REG_SW_CTRL_11			0x0D
+
+#define REG_POWER_MANAGEMENT_1		0x0E
+
+#define SW_PLL_POWER_DOWN		BIT(5)
+#define SW_POWER_MANAGEMENT_MODE_M	0x3
+#define SW_POWER_MANAGEMENT_MODE_S	3
+#define SW_POWER_NORMAL			0
+#define SW_ENERGY_DETECTION		1
+#define SW_SOFTWARE_POWER_DOWN		2
+
+#define REG_POWER_MANAGEMENT_2		0x0F
+
+#define REG_PORT_1_CTRL_0		0x10
+#define REG_PORT_2_CTRL_0		0x20
+#define REG_PORT_3_CTRL_0		0x30
+#define REG_PORT_4_CTRL_0		0x40
+#define REG_PORT_5_CTRL_0		0x50
+
+#define PORT_BROADCAST_STORM		BIT(7)
+#define PORT_DIFFSERV_ENABLE		BIT(6)
+#define PORT_802_1P_ENABLE		BIT(5)
+#define PORT_BASED_PRIO_S		3
+#define PORT_BASED_PRIO_M		KS_PRIO_M
+#define PORT_BASED_PRIO_0		0
+#define PORT_BASED_PRIO_1		1
+#define PORT_BASED_PRIO_2		2
+#define PORT_BASED_PRIO_3		3
+#define PORT_INSERT_TAG			BIT(2)
+#define PORT_REMOVE_TAG			BIT(1)
+#define KSZ8795_PORT_2QUEUE_SPLIT_EN	BIT(0)
+#define KSZ8873_PORT_4QUEUE_SPLIT_EN	BIT(0)
+
+#define REG_PORT_1_CTRL_1		0x11
+#define REG_PORT_2_CTRL_1		0x21
+#define REG_PORT_3_CTRL_1		0x31
+#define REG_PORT_4_CTRL_1		0x41
+#define REG_PORT_5_CTRL_1		0x51
+
+#define PORT_MIRROR_SNIFFER		BIT(7)
+#define PORT_MIRROR_RX			BIT(6)
+#define PORT_MIRROR_TX			BIT(5)
+#define PORT_VLAN_MEMBERSHIP		KS_PORT_M
+
+#define REG_PORT_1_CTRL_2		0x12
+#define REG_PORT_2_CTRL_2		0x22
+#define REG_PORT_3_CTRL_2		0x32
+#define REG_PORT_4_CTRL_2		0x42
+#define REG_PORT_5_CTRL_2		0x52
+
+#define KSZ8873_PORT_2QUEUE_SPLIT_EN	BIT(7)
+#define PORT_INGRESS_FILTER		BIT(6)
+#define PORT_DISCARD_NON_VID		BIT(5)
+#define PORT_FORCE_FLOW_CTRL		BIT(4)
+#define PORT_BACK_PRESSURE		BIT(3)
+
+#define REG_PORT_1_CTRL_3		0x13
+#define REG_PORT_2_CTRL_3		0x23
+#define REG_PORT_3_CTRL_3		0x33
+#define REG_PORT_4_CTRL_3		0x43
+#define REG_PORT_5_CTRL_3		0x53
+#define REG_PORT_1_CTRL_4		0x14
+#define REG_PORT_2_CTRL_4		0x24
+#define REG_PORT_3_CTRL_4		0x34
+#define REG_PORT_4_CTRL_4		0x44
+#define REG_PORT_5_CTRL_4		0x54
+
+#define PORT_DEFAULT_VID		0x0001
+
+#define REG_PORT_1_CTRL_5		0x15
+#define REG_PORT_2_CTRL_5		0x25
+#define REG_PORT_3_CTRL_5		0x35
+#define REG_PORT_4_CTRL_5		0x45
+#define REG_PORT_5_CTRL_5		0x55
+
+#define PORT_ACL_ENABLE			BIT(2)
+#define PORT_AUTHEN_MODE		0x3
+#define PORT_AUTHEN_PASS		0
+#define PORT_AUTHEN_BLOCK		1
+#define PORT_AUTHEN_TRAP		2
+
+#define REG_PORT_5_CTRL_6		0x56
+
+#define PORT_MII_INTERNAL_CLOCK		BIT(7)
+#define PORT_GMII_MAC_MODE		BIT(2)
+
+#define REG_PORT_1_CTRL_7		0x17
+#define REG_PORT_2_CTRL_7		0x27
+#define REG_PORT_3_CTRL_7		0x37
+#define REG_PORT_4_CTRL_7		0x47
+
+#define PORT_AUTO_NEG_ASYM_PAUSE	BIT(5)
+#define PORT_AUTO_NEG_SYM_PAUSE		BIT(4)
+#define PORT_AUTO_NEG_100BTX_FD		BIT(3)
+#define PORT_AUTO_NEG_100BTX		BIT(2)
+#define PORT_AUTO_NEG_10BT_FD		BIT(1)
+#define PORT_AUTO_NEG_10BT		BIT(0)
+
+#define REG_PORT_1_STATUS_0		0x18
+#define REG_PORT_2_STATUS_0		0x28
+#define REG_PORT_3_STATUS_0		0x38
+#define REG_PORT_4_STATUS_0		0x48
+
+/* For KSZ8765. */
+#define PORT_REMOTE_ASYM_PAUSE		BIT(5)
+#define PORT_REMOTE_SYM_PAUSE		BIT(4)
+#define PORT_REMOTE_100BTX_FD		BIT(3)
+#define PORT_REMOTE_100BTX		BIT(2)
+#define PORT_REMOTE_10BT_FD		BIT(1)
+#define PORT_REMOTE_10BT		BIT(0)
+
+#define REG_PORT_1_STATUS_1		0x19
+#define REG_PORT_2_STATUS_1		0x29
+#define REG_PORT_3_STATUS_1		0x39
+#define REG_PORT_4_STATUS_1		0x49
+
+#define PORT_HP_MDIX			BIT(7)
+#define PORT_REVERSED_POLARITY		BIT(5)
+#define PORT_TX_FLOW_CTRL		BIT(4)
+#define PORT_RX_FLOW_CTRL		BIT(3)
+#define PORT_STAT_SPEED_100MBIT		BIT(2)
+#define PORT_STAT_FULL_DUPLEX		BIT(1)
+
+#define PORT_REMOTE_FAULT		BIT(0)
+
+#define REG_PORT_1_LINK_MD_CTRL		0x1A
+#define REG_PORT_2_LINK_MD_CTRL		0x2A
+#define REG_PORT_3_LINK_MD_CTRL		0x3A
+#define REG_PORT_4_LINK_MD_CTRL		0x4A
+
+#define PORT_CABLE_10M_SHORT		BIT(7)
+#define PORT_CABLE_DIAG_RESULT_M	GENMASK(6, 5)
+#define PORT_CABLE_DIAG_RESULT_S	5
+#define PORT_CABLE_STAT_NORMAL		0
+#define PORT_CABLE_STAT_OPEN		1
+#define PORT_CABLE_STAT_SHORT		2
+#define PORT_CABLE_STAT_FAILED		3
+#define PORT_START_CABLE_DIAG		BIT(4)
+#define PORT_FORCE_LINK			BIT(3)
+#define PORT_POWER_SAVING		BIT(2)
+#define PORT_PHY_REMOTE_LOOPBACK	BIT(1)
+#define PORT_CABLE_FAULT_COUNTER_H	0x01
+
+#define REG_PORT_1_LINK_MD_RESULT	0x1B
+#define REG_PORT_2_LINK_MD_RESULT	0x2B
+#define REG_PORT_3_LINK_MD_RESULT	0x3B
+#define REG_PORT_4_LINK_MD_RESULT	0x4B
+
+#define PORT_CABLE_FAULT_COUNTER_L	0xFF
+#define PORT_CABLE_FAULT_COUNTER	0x1FF
+
+#define REG_PORT_1_CTRL_9		0x1C
+#define REG_PORT_2_CTRL_9		0x2C
+#define REG_PORT_3_CTRL_9		0x3C
+#define REG_PORT_4_CTRL_9		0x4C
+
+#define PORT_AUTO_NEG_ENABLE		BIT(7)
+#define PORT_AUTO_NEG_DISABLE		BIT(7)
+#define PORT_FORCE_100_MBIT		BIT(6)
+#define PORT_FORCE_FULL_DUPLEX		BIT(5)
+
+#define REG_PORT_1_CTRL_10		0x1D
+#define REG_PORT_2_CTRL_10		0x2D
+#define REG_PORT_3_CTRL_10		0x3D
+#define REG_PORT_4_CTRL_10		0x4D
+
+#define PORT_LED_OFF			BIT(7)
+#define PORT_TX_DISABLE			BIT(6)
+#define PORT_AUTO_NEG_RESTART		BIT(5)
+#define PORT_POWER_DOWN			BIT(3)
+#define PORT_AUTO_MDIX_DISABLE		BIT(2)
+#define PORT_FORCE_MDIX			BIT(1)
+#define PORT_MAC_LOOPBACK		BIT(0)
+#define KSZ8873_PORT_PHY_LOOPBACK	BIT(0)
+
+#define REG_PORT_1_STATUS_2		0x1E
+#define REG_PORT_2_STATUS_2		0x2E
+#define REG_PORT_3_STATUS_2		0x3E
+#define REG_PORT_4_STATUS_2		0x4E
+
+#define PORT_MDIX_STATUS		BIT(7)
+#define PORT_AUTO_NEG_COMPLETE		BIT(6)
+#define PORT_STAT_LINK_GOOD		BIT(5)
+
+#define REG_PORT_1_STATUS_3		0x1F
+#define REG_PORT_2_STATUS_3		0x2F
+#define REG_PORT_3_STATUS_3		0x3F
+#define REG_PORT_4_STATUS_3		0x4F
+
+#define PORT_PHY_LOOPBACK		BIT(7)
+#define PORT_PHY_ISOLATE		BIT(5)
+#define PORT_PHY_SOFT_RESET		BIT(4)
+#define PORT_PHY_FORCE_LINK		BIT(3)
+#define PORT_PHY_MODE_M			0x7
+#define PHY_MODE_IN_AUTO_NEG		1
+#define PHY_MODE_10BT_HALF		2
+#define PHY_MODE_100BT_HALF		3
+#define PHY_MODE_10BT_FULL		5
+#define PHY_MODE_100BT_FULL		6
+#define PHY_MODE_ISOLDATE		7
+
+#define REG_PORT_CTRL_0			0x00
+#define REG_PORT_CTRL_1			0x01
+#define REG_PORT_CTRL_2			0x02
+#define REG_PORT_CTRL_VID		0x03
+
+#define REG_PORT_CTRL_5			0x05
+
+#define REG_PORT_STATUS_1		0x09
+#define REG_PORT_LINK_MD_CTRL		0x0A
+#define REG_PORT_LINK_MD_RESULT		0x0B
+#define REG_PORT_CTRL_9			0x0C
+#define REG_PORT_CTRL_10		0x0D
+#define REG_PORT_STATUS_3		0x0F
+
+#define REG_PORT_CTRL_12		0xA0
+#define REG_PORT_CTRL_13		0xA1
+#define REG_PORT_RATE_CTRL_3		0xA2
+#define REG_PORT_RATE_CTRL_2		0xA3
+#define REG_PORT_RATE_CTRL_1		0xA4
+#define REG_PORT_RATE_CTRL_0		0xA5
+#define REG_PORT_RATE_LIMIT		0xA6
+#define REG_PORT_IN_RATE_0		0xA7
+#define REG_PORT_IN_RATE_1		0xA8
+#define REG_PORT_IN_RATE_2		0xA9
+#define REG_PORT_IN_RATE_3		0xAA
+#define REG_PORT_OUT_RATE_0		0xAB
+#define REG_PORT_OUT_RATE_1		0xAC
+#define REG_PORT_OUT_RATE_2		0xAD
+#define REG_PORT_OUT_RATE_3		0xAE
+
+#define PORT_CTRL_ADDR(port, addr)		\
+	((addr) + REG_PORT_1_CTRL_0 + (port) *	\
+		(REG_PORT_2_CTRL_0 - REG_PORT_1_CTRL_0))
+
+#define TABLE_EXT_SELECT_S		5
+#define TABLE_EEE_V			1
+#define TABLE_ACL_V			2
+#define TABLE_PME_V			4
+#define TABLE_LINK_MD_V			5
+#define TABLE_EEE			(TABLE_EEE_V << TABLE_EXT_SELECT_S)
+#define TABLE_ACL			(TABLE_ACL_V << TABLE_EXT_SELECT_S)
+#define TABLE_PME			(TABLE_PME_V << TABLE_EXT_SELECT_S)
+#define TABLE_LINK_MD			(TABLE_LINK_MD << TABLE_EXT_SELECT_S)
+#define TABLE_READ			BIT(4)
+#define TABLE_SELECT_S			2
+#define TABLE_STATIC_MAC_V		0
+#define TABLE_VLAN_V			1
+#define TABLE_DYNAMIC_MAC_V		2
+#define TABLE_MIB_V			3
+#define TABLE_STATIC_MAC		(TABLE_STATIC_MAC_V << TABLE_SELECT_S)
+#define TABLE_VLAN			(TABLE_VLAN_V << TABLE_SELECT_S)
+#define TABLE_DYNAMIC_MAC		(TABLE_DYNAMIC_MAC_V << TABLE_SELECT_S)
+#define TABLE_MIB			(TABLE_MIB_V << TABLE_SELECT_S)
+
+#define REG_IND_CTRL_1			0x6F
+
+#define TABLE_ENTRY_MASK		0x03FF
+#define TABLE_EXT_ENTRY_MASK		0x0FFF
+
+#define REG_IND_DATA_5			0x73
+#define REG_IND_DATA_2			0x76
+#define REG_IND_DATA_1			0x77
+#define REG_IND_DATA_0			0x78
+
+#define REG_IND_DATA_PME_EEE_ACL	0xA0
+
+#define REG_INT_STATUS			0x7C
+#define REG_INT_ENABLE			0x7D
+
+#define INT_PME				BIT(4)
+
+#define REG_ACL_INT_STATUS		0x7E
+#define REG_ACL_INT_ENABLE		0x7F
+
+#define INT_PORT_5			BIT(4)
+#define INT_PORT_4			BIT(3)
+#define INT_PORT_3			BIT(2)
+#define INT_PORT_2			BIT(1)
+#define INT_PORT_1			BIT(0)
+
+#define INT_PORT_ALL			\
+	(INT_PORT_5 | INT_PORT_4 | INT_PORT_3 | INT_PORT_2 | INT_PORT_1)
+
+#define REG_SW_CTRL_12			0x80
+#define REG_SW_CTRL_13			0x81
+
+#define SWITCH_802_1P_MASK		3
+#define SWITCH_802_1P_BASE		3
+#define SWITCH_802_1P_SHIFT		2
+
+#define SW_802_1P_MAP_M			KS_PRIO_M
+#define SW_802_1P_MAP_S			KS_PRIO_S
+
+#define REG_SWITCH_CTRL_14		0x82
+
+#define SW_PRIO_MAPPING_M		KS_PRIO_M
+#define SW_PRIO_MAPPING_S		6
+#define SW_PRIO_MAP_3_HI		0
+#define SW_PRIO_MAP_2_HI		2
+#define SW_PRIO_MAP_0_LO		3
+
+#define REG_SW_CTRL_15			0x83
+#define REG_SW_CTRL_16			0x84
+#define REG_SW_CTRL_17			0x85
+#define REG_SW_CTRL_18			0x86
+
+#define SW_SELF_ADDR_FILTER_ENABLE	BIT(6)
+
+#define REG_SW_UNK_UCAST_CTRL		0x83
+#define REG_SW_UNK_MCAST_CTRL		0x84
+#define REG_SW_UNK_VID_CTRL		0x85
+#define REG_SW_UNK_IP_MCAST_CTRL	0x86
+
+#define SW_UNK_FWD_ENABLE		BIT(5)
+#define SW_UNK_FWD_MAP			KS_PORT_M
+
+#define REG_SW_CTRL_19			0x87
+
+#define SW_IN_RATE_LIMIT_PERIOD_M	0x3
+#define SW_IN_RATE_LIMIT_PERIOD_S	4
+#define SW_IN_RATE_LIMIT_16_MS		0
+#define SW_IN_RATE_LIMIT_64_MS		1
+#define SW_IN_RATE_LIMIT_256_MS		2
+#define SW_OUT_RATE_LIMIT_QUEUE_BASED	BIT(3)
+#define SW_INS_TAG_ENABLE		BIT(2)
+
+#define REG_TOS_PRIO_CTRL_0		0x90
+#define REG_TOS_PRIO_CTRL_1		0x91
+#define REG_TOS_PRIO_CTRL_2		0x92
+#define REG_TOS_PRIO_CTRL_3		0x93
+#define REG_TOS_PRIO_CTRL_4		0x94
+#define REG_TOS_PRIO_CTRL_5		0x95
+#define REG_TOS_PRIO_CTRL_6		0x96
+#define REG_TOS_PRIO_CTRL_7		0x97
+#define REG_TOS_PRIO_CTRL_8		0x98
+#define REG_TOS_PRIO_CTRL_9		0x99
+#define REG_TOS_PRIO_CTRL_10		0x9A
+#define REG_TOS_PRIO_CTRL_11		0x9B
+#define REG_TOS_PRIO_CTRL_12		0x9C
+#define REG_TOS_PRIO_CTRL_13		0x9D
+#define REG_TOS_PRIO_CTRL_14		0x9E
+#define REG_TOS_PRIO_CTRL_15		0x9F
+
+#define TOS_PRIO_M			KS_PRIO_M
+#define TOS_PRIO_S			KS_PRIO_S
+
+#define REG_SW_CTRL_21			0xA4
+
+#define SW_IPV6_MLD_OPTION		BIT(3)
+#define SW_IPV6_MLD_SNOOP		BIT(2)
+
+#define REG_PORT_1_CTRL_12		0xB0
+#define REG_PORT_2_CTRL_12		0xC0
+#define REG_PORT_3_CTRL_12		0xD0
+#define REG_PORT_4_CTRL_12		0xE0
+#define REG_PORT_5_CTRL_12		0xF0
+
+#define PORT_PASS_ALL			BIT(6)
+#define PORT_INS_TAG_FOR_PORT_5_S	3
+#define PORT_INS_TAG_FOR_PORT_5		BIT(3)
+#define PORT_INS_TAG_FOR_PORT_4		BIT(2)
+#define PORT_INS_TAG_FOR_PORT_3		BIT(1)
+#define PORT_INS_TAG_FOR_PORT_2		BIT(0)
+
+#define REG_PORT_1_CTRL_13		0xB1
+#define REG_PORT_2_CTRL_13		0xC1
+#define REG_PORT_3_CTRL_13		0xD1
+#define REG_PORT_4_CTRL_13		0xE1
+#define REG_PORT_5_CTRL_13		0xF1
+
+#define KSZ8795_PORT_4QUEUE_SPLIT_EN	BIT(1)
+#define PORT_DROP_TAG			BIT(0)
+
+#define REG_PORT_1_CTRL_14		0xB2
+#define REG_PORT_2_CTRL_14		0xC2
+#define REG_PORT_3_CTRL_14		0xD2
+#define REG_PORT_4_CTRL_14		0xE2
+#define REG_PORT_5_CTRL_14		0xF2
+#define REG_PORT_1_CTRL_15		0xB3
+#define REG_PORT_2_CTRL_15		0xC3
+#define REG_PORT_3_CTRL_15		0xD3
+#define REG_PORT_4_CTRL_15		0xE3
+#define REG_PORT_5_CTRL_15		0xF3
+#define REG_PORT_1_CTRL_16		0xB4
+#define REG_PORT_2_CTRL_16		0xC4
+#define REG_PORT_3_CTRL_16		0xD4
+#define REG_PORT_4_CTRL_16		0xE4
+#define REG_PORT_5_CTRL_16		0xF4
+#define REG_PORT_1_CTRL_17		0xB5
+#define REG_PORT_2_CTRL_17		0xC5
+#define REG_PORT_3_CTRL_17		0xD5
+#define REG_PORT_4_CTRL_17		0xE5
+#define REG_PORT_5_CTRL_17		0xF5
+
+#define REG_PORT_1_RATE_CTRL_3		0xB2
+#define REG_PORT_1_RATE_CTRL_2		0xB3
+#define REG_PORT_1_RATE_CTRL_1		0xB4
+#define REG_PORT_1_RATE_CTRL_0		0xB5
+#define REG_PORT_2_RATE_CTRL_3		0xC2
+#define REG_PORT_2_RATE_CTRL_2		0xC3
+#define REG_PORT_2_RATE_CTRL_1		0xC4
+#define REG_PORT_2_RATE_CTRL_0		0xC5
+#define REG_PORT_3_RATE_CTRL_3		0xD2
+#define REG_PORT_3_RATE_CTRL_2		0xD3
+#define REG_PORT_3_RATE_CTRL_1		0xD4
+#define REG_PORT_3_RATE_CTRL_0		0xD5
+#define REG_PORT_4_RATE_CTRL_3		0xE2
+#define REG_PORT_4_RATE_CTRL_2		0xE3
+#define REG_PORT_4_RATE_CTRL_1		0xE4
+#define REG_PORT_4_RATE_CTRL_0		0xE5
+#define REG_PORT_5_RATE_CTRL_3		0xF2
+#define REG_PORT_5_RATE_CTRL_2		0xF3
+#define REG_PORT_5_RATE_CTRL_1		0xF4
+#define REG_PORT_5_RATE_CTRL_0		0xF5
+
+#define RATE_CTRL_ENABLE		BIT(7)
+#define RATE_RATIO_M			(BIT(7) - 1)
+
+#define PORT_OUT_RATE_ENABLE		BIT(7)
+
+#define REG_PORT_1_RATE_LIMIT		0xB6
+#define REG_PORT_2_RATE_LIMIT		0xC6
+#define REG_PORT_3_RATE_LIMIT		0xD6
+#define REG_PORT_4_RATE_LIMIT		0xE6
+#define REG_PORT_5_RATE_LIMIT		0xF6
+
+#define PORT_IN_PORT_BASED_S		6
+#define PORT_RATE_PACKET_BASED_S	5
+#define PORT_IN_FLOW_CTRL_S		4
+#define PORT_IN_LIMIT_MODE_M		0x3
+#define PORT_IN_LIMIT_MODE_S		2
+#define PORT_COUNT_IFG_S		1
+#define PORT_COUNT_PREAMBLE_S		0
+#define PORT_IN_PORT_BASED		BIT(PORT_IN_PORT_BASED_S)
+#define PORT_RATE_PACKET_BASED		BIT(PORT_RATE_PACKET_BASED_S)
+#define PORT_IN_FLOW_CTRL		BIT(PORT_IN_FLOW_CTRL_S)
+#define PORT_IN_ALL			0
+#define PORT_IN_UNICAST			1
+#define PORT_IN_MULTICAST		2
+#define PORT_IN_BROADCAST		3
+#define PORT_COUNT_IFG			BIT(PORT_COUNT_IFG_S)
+#define PORT_COUNT_PREAMBLE		BIT(PORT_COUNT_PREAMBLE_S)
+
+#define REG_PORT_1_IN_RATE_0		0xB7
+#define REG_PORT_2_IN_RATE_0		0xC7
+#define REG_PORT_3_IN_RATE_0		0xD7
+#define REG_PORT_4_IN_RATE_0		0xE7
+#define REG_PORT_5_IN_RATE_0		0xF7
+#define REG_PORT_1_IN_RATE_1		0xB8
+#define REG_PORT_2_IN_RATE_1		0xC8
+#define REG_PORT_3_IN_RATE_1		0xD8
+#define REG_PORT_4_IN_RATE_1		0xE8
+#define REG_PORT_5_IN_RATE_1		0xF8
+#define REG_PORT_1_IN_RATE_2		0xB9
+#define REG_PORT_2_IN_RATE_2		0xC9
+#define REG_PORT_3_IN_RATE_2		0xD9
+#define REG_PORT_4_IN_RATE_2		0xE9
+#define REG_PORT_5_IN_RATE_2		0xF9
+#define REG_PORT_1_IN_RATE_3		0xBA
+#define REG_PORT_2_IN_RATE_3		0xCA
+#define REG_PORT_3_IN_RATE_3		0xDA
+#define REG_PORT_4_IN_RATE_3		0xEA
+#define REG_PORT_5_IN_RATE_3		0xFA
+
+#define PORT_IN_RATE_ENABLE		BIT(7)
+#define PORT_RATE_LIMIT_M		(BIT(7) - 1)
+
+#define REG_PORT_1_OUT_RATE_0		0xBB
+#define REG_PORT_2_OUT_RATE_0		0xCB
+#define REG_PORT_3_OUT_RATE_0		0xDB
+#define REG_PORT_4_OUT_RATE_0		0xEB
+#define REG_PORT_5_OUT_RATE_0		0xFB
+#define REG_PORT_1_OUT_RATE_1		0xBC
+#define REG_PORT_2_OUT_RATE_1		0xCC
+#define REG_PORT_3_OUT_RATE_1		0xDC
+#define REG_PORT_4_OUT_RATE_1		0xEC
+#define REG_PORT_5_OUT_RATE_1		0xFC
+#define REG_PORT_1_OUT_RATE_2		0xBD
+#define REG_PORT_2_OUT_RATE_2		0xCD
+#define REG_PORT_3_OUT_RATE_2		0xDD
+#define REG_PORT_4_OUT_RATE_2		0xED
+#define REG_PORT_5_OUT_RATE_2		0xFD
+#define REG_PORT_1_OUT_RATE_3		0xBE
+#define REG_PORT_2_OUT_RATE_3		0xCE
+#define REG_PORT_3_OUT_RATE_3		0xDE
+#define REG_PORT_4_OUT_RATE_3		0xEE
+#define REG_PORT_5_OUT_RATE_3		0xFE
+
+/* 88x3 specific */
+
+#define REG_SW_INSERT_SRC_PVID		0xC2
+
+/* PME */
+
+#define SW_PME_OUTPUT_ENABLE		BIT(1)
+#define SW_PME_ACTIVE_HIGH		BIT(0)
+
+#define PORT_MAGIC_PACKET_DETECT	BIT(2)
+#define PORT_LINK_UP_DETECT		BIT(1)
+#define PORT_ENERGY_DETECT		BIT(0)
+
+/* ACL */
+
+#define ACL_FIRST_RULE_M		0xF
+
+#define ACL_MODE_M			0x3
+#define ACL_MODE_S			4
+#define ACL_MODE_DISABLE		0
+#define ACL_MODE_LAYER_2		1
+#define ACL_MODE_LAYER_3		2
+#define ACL_MODE_LAYER_4		3
+#define ACL_ENABLE_M			0x3
+#define ACL_ENABLE_S			2
+#define ACL_ENABLE_2_COUNT		0
+#define ACL_ENABLE_2_TYPE		1
+#define ACL_ENABLE_2_MAC		2
+#define ACL_ENABLE_2_BOTH		3
+#define ACL_ENABLE_3_IP			1
+#define ACL_ENABLE_3_SRC_DST_COMP	2
+#define ACL_ENABLE_4_PROTOCOL		0
+#define ACL_ENABLE_4_TCP_PORT_COMP	1
+#define ACL_ENABLE_4_UDP_PORT_COMP	2
+#define ACL_ENABLE_4_TCP_SEQN_COMP	3
+#define ACL_SRC				BIT(1)
+#define ACL_EQUAL			BIT(0)
+
+#define ACL_MAX_PORT			0xFFFF
+
+#define ACL_MIN_PORT			0xFFFF
+#define ACL_IP_ADDR			0xFFFFFFFF
+#define ACL_TCP_SEQNUM			0xFFFFFFFF
+
+#define ACL_RESERVED			0xF8
+#define ACL_PORT_MODE_M			0x3
+#define ACL_PORT_MODE_S			1
+#define ACL_PORT_MODE_DISABLE		0
+#define ACL_PORT_MODE_EITHER		1
+#define ACL_PORT_MODE_IN_RANGE		2
+#define ACL_PORT_MODE_OUT_OF_RANGE	3
+
+#define ACL_TCP_FLAG_ENABLE		BIT(0)
+
+#define ACL_TCP_FLAG_M			0xFF
+
+#define ACL_TCP_FLAG			0xFF
+#define ACL_ETH_TYPE			0xFFFF
+#define ACL_IP_M			0xFFFFFFFF
+
+#define ACL_PRIO_MODE_M			0x3
+#define ACL_PRIO_MODE_S			6
+#define ACL_PRIO_MODE_DISABLE		0
+#define ACL_PRIO_MODE_HIGHER		1
+#define ACL_PRIO_MODE_LOWER		2
+#define ACL_PRIO_MODE_REPLACE		3
+#define ACL_PRIO_M			0x7
+#define ACL_PRIO_S			3
+#define ACL_VLAN_PRIO_REPLACE		BIT(2)
+#define ACL_VLAN_PRIO_M			0x7
+#define ACL_VLAN_PRIO_HI_M		0x3
+
+#define ACL_VLAN_PRIO_LO_M		0x8
+#define ACL_VLAN_PRIO_S			7
+#define ACL_MAP_MODE_M			0x3
+#define ACL_MAP_MODE_S			5
+#define ACL_MAP_MODE_DISABLE		0
+#define ACL_MAP_MODE_OR			1
+#define ACL_MAP_MODE_AND		2
+#define ACL_MAP_MODE_REPLACE		3
+#define ACL_MAP_PORT_M			0x1F
+
+#define ACL_CNT_M			(BIT(11) - 1)
+#define ACL_CNT_S			5
+#define ACL_MSEC_UNIT			BIT(4)
+#define ACL_INTR_MODE			BIT(3)
+
+#define REG_PORT_ACL_BYTE_EN_MSB	0x10
+
+#define ACL_BYTE_EN_MSB_M		0x3F
+
+#define REG_PORT_ACL_BYTE_EN_LSB	0x11
+
+#define ACL_ACTION_START		0xA
+#define ACL_ACTION_LEN			2
+#define ACL_INTR_CNT_START		0xB
+#define ACL_RULESET_START		0xC
+#define ACL_RULESET_LEN			2
+#define ACL_TABLE_LEN			14
+
+#define ACL_ACTION_ENABLE		0x000C
+#define ACL_MATCH_ENABLE		0x1FF0
+#define ACL_RULESET_ENABLE		0x2003
+#define ACL_BYTE_ENABLE			((ACL_BYTE_EN_MSB_M << 8) | 0xFF)
+#define ACL_MODE_ENABLE			(0x10 << 8)
+
+#define REG_PORT_ACL_CTRL_0		0x12
+
+#define PORT_ACL_WRITE_DONE		BIT(6)
+#define PORT_ACL_READ_DONE		BIT(5)
+#define PORT_ACL_WRITE			BIT(4)
+#define PORT_ACL_INDEX_M		0xF
+
+#define REG_PORT_ACL_CTRL_1		0x13
+
+#define PORT_ACL_FORCE_DLR_MISS		BIT(0)
+
+#define KSZ8795_ID_HI			0x0022
+#define KSZ8795_ID_LO			0x1550
+#define KSZ8863_ID_LO			0x1430
+
+#define KSZ8795_SW_ID			0x8795
+
+#define PHY_REG_LINK_MD			0x1D
+
+#define PHY_START_CABLE_DIAG		BIT(15)
+#define PHY_CABLE_DIAG_RESULT_M		GENMASK(14, 13)
+#define PHY_CABLE_DIAG_RESULT		0x6000
+#define PHY_CABLE_STAT_NORMAL		0x0000
+#define PHY_CABLE_STAT_OPEN		0x2000
+#define PHY_CABLE_STAT_SHORT		0x4000
+#define PHY_CABLE_STAT_FAILED		0x6000
+#define PHY_CABLE_10M_SHORT		BIT(12)
+#define PHY_CABLE_FAULT_COUNTER_M	GENMASK(8, 0)
+
+#define PHY_REG_PHY_CTRL		0x1F
+
+#define PHY_MODE_M			0x7
+#define PHY_MODE_S			8
+#define PHY_STAT_REVERSED_POLARITY	BIT(5)
+#define PHY_STAT_MDIX			BIT(4)
+#define PHY_FORCE_LINK			BIT(3)
+#define PHY_POWER_SAVING_ENABLE		BIT(2)
+#define PHY_REMOTE_LOOPBACK		BIT(1)
+
+/* Chip resource */
+
+#define PRIO_QUEUES			4
+
+#define KS_PRIO_IN_REG			4
+
+#define MIB_COUNTER_NUM		0x20
+
+/* Common names used by other drivers */
+
+#define P_BCAST_STORM_CTRL		REG_PORT_CTRL_0
+#define P_PRIO_CTRL			REG_PORT_CTRL_0
+#define P_TAG_CTRL			REG_PORT_CTRL_0
+#define P_MIRROR_CTRL			REG_PORT_CTRL_1
+#define P_802_1P_CTRL			REG_PORT_CTRL_2
+#define P_PASS_ALL_CTRL			REG_PORT_CTRL_12
+#define P_INS_SRC_PVID_CTRL		REG_PORT_CTRL_12
+#define P_DROP_TAG_CTRL			REG_PORT_CTRL_13
+#define P_RATE_LIMIT_CTRL		REG_PORT_RATE_LIMIT
+
+#define S_UNKNOWN_DA_CTRL		REG_SWITCH_CTRL_12
+#define S_FORWARD_INVALID_VID_CTRL	REG_FORWARD_INVALID_VID
+
+#define S_FLUSH_TABLE_CTRL		REG_SW_CTRL_0
+#define S_LINK_AGING_CTRL		REG_SW_CTRL_0
+#define S_HUGE_PACKET_CTRL		REG_SW_CTRL_1
+#define S_MIRROR_CTRL			REG_SW_CTRL_3
+#define S_REPLACE_VID_CTRL		REG_SW_CTRL_4
+#define S_PASS_PAUSE_CTRL		REG_SW_CTRL_10
+#define S_802_1P_PRIO_CTRL		REG_SW_CTRL_12
+#define S_TOS_PRIO_CTRL			REG_TOS_PRIO_CTRL_0
+#define S_IPV6_MLD_CTRL			REG_SW_CTRL_21
+
+#define IND_ACC_TABLE(table)		((table) << 8)
+
+/* */
+#define REG_IND_EEE_GLOB2_LO		0x34
+#define REG_IND_EEE_GLOB2_HI		0x35
+
+/**
+ * MIB_COUNTER_VALUE			00-00000000-3FFFFFFF
+ * MIB_TOTAL_BYTES			00-0000000F-FFFFFFFF
+ * MIB_PACKET_DROPPED			00-00000000-0000FFFF
+ * MIB_COUNTER_VALID			00-00000020-00000000
+ * MIB_COUNTER_OVERFLOW			00-00000040-00000000
+ */
+
+#define MIB_COUNTER_VALUE		0x3FFFFFFF
+
+#define KSZ8795_MIB_TOTAL_RX_0		0x100
+#define KSZ8795_MIB_TOTAL_TX_0		0x101
+#define KSZ8795_MIB_TOTAL_RX_1		0x104
+#define KSZ8795_MIB_TOTAL_TX_1		0x105
+
+#define KSZ8863_MIB_PACKET_DROPPED_TX_0 0x100
+#define KSZ8863_MIB_PACKET_DROPPED_RX_0 0x105
+
+#define MIB_PACKET_DROPPED		0x0000FFFF
+
+#define MIB_TOTAL_BYTES_H		0x0000000F
+
+#define TAIL_TAG_OVERRIDE		BIT(6)
+#define TAIL_TAG_LOOKUP			BIT(7)
+
+#define FID_ENTRIES			128
+#define KSZ8_DYN_MAC_ENTRIES		1024
+
+#endif
-- 
cgit v1.3-3-g829e


From dcff1c05f28395c8e7cec7e7143e6565f64d8b2a Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Wed, 4 Sep 2024 08:27:41 +0200
Subject: net: dsa: microchip: clean up ksz8_reg definition macros

Remove macros that are already defined at more appropriate places.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8_reg.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8_reg.h b/drivers/net/dsa/microchip/ksz8_reg.h
index ff264d57594f..329688603a58 100644
--- a/drivers/net/dsa/microchip/ksz8_reg.h
+++ b/drivers/net/dsa/microchip/ksz8_reg.h
@@ -364,8 +364,6 @@
 #define REG_IND_DATA_1			0x77
 #define REG_IND_DATA_0			0x78
 
-#define REG_IND_DATA_PME_EEE_ACL	0xA0
-
 #define REG_INT_STATUS			0x7C
 #define REG_INT_ENABLE			0x7D
 
@@ -709,8 +707,6 @@
 #define KSZ8795_ID_LO			0x1550
 #define KSZ8863_ID_LO			0x1430
 
-#define KSZ8795_SW_ID			0x8795
-
 #define PHY_REG_LINK_MD			0x1D
 
 #define PHY_START_CABLE_DIAG		BIT(15)
-- 
cgit v1.3-3-g829e


From 23de126f9248a2f9218175ea0dd1c1403e334440 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Wed, 4 Sep 2024 08:27:42 +0200
Subject: net: dsa: microchip: replace unclear KSZ8830 strings

Replace ksz8830 with ksz88x3 for CHIP_ID definition and other
strings. This due to KSZ8830 not being an actual switch but the Chip
ID shared among KSZ8863/8873 switches, impossible to differentiate
from their Chip ID or Revision ID registers.

Now all KSZ*_CHIP_ID macros refer to actual, existing switches which
removes confusion.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8.c            |  2 +-
 drivers/net/dsa/microchip/ksz8863_smi.c     |  4 +--
 drivers/net/dsa/microchip/ksz_common.c      | 48 ++++++++++++++---------------
 drivers/net/dsa/microchip/ksz_common.h      |  4 +--
 drivers/net/dsa/microchip/ksz_spi.c         |  6 ++--
 include/linux/platform_data/microchip-ksz.h |  2 +-
 6 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index 7af3c0853505..da7110d67558 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -194,7 +194,7 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu)
 	case KSZ8794_CHIP_ID:
 	case KSZ8765_CHIP_ID:
 		return ksz8795_change_mtu(dev, frame_size);
-	case KSZ8830_CHIP_ID:
+	case KSZ88X3_CHIP_ID:
 	case KSZ8864_CHIP_ID:
 	case KSZ8895_CHIP_ID:
 		return ksz8863_change_mtu(dev, frame_size);
diff --git a/drivers/net/dsa/microchip/ksz8863_smi.c b/drivers/net/dsa/microchip/ksz8863_smi.c
index 5711a59e2ac9..a8bfcd917bf7 100644
--- a/drivers/net/dsa/microchip/ksz8863_smi.c
+++ b/drivers/net/dsa/microchip/ksz8863_smi.c
@@ -199,11 +199,11 @@ static void ksz8863_smi_shutdown(struct mdio_device *mdiodev)
 static const struct of_device_id ksz8863_dt_ids[] = {
 	{
 		.compatible = "microchip,ksz8863",
-		.data = &ksz_switch_chips[KSZ8830]
+		.data = &ksz_switch_chips[KSZ88X3]
 	},
 	{
 		.compatible = "microchip,ksz8873",
-		.data = &ksz_switch_chips[KSZ8830]
+		.data = &ksz_switch_chips[KSZ88X3]
 	},
 	{ },
 };
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index cd116de3ddb8..4e8710c7cb7b 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -246,16 +246,16 @@ static const struct ksz_drive_strength ksz9477_drive_strengths[] = {
 	{ SW_DRIVE_STRENGTH_28MA, 28000 },
 };
 
-/* ksz8830_drive_strengths - Drive strength mapping for KSZ8830, KSZ8873, ..
+/* ksz88x3_drive_strengths - Drive strength mapping for KSZ8863, KSZ8873, ..
  *			     variants.
  * This values are documented in KSZ8873 and KSZ8863 datasheets.
  */
-static const struct ksz_drive_strength ksz8830_drive_strengths[] = {
+static const struct ksz_drive_strength ksz88x3_drive_strengths[] = {
 	{ 0,  8000 },
 	{ KSZ8873_DRIVE_STRENGTH_16MA, 16000 },
 };
 
-static void ksz8830_phylink_mac_config(struct phylink_config *config,
+static void ksz88x3_phylink_mac_config(struct phylink_config *config,
 				       unsigned int mode,
 				       const struct phylink_link_state *state);
 static void ksz_phylink_mac_config(struct phylink_config *config,
@@ -265,8 +265,8 @@ static void ksz_phylink_mac_link_down(struct phylink_config *config,
 				      unsigned int mode,
 				      phy_interface_t interface);
 
-static const struct phylink_mac_ops ksz8830_phylink_mac_ops = {
-	.mac_config	= ksz8830_phylink_mac_config,
+static const struct phylink_mac_ops ksz88x3_phylink_mac_ops = {
+	.mac_config	= ksz88x3_phylink_mac_config,
 	.mac_link_down	= ksz_phylink_mac_link_down,
 	.mac_link_up	= ksz8_phylink_mac_link_up,
 };
@@ -1442,8 +1442,8 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.internal_phy = {true, true, true, true, false},
 	},
 
-	[KSZ8830] = {
-		.chip_id = KSZ8830_CHIP_ID,
+	[KSZ88X3] = {
+		.chip_id = KSZ88X3_CHIP_ID,
 		.dev_name = "KSZ8863/KSZ8873",
 		.num_vlans = 16,
 		.num_alus = 0,
@@ -1453,7 +1453,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.num_tx_queues = 4,
 		.num_ipms = 4,
 		.ops = &ksz88xx_dev_ops,
-		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
+		.phylink_mac_ops = &ksz88x3_phylink_mac_ops,
 		.mib_names = ksz88xx_mib_names,
 		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
 		.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -1487,7 +1487,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.num_tx_queues = 4,
 		.num_ipms = 4,
 		.ops = &ksz88xx_dev_ops,
-		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
+		.phylink_mac_ops = &ksz88x3_phylink_mac_ops,
 		.mib_names = ksz88xx_mib_names,
 		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
 		.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -1510,7 +1510,7 @@ const struct ksz_chip_data ksz_switch_chips[] = {
 		.num_tx_queues = 4,
 		.num_ipms = 4,
 		.ops = &ksz88xx_dev_ops,
-		.phylink_mac_ops = &ksz8830_phylink_mac_ops,
+		.phylink_mac_ops = &ksz88x3_phylink_mac_ops,
 		.mib_names = ksz88xx_mib_names,
 		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
 		.reg_mib_cnt = MIB_COUNTER_NUM,
@@ -2724,7 +2724,7 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
 	struct ksz_device *dev = ds->priv;
 
 	switch (dev->chip_id) {
-	case KSZ8830_CHIP_ID:
+	case KSZ88X3_CHIP_ID:
 		/* Silicon Errata Sheet (DS80000830A):
 		 * Port 1 does not work with LinkMD Cable-Testing.
 		 * Port 1 does not respond to received PAUSE control frames.
@@ -3050,7 +3050,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 	if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev))
 		proto = DSA_TAG_PROTO_KSZ8795;
 
-	if (dev->chip_id == KSZ8830_CHIP_ID ||
+	if (dev->chip_id == KSZ88X3_CHIP_ID ||
 	    dev->chip_id == KSZ8563_CHIP_ID ||
 	    dev->chip_id == KSZ9893_CHIP_ID ||
 	    dev->chip_id == KSZ9563_CHIP_ID)
@@ -3162,7 +3162,7 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
 	case KSZ8794_CHIP_ID:
 	case KSZ8765_CHIP_ID:
 		return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
-	case KSZ8830_CHIP_ID:
+	case KSZ88X3_CHIP_ID:
 	case KSZ8864_CHIP_ID:
 	case KSZ8895_CHIP_ID:
 		return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
@@ -3334,7 +3334,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit)
 	return interface;
 }
 
-static void ksz8830_phylink_mac_config(struct phylink_config *config,
+static void ksz88x3_phylink_mac_config(struct phylink_config *config,
 				       unsigned int mode,
 				       const struct phylink_link_state *state)
 {
@@ -3518,7 +3518,7 @@ static int ksz_switch_detect(struct ksz_device *dev)
 		break;
 	case KSZ88_FAMILY_ID:
 		if (id2 == KSZ88_CHIP_ID_63)
-			dev->chip_id = KSZ8830_CHIP_ID;
+			dev->chip_id = KSZ88X3_CHIP_ID;
 		else
 			return -ENODEV;
 		break;
@@ -4592,24 +4592,24 @@ static int ksz9477_drive_strength_write(struct ksz_device *dev,
 }
 
 /**
- * ksz8830_drive_strength_write() - Set the drive strength configuration for
- *				    KSZ8830 compatible chip variants.
+ * ksz88x3_drive_strength_write() - Set the drive strength configuration for
+ *				    KSZ8863 compatible chip variants.
  * @dev:       ksz device
  * @props:     Array of drive strength properties to be set
  * @num_props: Number of properties in the array
  *
- * This function applies the specified drive strength settings to KSZ8830 chip
+ * This function applies the specified drive strength settings to KSZ88X3 chip
  * variants (KSZ8873, KSZ8863).
  * It ensures the configurations align with what the chip variant supports and
  * warns or errors out on unsupported settings.
  *
  * Return: 0 on success, error code otherwise
  */
-static int ksz8830_drive_strength_write(struct ksz_device *dev,
+static int ksz88x3_drive_strength_write(struct ksz_device *dev,
 					struct ksz_driver_strength_prop *props,
 					int num_props)
 {
-	size_t array_size = ARRAY_SIZE(ksz8830_drive_strengths);
+	size_t array_size = ARRAY_SIZE(ksz88x3_drive_strengths);
 	int microamp;
 	int i, ret;
 
@@ -4622,10 +4622,10 @@ static int ksz8830_drive_strength_write(struct ksz_device *dev,
 	}
 
 	microamp = props[KSZ_DRIVER_STRENGTH_IO].value;
-	ret = ksz_drive_strength_to_reg(ksz8830_drive_strengths, array_size,
+	ret = ksz_drive_strength_to_reg(ksz88x3_drive_strengths, array_size,
 					microamp);
 	if (ret < 0) {
-		ksz_drive_strength_error(dev, ksz8830_drive_strengths,
+		ksz_drive_strength_error(dev, ksz88x3_drive_strengths,
 					 array_size, microamp);
 		return ret;
 	}
@@ -4685,8 +4685,8 @@ static int ksz_parse_drive_strength(struct ksz_device *dev)
 		return 0;
 
 	switch (dev->chip_id) {
-	case KSZ8830_CHIP_ID:
-		return ksz8830_drive_strength_write(dev, of_props,
+	case KSZ88X3_CHIP_ID:
+		return ksz88x3_drive_strength_write(dev, of_props,
 						    ARRAY_SIZE(of_props));
 	case KSZ8795_CHIP_ID:
 	case KSZ8794_CHIP_ID:
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index e08d5a1339f4..bec846e20682 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -200,7 +200,7 @@ enum ksz_model {
 	KSZ8795,
 	KSZ8794,
 	KSZ8765,
-	KSZ8830,
+	KSZ88X3,
 	KSZ8864,
 	KSZ8895,
 	KSZ9477,
@@ -628,7 +628,7 @@ static inline bool ksz_is_ksz87xx(struct ksz_device *dev)
 
 static inline bool ksz_is_ksz88x3(struct ksz_device *dev)
 {
-	return dev->chip_id == KSZ8830_CHIP_ID;
+	return dev->chip_id == KSZ88X3_CHIP_ID;
 }
 
 static inline bool ksz_is_8895_family(struct ksz_device *dev)
diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c
index f4287310e89f..e3e341431f09 100644
--- a/drivers/net/dsa/microchip/ksz_spi.c
+++ b/drivers/net/dsa/microchip/ksz_spi.c
@@ -54,7 +54,7 @@ static int ksz_spi_probe(struct spi_device *spi)
 	if (!chip)
 		return -EINVAL;
 
-	if (chip->chip_id == KSZ8830_CHIP_ID)
+	if (chip->chip_id == KSZ88X3_CHIP_ID)
 		regmap_config = ksz8863_regmap_config;
 	else if (chip->chip_id == KSZ8795_CHIP_ID ||
 		 chip->chip_id == KSZ8794_CHIP_ID ||
@@ -137,7 +137,7 @@ static const struct of_device_id ksz_dt_ids[] = {
 	},
 	{
 		.compatible = "microchip,ksz8863",
-		.data = &ksz_switch_chips[KSZ8830]
+		.data = &ksz_switch_chips[KSZ88X3]
 	},
 	{
 		.compatible = "microchip,ksz8864",
@@ -145,7 +145,7 @@ static const struct of_device_id ksz_dt_ids[] = {
 	},
 	{
 		.compatible = "microchip,ksz8873",
-		.data = &ksz_switch_chips[KSZ8830]
+		.data = &ksz_switch_chips[KSZ88X3]
 	},
 	{
 		.compatible = "microchip,ksz8895",
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index d074019474f5..2ee1a679e592 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -27,7 +27,7 @@ enum ksz_chip_id {
 	KSZ8795_CHIP_ID = 0x8795,
 	KSZ8794_CHIP_ID = 0x8794,
 	KSZ8765_CHIP_ID = 0x8765,
-	KSZ8830_CHIP_ID = 0x8830,
+	KSZ88X3_CHIP_ID = 0x8830,
 	KSZ8864_CHIP_ID = 0x8864,
 	KSZ8895_CHIP_ID = 0x8895,
 	KSZ9477_CHIP_ID = 0x00947700,
-- 
cgit v1.3-3-g829e


From b9c4d16e2a47213a83d25f6ff5e95df324ffef0c Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:08 +0300
Subject: lan743x: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 3a63ec091413..0f1c0edec460 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -1034,16 +1034,12 @@ static int lan743x_ethtool_get_ts_info(struct net_device *netdev,
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 
 	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				   SOF_TIMESTAMPING_RX_SOFTWARE |
-				   SOF_TIMESTAMPING_SOFTWARE |
 				   SOF_TIMESTAMPING_TX_HARDWARE |
 				   SOF_TIMESTAMPING_RX_HARDWARE |
 				   SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (adapter->ptp.ptp_clock)
 		ts_info->phc_index = ptp_clock_index(adapter->ptp.ptp_clock);
-	else
-		ts_info->phc_index = -1;
 
 	ts_info->tx_types = BIT(HWTSTAMP_TX_OFF) |
 			    BIT(HWTSTAMP_TX_ON) |
-- 
cgit v1.3-3-g829e


From f592435d132ca47e8f4d1df392c99a90a07efaa6 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:09 +0300
Subject: net: lan966x: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c
index aec7066d83b3..2474dfd330f4 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c
@@ -549,16 +549,13 @@ static int lan966x_get_ts_info(struct net_device *dev,
 
 	phc = &lan966x->phc[LAN966X_PHC_PORT];
 
-	info->phc_index = phc->clock ? ptp_clock_index(phc->clock) : -1;
-	if (info->phc_index == -1) {
-		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-					 SOF_TIMESTAMPING_RX_SOFTWARE |
-					 SOF_TIMESTAMPING_SOFTWARE;
+	if (phc->clock) {
+		info->phc_index = ptp_clock_index(phc->clock);
+	} else {
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
 		return 0;
 	}
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-				 SOF_TIMESTAMPING_RX_SOFTWARE |
-				 SOF_TIMESTAMPING_SOFTWARE |
 				 SOF_TIMESTAMPING_TX_HARDWARE |
 				 SOF_TIMESTAMPING_RX_HARDWARE |
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 35461b6d5802a1168613a7cae9eb77d8be0da2f9 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:10 +0300
Subject: net: sparx5: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c
index 4f800c1a435d..d898a7238b48 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c
@@ -1194,16 +1194,13 @@ static int sparx5_get_ts_info(struct net_device *dev,
 
 	phc = &sparx5->phc[SPARX5_PHC_PORT];
 
-	info->phc_index = phc->clock ? ptp_clock_index(phc->clock) : -1;
-	if (info->phc_index == -1) {
-		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-					 SOF_TIMESTAMPING_RX_SOFTWARE |
-					 SOF_TIMESTAMPING_SOFTWARE;
+	if (phc->clock) {
+		info->phc_index = ptp_clock_index(phc->clock);
+	} else {
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
 		return 0;
 	}
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-				 SOF_TIMESTAMPING_RX_SOFTWARE |
-				 SOF_TIMESTAMPING_SOFTWARE |
 				 SOF_TIMESTAMPING_TX_HARDWARE |
 				 SOF_TIMESTAMPING_RX_HARDWARE |
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 8a26d947176635a7b96505b8f0b15f2596a0cb8f Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:11 +0300
Subject: mlxsw: spectrum: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  6 ++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h | 20 --------------------
 2 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b9ffd7236aff..3f5e5d99251b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2786,7 +2786,9 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = {
 	.hwtstamp_get	= mlxsw_sp1_ptp_hwtstamp_get,
 	.hwtstamp_set	= mlxsw_sp1_ptp_hwtstamp_set,
 	.shaper_work	= mlxsw_sp1_ptp_shaper_work,
+#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
 	.get_ts_info	= mlxsw_sp1_ptp_get_ts_info,
+#endif
 	.get_stats_count = mlxsw_sp1_get_stats_count,
 	.get_stats_strings = mlxsw_sp1_get_stats_strings,
 	.get_stats	= mlxsw_sp1_get_stats,
@@ -2803,7 +2805,9 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
 	.hwtstamp_get	= mlxsw_sp2_ptp_hwtstamp_get,
 	.hwtstamp_set	= mlxsw_sp2_ptp_hwtstamp_set,
 	.shaper_work	= mlxsw_sp2_ptp_shaper_work,
+#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
 	.get_ts_info	= mlxsw_sp2_ptp_get_ts_info,
+#endif
 	.get_stats_count = mlxsw_sp2_get_stats_count,
 	.get_stats_strings = mlxsw_sp2_get_stats_strings,
 	.get_stats	= mlxsw_sp2_get_stats,
@@ -2820,7 +2824,9 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = {
 	.hwtstamp_get	= mlxsw_sp2_ptp_hwtstamp_get,
 	.hwtstamp_set	= mlxsw_sp2_ptp_hwtstamp_set,
 	.shaper_work	= mlxsw_sp2_ptp_shaper_work,
+#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
 	.get_ts_info	= mlxsw_sp2_ptp_get_ts_info,
+#endif
 	.get_stats_count = mlxsw_sp2_get_stats_count,
 	.get_stats_strings = mlxsw_sp2_get_stats_strings,
 	.get_stats	= mlxsw_sp2_get_stats,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
index 769095d4932d..c8aa1452fbb9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h
@@ -11,14 +11,6 @@ struct mlxsw_sp;
 struct mlxsw_sp_port;
 struct mlxsw_sp_ptp_clock;
 
-static inline int mlxsw_sp_ptp_get_ts_info_noptp(struct kernel_ethtool_ts_info *info)
-{
-	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
-	info->phc_index = -1;
-	return 0;
-}
-
 #if IS_REACHABLE(CONFIG_PTP_1588_CLOCK)
 
 struct mlxsw_sp_ptp_clock *
@@ -151,12 +143,6 @@ static inline void mlxsw_sp1_ptp_shaper_work(struct work_struct *work)
 {
 }
 
-static inline int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-					    struct kernel_ethtool_ts_info *info)
-{
-	return mlxsw_sp_ptp_get_ts_info_noptp(info);
-}
-
 static inline int mlxsw_sp1_get_stats_count(void)
 {
 	return 0;
@@ -226,12 +212,6 @@ mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 	return -EOPNOTSUPP;
 }
 
-static inline int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp,
-					    struct kernel_ethtool_ts_info *info)
-{
-	return mlxsw_sp_ptp_get_ts_info_noptp(info);
-}
-
 static inline int
 mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core,
 			      struct mlxsw_sp_port *mlxsw_sp_port,
-- 
cgit v1.3-3-g829e


From f40a3712ef1be1b3114d81114edff961ee2c1860 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:12 +0300
Subject: net: ethernet: ti: am65-cpsw-ethtool: Remove setting of RX software
 timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
index b60976947da5..539d5ca82f52 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
@@ -714,8 +714,6 @@ static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev,
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->phc_index = am65_cpts_phc_index(common->cpts);
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
-- 
cgit v1.3-3-g829e


From c76e2f40b7d9aa87fddd22cc2452dd4c822dd6fa Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:13 +0300
Subject: net: ethernet: ti: cpsw_ethtool: Remove setting of RX software
 timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ethtool.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index 53ed23d68722..21d55a180ef6 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -725,8 +725,6 @@ int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *inf
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->phc_index = cpsw->cpts->phc_index;
 	info->tx_types =
@@ -741,10 +739,7 @@ int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *inf
 int cpsw_get_ts_info(struct net_device *ndev, struct kernel_ethtool_ts_info *info)
 {
 	info->so_timestamping =
-		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE;
-	info->phc_index = -1;
+		SOF_TIMESTAMPING_TX_SOFTWARE;
 	info->tx_types = 0;
 	info->rx_filters = 0;
 	return 0;
-- 
cgit v1.3-3-g829e


From c5dbb6aeefbda74d8b523f291a7ac081c4c00aca Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:14 +0300
Subject: net: ti: icssg-prueth: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
index 5073ec195854..73b6cef10401 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -119,8 +119,6 @@ static int emac_get_ts_info(struct net_device *ndev,
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	info->phc_index = icss_iep_get_ptp_clock_idx(emac->iep);
-- 
cgit v1.3-3-g829e


From f9b74d602ee3a43a2c85a8cd444ae7f939fa338b Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:15 +0300
Subject: net: netcp: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/netcp_ethss.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index d286709ca3b9..63e686f0b119 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -2012,8 +2012,6 @@ static int keystone_get_ts_info(struct net_device *ndev,
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 	info->phc_index = gbe_intf->gbe_dev->cpts->phc_index;
 	info->tx_types =
@@ -2030,10 +2028,7 @@ static int keystone_get_ts_info(struct net_device *ndev,
 				struct kernel_ethtool_ts_info *info)
 {
 	info->so_timestamping =
-		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE;
-	info->phc_index = -1;
+		SOF_TIMESTAMPING_TX_SOFTWARE;
 	info->tx_types = 0;
 	info->rx_filters = 0;
 	return 0;
-- 
cgit v1.3-3-g829e


From 5df20ce03ef431ad820023bccb355f6de5f7f75c Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:16 +0300
Subject: i40e: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 3a6bece623f4..f2506511bbff 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2555,16 +2555,12 @@ static int i40e_get_ts_info(struct net_device *dev,
 		return ethtool_op_get_ts_info(dev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (pf->ptp_clock)
 		info->phc_index = ptp_clock_index(pf->ptp_clock);
-	else
-		info->phc_index = -1;
 
 	info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON);
 
-- 
cgit v1.3-3-g829e


From 6aebd824f45ab51b22148bf0100682cdcfbf4e87 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:17 +0300
Subject: ice: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index c7641d326ba5..793a64d44aa3 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3792,8 +3792,6 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info)
 		return ethtool_op_get_ts_info(dev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 638effa35d684fb89113f7541eb58a98641cff86 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:18 +0300
Subject: igb: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_ethtool.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 06b9970dffad..ca6ccbc13954 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2387,15 +2387,11 @@ static int igb_get_ts_info(struct net_device *dev,
 
 	if (adapter->ptp_clock)
 		info->phc_index = ptp_clock_index(adapter->ptp_clock);
-	else
-		info->phc_index = -1;
 
 	switch (adapter->hw.mac.type) {
 	case e1000_82575:
 		info->so_timestamping =
-			SOF_TIMESTAMPING_TX_SOFTWARE |
-			SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE;
+			SOF_TIMESTAMPING_TX_SOFTWARE;
 		return 0;
 	case e1000_82576:
 	case e1000_82580:
@@ -2405,8 +2401,6 @@ static int igb_get_ts_info(struct net_device *dev,
 	case e1000_i211:
 		info->so_timestamping =
 			SOF_TIMESTAMPING_TX_SOFTWARE |
-			SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE |
 			SOF_TIMESTAMPING_TX_HARDWARE |
 			SOF_TIMESTAMPING_RX_HARDWARE |
 			SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 29d2e49a62c14b7b25068acad6f9800c3425e129 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:19 +0300
Subject: igc: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igc/igc_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
index 457b5d7f1610..5b0c6f433767 100644
--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -1569,15 +1569,11 @@ static int igc_ethtool_get_ts_info(struct net_device *dev,
 
 	if (adapter->ptp_clock)
 		info->phc_index = ptp_clock_index(adapter->ptp_clock);
-	else
-		info->phc_index = -1;
 
 	switch (adapter->hw.mac.type) {
 	case igc_i225:
 		info->so_timestamping =
 			SOF_TIMESTAMPING_TX_SOFTWARE |
-			SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE |
 			SOF_TIMESTAMPING_TX_HARDWARE |
 			SOF_TIMESTAMPING_RX_HARDWARE |
 			SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 12283fad6d2ea43450a28de4394a756a401fa71c Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:20 +0300
Subject: ixgbe: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 4cac76254966..9482e0cca8b7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -3196,16 +3196,12 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (adapter->ptp_clock)
 		info->phc_index = ptp_clock_index(adapter->ptp_clock);
-	else
-		info->phc_index = -1;
 
 	info->tx_types =
 		BIT(HWTSTAMP_TX_OFF) |
-- 
cgit v1.3-3-g829e


From 4c6d910e0254206e2438d4481b3ceeda7355cf83 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:21 +0300
Subject: cxgb4: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Potnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index 3d091947ae00..7f3f5afa864f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -1556,12 +1556,9 @@ static int get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts
 	struct  adapter *adapter = pi->adapter;
 
 	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				   SOF_TIMESTAMPING_RX_SOFTWARE |
-				   SOF_TIMESTAMPING_SOFTWARE;
-
-	ts_info->so_timestamping |= SOF_TIMESTAMPING_RX_HARDWARE |
-				    SOF_TIMESTAMPING_TX_HARDWARE |
-				    SOF_TIMESTAMPING_RAW_HARDWARE;
+				   SOF_TIMESTAMPING_RX_HARDWARE |
+				   SOF_TIMESTAMPING_TX_HARDWARE |
+				   SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	ts_info->tx_types = (1 << HWTSTAMP_TX_OFF) |
 			    (1 << HWTSTAMP_TX_ON);
@@ -1575,8 +1572,6 @@ static int get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *ts
 
 	if (adapter->ptp_clock)
 		ts_info->phc_index = ptp_clock_index(adapter->ptp_clock);
-	else
-		ts_info->phc_index = -1;
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 26f74155df44fdcbc1962a7f404be6a8eec895e0 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 4 Sep 2024 10:49:22 +0300
Subject: bnx2x: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index c7b56a5e5425..adf7b6b94941 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -3640,16 +3640,12 @@ static int bnx2x_get_ts_info(struct net_device *dev,
 
 	if (bp->flags & PTP_SUPPORTED) {
 		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-					SOF_TIMESTAMPING_RX_SOFTWARE |
-					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_TX_HARDWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 
 		if (bp->ptp_clock)
 			info->phc_index = ptp_clock_index(bp->ptp_clock);
-		else
-			info->phc_index = -1;
 
 		info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 				   (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
-- 
cgit v1.3-3-g829e


From ded1a6d9e13a32d4e8bef0c63accf49b9415ff5f Mon Sep 17 00:00:00 2001
From: Rex Lu <rex.lu@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:33 +0800
Subject: wifi: mt76: mt7996: fix handling mbss enable/disable

When mbss was previously enabled, the TLV needs to be included when
disabling it again, in order to clear the firmware state.

Fixes: a7908d5b61e5 ("wifi: mt76: mt7996: fix non-main BSS no beacon issue for MBSS scenario")
Signed-off-by: Rex Lu <rex.lu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-9-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 238b1f78ff7c..e8d34bfbb41a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -822,7 +822,7 @@ mt7996_mcu_bss_mbssid_tlv(struct sk_buff *skb, struct ieee80211_vif *vif,
 	struct bss_info_uni_mbssid *mbssid;
 	struct tlv *tlv;
 
-	if (!vif->bss_conf.bssid_indicator)
+	if (!vif->bss_conf.bssid_indicator && enable)
 		return;
 
 	tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_11V_MBSSID, sizeof(*mbssid));
-- 
cgit v1.3-3-g829e


From 5353679ab4ada1112ff96e81c08650dd01699050 Mon Sep 17 00:00:00 2001
From: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:34 +0800
Subject: wifi: mt76: connac: add IEEE 802.11 fragmentation support for mt7996

Add fragment index into TXD.DW2 to support IEEE 802.11 fragmentation.

Signed-off-by: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-10-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h |  7 +++++++
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c       | 13 +++++++++++--
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index 353e66069840..3fc94bd7271f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -197,6 +197,13 @@ enum tx_mgnt_type {
 	MT_TX_ADDBA,
 };
 
+enum tx_frag_idx {
+	MT_TX_FRAG_NONE,
+	MT_TX_FRAG_FIRST,
+	MT_TX_FRAG_MID,
+	MT_TX_FRAG_LAST
+};
+
 #define MT_CT_INFO_APPLY_TXD		BIT(0)
 #define MT_CT_INFO_COPY_HOST_TXD_ALL	BIT(1)
 #define MT_CT_INFO_MGMT_FRAME		BIT(2)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index bc7111a71f98..60446dc2a3b3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -746,7 +746,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	bool multicast = is_multicast_ether_addr(hdr->addr1);
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
-	__le16 fc = hdr->frame_control;
+	__le16 fc = hdr->frame_control, sc = hdr->seq_ctrl;
 	u8 fc_type, fc_stype;
 	u32 val;
 
@@ -780,6 +780,15 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	val = FIELD_PREP(MT_TXD2_FRAME_TYPE, fc_type) |
 	      FIELD_PREP(MT_TXD2_SUB_TYPE, fc_stype);
 
+	if (ieee80211_has_morefrags(fc) && ieee80211_is_first_frag(sc))
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_FIRST);
+	else if (ieee80211_has_morefrags(fc) && !ieee80211_is_first_frag(sc))
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_MID);
+	else if (!ieee80211_has_morefrags(fc) && !ieee80211_is_first_frag(sc))
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_LAST);
+	else
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_NONE);
+
 	txwi[2] |= cpu_to_le32(val);
 
 	txwi[3] |= cpu_to_le32(FIELD_PREP(MT_TXD3_BCM, multicast));
@@ -789,7 +798,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	}
 
 	if (info->flags & IEEE80211_TX_CTL_INJECTED) {
-		u16 seqno = le16_to_cpu(hdr->seq_ctrl);
+		u16 seqno = le16_to_cpu(sc);
 
 		if (ieee80211_is_back_req(hdr->frame_control)) {
 			struct ieee80211_bar *bar;
-- 
cgit v1.3-3-g829e


From dcd21b27f1364560570dd2fed09fd56ab9314cd3 Mon Sep 17 00:00:00 2001
From: Michael-CY Lee <michael-cy.lee@mediatek.com>
Date: Fri, 16 Aug 2024 17:46:35 +0800
Subject: wifi: mt76: mt7996: set IEEE80211_KEY_FLAG_GENERATE_MMIE for other
 ciphers

When beacon protection is enabled, FW checks MMIE tag & length in the
beacon for every cipher mode. To pass the check, driver needs to set the
key flag IEEE80211_KEY_GENERATE_MMIE to let mac80211 generate and
initialize MMIE.

Signed-off-by: Michael-CY Lee <michael-cy.lee@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20240816094635.2391-11-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 1ab2fb292266..d43bd5c2432e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -364,14 +364,14 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	case WLAN_CIPHER_SUITE_SMS4:
 		break;
 	case WLAN_CIPHER_SUITE_AES_CMAC:
-		wcid_keyidx = &wcid->hw_key_idx2;
-		key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE;
-		fallthrough;
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
 	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
-		if (key->keyidx == 6 || key->keyidx == 7)
+		if (key->keyidx == 6 || key->keyidx == 7) {
+			wcid_keyidx = &wcid->hw_key_idx2;
+			key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE;
 			break;
+		}
 		fallthrough;
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_WEP104:
-- 
cgit v1.3-3-g829e


From f503ae90c7355e8506e68498fe84c1357894cd5b Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Tue, 13 Aug 2024 16:12:42 +0800
Subject: wifi: mt76: mt7996: fix NULL pointer dereference in
 mt7996_mcu_sta_bfer_he

Fix the NULL pointer dereference in mt7996_mcu_sta_bfer_he
routine adding an sta interface to the mt7996 driver.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Link: https://patch.msgid.link/20240813081242.3991814-1-make24@iscas.ac.cn
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index e8d34bfbb41a..8855095fef10 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1544,6 +1544,9 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
 	u8 nss_mcs = mt7996_mcu_get_sta_nss(mcs_map);
 	u8 snd_dim, sts;
 
+	if (!vc)
+		return;
+
 	bf->tx_mode = MT_PHY_TYPE_HE_SU;
 
 	mt7996_mcu_sta_sounding_rate(bf);
-- 
cgit v1.3-3-g829e


From a04b920fbc707deb699292cdae47006e8ea57d87 Mon Sep 17 00:00:00 2001
From: Peter Chiu <chui-hao.chiu@mediatek.com>
Date: Fri, 16 Aug 2024 17:50:40 +0800
Subject: wifi: mt76: connac: fix checksum offload fields of connac3 RXD

Fix incorrect RXD offset and bitfield related to RX checksum offload.

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Fixes: 4e9011fcdfc4 ("wifi: mt76: connac: move connac3 definitions in mt76_connac3_mac.h")
Co-developed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Link: https://patch.msgid.link/20240816095040.2574-1-shayne.chen@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h | 4 ++--
 drivers/net/wireless/mediatek/mt76/mt7925/mac.c       | 5 ++---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c       | 4 ++--
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index 3fc94bd7271f..db0c29e65185 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -28,8 +28,6 @@ enum {
 #define MT_RXD0_MESH			BIT(18)
 #define MT_RXD0_MHCP			BIT(19)
 #define MT_RXD0_NORMAL_ETH_TYPE_OFS	GENMASK(22, 16)
-#define MT_RXD0_NORMAL_IP_SUM		BIT(23)
-#define MT_RXD0_NORMAL_UDP_TCP_SUM	BIT(24)
 
 #define MT_RXD0_SW_PKT_TYPE_MASK	GENMASK(31, 16)
 #define MT_RXD0_SW_PKT_TYPE_MAP		0x380F
@@ -80,6 +78,8 @@ enum {
 #define MT_RXD3_NORMAL_BEACON_UC	BIT(21)
 #define MT_RXD3_NORMAL_CO_ANT		BIT(22)
 #define MT_RXD3_NORMAL_FCS_ERR		BIT(24)
+#define MT_RXD3_NORMAL_IP_SUM		BIT(26)
+#define MT_RXD3_NORMAL_UDP_TCP_SUM	BIT(27)
 #define MT_RXD3_NORMAL_VLAN2ETH		BIT(31)
 
 /* RXD DW4 */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
index cf36750cf709..634c42bbf23f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
@@ -352,7 +352,7 @@ mt7925_mac_fill_rx_rate(struct mt792x_dev *dev,
 static int
 mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 {
-	u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM;
+	u32 csum_mask = MT_RXD3_NORMAL_IP_SUM | MT_RXD3_NORMAL_UDP_TCP_SUM;
 	struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
 	bool hdr_trans, unicast, insert_ccmp_hdr = false;
 	u8 chfreq, qos_ctl = 0, remove_pad, amsdu_info;
@@ -362,7 +362,6 @@ mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 	struct mt792x_phy *phy = &dev->phy;
 	struct ieee80211_supported_band *sband;
 	u32 csum_status = *(u32 *)skb->cb;
-	u32 rxd0 = le32_to_cpu(rxd[0]);
 	u32 rxd1 = le32_to_cpu(rxd[1]);
 	u32 rxd2 = le32_to_cpu(rxd[2]);
 	u32 rxd3 = le32_to_cpu(rxd[3]);
@@ -420,7 +419,7 @@ mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
 	if (!sband->channels)
 		return -EINVAL;
 
-	if (mt76_is_mmio(&dev->mt76) && (rxd0 & csum_mask) == csum_mask &&
+	if (mt76_is_mmio(&dev->mt76) && (rxd3 & csum_mask) == csum_mask &&
 	    !(csum_status & (BIT(0) | BIT(2) | BIT(3))))
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 60446dc2a3b3..0d21414e2c88 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -435,7 +435,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
 	u32 rxd2 = le32_to_cpu(rxd[2]);
 	u32 rxd3 = le32_to_cpu(rxd[3]);
 	u32 rxd4 = le32_to_cpu(rxd[4]);
-	u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM;
+	u32 csum_mask = MT_RXD3_NORMAL_IP_SUM | MT_RXD3_NORMAL_UDP_TCP_SUM;
 	u32 csum_status = *(u32 *)skb->cb;
 	u32 mesh_mask = MT_RXD0_MESH | MT_RXD0_MHCP;
 	bool is_mesh = (rxd0 & mesh_mask) == mesh_mask;
@@ -497,7 +497,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
 	if (!sband->channels)
 		return -EINVAL;
 
-	if ((rxd0 & csum_mask) == csum_mask &&
+	if ((rxd3 & csum_mask) == csum_mask &&
 	    !(csum_status & (BIT(0) | BIT(2) | BIT(3))))
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-- 
cgit v1.3-3-g829e


From 9b8d932053b8b45d650360b36f701cf0f9b6470e Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:48 +0200
Subject: wifi: mt76: mt7603: fix mixed declarations and code

Move the qid variable declaration further up

Fixes: b473c0e47f04 ("wifi: mt76: mt7603: fix tx queue of loopback packets")
Link: https://patch.msgid.link/20240827093011.18621-1-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7603/dma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
index ea017f22fff2..863e5770df51 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
@@ -29,7 +29,7 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
 	struct ieee80211_sta *sta;
 	struct mt7603_sta *msta;
 	struct mt76_wcid *wcid;
-	u8 tid = 0, hwq = 0;
+	u8 qid, tid = 0, hwq = 0;
 	void *priv;
 	int idx;
 	u32 val;
@@ -57,7 +57,7 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
 	if (ieee80211_is_data_qos(hdr->frame_control)) {
 		tid = *ieee80211_get_qos_ctl(hdr) &
 			 IEEE80211_QOS_CTL_TAG1D_MASK;
-		u8 qid = tid_to_ac[tid];
+		qid = tid_to_ac[tid];
 		hwq = wmm_queue_map[qid];
 		skb_set_queue_mapping(skb, qid);
 	} else if (ieee80211_is_data(hdr->frame_control)) {
-- 
cgit v1.3-3-g829e


From 3dd99b8f20154708ed51b5059ed5e260108d3bed Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:49 +0200
Subject: wifi: mt76: mt7603: fix reading target power from eeprom

If the ext-PA target power is unset, fall back to the standard EEPROM value.

Link: https://patch.msgid.link/20240827093011.18621-2-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7603/init.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
index 6c55c72f28a2..f84c9a06af75 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
@@ -456,11 +456,13 @@ mt7603_init_txpower(struct mt7603_dev *dev,
 	int target_power = eeprom[MT_EE_TX_POWER_0_START_2G + 2] & ~BIT(7);
 	u8 *rate_power = &eeprom[MT_EE_TX_POWER_CCK];
 	bool ext_pa = eeprom[MT_EE_NIC_CONF_0 + 1] & BIT(1);
+	u8 ext_pa_pwr;
 	int max_offset, cur_offset;
 	int i;
 
-	if (ext_pa && is_mt7603(dev))
-		target_power = eeprom[MT_EE_TX_POWER_TSSI_OFF] & ~BIT(7);
+	ext_pa_pwr = eeprom[MT_EE_TX_POWER_TSSI_OFF];
+	if (ext_pa && is_mt7603(dev) && ext_pa_pwr != 0 && ext_pa_pwr != 0xff)
+		target_power = ext_pa_pwr & ~BIT(7);
 
 	if (target_power & BIT(6))
 		target_power = -(target_power & GENMASK(5, 0));
-- 
cgit v1.3-3-g829e


From 6ea13e6bd2af76e9e4de4534d9ac5500fb3266ba Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:50 +0200
Subject: wifi: mt76: mt7603: initialize chainmask

Fixes reported tx power by accounting for the combined output

Link: https://patch.msgid.link/20240827093011.18621-3-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c
index d951cb81df83..f5a6b03bc61d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/eeprom.c
@@ -181,6 +181,7 @@ int mt7603_eeprom_init(struct mt7603_dev *dev)
 	    is_mt7688(dev))
 		dev->mphy.antenna_mask = 1;
 
+	dev->mphy.chainmask = dev->mphy.antenna_mask;
 	mt76_eeprom_override(&dev->mphy);
 
 	return 0;
-- 
cgit v1.3-3-g829e


From e43b87f6b7bbcde8a33a14c173e5f56c03fe9221 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:51 +0200
Subject: wifi: mt76: fix mt76_get_rate

Do not assume that the first phy has 2 GHz support.
Check sband->band instead of accessing dev->phy.sband_2g.

Link: https://patch.msgid.link/20240827093011.18621-4-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index d96ee759828e..8733906fcb21 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1697,14 +1697,15 @@ int mt76_get_rate(struct mt76_dev *dev,
 		  struct ieee80211_supported_band *sband,
 		  int idx, bool cck)
 {
+	bool is_2g = sband->band == NL80211_BAND_2GHZ;
 	int i, offset = 0, len = sband->n_bitrates;
 
 	if (cck) {
-		if (sband != &dev->phy.sband_2g.sband)
+		if (!is_2g)
 			return 0;
 
 		idx &= ~BIT(2); /* short preamble */
-	} else if (sband == &dev->phy.sband_2g.sband) {
+	} else if (is_2g) {
 		offset = 4;
 	}
 
-- 
cgit v1.3-3-g829e


From f4fdd7716290a2fb342ec84f55140c1d436e6f4b Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Wed, 28 Aug 2024 08:34:22 +0200
Subject: wifi: mt76: partially move channel change code to core

This allows the core code to change the channel. Code deduplication and
preparation for adding scanning code to the core.

Link: https://patch.msgid.link/20240828063422.44813-1-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c      | 37 +++++++++++++++++++---
 drivers/net/wireless/mediatek/mt76/mt76.h          |  6 +++-
 drivers/net/wireless/mediatek/mt76/mt7603/beacon.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7603/init.c   |  1 +
 drivers/net/wireless/mediatek/mt76/mt7603/main.c   | 27 ++++------------
 drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h |  1 +
 drivers/net/wireless/mediatek/mt76/mt7615/main.c   | 27 ++++------------
 drivers/net/wireless/mediatek/mt76/mt7615/mcu.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7615/mmio.c   |  1 +
 drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7615/sdio.c   |  1 +
 .../net/wireless/mediatek/mt76/mt7615/testmode.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7615/usb.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   | 21 ++++++------
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt76x02_usb_core.c  |  5 +--
 drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h |  2 ++
 drivers/net/wireless/mediatek/mt76/mt76x2/pci.c    |  1 +
 .../net/wireless/mediatek/mt76/mt76x2/pci_main.c   | 25 ++++-----------
 drivers/net/wireless/mediatek/mt76/mt76x2/usb.c    |  1 +
 .../net/wireless/mediatek/mt76/mt76x2/usb_main.c   | 25 +++------------
 drivers/net/wireless/mediatek/mt76/mt7915/main.c   | 19 ++---------
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7915/mmio.c   |  1 +
 drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h |  2 +-
 .../net/wireless/mediatek/mt76/mt7915/testmode.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/main.c   | 23 ++++----------
 drivers/net/wireless/mediatek/mt76/mt7921/mcu.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h |  1 +
 drivers/net/wireless/mediatek/mt76/mt7921/pci.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt7921/sdio.c   |  1 +
 drivers/net/wireless/mediatek/mt76/mt7921/usb.c    |  1 +
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   | 23 +++-----------
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/mmio.c   |  1 +
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h |  2 +-
 39 files changed, 116 insertions(+), 162 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 8733906fcb21..a24186c9a913 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -929,13 +929,19 @@ void mt76_update_survey(struct mt76_phy *phy)
 }
 EXPORT_SYMBOL_GPL(mt76_update_survey);
 
-void mt76_set_channel(struct mt76_phy *phy)
+int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef,
+		     bool offchannel)
 {
 	struct mt76_dev *dev = phy->dev;
-	struct ieee80211_hw *hw = phy->hw;
-	struct cfg80211_chan_def *chandef = &hw->conf.chandef;
-	bool offchannel = hw->conf.flags & IEEE80211_CONF_OFFCHANNEL;
 	int timeout = HZ / 5;
+	int ret;
+
+	cancel_delayed_work_sync(&phy->mac_work);
+
+	mutex_lock(&dev->mutex);
+	set_bit(MT76_RESET, &phy->state);
+
+	ieee80211_stop_queues(phy->hw);
 
 	wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(phy), timeout);
 	mt76_update_survey(phy);
@@ -946,14 +952,35 @@ void mt76_set_channel(struct mt76_phy *phy)
 
 	phy->chandef = *chandef;
 	phy->chan_state = mt76_channel_state(phy, chandef->chan);
+	phy->offchannel = offchannel;
 
 	if (!offchannel)
 		phy->main_chan = chandef->chan;
 
 	if (chandef->chan != phy->main_chan)
 		memset(phy->chan_state, 0, sizeof(*phy->chan_state));
+
+	ret = dev->drv->set_channel(phy);
+
+	clear_bit(MT76_RESET, &phy->state);
+	ieee80211_wake_queues(phy->hw);
+
+	mt76_worker_schedule(&dev->tx_worker);
+
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+int mt76_update_channel(struct mt76_phy *phy)
+{
+	struct ieee80211_hw *hw = phy->hw;
+	struct cfg80211_chan_def *chandef = &hw->conf.chandef;
+	bool offchannel = hw->conf.flags & IEEE80211_CONF_OFFCHANNEL;
+
+	return mt76_set_channel(phy, chandef, offchannel);
 }
-EXPORT_SYMBOL_GPL(mt76_set_channel);
+EXPORT_SYMBOL_GPL(mt76_update_channel);
 
 int mt76_get_survey(struct ieee80211_hw *hw, int idx,
 		    struct survey_info *survey)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 4a58a78d5ed2..6c054f43e7ce 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -487,6 +487,7 @@ struct mt76_driver_ops {
 	u8 mcs_rates;
 
 	void (*update_survey)(struct mt76_phy *phy);
+	int (*set_channel)(struct mt76_phy *phy);
 
 	int (*tx_prepare_skb)(struct mt76_dev *dev, void *txwi_ptr,
 			      enum mt76_txq_id qid, struct mt76_wcid *wcid,
@@ -768,6 +769,7 @@ struct mt76_phy {
 
 	struct cfg80211_chan_def chandef;
 	struct ieee80211_channel *main_chan;
+	bool offchannel;
 
 	struct mt76_channel_state *chan_state;
 	enum mt76_dfs_state dfs_state;
@@ -1370,7 +1372,7 @@ void mt76_release_buffered_frames(struct ieee80211_hw *hw,
 				  enum ieee80211_frame_release_type reason,
 				  bool more_data);
 bool mt76_has_tx_pending(struct mt76_phy *phy);
-void mt76_set_channel(struct mt76_phy *phy);
+int mt76_update_channel(struct mt76_phy *phy);
 void mt76_update_survey(struct mt76_phy *phy);
 void mt76_update_survey_active_time(struct mt76_phy *phy, ktime_t time);
 int mt76_get_survey(struct ieee80211_hw *hw, int idx,
@@ -1484,6 +1486,8 @@ void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames);
 void mt76_testmode_tx_pending(struct mt76_phy *phy);
 void mt76_queue_tx_complete(struct mt76_dev *dev, struct mt76_queue *q,
 			    struct mt76_queue_entry *e);
+int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef,
+		     bool offchannel);
 
 /* usb */
 static inline bool mt76u_urb_error(struct urb *urb)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
index c223f7c19e6d..6457ee06bb5a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
@@ -107,7 +107,7 @@ void mt7603_pre_tbtt_tasklet(struct tasklet_struct *t)
 	struct sk_buff *skb;
 	int i, nframes;
 
-	if (mt76_hw(dev)->conf.flags & IEEE80211_CONF_OFFCHANNEL)
+	if (dev->mphy.offchannel)
 		return;
 
 	data.dev = dev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
index f84c9a06af75..1528a8be7762 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
@@ -18,6 +18,7 @@ const struct mt76_driver_ops mt7603_drv_ops = {
 	.sta_assoc = mt7603_sta_assoc,
 	.sta_remove = mt7603_sta_remove,
 	.update_survey = mt7603_update_channel,
+	.set_channel = mt7603_set_channel,
 };
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index f35fa643c0da..3d3a4cc2bab1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -133,30 +133,24 @@ void mt7603_init_edcca(struct mt7603_dev *dev)
 	mt7603_edcca_set_strict(dev, false);
 }
 
-static int
-mt7603_set_channel(struct ieee80211_hw *hw, struct cfg80211_chan_def *def)
+int mt7603_set_channel(struct mt76_phy *mphy)
 {
-	struct mt7603_dev *dev = hw->priv;
+	struct mt7603_dev *dev = container_of(mphy->dev, struct mt7603_dev, mt76);
+	struct cfg80211_chan_def *def = &mphy->chandef;
+
 	u8 *rssi_data = (u8 *)dev->mt76.eeprom.data;
 	int idx, ret;
 	u8 bw = MT_BW_20;
 	bool failed = false;
 
-	ieee80211_stop_queues(hw);
-	cancel_delayed_work_sync(&dev->mphy.mac_work);
 	tasklet_disable(&dev->mt76.pre_tbtt_tasklet);
 
-	mutex_lock(&dev->mt76.mutex);
-	set_bit(MT76_RESET, &dev->mphy.state);
-
 	mt7603_beacon_set_timer(dev, -1, 0);
-	mt76_set_channel(&dev->mphy);
 	mt7603_mac_stop(dev);
 
 	if (def->width == NL80211_CHAN_WIDTH_40)
 		bw = MT_BW_40;
 
-	dev->mphy.chandef = *def;
 	mt76_rmw_field(dev, MT_AGG_BWCR, MT_AGG_BWCR_BW, bw);
 	ret = mt7603_mcu_set_channel(dev);
 	if (ret) {
@@ -180,10 +174,6 @@ mt7603_set_channel(struct ieee80211_hw *hw, struct cfg80211_chan_def *def)
 	mt7603_mac_set_timing(dev);
 	mt7603_mac_start(dev);
 
-	clear_bit(MT76_RESET, &dev->mphy.state);
-
-	mt76_txq_schedule_all(&dev->mphy);
-
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mphy.mac_work,
 				     msecs_to_jiffies(MT7603_WATCHDOG_TIME));
 
@@ -199,17 +189,14 @@ mt7603_set_channel(struct ieee80211_hw *hw, struct cfg80211_chan_def *def)
 	mt7603_init_edcca(dev);
 
 out:
-	if (!(mt76_hw(dev)->conf.flags & IEEE80211_CONF_OFFCHANNEL))
+	if (!mphy->offchannel)
 		mt7603_beacon_set_timer(dev, -1, dev->mt76.beacon_int);
-	mutex_unlock(&dev->mt76.mutex);
 
 	tasklet_enable(&dev->mt76.pre_tbtt_tasklet);
 
 	if (failed)
 		mt7603_mac_work(&dev->mphy.mac_work.work);
 
-	ieee80211_wake_queues(hw);
-
 	return ret;
 }
 
@@ -227,7 +214,7 @@ static int mt7603_set_sar_specs(struct ieee80211_hw *hw,
 	if (err)
 		return err;
 
-	return mt7603_set_channel(hw, &mphy->chandef);
+	return mt76_update_channel(mphy);
 }
 
 static int
@@ -238,7 +225,7 @@ mt7603_config(struct ieee80211_hw *hw, u32 changed)
 
 	if (changed & (IEEE80211_CONF_CHANGE_CHANNEL |
 		       IEEE80211_CONF_CHANGE_POWER))
-		ret = mt7603_set_channel(hw, &hw->conf.chandef);
+		ret = mt76_update_channel(&dev->mphy);
 
 	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
 		mutex_lock(&dev->mt76.mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index 9e58df7042ad..dbdfe596f29e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -213,6 +213,7 @@ void mt7603_mac_sta_poll(struct mt7603_dev *dev);
 
 void mt7603_pse_client_reset(struct mt7603_dev *dev);
 
+int mt7603_set_channel(struct mt76_phy *mphy);
 int mt7603_mcu_set_channel(struct mt7603_dev *dev);
 int mt7603_mcu_set_eeprom(struct mt7603_dev *dev);
 void mt7603_mcu_exit(struct mt7603_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
index 50e262c1622f..376975388007 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c
@@ -282,19 +282,14 @@ static void mt7615_remove_interface(struct ieee80211_hw *hw,
 	mt76_wcid_cleanup(&dev->mt76, &mvif->sta.wcid);
 }
 
-int mt7615_set_channel(struct mt7615_phy *phy)
+int mt7615_set_channel(struct mt76_phy *mphy)
 {
+	struct mt7615_phy *phy = mphy->priv;
 	struct mt7615_dev *dev = phy->dev;
 	bool ext_phy = phy != &dev->phy;
 	int ret;
 
-	cancel_delayed_work_sync(&phy->mt76->mac_work);
-
-	mt7615_mutex_acquire(dev);
-
-	set_bit(MT76_RESET, &phy->mt76->state);
-
-	mt76_set_channel(phy->mt76);
+	mt76_connac_pm_wake(mphy, &dev->pm);
 
 	if (is_mt7615(&dev->mt76) && dev->flash_eeprom) {
 		ret = mt7615_mcu_apply_rx_dcoc(phy);
@@ -325,11 +320,8 @@ int mt7615_set_channel(struct mt7615_phy *phy)
 	phy->chfreq = mt76_rr(dev, MT_CHFREQ(ext_phy));
 
 out:
-	clear_bit(MT76_RESET, &phy->mt76->state);
+	mt76_connac_power_save_sched(mphy, &dev->pm);
 
-	mt7615_mutex_release(dev);
-
-	mt76_worker_schedule(&dev->mt76.tx_worker);
 	if (!mt76_testmode_enabled(phy->mt76)) {
 		unsigned long timeout = mt7615_get_macwork_timeout(dev);
 
@@ -339,6 +331,7 @@ out:
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mt7615_set_channel);
 
 static int mt7615_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			  struct ieee80211_vif *vif, struct ieee80211_sta *sta,
@@ -425,11 +418,7 @@ static int mt7615_set_sar_specs(struct ieee80211_hw *hw,
 	if (mt7615_firmware_offload(phy->dev))
 		return mt76_connac_mcu_set_rate_txpower(phy->mt76);
 
-	ieee80211_stop_queues(hw);
-	err = mt7615_set_channel(phy);
-	ieee80211_wake_queues(hw);
-
-	return err;
+	return mt76_update_channel(phy->mt76);
 }
 
 static int mt7615_config(struct ieee80211_hw *hw, u32 changed)
@@ -448,9 +437,7 @@ static int mt7615_config(struct ieee80211_hw *hw, u32 changed)
 			mt7615_mutex_release(dev);
 		}
 #endif
-		ieee80211_stop_queues(hw);
-		ret = mt7615_set_channel(phy);
-		ieee80211_wake_queues(hw);
+		ret = mt76_update_channel(phy->mt76);
 	}
 
 	mt7615_mutex_acquire(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index d50d967828be..3b57d967190a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -2151,7 +2151,7 @@ int mt7615_mcu_set_chan_info(struct mt7615_phy *phy, int cmd)
 	if (cmd == MCU_EXT_CMD(SET_RX_PATH) ||
 	    phy->mt76->hw->conf.flags & IEEE80211_CONF_MONITOR)
 		req.switch_reason = CH_SWITCH_NORMAL;
-	else if (phy->mt76->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)
+	else if (phy->mt76->offchannel)
 		req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD;
 	else if (!cfg80211_reg_can_beacon(phy->mt76->hw->wiphy, chandef,
 					  NL80211_IFTYPE_AP))
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
index 87a956ea3ad7..dbb2c82407df 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c
@@ -182,6 +182,7 @@ int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base,
 		.sta_add = mt7615_mac_sta_add,
 		.sta_remove = mt7615_mac_sta_remove,
 		.update_survey = mt7615_update_channel,
+		.set_channel = mt7615_set_channel,
 	};
 	struct mt76_bus_ops *bus_ops;
 	struct ieee80211_ops *ops;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
index a20322aae967..68f4a7727a26 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
@@ -457,7 +457,7 @@ void mt7615_roc_work(struct work_struct *work);
 void mt7615_roc_timer(struct timer_list *timer);
 void mt7615_init_txpower(struct mt7615_dev *dev,
 			 struct ieee80211_supported_band *sband);
-int mt7615_set_channel(struct mt7615_phy *phy);
+int mt7615_set_channel(struct mt76_phy *mphy);
 void mt7615_init_work(struct mt7615_dev *dev);
 
 int mt7615_mcu_restart(struct mt76_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
index 9692890ba51b..aebfc4576aa4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.c
@@ -87,6 +87,7 @@ static int mt7663s_probe(struct sdio_func *func,
 		.sta_add = mt7615_mac_sta_add,
 		.sta_remove = mt7615_mac_sta_remove,
 		.update_survey = mt7615_update_channel,
+		.set_channel = mt7615_set_channel,
 	};
 	static const struct mt76_bus_ops mt7663s_ops = {
 		.rr = mt76s_rr,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c
index a3d1cfa729ed..03f5af84424b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/testmode.c
@@ -141,7 +141,7 @@ mt7615_tm_init(struct mt7615_phy *phy)
 	mt7615_mcu_set_sku_en(phy, phy->mt76->test.state == MT76_TM_STATE_OFF);
 
 	mutex_unlock(&dev->mt76.mutex);
-	mt7615_set_channel(phy);
+	mt76_update_channel(phy->mt76);
 	mt7615_ops.configure_filter(phy->mt76->hw, 0, &total_flags, 0);
 	mutex_lock(&dev->mt76.mutex);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
index 9335ca0776fe..5020af52c68c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb.c
@@ -123,6 +123,7 @@ static int mt7663u_probe(struct usb_interface *usb_intf,
 		.sta_add = mt7615_mac_sta_add,
 		.sta_remove = mt7615_mac_sta_remove,
 		.update_survey = mt7615_update_channel,
+		.set_channel = mt7615_set_channel,
 	};
 	static struct mt76_bus_ops bus_ops = {
 		.rr = mt7663u_rr,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index 07380cce8755..4aa2dcedc874 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -8,16 +8,15 @@
 #include <linux/etherdevice.h>
 #include "mt76x0.h"
 
-static void
-mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
+int mt76x0_set_channel(struct mt76_phy *mphy)
 {
-	cancel_delayed_work_sync(&dev->cal_work);
+	struct mt76x02_dev *dev = container_of(mphy->dev, struct mt76x02_dev, mt76);
+
 	mt76x02_pre_tbtt_enable(dev, false);
 	if (mt76_is_mmio(&dev->mt76))
 		tasklet_disable(&dev->dfs_pd.dfs_tasklet);
 
-	mt76_set_channel(&dev->mphy);
-	mt76x0_phy_set_channel(dev, chandef);
+	mt76x0_phy_set_channel(dev, &mphy->chandef);
 
 	mt76x02_mac_cc_reset(dev);
 	mt76x02_edcca_init(dev);
@@ -28,8 +27,9 @@ mt76x0_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
 	}
 	mt76x02_pre_tbtt_enable(dev, true);
 
-	mt76_txq_schedule_all(&dev->mphy);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(mt76x0_set_channel);
 
 int mt76x0_set_sar_specs(struct ieee80211_hw *hw,
 			 const struct cfg80211_sar_specs *sar)
@@ -61,13 +61,10 @@ int mt76x0_config(struct ieee80211_hw *hw, u32 changed)
 {
 	struct mt76x02_dev *dev = hw->priv;
 
-	mutex_lock(&dev->mt76.mutex);
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL)
+		mt76_update_channel(&dev->mphy);
 
-	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
-		ieee80211_stop_queues(hw);
-		mt76x0_set_channel(dev, &hw->conf.chandef);
-		ieee80211_wake_queues(hw);
-	}
+	mutex_lock(&dev->mt76.mutex);
 
 	if (changed & IEEE80211_CONF_CHANGE_POWER) {
 		struct mt76_phy *mphy = &dev->mphy;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 99dcb8feb9f7..50f755344968 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -49,6 +49,7 @@ void mt76x0_chip_onoff(struct mt76x02_dev *dev, bool enable, bool reset);
 void mt76x0_mac_stop(struct mt76x02_dev *dev);
 
 int mt76x0_config(struct ieee80211_hw *hw, u32 changed);
+int mt76x0_set_channel(struct mt76_phy *mphy);
 int mt76x0_set_sar_specs(struct ieee80211_hw *hw,
 			 const struct cfg80211_sar_specs *sar);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index 2ecee7c5c80d..1eb955f3ca13 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -159,6 +159,7 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			     MT_DRV_SW_RX_AIRTIME,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
+		.set_channel = mt76x0_set_channel,
 		.tx_prepare_skb = mt76x02_tx_prepare_skb,
 		.tx_complete_skb = mt76x02_tx_complete_skb,
 		.rx_skb = mt76x02_queue_rx_skb,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 390f502e97f0..b031c500b741 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -217,6 +217,7 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 		.drv_flags = MT_DRV_SW_RX_AIRTIME,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
+		.set_channel = mt76x0_set_channel,
 		.tx_prepare_skb = mt76x02u_tx_prepare_skb,
 		.tx_complete_skb = mt76x02u_tx_complete_skb,
 		.tx_status_data = mt76x02_tx_status_data,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 35b7ebc2c9c6..4a49a3036a46 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -22,7 +22,7 @@ static void mt76x02_pre_tbtt_tasklet(struct tasklet_struct *t)
 	struct sk_buff *skb;
 	int i;
 
-	if (mt76_hw(dev)->conf.flags & IEEE80211_CONF_OFFCHANNEL)
+	if (dev->mphy.offchannel)
 		return;
 
 	__skb_queue_head_init(&data.q);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
index 29b9a15f8dbe..0e1ede9314d8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
@@ -188,10 +188,7 @@ static void mt76x02u_pre_tbtt_work(struct work_struct *work)
 	struct sk_buff *skb;
 	int nbeacons;
 
-	if (!dev->mt76.beacon_mask)
-		return;
-
-	if (mt76_hw(dev)->conf.flags & IEEE80211_CONF_OFFCHANNEL)
+	if (!dev->mt76.beacon_mask || dev->mphy.offchannel)
 		return;
 
 	__skb_queue_head_init(&data.q);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index be1217329a77..f051721bb00e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -47,6 +47,8 @@ void mt76x2_phy_power_on(struct mt76x02_dev *dev);
 void mt76x2_stop_hardware(struct mt76x02_dev *dev);
 int mt76x2_eeprom_init(struct mt76x02_dev *dev);
 int mt76x2_apply_calibration_data(struct mt76x02_dev *dev, int channel);
+int mt76x2e_set_channel(struct mt76_phy *phy);
+int mt76x2u_set_channel(struct mt76_phy *phy);
 
 void mt76x2_phy_set_antenna(struct mt76x02_dev *dev);
 int mt76x2_phy_start(struct mt76x02_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index 30959746e924..67c9d1caa0bd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -25,6 +25,7 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 			     MT_DRV_SW_RX_AIRTIME,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
+		.set_channel = mt76x2e_set_channel,
 		.tx_prepare_skb = mt76x02_tx_prepare_skb,
 		.tx_complete_skb = mt76x02_tx_complete_skb,
 		.rx_skb = mt76x02_queue_rx_skb,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
index 6accea551319..eb70130d2711 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c
@@ -32,33 +32,25 @@ mt76x2_stop(struct ieee80211_hw *hw, bool suspend)
 	mt76x2_stop_hardware(dev);
 }
 
-static void
-mt76x2_set_channel(struct mt76x02_dev *dev, struct cfg80211_chan_def *chandef)
+int mt76x2e_set_channel(struct mt76_phy *phy)
 {
-	cancel_delayed_work_sync(&dev->cal_work);
+	struct mt76x02_dev *dev = container_of(phy->dev, struct mt76x02_dev, mt76);
+
 	tasklet_disable(&dev->mt76.pre_tbtt_tasklet);
 	tasklet_disable(&dev->dfs_pd.dfs_tasklet);
 
-	mutex_lock(&dev->mt76.mutex);
-	set_bit(MT76_RESET, &dev->mphy.state);
-
-	mt76_set_channel(&dev->mphy);
-
 	mt76x2_mac_stop(dev, true);
-	mt76x2_phy_set_channel(dev, chandef);
+	mt76x2_phy_set_channel(dev, &phy->chandef);
 
 	mt76x02_mac_cc_reset(dev);
 	mt76x02_dfs_init_params(dev);
 
 	mt76x2_mac_resume(dev);
 
-	clear_bit(MT76_RESET, &dev->mphy.state);
-	mutex_unlock(&dev->mt76.mutex);
-
 	tasklet_enable(&dev->dfs_pd.dfs_tasklet);
 	tasklet_enable(&dev->mt76.pre_tbtt_tasklet);
 
-	mt76_txq_schedule_all(&dev->mphy);
+	return 0;
 }
 
 static int
@@ -95,11 +87,8 @@ mt76x2_config(struct ieee80211_hw *hw, u32 changed)
 
 	mutex_unlock(&dev->mt76.mutex);
 
-	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
-		ieee80211_stop_queues(hw);
-		mt76x2_set_channel(dev, &hw->conf.chandef);
-		ieee80211_wake_queues(hw);
-	}
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL)
+		mt76_update_channel(&dev->mphy);
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index e92bb871f231..e832ad53e239 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -32,6 +32,7 @@ static int mt76x2u_probe(struct usb_interface *intf,
 		.drv_flags = MT_DRV_SW_RX_AIRTIME,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
+		.set_channel = mt76x2u_set_channel,
 		.tx_prepare_skb = mt76x02u_tx_prepare_skb,
 		.tx_complete_skb = mt76x02u_tx_complete_skb,
 		.tx_status_data = mt76x02_tx_status_data,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index ba0241c36672..83e7061b10e2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -31,32 +31,20 @@ static void mt76x2u_stop(struct ieee80211_hw *hw, bool suspend)
 	mt76x2u_stop_hw(dev);
 }
 
-static int
-mt76x2u_set_channel(struct mt76x02_dev *dev,
-		    struct cfg80211_chan_def *chandef)
+int mt76x2u_set_channel(struct mt76_phy *mphy)
 {
+	struct mt76x02_dev *dev = container_of(mphy->dev, struct mt76x02_dev, mt76);
 	int err;
 
-	cancel_delayed_work_sync(&dev->cal_work);
 	mt76x02_pre_tbtt_enable(dev, false);
-
-	mutex_lock(&dev->mt76.mutex);
-	set_bit(MT76_RESET, &dev->mphy.state);
-
-	mt76_set_channel(&dev->mphy);
-
 	mt76x2_mac_stop(dev, false);
 
-	err = mt76x2u_phy_set_channel(dev, chandef);
+	err = mt76x2u_phy_set_channel(dev, &mphy->chandef);
 
 	mt76x02_mac_cc_reset(dev);
 	mt76x2_mac_resume(dev);
 
-	clear_bit(MT76_RESET, &dev->mphy.state);
-	mutex_unlock(&dev->mt76.mutex);
-
 	mt76x02_pre_tbtt_enable(dev, true);
-	mt76_txq_schedule_all(&dev->mphy);
 
 	return err;
 }
@@ -93,11 +81,8 @@ mt76x2u_config(struct ieee80211_hw *hw, u32 changed)
 
 	mutex_unlock(&dev->mt76.mutex);
 
-	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
-		ieee80211_stop_queues(hw);
-		err = mt76x2u_set_channel(dev, &hw->conf.chandef);
-		ieee80211_wake_queues(hw);
-	}
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL)
+		mt76_update_channel(&dev->mphy);
 
 	return err;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 049223df9beb..87a7b1589af2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -317,18 +317,12 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw,
 	mt76_wcid_cleanup(&dev->mt76, &msta->wcid);
 }
 
-int mt7915_set_channel(struct mt7915_phy *phy)
+int mt7915_set_channel(struct mt76_phy *mphy)
 {
+	struct mt7915_phy *phy = mphy->priv;
 	struct mt7915_dev *dev = phy->dev;
 	int ret;
 
-	cancel_delayed_work_sync(&phy->mt76->mac_work);
-
-	mutex_lock(&dev->mt76.mutex);
-	set_bit(MT76_RESET, &phy->mt76->state);
-
-	mt76_set_channel(phy->mt76);
-
 	if (dev->cal) {
 		ret = mt7915_mcu_apply_tx_dpd(phy);
 		if (ret)
@@ -347,11 +341,6 @@ int mt7915_set_channel(struct mt7915_phy *phy)
 	phy->noise = 0;
 
 out:
-	clear_bit(MT76_RESET, &phy->mt76->state);
-	mutex_unlock(&dev->mt76.mutex);
-
-	mt76_txq_schedule_all(phy->mt76);
-
 	if (!mt76_testmode_enabled(phy->mt76))
 		ieee80211_queue_delayed_work(phy->mt76->hw,
 					     &phy->mt76->mac_work,
@@ -464,11 +453,9 @@ static int mt7915_config(struct ieee80211_hw *hw, u32 changed)
 			mutex_unlock(&dev->mt76.mutex);
 		}
 #endif
-		ieee80211_stop_queues(hw);
-		ret = mt7915_set_channel(phy);
+		ret = mt76_update_channel(phy->mt76);
 		if (ret)
 			return ret;
-		ieee80211_wake_queues(hw);
 	}
 
 	if (changed & (IEEE80211_CONF_CHANGE_POWER |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 2185cd24e2e1..b2cad75eafb9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -2747,7 +2747,7 @@ int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd)
 
 	if (phy->mt76->hw->conf.flags & IEEE80211_CONF_MONITOR)
 		req.switch_reason = CH_SWITCH_NORMAL;
-	else if (phy->mt76->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL ||
+	else if (phy->mt76->offchannel ||
 		 phy->mt76->hw->conf.flags & IEEE80211_CONF_IDLE)
 		req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD;
 	else if (!cfg80211_reg_can_beacon(phy->mt76->hw->wiphy, chandef,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index d6ecd698cdcd..ec7cf57521d9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -929,6 +929,7 @@ struct mt7915_dev *mt7915_mmio_probe(struct device *pdev,
 		.sta_add = mt7915_mac_sta_add,
 		.sta_remove = mt7915_mac_sta_remove,
 		.update_survey = mt7915_update_channel,
+		.set_channel = mt7915_set_channel,
 	};
 	struct mt7915_dev *dev;
 	struct mt76_dev *mdev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index a30d08eb0656..712471c2a8e9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -463,7 +463,7 @@ int mt7915_mcu_add_rate_ctrl(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 			     struct ieee80211_sta *sta, bool changed);
 int mt7915_mcu_add_smps(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta);
-int mt7915_set_channel(struct mt7915_phy *phy);
+int mt7915_set_channel(struct mt76_phy *mphy);
 int mt7915_mcu_set_chan_info(struct mt7915_phy *phy, int cmd);
 int mt7915_mcu_set_tx(struct mt7915_dev *dev, struct ieee80211_vif *vif);
 int mt7915_mcu_update_edca(struct mt7915_dev *dev, void *req);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
index 0d76ae31b376..1ed8e77eb549 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
@@ -425,7 +425,7 @@ static void
 mt7915_tm_update_channel(struct mt7915_phy *phy)
 {
 	mutex_unlock(&phy->dev->mt76.mutex);
-	mt7915_set_channel(phy);
+	mt76_update_channel(phy->mt76);
 	mutex_lock(&phy->dev->mt76.mutex);
 
 	mt7915_mcu_set_chan_info(phy, MCU_EXT_CMD(SET_RX_PATH));
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 23b228804289..ffb2b68ddd51 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -455,37 +455,30 @@ static int mt7921_cancel_remain_on_channel(struct ieee80211_hw *hw,
 	return mt7921_abort_roc(phy, mvif);
 }
 
-static int mt7921_set_channel(struct mt792x_phy *phy)
+int mt7921_set_channel(struct mt76_phy *mphy)
 {
+	struct mt792x_phy *phy = mphy->priv;
 	struct mt792x_dev *dev = phy->dev;
 	int ret;
 
-	cancel_delayed_work_sync(&phy->mt76->mac_work);
-
-	mt792x_mutex_acquire(dev);
-	set_bit(MT76_RESET, &phy->mt76->state);
-
-	mt76_set_channel(phy->mt76);
-
+	mt76_connac_pm_wake(mphy, &dev->pm);
 	ret = mt7921_mcu_set_chan_info(phy, MCU_EXT_CMD(CHANNEL_SWITCH));
 	if (ret)
 		goto out;
 
 	mt792x_mac_set_timeing(phy);
-
 	mt792x_mac_reset_counters(phy);
 	phy->noise = 0;
 
 out:
-	clear_bit(MT76_RESET, &phy->mt76->state);
-	mt792x_mutex_release(dev);
+	mt76_connac_power_save_sched(mphy, &dev->pm);
 
-	mt76_worker_schedule(&dev->mt76.tx_worker);
-	ieee80211_queue_delayed_work(phy->mt76->hw, &phy->mt76->mac_work,
+	ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
 				     MT792x_WATCHDOG_TIME);
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mt7921_set_channel);
 
 static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			  struct ieee80211_vif *vif, struct ieee80211_sta *sta,
@@ -620,11 +613,9 @@ static int mt7921_config(struct ieee80211_hw *hw, u32 changed)
 	int ret = 0;
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
-		ieee80211_stop_queues(hw);
-		ret = mt7921_set_channel(phy);
+		ret = mt76_update_channel(phy->mt76);
 		if (ret)
 			return ret;
-		ieee80211_wake_queues(hw);
 	}
 
 	mt792x_mutex_acquire(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
index 394fcd799345..02c1de8620a7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c
@@ -890,7 +890,7 @@ int mt7921_mcu_set_chan_info(struct mt792x_phy *phy, int cmd)
 	if (cmd == MCU_EXT_CMD(SET_RX_PATH) ||
 	    dev->mt76.hw->conf.flags & IEEE80211_CONF_MONITOR)
 		req.switch_reason = CH_SWITCH_NORMAL;
-	else if (dev->mt76.hw->conf.flags & IEEE80211_CONF_OFFCHANNEL)
+	else if (phy->mt76->offchannel)
 		req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD;
 	else if (!cfg80211_reg_can_beacon(dev->mt76.hw->wiphy, chandef,
 					  NL80211_IFTYPE_AP))
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 6c5392c5d207..0b4f4c8d8858 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -186,6 +186,7 @@ int __mt7921_start(struct mt792x_phy *phy);
 int mt7921_register_device(struct mt792x_dev *dev);
 void mt7921_unregister_device(struct mt792x_dev *dev);
 int mt7921_run_firmware(struct mt792x_dev *dev);
+int mt7921_set_channel(struct mt76_phy *mphy);
 int mt7921_mcu_set_bss_pm(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 			  bool enable);
 int mt7921_mcu_sta_update(struct mt792x_dev *dev, struct ieee80211_sta *sta,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index a7430216a80d..bb8cfff78dc5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -247,6 +247,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
+		.set_channel = mt7921_set_channel,
 	};
 	static const struct mt792x_hif_ops mt7921_pcie_ops = {
 		.init_reset = mt7921e_init_reset,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 004d942ee11a..2ef502d0ce9a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -103,6 +103,7 @@ static int mt7921s_probe(struct sdio_func *func,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
+		.set_channel = mt7921_set_channel,
 	};
 	static const struct mt76_bus_ops mt7921s_ops = {
 		.rr = mt76s_rr,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 8b7c03c47598..3b5e52db4a13 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -154,6 +154,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 		.sta_assoc = mt7921_mac_sta_assoc,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
+		.set_channel = mt7921_set_channel,
 	};
 	static const struct mt792x_hif_ops hif_ops = {
 		.mcu_init = mt7921u_mcu_init,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index d43bd5c2432e..39f071ece35e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -291,18 +291,11 @@ static void mt7996_remove_interface(struct ieee80211_hw *hw,
 	mt76_wcid_cleanup(&dev->mt76, &msta->wcid);
 }
 
-int mt7996_set_channel(struct mt7996_phy *phy)
+int mt7996_set_channel(struct mt76_phy *mphy)
 {
-	struct mt7996_dev *dev = phy->dev;
+	struct mt7996_phy *phy = mphy->priv;
 	int ret;
 
-	cancel_delayed_work_sync(&phy->mt76->mac_work);
-
-	mutex_lock(&dev->mt76.mutex);
-	set_bit(MT76_RESET, &phy->mt76->state);
-
-	mt76_set_channel(phy->mt76);
-
 	ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_SWITCH);
 	if (ret)
 		goto out;
@@ -318,13 +311,7 @@ int mt7996_set_channel(struct mt7996_phy *phy)
 	phy->noise = 0;
 
 out:
-	clear_bit(MT76_RESET, &phy->mt76->state);
-	mutex_unlock(&dev->mt76.mutex);
-
-	mt76_txq_schedule_all(phy->mt76);
-
-	ieee80211_queue_delayed_work(phy->mt76->hw,
-				     &phy->mt76->mac_work,
+	ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work,
 				     MT7996_WATCHDOG_TIME);
 
 	return ret;
@@ -415,11 +402,9 @@ static int mt7996_config(struct ieee80211_hw *hw, u32 changed)
 	int ret;
 
 	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
-		ieee80211_stop_queues(hw);
-		ret = mt7996_set_channel(phy);
+		ret = mt76_update_channel(phy->mt76);
 		if (ret)
 			return ret;
-		ieee80211_wake_queues(hw);
 	}
 
 	if (changed & (IEEE80211_CONF_CHANGE_POWER |
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 8855095fef10..a1a0df43e1cd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -3463,7 +3463,7 @@ int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag)
 
 	if (phy->mt76->hw->conf.flags & IEEE80211_CONF_MONITOR)
 		req.switch_reason = CH_SWITCH_NORMAL;
-	else if (phy->mt76->hw->conf.flags & IEEE80211_CONF_OFFCHANNEL ||
+	else if (phy->mt76->offchannel ||
 		 phy->mt76->hw->conf.flags & IEEE80211_CONF_IDLE)
 		req.switch_reason = CH_SWITCH_SCAN_BYPASS_DPD;
 	else if (!cfg80211_reg_can_beacon(phy->mt76->hw->wiphy, chandef,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index 928a9663b49e..40e45fb2b626 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -620,6 +620,7 @@ struct mt7996_dev *mt7996_mmio_probe(struct device *pdev,
 		.sta_add = mt7996_mac_sta_add,
 		.sta_remove = mt7996_mac_sta_remove,
 		.update_survey = mt7996_update_channel,
+		.set_channel = mt7996_set_channel,
 	};
 	struct mt7996_dev *dev;
 	struct mt76_dev *mdev;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 177cfff31120..ab8c9070630b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -468,7 +468,7 @@ int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_he_obss_pd *he_obss_pd);
 int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			     struct ieee80211_sta *sta, bool changed);
-int mt7996_set_channel(struct mt7996_phy *phy);
+int mt7996_set_channel(struct mt76_phy *mphy);
 int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag);
 int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif);
 int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
-- 
cgit v1.3-3-g829e


From a26a5107bc52922cf5f67361e307ad66547b51c7 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 5 Sep 2024 18:04:00 +0300
Subject: wifi: cfg80211: fix UBSAN noise in cfg80211_wext_siwscan()

Looking at https://syzkaller.appspot.com/bug?extid=1a3986bbd3169c307819
and running reproducer with CONFIG_UBSAN_BOUNDS, I've noticed the
following:

[ T4985] UBSAN: array-index-out-of-bounds in net/wireless/scan.c:3479:25
[ T4985] index 164 is out of range for type 'struct ieee80211_channel *[]'
<...skipped...>
[ T4985] Call Trace:
[ T4985]  <TASK>
[ T4985]  dump_stack_lvl+0x1c2/0x2a0
[ T4985]  ? __pfx_dump_stack_lvl+0x10/0x10
[ T4985]  ? __pfx__printk+0x10/0x10
[ T4985]  __ubsan_handle_out_of_bounds+0x127/0x150
[ T4985]  cfg80211_wext_siwscan+0x11a4/0x1260
<...the rest is not too useful...>

Even if we do 'creq->n_channels = n_channels' before 'creq->ssids =
(void *)&creq->channels[n_channels]', UBSAN treats the latter as
off-by-one error. Fix this by using pointer arithmetic rather than
an expression with explicit array indexing and use convenient
'struct_size()' to simplify the math here and in 'kzalloc()' above.

Fixes: 5ba63533bbf6 ("cfg80211: fix alignment problem in scan request")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20240905150400.126386-1-dmantipov@yandex.ru
[fix coding style for multi-line calculation]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 64eeed82d43d..3ff818849d83 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -3467,8 +3467,8 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 		n_channels = ieee80211_get_num_supported_channels(wiphy);
 	}
 
-	creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) +
-		       n_channels * sizeof(void *),
+	creq = kzalloc(struct_size(creq, channels, n_channels) +
+		       sizeof(struct cfg80211_ssid),
 		       GFP_ATOMIC);
 	if (!creq)
 		return -ENOMEM;
@@ -3476,7 +3476,7 @@ int cfg80211_wext_siwscan(struct net_device *dev,
 	creq->wiphy = wiphy;
 	creq->wdev = dev->ieee80211_ptr;
 	/* SSIDs come after channels */
-	creq->ssids = (void *)&creq->channels[n_channels];
+	creq->ssids = (void *)creq + struct_size(creq, channels, n_channels);
 	creq->n_channels = n_channels;
 	creq->n_ssids = 1;
 	creq->scan_start = jiffies;
-- 
cgit v1.3-3-g829e


From f54a1baee098170b13b624ca5ed2afdb4d29edbc Mon Sep 17 00:00:00 2001
From: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Date: Wed, 4 Sep 2024 19:50:21 +0530
Subject: wifi: cfg80211: Avoid RCU debug splat in __cfg80211_bss_update error
 paths

Replace rcu_dereference() with rcu_access_pointer() since we already
hold the lock and own the 'tmp' at this point. This is needed to avoid
suspicious rcu_dereference_check warnings in__cfg80211_bss_update error
paths.

Signed-off-by: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Link: https://patch.msgid.link/20240904142021.3887360-1-quic_vjakkam@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 3ff818849d83..1ef6448bc636 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2008,10 +2008,10 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
 	return found;
 
 free_ies:
-	ies = (void *)rcu_dereference(tmp->pub.beacon_ies);
+	ies = (void *)rcu_access_pointer(tmp->pub.beacon_ies);
 	if (ies)
 		kfree_rcu(ies, rcu_head);
-	ies = (void *)rcu_dereference(tmp->pub.proberesp_ies);
+	ies = (void *)rcu_access_pointer(tmp->pub.proberesp_ies);
 	if (ies)
 		kfree_rcu(ies, rcu_head);
 
-- 
cgit v1.3-3-g829e


From cac9544cecf6d0aa1ad629ba8f403b05b8bee005 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 25 Aug 2024 19:17:03 +0300
Subject: wifi: iwlwifi: mvm: replace CONFIG_PM by CONFIG_PM_SLEEP

Replace the ifdef CONFIG_PM by CONFIG_PM_SLEEP. CONFIG_PM was useful
when we had CONFIG_PM_RUNTIME but that was removed long ago.
Use PM_SLEEP consistently across the driver.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240825191257.44e47ba584de.I64f985d0405345252b76b7157291b79677abd64d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/Makefile   | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      | 6 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c      | 7 +++++--
 4 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/Makefile b/drivers/net/wireless/intel/iwlwifi/mvm/Makefile
index 8873904f51ec..59751f123571 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/Makefile
@@ -13,7 +13,7 @@ iwlmvm-y += ptp.o
 iwlmvm-y += time-sync.o
 iwlmvm-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o debugfs-vif.o
 iwlmvm-$(CONFIG_IWLWIFI_LEDS) += led.o
-iwlmvm-$(CONFIG_PM) += d3.o
+iwlmvm-$(CONFIG_PM_SLEEP) += d3.o
 iwlmvm-$(CONFIG_IWLMEI) += vendor-cmd.o
 
 subdir-ccflags-y += -I $(src)/../
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 6f5b16eb4902..a327893c6dce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1232,7 +1232,7 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm)
 		mvm->nvm_data = NULL;
 	}
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	/* fast_resume will be cleared by iwl_mvm_fast_resume */
 	fast_resume = mvm->fast_resume;
 
@@ -1254,7 +1254,7 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm)
 			set_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status);
 		}
 	}
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
 
 	if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status)) {
 		/*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index c9b69c3a61fc..ef07cff203b0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -512,7 +512,7 @@ struct iwl_mvm_vif {
 	bool bf_enabled;
 	bool ba_enabled;
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	/* WoWLAN GTK rekey data */
 	struct {
 		u8 kck[NL80211_KCK_EXT_LEN];
@@ -1178,7 +1178,7 @@ struct iwl_mvm {
 
 	struct ieee80211_vif *p2p_device_vif;
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	struct wiphy_wowlan_support wowlan;
 	int gtk_ivlen, gtk_icvlen, ptk_ivlen, ptk_icvlen;
 
@@ -2306,7 +2306,7 @@ void iwl_mvm_ipv6_addr_change(struct ieee80211_hw *hw,
 void iwl_mvm_set_default_unicast_key(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif, int idx);
 extern const struct file_operations iwl_dbgfs_d3_test_ops;
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 void iwl_mvm_set_last_nonqos_seq(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif);
 void iwl_mvm_fast_suspend(struct iwl_mvm *mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 2cd89ccaef9a..4dd4a9d5c71f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -2155,6 +2155,7 @@ static void iwl_op_mode_mvm_time_point(struct iwl_op_mode *op_mode,
 	iwl_dbg_tlv_time_point(&mvm->fwrt, tp_id, tp_data);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static void iwl_op_mode_mvm_device_powered_off(struct iwl_op_mode *op_mode)
 {
 	struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
@@ -2163,11 +2164,13 @@ static void iwl_op_mode_mvm_device_powered_off(struct iwl_op_mode *op_mode)
 	clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status);
 	mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
 	iwl_mvm_stop_device(mvm);
-#ifdef CONFIG_PM
 	mvm->fast_resume = false;
-#endif
 	mutex_unlock(&mvm->mutex);
 }
+#else
+static void iwl_op_mode_mvm_device_powered_off(struct iwl_op_mode *op_mode)
+{}
+#endif
 
 #define IWL_MVM_COMMON_OPS					\
 	/* these could be differentiated */			\
-- 
cgit v1.3-3-g829e


From 0fdcc994a42cf1306bc0e9ca6c9adeec657f5f02 Mon Sep 17 00:00:00 2001
From: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Date: Wed, 4 Sep 2024 08:39:15 +0530
Subject: wifi: cfg80211: make BSS source types public

Define public enum with BSS source types in core.h. Upcoming patches
need this to store BSS source type in struct cfg80211_internal_bss.

Signed-off-by: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Link: https://patch.msgid.link/20240904030917.3602369-2-quic_vjakkam@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.h | 6 ++++++
 net/wireless/scan.c | 6 +-----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/wireless/core.h b/net/wireless/core.h
index 41c8c0e3ba2e..eace1800f5de 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -170,6 +170,12 @@ static inline int for_each_rdev_check_rtnl(void)
 	if (for_each_rdev_check_rtnl()) {} else				\
 		list_for_each_entry(rdev, &cfg80211_rdev_list, list)
 
+enum bss_source_type {
+	BSS_SOURCE_DIRECT = 0,
+	BSS_SOURCE_MBSSID,
+	BSS_SOURCE_STA_PROFILE,
+};
+
 struct cfg80211_internal_bss {
 	struct list_head list;
 	struct list_head hidden_list;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 1ef6448bc636..2d8987628530 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2149,11 +2149,7 @@ struct cfg80211_inform_single_bss_data {
 	const u8 *ie;
 	size_t ielen;
 
-	enum {
-		BSS_SOURCE_DIRECT = 0,
-		BSS_SOURCE_MBSSID,
-		BSS_SOURCE_STA_PROFILE,
-	} bss_source;
+	enum bss_source_type bss_source;
 	/* Set if reporting bss_source != BSS_SOURCE_DIRECT */
 	struct cfg80211_bss *source_bss;
 	u8 max_bssid_indicator;
-- 
cgit v1.3-3-g829e


From bff93c89ab19886e17f0a86ea59f2e37141f2ab6 Mon Sep 17 00:00:00 2001
From: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Date: Wed, 4 Sep 2024 08:39:16 +0530
Subject: wifi: cfg80211: skip indicating signal for per-STA profile BSSs

Currently signal of the BSS entry generated from the per-STA profile
indicated as zero, but userspace may consider it as high signal
strength since 0 dBm is a valid RSSI value.

To avoid this don't report the signal to userspace when the BSS entry
created from a per-STA profile.

Signed-off-by: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Link: https://patch.msgid.link/20240904030917.3602369-3-quic_vjakkam@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.h    |  2 ++
 net/wireless/nl80211.c | 26 +++++++++++++++-----------
 net/wireless/scan.c    |  2 ++
 3 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/net/wireless/core.h b/net/wireless/core.h
index eace1800f5de..3b3e3cd7027a 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -197,6 +197,8 @@ struct cfg80211_internal_bss {
 	 */
 	u8 parent_bssid[ETH_ALEN] __aligned(2);
 
+	enum bss_source_type bss_source;
+
 	/* must be last because of priv member */
 	struct cfg80211_bss pub;
 };
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index b368e23847dd..3a11a1a74a54 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10507,17 +10507,21 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 				NL80211_BSS_CHAIN_SIGNAL))
 		goto nla_put_failure;
 
-	switch (rdev->wiphy.signal_type) {
-	case CFG80211_SIGNAL_TYPE_MBM:
-		if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal))
-			goto nla_put_failure;
-		break;
-	case CFG80211_SIGNAL_TYPE_UNSPEC:
-		if (nla_put_u8(msg, NL80211_BSS_SIGNAL_UNSPEC, res->signal))
-			goto nla_put_failure;
-		break;
-	default:
-		break;
+	if (intbss->bss_source != BSS_SOURCE_STA_PROFILE) {
+		switch (rdev->wiphy.signal_type) {
+		case CFG80211_SIGNAL_TYPE_MBM:
+			if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM,
+					res->signal))
+				goto nla_put_failure;
+			break;
+		case CFG80211_SIGNAL_TYPE_UNSPEC:
+			if (nla_put_u8(msg, NL80211_BSS_SIGNAL_UNSPEC,
+				       res->signal))
+				goto nla_put_failure;
+			break;
+		default:
+			break;
+		}
 	}
 
 	switch (wdev->iftype) {
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 2d8987628530..c1417f7cd029 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1910,6 +1910,7 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 	known->pub.bssid_index = new->pub.bssid_index;
 	known->pub.use_for &= new->pub.use_for;
 	known->pub.cannot_use_reasons = new->pub.cannot_use_reasons;
+	known->bss_source = new->bss_source;
 
 	return true;
 }
@@ -2264,6 +2265,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 	       IEEE80211_MAX_CHAINS);
 	tmp.pub.use_for = data->use_for;
 	tmp.pub.cannot_use_reasons = data->cannot_use_reasons;
+	tmp.bss_source = data->bss_source;
 
 	switch (data->bss_source) {
 	case BSS_SOURCE_MBSSID:
-- 
cgit v1.3-3-g829e


From 450732abad6a75ff5a896a306be238123379e6db Mon Sep 17 00:00:00 2001
From: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Date: Wed, 4 Sep 2024 08:39:17 +0530
Subject: wifi: cfg80211: avoid overriding direct/MBSSID BSS with per-STA
 profile BSS

Avoid overriding BSS information generated from MBSSID or direct source
with BSS information generated from per-STA profile source to avoid
losing actual signal strength and information elements such as RNR and
Basic ML elements.

Signed-off-by: Veerendranath Jakkam <quic_vjakkam@quicinc.com>
Link: https://patch.msgid.link/20240904030917.3602369-4-quic_vjakkam@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index c1417f7cd029..59a90bf3c0d6 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2905,6 +2905,9 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy,
 	struct element *reporter_rnr = NULL;
 	struct ieee80211_multi_link_elem *ml_elem;
 	struct cfg80211_mle *mle;
+	const struct element *ssid_elem;
+	const u8 *ssid = NULL;
+	size_t ssid_len = 0;
 	u16 control;
 	u8 ml_common_len;
 	u8 *new_ie = NULL;
@@ -2959,6 +2962,13 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy,
 						 bss_change_count,
 						 gfp);
 
+	ssid_elem = cfg80211_find_elem(WLAN_EID_SSID, tx_data->ie,
+				       tx_data->ielen);
+	if (ssid_elem) {
+		ssid = ssid_elem->data;
+		ssid_len = ssid_elem->datalen;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(mle->sta_prof) && mle->sta_prof[i]; i++) {
 		const struct ieee80211_neighbor_ap_info *ap_info;
 		enum nl80211_band band;
@@ -3040,6 +3050,23 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy,
 		freq = ieee80211_channel_to_freq_khz(ap_info->channel, band);
 		data.channel = ieee80211_get_channel_khz(wiphy, freq);
 
+		/* Skip if BSS entry generated from MBSSID or DIRECT source
+		 * frame data available already.
+		 */
+		bss = cfg80211_get_bss(wiphy, data.channel, data.bssid, ssid,
+				       ssid_len, IEEE80211_BSS_TYPE_ANY,
+				       IEEE80211_PRIVACY_ANY);
+		if (bss) {
+			struct cfg80211_internal_bss *ibss = bss_from_pub(bss);
+
+			if (data.capability == bss->capability &&
+			    ibss->bss_source != BSS_SOURCE_STA_PROFILE) {
+				cfg80211_put_bss(wiphy, bss);
+				continue;
+			}
+			cfg80211_put_bss(wiphy, bss);
+		}
+
 		if (use_for == NL80211_BSS_USE_FOR_MLD_LINK &&
 		    !(wiphy->flags & WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY)) {
 			use_for = 0;
-- 
cgit v1.3-3-g829e


From 3702a33216e6b76361690630e3ab1a33b0ef03af Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Wed, 4 Sep 2024 19:12:56 +0800
Subject: wifi: mac80211: introduce EHT rate support in AQL airtime

Add definitions related to EHT mode and airtime calculation
according to the 802.11BE_D4.0.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Signed-off-by: Quan Zhou <quan.zhou@mediatek.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20240904111256.11734-1-mingyen.hsieh@mediatek.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/airtime.c | 140 ++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 134 insertions(+), 6 deletions(-)

diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c
index fdf8b658fede..c61df637232a 100644
--- a/net/mac80211/airtime.c
+++ b/net/mac80211/airtime.c
@@ -55,10 +55,21 @@
 #define HE_DURATION_S(shift, streams, gi, bps)		\
 	(HE_DURATION(streams, gi, bps) >> shift)
 
+/* gi in HE/EHT is identical. It matches enum nl80211_eht_gi as well */
+#define EHT_GI_08 HE_GI_08
+#define EHT_GI_16 HE_GI_16
+#define EHT_GI_32 HE_GI_32
+
+#define EHT_DURATION(streams, gi, bps)			\
+	HE_DURATION(streams, gi, bps)
+#define EHT_DURATION_S(shift, streams, gi, bps)		\
+	HE_DURATION_S(shift, streams, gi, bps)
+
 #define BW_20			0
 #define BW_40			1
 #define BW_80			2
 #define BW_160			3
+#define BW_320			4
 
 /*
  * Define group sort order: HT40 -> SGI -> #streams
@@ -68,17 +79,26 @@
 #define IEEE80211_VHT_STREAM_GROUPS	8 /* BW(=4) * SGI(=2) */
 
 #define IEEE80211_HE_MAX_STREAMS	8
+#define IEEE80211_HE_STREAM_GROUPS	12 /* BW(=4) * GI(=3) */
+
+#define IEEE80211_EHT_MAX_STREAMS	8
+#define IEEE80211_EHT_STREAM_GROUPS	15 /* BW(=5) * GI(=3) */
 
 #define IEEE80211_HT_GROUPS_NB	(IEEE80211_MAX_STREAMS *	\
 				 IEEE80211_HT_STREAM_GROUPS)
 #define IEEE80211_VHT_GROUPS_NB	(IEEE80211_MAX_STREAMS *	\
 					 IEEE80211_VHT_STREAM_GROUPS)
+#define IEEE80211_HE_GROUPS_NB	(IEEE80211_HE_MAX_STREAMS *	\
+				 IEEE80211_HE_STREAM_GROUPS)
+#define IEEE80211_EHT_GROUPS_NB	(IEEE80211_EHT_MAX_STREAMS *	\
+				 IEEE80211_EHT_STREAM_GROUPS)
 
 #define IEEE80211_HT_GROUP_0	0
 #define IEEE80211_VHT_GROUP_0	(IEEE80211_HT_GROUP_0 + IEEE80211_HT_GROUPS_NB)
 #define IEEE80211_HE_GROUP_0	(IEEE80211_VHT_GROUP_0 + IEEE80211_VHT_GROUPS_NB)
+#define IEEE80211_EHT_GROUP_0	(IEEE80211_HE_GROUP_0 + IEEE80211_HE_GROUPS_NB)
 
-#define MCS_GROUP_RATES		12
+#define MCS_GROUP_RATES		14
 
 #define HT_GROUP_IDX(_streams, _sgi, _ht40)	\
 	IEEE80211_HT_GROUP_0 +			\
@@ -203,6 +223,69 @@
 #define HE_GROUP(_streams, _gi, _bw)					\
 	__HE_GROUP(_streams, _gi, _bw,				\
 		   HE_GROUP_SHIFT(_streams, _gi, _bw))
+
+#define EHT_BW2VBPS(_bw, r5, r4, r3, r2, r1)					\
+	((_bw) == BW_320 ? r5 : BW2VBPS(_bw, r4, r3, r2, r1))
+
+#define EHT_GROUP_IDX(_streams, _gi, _bw)				\
+	(IEEE80211_EHT_GROUP_0 +					\
+	 IEEE80211_EHT_MAX_STREAMS * 3 * (_bw) +			\
+	 IEEE80211_EHT_MAX_STREAMS * (_gi) +				\
+	 (_streams) - 1)
+
+#define __EHT_GROUP(_streams, _gi, _bw, _s)						\
+	[EHT_GROUP_IDX(_streams, _gi, _bw)] = {						\
+	.shift = _s,									\
+	.duration = {									\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw,  1960,   980,  490,  234,  117)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw,  3920,  1960,  980,  468,  234)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw,  5880,  2937, 1470,  702,  351)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw,  7840,  3920, 1960,  936,  468)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 11760,  5880, 2940, 1404,  702)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 15680,  7840, 3920, 1872,  936)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 17640,  8820, 4410, 2106, 1053)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 19600,  9800, 4900, 2340, 1170)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 23520, 11760, 5880, 2808, 1404)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 26133, 13066, 6533, 3120, 1560)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 29400, 14700, 7350, 3510, 1755)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 32666, 16333, 8166, 3900, 1950)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 35280, 17640, 8820, 4212, 2106)),	\
+		EHT_DURATION_S(_s, _streams, _gi,					\
+			       EHT_BW2VBPS(_bw, 39200, 19600, 9800, 4680, 2340))	\
+		}									\
+}
+
+#define EHT_GROUP_SHIFT(_streams, _gi, _bw)						\
+	GROUP_SHIFT(EHT_DURATION(_streams, _gi,						\
+				 EHT_BW2VBPS(_bw, 1960, 980, 490, 234, 117)))
+
+#define EHT_GROUP(_streams, _gi, _bw)					\
+	__EHT_GROUP(_streams, _gi, _bw,				\
+		   EHT_GROUP_SHIFT(_streams, _gi, _bw))
+
+#define EHT_GROUP_RANGE(_gi, _bw)	\
+	EHT_GROUP(1, _gi, _bw),		\
+	EHT_GROUP(2, _gi, _bw),		\
+	EHT_GROUP(3, _gi, _bw),		\
+	EHT_GROUP(4, _gi, _bw),		\
+	EHT_GROUP(5, _gi, _bw),		\
+	EHT_GROUP(6, _gi, _bw),		\
+	EHT_GROUP(7, _gi, _bw),		\
+	EHT_GROUP(8, _gi, _bw)
+
 struct mcs_group {
 	u8 shift;
 	u16 duration[MCS_GROUP_RATES];
@@ -376,6 +459,26 @@ static const struct mcs_group airtime_mcs_groups[] = {
 	HE_GROUP(6, HE_GI_32, BW_160),
 	HE_GROUP(7, HE_GI_32, BW_160),
 	HE_GROUP(8, HE_GI_32, BW_160),
+
+	EHT_GROUP_RANGE(EHT_GI_08, BW_20),
+	EHT_GROUP_RANGE(EHT_GI_16, BW_20),
+	EHT_GROUP_RANGE(EHT_GI_32, BW_20),
+
+	EHT_GROUP_RANGE(EHT_GI_08, BW_40),
+	EHT_GROUP_RANGE(EHT_GI_16, BW_40),
+	EHT_GROUP_RANGE(EHT_GI_32, BW_40),
+
+	EHT_GROUP_RANGE(EHT_GI_08, BW_80),
+	EHT_GROUP_RANGE(EHT_GI_16, BW_80),
+	EHT_GROUP_RANGE(EHT_GI_32, BW_80),
+
+	EHT_GROUP_RANGE(EHT_GI_08, BW_160),
+	EHT_GROUP_RANGE(EHT_GI_16, BW_160),
+	EHT_GROUP_RANGE(EHT_GI_32, BW_160),
+
+	EHT_GROUP_RANGE(EHT_GI_08, BW_320),
+	EHT_GROUP_RANGE(EHT_GI_16, BW_320),
+	EHT_GROUP_RANGE(EHT_GI_32, BW_320),
 };
 
 static u32
@@ -422,6 +525,9 @@ static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw,
 	case RATE_INFO_BW_160:
 		bw = BW_160;
 		break;
+	case RATE_INFO_BW_320:
+		bw = BW_320;
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -443,14 +549,27 @@ static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw,
 		idx = status->rate_idx;
 		group = HE_GROUP_IDX(streams, status->he_gi, bw);
 		break;
+	case RX_ENC_EHT:
+		streams = status->nss;
+		idx = status->rate_idx;
+		group = EHT_GROUP_IDX(streams, status->eht.gi, bw);
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
 	}
 
-	if (WARN_ON_ONCE((status->encoding != RX_ENC_HE && streams > 4) ||
-			 (status->encoding == RX_ENC_HE && streams > 8)))
-		return 0;
+	switch (status->encoding) {
+	case RX_ENC_EHT:
+	case RX_ENC_HE:
+		if (WARN_ON_ONCE(streams > 8))
+			return 0;
+		break;
+	default:
+		if (WARN_ON_ONCE(streams > 4))
+			return 0;
+		break;
+	}
 
 	if (idx >= MCS_GROUP_RATES)
 		return 0;
@@ -517,7 +636,9 @@ static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw,
 	stat->nss = ri->nss;
 	stat->rate_idx = ri->mcs;
 
-	if (ri->flags & RATE_INFO_FLAGS_HE_MCS)
+	if (ri->flags & RATE_INFO_FLAGS_EHT_MCS)
+		stat->encoding = RX_ENC_EHT;
+	else if (ri->flags & RATE_INFO_FLAGS_HE_MCS)
 		stat->encoding = RX_ENC_HE;
 	else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS)
 		stat->encoding = RX_ENC_VHT;
@@ -529,7 +650,14 @@ static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw,
 	if (ri->flags & RATE_INFO_FLAGS_SHORT_GI)
 		stat->enc_flags |= RX_ENC_FLAG_SHORT_GI;
 
-	stat->he_gi = ri->he_gi;
+	switch (stat->encoding) {
+	case RX_ENC_EHT:
+		stat->eht.gi = ri->eht_gi;
+		break;
+	default:
+		stat->he_gi = ri->he_gi;
+		break;
+	}
 
 	if (stat->encoding != RX_ENC_LEGACY)
 		return true;
-- 
cgit v1.3-3-g829e


From 6241d79f0043298e30679535472a8498d99161b0 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:19 +0530
Subject: Revert "wifi: mac80211: move radar detect work to sdata"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit ce9e660ef32e ("wifi: mac80211: move radar detect work to sdata").

To enable radar detection with MLO, it’s essential to handle it on a
per-link basis. This is because when using MLO, multiple links may already
be active and beaconing. In this scenario, another link should be able to
initiate a radar detection. Also, if underlying links are associated with
different hardware devices but grouped together for MLO, they could
potentially start radar detection simultaneously. Therefore, it makes
sense to manage radar detection settings separately for each link by moving
them back to a per-link data structure.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-2-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c         | 6 +++---
 net/mac80211/ieee80211_i.h | 3 +--
 net/mac80211/iface.c       | 4 +---
 net/mac80211/link.c        | 2 ++
 net/mac80211/mlme.c        | 9 +++++----
 net/mac80211/util.c        | 2 +-
 6 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index b02b84ce2130..184e9d54064b 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1664,7 +1664,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 
 	if (sdata->wdev.cac_started) {
 		chandef = link_conf->chanreq.oper;
-		wiphy_delayed_work_cancel(wiphy, &sdata->dfs_cac_timer_work);
+		wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED,
 				   GFP_KERNEL);
@@ -3485,7 +3485,7 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	if (err)
 		goto out_unlock;
 
-	wiphy_delayed_work_queue(wiphy, &sdata->dfs_cac_timer_work,
+	wiphy_delayed_work_queue(wiphy, &sdata->deflink.dfs_cac_timer_work,
 				 msecs_to_jiffies(cac_time_ms));
 
  out_unlock:
@@ -3502,7 +3502,7 @@ static void ieee80211_end_cac(struct wiphy *wiphy,
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		wiphy_delayed_work_cancel(wiphy,
-					  &sdata->dfs_cac_timer_work);
+					  &sdata->deflink.dfs_cac_timer_work);
 
 		if (sdata->wdev.cac_started) {
 			ieee80211_link_release_channel(&sdata->deflink);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 6305c4e9cca1..9c2c826ef90c 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1067,6 +1067,7 @@ struct ieee80211_link_data {
 	int ap_power_level; /* in dBm */
 
 	bool radar_required;
+	struct wiphy_delayed_work dfs_cac_timer_work;
 
 	union {
 		struct ieee80211_link_data_managed mgd;
@@ -1165,8 +1166,6 @@ struct ieee80211_sub_if_data {
 	struct ieee80211_link_data deflink;
 	struct ieee80211_link_data __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS];
 
-	struct wiphy_delayed_work dfs_cac_timer_work;
-
 	/* for ieee80211_set_active_links_async() */
 	struct wiphy_work activate_links_work;
 	u16 desired_active_links;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index b4ad66af3af3..7bb71ac52277 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -550,7 +550,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	wiphy_work_cancel(local->hw.wiphy,
 			  &sdata->deflink.color_change_finalize_work);
 	wiphy_delayed_work_cancel(local->hw.wiphy,
-				  &sdata->dfs_cac_timer_work);
+				  &sdata->deflink.dfs_cac_timer_work);
 
 	if (sdata->wdev.cac_started) {
 		chandef = sdata->vif.bss_conf.chanreq.oper;
@@ -1729,8 +1729,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	wiphy_work_init(&sdata->work, ieee80211_iface_work);
 	wiphy_work_init(&sdata->activate_links_work,
 			ieee80211_activate_links_work);
-	wiphy_delayed_work_init(&sdata->dfs_cac_timer_work,
-				ieee80211_dfs_cac_timer_work);
 
 	switch (type) {
 	case NL80211_IFTYPE_P2P_GO:
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index 1a211b8d4057..b4378969cbf1 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -45,6 +45,8 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 			  ieee80211_color_collision_detection_work);
 	INIT_LIST_HEAD(&link->assigned_chanctx_list);
 	INIT_LIST_HEAD(&link->reserved_chanctx_list);
+	wiphy_delayed_work_init(&link->dfs_cac_timer_work,
+				ieee80211_dfs_cac_timer_work);
 
 	if (!deflink) {
 		switch (sdata->vif.type) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 746f51ac0306..85789c184949 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3031,15 +3031,16 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t)
 
 void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
-	struct ieee80211_sub_if_data *sdata =
-		container_of(work, struct ieee80211_sub_if_data,
+	struct ieee80211_link_data *link =
+		container_of(work, struct ieee80211_link_data,
 			     dfs_cac_timer_work.work);
-	struct cfg80211_chan_def chandef = sdata->vif.bss_conf.chanreq.oper;
+	struct cfg80211_chan_def chandef = link->conf->chanreq.oper;
+	struct ieee80211_sub_if_data *sdata = link->sdata;
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
 	if (sdata->wdev.cac_started) {
-		ieee80211_link_release_channel(&sdata->deflink);
+		ieee80211_link_release_channel(link);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED,
 				   GFP_KERNEL);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 3b9468dc3029..071cbb7929d9 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3476,7 +3476,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
 		wiphy_delayed_work_cancel(local->hw.wiphy,
-					  &sdata->dfs_cac_timer_work);
+					  &sdata->deflink.dfs_cac_timer_work);
 
 		if (sdata->wdev.cac_started) {
 			chandef = sdata->vif.bss_conf.chanreq.oper;
-- 
cgit v1.3-3-g829e


From f403fed7f98eab72c4104ecc77aff6f87b12658f Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:20 +0530
Subject: wifi: mac80211: remove label usage in
 ieee80211_start_radar_detection()

After locks rework [1], ieee80211_start_radar_detection() function is no
longer acquiring any lock as such explicitly. Hence, it is not unlocking
anything as well. However, label "out_unlock" is still used which creates
confusion. Also, now there is no need of goto label as such.

Get rid of the goto logic and use direct return statements.

[1]: https://lore.kernel.org/all/20230828135928.b1c6efffe9ad.I4aec875e25abc9ef0b5ad1e70b5747fd483fbd3c@changeid/

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-3-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 184e9d54064b..d3115be54997 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3471,10 +3471,8 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
-	if (!list_empty(&local->roc_list) || local->scanning) {
-		err = -EBUSY;
-		goto out_unlock;
-	}
+	if (!list_empty(&local->roc_list) || local->scanning)
+		return -EBUSY;
 
 	/* whatever, but channel contexts should not complain about that one */
 	sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
@@ -3483,13 +3481,12 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	err = ieee80211_link_use_channel(&sdata->deflink, &chanreq,
 					 IEEE80211_CHANCTX_SHARED);
 	if (err)
-		goto out_unlock;
+		return err;
 
 	wiphy_delayed_work_queue(wiphy, &sdata->deflink.dfs_cac_timer_work,
 				 msecs_to_jiffies(cac_time_ms));
 
- out_unlock:
-	return err;
+	return 0;
 }
 
 static void ieee80211_end_cac(struct wiphy *wiphy,
-- 
cgit v1.3-3-g829e


From f4bb650cfab4a3ffaf00b283f42b0941af1912c9 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:21 +0530
Subject: wifi: trace: unlink rdev_end_cac trace event from wiphy_netdev_evt
 class

rdev_end_cac trace event is linked with wiphy_netdev_evt event class.
There is no option to pass link ID currently to wiphy_netdev_evt class.
A subsequent change would pass link ID to rdev_end_cac event and hence
it can no longer derive the event class from wiphy_netdev_evt.

Therefore, unlink rdev_end_cac event from wiphy_netdev_evt and define it's
own independent trace event. Link ID would be passed in subsequent change.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-4-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/trace.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 5c26f065bd68..7fc7de9bcc34 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -805,9 +805,18 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa,
 	TP_ARGS(wiphy, netdev)
 );
 
-DEFINE_EVENT(wiphy_netdev_evt, rdev_end_cac,
-	     TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
-	     TP_ARGS(wiphy, netdev)
+TRACE_EVENT(rdev_end_cac,
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
+	TP_ARGS(wiphy, netdev),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		NETDEV_ENTRY
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		NETDEV_ASSIGN;
+	),
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG)
 );
 
 DECLARE_EVENT_CLASS(station_add_change,
-- 
cgit v1.3-3-g829e


From 62c16f219a73c237b5bef9bd160e32fbb38794f9 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:22 +0530
Subject: wifi: cfg80211: move DFS related members to links[] in wireless_dev

A few members related to DFS handling are currently under per wireless
device data structure. However, in order to support DFS with MLO, there is
a need to have them on a per-link manner.

Hence, as a preliminary step, move members cac_started, cac_start_time
and cac_time_ms to be on a per-link basis.

Since currently, link ID is not known at all places, use default value of
0 for now.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-5-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/11h.c      |  4 ++--
 drivers/net/wireless/marvell/mwifiex/cfg80211.c |  4 ++--
 drivers/net/wireless/quantenna/qtnfmac/event.c  |  6 +++---
 include/net/cfg80211.h                          | 17 +++++++++--------
 net/mac80211/cfg.c                              |  8 ++++----
 net/mac80211/iface.c                            |  2 +-
 net/mac80211/mlme.c                             |  2 +-
 net/mac80211/scan.c                             |  2 +-
 net/mac80211/util.c                             |  2 +-
 net/wireless/ibss.c                             |  2 +-
 net/wireless/mesh.c                             |  2 +-
 net/wireless/mlme.c                             | 11 ++++++-----
 net/wireless/nl80211.c                          | 10 +++++-----
 net/wireless/reg.c                              |  2 +-
 14 files changed, 38 insertions(+), 36 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11h.c b/drivers/net/wireless/marvell/mwifiex/11h.c
index b90f922f1cdc..fb2cad096758 100644
--- a/drivers/net/wireless/marvell/mwifiex/11h.c
+++ b/drivers/net/wireless/marvell/mwifiex/11h.c
@@ -117,7 +117,7 @@ void mwifiex_dfs_cac_work_queue(struct work_struct *work)
 				     dfs_cac_work);
 
 	chandef = priv->dfs_chandef;
-	if (priv->wdev.cac_started) {
+	if (priv->wdev.links[0].cac_started) {
 		mwifiex_dbg(priv->adapter, MSG,
 			    "CAC timer finished; No radar detected\n");
 		cfg80211_cac_event(priv->netdev, &chandef,
@@ -174,7 +174,7 @@ int mwifiex_stop_radar_detection(struct mwifiex_private *priv,
  */
 void mwifiex_abort_cac(struct mwifiex_private *priv)
 {
-	if (priv->wdev.cac_started) {
+	if (priv->wdev.links[0].cac_started) {
 		if (mwifiex_stop_radar_detection(priv, &priv->dfs_chandef))
 			mwifiex_dbg(priv->adapter, ERROR,
 				    "failed to stop CAC in FW\n");
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 5209e1c7d2e7..9d154c42465e 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1906,7 +1906,7 @@ mwifiex_cfg80211_del_station(struct wiphy *wiphy, struct net_device *dev,
 	struct mwifiex_sta_node *sta_node;
 	u8 deauth_mac[ETH_ALEN];
 
-	if (!priv->bss_started && priv->wdev.cac_started) {
+	if (!priv->bss_started && priv->wdev.links[0].cac_started) {
 		mwifiex_dbg(priv->adapter, INFO, "%s: abort CAC!\n", __func__);
 		mwifiex_abort_cac(priv);
 	}
@@ -4038,7 +4038,7 @@ mwifiex_cfg80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 		return -EBUSY;
 	}
 
-	if (priv->wdev.cac_started)
+	if (priv->wdev.links[0].cac_started)
 		return -EBUSY;
 
 	if (cfg80211_chandef_identical(&params->chandef,
diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c
index 76b07db284f8..8bd1e14e5de9 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/event.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/event.c
@@ -520,21 +520,21 @@ static int qtnf_event_handle_radar(struct qtnf_vif *vif,
 		cfg80211_radar_event(wiphy, &chandef, GFP_KERNEL);
 		break;
 	case QLINK_RADAR_CAC_FINISHED:
-		if (!vif->wdev.cac_started)
+		if (!vif->wdev.links[0].cac_started)
 			break;
 
 		cfg80211_cac_event(vif->netdev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED, GFP_KERNEL);
 		break;
 	case QLINK_RADAR_CAC_ABORTED:
-		if (!vif->wdev.cac_started)
+		if (!vif->wdev.links[0].cac_started)
 			break;
 
 		cfg80211_cac_event(vif->netdev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED, GFP_KERNEL);
 		break;
 	case QLINK_RADAR_CAC_STARTED:
-		if (vif->wdev.cac_started)
+		if (vif->wdev.links[0].cac_started)
 			break;
 
 		if (!wiphy_ext_feature_isset(wiphy,
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 192d72c8b465..727a94a6b7c3 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6194,9 +6194,6 @@ enum ieee80211_ap_reg_power {
  * @address: The address for this device, valid only if @netdev is %NULL
  * @is_running: true if this is a non-netdev device that has been started, e.g.
  *	the P2P Device.
- * @cac_started: true if DFS channel availability check has been started
- * @cac_start_time: timestamp (jiffies) when the dfs state was entered.
- * @cac_time_ms: CAC time in ms
  * @ps: powersave mode is enabled
  * @ps_timeout: dynamic powersave timeout
  * @ap_unexpected_nlportid: (private) netlink port ID of application
@@ -6220,6 +6217,11 @@ enum ieee80211_ap_reg_power {
  *	unprotected beacon report
  * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr
  *	@ap and @client for each link
+ * @links[].cac_started: true if DFS channel availability check has been
+ *	started
+ * @links[].cac_start_time: timestamp (jiffies) when the dfs state was
+ *	entered.
+ * @links[].cac_time_ms: CAC time in ms
  * @valid_links: bitmap describing what elements of @links are valid
  */
 struct wireless_dev {
@@ -6261,11 +6263,6 @@ struct wireless_dev {
 	u32 owner_nlportid;
 	bool nl_owner_dead;
 
-	/* FIXME: need to rework radar detection for MLO */
-	bool cac_started;
-	unsigned long cac_start_time;
-	unsigned int cac_time_ms;
-
 #ifdef CONFIG_CFG80211_WEXT
 	/* wext data */
 	struct {
@@ -6332,6 +6329,10 @@ struct wireless_dev {
 				struct cfg80211_internal_bss *current_bss;
 			} client;
 		};
+
+		bool cac_started;
+		unsigned long cac_start_time;
+		unsigned int cac_time_ms;
 	} links[IEEE80211_MLD_MAX_NUM_LINKS];
 	u16 valid_links;
 };
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index d3115be54997..5725ab6f495f 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1662,7 +1662,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 	ieee80211_link_info_change_notify(sdata, link,
 					  BSS_CHANGED_BEACON_ENABLED);
 
-	if (sdata->wdev.cac_started) {
+	if (sdata->wdev.links[0].cac_started) {
 		chandef = link_conf->chanreq.oper;
 		wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work);
 		cfg80211_cac_event(sdata->dev, &chandef,
@@ -3501,9 +3501,9 @@ static void ieee80211_end_cac(struct wiphy *wiphy,
 		wiphy_delayed_work_cancel(wiphy,
 					  &sdata->deflink.dfs_cac_timer_work);
 
-		if (sdata->wdev.cac_started) {
+		if (sdata->wdev.links[0].cac_started) {
 			ieee80211_link_release_channel(&sdata->deflink);
-			sdata->wdev.cac_started = false;
+			sdata->wdev.links[0].cac_started = false;
 		}
 	}
 }
@@ -3958,7 +3958,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 	if (!list_empty(&local->roc_list) || local->scanning)
 		return -EBUSY;
 
-	if (sdata->wdev.cac_started)
+	if (sdata->wdev.links[0].cac_started)
 		return -EBUSY;
 
 	if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS))
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7bb71ac52277..bdaf8e215965 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -552,7 +552,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	wiphy_delayed_work_cancel(local->hw.wiphy,
 				  &sdata->deflink.dfs_cac_timer_work);
 
-	if (sdata->wdev.cac_started) {
+	if (sdata->wdev.links[0].cac_started) {
 		chandef = sdata->vif.bss_conf.chanreq.oper;
 		WARN_ON(local->suspended);
 		ieee80211_link_release_channel(&sdata->deflink);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 85789c184949..79579c89e281 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3039,7 +3039,7 @@ void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work)
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
-	if (sdata->wdev.cac_started) {
+	if (sdata->wdev.links[0].cac_started) {
 		ieee80211_link_release_channel(link);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED,
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 14e18fd9e919..6735620378f4 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -585,7 +585,7 @@ static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata)
 		return false;
 
 	list_for_each_entry(sdata_iter, &local->interfaces, list) {
-		if (sdata_iter->wdev.cac_started)
+		if (sdata_iter->wdev.links[0].cac_started)
 			return false;
 	}
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 071cbb7929d9..ab17361dba97 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3478,7 +3478,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 		wiphy_delayed_work_cancel(local->hw.wiphy,
 					  &sdata->deflink.dfs_cac_timer_work);
 
-		if (sdata->wdev.cac_started) {
+		if (sdata->wdev.links[0].cac_started) {
 			chandef = sdata->vif.bss_conf.chanreq.oper;
 			ieee80211_link_release_channel(&sdata->deflink);
 			cfg80211_cac_event(sdata->dev,
diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
index 34e5acff3935..1e3ed29f7cfc 100644
--- a/net/wireless/ibss.c
+++ b/net/wireless/ibss.c
@@ -94,7 +94,7 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
 
 	lockdep_assert_held(&rdev->wiphy.mtx);
 
-	if (wdev->cac_started)
+	if (wdev->links[0].cac_started)
 		return -EBUSY;
 
 	if (wdev->u.ibss.ssid_len)
diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
index aaca65b66af4..2c6654075ca9 100644
--- a/net/wireless/mesh.c
+++ b/net/wireless/mesh.c
@@ -127,7 +127,7 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
 	if (!rdev->ops->join_mesh)
 		return -EOPNOTSUPP;
 
-	if (wdev->cac_started)
+	if (wdev->links[0].cac_started)
 		return -EBUSY;
 
 	if (!setup->chandef.chan) {
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 4052041a19ea..fddd6a62b942 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -1123,13 +1123,14 @@ void cfg80211_cac_event(struct net_device *netdev,
 
 	trace_cfg80211_cac_event(netdev, event);
 
-	if (WARN_ON(!wdev->cac_started && event != NL80211_RADAR_CAC_STARTED))
+	if (WARN_ON(!wdev->links[0].cac_started &&
+		    event != NL80211_RADAR_CAC_STARTED))
 		return;
 
 	switch (event) {
 	case NL80211_RADAR_CAC_FINISHED:
-		timeout = wdev->cac_start_time +
-			  msecs_to_jiffies(wdev->cac_time_ms);
+		timeout = wdev->links[0].cac_start_time +
+			  msecs_to_jiffies(wdev->links[0].cac_time_ms);
 		WARN_ON(!time_after_eq(jiffies, timeout));
 		cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE);
 		memcpy(&rdev->cac_done_chandef, chandef,
@@ -1138,10 +1139,10 @@ void cfg80211_cac_event(struct net_device *netdev,
 		cfg80211_sched_dfs_chan_update(rdev);
 		fallthrough;
 	case NL80211_RADAR_CAC_ABORTED:
-		wdev->cac_started = false;
+		wdev->links[0].cac_started = false;
 		break;
 	case NL80211_RADAR_CAC_STARTED:
-		wdev->cac_started = true;
+		wdev->links[0].cac_started = true;
 		break;
 	default:
 		WARN_ON(1);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 3a11a1a74a54..f4fdf32d5d07 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6066,7 +6066,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->start_ap)
 		return -EOPNOTSUPP;
 
-	if (wdev->cac_started)
+	if (wdev->links[0].cac_started)
 		return -EBUSY;
 
 	if (wdev->links[link_id].ap.beacon_interval)
@@ -10121,7 +10121,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		goto unlock;
 	}
 
-	if (cfg80211_beaconing_iface_active(wdev) || wdev->cac_started) {
+	if (cfg80211_beaconing_iface_active(wdev) || wdev->links[0].cac_started) {
 		err = -EBUSY;
 		goto unlock;
 	}
@@ -10157,9 +10157,9 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		default:
 			break;
 		}
-		wdev->cac_started = true;
-		wdev->cac_start_time = jiffies;
-		wdev->cac_time_ms = cac_time_ms;
+		wdev->links[0].cac_started = true;
+		wdev->links[0].cac_start_time = jiffies;
+		wdev->links[0].cac_time_ms = cac_time_ms;
 	}
 unlock:
 	wiphy_unlock(wiphy);
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 4a27f3823e25..898abc6d0609 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -4241,7 +4241,7 @@ static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev)
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		struct cfg80211_chan_def *chandef;
 
-		if (!wdev->cac_started)
+		if (!wdev->links[0].cac_started)
 			continue;
 
 		/* FIXME: radar detection is tied to link 0 for now */
-- 
cgit v1.3-3-g829e


From 81f67d60ebf290da068af96ad0c4a4e4faebdf1d Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:23 +0530
Subject: wifi: cfg80211: handle DFS per link

Currently, during starting a radar detection, no link id information is
parsed and passed down. In order to support starting radar detection
during Multi Link Operation, it is required to pass link id as well.

Add changes to first parse and then pass link id in the start radar
detection path.

Additionally, update notification APIs to allow drivers/mac80211 to
pass the link ID.

However, everything is handled at link 0 only until all API's are ready to
handle it per link.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-6-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/11h.c        |  7 ++---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c   |  2 +-
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.c |  2 +-
 drivers/net/wireless/quantenna/qtnfmac/event.c    |  6 ++---
 include/net/cfg80211.h                            |  8 +++---
 net/mac80211/cfg.c                                |  6 ++---
 net/mac80211/iface.c                              |  2 +-
 net/mac80211/mlme.c                               |  2 +-
 net/mac80211/util.c                               |  2 +-
 net/wireless/mlme.c                               |  9 ++++---
 net/wireless/nl80211.c                            | 24 ++++++++++++++----
 net/wireless/rdev-ops.h                           | 13 +++++-----
 net/wireless/reg.c                                | 19 ++++++++------
 net/wireless/trace.h                              | 31 +++++++++++++++--------
 14 files changed, 82 insertions(+), 51 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11h.c b/drivers/net/wireless/marvell/mwifiex/11h.c
index fb2cad096758..032b93a41d99 100644
--- a/drivers/net/wireless/marvell/mwifiex/11h.c
+++ b/drivers/net/wireless/marvell/mwifiex/11h.c
@@ -122,7 +122,7 @@ void mwifiex_dfs_cac_work_queue(struct work_struct *work)
 			    "CAC timer finished; No radar detected\n");
 		cfg80211_cac_event(priv->netdev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED,
-				   GFP_KERNEL);
+				   GFP_KERNEL, 0);
 	}
 }
 
@@ -182,7 +182,8 @@ void mwifiex_abort_cac(struct mwifiex_private *priv)
 			    "Aborting delayed work for CAC.\n");
 		cancel_delayed_work_sync(&priv->dfs_cac_work);
 		cfg80211_cac_event(priv->netdev, &priv->dfs_chandef,
-				   NL80211_RADAR_CAC_ABORTED, GFP_KERNEL);
+				   NL80211_RADAR_CAC_ABORTED, GFP_KERNEL,
+				   0);
 	}
 }
 
@@ -221,7 +222,7 @@ int mwifiex_11h_handle_chanrpt_ready(struct mwifiex_private *priv,
 				cfg80211_cac_event(priv->netdev,
 						   &priv->dfs_chandef,
 						   NL80211_RADAR_DETECTED,
-						   GFP_KERNEL);
+						   GFP_KERNEL, 0);
 			}
 			break;
 		default:
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 9d154c42465e..fca3eea7ee84 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4205,7 +4205,7 @@ static int
 mwifiex_cfg80211_start_radar_detection(struct wiphy *wiphy,
 				       struct net_device *dev,
 				       struct cfg80211_chan_def *chandef,
-				       u32 cac_time_ms)
+				       u32 cac_time_ms, int link_id)
 {
 	struct mwifiex_private *priv = mwifiex_netdev_get_priv(dev);
 	struct mwifiex_radar_params radar_params;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 663d77770fce..8b97accf6638 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -837,7 +837,7 @@ static int qtnf_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 static int qtnf_start_radar_detection(struct wiphy *wiphy,
 				      struct net_device *ndev,
 				      struct cfg80211_chan_def *chandef,
-				      u32 cac_time_ms)
+				      u32 cac_time_ms, int link_id)
 {
 	struct qtnf_vif *vif = qtnf_netdev_get_priv(ndev);
 	int ret;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c
index 8bd1e14e5de9..71840f41b73c 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/event.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/event.c
@@ -524,14 +524,14 @@ static int qtnf_event_handle_radar(struct qtnf_vif *vif,
 			break;
 
 		cfg80211_cac_event(vif->netdev, &chandef,
-				   NL80211_RADAR_CAC_FINISHED, GFP_KERNEL);
+				   NL80211_RADAR_CAC_FINISHED, GFP_KERNEL, 0);
 		break;
 	case QLINK_RADAR_CAC_ABORTED:
 		if (!vif->wdev.links[0].cac_started)
 			break;
 
 		cfg80211_cac_event(vif->netdev, &chandef,
-				   NL80211_RADAR_CAC_ABORTED, GFP_KERNEL);
+				   NL80211_RADAR_CAC_ABORTED, GFP_KERNEL, 0);
 		break;
 	case QLINK_RADAR_CAC_STARTED:
 		if (vif->wdev.links[0].cac_started)
@@ -542,7 +542,7 @@ static int qtnf_event_handle_radar(struct qtnf_vif *vif,
 			break;
 
 		cfg80211_cac_event(vif->netdev, &chandef,
-				   NL80211_RADAR_CAC_STARTED, GFP_KERNEL);
+				   NL80211_RADAR_CAC_STARTED, GFP_KERNEL, 0);
 		break;
 	default:
 		pr_warn("%s: unhandled radar event %u\n",
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 727a94a6b7c3..efdea667cb92 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4837,9 +4837,9 @@ struct cfg80211_ops {
 	int	(*start_radar_detection)(struct wiphy *wiphy,
 					 struct net_device *dev,
 					 struct cfg80211_chan_def *chandef,
-					 u32 cac_time_ms);
+					 u32 cac_time_ms, int link_id);
 	void	(*end_cac)(struct wiphy *wiphy,
-				struct net_device *dev);
+			   struct net_device *dev, unsigned int link_id);
 	int	(*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev,
 				 struct cfg80211_update_ft_ies_params *ftie);
 	int	(*crit_proto_start)(struct wiphy *wiphy,
@@ -8741,6 +8741,7 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac,
  * @chandef: chandef for the current channel
  * @event: type of event
  * @gfp: context flags
+ * @link_id: valid link_id for MLO operation or 0 otherwise.
  *
  * This function is called when a Channel availability check (CAC) is finished
  * or aborted. This must be called to notify the completion of a CAC process,
@@ -8748,7 +8749,8 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac,
  */
 void cfg80211_cac_event(struct net_device *netdev,
 			const struct cfg80211_chan_def *chandef,
-			enum nl80211_radar_event event, gfp_t gfp);
+			enum nl80211_radar_event event, gfp_t gfp,
+			unsigned int link_id);
 
 /**
  * cfg80211_background_cac_abort - Channel Availability Check offchan abort event
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 5725ab6f495f..67dd780530fb 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1667,7 +1667,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 		wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED,
-				   GFP_KERNEL);
+				   GFP_KERNEL, 0);
 	}
 
 	drv_stop_ap(sdata->local, sdata, link_conf);
@@ -3462,7 +3462,7 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy,
 static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 					   struct net_device *dev,
 					   struct cfg80211_chan_def *chandef,
-					   u32 cac_time_ms)
+					   u32 cac_time_ms, int link_id)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_chan_req chanreq = { .oper = *chandef };
@@ -3490,7 +3490,7 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 }
 
 static void ieee80211_end_cac(struct wiphy *wiphy,
-			      struct net_device *dev)
+			      struct net_device *dev, unsigned int link_id)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index bdaf8e215965..e074de893ed6 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -558,7 +558,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 		ieee80211_link_release_channel(&sdata->deflink);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED,
-				   GFP_KERNEL);
+				   GFP_KERNEL, 0);
 	}
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP) {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 79579c89e281..715709860fdd 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3043,7 +3043,7 @@ void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work)
 		ieee80211_link_release_channel(link);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED,
-				   GFP_KERNEL);
+				   GFP_KERNEL, 0);
 	}
 }
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ab17361dba97..c4fd60fbcfd4 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3484,7 +3484,7 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 			cfg80211_cac_event(sdata->dev,
 					   &chandef,
 					   NL80211_RADAR_CAC_ABORTED,
-					   GFP_KERNEL);
+					   GFP_KERNEL, 0);
 		}
 	}
 }
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index fddd6a62b942..115c8cd28aaf 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -1110,18 +1110,19 @@ EXPORT_SYMBOL(__cfg80211_radar_event);
 
 void cfg80211_cac_event(struct net_device *netdev,
 			const struct cfg80211_chan_def *chandef,
-			enum nl80211_radar_event event, gfp_t gfp)
+			enum nl80211_radar_event event, gfp_t gfp,
+			unsigned int link_id)
 {
 	struct wireless_dev *wdev = netdev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	unsigned long timeout;
 
-	/* not yet supported */
-	if (wdev->valid_links)
+	if (WARN_ON(wdev->valid_links &&
+		    !(wdev->valid_links & BIT(link_id))))
 		return;
 
-	trace_cfg80211_cac_event(netdev, event);
+	trace_cfg80211_cac_event(netdev, event, link_id);
 
 	if (WARN_ON(!wdev->links[0].cac_started &&
 		    event != NL80211_RADAR_CAC_STARTED))
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index f4fdf32d5d07..7d9264304a8a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10121,7 +10121,20 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		goto unlock;
 	}
 
-	if (cfg80211_beaconing_iface_active(wdev) || wdev->links[0].cac_started) {
+	if (cfg80211_beaconing_iface_active(wdev)) {
+		/* During MLO other link(s) can beacon, only the current link
+		 * can not already beacon
+		 */
+		if (wdev->valid_links &&
+		    !wdev->links[0].ap.beacon_interval) {
+			/* nothing */
+		} else {
+			err = -EBUSY;
+			goto unlock;
+		}
+	}
+
+	if (wdev->links[0].cac_started) {
 		err = -EBUSY;
 		goto unlock;
 	}
@@ -10141,7 +10154,8 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	if (WARN_ON(!cac_time_ms))
 		cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
 
-	err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms);
+	err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms,
+					 0);
 	if (!err) {
 		switch (wdev->iftype) {
 		case NL80211_IFTYPE_AP:
@@ -16515,10 +16529,10 @@ nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info)
 	SELECTOR(__sel, NETDEV_UP_NOTMX,		\
 		 NL80211_FLAG_NEED_NETDEV_UP |		\
 		 NL80211_FLAG_NO_WIPHY_MTX)		\
-	SELECTOR(__sel, NETDEV_UP_NOTMX_NOMLO,		\
+	SELECTOR(__sel, NETDEV_UP_NOTMX_MLO,		\
 		 NL80211_FLAG_NEED_NETDEV_UP |		\
 		 NL80211_FLAG_NO_WIPHY_MTX |		\
-		 NL80211_FLAG_MLO_UNSUPPORTED)		\
+		 NL80211_FLAG_MLO_VALID_LINK_ID)	\
 	SELECTOR(__sel, NETDEV_UP_CLEAR,		\
 		 NL80211_FLAG_NEED_NETDEV_UP |		\
 		 NL80211_FLAG_CLEAR_SKB)		\
@@ -17413,7 +17427,7 @@ static const struct genl_small_ops nl80211_small_ops[] = {
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP |
 					 NL80211_FLAG_NO_WIPHY_MTX |
-					 NL80211_FLAG_MLO_UNSUPPORTED),
+					 NL80211_FLAG_MLO_VALID_LINK_ID),
 	},
 	{
 		.cmd = NL80211_CMD_GET_PROTOCOL_FEATURES,
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index ec3f4aa1c807..f5adbf6b5c84 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -1200,26 +1200,27 @@ static inline int
 rdev_start_radar_detection(struct cfg80211_registered_device *rdev,
 			   struct net_device *dev,
 			   struct cfg80211_chan_def *chandef,
-			   u32 cac_time_ms)
+			   u32 cac_time_ms, int link_id)
 {
 	int ret = -EOPNOTSUPP;
 
 	trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef,
-					 cac_time_ms);
+					 cac_time_ms, link_id);
 	if (rdev->ops->start_radar_detection)
 		ret = rdev->ops->start_radar_detection(&rdev->wiphy, dev,
-						       chandef, cac_time_ms);
+						       chandef, cac_time_ms,
+						       link_id);
 	trace_rdev_return_int(&rdev->wiphy, ret);
 	return ret;
 }
 
 static inline void
 rdev_end_cac(struct cfg80211_registered_device *rdev,
-	     struct net_device *dev)
+	     struct net_device *dev, unsigned int link_id)
 {
-	trace_rdev_end_cac(&rdev->wiphy, dev);
+	trace_rdev_end_cac(&rdev->wiphy, dev, link_id);
 	if (rdev->ops->end_cac)
-		rdev->ops->end_cac(&rdev->wiphy, dev);
+		rdev->ops->end_cac(&rdev->wiphy, dev, link_id);
 	trace_rdev_return_void(&rdev->wiphy);
 }
 
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 898abc6d0609..6489ba943a63 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -4229,6 +4229,8 @@ EXPORT_SYMBOL(regulatory_pre_cac_allowed);
 static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev)
 {
 	struct wireless_dev *wdev;
+	unsigned int link_id;
+
 	/* If we finished CAC or received radar, we should end any
 	 * CAC running on the same channels.
 	 * the check !cfg80211_chandef_dfs_usable contain 2 options:
@@ -4241,16 +4243,17 @@ static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev)
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		struct cfg80211_chan_def *chandef;
 
-		if (!wdev->links[0].cac_started)
-			continue;
+		for_each_valid_link(wdev, link_id) {
+			if (!wdev->links[link_id].cac_started)
+				continue;
 
-		/* FIXME: radar detection is tied to link 0 for now */
-		chandef = wdev_chandef(wdev, 0);
-		if (!chandef)
-			continue;
+			chandef = wdev_chandef(wdev, link_id);
+			if (!chandef)
+				continue;
 
-		if (!cfg80211_chandef_dfs_usable(&rdev->wiphy, chandef))
-			rdev_end_cac(rdev, wdev->netdev);
+			if (!cfg80211_chandef_dfs_usable(&rdev->wiphy, chandef))
+				rdev_end_cac(rdev, wdev->netdev, link_id);
+		}
 	}
 }
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 7fc7de9bcc34..97c21b627791 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -806,17 +806,21 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa,
 );
 
 TRACE_EVENT(rdev_end_cac,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev),
-	TP_ARGS(wiphy, netdev),
+	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
+		 unsigned int link_id),
+	TP_ARGS(wiphy, netdev, link_id),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
+		__field(unsigned int, link_id)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
+		__entry->link_id = link_id;
 	),
-	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, WIPHY_PR_ARG, NETDEV_PR_ARG)
+	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", link_id: %d",
+		  WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->link_id)
 );
 
 DECLARE_EVENT_CLASS(station_add_change,
@@ -2661,24 +2665,26 @@ TRACE_EVENT(rdev_external_auth,
 TRACE_EVENT(rdev_start_radar_detection,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
 		 struct cfg80211_chan_def *chandef,
-		 u32 cac_time_ms),
-	TP_ARGS(wiphy, netdev, chandef, cac_time_ms),
+		 u32 cac_time_ms, int link_id),
+	TP_ARGS(wiphy, netdev, chandef, cac_time_ms, link_id),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
 		CHAN_DEF_ENTRY
 		__field(u32, cac_time_ms)
+		__field(int, link_id)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		NETDEV_ASSIGN;
 		CHAN_DEF_ASSIGN(chandef);
 		__entry->cac_time_ms = cac_time_ms;
+		__entry->link_id = link_id;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT
-		  ", cac_time_ms=%u",
+		  ", cac_time_ms=%u, link_id=%d",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG,
-		  __entry->cac_time_ms)
+		  __entry->cac_time_ms, __entry->link_id)
 );
 
 TRACE_EVENT(rdev_set_mcast_rate,
@@ -3492,18 +3498,21 @@ TRACE_EVENT(cfg80211_radar_event,
 );
 
 TRACE_EVENT(cfg80211_cac_event,
-	TP_PROTO(struct net_device *netdev, enum nl80211_radar_event evt),
-	TP_ARGS(netdev, evt),
+	TP_PROTO(struct net_device *netdev, enum nl80211_radar_event evt,
+		 unsigned int link_id),
+	TP_ARGS(netdev, evt, link_id),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
 		__field(enum nl80211_radar_event, evt)
+		__field(unsigned int, link_id)
 	),
 	TP_fast_assign(
 		NETDEV_ASSIGN;
 		__entry->evt = evt;
+		__entry->link_id = link_id;
 	),
-	TP_printk(NETDEV_PR_FMT ",  event: %d",
-		  NETDEV_PR_ARG, __entry->evt)
+	TP_printk(NETDEV_PR_FMT ",  event: %d, link_id=%u",
+		  NETDEV_PR_ARG, __entry->evt, __entry->link_id)
 );
 
 DECLARE_EVENT_CLASS(cfg80211_rx_evt,
-- 
cgit v1.3-3-g829e


From d74380ee99b59a2e46612c12c85e701ab213f4ea Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:24 +0530
Subject: wifi: mac80211: handle DFS per link

In order to support DFS with MLO, handle the link ID now passed from
cfg80211, adjust the code to do everything per link and call the
notifications to cfg80211 correctly.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-7-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c  | 26 ++++++++++++++++++--------
 net/mac80211/link.c | 10 ++++++++++
 net/mac80211/util.c | 28 +++++++++++++++++++---------
 3 files changed, 47 insertions(+), 17 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 67dd780530fb..57e66c671e2e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3467,6 +3467,7 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_chan_req chanreq = { .oper = *chandef };
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_link_data *link_data;
 	int err;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
@@ -3474,16 +3475,20 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy,
 	if (!list_empty(&local->roc_list) || local->scanning)
 		return -EBUSY;
 
+	link_data = sdata_dereference(sdata->link[link_id], sdata);
+	if (!link_data)
+		return -ENOLINK;
+
 	/* whatever, but channel contexts should not complain about that one */
-	sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
-	sdata->deflink.needed_rx_chains = local->rx_chains;
+	link_data->smps_mode = IEEE80211_SMPS_OFF;
+	link_data->needed_rx_chains = local->rx_chains;
 
-	err = ieee80211_link_use_channel(&sdata->deflink, &chanreq,
+	err = ieee80211_link_use_channel(link_data, &chanreq,
 					 IEEE80211_CHANCTX_SHARED);
 	if (err)
 		return err;
 
-	wiphy_delayed_work_queue(wiphy, &sdata->deflink.dfs_cac_timer_work,
+	wiphy_delayed_work_queue(wiphy, &link_data->dfs_cac_timer_work,
 				 msecs_to_jiffies(cac_time_ms));
 
 	return 0;
@@ -3494,16 +3499,21 @@ static void ieee80211_end_cac(struct wiphy *wiphy,
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_link_data *link_data;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
+		link_data = sdata_dereference(sdata->link[link_id], sdata);
+		if (!link_data)
+			continue;
+
 		wiphy_delayed_work_cancel(wiphy,
-					  &sdata->deflink.dfs_cac_timer_work);
+					  &link_data->dfs_cac_timer_work);
 
-		if (sdata->wdev.links[0].cac_started) {
-			ieee80211_link_release_channel(&sdata->deflink);
-			sdata->wdev.links[0].cac_started = false;
+		if (sdata->wdev.links[link_id].cac_started) {
+			ieee80211_link_release_channel(link_data);
+			sdata->wdev.links[link_id].cac_started = false;
 		}
 	}
 }
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index b4378969cbf1..0bbac64d5fa0 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -77,6 +77,16 @@ void ieee80211_link_stop(struct ieee80211_link_data *link)
 			  &link->color_change_finalize_work);
 	wiphy_work_cancel(link->sdata->local->hw.wiphy,
 			  &link->csa.finalize_work);
+
+	if (link->sdata->wdev.links[link->link_id].cac_started) {
+		wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy,
+					  &link->dfs_cac_timer_work);
+		cfg80211_cac_event(link->sdata->dev,
+				   &link->conf->chanreq.oper,
+				   NL80211_RADAR_CAC_ABORTED,
+				   GFP_KERNEL, link->link_id);
+	}
+
 	ieee80211_link_release_channel(link);
 }
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index c4fd60fbcfd4..2e37d2639074 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3471,20 +3471,30 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct cfg80211_chan_def chandef;
+	struct ieee80211_link_data *link;
+	unsigned int link_id;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		wiphy_delayed_work_cancel(local->hw.wiphy,
-					  &sdata->deflink.dfs_cac_timer_work);
-
-		if (sdata->wdev.links[0].cac_started) {
-			chandef = sdata->vif.bss_conf.chanreq.oper;
-			ieee80211_link_release_channel(&sdata->deflink);
-			cfg80211_cac_event(sdata->dev,
-					   &chandef,
+		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
+		     link_id++) {
+			link = sdata_dereference(sdata->link[link_id],
+						 sdata);
+			if (!link)
+				continue;
+
+			wiphy_delayed_work_cancel(local->hw.wiphy,
+						  &link->dfs_cac_timer_work);
+
+			if (!sdata->wdev.links[link_id].cac_started)
+				continue;
+
+			chandef = link->conf->chanreq.oper;
+			ieee80211_link_release_channel(link);
+			cfg80211_cac_event(sdata->dev, &chandef,
 					   NL80211_RADAR_CAC_ABORTED,
-					   GFP_KERNEL, 0);
+					   GFP_KERNEL, link_id);
 		}
 	}
 }
-- 
cgit v1.3-3-g829e


From 0b7798232eee010d8c52e1ab5f96a1cce0d4183e Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:25 +0530
Subject: wifi: cfg80211/mac80211: use proper link ID for DFS

Now that all APIs have support to handle DFS per link, use proper link ID
instead of 0.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-8-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c     |  6 +++---
 net/mac80211/mlme.c    |  4 ++--
 net/mac80211/scan.c    |  6 ++++--
 net/wireless/mlme.c    | 10 +++++-----
 net/wireless/nl80211.c | 15 ++++++++-------
 5 files changed, 22 insertions(+), 19 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 57e66c671e2e..847304a3a29a 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1662,12 +1662,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev,
 	ieee80211_link_info_change_notify(sdata, link,
 					  BSS_CHANGED_BEACON_ENABLED);
 
-	if (sdata->wdev.links[0].cac_started) {
+	if (sdata->wdev.links[link_id].cac_started) {
 		chandef = link_conf->chanreq.oper;
 		wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_ABORTED,
-				   GFP_KERNEL, 0);
+				   GFP_KERNEL, link_id);
 	}
 
 	drv_stop_ap(sdata->local, sdata, link_conf);
@@ -3968,7 +3968,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 	if (!list_empty(&local->roc_list) || local->scanning)
 		return -EBUSY;
 
-	if (sdata->wdev.links[0].cac_started)
+	if (sdata->wdev.links[link_id].cac_started)
 		return -EBUSY;
 
 	if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS))
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 715709860fdd..735e78adb0db 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3039,11 +3039,11 @@ void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work)
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
-	if (sdata->wdev.links[0].cac_started) {
+	if (sdata->wdev.links[link->link_id].cac_started) {
 		ieee80211_link_release_channel(link);
 		cfg80211_cac_event(sdata->dev, &chandef,
 				   NL80211_RADAR_CAC_FINISHED,
-				   GFP_KERNEL, 0);
+				   GFP_KERNEL, link->link_id);
 	}
 }
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 6735620378f4..adb88c06b598 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -575,6 +575,7 @@ static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_sub_if_data *sdata_iter;
+	unsigned int link_id;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
@@ -585,8 +586,9 @@ static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata)
 		return false;
 
 	list_for_each_entry(sdata_iter, &local->interfaces, list) {
-		if (sdata_iter->wdev.links[0].cac_started)
-			return false;
+		for_each_valid_link(&sdata_iter->wdev, link_id)
+			if (sdata_iter->wdev.links[link_id].cac_started)
+				return false;
 	}
 
 	return true;
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 115c8cd28aaf..4dac81854721 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -1124,14 +1124,14 @@ void cfg80211_cac_event(struct net_device *netdev,
 
 	trace_cfg80211_cac_event(netdev, event, link_id);
 
-	if (WARN_ON(!wdev->links[0].cac_started &&
+	if (WARN_ON(!wdev->links[link_id].cac_started &&
 		    event != NL80211_RADAR_CAC_STARTED))
 		return;
 
 	switch (event) {
 	case NL80211_RADAR_CAC_FINISHED:
-		timeout = wdev->links[0].cac_start_time +
-			  msecs_to_jiffies(wdev->links[0].cac_time_ms);
+		timeout = wdev->links[link_id].cac_start_time +
+			  msecs_to_jiffies(wdev->links[link_id].cac_time_ms);
 		WARN_ON(!time_after_eq(jiffies, timeout));
 		cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE);
 		memcpy(&rdev->cac_done_chandef, chandef,
@@ -1140,10 +1140,10 @@ void cfg80211_cac_event(struct net_device *netdev,
 		cfg80211_sched_dfs_chan_update(rdev);
 		fallthrough;
 	case NL80211_RADAR_CAC_ABORTED:
-		wdev->links[0].cac_started = false;
+		wdev->links[link_id].cac_started = false;
 		break;
 	case NL80211_RADAR_CAC_STARTED:
-		wdev->links[0].cac_started = true;
+		wdev->links[link_id].cac_started = true;
 		break;
 	default:
 		WARN_ON(1);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7d9264304a8a..8bad3c6db39d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6066,7 +6066,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->start_ap)
 		return -EOPNOTSUPP;
 
-	if (wdev->links[0].cac_started)
+	if (wdev->links[link_id].cac_started)
 		return -EBUSY;
 
 	if (wdev->links[link_id].ap.beacon_interval)
@@ -10072,6 +10072,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int link_id = nl80211_link_id(info->attrs);
 	struct wiphy *wiphy = wdev->wiphy;
 	struct cfg80211_chan_def chandef;
 	enum nl80211_dfs_regions dfs_region;
@@ -10126,7 +10127,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		 * can not already beacon
 		 */
 		if (wdev->valid_links &&
-		    !wdev->links[0].ap.beacon_interval) {
+		    !wdev->links[link_id].ap.beacon_interval) {
 			/* nothing */
 		} else {
 			err = -EBUSY;
@@ -10134,7 +10135,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		}
 	}
 
-	if (wdev->links[0].cac_started) {
+	if (wdev->links[link_id].cac_started) {
 		err = -EBUSY;
 		goto unlock;
 	}
@@ -10155,7 +10156,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
 
 	err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms,
-					 0);
+					 link_id);
 	if (!err) {
 		switch (wdev->iftype) {
 		case NL80211_IFTYPE_AP:
@@ -10171,9 +10172,9 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 		default:
 			break;
 		}
-		wdev->links[0].cac_started = true;
-		wdev->links[0].cac_start_time = jiffies;
-		wdev->links[0].cac_time_ms = cac_time_ms;
+		wdev->links[link_id].cac_started = true;
+		wdev->links[link_id].cac_start_time = jiffies;
+		wdev->links[link_id].cac_time_ms = cac_time_ms;
 	}
 unlock:
 	wiphy_unlock(wiphy);
-- 
cgit v1.3-3-g829e


From bca8bc0399ac2efd56e6adbed0307e10125a556c Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 6 Sep 2024 12:14:26 +0530
Subject: wifi: mac80211: handle ieee80211_radar_detected() for MLO

Currently DFS works under assumption there could be only one channel
context in the hardware. Hence, drivers just calls the function
ieee80211_radar_detected() passing the hardware structure. However, with
MLO, this obviously will not work since number of channel contexts will be
more than one and hence drivers would need to pass the channel information
as well on which the radar is detected.

Also, when radar is detected in one of the links, other link's CAC should
not be cancelled.

Hence, in order to support DFS with MLO, do the following changes -
  * Add channel context conf pointer as an argument to the function
    ieee80211_radar_detected(). During MLO, drivers would have to pass on
    which channel context conf radar is detected. Otherwise, drivers could
    just pass NULL.
  * ieee80211_radar_detected() will iterate over all channel contexts
    present and
  	* if channel context conf is passed, only mark that as radar
  	  detected
  	* if NULL is passed, then mark all channel contexts as radar
  	  detected
  	* Then as usual, schedule the radar detected work.
  * In the worker, go over all the contexts again and for all such context
    which is marked with radar detected, cancel the ongoing CAC by calling
    ieee80211_dfs_cac_cancel() and then notify cfg80211 via
    cfg80211_radar_event().
  * To cancel the CAC, pass the channel context as well where radar is
    detected to ieee80211_dfs_cac_cancel(). This ensures that CAC is
    canceled only on the links using the provided context, leaving other
    links unaffected.

This would also help in scenarios where there is split phy 5 GHz radio,
which is capable of DFS channels in both lower and upper band. In this
case, simultaneous radars can be detected.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20240906064426.2101315-9-quic_adisi@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath10k/debug.c          |  4 +-
 drivers/net/wireless/ath/ath10k/mac.c            |  2 +-
 drivers/net/wireless/ath/ath10k/wmi.c            |  2 +-
 drivers/net/wireless/ath/ath11k/wmi.c            |  2 +-
 drivers/net/wireless/ath/ath12k/wmi.c            |  2 +-
 drivers/net/wireless/ath/ath9k/dfs.c             |  2 +-
 drivers/net/wireless/ath/ath9k/dfs_debug.c       |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7615/mcu.c  |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c |  4 +-
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c  |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c  |  2 +-
 drivers/net/wireless/ti/wl18xx/event.c           |  2 +-
 drivers/net/wireless/virtual/mac80211_hwsim.c    |  2 +-
 include/net/mac80211.h                           |  5 ++-
 net/mac80211/chan.c                              |  1 +
 net/mac80211/ieee80211_i.h                       |  5 ++-
 net/mac80211/pm.c                                |  2 +-
 net/mac80211/util.c                              | 52 +++++++++++++++++++-----
 18 files changed, 66 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index b93a64bf8190..35bfe7232e95 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -3,7 +3,7 @@
  * Copyright (c) 2005-2011 Atheros Communications Inc.
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -1774,7 +1774,7 @@ static ssize_t ath10k_write_simulate_radar(struct file *file,
 	if (!arvif->is_started)
 		return -EINVAL;
 
-	ieee80211_radar_detected(ar->hw);
+	ieee80211_radar_detected(ar->hw, NULL);
 
 	return count;
 }
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index a5da32e87106..646e1737d4c4 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -1437,7 +1437,7 @@ static void ath10k_recalc_radar_detection(struct ath10k *ar)
 		 * by indicating that radar was detected.
 		 */
 		ath10k_warn(ar, "failed to start CAC: %d\n", ret);
-		ieee80211_radar_detected(ar->hw);
+		ieee80211_radar_detected(ar->hw, NULL);
 	}
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index fe2344598364..4861179b2217 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -3990,7 +3990,7 @@ static void ath10k_radar_detected(struct ath10k *ar)
 	if (ar->dfs_block_radar_events)
 		ath10k_info(ar, "DFS Radar detected, but ignored as requested\n");
 	else
-		ieee80211_radar_detected(ar->hw);
+		ieee80211_radar_detected(ar->hw, NULL);
 }
 
 static void ath10k_radar_confirmation_work(struct work_struct *work)
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 2662092ee00a..87abfa547529 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -8358,7 +8358,7 @@ ath11k_wmi_pdev_dfs_radar_detected_event(struct ath11k_base *ab, struct sk_buff
 	if (ar->dfs_block_radar_events)
 		ath11k_info(ab, "DFS Radar detected, but ignored as requested\n");
 	else
-		ieee80211_radar_detected(ar->hw);
+		ieee80211_radar_detected(ar->hw, NULL);
 
 exit:
 	rcu_read_unlock();
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index a76413320dbf..2cd3ff9b0164 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -6789,7 +6789,7 @@ ath12k_wmi_pdev_dfs_radar_detected_event(struct ath12k_base *ab, struct sk_buff
 	if (ar->dfs_block_radar_events)
 		ath12k_info(ab, "DFS Radar detected, but ignored as requested\n");
 	else
-		ieee80211_radar_detected(ath12k_ar_to_hw(ar));
+		ieee80211_radar_detected(ath12k_ar_to_hw(ar), NULL);
 
 exit:
 	rcu_read_unlock();
diff --git a/drivers/net/wireless/ath/ath9k/dfs.c b/drivers/net/wireless/ath/ath9k/dfs.c
index 11349218bc21..3689e12db9f7 100644
--- a/drivers/net/wireless/ath/ath9k/dfs.c
+++ b/drivers/net/wireless/ath/ath9k/dfs.c
@@ -280,7 +280,7 @@ ath9k_dfs_process_radar_pulse(struct ath_softc *sc, struct pulse_event *pe)
 	if (!pd->add_pulse(pd, pe, NULL))
 		return;
 	DFS_STAT_INC(sc, radar_detected);
-	ieee80211_radar_detected(sc->hw);
+	ieee80211_radar_detected(sc->hw, NULL);
 }
 
 /*
diff --git a/drivers/net/wireless/ath/ath9k/dfs_debug.c b/drivers/net/wireless/ath/ath9k/dfs_debug.c
index 8e18e9b4ef48..426caa057396 100644
--- a/drivers/net/wireless/ath/ath9k/dfs_debug.c
+++ b/drivers/net/wireless/ath/ath9k/dfs_debug.c
@@ -116,7 +116,7 @@ static ssize_t write_file_simulate_radar(struct file *file,
 {
 	struct ath_softc *sc = file->private_data;
 
-	ieee80211_radar_detected(sc->hw);
+	ieee80211_radar_detected(sc->hw, NULL);
 
 	return count;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index d50d967828be..53c8ebe179dd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -394,7 +394,7 @@ mt7615_mcu_rx_radar_detected(struct mt7615_dev *dev, struct sk_buff *skb)
 	if (mt76_phy_dfs_state(mphy) < MT_DFS_STATE_CAC)
 		return;
 
-	ieee80211_radar_detected(mphy->hw);
+	ieee80211_radar_detected(mphy->hw, NULL);
 	dev->hw_pattern++;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
index 024a5c0a5a57..7a07636d09c6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
@@ -630,7 +630,7 @@ static void mt76x02_dfs_tasklet(struct tasklet_struct *t)
 		radar_detected = mt76x02_dfs_check_detection(dev);
 		if (radar_detected) {
 			/* sw detector rx radar pattern */
-			ieee80211_radar_detected(dev->mt76.hw);
+			ieee80211_radar_detected(dev->mt76.hw, NULL);
 			mt76x02_dfs_detector_reset(dev);
 
 			return;
@@ -658,7 +658,7 @@ static void mt76x02_dfs_tasklet(struct tasklet_struct *t)
 
 		/* hw detector rx radar pattern */
 		dfs_pd->stats[i].hw_pattern++;
-		ieee80211_radar_detected(dev->mt76.hw);
+		ieee80211_radar_detected(dev->mt76.hw, NULL);
 		mt76x02_dfs_detector_reset(dev);
 
 		return;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 2185cd24e2e1..5f180851060d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -293,7 +293,7 @@ mt7915_mcu_rx_radar_detected(struct mt7915_dev *dev, struct sk_buff *skb)
 						&dev->rdd2_chandef,
 						GFP_ATOMIC);
 	else
-		ieee80211_radar_detected(mphy->hw);
+		ieee80211_radar_detected(mphy->hw, NULL);
 	dev->hw_pattern++;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 2e4fa9f48dfb..f8921546a5e6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -371,7 +371,7 @@ mt7996_mcu_rx_radar_detected(struct mt7996_dev *dev, struct sk_buff *skb)
 						&dev->rdd2_chandef,
 						GFP_ATOMIC);
 	else
-		ieee80211_radar_detected(mphy->hw);
+		ieee80211_radar_detected(mphy->hw, NULL);
 	dev->hw_pattern++;
 }
 
diff --git a/drivers/net/wireless/ti/wl18xx/event.c b/drivers/net/wireless/ti/wl18xx/event.c
index 34d95f458e1a..a9f090e15cbb 100644
--- a/drivers/net/wireless/ti/wl18xx/event.c
+++ b/drivers/net/wireless/ti/wl18xx/event.c
@@ -142,7 +142,7 @@ int wl18xx_process_mailbox_events(struct wl1271 *wl)
 			    wl18xx_radar_type_decode(mbox->radar_type));
 
 		if (!wl->radar_debug_mode)
-			ieee80211_radar_detected(wl->hw);
+			ieee80211_radar_detected(wl->hw, NULL);
 	}
 
 	if (vector & PERIODIC_SCAN_REPORT_EVENT_ID) {
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index 5fe9e4e26142..f0e528abb1b4 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -1146,7 +1146,7 @@ static int hwsim_write_simulate_radar(void *dat, u64 val)
 {
 	struct mac80211_hwsim_data *data = dat;
 
-	ieee80211_radar_detected(data->hw);
+	ieee80211_radar_detected(data->hw, NULL);
 
 	return 0;
 }
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index adfec877f392..954dff901b69 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6748,8 +6748,11 @@ void ieee80211_cqm_beacon_loss_notify(struct ieee80211_vif *vif, gfp_t gfp);
  * ieee80211_radar_detected - inform that a radar was detected
  *
  * @hw: pointer as obtained from ieee80211_alloc_hw()
+ * @chanctx_conf: Channel context on which radar is detected. Mandatory to
+ *	pass a valid pointer during MLO. For non-MLO %NULL can be passed
  */
-void ieee80211_radar_detected(struct ieee80211_hw *hw);
+void ieee80211_radar_detected(struct ieee80211_hw *hw,
+			      struct ieee80211_chanctx_conf *chanctx_conf);
 
 /**
  * ieee80211_chswitch_done - Complete channel switch process
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index b72e4036526b..cca6d14084d2 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -683,6 +683,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local,
 	ctx->mode = mode;
 	ctx->conf.radar_enabled = false;
 	ctx->conf.radio_idx = radio_idx;
+	ctx->radar_detected = false;
 	_ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false);
 
 	return ctx;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 9c2c826ef90c..4f0390918b60 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -893,6 +893,8 @@ struct ieee80211_chanctx {
 	struct ieee80211_chan_req req;
 
 	struct ieee80211_chanctx_conf conf;
+
+	bool radar_detected;
 };
 
 struct mac80211_qos_map {
@@ -2649,7 +2651,8 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local,
 bool ieee80211_is_radar_required(struct ieee80211_local *local);
 
 void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work);
-void ieee80211_dfs_cac_cancel(struct ieee80211_local *local);
+void ieee80211_dfs_cac_cancel(struct ieee80211_local *local,
+			      struct ieee80211_chanctx *chanctx);
 void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy,
 				       struct wiphy_work *work);
 int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index d823d58303e8..7be52345f218 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -32,7 +32,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 
 	ieee80211_scan_cancel(local);
 
-	ieee80211_dfs_cac_cancel(local);
+	ieee80211_dfs_cac_cancel(local, NULL);
 
 	ieee80211_roc_purge(local, NULL);
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 2e37d2639074..f94faa86ba8a 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3467,11 +3467,16 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 	return ts;
 }
 
-void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
+/* Cancel CAC for the interfaces under the specified @local. If @ctx is
+ * also provided, only the interfaces using that ctx will be canceled.
+ */
+void ieee80211_dfs_cac_cancel(struct ieee80211_local *local,
+			      struct ieee80211_chanctx *ctx)
 {
 	struct ieee80211_sub_if_data *sdata;
 	struct cfg80211_chan_def chandef;
 	struct ieee80211_link_data *link;
+	struct ieee80211_chanctx_conf *chanctx_conf;
 	unsigned int link_id;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
@@ -3484,6 +3489,11 @@ void ieee80211_dfs_cac_cancel(struct ieee80211_local *local)
 			if (!link)
 				continue;
 
+			chanctx_conf = sdata_dereference(link->conf->chanctx_conf,
+							 sdata);
+			if (ctx && &ctx->conf != chanctx_conf)
+				continue;
+
 			wiphy_delayed_work_cancel(local->hw.wiphy,
 						  &link->dfs_cac_timer_work);
 
@@ -3504,9 +3514,8 @@ void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy,
 {
 	struct ieee80211_local *local =
 		container_of(work, struct ieee80211_local, radar_detected_work);
-	struct cfg80211_chan_def chandef = local->hw.conf.chandef;
+	struct cfg80211_chan_def chandef;
 	struct ieee80211_chanctx *ctx;
-	int num_chanctx = 0;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
@@ -3514,25 +3523,46 @@ void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy,
 		if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER)
 			continue;
 
-		num_chanctx++;
+		if (!ctx->radar_detected)
+			continue;
+
+		ctx->radar_detected = false;
+
 		chandef = ctx->conf.def;
+
+		ieee80211_dfs_cac_cancel(local, ctx);
+		cfg80211_radar_event(local->hw.wiphy, &chandef, GFP_KERNEL);
 	}
+}
 
-	ieee80211_dfs_cac_cancel(local);
+static void
+ieee80211_radar_mark_chan_ctx_iterator(struct ieee80211_hw *hw,
+				       struct ieee80211_chanctx_conf *chanctx_conf,
+				       void *data)
+{
+	struct ieee80211_chanctx *ctx =
+		container_of(chanctx_conf, struct ieee80211_chanctx,
+			     conf);
 
-	if (num_chanctx > 1)
-		/* XXX: multi-channel is not supported yet */
-		WARN_ON(1);
-	else
-		cfg80211_radar_event(local->hw.wiphy, &chandef, GFP_KERNEL);
+	if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER)
+		return;
+
+	if (data && data != chanctx_conf)
+		return;
+
+	ctx->radar_detected = true;
 }
 
-void ieee80211_radar_detected(struct ieee80211_hw *hw)
+void ieee80211_radar_detected(struct ieee80211_hw *hw,
+			      struct ieee80211_chanctx_conf *chanctx_conf)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 
 	trace_api_radar_detected(local);
 
+	ieee80211_iter_chan_contexts_atomic(hw, ieee80211_radar_mark_chan_ctx_iterator,
+					    chanctx_conf);
+
 	wiphy_work_queue(hw->wiphy, &local->radar_detected_work);
 }
 EXPORT_SYMBOL(ieee80211_radar_detected);
-- 
cgit v1.3-3-g829e


From 0b3be9d1d34e21dada69c539fbf51a5fe868028a Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:53 +0200
Subject: wifi: mt76: add separate tx scheduling queue for off-channel tx

Ensure that packets are not sent out to the wrong channel

Link: https://patch.msgid.link/20240827093011.18621-6-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c |  7 ++--
 drivers/net/wireless/mediatek/mt76/mt76.h     |  1 +
 drivers/net/wireless/mediatek/mt76/tx.c       | 59 +++++++++++++++++----------
 3 files changed, 41 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index a24186c9a913..6183b021f6eb 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -941,8 +941,7 @@ int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef,
 	mutex_lock(&dev->mutex);
 	set_bit(MT76_RESET, &phy->state);
 
-	ieee80211_stop_queues(phy->hw);
-
+	mt76_worker_disable(&dev->tx_worker);
 	wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(phy), timeout);
 	mt76_update_survey(phy);
 
@@ -959,12 +958,11 @@ int mt76_set_channel(struct mt76_phy *phy, struct cfg80211_chan_def *chandef,
 
 	if (chandef->chan != phy->main_chan)
 		memset(phy->chan_state, 0, sizeof(*phy->chan_state));
+	mt76_worker_enable(&dev->tx_worker);
 
 	ret = dev->drv->set_channel(phy);
 
 	clear_bit(MT76_RESET, &phy->state);
-	ieee80211_wake_queues(phy->hw);
-
 	mt76_worker_schedule(&dev->tx_worker);
 
 	mutex_unlock(&dev->mutex);
@@ -1548,6 +1546,7 @@ void mt76_wcid_init(struct mt76_wcid *wcid)
 {
 	INIT_LIST_HEAD(&wcid->tx_list);
 	skb_queue_head_init(&wcid->tx_pending);
+	skb_queue_head_init(&wcid->tx_offchannel);
 
 	INIT_LIST_HEAD(&wcid->list);
 	idr_init(&wcid->pktid);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 6c054f43e7ce..87048aa27fbf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -361,6 +361,7 @@ struct mt76_wcid {
 
 	struct list_head tx_list;
 	struct sk_buff_head tx_pending;
+	struct sk_buff_head tx_offchannel;
 
 	struct list_head list;
 	struct idr pktid;
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 5cf6edee4d13..34d93f08f415 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -330,6 +330,7 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 	struct mt76_wcid *wcid, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct sk_buff_head *head;
 
 	if (mt76_testmode_enabled(phy)) {
 		ieee80211_free_txskb(phy->hw, skb);
@@ -345,9 +346,15 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta,
 
 	info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->band_idx);
 
-	spin_lock_bh(&wcid->tx_pending.lock);
-	__skb_queue_tail(&wcid->tx_pending, skb);
-	spin_unlock_bh(&wcid->tx_pending.lock);
+	if ((info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) ||
+	    (info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK))
+		head = &wcid->tx_offchannel;
+	else
+		head = &wcid->tx_pending;
+
+	spin_lock_bh(&head->lock);
+	__skb_queue_tail(head, skb);
+	spin_unlock_bh(&head->lock);
 
 	spin_lock_bh(&phy->tx_lock);
 	if (list_empty(&wcid->tx_list))
@@ -478,7 +485,7 @@ mt76_txq_send_burst(struct mt76_phy *phy, struct mt76_queue *q,
 		return idx;
 
 	do {
-		if (test_bit(MT76_RESET, &phy->state))
+		if (test_bit(MT76_RESET, &phy->state) || phy->offchannel)
 			return -EBUSY;
 
 		if (stop || mt76_txq_stopped(q))
@@ -522,7 +529,7 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid)
 	while (1) {
 		int n_frames = 0;
 
-		if (test_bit(MT76_RESET, &phy->state))
+		if (test_bit(MT76_RESET, &phy->state) || phy->offchannel)
 			return -EBUSY;
 
 		if (dev->queue_ops->tx_cleanup &&
@@ -568,7 +575,7 @@ void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid)
 {
 	int len;
 
-	if (qid >= 4)
+	if (qid >= 4 || phy->offchannel)
 		return;
 
 	local_bh_disable();
@@ -586,7 +593,8 @@ void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid)
 EXPORT_SYMBOL_GPL(mt76_txq_schedule);
 
 static int
-mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid)
+mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid,
+			       struct sk_buff_head *head)
 {
 	struct mt76_dev *dev = phy->dev;
 	struct ieee80211_sta *sta;
@@ -594,8 +602,8 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid)
 	struct sk_buff *skb;
 	int ret = 0;
 
-	spin_lock(&wcid->tx_pending.lock);
-	while ((skb = skb_peek(&wcid->tx_pending)) != NULL) {
+	spin_lock(&head->lock);
+	while ((skb = skb_peek(head)) != NULL) {
 		struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 		int qid = skb_get_queue_mapping(skb);
@@ -607,13 +615,13 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid)
 			qid = MT_TXQ_PSD;
 
 		q = phy->q_tx[qid];
-		if (mt76_txq_stopped(q)) {
+		if (mt76_txq_stopped(q) || test_bit(MT76_RESET, &phy->state)) {
 			ret = -1;
 			break;
 		}
 
-		__skb_unlink(skb, &wcid->tx_pending);
-		spin_unlock(&wcid->tx_pending.lock);
+		__skb_unlink(skb, head);
+		spin_unlock(&head->lock);
 
 		sta = wcid_to_sta(wcid);
 		spin_lock(&q->lock);
@@ -621,15 +629,17 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid)
 		dev->queue_ops->kick(dev, q);
 		spin_unlock(&q->lock);
 
-		spin_lock(&wcid->tx_pending.lock);
+		spin_lock(&head->lock);
 	}
-	spin_unlock(&wcid->tx_pending.lock);
+	spin_unlock(&head->lock);
 
 	return ret;
 }
 
 static void mt76_txq_schedule_pending(struct mt76_phy *phy)
 {
+	LIST_HEAD(tx_list);
+
 	if (list_empty(&phy->tx_list))
 		return;
 
@@ -637,22 +647,27 @@ static void mt76_txq_schedule_pending(struct mt76_phy *phy)
 	rcu_read_lock();
 
 	spin_lock(&phy->tx_lock);
-	while (!list_empty(&phy->tx_list)) {
-		struct mt76_wcid *wcid = NULL;
+	list_splice_init(&phy->tx_list, &tx_list);
+	while (!list_empty(&tx_list)) {
+		struct mt76_wcid *wcid;
 		int ret;
 
-		wcid = list_first_entry(&phy->tx_list, struct mt76_wcid, tx_list);
+		wcid = list_first_entry(&tx_list, struct mt76_wcid, tx_list);
 		list_del_init(&wcid->tx_list);
 
 		spin_unlock(&phy->tx_lock);
-		ret = mt76_txq_schedule_pending_wcid(phy, wcid);
+		ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_offchannel);
+		if (ret >= 0 && !phy->offchannel)
+			ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_pending);
 		spin_lock(&phy->tx_lock);
 
-		if (ret) {
-			if (list_empty(&wcid->tx_list))
-				list_add_tail(&wcid->tx_list, &phy->tx_list);
+		if (!skb_queue_empty(&wcid->tx_pending) &&
+		    !skb_queue_empty(&wcid->tx_offchannel) &&
+		    list_empty(&wcid->tx_list))
+			list_add_tail(&wcid->tx_list, &phy->tx_list);
+
+		if (ret < 0)
 			break;
-		}
 	}
 	spin_unlock(&phy->tx_lock);
 
-- 
cgit v1.3-3-g829e


From 256cbd26fbafb30ba3314339106e5c594e9bd5f9 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:54 +0200
Subject: wifi: mt76: mt7915: disable tx worker during tx BA session
 enable/disable

Avoids firmware race condition.

Link: https://patch.msgid.link/20240827093011.18621-7-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index b2cad75eafb9..43f1a45b34ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -690,13 +690,17 @@ int mt7915_mcu_add_tx_ba(struct mt7915_dev *dev,
 {
 	struct mt7915_sta *msta = (struct mt7915_sta *)params->sta->drv_priv;
 	struct mt7915_vif *mvif = msta->vif;
+	int ret;
 
+	mt76_worker_disable(&dev->mt76.tx_worker);
 	if (enable && !params->amsdu)
 		msta->wcid.amsdu = false;
+	ret = mt76_connac_mcu_sta_ba(&dev->mt76, &mvif->mt76, params,
+				     MCU_EXT_CMD(STA_REC_UPDATE),
+				     enable, true);
+	mt76_worker_enable(&dev->mt76.tx_worker);
 
-	return mt76_connac_mcu_sta_ba(&dev->mt76, &mvif->mt76, params,
-				      MCU_EXT_CMD(STA_REC_UPDATE),
-				      enable, true);
+	return ret;
 }
 
 int mt7915_mcu_add_rx_ba(struct mt7915_dev *dev,
-- 
cgit v1.3-3-g829e


From f3049b88b2b32326df97461813ae73e8bbc296fc Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:55 +0200
Subject: wifi: mt76: mt7915: allocate vif wcid in the same range as stations

Reduces the amount of unnecessary WTBL bank switching, while still reserving
WTBL entries for vifs.

Link: https://patch.msgid.link/20240827093011.18621-8-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 87a7b1589af2..a89674d6b602 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -245,7 +245,9 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	dev->mt76.vif_mask |= BIT_ULL(mvif->mt76.idx);
 	phy->omac_mask |= BIT_ULL(mvif->mt76.omac_idx);
 
-	idx = MT7915_WTBL_RESERVED - mvif->mt76.idx;
+	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, mt7915_wtbl_size(dev));
+	if (idx < 0)
+		return -ENOSPC;
 
 	INIT_LIST_HEAD(&mvif->sta.rc_list);
 	INIT_LIST_HEAD(&mvif->sta.wcid.poll_list);
@@ -292,6 +294,7 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw,
 
 	mt7915_mcu_add_bss_info(phy, vif, false);
 	mt7915_mcu_add_sta(dev, vif, NULL, false);
+	mt76_wcid_mask_clear(dev->mt76.wcid_mask, mvif->sta.wcid.idx);
 
 	mutex_lock(&dev->mt76.mutex);
 	mt76_testmode_reset(phy->mt76, true);
-- 
cgit v1.3-3-g829e


From dfaf079a1aa0cf92d119a5322b45c6d45e636591 Mon Sep 17 00:00:00 2001
From: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Date: Tue, 27 Aug 2024 11:29:56 +0200
Subject: wifi: mt76: connac: add support for IEEE 802.11 fragmentation

Add fragmentation index into TXD.DW2 to support IEEE 802.11 fragmentation.

Signed-off-by: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Link: https://patch.msgid.link/20240827093011.18621-9-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h |  7 +++++++
 drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c  | 10 +++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h
index 5f132115ebfc..eb4765365b8c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac2_mac.h
@@ -355,4 +355,11 @@ enum tx_port_idx {
 	MT_TX_PORT_IDX_MCU
 };
 
+enum tx_frag_idx {
+	MT_TX_FRAG_NONE,
+	MT_TX_FRAG_FIRST,
+	MT_TX_FRAG_MID,
+	MT_TX_FRAG_LAST
+};
+
 #endif /* __MT76_CONNAC2_MAC_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index b841bf628d02..a3db65254e37 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -391,6 +391,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	bool multicast = is_multicast_ether_addr(hdr->addr1);
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	__le16 fc = hdr->frame_control;
+	__le16 sc = hdr->seq_ctrl;
 	u8 fc_type, fc_stype;
 	u32 val;
 
@@ -432,6 +433,13 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	    info->flags & IEEE80211_TX_CTL_USE_MINRATE)
 		val |= MT_TXD2_FIX_RATE;
 
+	if (ieee80211_has_morefrags(fc) && ieee80211_is_first_frag(sc))
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_FIRST);
+	else if (ieee80211_has_morefrags(fc) && !ieee80211_is_first_frag(sc))
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_MID);
+	else if (!ieee80211_has_morefrags(fc) && !ieee80211_is_first_frag(sc))
+		val |= FIELD_PREP(MT_TXD2_FRAG, MT_TX_FRAG_LAST);
+
 	txwi[2] |= cpu_to_le32(val);
 
 	if (ieee80211_is_beacon(fc)) {
@@ -440,7 +448,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	}
 
 	if (info->flags & IEEE80211_TX_CTL_INJECTED) {
-		u16 seqno = le16_to_cpu(hdr->seq_ctrl);
+		u16 seqno = le16_to_cpu(sc);
 
 		if (ieee80211_is_back_req(hdr->frame_control)) {
 			struct ieee80211_bar *bar;
-- 
cgit v1.3-3-g829e


From 8a977b3f9624e8e91d8fe54cbe4e59d41d41d0f1 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:57 +0200
Subject: wifi: mt76: connac: add support for passing connection state directly

Preparation for improvements to sta handling. No functional changes.

Link: https://patch.msgid.link/20240827093011.18621-10-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7615/mcu.c      |  4 +++-
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 17 ++++++++---------
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c      |  4 +++-
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c      |  5 ++++-
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c      |  4 +++-
 6 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index 3b57d967190a..f6eb9939c3e2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -847,6 +847,7 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif,
 	struct wtbl_req_hdr *wtbl_hdr;
 	struct mt7615_sta *msta;
 	bool new_entry = true;
+	int conn_state;
 	int cmd, err;
 
 	msta = sta ? (struct mt7615_sta *)sta->drv_priv : &mvif->sta;
@@ -863,8 +864,9 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif,
 		else
 			mvif->sta_added = true;
 	}
+	conn_state = enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT;
 	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, sskb, vif, link_sta,
-				      enable, new_entry);
+				      conn_state, new_entry);
 	if (enable && sta)
 		mt76_connac_mcu_sta_tlv(phy->mt76, sskb, sta, vif, 0,
 					MT76_STA_INFO_STATE_ASSOC);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 4dce03ddbfa4..7afb9ac30ab9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -371,7 +371,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_bss_omac_tlv);
 void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_link_sta *link_sta,
-				   bool enable, bool newly)
+				   int conn_state, bool newly)
 {
 	struct sta_rec_basic *basic;
 	struct tlv *tlv;
@@ -382,13 +382,9 @@ void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb,
 	basic = (struct sta_rec_basic *)tlv;
 	basic->extra_info = cpu_to_le16(EXTRA_INFO_VER);
 
-	if (enable) {
-		if (newly)
-			basic->extra_info |= cpu_to_le16(EXTRA_INFO_NEW);
-		basic->conn_state = CONN_STATE_PORT_SECURE;
-	} else {
-		basic->conn_state = CONN_STATE_DISCONNECT;
-	}
+	if (newly && conn_state != CONN_STATE_DISCONNECT)
+		basic->extra_info |= cpu_to_le16(EXTRA_INFO_NEW);
+	basic->conn_state = conn_state;
 
 	if (!link_sta) {
 		basic->conn_type = cpu_to_le32(CONNECTION_INFRA_BC);
@@ -1051,15 +1047,18 @@ int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy,
 	struct wtbl_req_hdr *wtbl_hdr;
 	struct tlv *sta_wtbl;
 	struct sk_buff *skb;
+	int conn_state;
 
 	skb = mt76_connac_mcu_alloc_sta_req(dev, mvif, info->wcid);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
+	conn_state = info->enable ? CONN_STATE_PORT_SECURE :
+				    CONN_STATE_DISCONNECT;
 	link_sta = info->sta ? &info->sta->deflink : NULL;
 	if (info->sta || !info->offload_fw)
 		mt76_connac_mcu_sta_basic_tlv(dev, skb, info->vif,
-					      link_sta, info->enable,
+					      link_sta, conn_state,
 					      info->newly);
 	if (info->sta && info->enable)
 		mt76_connac_mcu_sta_tlv(phy, skb, info->sta,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 4242d436de26..e04ae7eddb01 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -1898,7 +1898,7 @@ int mt76_connac_mcu_set_vif_ps(struct mt76_dev *dev, struct ieee80211_vif *vif);
 void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_link_sta *link_sta,
-				   bool enable, bool newly);
+				   int state, bool newly);
 void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, struct sk_buff *skb,
 				      struct ieee80211_vif *vif,
 				      struct ieee80211_sta *sta, void *sta_wtbl,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 43f1a45b34ab..10de8b994e2e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -1663,6 +1663,7 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 	struct ieee80211_link_sta *link_sta;
 	struct mt7915_sta *msta;
 	struct sk_buff *skb;
+	int conn_state;
 	int ret;
 
 	msta = sta ? (struct mt7915_sta *)sta->drv_priv : &mvif->sta;
@@ -1674,7 +1675,8 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 		return PTR_ERR(skb);
 
 	/* starec basic */
-	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta, enable,
+	conn_state = enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT;
+	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta, conn_state,
 				      !rcu_access_pointer(dev->mt76.wcid[msta->wcid.idx]));
 	if (!enable)
 		goto out;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 9dc22fbe25d3..473ed54e8710 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -1770,16 +1770,19 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy,
 	struct mt76_vif *mvif = (struct mt76_vif *)info->vif->drv_priv;
 	struct mt76_dev *dev = phy->dev;
 	struct sk_buff *skb;
+	int conn_state;
 
 	skb = __mt76_connac_mcu_alloc_sta_req(dev, mvif, info->wcid,
 					      MT7925_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
+	conn_state = info->enable ? CONN_STATE_PORT_SECURE :
+				    CONN_STATE_DISCONNECT;
 	if (info->link_sta)
 		mt76_connac_mcu_sta_basic_tlv(dev, skb, info->vif,
 					      info->link_sta,
-					      info->enable, info->newly);
+					      conn_state, info->newly);
 	if (info->link_sta && info->enable) {
 		mt7925_mcu_sta_phy_tlv(skb, info->vif, info->link_sta);
 		mt7925_mcu_sta_ht_tlv(skb, info->link_sta);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index a1a0df43e1cd..caa0ff619475 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2163,6 +2163,7 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	struct ieee80211_link_sta *link_sta;
 	struct mt7996_sta *msta;
 	struct sk_buff *skb;
+	int conn_state;
 	int ret;
 
 	msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->sta;
@@ -2175,8 +2176,9 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		return PTR_ERR(skb);
 
 	/* starec basic */
+	conn_state = enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT;
 	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta,
-				      enable, newly);
+				      conn_state, newly);
 
 	if (!enable)
 		goto out;
-- 
cgit v1.3-3-g829e


From 17b0f68a72ae1a13e53135418d5ae5322f220294 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:58 +0200
Subject: wifi: mt76: change .sta_assoc callback to .sta_event

Also report auth/disassoc events, in order to give the driver more control over
handling the station state.

Link: https://patch.msgid.link/20240827093011.18621-11-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c      | 23 ++++++++++++++++------
 drivers/net/wireless/mediatek/mt76/mt76.h          | 10 ++++++++--
 drivers/net/wireless/mediatek/mt76/mt7603/init.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7603/main.c   | 14 +++++++++----
 drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt7921/main.c   | 11 ++++++++---
 drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt7921/pci.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/sdio.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7921/usb.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7925/main.c   | 21 +++++++++++---------
 drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt7925/pci.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7925/usb.c    |  2 +-
 14 files changed, 67 insertions(+), 36 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 6183b021f6eb..9d5561f44134 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1509,21 +1509,32 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt76_phy *phy = hw->priv;
 	struct mt76_dev *dev = phy->dev;
+	enum mt76_sta_event ev;
 
 	if (old_state == IEEE80211_STA_NOTEXIST &&
 	    new_state == IEEE80211_STA_NONE)
 		return mt76_sta_add(phy, vif, sta);
 
-	if (old_state == IEEE80211_STA_AUTH &&
-	    new_state == IEEE80211_STA_ASSOC &&
-	    dev->drv->sta_assoc)
-		dev->drv->sta_assoc(dev, vif, sta);
-
 	if (old_state == IEEE80211_STA_NONE &&
 	    new_state == IEEE80211_STA_NOTEXIST)
 		mt76_sta_remove(dev, vif, sta);
 
-	return 0;
+	if (!dev->drv->sta_event)
+		return 0;
+
+	if (old_state == IEEE80211_STA_AUTH &&
+	    new_state == IEEE80211_STA_ASSOC)
+		ev = MT76_STA_EVENT_ASSOC;
+	else if (old_state == IEEE80211_STA_ASSOC &&
+		 new_state == IEEE80211_STA_AUTHORIZED)
+		ev = MT76_STA_EVENT_AUTHORIZE;
+	else if (old_state == IEEE80211_STA_ASSOC &&
+		 new_state == IEEE80211_STA_AUTH)
+		ev = MT76_STA_EVENT_DISASSOC;
+	else
+		return 0;
+
+	return dev->drv->sta_event(dev, vif, sta, ev);
 }
 EXPORT_SYMBOL_GPL(mt76_sta_state);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 87048aa27fbf..f1cd9dc86b42 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -467,6 +467,12 @@ enum {
 	MT76_STATE_WED_RESET,
 };
 
+enum mt76_sta_event {
+	MT76_STA_EVENT_ASSOC,
+	MT76_STA_EVENT_AUTHORIZE,
+	MT76_STA_EVENT_DISASSOC,
+};
+
 struct mt76_hw_cap {
 	bool has_2ghz;
 	bool has_5ghz;
@@ -513,8 +519,8 @@ struct mt76_driver_ops {
 	int (*sta_add)(struct mt76_dev *dev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 
-	void (*sta_assoc)(struct mt76_dev *dev, struct ieee80211_vif *vif,
-			  struct ieee80211_sta *sta);
+	int (*sta_event)(struct mt76_dev *dev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev);
 
 	void (*sta_remove)(struct mt76_dev *dev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
index 1528a8be7762..86617a3e4328 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
@@ -15,7 +15,7 @@ const struct mt76_driver_ops mt7603_drv_ops = {
 	.rx_poll_complete = mt7603_rx_poll_complete,
 	.sta_ps = mt7603_sta_ps,
 	.sta_add = mt7603_sta_add,
-	.sta_assoc = mt7603_sta_assoc,
+	.sta_event = mt7603_sta_event,
 	.sta_remove = mt7603_sta_remove,
 	.update_survey = mt7603_update_channel,
 	.set_channel = mt7603_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index 3d3a4cc2bab1..574f74ad325d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -355,13 +355,19 @@ mt7603_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	return ret;
 }
 
-void
-mt7603_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-		 struct ieee80211_sta *sta)
+int
+mt7603_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+		 struct ieee80211_sta *sta, enum mt76_sta_event ev)
 {
 	struct mt7603_dev *dev = container_of(mdev, struct mt7603_dev, mt76);
 
-	mt7603_wtbl_update_cap(dev, sta);
+	if (ev == MT76_STA_EVENT_ASSOC) {
+		mutex_lock(&dev->mt76.mutex);
+		mt7603_wtbl_update_cap(dev, sta);
+		mutex_unlock(&dev->mt76.mutex);
+	}
+
+	return 0;
 }
 
 void
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index dbdfe596f29e..55a034ccbacd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -246,8 +246,8 @@ void mt7603_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q);
 void mt7603_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps);
 int mt7603_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		   struct ieee80211_sta *sta);
-void mt7603_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-		      struct ieee80211_sta *sta);
+int mt7603_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+		     struct ieee80211_sta *sta, enum mt76_sta_event ev);
 void mt7603_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index ffb2b68ddd51..a7f5bfbc02ed 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -822,13 +822,16 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 }
 EXPORT_SYMBOL_GPL(mt7921_mac_sta_add);
 
-void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			  struct ieee80211_sta *sta)
+int mt7921_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev)
 {
 	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 
+	if (ev != MT76_STA_EVENT_ASSOC)
+	    return 0;
+
 	mt792x_mutex_acquire(dev);
 
 	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls)
@@ -844,8 +847,10 @@ void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	mt7921_mcu_sta_update(dev, sta, vif, true, MT76_STA_INFO_STATE_ASSOC);
 
 	mt792x_mutex_release(dev);
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(mt7921_mac_sta_assoc);
+EXPORT_SYMBOL_GPL(mt7921_mac_sta_event);
 
 void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
index 0b4f4c8d8858..16c89815c0b8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h
@@ -245,8 +245,8 @@ int mt7921_mac_init(struct mt792x_dev *dev);
 bool mt7921_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
 int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
-void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			  struct ieee80211_sta *sta);
+int mt7921_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev);
 void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 void mt7921_mac_reset_work(struct work_struct *work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
index bb8cfff78dc5..67723c22aea6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c
@@ -244,7 +244,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev,
 		.rx_skb = mt7921_queue_rx_skb,
 		.rx_poll_complete = mt792x_rx_poll_complete,
 		.sta_add = mt7921_mac_sta_add,
-		.sta_assoc = mt7921_mac_sta_assoc,
+		.sta_event = mt7921_mac_sta_event,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
 		.set_channel = mt7921_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
index 2ef502d0ce9a..95f526f7bb99 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/sdio.c
@@ -100,7 +100,7 @@ static int mt7921s_probe(struct sdio_func *func,
 		.rx_skb = mt7921_queue_rx_skb,
 		.rx_check = mt7921_rx_check,
 		.sta_add = mt7921_mac_sta_add,
-		.sta_assoc = mt7921_mac_sta_assoc,
+		.sta_event = mt7921_mac_sta_event,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
 		.set_channel = mt7921_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
index 3b5e52db4a13..8aa4f0203208 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/usb.c
@@ -151,7 +151,7 @@ static int mt7921u_probe(struct usb_interface *usb_intf,
 		.rx_skb = mt7921_queue_rx_skb,
 		.rx_check = mt7921_rx_check,
 		.sta_add = mt7921_mac_sta_add,
-		.sta_assoc = mt7921_mac_sta_assoc,
+		.sta_event = mt7921_mac_sta_event,
 		.sta_remove = mt7921_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
 		.set_channel = mt7921_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 8c0768bf9343..38a301533297 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1078,23 +1078,26 @@ static void mt7925_mac_link_sta_assoc(struct mt76_dev *mdev,
 	mt792x_mutex_release(dev);
 }
 
-void mt7925_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			  struct ieee80211_sta *sta)
+int mt7925_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev)
 {
+	struct ieee80211_link_sta *link_sta = &sta->deflink;
+
+	if (ev != MT76_STA_EVENT_ASSOC)
+		return 0;
+
 	if (ieee80211_vif_is_mld(vif)) {
 		struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-		struct ieee80211_link_sta *link_sta;
 
 		link_sta = mt792x_sta_to_link_sta(vif, sta, msta->deflink_id);
-
 		mt7925_mac_set_links(mdev, vif);
-
-		mt7925_mac_link_sta_assoc(mdev, vif, link_sta);
-	} else {
-		mt7925_mac_link_sta_assoc(mdev, vif, &sta->deflink);
 	}
+
+	mt7925_mac_link_sta_assoc(mdev, vif, link_sta);
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(mt7925_mac_sta_assoc);
+EXPORT_SYMBOL_GPL(mt7925_mac_sta_event);
 
 static void mt7925_mac_link_sta_remove(struct mt76_dev *mdev,
 				       struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index 669f3a079d04..e80824a10b2c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -219,8 +219,8 @@ int mt7925_mac_init(struct mt792x_dev *dev);
 int mt7925_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
 bool mt7925_mac_wtbl_update(struct mt792x_dev *dev, int idx, u32 mask);
-void mt7925_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			  struct ieee80211_sta *sta);
+int mt7925_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev);
 void mt7925_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 void mt7925_mac_reset_work(struct work_struct *work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index 6e4f4e78c350..cb25eb50a45b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -279,7 +279,7 @@ static int mt7925_pci_probe(struct pci_dev *pdev,
 		.rx_skb = mt7925_queue_rx_skb,
 		.rx_poll_complete = mt792x_rx_poll_complete,
 		.sta_add = mt7925_mac_sta_add,
-		.sta_assoc = mt7925_mac_sta_assoc,
+		.sta_event = mt7925_mac_sta_event,
 		.sta_remove = mt7925_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
 	};
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
index 1e0f094fc905..682db1bab21c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/usb.c
@@ -142,7 +142,7 @@ static int mt7925u_probe(struct usb_interface *usb_intf,
 		.rx_skb = mt7925_queue_rx_skb,
 		.rx_check = mt7925_rx_check,
 		.sta_add = mt7925_mac_sta_add,
-		.sta_assoc = mt7925_mac_sta_assoc,
+		.sta_event = mt7925_mac_sta_event,
 		.sta_remove = mt7925_mac_sta_remove,
 		.update_survey = mt792x_update_channel,
 	};
-- 
cgit v1.3-3-g829e


From 33eb14f1029085bb32e745c6d7a69b06eb3caec4 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:29:59 +0200
Subject: wifi: mt76: mt7915: use mac80211 .sta_state op

Allows adding stations before assoc, though they are not passed to the
firmware yet at that point.

Link: https://patch.msgid.link/20240827093011.18621-12-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h          |   1 +
 .../net/wireless/mediatek/mt76/mt76_connac_mcu.c   |   2 +-
 drivers/net/wireless/mediatek/mt76/mt7915/main.c   | 105 +++++++++++++--------
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c    |  26 ++---
 drivers/net/wireless/mediatek/mt76/mt7915/mmio.c   |   1 +
 drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h |   4 +-
 .../net/wireless/mediatek/mt76/mt7915/testmode.c   |   4 +-
 drivers/net/wireless/mediatek/mt76/tx.c            |   3 +
 8 files changed, 90 insertions(+), 56 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index f1cd9dc86b42..43e743b510ba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -347,6 +347,7 @@ struct mt76_wcid {
 	u8 hw_key_idx2;
 
 	u8 sta:1;
+	u8 sta_disabled:1;
 	u8 amsdu:1;
 	u8 phy_idx:2;
 	u8 link_id:4;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 7afb9ac30ab9..3a575cebe4a9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -283,7 +283,7 @@ __mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif *mvif,
 	};
 	struct sk_buff *skb;
 
-	if (wcid && !wcid->sta)
+	if (wcid && !wcid->sta && !wcid->sta_disabled)
 		hdr.muar_idx = 0xe;
 
 	mt76_connac_mcu_get_wlan_idx(dev, wcid, &hdr.wlan_idx_lo,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index a89674d6b602..9bf308429db3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -274,7 +274,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw,
 	memset(&mvif->cap, -1, sizeof(mvif->cap));
 
 	mt7915_mcu_add_bss_info(phy, vif, true);
-	mt7915_mcu_add_sta(dev, vif, NULL, true);
+	mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_PORT_SECURE, true);
 	rcu_assign_pointer(dev->mt76.wcid[idx], &mvif->sta.wcid);
 
 out:
@@ -293,7 +293,7 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw,
 	int idx = msta->wcid.idx;
 
 	mt7915_mcu_add_bss_info(phy, vif, false);
-	mt7915_mcu_add_sta(dev, vif, NULL, false);
+	mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_DISCONNECT, false);
 	mt76_wcid_mask_clear(dev->mt76.wcid_mask, mvif->sta.wcid.idx);
 
 	mutex_lock(&dev->mt76.mutex);
@@ -366,6 +366,9 @@ static int mt7915_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	int idx = key->keyidx;
 	int err = 0;
 
+	if (sta && !wcid->sta)
+		return -EOPNOTSUPP;
+
 	/* The hardware does not support per-STA RX GTK, fallback
 	 * to software mode for these.
 	 */
@@ -623,7 +626,7 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 	if (set_bss_info == 1)
 		mt7915_mcu_add_bss_info(phy, vif, true);
 	if (set_sta == 1)
-		mt7915_mcu_add_sta(dev, vif, NULL, true);
+		mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_PORT_SECURE, false);
 
 	if (changed & BSS_CHANGED_ERP_CTS_PROT)
 		mt7915_mac_enable_rtscts(dev, vif, info->use_cts_prot);
@@ -658,7 +661,7 @@ static void mt7915_bss_info_changed(struct ieee80211_hw *hw,
 	if (set_bss_info == 0)
 		mt7915_mcu_add_bss_info(phy, vif, false);
 	if (set_sta == 0)
-		mt7915_mcu_add_sta(dev, vif, NULL, false);
+		mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_DISCONNECT, false);
 
 	mutex_unlock(&dev->mt76.mutex);
 }
@@ -696,7 +699,7 @@ mt7915_start_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	err = mt7915_mcu_add_bss_info(phy, vif, true);
 	if (err)
 		goto out;
-	err = mt7915_mcu_add_sta(dev, vif, NULL, true);
+	err = mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_PORT_SECURE, false);
 out:
 	mutex_unlock(&dev->mt76.mutex);
 
@@ -710,7 +713,7 @@ mt7915_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct mt7915_dev *dev = mt7915_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
-	mt7915_mcu_add_sta(dev, vif, NULL, false);
+	mt7915_mcu_add_sta(dev, vif, NULL, CONN_STATE_DISCONNECT, false);
 	mutex_unlock(&dev->mt76.mutex);
 }
 
@@ -733,8 +736,7 @@ int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
 	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
 	bool ext_phy = mvif->phy != &dev->phy;
-	int ret, idx;
-	u32 addr;
+	int idx;
 
 	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7915_WTBL_STA);
 	if (idx < 0)
@@ -743,25 +745,61 @@ int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	INIT_LIST_HEAD(&msta->rc_list);
 	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	msta->vif = mvif;
-	msta->wcid.sta = 1;
+	msta->wcid.sta_disabled = 1;
 	msta->wcid.idx = idx;
 	msta->wcid.phy_idx = ext_phy;
-	msta->wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	msta->jiffies = jiffies;
 
 	ewma_avg_signal_init(&msta->avg_ack_signal);
 
 	mt7915_mac_wtbl_update(dev, idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
+	mt7915_mcu_add_sta(dev, vif, sta, CONN_STATE_DISCONNECT, true);
 
-	ret = mt7915_mcu_add_sta(dev, vif, sta, true);
-	if (ret)
-		return ret;
+	return 0;
+}
+
+int mt7915_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev)
+{
+	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
+	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
+	int i, ret;
+	u32 addr;
+
+	switch (ev) {
+	case MT76_STA_EVENT_ASSOC:
+		ret = mt7915_mcu_add_sta(dev, vif, sta, CONN_STATE_CONNECT, true);
+		if (ret)
+			return ret;
+
+		addr = mt7915_mac_wtbl_lmac_addr(dev, msta->wcid.idx, 30);
+		mt76_rmw_field(dev, addr, GENMASK(7, 0), 0xa0);
+
+		ret = mt7915_mcu_add_rate_ctrl(dev, vif, sta, false);
+		if (ret)
+			return ret;
+
+		msta->wcid.tx_info |= MT_WCID_TX_INFO_SET;
+		msta->wcid.sta = 1;
+		msta->wcid.sta_disabled = 0;
+
+		return 0;
+
+	case MT76_STA_EVENT_AUTHORIZE:
+		return mt7915_mcu_add_sta(dev, vif, sta, CONN_STATE_PORT_SECURE, false);
 
-	addr = mt7915_mac_wtbl_lmac_addr(dev, msta->wcid.idx, 30);
-	mt76_rmw_field(dev, addr, GENMASK(7, 0), 0xa0);
+	case MT76_STA_EVENT_DISASSOC:
+		for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++)
+			mt7915_mac_twt_teardown_flow(dev, msta, i);
 
-	return mt7915_mcu_add_rate_ctrl(dev, vif, sta, false);
+		mt7915_mcu_add_sta(dev, vif, sta, CONN_STATE_DISCONNECT, false);
+		msta->wcid.sta_disabled = 1;
+		msta->wcid.sta = 0;
+		return 0;
+	}
+
+	return 0;
 }
 
 void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
@@ -769,16 +807,10 @@ void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
 	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
-	int i;
-
-	mt7915_mcu_add_sta(dev, vif, sta, false);
 
 	mt7915_mac_wtbl_update(dev, msta->wcid.idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
 
-	for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++)
-		mt7915_mac_twt_teardown_flow(dev, msta, i);
-
 	spin_lock_bh(&mdev->sta_poll_lock);
 	if (!list_empty(&msta->wcid.poll_list))
 		list_del_init(&msta->wcid.poll_list);
@@ -885,22 +917,6 @@ mt7915_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	return ret;
 }
 
-static int
-mt7915_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-	       struct ieee80211_sta *sta)
-{
-	return mt76_sta_state(hw, vif, sta, IEEE80211_STA_NOTEXIST,
-			      IEEE80211_STA_NONE);
-}
-
-static int
-mt7915_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		  struct ieee80211_sta *sta)
-{
-	return mt76_sta_state(hw, vif, sta, IEEE80211_STA_NONE,
-			      IEEE80211_STA_NOTEXIST);
-}
-
 static int
 mt7915_get_stats(struct ieee80211_hw *hw,
 		 struct ieee80211_low_level_stats *stats)
@@ -1154,6 +1170,10 @@ static void mt7915_sta_rc_update(struct ieee80211_hw *hw,
 {
 	struct mt7915_phy *phy = mt7915_hw_phy(hw);
 	struct mt7915_dev *dev = phy->dev;
+	struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv;
+
+	if (!msta->wcid.sta)
+		return;
 
 	mt7915_sta_rc_work(&changed, sta);
 	ieee80211_queue_work(hw, &dev->rc_work);
@@ -1197,6 +1217,9 @@ static void mt7915_sta_set_4addr(struct ieee80211_hw *hw,
 	else
 		clear_bit(MT_WCID_FLAG_4ADDR, &msta->wcid.flags);
 
+	if (!msta->wcid.sta)
+		return;
+
 	mt76_connac_mcu_wtbl_update_hdr_trans(&dev->mt76, vif, sta);
 }
 
@@ -1213,6 +1236,9 @@ static void mt7915_sta_set_decap_offload(struct ieee80211_hw *hw,
 	else
 		clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags);
 
+	if (!msta->wcid.sta)
+		return;
+
 	mt76_connac_mcu_wtbl_update_hdr_trans(&dev->mt76, vif, sta);
 }
 
@@ -1666,8 +1692,7 @@ const struct ieee80211_ops mt7915_ops = {
 	.bss_info_changed = mt7915_bss_info_changed,
 	.start_ap = mt7915_start_ap,
 	.stop_ap = mt7915_stop_ap,
-	.sta_add = mt7915_sta_add,
-	.sta_remove = mt7915_sta_remove,
+	.sta_state = mt76_sta_state,
 	.sta_pre_rcu_remove = mt76_sta_pre_rcu_remove,
 	.sta_rc_update = mt7915_sta_rc_update,
 	.set_key = mt7915_set_key,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 10de8b994e2e..2ef8d90132dd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -1657,13 +1657,12 @@ mt7915_mcu_add_group(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 }
 
 int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
-		       struct ieee80211_sta *sta, bool enable)
+		       struct ieee80211_sta *sta, int conn_state, bool newly)
 {
 	struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv;
 	struct ieee80211_link_sta *link_sta;
 	struct mt7915_sta *msta;
 	struct sk_buff *skb;
-	int conn_state;
 	int ret;
 
 	msta = sta ? (struct mt7915_sta *)sta->drv_priv : &mvif->sta;
@@ -1675,14 +1674,10 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 		return PTR_ERR(skb);
 
 	/* starec basic */
-	conn_state = enable ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT;
-	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta, conn_state,
-				      !rcu_access_pointer(dev->mt76.wcid[msta->wcid.idx]));
-	if (!enable)
-		goto out;
-
+	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, vif, link_sta,
+				      conn_state, newly);
 	/* tag order is in accordance with firmware dependency. */
-	if (sta) {
+	if (sta && conn_state != CONN_STATE_DISCONNECT) {
 		/* starec bfer */
 		mt7915_mcu_sta_bfer_tlv(dev, skb, vif, sta);
 		/* starec ht */
@@ -1693,12 +1688,17 @@ int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
 		mt76_connac_mcu_sta_uapsd(skb, vif, sta);
 	}
 
-	ret = mt7915_mcu_sta_wtbl_tlv(dev, skb, vif, sta);
-	if (ret) {
-		dev_kfree_skb(skb);
-		return ret;
+	if (newly || conn_state != CONN_STATE_DISCONNECT) {
+		ret = mt7915_mcu_sta_wtbl_tlv(dev, skb, vif, sta);
+		if (ret) {
+			dev_kfree_skb(skb);
+			return ret;
+		}
 	}
 
+	if (conn_state == CONN_STATE_DISCONNECT)
+		goto out;
+
 	if (sta) {
 		/* starec amsdu */
 		mt7915_mcu_sta_amsdu_tlv(dev, skb, vif, sta);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index ec7cf57521d9..44e112b8b5b3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -927,6 +927,7 @@ struct mt7915_dev *mt7915_mmio_probe(struct device *pdev,
 		.rx_check = mt7915_rx_check,
 		.rx_poll_complete = mt7915_rx_poll_complete,
 		.sta_add = mt7915_mac_sta_add,
+		.sta_event = mt7915_mac_sta_event,
 		.sta_remove = mt7915_mac_sta_remove,
 		.update_survey = mt7915_update_channel,
 		.set_channel = mt7915_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
index 712471c2a8e9..ac0b1f0eb27c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h
@@ -444,7 +444,7 @@ int mt7915_mcu_add_dev_info(struct mt7915_phy *phy,
 int mt7915_mcu_add_bss_info(struct mt7915_phy *phy,
 			    struct ieee80211_vif *vif, int enable);
 int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif,
-		       struct ieee80211_sta *sta, bool enable);
+		       struct ieee80211_sta *sta, int conn_state, bool newly);
 int mt7915_mcu_add_tx_ba(struct mt7915_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool add);
@@ -560,6 +560,8 @@ void mt7915_mac_write_txwi(struct mt76_dev *dev, __le32 *txwi,
 void mt7915_mac_set_timing(struct mt7915_phy *phy);
 int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		       struct ieee80211_sta *sta);
+int mt7915_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, enum mt76_sta_event ev);
 void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 			   struct ieee80211_sta *sta);
 void mt7915_mac_work(struct work_struct *work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
index 1ed8e77eb549..d534fff5c952 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c
@@ -404,6 +404,7 @@ static void
 mt7915_tm_init(struct mt7915_phy *phy, bool en)
 {
 	struct mt7915_dev *dev = phy->dev;
+	int state;
 
 	if (!test_bit(MT76_STATE_RUNNING, &phy->mt76->state))
 		return;
@@ -415,7 +416,8 @@ mt7915_tm_init(struct mt7915_phy *phy, bool en)
 	mt7915_tm_set_trx(phy, TM_MAC_TXRX, !en);
 
 	mt7915_mcu_add_bss_info(phy, phy->monitor_vif, en);
-	mt7915_mcu_add_sta(dev, phy->monitor_vif, NULL, en);
+	state = en ? CONN_STATE_PORT_SECURE : CONN_STATE_DISCONNECT;
+	mt7915_mcu_add_sta(dev, phy->monitor_vif, NULL, state, true);
 
 	if (!en)
 		mt7915_tm_set_tam_arb(phy, en, 0);
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 34d93f08f415..ce193e625666 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -313,6 +313,9 @@ __mt76_tx_queue_skb(struct mt76_phy *phy, int qid, struct sk_buff *skb,
 		return idx;
 
 	wcid = (struct mt76_wcid *)sta->drv_priv;
+	if (!wcid->sta)
+		return idx;
+
 	q->entry[idx].wcid = wcid->idx;
 
 	if (!non_aql)
-- 
cgit v1.3-3-g829e


From 8351a4a40bdde127ef806e1017aefdb360978f93 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:00 +0200
Subject: wifi: mt76: mt7915: set MT76_MCU_RESET early in mt7915_mac_full_reset

This avoids running into unnecessary timeouts waiting for MCU responses

Link: https://patch.msgid.link/20240827093011.18621-13-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 8008ce3fa6c7..dcec27be5a40 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1448,6 +1448,7 @@ mt7915_mac_full_reset(struct mt7915_dev *dev)
 
 	dev->recovery.hw_full_reset = true;
 
+	set_bit(MT76_MCU_RESET, &dev->mphy.state);
 	wake_up(&dev->mt76.mcu.wait);
 	ieee80211_stop_queues(mt76_hw(dev));
 	if (ext_phy)
-- 
cgit v1.3-3-g829e


From 3688c18b65aeb2a1f2fde108400afbab129a8cc1 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:01 +0200
Subject: wifi: mt76: mt7915: retry mcu messages

In some cases MCU messages can get lost. Instead of failing completely,
attempt to recover by re-sending them.

Link: https://patch.msgid.link/20240827093011.18621-14-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mcu.c        | 20 ++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76.h       |  3 +++
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c |  7 ++-----
 3 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mcu.c b/drivers/net/wireless/mediatek/mt76/mcu.c
index a8cafa39a56d..98da82b74094 100644
--- a/drivers/net/wireless/mediatek/mt76/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mcu.c
@@ -73,6 +73,8 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb,
 				  int cmd, bool wait_resp,
 				  struct sk_buff **ret_skb)
 {
+	unsigned int retry = 0;
+	struct sk_buff *orig_skb = NULL;
 	unsigned long expires;
 	int ret, seq;
 
@@ -81,6 +83,14 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb,
 
 	mutex_lock(&dev->mcu.mutex);
 
+	if (dev->mcu_ops->mcu_skb_prepare_msg) {
+		ret = dev->mcu_ops->mcu_skb_prepare_msg(dev, skb, cmd, &seq);
+		if (ret < 0)
+			goto out;
+	}
+
+retry:
+	orig_skb = skb_get(skb);
 	ret = dev->mcu_ops->mcu_skb_send_msg(dev, skb, cmd, &seq);
 	if (ret < 0)
 		goto out;
@@ -94,6 +104,14 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb,
 
 	do {
 		skb = mt76_mcu_get_response(dev, expires);
+		if (!skb && !test_bit(MT76_MCU_RESET, &dev->phy.state) &&
+		    retry++ < dev->mcu_ops->max_retry) {
+			dev_err(dev->dev, "Retry message %08x (seq %d)\n",
+				cmd, seq);
+			skb = orig_skb;
+			goto retry;
+		}
+
 		ret = dev->mcu_ops->mcu_parse_response(dev, cmd, skb, seq);
 		if (!ret && ret_skb)
 			*ret_skb = skb;
@@ -101,7 +119,9 @@ int mt76_mcu_skb_send_and_get_msg(struct mt76_dev *dev, struct sk_buff *skb,
 			dev_kfree_skb(skb);
 	} while (ret == -EAGAIN);
 
+
 out:
+	dev_kfree_skb(orig_skb);
 	mutex_unlock(&dev->mcu.mutex);
 
 	return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 43e743b510ba..794cd33be68b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -230,11 +230,14 @@ struct mt76_queue {
 };
 
 struct mt76_mcu_ops {
+	unsigned int max_retry;
 	u32 headroom;
 	u32 tailroom;
 
 	int (*mcu_send_msg)(struct mt76_dev *dev, int cmd, const void *data,
 			    int len, bool wait_resp);
+	int (*mcu_skb_prepare_msg)(struct mt76_dev *dev, struct sk_buff *skb,
+				   int cmd, int *seq);
 	int (*mcu_skb_send_msg)(struct mt76_dev *dev, struct sk_buff *skb,
 				int cmd, int *seq);
 	int (*mcu_parse_response)(struct mt76_dev *dev, int cmd,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 2ef8d90132dd..0cde1b3c7d41 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -191,11 +191,6 @@ mt7915_mcu_send_message(struct mt76_dev *mdev, struct sk_buff *skb,
 {
 	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
 	enum mt76_mcuq_id qid;
-	int ret;
-
-	ret = mt76_connac2_mcu_fill_message(mdev, skb, cmd, wait_seq);
-	if (ret)
-		return ret;
 
 	if (cmd == MCU_CMD(FW_SCATTER))
 		qid = MT_MCUQ_FWDL;
@@ -2382,7 +2377,9 @@ int mt7915_mcu_init_firmware(struct mt7915_dev *dev)
 int mt7915_mcu_init(struct mt7915_dev *dev)
 {
 	static const struct mt76_mcu_ops mt7915_mcu_ops = {
+		.max_retry = 3,
 		.headroom = sizeof(struct mt76_connac2_mcu_txd),
+		.mcu_skb_prepare_msg = mt76_connac2_mcu_fill_message,
 		.mcu_skb_send_msg = mt7915_mcu_send_message,
 		.mcu_parse_response = mt7915_mcu_parse_response,
 	};
-- 
cgit v1.3-3-g829e


From 10f73bb3938f7c5cee78b8bdb7dca328c639c9e6 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:02 +0200
Subject: wifi: mt76: mt7915: reset the device after MCU timeout

On MT7915, MCU hangs do not trigger watchdog interrupts, so they can only
be detected through MCU message timeouts. Ensure that the hardware gets
restarted when that happens in order to prevent a permanent stuck state.

Link: https://patch.msgid.link/20240827093011.18621-15-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 0cde1b3c7d41..81375b5d0021 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -157,12 +157,21 @@ static int
 mt7915_mcu_parse_response(struct mt76_dev *mdev, int cmd,
 			  struct sk_buff *skb, int seq)
 {
+	struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76);
 	struct mt76_connac2_mcu_rxd *rxd;
 	int ret = 0;
 
 	if (!skb) {
 		dev_err(mdev->dev, "Message %08x (seq %d) timeout\n",
 			cmd, seq);
+
+		if (!test_and_set_bit(MT76_MCU_RESET, &dev->mphy.state)) {
+			dev->recovery.restart = true;
+			wake_up(&dev->mt76.mcu.wait);
+			queue_work(dev->mt76.wq, &dev->reset_work);
+			wake_up(&dev->reset_wait);
+		}
+
 		return -ETIMEDOUT;
 	}
 
-- 
cgit v1.3-3-g829e


From f2cc859149240d910fdc6405717673e0b84bfda8 Mon Sep 17 00:00:00 2001
From: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Date: Tue, 27 Aug 2024 11:30:03 +0200
Subject: wifi: mt76: mt7915: add dummy HW offload of IEEE 802.11 fragmentation

Currently, CONNAC2 series do not support encryption for fragmented Tx frames.
Therefore, add dummy function mt7915_set_frag_threshold() to prevent SW
IEEE 802.11 fragmentation.

Signed-off-by: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Link: https://patch.msgid.link/20240827093011.18621-16-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/init.c | 1 +
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index a978f434dc5e..511e0d04eb95 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -398,6 +398,7 @@ mt7915_init_wiphy(struct mt7915_phy *phy)
 	ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD);
 	ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID);
 	ieee80211_hw_set(hw, WANT_MONITOR_VIF);
+	ieee80211_hw_set(hw, SUPPORTS_TX_FRAG);
 
 	hw->max_tx_fragments = 4;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 9bf308429db3..e80db20035ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1594,6 +1594,12 @@ mt7915_twt_teardown_request(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
+static int
+mt7915_set_frag_threshold(struct ieee80211_hw *hw, u32 val)
+{
+	return 0;
+}
+
 static int
 mt7915_set_radar_background(struct ieee80211_hw *hw,
 			    struct cfg80211_chan_def *chandef)
@@ -1723,6 +1729,7 @@ const struct ieee80211_ops mt7915_ops = {
 	.sta_set_decap_offload = mt7915_sta_set_decap_offload,
 	.add_twt_setup = mt7915_mac_add_twt_setup,
 	.twt_teardown_request = mt7915_twt_teardown_request,
+	.set_frag_threshold = mt7915_set_frag_threshold,
 	CFG80211_TESTMODE_CMD(mt76_testmode_cmd)
 	CFG80211_TESTMODE_DUMP(mt76_testmode_dump)
 #ifdef CONFIG_MAC80211_DEBUGFS
-- 
cgit v1.3-3-g829e


From 8f7152f10cb434f954aeff85ca1be9cd4d01912b Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:04 +0200
Subject: wifi: mt76: mt7915: hold dev->mt76.mutex while disabling tx worker

Prevent racing against other functions disabling the same worker

Link: https://patch.msgid.link/20240827093011.18621-17-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index dcec27be5a40..fc03cb499e71 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1538,12 +1538,14 @@ void mt7915_mac_reset_work(struct work_struct *work)
 		set_bit(MT76_RESET, &phy2->mt76->state);
 		cancel_delayed_work_sync(&phy2->mt76->mac_work);
 	}
+
+	mutex_lock(&dev->mt76.mutex);
+
 	mt76_worker_disable(&dev->mt76.tx_worker);
 	mt76_for_each_q_rx(&dev->mt76, i)
 		napi_disable(&dev->mt76.napi[i]);
 	napi_disable(&dev->mt76.tx_napi);
 
-	mutex_lock(&dev->mt76.mutex);
 
 	if (mtk_wed_device_active(&dev->mt76.mmio.wed))
 		mtk_wed_device_stop(&dev->mt76.mmio.wed);
-- 
cgit v1.3-3-g829e


From b2141eadf8be6285ff8980cab153079231cab4fd Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:05 +0200
Subject: wifi: mt76: connac: move mt7615_mcu_del_wtbl_all to connac

Preparation for reusing it in mt7915

Link: https://patch.msgid.link/20240827093011.18621-18-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7615/init.c     |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7615/mcu.c      | 10 ----------
 drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h   |  1 -
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 11 +++++++++++
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h |  1 +
 5 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index f7722f67db57..f9274c130c57 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -319,7 +319,7 @@ void mt7615_init_work(struct mt7615_dev *dev)
 	mt7615_mcu_set_eeprom(dev);
 	mt7615_mac_init(dev);
 	mt7615_phy_init(dev);
-	mt7615_mcu_del_wtbl_all(dev);
+	mt76_connac_mcu_del_wtbl_all(&dev->mt76);
 	mt7615_check_offload_capability(dev);
 }
 EXPORT_SYMBOL_GPL(mt7615_init_work);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
index f6eb9939c3e2..159218874802 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c
@@ -1880,16 +1880,6 @@ out:
 				 sizeof(req), true);
 }
 
-int mt7615_mcu_del_wtbl_all(struct mt7615_dev *dev)
-{
-	struct wtbl_req_hdr req = {
-		.operation = WTBL_RESET_ALL,
-	};
-
-	return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(WTBL_UPDATE),
-				 &req, sizeof(req), true);
-}
-
 int mt7615_mcu_set_fcc5_lpn(struct mt7615_dev *dev, int val)
 {
 	struct {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
index 68f4a7727a26..530da48ce3ea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h
@@ -399,7 +399,6 @@ void mt7615_mac_set_rates(struct mt7615_phy *phy, struct mt7615_sta *sta,
 			  struct ieee80211_tx_rate *rates);
 void mt7615_pm_wake_work(struct work_struct *work);
 void mt7615_pm_power_save_work(struct work_struct *work);
-int mt7615_mcu_del_wtbl_all(struct mt7615_dev *dev);
 int mt7615_mcu_set_chan_info(struct mt7615_phy *phy, int cmd);
 int mt7615_mcu_set_wmm(struct mt7615_dev *dev, u8 queue,
 		       const struct ieee80211_tx_queue_params *params);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index 3a575cebe4a9..864246f94088 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -2849,6 +2849,17 @@ int mt76_connac_mcu_restart(struct mt76_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76_connac_mcu_restart);
 
+int mt76_connac_mcu_del_wtbl_all(struct mt76_dev *dev)
+{
+	struct wtbl_req_hdr req = {
+		.operation = WTBL_RESET_ALL,
+	};
+
+	return mt76_mcu_send_msg(dev, MCU_EXT_CMD(WTBL_UPDATE),
+				 &req, sizeof(req), true);
+}
+EXPORT_SYMBOL_GPL(mt76_connac_mcu_del_wtbl_all);
+
 int mt76_connac_mcu_rdd_cmd(struct mt76_dev *dev, int cmd, u8 index,
 			    u8 rx_sel, u8 val)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index e04ae7eddb01..66d70d6e7957 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -2032,6 +2032,7 @@ void mt76_connac_mcu_wtbl_smps_tlv(struct sk_buff *skb,
 				   void *sta_wtbl, void *wtbl_tlv);
 int mt76_connac_mcu_set_pm(struct mt76_dev *dev, int band, int enter);
 int mt76_connac_mcu_restart(struct mt76_dev *dev);
+int mt76_connac_mcu_del_wtbl_all(struct mt76_dev *dev);
 int mt76_connac_mcu_rdd_cmd(struct mt76_dev *dev, int cmd, u8 index,
 			    u8 rx_sel, u8 val);
 int mt76_connac_mcu_sta_wed_update(struct mt76_dev *dev, struct sk_buff *skb);
-- 
cgit v1.3-3-g829e


From 328e35c7bfc673cde5a3a453318d044f8f83b505 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:06 +0200
Subject: wifi: mt76: mt7915: improve hardware restart reliability

- use reconfig_complete to restart mac_work / queues
- reset full wtbl after firmware init
- clear wcid and vif mask to avoid leak
- fix sta poll list corruption

Link: https://patch.msgid.link/20240827093011.18621-19-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c  | 25 ++++++++++++------------
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 12 ++++++++++++
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c  |  2 ++
 3 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index fc03cb499e71..54974ff72a5b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1463,26 +1463,27 @@ mt7915_mac_full_reset(struct mt7915_dev *dev)
 		if (!mt7915_mac_restart(dev))
 			break;
 	}
-	mutex_unlock(&dev->mt76.mutex);
 
 	if (i == 10)
 		dev_err(dev->mt76.dev, "chip full reset failed\n");
 
-	ieee80211_restart_hw(mt76_hw(dev));
-	if (ext_phy)
-		ieee80211_restart_hw(ext_phy->hw);
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	while (!list_empty(&dev->mt76.sta_poll_list))
+		list_del_init(dev->mt76.sta_poll_list.next);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
-	ieee80211_wake_queues(mt76_hw(dev));
-	if (ext_phy)
-		ieee80211_wake_queues(ext_phy->hw);
+	memset(dev->mt76.wcid_mask, 0, sizeof(dev->mt76.wcid_mask));
+	dev->mt76.vif_mask = 0;
 
+	i = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7915_WTBL_STA);
+	dev->mt76.global_wcid.idx = i;
 	dev->recovery.hw_full_reset = false;
-	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mphy.mac_work,
-				     MT7915_WATCHDOG_TIME);
+
+	mutex_unlock(&dev->mt76.mutex);
+
+	ieee80211_restart_hw(mt76_hw(dev));
 	if (ext_phy)
-		ieee80211_queue_delayed_work(ext_phy->hw,
-					     &ext_phy->mac_work,
-					     MT7915_WATCHDOG_TIME);
+		ieee80211_restart_hw(ext_phy->hw);
 }
 
 /* system error recovery */
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index e80db20035ab..51885484aab6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1682,6 +1682,17 @@ mt7915_net_fill_forward_path(struct ieee80211_hw *hw,
 }
 #endif
 
+static void
+mt7915_reconfig_complete(struct ieee80211_hw *hw,
+			 enum ieee80211_reconfig_type reconfig_type)
+{
+	struct mt7915_phy *phy = mt7915_hw_phy(hw);
+
+	ieee80211_wake_queues(hw);
+	ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work,
+				     MT7915_WATCHDOG_TIME);
+}
+
 const struct ieee80211_ops mt7915_ops = {
 	.add_chanctx = ieee80211_emulate_add_chanctx,
 	.remove_chanctx = ieee80211_emulate_remove_chanctx,
@@ -1740,4 +1751,5 @@ const struct ieee80211_ops mt7915_ops = {
 	.net_fill_forward_path = mt7915_net_fill_forward_path,
 	.net_setup_tc = mt76_wed_net_setup_tc,
 #endif
+	.reconfig_complete = mt7915_reconfig_complete,
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 81375b5d0021..72c8e574dfb7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -2362,6 +2362,8 @@ int mt7915_mcu_init_firmware(struct mt7915_dev *dev)
 	if (ret)
 		return ret;
 
+	mt76_connac_mcu_del_wtbl_all(&dev->mt76);
+
 	if ((mtk_wed_device_active(&dev->mt76.mmio.wed) &&
 	     is_mt7915(&dev->mt76)) ||
 	    !mtk_wed_get_rx_capa(&dev->mt76.mmio.wed))
-- 
cgit v1.3-3-g829e


From c37784435277f040cda9552d8b22e21604dd54bd Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:07 +0200
Subject: wifi: mt76: shrink mt76_queue_buf

Reuse one bit from the length field for skip_unmap

Link: https://patch.msgid.link/20240827093011.18621-20-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 794cd33be68b..0b75a45ad2e8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -162,8 +162,8 @@ enum mt76_dfs_state {
 
 struct mt76_queue_buf {
 	dma_addr_t addr;
-	u16 len;
-	bool skip_unmap;
+	u16 len:15,
+	    skip_unmap:1;
 };
 
 struct mt76_tx_info {
-- 
cgit v1.3-3-g829e


From 6ac80fce713e875a316a58975b830720a3e27721 Mon Sep 17 00:00:00 2001
From: Howard Hsu <howard-yh.hsu@mediatek.com>
Date: Tue, 27 Aug 2024 11:30:08 +0200
Subject: wifi: mt76: mt7915: fix rx filter setting for bfee functionality

Fix rx filter setting to prevent dropping NDPA frames. Without this
change, bfee functionality may behave abnormally.

Fixes: e57b7901469f ("mt76: add mac80211 driver for MT7915 PCIe-based chipsets")
Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com>
Link: https://patch.msgid.link/20240827093011.18621-21-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index 51885484aab6..db2cf6e11cf3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -557,8 +557,7 @@ static void mt7915_configure_filter(struct ieee80211_hw *hw,
 
 	MT76_FILTER(CONTROL, MT_WF_RFCR_DROP_CTS |
 			     MT_WF_RFCR_DROP_RTS |
-			     MT_WF_RFCR_DROP_CTL_RSV |
-			     MT_WF_RFCR_DROP_NDPA);
+			     MT_WF_RFCR_DROP_CTL_RSV);
 
 	*total_flags = flags;
 	rxfilter = phy->rxfilter;
-- 
cgit v1.3-3-g829e


From eeb672b50d32269516d345911d7c9ae15ac238b2 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:09 +0200
Subject: wifi: mt76: mt7915: always query station rx rate from firmware

When offloading is enabled, the software rx path may not have the latest
rate information.

Link: https://patch.msgid.link/20240827093011.18621-22-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
index db2cf6e11cf3..d75e8dea1fbd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
@@ -1094,8 +1094,7 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw,
 	struct rate_info *txrate = &msta->wcid.rate;
 	struct rate_info rxrate = {};
 
-	if (is_mt7915(&phy->dev->mt76) &&
-	    !mt7915_mcu_get_rx_rate(phy, vif, sta, &rxrate)) {
+	if (!mt7915_mcu_get_rx_rate(phy, vif, sta, &rxrate)) {
 		sinfo->rxrate = rxrate;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 	}
-- 
cgit v1.3-3-g829e


From 9e461f4a2329109571f4b10f9bcad28d07e6ebb3 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:10 +0200
Subject: wifi: mt76: mt7996: fix uninitialized TLV data

Use skb_put_zero instead of skb_put

Fixes: 98686cd21624 ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
Link: https://patch.msgid.link/20240827093011.18621-23-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index caa0ff619475..327337b31279 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -735,7 +735,7 @@ void mt7996_mcu_rx_event(struct mt7996_dev *dev, struct sk_buff *skb)
 static struct tlv *
 mt7996_mcu_add_uni_tlv(struct sk_buff *skb, u16 tag, u16 len)
 {
-	struct tlv *ptlv = skb_put(skb, len);
+	struct tlv *ptlv = skb_put_zero(skb, len);
 
 	ptlv->tag = cpu_to_le16(tag);
 	ptlv->len = cpu_to_le16(len);
-- 
cgit v1.3-3-g829e


From b13cd593ef2402e413e5c5c63e1b5e9ab5ed0e6e Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 27 Aug 2024 11:30:11 +0200
Subject: wifi: mt76: mt7915: avoid long MCU command timeouts during SER

Immediately abort MCU commands when firmware requests DMA restart.

Link: https://patch.msgid.link/20240827093011.18621-24-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 54974ff72a5b..cf77ce0c8759 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -1696,6 +1696,11 @@ void mt7915_reset(struct mt7915_dev *dev)
 		return;
 	}
 
+	if ((READ_ONCE(dev->recovery.state) & MT_MCU_CMD_STOP_DMA)) {
+		set_bit(MT76_MCU_RESET, &dev->mphy.state);
+		wake_up(&dev->mt76.mcu.wait);
+	}
+
 	queue_work(dev->mt76.wq, &dev->reset_work);
 	wake_up(&dev->reset_wait);
 }
-- 
cgit v1.3-3-g829e


From 267efeda8c55f30e0e7c5b7fd03dea4efec6916c Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Tue, 3 Sep 2024 09:49:55 +0800
Subject: wifi: mt76: mt7915: check devm_kasprintf() returned value

devm_kasprintf() can return a NULL pointer on failure but this returned
value is not checked. Fix this lack and check the returned value.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: 6ae39b7c7ed4 ("wifi: mt76: mt7921: Support temp sensor")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://patch.msgid.link/20240903014955.4145423-1-make24@iscas.ac.cn
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
index 511e0d04eb95..6bef96e3d2a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
@@ -194,6 +194,8 @@ static int mt7915_thermal_init(struct mt7915_phy *phy)
 
 	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7915_%s",
 			      wiphy_name(wiphy));
+	if (!name)
+		return -ENOMEM;
 
 	cdev = thermal_cooling_device_register(name, phy, &mt7915_thermal_ops);
 	if (!IS_ERR(cdev)) {
-- 
cgit v1.3-3-g829e


From 1ccc9e476ce76e8577ba4fdbd1f63cb3e3499d38 Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Tue, 3 Sep 2024 09:44:55 +0800
Subject: wifi: mt76: mt7921: Check devm_kasprintf() returned value

devm_kasprintf() can return a NULL pointer on failure but this returned
value is not checked. Fix this lack and check the returned value.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: 6ae39b7c7ed4 ("wifi: mt76: mt7921: Support temp sensor")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Reviwed-by: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://patch.msgid.link/20240903014455.4144536-1-make24@iscas.ac.cn
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
index 57672c69150e..d1d64fa7d35d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
@@ -52,6 +52,8 @@ static int mt7921_thermal_init(struct mt792x_phy *phy)
 
 	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7921_%s",
 			      wiphy_name(wiphy));
+	if (!name)
+		return -ENOMEM;
 
 	hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy,
 						       mt7921_hwmon_groups);
-- 
cgit v1.3-3-g829e


From bb6fe2b92ae7bab4d95976a1a4d705d40731f690 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 15 Aug 2024 12:36:33 -0600
Subject: wifi: mt76: Avoid multiple -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in order to avoid ending up with a flexible-array member in the
middle of multiple other structs, we use the `struct_group_tagged()`
helper to create a new tagged `struct mt76_connac2_mcu_rxd_hdr`.
This structure groups together all the members of the flexible
`struct mt76_connac2_mcu_rxd` except the flexible array.

As a result, the array is effectively separated from the rest of the
members without modifying the memory layout of the flexible structure.
We then change the type of the middle struct members currently causing
trouble from `struct mt76_connac2_mcu_rxd` to `struct
mt76_connac2_mcu_rxd_hdr`.

We also want to ensure that when new members need to be added to the
flexible structure, they are always included within the newly created
tagged struct. For this, we use `static_assert()`. This ensures that the
memory layout for both the flexible structure and the new tagged struct
is the same after any changes.

This approach avoids having to implement `struct mt76_connac2_mcu_rxd_hdr`
as a completely separate structure, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

So, with these changes, fix the following warnings:

drivers/net/wireless/mediatek/mt76/mt7915/mcu.h:32:37: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/mediatek/mt76/mt7915/mcu.h:40:37: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/mediatek/mt76/mt7915/mcu.h:49:37: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/mediatek/mt76/mt7915/mcu.h:58:37: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/Zr5KsZugaEXrApQJ@elsanto
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt76_connac_mcu.h   | 25 +++++++++++++---------
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.h    |  8 +++----
 2 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
index 66d70d6e7957..1b0e80dfc346 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h
@@ -115,21 +115,26 @@ struct mt76_connac2_mcu_uni_txd {
 } __packed __aligned(4);
 
 struct mt76_connac2_mcu_rxd {
-	__le32 rxd[6];
+	/* New members MUST be added within the struct_group() macro below. */
+	struct_group_tagged(mt76_connac2_mcu_rxd_hdr, hdr,
+		__le32 rxd[6];
 
-	__le16 len;
-	__le16 pkt_type_id;
+		__le16 len;
+		__le16 pkt_type_id;
 
-	u8 eid;
-	u8 seq;
-	u8 option;
-	u8 rsv;
-	u8 ext_eid;
-	u8 rsv1[2];
-	u8 s2d_index;
+		u8 eid;
+		u8 seq;
+		u8 option;
+		u8 rsv;
+		u8 ext_eid;
+		u8 rsv1[2];
+		u8 s2d_index;
+	);
 
 	u8 tlv[];
 };
+static_assert(offsetof(struct mt76_connac2_mcu_rxd, tlv) == sizeof(struct mt76_connac2_mcu_rxd_hdr),
+	      "struct member likely outside of struct_group_tagged()");
 
 struct mt76_connac2_patch_hdr {
 	char build_date[16];
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
index b41ac4aaced7..49476a4182fd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
@@ -29,7 +29,7 @@ struct mt7915_mcu_thermal_ctrl {
 } __packed;
 
 struct mt7915_mcu_thermal_notify {
-	struct mt76_connac2_mcu_rxd rxd;
+	struct mt76_connac2_mcu_rxd_hdr rxd;
 
 	struct mt7915_mcu_thermal_ctrl ctrl;
 	__le32 temperature;
@@ -37,7 +37,7 @@ struct mt7915_mcu_thermal_notify {
 } __packed;
 
 struct mt7915_mcu_csa_notify {
-	struct mt76_connac2_mcu_rxd rxd;
+	struct mt76_connac2_mcu_rxd_hdr rxd;
 
 	u8 omac_idx;
 	u8 csa_count;
@@ -46,7 +46,7 @@ struct mt7915_mcu_csa_notify {
 } __packed;
 
 struct mt7915_mcu_bcc_notify {
-	struct mt76_connac2_mcu_rxd rxd;
+	struct mt76_connac2_mcu_rxd_hdr rxd;
 
 	u8 band_idx;
 	u8 omac_idx;
@@ -55,7 +55,7 @@ struct mt7915_mcu_bcc_notify {
 } __packed;
 
 struct mt7915_mcu_rdd_report {
-	struct mt76_connac2_mcu_rxd rxd;
+	struct mt76_connac2_mcu_rxd_hdr rxd;
 
 	u8 band_idx;
 	u8 long_detected;
-- 
cgit v1.3-3-g829e


From 45064d19fd3af6aeb0887b35b5564927980cf150 Mon Sep 17 00:00:00 2001
From: Michael Lo <michael.lo@mediatek.com>
Date: Mon, 2 Sep 2024 17:00:54 +0800
Subject: wifi: mt76: mt7925: fix a potential association failure upon resuming

In multi-channel scenarios, the granted channel must be aborted before
suspending. Otherwise, the firmware will be put into a wrong state,
resulting in an association failure after resuming.

With this patch, the granted channel will be aborted before suspending
if necessary.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Michael Lo <michael.lo@mediatek.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20240902090054.15806-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/main.c   | 15 +++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h |  1 +
 drivers/net/wireless/mediatek/mt76/mt7925/pci.c    |  2 ++
 3 files changed, 18 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 38a301533297..791c8b00e112 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -439,6 +439,19 @@ static void mt7925_roc_iter(void *priv, u8 *mac,
 	mt7925_mcu_abort_roc(phy, &mvif->bss_conf, phy->roc_token_id);
 }
 
+void mt7925_roc_abort_sync(struct mt792x_dev *dev)
+{
+	struct mt792x_phy *phy = &dev->phy;
+
+	del_timer_sync(&phy->roc_timer);
+	cancel_work_sync(&phy->roc_work);
+	if (test_and_clear_bit(MT76_STATE_ROC, &phy->mt76->state))
+		ieee80211_iterate_interfaces(mt76_hw(dev),
+					     IEEE80211_IFACE_ITER_RESUME_ALL,
+					     mt7925_roc_iter, (void *)phy);
+}
+EXPORT_SYMBOL_GPL(mt7925_roc_abort_sync);
+
 void mt7925_roc_work(struct work_struct *work)
 {
 	struct mt792x_phy *phy;
@@ -1112,6 +1125,8 @@ static void mt7925_mac_link_sta_remove(struct mt76_dev *mdev,
 	msta = (struct mt792x_sta *)link_sta->sta->drv_priv;
 	mlink = mt792x_sta_to_link(msta, link_id);
 
+	mt7925_roc_abort_sync(dev);
+
 	mt76_connac_free_pending_tx_skbs(&dev->pm, &mlink->wcid);
 	mt76_connac_pm_wake(&dev->mphy, &dev->pm);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index e80824a10b2c..f5c02e5f5066 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -307,6 +307,7 @@ int mt7925_mcu_set_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf,
 		       enum mt7925_roc_req type, u8 token_id);
 int mt7925_mcu_abort_roc(struct mt792x_phy *phy, struct mt792x_bss_conf *mconf,
 			 u8 token_id);
+void mt7925_roc_abort_sync(struct mt792x_dev *dev);
 int mt7925_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb,
 			    int cmd, int *wait_seq);
 int mt7925_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
index cb25eb50a45b..9aec675450f2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c
@@ -449,6 +449,8 @@ static int mt7925_pci_suspend(struct device *device)
 	cancel_delayed_work_sync(&pm->ps_work);
 	cancel_work_sync(&pm->wake_work);
 
+	mt7925_roc_abort_sync(dev);
+
 	err = mt792x_mcu_drv_pmctrl(dev);
 	if (err < 0)
 		goto restore_suspend;
-- 
cgit v1.3-3-g829e


From df6b08670f76b77f7025ab543686ee4ef45a5724 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 15:52:13 +0800
Subject: wifi: mt76: mt7925: convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://patch.msgid.link/20240904075213.1352976-1-nichen@iscas.ac.cn
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 473ed54e8710..e07b43dd8638 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -2174,12 +2174,12 @@ void mt7925_mcu_bss_rlm_tlv(struct sk_buff *skb, struct mt76_phy *phy,
 
 	tlv = mt76_connac_mcu_add_tlv(skb, UNI_BSS_INFO_RLM, sizeof(*req));
 	req = (struct bss_rlm_tlv *)tlv;
-	req->control_channel = chandef->chan->hw_value,
-	req->center_chan = ieee80211_frequency_to_channel(freq1),
-	req->center_chan2 = ieee80211_frequency_to_channel(freq2),
-	req->tx_streams = hweight8(phy->antenna_mask),
-	req->ht_op_info = 4, /* set HT 40M allowed */
-	req->rx_streams = hweight8(phy->antenna_mask),
+	req->control_channel = chandef->chan->hw_value;
+	req->center_chan = ieee80211_frequency_to_channel(freq1);
+	req->center_chan2 = ieee80211_frequency_to_channel(freq2);
+	req->tx_streams = hweight8(phy->antenna_mask);
+	req->ht_op_info = 4; /* set HT 40M allowed */
+	req->rx_streams = hweight8(phy->antenna_mask);
 	req->band = band;
 
 	switch (chandef->width) {
-- 
cgit v1.3-3-g829e


From 5acdc432f832d810e0d638164c393b877291d9b4 Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Thu, 5 Sep 2024 09:47:53 +0800
Subject: wifi: mt76: mt7615: check devm_kasprintf() returned value

devm_kasprintf() can return a NULL pointer on failure but this returned
value is not checked. Fix this lack and check the returned value.

Found by code review.

Cc: stable@vger.kernel.org
Fixes: 0bb4e9187ea4 ("mt76: mt7615: fix hwmon temp sensor mem use-after-free")
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Reviewed-by: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://patch.msgid.link/20240905014753.353271-1-make24@iscas.ac.cn
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7615/init.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
index f9274c130c57..66ba3be27343 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
@@ -56,6 +56,9 @@ int mt7615_thermal_init(struct mt7615_dev *dev)
 
 	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7615_%s",
 			      wiphy_name(wiphy));
+	if (!name)
+		return -ENOMEM;
+
 	hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, dev,
 						       mt7615_hwmon_groups);
 	return PTR_ERR_OR_ZERO(hwmon);
-- 
cgit v1.3-3-g829e


From 9679ca7326e52282cc923c4d71d81c999cb6cd55 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 19 Aug 2024 09:53:33 +0800
Subject: wifi: mt76: mt7925: fix a potential array-index-out-of-bounds issue
 for clc

Due to the lack of checks on the clc array, if the firmware supports
more clc configuration, it will cause illegal memory access.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20240819015334.14580-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index e07b43dd8638..748ea6adbc6b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -638,6 +638,9 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	for (offset = 0; offset < len; offset += le32_to_cpu(clc->len)) {
 		clc = (const struct mt7925_clc *)(clc_base + offset);
 
+		if (clc->idx > ARRAY_SIZE(phy->clc))
+			break;
+
 		/* do not init buf again if chip reset triggered */
 		if (phy->clc[clc->idx])
 			continue;
-- 
cgit v1.3-3-g829e


From 6bba05d651ef77f2c3f3c67b9ace093fee4e01e1 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 19 Aug 2024 09:53:34 +0800
Subject: wifi: mt76: mt7925: replace chan config with extend txpower config
 for clc

Since MT792x_CLC_CHAN is currently not in use, we have added an
extension for setting txpower to replace it.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20240819015334.14580-2-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt792x.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 7fa74d59cc48..ab12616ec2b8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -68,7 +68,7 @@ struct mt792x_fw_features {
 
 enum {
 	MT792x_CLC_POWER,
-	MT792x_CLC_CHAN,
+	MT792x_CLC_POWER_EXT,
 	MT792x_CLC_MAX_NUM,
 };
 
-- 
cgit v1.3-3-g829e


From 597b8af58bb2df443ebbdbdc4eef297f5d79d356 Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:57:46 +0200
Subject: ice: add new VSI type for subfunctions

Add required plumbing for new VSI type dedicated to devlink subfunctions.
Make sure that the vsi is properly configured and destroyed. Also allow
loading XDP and AF_XDP sockets.

The first implementation of devlink subfunctions supports only one Tx/Rx
queue pair per given subfunction.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c    |  5 ++++-
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c |  1 +
 drivers/net/ethernet/intel/ice/ice_lib.c     | 25 +++++++++++++++++++++++--
 drivers/net/ethernet/intel/ice/ice_main.c    |  7 +++++--
 drivers/net/ethernet/intel/ice/ice_type.h    |  1 +
 drivers/net/ethernet/intel/ice/ice_xsk.c     |  2 +-
 6 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index c158749a80e0..4a9a6899fc45 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -325,6 +325,9 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf
 		tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id;
 		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VF;
 		break;
+	case ICE_VSI_SF:
+		tlan_ctx->vmvf_type = ICE_TLAN_CTX_VMVF_TYPE_VMQ;
+		break;
 	default:
 		return;
 	}
@@ -540,7 +543,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 
 	ring->rx_buf_len = ring->vsi->rx_buf_len;
 
-	if (ring->vsi->type == ICE_VSI_PF) {
+	if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) {
 		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) {
 			err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 						 ring->q_index,
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index a94e7072b570..a7c510832824 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -187,6 +187,7 @@ void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi)
 		vsi->tc_cfg.numtc = ice_dcb_get_num_tc(cfg);
 		break;
 	case ICE_VSI_CHNL:
+	case ICE_VSI_SF:
 		vsi->tc_cfg.ena_tc = BIT(ice_get_first_droptc(vsi));
 		vsi->tc_cfg.numtc = 1;
 		break;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 737c00b02dd0..cb90a393709b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -20,6 +20,8 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type)
 		return "ICE_VSI_PF";
 	case ICE_VSI_VF:
 		return "ICE_VSI_VF";
+	case ICE_VSI_SF:
+		return "ICE_VSI_SF";
 	case ICE_VSI_CTRL:
 		return "ICE_VSI_CTRL";
 	case ICE_VSI_CHNL:
@@ -135,6 +137,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 {
 	switch (vsi->type) {
 	case ICE_VSI_PF:
+	case ICE_VSI_SF:
 	case ICE_VSI_CTRL:
 	case ICE_VSI_LB:
 		/* a user could change the values of num_[tr]x_desc using
@@ -201,6 +204,12 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 					   max_t(int, vsi->alloc_rxq,
 						 vsi->alloc_txq));
 		break;
+	case ICE_VSI_SF:
+		vsi->alloc_txq = 1;
+		vsi->alloc_rxq = 1;
+		vsi->num_q_vectors = 1;
+		vsi->irq_dyn_alloc = true;
+		break;
 	case ICE_VSI_VF:
 		if (vf->num_req_qs)
 			vf->num_vf_qs = vf->num_req_qs;
@@ -559,6 +568,7 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
+	case ICE_VSI_SF:
 		/* Setup default MSIX irq handler for VSI */
 		vsi->irq_handler = ice_msix_clean_rings;
 		break;
@@ -889,6 +899,11 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi)
 					      max_rss_size);
 		vsi->rss_lut_type = ICE_LUT_PF;
 		break;
+	case ICE_VSI_SF:
+		vsi->rss_table_size = ICE_LUT_VSI_SIZE;
+		vsi->rss_size = min_t(u16, num_online_cpus(), max_rss_size);
+		vsi->rss_lut_type = ICE_LUT_VSI;
+		break;
 	case ICE_VSI_VF:
 		/* VF VSI will get a small RSS table.
 		 * For VSI_LUT, LUT size should be set to 64 bytes.
@@ -1136,6 +1151,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_PF;
 		break;
 	case ICE_VSI_VF:
+	case ICE_VSI_SF:
 		/* VF VSI will gets a small RSS table which is a VSI LUT type */
 		lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI;
 		break;
@@ -1214,6 +1230,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags)
 	case ICE_VSI_PF:
 		ctxt->flags = ICE_AQ_VSI_TYPE_PF;
 		break;
+	case ICE_VSI_SF:
 	case ICE_VSI_CHNL:
 		ctxt->flags = ICE_AQ_VSI_TYPE_VMDQ2;
 		break;
@@ -2095,6 +2112,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi)
 	case ICE_VSI_CHNL:
 	case ICE_VSI_LB:
 	case ICE_VSI_PF:
+	case ICE_VSI_SF:
 		max_agg_nodes = ICE_MAX_PF_AGG_NODES;
 		agg_node_id_start = ICE_PF_AGG_NODE_ID_START;
 		agg_node_iter = &pf->pf_agg_node[0];
@@ -2264,6 +2282,7 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 
 	switch (vsi->type) {
 	case ICE_VSI_CTRL:
+	case ICE_VSI_SF:
 	case ICE_VSI_PF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
 		if (ret)
@@ -2648,7 +2667,8 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
 
 	clear_bit(ICE_VSI_NEEDS_RESTART, vsi->state);
 
-	if (vsi->netdev && vsi->type == ICE_VSI_PF) {
+	if (vsi->netdev && (vsi->type == ICE_VSI_PF ||
+			    vsi->type == ICE_VSI_SF)) {
 		if (netif_running(vsi->netdev)) {
 			if (!locked)
 				rtnl_lock();
@@ -2676,7 +2696,8 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 
 	set_bit(ICE_VSI_NEEDS_RESTART, vsi->state);
 
-	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
+	if (vsi->netdev && (vsi->type == ICE_VSI_PF ||
+			    vsi->type == ICE_VSI_SF)) {
 		if (netif_running(vsi->netdev)) {
 			if (!locked)
 				rtnl_lock();
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c7db88b517da..ad485d22f302 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2974,6 +2974,9 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi)
 	if (avail < cpus / 2)
 		return -ENOMEM;
 
+	if (vsi->type == ICE_VSI_SF)
+		avail = vsi->alloc_txq;
+
 	vsi->num_xdp_txq = min_t(u16, avail, cpus);
 
 	if (vsi->num_xdp_txq < cpus)
@@ -3095,8 +3098,8 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	struct ice_vsi *vsi = np->vsi;
 	int ret;
 
-	if (vsi->type != ICE_VSI_PF) {
-		NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI");
+	if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_SF) {
+		NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF or SF VSI");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index b9e443232335..45768796691f 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -159,6 +159,7 @@ enum ice_vsi_type {
 	ICE_VSI_CTRL = 3,	/* equates to ICE_VSI_PF with 1 queue pair */
 	ICE_VSI_CHNL = 4,
 	ICE_VSI_LB = 6,
+	ICE_VSI_SF = 9,
 };
 
 struct ice_link_status {
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 5dee829bfc47..334ae945d640 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -289,7 +289,7 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 {
 	int err;
 
-	if (vsi->type != ICE_VSI_PF)
+	if (vsi->type != ICE_VSI_PF && vsi->type != ICE_VSI_SF)
 		return -EINVAL;
 
 	if (qid >= vsi->netdev->real_num_rx_queues ||
-- 
cgit v1.3-3-g829e


From 004688c4cb5b2ef598fc33e4daf07ef76f79c16c Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:57:47 +0200
Subject: ice: export ice ndo_ops functions

Make some of the netdevice_ops functions visible from outside for
another VSI type created netdev.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h      |  8 +++++++
 drivers/net/ethernet/intel/ice/ice_lib.c  | 20 ++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.h  |  1 +
 drivers/net/ethernet/intel/ice/ice_main.c | 35 ++++++-------------------------
 4 files changed, 35 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index ce8b5505b16d..e962bdf71204 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -1003,6 +1003,14 @@ void ice_unload(struct ice_pf *pf);
 void ice_adv_lnk_speed_maps_init(void);
 int ice_init_dev(struct ice_pf *pf);
 void ice_deinit_dev(struct ice_pf *pf);
+int ice_change_mtu(struct net_device *netdev, int new_mtu);
+void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue);
+int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp);
+void ice_set_netdev_features(struct net_device *netdev);
+int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid);
+int ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid);
+void ice_get_stats64(struct net_device *netdev,
+		     struct rtnl_link_stats64 *stats);
 
 /**
  * ice_set_rdma_cap - enable RDMA support
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index cb90a393709b..3038849cd37a 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2767,6 +2767,26 @@ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL);
 }
 
+/**
+ * ice_napi_add - register NAPI handler for the VSI
+ * @vsi: VSI for which NAPI handler is to be registered
+ *
+ * This function is only called in the driver's load path. Registering the NAPI
+ * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume,
+ * reset/rebuild, etc.)
+ */
+void ice_napi_add(struct ice_vsi *vsi)
+{
+	int v_idx;
+
+	if (!vsi->netdev)
+		return;
+
+	ice_for_each_q_vector(vsi, v_idx)
+		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
+			       ice_napi_poll);
+}
+
 /**
  * ice_vsi_release - Delete a VSI and free its resources
  * @vsi: the VSI being removed
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 36d86535695d..6c2ac56d1746 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -45,6 +45,7 @@ struct ice_vsi *
 ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
 
 void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
+void ice_napi_add(struct ice_vsi *vsi);
 
 void ice_vsi_clear_napi_queues(struct ice_vsi *vsi);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ad485d22f302..53f002153432 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3092,7 +3092,7 @@ static int ice_xdp_safe_mode(struct net_device __always_unused *dev,
  * @dev: netdevice
  * @xdp: XDP command
  */
-static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_vsi *vsi = np->vsi;
@@ -3558,26 +3558,6 @@ skip_req_irq:
 	return 0;
 }
 
-/**
- * ice_napi_add - register NAPI handler for the VSI
- * @vsi: VSI for which NAPI handler is to be registered
- *
- * This function is only called in the driver's load path. Registering the NAPI
- * handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume,
- * reset/rebuild, etc.)
- */
-static void ice_napi_add(struct ice_vsi *vsi)
-{
-	int v_idx;
-
-	if (!vsi->netdev)
-		return;
-
-	ice_for_each_q_vector(vsi, v_idx)
-		netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
-			       ice_napi_poll);
-}
-
 /**
  * ice_set_ops - set netdev and ethtools ops for the given netdev
  * @vsi: the VSI associated with the new netdev
@@ -3611,7 +3591,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
  * ice_set_netdev_features - set features for the given netdev
  * @netdev: netdev instance
  */
-static void ice_set_netdev_features(struct net_device *netdev)
+void ice_set_netdev_features(struct net_device *netdev)
 {
 	struct ice_pf *pf = ice_netdev_to_pf(netdev);
 	bool is_dvm_ena = ice_is_dvm_ena(&pf->hw);
@@ -3793,8 +3773,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
  *
  * net_device_ops implementation for adding VLAN IDs
  */
-static int
-ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
+int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi_vlan_ops *vlan_ops;
@@ -3856,8 +3835,7 @@ finish:
  *
  * net_device_ops implementation for removing VLAN IDs
  */
-static int
-ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
+int ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi_vlan_ops *vlan_ops;
@@ -7127,7 +7105,6 @@ void ice_update_pf_stats(struct ice_pf *pf)
  * @netdev: network interface device structure
  * @stats: main device statistics structure
  */
-static
 void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
@@ -7804,7 +7781,7 @@ clear_recovery:
  *
  * Returns 0 on success, negative on failure
  */
-static int ice_change_mtu(struct net_device *netdev, int new_mtu)
+int ice_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_vsi *vsi = np->vsi;
@@ -8228,7 +8205,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
  * @netdev: network interface device structure
  * @txqueue: Tx queue
  */
-static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_tx_ring *tx_ring = NULL;
-- 
cgit v1.3-3-g829e


From eda69d654c7edae21312f731e0308941cb2ee2a9 Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:57:48 +0200
Subject: ice: add basic devlink subfunctions support

Implement devlink port handlers responsible for ethernet type devlink
subfunctions. Create subfunction devlink port and setup all resources
needed for a subfunction netdev to operate. Configure new VSI for each
new subfunction, initialize and configure interrupts and Tx/Rx resources.
Set correct MAC filters and create new netdev.

For now, subfunction is limited to only one Tx/Rx queue pair.

Only allocate new subfunction VSI with devlink port new command.
Allocate and free subfunction MSIX interrupt vectors using new API
calls with pci_msix_alloc_irq_at and pci_msix_free_irq.

Support both automatic and manual subfunction numbers. If no subfunction
number is provided, use xa_alloc to pick a number automatically. This
will find the first free index and use that as the number. This reduces
burden on users in the simple case where a specific number is not
required. It may also be slightly faster to check that a number exists
since xarray lookup should be faster than a linear scan of the dyn_ports
xarray.

Co-developed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c   |   3 +
 .../net/ethernet/intel/ice/devlink/devlink_port.c  | 288 +++++++++++++++++++++
 .../net/ethernet/intel/ice/devlink/devlink_port.h  |  34 +++
 drivers/net/ethernet/intel/ice/ice.h               |   4 +
 drivers/net/ethernet/intel/ice/ice_lib.c           |   5 +-
 drivers/net/ethernet/intel/ice/ice_lib.h           |   2 +
 drivers/net/ethernet/intel/ice/ice_main.c          |   7 +
 7 files changed, 341 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 810a901d7afd..b7eb1b56f2c6 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -6,6 +6,7 @@
 #include "ice.h"
 #include "ice_lib.h"
 #include "devlink.h"
+#include "devlink_port.h"
 #include "ice_eswitch.h"
 #include "ice_fw_update.h"
 #include "ice_dcb_lib.h"
@@ -1277,6 +1278,8 @@ static const struct devlink_ops ice_devlink_ops = {
 
 	.rate_leaf_parent_set = ice_devlink_set_parent,
 	.rate_node_parent_set = ice_devlink_set_parent,
+
+	.port_new = ice_devlink_port_new,
 };
 
 static int
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 62ef8e2fb5f1..6202568a3e05 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -5,6 +5,9 @@
 
 #include "ice.h"
 #include "devlink.h"
+#include "devlink_port.h"
+#include "ice_lib.h"
+#include "ice_fltr.h"
 
 static int ice_active_port_option = -1;
 
@@ -485,3 +488,288 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf)
 	devl_rate_leaf_destroy(&vf->devlink_port);
 	devl_port_unregister(&vf->devlink_port);
 }
+
+/**
+ * ice_dealloc_dynamic_port - Deallocate and remove a dynamic port
+ * @dyn_port: dynamic port instance to deallocate
+ *
+ * Free resources associated with a dynamically added devlink port. Will
+ * deactivate the port if its currently active.
+ */
+static void ice_dealloc_dynamic_port(struct ice_dynamic_port *dyn_port)
+{
+	struct devlink_port *devlink_port = &dyn_port->devlink_port;
+	struct ice_pf *pf = dyn_port->pf;
+
+	xa_erase(&pf->sf_nums, devlink_port->attrs.pci_sf.sf);
+	devl_port_unregister(devlink_port);
+	ice_vsi_free(dyn_port->vsi);
+	xa_erase(&pf->dyn_ports, dyn_port->vsi->idx);
+	kfree(dyn_port);
+}
+
+/**
+ * ice_dealloc_all_dynamic_ports - Deallocate all dynamic devlink ports
+ * @pf: pointer to the pf structure
+ */
+void ice_dealloc_all_dynamic_ports(struct ice_pf *pf)
+{
+	struct ice_dynamic_port *dyn_port;
+	unsigned long index;
+
+	xa_for_each(&pf->dyn_ports, index, dyn_port)
+		ice_dealloc_dynamic_port(dyn_port);
+}
+
+/**
+ * ice_devlink_port_new_check_attr - Check that new port attributes are valid
+ * @pf: pointer to the PF structure
+ * @new_attr: the attributes for the new port
+ * @extack: extack for reporting error messages
+ *
+ * Check that the attributes for the new port are valid before continuing to
+ * allocate the devlink port.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_new_check_attr(struct ice_pf *pf,
+				const struct devlink_port_new_attrs *new_attr,
+				struct netlink_ext_ack *extack)
+{
+	if (new_attr->flavour != DEVLINK_PORT_FLAVOUR_PCI_SF) {
+		NL_SET_ERR_MSG_MOD(extack, "Flavour other than pcisf is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (new_attr->controller_valid) {
+		NL_SET_ERR_MSG_MOD(extack, "Setting controller is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (new_attr->port_index_valid) {
+		NL_SET_ERR_MSG_MOD(extack, "Driver does not support user defined port index assignment");
+		return -EOPNOTSUPP;
+	}
+
+	if (new_attr->pfnum != pf->hw.pf_id) {
+		NL_SET_ERR_MSG_MOD(extack, "Incorrect pfnum supplied");
+		return -EINVAL;
+	}
+
+	if (!pci_msix_can_alloc_dyn(pf->pdev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Dynamic MSIX-X interrupt allocation is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_devlink_port_del - devlink handler for port delete
+ * @devlink: pointer to devlink
+ * @port: devlink port to be deleted
+ * @extack: pointer to extack
+ *
+ * Deletes devlink port and deallocates all resources associated with
+ * created subfunction.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_del(struct devlink *devlink, struct devlink_port *port,
+		     struct netlink_ext_ack *extack)
+{
+	struct ice_dynamic_port *dyn_port;
+
+	dyn_port = ice_devlink_port_to_dyn(port);
+	ice_dealloc_dynamic_port(dyn_port);
+
+	return 0;
+}
+
+static const struct devlink_port_ops ice_devlink_port_sf_ops = {
+	.port_del = ice_devlink_port_del,
+};
+
+/**
+ * ice_reserve_sf_num - Reserve a subfunction number for this port
+ * @pf: pointer to the pf structure
+ * @new_attr: devlink port attributes requested
+ * @extack: extack for reporting error messages
+ * @sfnum: on success, the sf number reserved
+ *
+ * Reserve a subfunction number for this port. Only called for
+ * DEVLINK_PORT_FLAVOUR_PCI_SF ports.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_reserve_sf_num(struct ice_pf *pf,
+		   const struct devlink_port_new_attrs *new_attr,
+		   struct netlink_ext_ack *extack, u32 *sfnum)
+{
+	int err;
+
+	/* If user didn't request an explicit number, pick one */
+	if (!new_attr->sfnum_valid)
+		return xa_alloc(&pf->sf_nums, sfnum, NULL, xa_limit_32b,
+				GFP_KERNEL);
+
+	/* Otherwise, check and use the number provided */
+	err = xa_insert(&pf->sf_nums, new_attr->sfnum, NULL, GFP_KERNEL);
+	if (err) {
+		if (err == -EBUSY)
+			NL_SET_ERR_MSG_MOD(extack, "Subfunction with given sfnum already exists");
+		return err;
+	}
+
+	*sfnum = new_attr->sfnum;
+
+	return 0;
+}
+
+/**
+ * ice_devlink_create_sf_port - Register PCI subfunction devlink port
+ * @dyn_port: the dynamic port instance structure for this subfunction
+ *
+ * Register PCI subfunction flavour devlink port for a dynamically added
+ * subfunction port.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_devlink_create_sf_port(struct ice_dynamic_port *dyn_port)
+{
+	struct devlink_port_attrs attrs = {};
+	struct devlink_port *devlink_port;
+	struct devlink *devlink;
+	struct ice_vsi *vsi;
+	struct ice_pf *pf;
+
+	vsi = dyn_port->vsi;
+	pf = dyn_port->pf;
+
+	devlink_port = &dyn_port->devlink_port;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_SF;
+	attrs.pci_sf.pf = pf->hw.pf_id;
+	attrs.pci_sf.sf = dyn_port->sfnum;
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+	devlink = priv_to_devlink(pf);
+
+	return devl_port_register_with_ops(devlink, devlink_port, vsi->idx,
+					   &ice_devlink_port_sf_ops);
+}
+
+/**
+ * ice_devlink_destroy_sf_port - Destroy the devlink_port for this SF
+ * @dyn_port: the dynamic port instance structure for this subfunction
+ *
+ * Unregisters the devlink_port structure associated with this SF.
+ */
+void ice_devlink_destroy_sf_port(struct ice_dynamic_port *dyn_port)
+{
+	devl_port_unregister(&dyn_port->devlink_port);
+}
+
+/**
+ * ice_alloc_dynamic_port - Allocate new dynamic port
+ * @pf: pointer to the pf structure
+ * @new_attr: devlink port attributes requested
+ * @extack: extack for reporting error messages
+ * @devlink_port: index of newly created devlink port
+ *
+ * Allocate a new dynamic port instance and prepare it for configuration
+ * with devlink.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_alloc_dynamic_port(struct ice_pf *pf,
+		       const struct devlink_port_new_attrs *new_attr,
+		       struct netlink_ext_ack *extack,
+		       struct devlink_port **devlink_port)
+{
+	struct ice_dynamic_port *dyn_port;
+	struct ice_vsi *vsi;
+	u32 sfnum;
+	int err;
+
+	err = ice_reserve_sf_num(pf, new_attr, extack, &sfnum);
+	if (err)
+		return err;
+
+	dyn_port = kzalloc(sizeof(*dyn_port), GFP_KERNEL);
+	if (!dyn_port) {
+		err = -ENOMEM;
+		goto unroll_reserve_sf_num;
+	}
+
+	vsi = ice_vsi_alloc(pf);
+	if (!vsi) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to allocate VSI");
+		err = -ENOMEM;
+		goto unroll_dyn_port_alloc;
+	}
+
+	dyn_port->vsi = vsi;
+	dyn_port->pf = pf;
+	dyn_port->sfnum = sfnum;
+	eth_random_addr(dyn_port->hw_addr);
+
+	err = xa_insert(&pf->dyn_ports, vsi->idx, dyn_port, GFP_KERNEL);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Port index reservation failed");
+		goto unroll_vsi_alloc;
+	}
+
+	err = ice_devlink_create_sf_port(dyn_port);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Port registration failed");
+		goto unroll_xa_insert;
+	}
+
+	*devlink_port = &dyn_port->devlink_port;
+
+	return 0;
+
+unroll_xa_insert:
+	xa_erase(&pf->dyn_ports, vsi->idx);
+unroll_vsi_alloc:
+	ice_vsi_free(vsi);
+unroll_dyn_port_alloc:
+	kfree(dyn_port);
+unroll_reserve_sf_num:
+	xa_erase(&pf->sf_nums, sfnum);
+
+	return err;
+}
+
+/**
+ * ice_devlink_port_new - devlink handler for the new port
+ * @devlink: pointer to devlink
+ * @new_attr: pointer to the port new attributes
+ * @extack: extack for reporting error messages
+ * @devlink_port: pointer to a new port
+ *
+ * Creates new devlink port, checks new port attributes and reject
+ * any unsupported parameters, allocates new subfunction for that port.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int
+ice_devlink_port_new(struct devlink *devlink,
+		     const struct devlink_port_new_attrs *new_attr,
+		     struct netlink_ext_ack *extack,
+		     struct devlink_port **devlink_port)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	int err;
+
+	err = ice_devlink_port_new_check_attr(pf, new_attr, extack);
+	if (err)
+		return err;
+
+	return ice_alloc_dynamic_port(pf, new_attr, extack, devlink_port);
+}
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
index 9223bcdb6444..08ebf56664a5 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
@@ -4,9 +4,43 @@
 #ifndef _DEVLINK_PORT_H_
 #define _DEVLINK_PORT_H_
 
+#include "../ice.h"
+
+/**
+ * struct ice_dynamic_port - Track dynamically added devlink port instance
+ * @hw_addr: the HW address for this port
+ * @active: true if the port has been activated
+ * @devlink_port: the associated devlink port structure
+ * @pf: pointer to the PF private structure
+ * @vsi: the VSI associated with this port
+ * @sfnum: the subfunction ID
+ *
+ * An instance of a dynamically added devlink port. Each port flavour
+ */
+struct ice_dynamic_port {
+	u8 hw_addr[ETH_ALEN];
+	u8 active: 1;
+	struct devlink_port devlink_port;
+	struct ice_pf *pf;
+	struct ice_vsi *vsi;
+	u32 sfnum;
+};
+
+void ice_dealloc_all_dynamic_ports(struct ice_pf *pf);
+
 int ice_devlink_create_pf_port(struct ice_pf *pf);
 void ice_devlink_destroy_pf_port(struct ice_pf *pf);
 int ice_devlink_create_vf_port(struct ice_vf *vf);
 void ice_devlink_destroy_vf_port(struct ice_vf *vf);
+int ice_devlink_create_sf_port(struct ice_dynamic_port *dyn_port);
+void ice_devlink_destroy_sf_port(struct ice_dynamic_port *dyn_port);
+
+#define ice_devlink_port_to_dyn(port) \
+	container_of(port, struct ice_dynamic_port, devlink_port)
 
+int
+ice_devlink_port_new(struct devlink *devlink,
+		     const struct devlink_port_new_attrs *new_attr,
+		     struct netlink_ext_ack *extack,
+		     struct devlink_port **devlink_port);
 #endif /* _DEVLINK_PORT_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index e962bdf71204..19ce6ea63ca3 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -652,6 +652,9 @@ struct ice_pf {
 	struct ice_eswitch eswitch;
 	struct ice_esw_br_port *br_port;
 
+	struct xarray dyn_ports;
+	struct xarray sf_nums;
+
 #define ICE_INVALID_AGG_NODE_ID		0
 #define ICE_PF_AGG_NODE_ID_START	1
 #define ICE_MAX_PF_AGG_NODES		32
@@ -918,6 +921,7 @@ int ice_vsi_open(struct ice_vsi *vsi);
 void ice_set_ethtool_ops(struct net_device *netdev);
 void ice_set_ethtool_repr_ops(struct net_device *netdev);
 void ice_set_ethtool_safe_mode_ops(struct net_device *netdev);
+void ice_set_ethtool_sf_ops(struct net_device *netdev);
 u16 ice_get_avail_txq_count(struct ice_pf *pf);
 u16 ice_get_avail_rxq_count(struct ice_pf *pf);
 int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 3038849cd37a..570425772b63 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -7,6 +7,7 @@
 #include "ice_lib.h"
 #include "ice_fltr.h"
 #include "ice_dcb_lib.h"
+#include "ice_type.h"
 #include "ice_vsi_vlan_ops.h"
 
 /**
@@ -432,7 +433,7 @@ err_out:
  * This deallocates the VSI's queue resources, removes it from the PF's
  * VSI array if necessary, and deallocates the VSI
  */
-static void ice_vsi_free(struct ice_vsi *vsi)
+void ice_vsi_free(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = NULL;
 	struct device *dev;
@@ -605,7 +606,7 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
  *
  * returns a pointer to a VSI on success, NULL on failure.
  */
-static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf)
+struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf)
 {
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_vsi *vsi = NULL;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 6c2ac56d1746..1a6cfc8693ce 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -60,6 +60,8 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked);
 
 int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags);
 int ice_vsi_cfg(struct ice_vsi *vsi);
+struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf);
+void ice_vsi_free(struct ice_vsi *vsi);
 
 bool ice_is_reset_in_progress(unsigned long *state);
 int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 53f002153432..b11124fef4b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4004,6 +4004,9 @@ static void ice_deinit_pf(struct ice_pf *pf)
 
 	if (pf->ptp.clock)
 		ptp_clock_unregister(pf->ptp.clock);
+
+	xa_destroy(&pf->dyn_ports);
+	xa_destroy(&pf->sf_nums);
 }
 
 /**
@@ -4097,6 +4100,9 @@ static int ice_init_pf(struct ice_pf *pf)
 	hash_init(pf->vfs.table);
 	ice_mbx_init_snapshot(&pf->hw);
 
+	xa_init(&pf->dyn_ports);
+	xa_init(&pf->sf_nums);
+
 	return 0;
 }
 
@@ -5439,6 +5445,7 @@ static void ice_remove(struct pci_dev *pdev)
 		ice_remove_arfs(pf);
 
 	devl_lock(priv_to_devlink(pf));
+	ice_dealloc_all_dynamic_ports(pf);
 	ice_deinit_devlink(pf);
 
 	ice_unload(pf);
-- 
cgit v1.3-3-g829e


From 747967b0bbfae121d1f474b077001ddb24537259 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:49 +0200
Subject: ice: treat subfunction VSI the same as PF VSI

When subfunction VSI is open the same code as for PF VSI should be
executed. Also when up is complete. Reflect that in code by adding
subfunction VSI to consideration.

In case of stopping, PF doesn't have additional tasks, so the same
is with subfunction VSI.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index b11124fef4b9..c2e56413645a 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -6754,7 +6754,8 @@ static int ice_up_complete(struct ice_vsi *vsi)
 
 	if (vsi->port_info &&
 	    (vsi->port_info->phy.link_info.link_info & ICE_AQ_LINK_UP) &&
-	    vsi->netdev && vsi->type == ICE_VSI_PF) {
+	    ((vsi->netdev && (vsi->type == ICE_VSI_PF ||
+			      vsi->type == ICE_VSI_SF)))) {
 		ice_print_link_msg(vsi, true);
 		netif_tx_start_all_queues(vsi->netdev);
 		netif_carrier_on(vsi->netdev);
@@ -7452,7 +7453,7 @@ int ice_vsi_open(struct ice_vsi *vsi)
 
 	ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc);
 
-	if (vsi->type == ICE_VSI_PF) {
+	if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_SF) {
 		/* Notify the stack of the actual queue counts. */
 		err = netif_set_real_num_tx_queues(vsi->netdev, vsi->num_txq);
 		if (err)
-- 
cgit v1.3-3-g829e


From f43e3be662e6e75352e0242e2a58c936d7a9a65f Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:57:50 +0200
Subject: ice: allocate devlink for subfunction

Allocate devlink for subfunction instance.

Create header file for subfunction device. Define subfunction device
structure there as it is needed for devlink allocation.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c | 31 ++++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/devlink/devlink.h |  1 +
 drivers/net/ethernet/intel/ice/ice_sf_eth.h      | 15 ++++++++++++
 3 files changed, 47 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_eth.h

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index b7eb1b56f2c6..445538959459 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -10,6 +10,7 @@
 #include "ice_eswitch.h"
 #include "ice_fw_update.h"
 #include "ice_dcb_lib.h"
+#include "ice_sf_eth.h"
 
 /* context for devlink info version reporting */
 struct ice_info_ctx {
@@ -1282,6 +1283,8 @@ static const struct devlink_ops ice_devlink_ops = {
 	.port_new = ice_devlink_port_new,
 };
 
+static const struct devlink_ops ice_sf_devlink_ops;
+
 static int
 ice_devlink_enable_roce_get(struct devlink *devlink, u32 id,
 			    struct devlink_param_gset_ctx *ctx)
@@ -1564,6 +1567,34 @@ struct ice_pf *ice_allocate_pf(struct device *dev)
 	return devlink_priv(devlink);
 }
 
+/**
+ * ice_allocate_sf - Allocate devlink and return SF structure pointer
+ * @dev: the device to allocate for
+ * @pf: pointer to the PF structure
+ *
+ * Allocate a devlink instance for SF.
+ *
+ * Return: ice_sf_priv pointer to allocated memory or ERR_PTR in case of error
+ */
+struct ice_sf_priv *ice_allocate_sf(struct device *dev, struct ice_pf *pf)
+{
+	struct devlink *devlink;
+	int err;
+
+	devlink = devlink_alloc(&ice_sf_devlink_ops, sizeof(struct ice_sf_priv),
+				dev);
+	if (!devlink)
+		return ERR_PTR(-ENOMEM);
+
+	err = devl_nested_devlink_set(priv_to_devlink(pf), devlink);
+	if (err) {
+		devlink_free(devlink);
+		return ERR_PTR(err);
+	}
+
+	return devlink_priv(devlink);
+}
+
 /**
  * ice_devlink_register - Register devlink interface for this PF
  * @pf: the PF to register the devlink for.
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.h b/drivers/net/ethernet/intel/ice/devlink/devlink.h
index d291c0e2e17b..1af3b0763fbb 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.h
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.h
@@ -5,6 +5,7 @@
 #define _ICE_DEVLINK_H_
 
 struct ice_pf *ice_allocate_pf(struct device *dev);
+struct ice_sf_priv *ice_allocate_sf(struct device *dev, struct ice_pf *pf);
 
 void ice_devlink_register(struct ice_pf *pf);
 void ice_devlink_unregister(struct ice_pf *pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.h b/drivers/net/ethernet/intel/ice/ice_sf_eth.h
new file mode 100644
index 000000000000..267da33a0135
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024, Intel Corporation. */
+
+#ifndef _ICE_SF_ETH_H_
+#define _ICE_SF_ETH_H_
+
+#include <linux/auxiliary_bus.h>
+#include "ice.h"
+
+struct ice_sf_priv {
+	struct ice_sf_dev *dev;
+	struct devlink_port devlink_port;
+};
+
+#endif /* _ICE_SF_ETH_H_ */
-- 
cgit v1.3-3-g829e


From 177ef7f1e2a051e8962048ffd41973d29be3302c Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:57:51 +0200
Subject: ice: base subfunction aux driver

Implement subfunction driver. It is probe when subfunction port is
activated.

VSI is already created. During the probe VSI is being configured.
MAC unicast and broadcast filter is added to allow traffic to pass.

Store subfunction pointer in VSI struct. The same is done for VF
pointer. Make union of subfunction and VF pointer as only one of them
can be set with one VSI.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile            |   1 +
 .../net/ethernet/intel/ice/devlink/devlink_port.c  |  41 ++++++
 .../net/ethernet/intel/ice/devlink/devlink_port.h  |   3 +
 drivers/net/ethernet/intel/ice/ice.h               |   7 +-
 drivers/net/ethernet/intel/ice/ice_main.c          |  10 ++
 drivers/net/ethernet/intel/ice/ice_sf_eth.c        | 139 +++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_sf_eth.h        |  15 +++
 7 files changed, 215 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_eth.c

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index b4f6fa4ba13d..81acb590eac6 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -33,6 +33,7 @@ ice-y := ice_main.o	\
 	 ice_idc.o	\
 	 devlink/devlink.o	\
 	 devlink/devlink_port.o \
+	 ice_sf_eth.o	\
 	 ice_ddp.o	\
 	 ice_fw_update.o \
 	 ice_lag.o	\
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 6202568a3e05..9abd31e44df5 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -489,6 +489,47 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf)
 	devl_port_unregister(&vf->devlink_port);
 }
 
+/**
+ * ice_devlink_create_sf_dev_port - Register virtual port for a subfunction
+ * @sf_dev: the subfunction device to create a devlink port for
+ *
+ * Register virtual flavour devlink port for the subfunction auxiliary device
+ * created after activating a dynamically added devlink port.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_devlink_create_sf_dev_port(struct ice_sf_dev *sf_dev)
+{
+	struct devlink_port_attrs attrs = {};
+	struct ice_dynamic_port *dyn_port;
+	struct devlink_port *devlink_port;
+	struct devlink *devlink;
+	struct ice_vsi *vsi;
+
+	dyn_port = sf_dev->dyn_port;
+	vsi = dyn_port->vsi;
+
+	devlink_port = &sf_dev->priv->devlink_port;
+
+	attrs.flavour = DEVLINK_PORT_FLAVOUR_VIRTUAL;
+
+	devlink_port_attrs_set(devlink_port, &attrs);
+	devlink = priv_to_devlink(sf_dev->priv);
+
+	return devl_port_register(devlink, devlink_port, vsi->idx);
+}
+
+/**
+ * ice_devlink_destroy_sf_dev_port - Destroy virtual port for a subfunction
+ * @sf_dev: the subfunction device to create a devlink port for
+ *
+ * Unregisters the virtual port associated with this subfunction.
+ */
+void ice_devlink_destroy_sf_dev_port(struct ice_sf_dev *sf_dev)
+{
+	devl_port_unregister(&sf_dev->priv->devlink_port);
+}
+
 /**
  * ice_dealloc_dynamic_port - Deallocate and remove a dynamic port
  * @dyn_port: dynamic port instance to deallocate
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
index 08ebf56664a5..97b21b58c300 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
@@ -5,6 +5,7 @@
 #define _DEVLINK_PORT_H_
 
 #include "../ice.h"
+#include "../ice_sf_eth.h"
 
 /**
  * struct ice_dynamic_port - Track dynamically added devlink port instance
@@ -34,6 +35,8 @@ int ice_devlink_create_vf_port(struct ice_vf *vf);
 void ice_devlink_destroy_vf_port(struct ice_vf *vf);
 int ice_devlink_create_sf_port(struct ice_dynamic_port *dyn_port);
 void ice_devlink_destroy_sf_port(struct ice_dynamic_port *dyn_port);
+int ice_devlink_create_sf_dev_port(struct ice_sf_dev *sf_dev);
+void ice_devlink_destroy_sf_dev_port(struct ice_sf_dev *sf_dev);
 
 #define ice_devlink_port_to_dyn(port) \
 	container_of(port, struct ice_dynamic_port, devlink_port)
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 19ce6ea63ca3..d6f80da30dec 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -451,7 +451,12 @@ struct ice_vsi {
 	struct_group_tagged(ice_vsi_cfg_params, params,
 		struct ice_port_info *port_info; /* back pointer to port_info */
 		struct ice_channel *ch; /* VSI's channel structure, may be NULL */
-		struct ice_vf *vf; /* VF associated with this VSI, may be NULL */
+		union {
+			/* VF associated with this VSI, may be NULL */
+			struct ice_vf *vf;
+			/* SF associated with this VSI, may be NULL */
+			struct ice_dynamic_port *sf;
+		};
 		u32 flags; /* VSI flags used for rebuild and configuration */
 		enum ice_vsi_type type; /* the type of the VSI */
 	);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c2e56413645a..59c0e88153c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -15,6 +15,7 @@
 #include "ice_dcb_nl.h"
 #include "devlink/devlink.h"
 #include "devlink/devlink_port.h"
+#include "ice_sf_eth.h"
 #include "ice_hwmon.h"
 /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the
  * ice tracepoint functions. This must be done exactly once across the
@@ -5934,8 +5935,16 @@ static int __init ice_module_init(void)
 		goto err_dest_lag_wq;
 	}
 
+	status = ice_sf_driver_register();
+	if (status) {
+		pr_err("Failed to register SF driver, err %d\n", status);
+		goto err_sf_driver;
+	}
+
 	return 0;
 
+err_sf_driver:
+	pci_unregister_driver(&ice_driver);
 err_dest_lag_wq:
 	destroy_workqueue(ice_lag_wq);
 	ice_debugfs_exit();
@@ -5953,6 +5962,7 @@ module_init(ice_module_init);
  */
 static void __exit ice_module_exit(void)
 {
+	ice_sf_driver_unregister();
 	pci_unregister_driver(&ice_driver);
 	ice_debugfs_exit();
 	destroy_workqueue(ice_wq);
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
new file mode 100644
index 000000000000..02556f72b831
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Intel Corporation. */
+#include "ice.h"
+#include "ice_lib.h"
+#include "ice_fltr.h"
+#include "ice_sf_eth.h"
+#include "devlink/devlink_port.h"
+#include "devlink/devlink.h"
+
+/**
+ * ice_sf_dev_probe - subfunction driver probe function
+ * @adev: pointer to the auxiliary device
+ * @id: pointer to the auxiliary_device id
+ *
+ * Configure VSI and netdev resources for the subfunction device.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int ice_sf_dev_probe(struct auxiliary_device *adev,
+			    const struct auxiliary_device_id *id)
+{
+	struct ice_sf_dev *sf_dev = ice_adev_to_sf_dev(adev);
+	struct ice_dynamic_port *dyn_port = sf_dev->dyn_port;
+	struct ice_vsi *vsi = dyn_port->vsi;
+	struct ice_pf *pf = dyn_port->pf;
+	struct device *dev = &adev->dev;
+	struct ice_sf_priv *priv;
+	struct devlink *devlink;
+	int err;
+
+	vsi->type = ICE_VSI_SF;
+	vsi->port_info = pf->hw.port_info;
+	vsi->flags = ICE_VSI_FLAG_INIT;
+
+	priv = ice_allocate_sf(&adev->dev, pf);
+	if (!priv) {
+		dev_err(dev, "Subfunction devlink alloc failed");
+		return -ENOMEM;
+	}
+
+	priv->dev = sf_dev;
+	sf_dev->priv = priv;
+	devlink = priv_to_devlink(priv);
+
+	devl_lock(devlink);
+
+	err = ice_vsi_cfg(vsi);
+	if (err) {
+		dev_err(dev, "Subfunction vsi config failed");
+		goto err_free_devlink;
+	}
+	vsi->sf = dyn_port;
+
+	err = ice_devlink_create_sf_dev_port(sf_dev);
+	if (err) {
+		dev_err(dev, "Cannot add ice virtual devlink port for subfunction");
+		goto err_vsi_decfg;
+	}
+
+	err = devl_port_fn_devlink_set(&dyn_port->devlink_port, devlink);
+	if (err) {
+		dev_err(dev, "Can't link devlink instance to SF devlink port");
+		goto err_devlink_destroy;
+	}
+
+	ice_napi_add(vsi);
+
+	devl_register(devlink);
+	devl_unlock(devlink);
+
+	return 0;
+
+err_devlink_destroy:
+	ice_devlink_destroy_sf_dev_port(sf_dev);
+err_vsi_decfg:
+	ice_vsi_decfg(vsi);
+err_free_devlink:
+	devl_unlock(devlink);
+	devlink_free(devlink);
+	return err;
+}
+
+/**
+ * ice_sf_dev_remove - subfunction driver remove function
+ * @adev: pointer to the auxiliary device
+ *
+ * Deinitalize VSI and netdev resources for the subfunction device.
+ */
+static void ice_sf_dev_remove(struct auxiliary_device *adev)
+{
+	struct ice_sf_dev *sf_dev = ice_adev_to_sf_dev(adev);
+	struct ice_dynamic_port *dyn_port = sf_dev->dyn_port;
+	struct ice_vsi *vsi = dyn_port->vsi;
+	struct devlink *devlink;
+
+	devlink = priv_to_devlink(sf_dev->priv);
+	devl_lock(devlink);
+
+	ice_vsi_close(vsi);
+
+	ice_devlink_destroy_sf_dev_port(sf_dev);
+	devl_unregister(devlink);
+	devl_unlock(devlink);
+	devlink_free(devlink);
+	ice_vsi_decfg(vsi);
+}
+
+static const struct auxiliary_device_id ice_sf_dev_id_table[] = {
+	{ .name = "ice.sf", },
+	{ },
+};
+
+MODULE_DEVICE_TABLE(auxiliary, ice_sf_dev_id_table);
+
+static struct auxiliary_driver ice_sf_driver = {
+	.name = "sf",
+	.probe = ice_sf_dev_probe,
+	.remove = ice_sf_dev_remove,
+	.id_table = ice_sf_dev_id_table
+};
+
+/**
+ * ice_sf_driver_register - Register new auxiliary subfunction driver
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_sf_driver_register(void)
+{
+	return auxiliary_driver_register(&ice_sf_driver);
+}
+
+/**
+ * ice_sf_driver_unregister - Unregister new auxiliary subfunction driver
+ *
+ */
+void ice_sf_driver_unregister(void)
+{
+	auxiliary_driver_unregister(&ice_sf_driver);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.h b/drivers/net/ethernet/intel/ice/ice_sf_eth.h
index 267da33a0135..e972c50f96c9 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.h
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.h
@@ -7,9 +7,24 @@
 #include <linux/auxiliary_bus.h>
 #include "ice.h"
 
+struct ice_sf_dev {
+	struct auxiliary_device adev;
+	struct ice_dynamic_port *dyn_port;
+	struct ice_sf_priv *priv;
+};
+
 struct ice_sf_priv {
 	struct ice_sf_dev *dev;
 	struct devlink_port devlink_port;
 };
 
+static inline struct
+ice_sf_dev *ice_adev_to_sf_dev(struct auxiliary_device *adev)
+{
+	return container_of(adev, struct ice_sf_dev, adev);
+}
+
+int ice_sf_driver_register(void);
+void ice_sf_driver_unregister(void);
+
 #endif /* _ICE_SF_ETH_H_ */
-- 
cgit v1.3-3-g829e


From 8f9b681adb4437c8b2d1ad998d66b79558bc900a Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:57:52 +0200
Subject: ice: implement netdev for subfunction

Configure netdevice for subfunction usecase. Mostly it is reusing ops
from the PF netdevice.

SF netdev is linked to devlink port registered after SF activation.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_sf_eth.c | 86 ++++++++++++++++++++++++++++-
 1 file changed, 85 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index 02556f72b831..05d9e7384c5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -2,11 +2,86 @@
 /* Copyright (c) 2024, Intel Corporation. */
 #include "ice.h"
 #include "ice_lib.h"
+#include "ice_txrx.h"
 #include "ice_fltr.h"
 #include "ice_sf_eth.h"
 #include "devlink/devlink_port.h"
 #include "devlink/devlink.h"
 
+static const struct net_device_ops ice_sf_netdev_ops = {
+	.ndo_open = ice_open,
+	.ndo_stop = ice_stop,
+	.ndo_start_xmit = ice_start_xmit,
+	.ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid,
+	.ndo_change_mtu = ice_change_mtu,
+	.ndo_get_stats64 = ice_get_stats64,
+	.ndo_tx_timeout = ice_tx_timeout,
+	.ndo_bpf = ice_xdp,
+	.ndo_xdp_xmit = ice_xdp_xmit,
+	.ndo_xsk_wakeup = ice_xsk_wakeup,
+};
+
+/**
+ * ice_sf_cfg_netdev - Allocate, configure and register a netdev
+ * @dyn_port: subfunction associated with configured netdev
+ * @devlink_port: subfunction devlink port to be linked with netdev
+ *
+ * Return: 0 on success, negative value on failure
+ */
+static int ice_sf_cfg_netdev(struct ice_dynamic_port *dyn_port,
+			     struct devlink_port *devlink_port)
+{
+	struct ice_vsi *vsi = dyn_port->vsi;
+	struct ice_netdev_priv *np;
+	struct net_device *netdev;
+	int err;
+
+	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
+				    vsi->alloc_rxq);
+	if (!netdev)
+		return -ENOMEM;
+
+	SET_NETDEV_DEV(netdev, &vsi->back->pdev->dev);
+	set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
+	vsi->netdev = netdev;
+	np = netdev_priv(netdev);
+	np->vsi = vsi;
+
+	ice_set_netdev_features(netdev);
+
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+			       NETDEV_XDP_ACT_XSK_ZEROCOPY |
+			       NETDEV_XDP_ACT_RX_SG;
+	netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD;
+
+	eth_hw_addr_set(netdev, dyn_port->hw_addr);
+	ether_addr_copy(netdev->perm_addr, dyn_port->hw_addr);
+	netdev->netdev_ops = &ice_sf_netdev_ops;
+	SET_NETDEV_DEVLINK_PORT(netdev, devlink_port);
+
+	err = register_netdev(netdev);
+	if (err) {
+		free_netdev(netdev);
+		vsi->netdev = NULL;
+		return -ENOMEM;
+	}
+	set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
+	netif_carrier_off(netdev);
+	netif_tx_stop_all_queues(netdev);
+
+	return 0;
+}
+
+static void ice_sf_decfg_netdev(struct ice_vsi *vsi)
+{
+	unregister_netdev(vsi->netdev);
+	clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state);
+	free_netdev(vsi->netdev);
+	vsi->netdev = NULL;
+	clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state);
+}
+
 /**
  * ice_sf_dev_probe - subfunction driver probe function
  * @adev: pointer to the auxiliary device
@@ -57,10 +132,16 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev,
 		goto err_vsi_decfg;
 	}
 
+	err = ice_sf_cfg_netdev(dyn_port, &sf_dev->priv->devlink_port);
+	if (err) {
+		dev_err(dev, "Subfunction netdev config failed");
+		goto err_devlink_destroy;
+	}
+
 	err = devl_port_fn_devlink_set(&dyn_port->devlink_port, devlink);
 	if (err) {
 		dev_err(dev, "Can't link devlink instance to SF devlink port");
-		goto err_devlink_destroy;
+		goto err_netdev_decfg;
 	}
 
 	ice_napi_add(vsi);
@@ -70,6 +151,8 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev,
 
 	return 0;
 
+err_netdev_decfg:
+	ice_sf_decfg_netdev(vsi);
 err_devlink_destroy:
 	ice_devlink_destroy_sf_dev_port(sf_dev);
 err_vsi_decfg:
@@ -98,6 +181,7 @@ static void ice_sf_dev_remove(struct auxiliary_device *adev)
 
 	ice_vsi_close(vsi);
 
+	ice_sf_decfg_netdev(vsi);
 	ice_devlink_destroy_sf_dev_port(sf_dev);
 	devl_unregister(devlink);
 	devl_unlock(devlink);
-- 
cgit v1.3-3-g829e


From 415db8399d06a45ebd7b7d26b951f831a4b01801 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:53 +0200
Subject: ice: make representor code generic

Keep the same flow of port representor creation, but instead of general
attach function create helpers for specific representor type.

Store function pointer for add and remove representor.

Type of port representor can be also known based on VSI type, but it
is more clean to have it directly saved in port representor structure.

Add devlink lock for whole port representor creation and destruction.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/devlink/devlink_port.h  |  2 +
 drivers/net/ethernet/intel/ice/ice_eswitch.c       | 72 +++++++++++++-----
 drivers/net/ethernet/intel/ice/ice_eswitch.h       | 11 +--
 drivers/net/ethernet/intel/ice/ice_repr.c          | 88 +++++++++++-----------
 drivers/net/ethernet/intel/ice/ice_repr.h          | 16 +++-
 drivers/net/ethernet/intel/ice/ice_sriov.c         |  4 +-
 drivers/net/ethernet/intel/ice/ice_vf_lib.c        |  4 +-
 7 files changed, 121 insertions(+), 76 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
index 97b21b58c300..479d2b976745 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
@@ -14,6 +14,7 @@
  * @devlink_port: the associated devlink port structure
  * @pf: pointer to the PF private structure
  * @vsi: the VSI associated with this port
+ * @repr_id: the representor ID
  * @sfnum: the subfunction ID
  *
  * An instance of a dynamically added devlink port. Each port flavour
@@ -24,6 +25,7 @@ struct ice_dynamic_port {
 	struct devlink_port devlink_port;
 	struct ice_pf *pf;
 	struct ice_vsi *vsi;
+	unsigned long repr_id;
 	u32 sfnum;
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 3cfa071e3718..00d49477bdcb 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -452,11 +452,9 @@ static void ice_eswitch_start_reprs(struct ice_pf *pf)
 	ice_eswitch_start_all_tx_queues(pf);
 }
 
-int
-ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
+static int
+ice_eswitch_attach(struct ice_pf *pf, struct ice_repr *repr, unsigned long *id)
 {
-	struct devlink *devlink = priv_to_devlink(pf);
-	struct ice_repr *repr;
 	int err;
 
 	if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_LEGACY)
@@ -470,13 +468,9 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 
 	ice_eswitch_stop_reprs(pf);
 
-	devl_lock(devlink);
-	repr = ice_repr_add_vf(vf);
-	devl_unlock(devlink);
-	if (IS_ERR(repr)) {
-		err = PTR_ERR(repr);
+	err = repr->ops.add(repr);
+	if (err)
 		goto err_create_repr;
-	}
 
 	err = ice_eswitch_setup_repr(pf, repr);
 	if (err)
@@ -486,7 +480,7 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 	if (err)
 		goto err_xa_alloc;
 
-	vf->repr_id = repr->id;
+	*id = repr->id;
 
 	ice_eswitch_start_reprs(pf);
 
@@ -495,9 +489,7 @@ ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
 err_xa_alloc:
 	ice_eswitch_release_repr(pf, repr);
 err_setup_repr:
-	devl_lock(devlink);
-	ice_repr_rem_vf(repr);
-	devl_unlock(devlink);
+	repr->ops.rem(repr);
 err_create_repr:
 	if (xa_empty(&pf->eswitch.reprs))
 		ice_eswitch_disable_switchdev(pf);
@@ -506,14 +498,35 @@ err_create_repr:
 	return err;
 }
 
-void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
+/**
+ * ice_eswitch_attach_vf - attach VF to a eswitch
+ * @pf: pointer to PF structure
+ * @vf: pointer to VF structure to be attached
+ *
+ * During attaching port representor for VF is created.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id);
+	struct ice_repr *repr = ice_repr_create_vf(vf);
 	struct devlink *devlink = priv_to_devlink(pf);
+	int err;
 
-	if (!repr)
-		return;
+	if (IS_ERR(repr))
+		return PTR_ERR(repr);
 
+	devl_lock(devlink);
+	err = ice_eswitch_attach(pf, repr, &vf->repr_id);
+	if (err)
+		ice_repr_destroy(repr);
+	devl_unlock(devlink);
+
+	return err;
+}
+
+static void ice_eswitch_detach(struct ice_pf *pf, struct ice_repr *repr)
+{
 	ice_eswitch_stop_reprs(pf);
 	xa_erase(&pf->eswitch.reprs, repr->id);
 
@@ -521,10 +534,12 @@ void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
 		ice_eswitch_disable_switchdev(pf);
 
 	ice_eswitch_release_repr(pf, repr);
-	devl_lock(devlink);
-	ice_repr_rem_vf(repr);
+	repr->ops.rem(repr);
+	ice_repr_destroy(repr);
 
 	if (xa_empty(&pf->eswitch.reprs)) {
+		struct devlink *devlink = priv_to_devlink(pf);
+
 		/* since all port representors are destroyed, there is
 		 * no point in keeping the nodes
 		 */
@@ -533,6 +548,23 @@ void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf)
 	} else {
 		ice_eswitch_start_reprs(pf);
 	}
+}
+
+/**
+ * ice_eswitch_detach_vf - detach VF from a eswitch
+ * @pf: pointer to PF structure
+ * @vf: pointer to VF structure to be detached
+ */
+void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf)
+{
+	struct ice_repr *repr = xa_load(&pf->eswitch.reprs, vf->repr_id);
+	struct devlink *devlink = priv_to_devlink(pf);
+
+	if (!repr)
+		return;
+
+	devl_lock(devlink);
+	ice_eswitch_detach(pf, repr);
 	devl_unlock(devlink);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h
index 78fd39a6935d..d1699954a7ad 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h
@@ -5,11 +5,11 @@
 #define _ICE_ESWITCH_H_
 
 #include <net/devlink.h>
+#include "devlink/devlink_port.h"
 
 #ifdef CONFIG_ICE_SWITCHDEV
-void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf);
-int
-ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf);
+void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf);
+int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf);
 
 int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int
@@ -31,10 +31,11 @@ struct net_device *ice_eswitch_get_target(struct ice_rx_ring *rx_ring,
 int ice_eswitch_cfg_vsi(struct ice_vsi *vsi, const u8 *mac);
 void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac);
 #else /* CONFIG_ICE_SWITCHDEV */
-static inline void ice_eswitch_detach(struct ice_pf *pf, struct ice_vf *vf) { }
+static inline void
+ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf) { }
 
 static inline int
-ice_eswitch_attach(struct ice_pf *pf, struct ice_vf *vf)
+ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index bdda3401e343..5d71f623b1e0 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -283,34 +283,23 @@ ice_repr_reg_netdev(struct net_device *netdev)
 	return register_netdev(netdev);
 }
 
-static void ice_repr_remove_node(struct devlink_port *devlink_port)
-{
-	devl_rate_leaf_destroy(devlink_port);
-}
-
 /**
- * ice_repr_rem - remove representor from VF
+ * ice_repr_destroy - remove representor from VF
  * @repr: pointer to representor structure
  */
-static void ice_repr_rem(struct ice_repr *repr)
+void ice_repr_destroy(struct ice_repr *repr)
 {
 	free_percpu(repr->stats);
 	free_netdev(repr->netdev);
 	kfree(repr);
 }
 
-/**
- * ice_repr_rem_vf - remove representor from VF
- * @repr: pointer to representor structure
- */
-void ice_repr_rem_vf(struct ice_repr *repr)
+static void ice_repr_rem_vf(struct ice_repr *repr)
 {
-	ice_repr_remove_node(&repr->vf->devlink_port);
 	ice_eswitch_decfg_vsi(repr->src_vsi, repr->parent_mac);
 	unregister_netdev(repr->netdev);
 	ice_devlink_destroy_vf_port(repr->vf);
 	ice_virtchnl_set_dflt_ops(repr->vf);
-	ice_repr_rem(repr);
 }
 
 static void ice_repr_set_tx_topology(struct ice_pf *pf)
@@ -327,13 +316,10 @@ static void ice_repr_set_tx_topology(struct ice_pf *pf)
 }
 
 /**
- * ice_repr_add - add representor for generic VSI
- * @pf: pointer to PF structure
+ * ice_repr_create - add representor for generic VSI
  * @src_vsi: pointer to VSI structure of device to represent
- * @parent_mac: device MAC address
  */
-static struct ice_repr *
-ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac)
+static struct ice_repr *ice_repr_create(struct ice_vsi *src_vsi)
 {
 	struct ice_netdev_priv *np;
 	struct ice_repr *repr;
@@ -360,7 +346,10 @@ ice_repr_add(struct ice_pf *pf, struct ice_vsi *src_vsi, const u8 *parent_mac)
 	np = netdev_priv(repr->netdev);
 	np->repr = repr;
 
-	ether_addr_copy(repr->parent_mac, parent_mac);
+	repr->netdev->min_mtu = ETH_MIN_MTU;
+	repr->netdev->max_mtu = ICE_MAX_MTU;
+
+	SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(src_vsi->back));
 
 	return repr;
 
@@ -371,32 +360,15 @@ err_alloc:
 	return ERR_PTR(err);
 }
 
-struct ice_repr *ice_repr_add_vf(struct ice_vf *vf)
+static int ice_repr_add_vf(struct ice_repr *repr)
 {
-	struct ice_repr *repr;
-	struct ice_vsi *vsi;
+	struct ice_vf *vf = repr->vf;
 	int err;
 
-	vsi = ice_get_vf_vsi(vf);
-	if (!vsi)
-		return ERR_PTR(-ENOENT);
-
 	err = ice_devlink_create_vf_port(vf);
 	if (err)
-		return ERR_PTR(err);
-
-	repr = ice_repr_add(vf->pf, vsi, vf->hw_lan_addr);
-	if (IS_ERR(repr)) {
-		err = PTR_ERR(repr);
-		goto err_repr_add;
-	}
-
-	repr->vf = vf;
+		return err;
 
-	repr->netdev->min_mtu = ETH_MIN_MTU;
-	repr->netdev->max_mtu = ICE_MAX_MTU;
-
-	SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(vf->pf));
 	SET_NETDEV_DEVLINK_PORT(repr->netdev, &vf->devlink_port);
 	err = ice_repr_reg_netdev(repr->netdev);
 	if (err)
@@ -409,15 +381,43 @@ struct ice_repr *ice_repr_add_vf(struct ice_vf *vf)
 	ice_virtchnl_set_repr_ops(vf);
 	ice_repr_set_tx_topology(vf->pf);
 
-	return repr;
+	return 0;
 
 err_cfg_vsi:
 	unregister_netdev(repr->netdev);
 err_netdev:
-	ice_repr_rem(repr);
-err_repr_add:
 	ice_devlink_destroy_vf_port(vf);
-	return ERR_PTR(err);
+	return err;
+}
+
+/**
+ * ice_repr_create_vf - add representor for VF VSI
+ * @vf: VF to create port representor on
+ *
+ * Set correct representor type for VF and functions pointer.
+ *
+ * Return: created port representor on success, error otherwise
+ */
+struct ice_repr *ice_repr_create_vf(struct ice_vf *vf)
+{
+	struct ice_vsi *vsi = ice_get_vf_vsi(vf);
+	struct ice_repr *repr;
+
+	if (!vsi)
+		return ERR_PTR(-EINVAL);
+
+	repr = ice_repr_create(vsi);
+	if (!repr)
+		return ERR_PTR(-ENOMEM);
+
+	repr->type = ICE_REPR_TYPE_VF;
+	repr->vf = vf;
+	repr->ops.add = ice_repr_add_vf;
+	repr->ops.rem = ice_repr_rem_vf;
+
+	ether_addr_copy(repr->parent_mac, vf->hw_lan_addr);
+
+	return repr;
 }
 
 struct ice_repr *ice_repr_get(struct ice_pf *pf, u32 id)
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h
index 488661b2900b..c6e77b9c6a32 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.h
+++ b/drivers/net/ethernet/intel/ice/ice_repr.h
@@ -15,19 +15,29 @@ struct ice_repr_pcpu_stats {
 	u64 tx_drops;
 };
 
+enum ice_repr_type {
+	ICE_REPR_TYPE_VF,
+};
+
 struct ice_repr {
 	struct ice_vsi *src_vsi;
-	struct ice_vf *vf;
 	struct net_device *netdev;
 	struct metadata_dst *dst;
 	struct ice_esw_br_port *br_port;
 	struct ice_repr_pcpu_stats __percpu *stats;
 	u32 id;
 	u8 parent_mac[ETH_ALEN];
+	enum ice_repr_type type;
+	struct ice_vf *vf;
+	struct {
+		int (*add)(struct ice_repr *repr);
+		void (*rem)(struct ice_repr *repr);
+	} ops;
 };
 
-struct ice_repr *ice_repr_add_vf(struct ice_vf *vf);
-void ice_repr_rem_vf(struct ice_repr *repr);
+struct ice_repr *ice_repr_create_vf(struct ice_vf *vf);
+
+void ice_repr_destroy(struct ice_repr *repr);
 
 void ice_repr_start_tx_queues(struct ice_repr *repr);
 void ice_repr_stop_tx_queues(struct ice_repr *repr);
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 55ef33208456..e34fe2516ccc 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -175,7 +175,7 @@ void ice_free_vfs(struct ice_pf *pf)
 	ice_for_each_vf(pf, bkt, vf) {
 		mutex_lock(&vf->cfg_lock);
 
-		ice_eswitch_detach(pf, vf);
+		ice_eswitch_detach_vf(pf, vf);
 		ice_dis_vf_qs(vf);
 
 		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
@@ -598,7 +598,7 @@ static int ice_start_vfs(struct ice_pf *pf)
 			goto teardown;
 		}
 
-		retval = ice_eswitch_attach(pf, vf);
+		retval = ice_eswitch_attach_vf(pf, vf);
 		if (retval) {
 			dev_err(ice_pf_to_dev(pf), "Failed to attach VF %d to eswitch, error %d",
 				vf->vf_id, retval);
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index 5635e9da2212..a69e91f88d81 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -766,7 +766,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)
 	ice_for_each_vf(pf, bkt, vf) {
 		mutex_lock(&vf->cfg_lock);
 
-		ice_eswitch_detach(pf, vf);
+		ice_eswitch_detach_vf(pf, vf);
 		vf->driver_caps = 0;
 		ice_vc_set_default_allowlist(vf);
 
@@ -782,7 +782,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)
 		ice_vf_rebuild_vsi(vf);
 		ice_vf_post_vsi_rebuild(vf);
 
-		ice_eswitch_attach(pf, vf);
+		ice_eswitch_attach_vf(pf, vf);
 
 		mutex_unlock(&vf->cfg_lock);
 	}
-- 
cgit v1.3-3-g829e


From 977514fb0fa84ca199262b1a9c1d6f3d8175e775 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:54 +0200
Subject: ice: create port representor for SF

Implement attaching and detaching SF port representor. It is done in the
same way as the VF port representor.

SF port representor is always added or removed with devlink
lock taken.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/devlink/devlink_port.c  |  6 +--
 drivers/net/ethernet/intel/ice/ice_eswitch.c       | 39 ++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_eswitch.h       | 11 +++++
 drivers/net/ethernet/intel/ice/ice_repr.c          | 52 ++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_repr.h          |  7 ++-
 drivers/net/ethernet/intel/ice/ice_sf_eth.c        |  2 +
 6 files changed, 113 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 9abd31e44df5..dc62046e26b7 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -543,7 +543,7 @@ static void ice_dealloc_dynamic_port(struct ice_dynamic_port *dyn_port)
 	struct ice_pf *pf = dyn_port->pf;
 
 	xa_erase(&pf->sf_nums, devlink_port->attrs.pci_sf.sf);
-	devl_port_unregister(devlink_port);
+	ice_eswitch_detach_sf(pf, dyn_port);
 	ice_vsi_free(dyn_port->vsi);
 	xa_erase(&pf->dyn_ports, dyn_port->vsi->idx);
 	kfree(dyn_port);
@@ -765,9 +765,9 @@ ice_alloc_dynamic_port(struct ice_pf *pf,
 		goto unroll_vsi_alloc;
 	}
 
-	err = ice_devlink_create_sf_port(dyn_port);
+	err = ice_eswitch_attach_sf(pf, dyn_port);
 	if (err) {
-		NL_SET_ERR_MSG_MOD(extack, "Port registration failed");
+		NL_SET_ERR_MSG_MOD(extack, "Failed to attach SF to eswitch");
 		goto unroll_xa_insert;
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 00d49477bdcb..c0b3e70a7ea3 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -525,6 +525,30 @@ int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 	return err;
 }
 
+/**
+ * ice_eswitch_attach_sf - attach SF to a eswitch
+ * @pf: pointer to PF structure
+ * @sf: pointer to SF structure to be attached
+ *
+ * During attaching port representor for SF is created.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf)
+{
+	struct ice_repr *repr = ice_repr_create_sf(sf);
+	int err;
+
+	if (IS_ERR(repr))
+		return PTR_ERR(repr);
+
+	err = ice_eswitch_attach(pf, repr, &sf->repr_id);
+	if (err)
+		ice_repr_destroy(repr);
+
+	return err;
+}
+
 static void ice_eswitch_detach(struct ice_pf *pf, struct ice_repr *repr)
 {
 	ice_eswitch_stop_reprs(pf);
@@ -568,6 +592,21 @@ void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf)
 	devl_unlock(devlink);
 }
 
+/**
+ * ice_eswitch_detach_sf - detach SF from a eswitch
+ * @pf: pointer to PF structure
+ * @sf: pointer to SF structure to be detached
+ */
+void ice_eswitch_detach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf)
+{
+	struct ice_repr *repr = xa_load(&pf->eswitch.reprs, sf->repr_id);
+
+	if (!repr)
+		return;
+
+	ice_eswitch_detach(pf, repr);
+}
+
 /**
  * ice_eswitch_get_target - get netdev based on src_vsi from descriptor
  * @rx_ring: ring used to receive the packet
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.h b/drivers/net/ethernet/intel/ice/ice_eswitch.h
index d1699954a7ad..20ce32dda69c 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.h
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.h
@@ -9,7 +9,9 @@
 
 #ifdef CONFIG_ICE_SWITCHDEV
 void ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf);
+void ice_eswitch_detach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf);
 int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf);
+int ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf);
 
 int ice_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int
@@ -34,12 +36,21 @@ void ice_eswitch_decfg_vsi(struct ice_vsi *vsi, const u8 *mac);
 static inline void
 ice_eswitch_detach_vf(struct ice_pf *pf, struct ice_vf *vf) { }
 
+static inline void
+ice_eswitch_detach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf) { }
+
 static inline int
 ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
 	return -EOPNOTSUPP;
 }
 
+static inline int
+ice_eswitch_attach_sf(struct ice_pf *pf, struct ice_dynamic_port *sf)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline void ice_eswitch_stop_all_tx_queues(struct ice_pf *pf) { }
 
 static inline void
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 5d71f623b1e0..5ea8b512c421 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -302,6 +302,12 @@ static void ice_repr_rem_vf(struct ice_repr *repr)
 	ice_virtchnl_set_dflt_ops(repr->vf);
 }
 
+static void ice_repr_rem_sf(struct ice_repr *repr)
+{
+	unregister_netdev(repr->netdev);
+	ice_devlink_destroy_sf_port(repr->sf);
+}
+
 static void ice_repr_set_tx_topology(struct ice_pf *pf)
 {
 	struct devlink *devlink;
@@ -420,6 +426,52 @@ struct ice_repr *ice_repr_create_vf(struct ice_vf *vf)
 	return repr;
 }
 
+static int ice_repr_add_sf(struct ice_repr *repr)
+{
+	struct ice_dynamic_port *sf = repr->sf;
+	int err;
+
+	err = ice_devlink_create_sf_port(sf);
+	if (err)
+		return err;
+
+	SET_NETDEV_DEVLINK_PORT(repr->netdev, &sf->devlink_port);
+	err = ice_repr_reg_netdev(repr->netdev);
+	if (err)
+		goto err_netdev;
+
+	return 0;
+
+err_netdev:
+	ice_devlink_destroy_sf_port(sf);
+	return err;
+}
+
+/**
+ * ice_repr_create_sf - add representor for SF VSI
+ * @sf: SF to create port representor on
+ *
+ * Set correct representor type for SF and functions pointer.
+ *
+ * Return: created port representor on success, error otherwise
+ */
+struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf)
+{
+	struct ice_repr *repr = ice_repr_create(sf->vsi);
+
+	if (!repr)
+		return ERR_PTR(-ENOMEM);
+
+	repr->type = ICE_REPR_TYPE_SF;
+	repr->sf = sf;
+	repr->ops.add = ice_repr_add_sf;
+	repr->ops.rem = ice_repr_rem_sf;
+
+	ether_addr_copy(repr->parent_mac, sf->hw_addr);
+
+	return repr;
+}
+
 struct ice_repr *ice_repr_get(struct ice_pf *pf, u32 id)
 {
 	return xa_load(&pf->eswitch.reprs, id);
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h
index c6e77b9c6a32..ee28632e87b4 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.h
+++ b/drivers/net/ethernet/intel/ice/ice_repr.h
@@ -17,6 +17,7 @@ struct ice_repr_pcpu_stats {
 
 enum ice_repr_type {
 	ICE_REPR_TYPE_VF,
+	ICE_REPR_TYPE_SF,
 };
 
 struct ice_repr {
@@ -28,7 +29,10 @@ struct ice_repr {
 	u32 id;
 	u8 parent_mac[ETH_ALEN];
 	enum ice_repr_type type;
-	struct ice_vf *vf;
+	union {
+		struct ice_vf *vf;
+		struct ice_dynamic_port *sf;
+	};
 	struct {
 		int (*add)(struct ice_repr *repr);
 		void (*rem)(struct ice_repr *repr);
@@ -36,6 +40,7 @@ struct ice_repr {
 };
 
 struct ice_repr *ice_repr_create_vf(struct ice_vf *vf);
+struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf);
 
 void ice_repr_destroy(struct ice_repr *repr);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index 05d9e7384c5e..e90546aea729 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -126,6 +126,8 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev,
 	}
 	vsi->sf = dyn_port;
 
+	ice_eswitch_update_repr(&dyn_port->repr_id, vsi);
+
 	err = ice_devlink_create_sf_dev_port(sf_dev);
 	if (err) {
 		dev_err(dev, "Cannot add ice virtual devlink port for subfunction");
-- 
cgit v1.3-3-g829e


From ef25090371725a340675a701b9ebd1a125a03ae1 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:55 +0200
Subject: ice: don't set target VSI for subfunction

Add check for subfunction before setting target VSI. It is needed for PF
in switchdev mode but not for subfunction (even in switchdev mode).

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index c9bc3f1add5d..8208055d6e7f 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -2368,7 +2368,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 					ICE_TXD_CTX_QW1_CMD_S);
 
 	ice_tstamp(tx_ring, skb, first, &offload);
-	if (ice_is_switchdev_running(vsi->back))
+	if (ice_is_switchdev_running(vsi->back) && vsi->type != ICE_VSI_SF)
 		ice_eswitch_set_target_vsi(skb, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
-- 
cgit v1.3-3-g829e


From 0f00a897c9fcbd20dcd47996a2cadde2b41adadc Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:56 +0200
Subject: ice: check if SF is ready in ethtool ops

Now there is another type of port representor. Correct checking if
parent device is ready to reflect also new PR type.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c |  7 +++----
 drivers/net/ethernet/intel/ice/ice_repr.c    | 12 ++++++++++++
 drivers/net/ethernet/intel/ice/ice_repr.h    |  1 +
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 793a64d44aa3..d5cc934d1359 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4412,7 +4412,7 @@ ice_repr_get_drvinfo(struct net_device *netdev,
 {
 	struct ice_repr *repr = ice_netdev_to_repr(netdev);
 
-	if (ice_check_vf_ready_for_cfg(repr->vf))
+	if (repr->ops.ready(repr))
 		return;
 
 	__ice_get_drvinfo(netdev, drvinfo, repr->src_vsi);
@@ -4424,8 +4424,7 @@ ice_repr_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	struct ice_repr *repr = ice_netdev_to_repr(netdev);
 
 	/* for port representors only ETH_SS_STATS is supported */
-	if (ice_check_vf_ready_for_cfg(repr->vf) ||
-	    stringset != ETH_SS_STATS)
+	if (repr->ops.ready(repr) || stringset != ETH_SS_STATS)
 		return;
 
 	__ice_get_strings(netdev, stringset, data, repr->src_vsi);
@@ -4438,7 +4437,7 @@ ice_repr_get_ethtool_stats(struct net_device *netdev,
 {
 	struct ice_repr *repr = ice_netdev_to_repr(netdev);
 
-	if (ice_check_vf_ready_for_cfg(repr->vf))
+	if (repr->ops.ready(repr))
 		return;
 
 	__ice_get_ethtool_stats(netdev, stats, data, repr->src_vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 5ea8b512c421..229831fe2cd2 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -283,6 +283,16 @@ ice_repr_reg_netdev(struct net_device *netdev)
 	return register_netdev(netdev);
 }
 
+static int ice_repr_ready_vf(struct ice_repr *repr)
+{
+	return !ice_check_vf_ready_for_cfg(repr->vf);
+}
+
+static int ice_repr_ready_sf(struct ice_repr *repr)
+{
+	return !repr->sf->active;
+}
+
 /**
  * ice_repr_destroy - remove representor from VF
  * @repr: pointer to representor structure
@@ -420,6 +430,7 @@ struct ice_repr *ice_repr_create_vf(struct ice_vf *vf)
 	repr->vf = vf;
 	repr->ops.add = ice_repr_add_vf;
 	repr->ops.rem = ice_repr_rem_vf;
+	repr->ops.ready = ice_repr_ready_vf;
 
 	ether_addr_copy(repr->parent_mac, vf->hw_lan_addr);
 
@@ -466,6 +477,7 @@ struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf)
 	repr->sf = sf;
 	repr->ops.add = ice_repr_add_sf;
 	repr->ops.rem = ice_repr_rem_sf;
+	repr->ops.ready = ice_repr_ready_sf;
 
 	ether_addr_copy(repr->parent_mac, sf->hw_addr);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.h b/drivers/net/ethernet/intel/ice/ice_repr.h
index ee28632e87b4..35bd93165e1e 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.h
+++ b/drivers/net/ethernet/intel/ice/ice_repr.h
@@ -36,6 +36,7 @@ struct ice_repr {
 	struct {
 		int (*add)(struct ice_repr *repr);
 		void (*rem)(struct ice_repr *repr);
+		int (*ready)(struct ice_repr *repr);
 	} ops;
 };
 
-- 
cgit v1.3-3-g829e


From 54f07712395216e1961b1daf8b92f8e76368655d Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:57 +0200
Subject: ice: implement netdevice ops for SF representor

Subfunction port representor needs the basic netdevice ops to work
correctly. Create them.

Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_repr.c | 57 +++++++++++++++++++++++--------
 1 file changed, 43 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 229831fe2cd2..78abfdf5d47b 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -59,12 +59,13 @@ static void
 ice_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_repr *repr = np->repr;
 	struct ice_eth_stats *eth_stats;
 	struct ice_vsi *vsi;
 
-	if (ice_is_vf_disabled(np->repr->vf))
+	if (repr->ops.ready(repr))
 		return;
-	vsi = np->repr->src_vsi;
+	vsi = repr->src_vsi;
 
 	ice_update_vsi_stats(vsi);
 	eth_stats = &vsi->eth_stats;
@@ -93,7 +94,7 @@ struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev)
 }
 
 /**
- * ice_repr_open - Enable port representor's network interface
+ * ice_repr_vf_open - Enable port representor's network interface
  * @netdev: network interface device structure
  *
  * The open entry point is called when a port representor's network
@@ -102,7 +103,7 @@ struct ice_repr *ice_netdev_to_repr(const struct net_device *netdev)
  *
  * Returns 0 on success
  */
-static int ice_repr_open(struct net_device *netdev)
+static int ice_repr_vf_open(struct net_device *netdev)
 {
 	struct ice_repr *repr = ice_netdev_to_repr(netdev);
 	struct ice_vf *vf;
@@ -118,8 +119,16 @@ static int ice_repr_open(struct net_device *netdev)
 	return 0;
 }
 
+static int ice_repr_sf_open(struct net_device *netdev)
+{
+	netif_carrier_on(netdev);
+	netif_tx_start_all_queues(netdev);
+
+	return 0;
+}
+
 /**
- * ice_repr_stop - Disable port representor's network interface
+ * ice_repr_vf_stop - Disable port representor's network interface
  * @netdev: network interface device structure
  *
  * The stop entry point is called when a port representor's network
@@ -128,7 +137,7 @@ static int ice_repr_open(struct net_device *netdev)
  *
  * Returns 0 on success
  */
-static int ice_repr_stop(struct net_device *netdev)
+static int ice_repr_vf_stop(struct net_device *netdev)
 {
 	struct ice_repr *repr = ice_netdev_to_repr(netdev);
 	struct ice_vf *vf;
@@ -144,6 +153,14 @@ static int ice_repr_stop(struct net_device *netdev)
 	return 0;
 }
 
+static int ice_repr_sf_stop(struct net_device *netdev)
+{
+	netif_carrier_off(netdev);
+	netif_tx_stop_all_queues(netdev);
+
+	return 0;
+}
+
 /**
  * ice_repr_sp_stats64 - get slow path stats for port representor
  * @dev: network interface device structure
@@ -245,10 +262,20 @@ ice_repr_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 	}
 }
 
-static const struct net_device_ops ice_repr_netdev_ops = {
+static const struct net_device_ops ice_repr_vf_netdev_ops = {
+	.ndo_get_stats64 = ice_repr_get_stats64,
+	.ndo_open = ice_repr_vf_open,
+	.ndo_stop = ice_repr_vf_stop,
+	.ndo_start_xmit = ice_eswitch_port_start_xmit,
+	.ndo_setup_tc = ice_repr_setup_tc,
+	.ndo_has_offload_stats = ice_repr_ndo_has_offload_stats,
+	.ndo_get_offload_stats = ice_repr_ndo_get_offload_stats,
+};
+
+static const struct net_device_ops ice_repr_sf_netdev_ops = {
 	.ndo_get_stats64 = ice_repr_get_stats64,
-	.ndo_open = ice_repr_open,
-	.ndo_stop = ice_repr_stop,
+	.ndo_open = ice_repr_sf_open,
+	.ndo_stop = ice_repr_sf_stop,
 	.ndo_start_xmit = ice_eswitch_port_start_xmit,
 	.ndo_setup_tc = ice_repr_setup_tc,
 	.ndo_has_offload_stats = ice_repr_ndo_has_offload_stats,
@@ -261,18 +288,20 @@ static const struct net_device_ops ice_repr_netdev_ops = {
  */
 bool ice_is_port_repr_netdev(const struct net_device *netdev)
 {
-	return netdev && (netdev->netdev_ops == &ice_repr_netdev_ops);
+	return netdev && (netdev->netdev_ops == &ice_repr_vf_netdev_ops ||
+			  netdev->netdev_ops == &ice_repr_sf_netdev_ops);
 }
 
 /**
  * ice_repr_reg_netdev - register port representor netdev
  * @netdev: pointer to port representor netdev
+ * @ops: new ops for netdev
  */
 static int
-ice_repr_reg_netdev(struct net_device *netdev)
+ice_repr_reg_netdev(struct net_device *netdev, const struct net_device_ops *ops)
 {
 	eth_hw_addr_random(netdev);
-	netdev->netdev_ops = &ice_repr_netdev_ops;
+	netdev->netdev_ops = ops;
 	ice_set_ethtool_repr_ops(netdev);
 
 	netdev->hw_features |= NETIF_F_HW_TC;
@@ -386,7 +415,7 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 		return err;
 
 	SET_NETDEV_DEVLINK_PORT(repr->netdev, &vf->devlink_port);
-	err = ice_repr_reg_netdev(repr->netdev);
+	err = ice_repr_reg_netdev(repr->netdev, &ice_repr_vf_netdev_ops);
 	if (err)
 		goto err_netdev;
 
@@ -447,7 +476,7 @@ static int ice_repr_add_sf(struct ice_repr *repr)
 		return err;
 
 	SET_NETDEV_DEVLINK_PORT(repr->netdev, &sf->devlink_port);
-	err = ice_repr_reg_netdev(repr->netdev);
+	err = ice_repr_reg_netdev(repr->netdev, &ice_repr_sf_netdev_ops);
 	if (err)
 		goto err_netdev;
 
-- 
cgit v1.3-3-g829e


From 7cde47431df52c73ce51287ccacdc572bb3ddd0a Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:58 +0200
Subject: ice: support subfunction devlink Tx topology

Flow for creating Tx topology is the same as for VF port representors,
but the devlink port is stored in different place (sf->devlink_port).

When creating VF devlink lock isn't taken, when creating subfunction it
is. Setting Tx topology function needs to take this lock, check if it
was taken before to not do it twice.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink.c      | 12 ++++++++++++
 drivers/net/ethernet/intel/ice/devlink/devlink_port.c |  1 +
 drivers/net/ethernet/intel/ice/ice_repr.c             | 12 +++++++-----
 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 445538959459..415445cefdb2 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -746,6 +746,7 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node
 				 struct ice_sched_node *tc_node, struct ice_pf *pf)
 {
 	struct devlink_rate *rate_node = NULL;
+	struct ice_dynamic_port *sf;
 	struct ice_vf *vf;
 	int i;
 
@@ -757,6 +758,7 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node
 		/* create root node */
 		rate_node = devl_rate_node_create(devlink, node, node->name, NULL);
 	} else if (node->vsi_handle &&
+		   pf->vsi[node->vsi_handle]->type == ICE_VSI_VF &&
 		   pf->vsi[node->vsi_handle]->vf) {
 		vf = pf->vsi[node->vsi_handle]->vf;
 		if (!vf->devlink_port.devlink_rate)
@@ -765,6 +767,16 @@ static void ice_traverse_tx_tree(struct devlink *devlink, struct ice_sched_node
 			 */
 			devl_rate_leaf_create(&vf->devlink_port, node,
 					      node->parent->rate_node);
+	} else if (node->vsi_handle &&
+		   pf->vsi[node->vsi_handle]->type == ICE_VSI_SF &&
+		   pf->vsi[node->vsi_handle]->sf) {
+		sf = pf->vsi[node->vsi_handle]->sf;
+		if (!sf->devlink_port.devlink_rate)
+			/* leaf nodes doesn't have children
+			 * so we don't set rate_node
+			 */
+			devl_rate_leaf_create(&sf->devlink_port, node,
+					      node->parent->rate_node);
 	} else if (node->info.data.elem_type != ICE_AQC_ELEM_TYPE_LEAF &&
 		   node->parent->rate_node) {
 		rate_node = devl_rate_node_create(devlink, node, node->name,
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index dc62046e26b7..c653a1f44bda 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -711,6 +711,7 @@ int ice_devlink_create_sf_port(struct ice_dynamic_port *dyn_port)
  */
 void ice_devlink_destroy_sf_port(struct ice_dynamic_port *dyn_port)
 {
+	devl_rate_leaf_destroy(&dyn_port->devlink_port);
 	devl_port_unregister(&dyn_port->devlink_port);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 78abfdf5d47b..00d4a9125dfa 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -347,16 +347,13 @@ static void ice_repr_rem_sf(struct ice_repr *repr)
 	ice_devlink_destroy_sf_port(repr->sf);
 }
 
-static void ice_repr_set_tx_topology(struct ice_pf *pf)
+static void ice_repr_set_tx_topology(struct ice_pf *pf, struct devlink *devlink)
 {
-	struct devlink *devlink;
-
 	/* only export if ADQ and DCB disabled and eswitch enabled*/
 	if (ice_is_adq_active(pf) || ice_is_dcb_active(pf) ||
 	    !ice_is_switchdev_running(pf))
 		return;
 
-	devlink = priv_to_devlink(pf);
 	ice_devlink_rate_init_tx_topology(devlink, ice_get_main_vsi(pf));
 }
 
@@ -408,6 +405,7 @@ err_alloc:
 static int ice_repr_add_vf(struct ice_repr *repr)
 {
 	struct ice_vf *vf = repr->vf;
+	struct devlink *devlink;
 	int err;
 
 	err = ice_devlink_create_vf_port(vf);
@@ -424,7 +422,9 @@ static int ice_repr_add_vf(struct ice_repr *repr)
 		goto err_cfg_vsi;
 
 	ice_virtchnl_set_repr_ops(vf);
-	ice_repr_set_tx_topology(vf->pf);
+
+	devlink = priv_to_devlink(vf->pf);
+	ice_repr_set_tx_topology(vf->pf, devlink);
 
 	return 0;
 
@@ -480,6 +480,8 @@ static int ice_repr_add_sf(struct ice_repr *repr)
 	if (err)
 		goto err_netdev;
 
+	ice_repr_set_tx_topology(sf->vsi->back, priv_to_devlink(sf->vsi->back));
+
 	return 0;
 
 err_netdev:
-- 
cgit v1.3-3-g829e


From 0c6a3cb6f181c8edb1246016d12dbd08366eb383 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 20 Aug 2024 08:57:59 +0200
Subject: ice: basic support for VLAN in subfunctions

Implement add / delete vlan for subfunction type VSI.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/Makefile             |  1 +
 .../net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c    | 21 +++++++++++++++++++++
 .../net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h    | 13 +++++++++++++
 drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c   |  4 ++++
 4 files changed, 39 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c
 create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h

diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile
index 81acb590eac6..3307d551f431 100644
--- a/drivers/net/ethernet/intel/ice/Makefile
+++ b/drivers/net/ethernet/intel/ice/Makefile
@@ -34,6 +34,7 @@ ice-y := ice_main.o	\
 	 devlink/devlink.o	\
 	 devlink/devlink_port.o \
 	 ice_sf_eth.o	\
+	 ice_sf_vsi_vlan_ops.o \
 	 ice_ddp.o	\
 	 ice_fw_update.o \
 	 ice_lag.o	\
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c
new file mode 100644
index 000000000000..3d7e96721cf9
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023, Intel Corporation. */
+
+#include "ice_vsi_vlan_ops.h"
+#include "ice_vsi_vlan_lib.h"
+#include "ice_vlan_mode.h"
+#include "ice.h"
+#include "ice_sf_vsi_vlan_ops.h"
+
+void ice_sf_vsi_init_vlan_ops(struct ice_vsi *vsi)
+{
+	struct ice_vsi_vlan_ops *vlan_ops;
+
+	if (ice_is_dvm_ena(&vsi->back->hw))
+		vlan_ops = &vsi->outer_vlan_ops;
+	else
+		vlan_ops = &vsi->inner_vlan_ops;
+
+	vlan_ops->add_vlan = ice_vsi_add_vlan;
+	vlan_ops->del_vlan = ice_vsi_del_vlan;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h
new file mode 100644
index 000000000000..8c44eafceea0
--- /dev/null
+++ b/drivers/net/ethernet/intel/ice/ice_sf_vsi_vlan_ops.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023, Intel Corporation. */
+
+#ifndef _ICE_SF_VSI_VLAN_OPS_H_
+#define _ICE_SF_VSI_VLAN_OPS_H_
+
+#include "ice_vsi_vlan_ops.h"
+
+struct ice_vsi;
+
+void ice_sf_vsi_init_vlan_ops(struct ice_vsi *vsi);
+
+#endif /* _ICE_SF_VSI_VLAN_OPS_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c
index 7aae7fdcfcdb..8c7a9b41fb63 100644
--- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c
+++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_ops.c
@@ -3,6 +3,7 @@
 
 #include "ice_pf_vsi_vlan_ops.h"
 #include "ice_vf_vsi_vlan_ops.h"
+#include "ice_sf_vsi_vlan_ops.h"
 #include "ice_lib.h"
 #include "ice.h"
 
@@ -77,6 +78,9 @@ void ice_vsi_init_vlan_ops(struct ice_vsi *vsi)
 	case ICE_VSI_VF:
 		ice_vf_vsi_init_vlan_ops(vsi);
 		break;
+	case ICE_VSI_SF:
+		ice_sf_vsi_init_vlan_ops(vsi);
+		break;
 	default:
 		dev_dbg(ice_pf_to_dev(vsi->back), "%s does not support VLAN operations\n",
 			ice_vsi_type_str(vsi->type));
-- 
cgit v1.3-3-g829e


From 13acc5c4cdbeccf3274cbbd4de2e2d316b8c4ce6 Mon Sep 17 00:00:00 2001
From: Piotr Raczynski <piotr.raczynski@intel.com>
Date: Tue, 20 Aug 2024 08:58:00 +0200
Subject: ice: subfunction activation and base devlink ops

Use previously implemented SF aux driver. It is probe during SF
activation and remove after deactivation.

Implement set/get hw_address and set/get state as basic devlink ops for
subfunction.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Piotr Raczynski <piotr.raczynski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/devlink/devlink_port.c  | 176 +++++++++++++++++++++
 .../net/ethernet/intel/ice/devlink/devlink_port.h  |   7 +
 drivers/net/ethernet/intel/ice/ice_sf_eth.c        | 104 ++++++++++++
 drivers/net/ethernet/intel/ice/ice_sf_eth.h        |   3 +
 4 files changed, 290 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index c653a1f44bda..928c8bdb6649 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -530,6 +530,48 @@ void ice_devlink_destroy_sf_dev_port(struct ice_sf_dev *sf_dev)
 	devl_port_unregister(&sf_dev->priv->devlink_port);
 }
 
+/**
+ * ice_activate_dynamic_port - Activate a dynamic port
+ * @dyn_port: dynamic port instance to activate
+ * @extack: extack for reporting error messages
+ *
+ * Activate the dynamic port based on its flavour.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_activate_dynamic_port(struct ice_dynamic_port *dyn_port,
+			  struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (dyn_port->active)
+		return 0;
+
+	err = ice_sf_eth_activate(dyn_port, extack);
+	if (err)
+		return err;
+
+	dyn_port->active = true;
+
+	return 0;
+}
+
+/**
+ * ice_deactivate_dynamic_port - Deactivate a dynamic port
+ * @dyn_port: dynamic port instance to deactivate
+ *
+ * Undo activation of a dynamic port.
+ */
+static void ice_deactivate_dynamic_port(struct ice_dynamic_port *dyn_port)
+{
+	if (!dyn_port->active)
+		return;
+
+	ice_sf_eth_deactivate(dyn_port);
+	dyn_port->active = false;
+}
+
 /**
  * ice_dealloc_dynamic_port - Deallocate and remove a dynamic port
  * @dyn_port: dynamic port instance to deallocate
@@ -542,6 +584,8 @@ static void ice_dealloc_dynamic_port(struct ice_dynamic_port *dyn_port)
 	struct devlink_port *devlink_port = &dyn_port->devlink_port;
 	struct ice_pf *pf = dyn_port->pf;
 
+	ice_deactivate_dynamic_port(dyn_port);
+
 	xa_erase(&pf->sf_nums, devlink_port->attrs.pci_sf.sf);
 	ice_eswitch_detach_sf(pf, dyn_port);
 	ice_vsi_free(dyn_port->vsi);
@@ -629,8 +673,140 @@ ice_devlink_port_del(struct devlink *devlink, struct devlink_port *port,
 	return 0;
 }
 
+/**
+ * ice_devlink_port_fn_hw_addr_set - devlink handler for mac address set
+ * @port: pointer to devlink port
+ * @hw_addr: hw address to set
+ * @hw_addr_len: hw address length
+ * @extack: extack for reporting error messages
+ *
+ * Sets mac address for the port, verifies arguments and copies address
+ * to the subfunction structure.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_fn_hw_addr_set(struct devlink_port *port, const u8 *hw_addr,
+				int hw_addr_len,
+				struct netlink_ext_ack *extack)
+{
+	struct ice_dynamic_port *dyn_port;
+
+	dyn_port = ice_devlink_port_to_dyn(port);
+
+	if (dyn_port->attached) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Ethernet address can be change only in detached state");
+		return -EBUSY;
+	}
+
+	if (hw_addr_len != ETH_ALEN || !is_valid_ether_addr(hw_addr)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid ethernet address");
+		return -EADDRNOTAVAIL;
+	}
+
+	ether_addr_copy(dyn_port->hw_addr, hw_addr);
+
+	return 0;
+}
+
+/**
+ * ice_devlink_port_fn_hw_addr_get - devlink handler for mac address get
+ * @port: pointer to devlink port
+ * @hw_addr: hw address to set
+ * @hw_addr_len: hw address length
+ * @extack: extack for reporting error messages
+ *
+ * Returns mac address for the port.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_fn_hw_addr_get(struct devlink_port *port, u8 *hw_addr,
+				int *hw_addr_len,
+				struct netlink_ext_ack *extack)
+{
+	struct ice_dynamic_port *dyn_port;
+
+	dyn_port = ice_devlink_port_to_dyn(port);
+
+	ether_addr_copy(hw_addr, dyn_port->hw_addr);
+	*hw_addr_len = ETH_ALEN;
+
+	return 0;
+}
+
+/**
+ * ice_devlink_port_fn_state_set - devlink handler for port state set
+ * @port: pointer to devlink port
+ * @state: state to set
+ * @extack: extack for reporting error messages
+ *
+ * Activates or deactivates the port.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_fn_state_set(struct devlink_port *port,
+			      enum devlink_port_fn_state state,
+			      struct netlink_ext_ack *extack)
+{
+	struct ice_dynamic_port *dyn_port;
+
+	dyn_port = ice_devlink_port_to_dyn(port);
+
+	switch (state) {
+	case DEVLINK_PORT_FN_STATE_ACTIVE:
+		return ice_activate_dynamic_port(dyn_port, extack);
+
+	case DEVLINK_PORT_FN_STATE_INACTIVE:
+		ice_deactivate_dynamic_port(dyn_port);
+		break;
+	}
+
+	return 0;
+}
+
+/**
+ * ice_devlink_port_fn_state_get - devlink handler for port state get
+ * @port: pointer to devlink port
+ * @state: admin configured state of the port
+ * @opstate: current port operational state
+ * @extack: extack for reporting error messages
+ *
+ * Gets port state.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+static int
+ice_devlink_port_fn_state_get(struct devlink_port *port,
+			      enum devlink_port_fn_state *state,
+			      enum devlink_port_fn_opstate *opstate,
+			      struct netlink_ext_ack *extack)
+{
+	struct ice_dynamic_port *dyn_port;
+
+	dyn_port = ice_devlink_port_to_dyn(port);
+
+	if (dyn_port->active)
+		*state = DEVLINK_PORT_FN_STATE_ACTIVE;
+	else
+		*state = DEVLINK_PORT_FN_STATE_INACTIVE;
+
+	if (dyn_port->attached)
+		*opstate = DEVLINK_PORT_FN_OPSTATE_ATTACHED;
+	else
+		*opstate = DEVLINK_PORT_FN_OPSTATE_DETACHED;
+
+	return 0;
+}
+
 static const struct devlink_port_ops ice_devlink_port_sf_ops = {
 	.port_del = ice_devlink_port_del,
+	.port_fn_hw_addr_get = ice_devlink_port_fn_hw_addr_get,
+	.port_fn_hw_addr_set = ice_devlink_port_fn_hw_addr_set,
+	.port_fn_state_get = ice_devlink_port_fn_state_get,
+	.port_fn_state_set = ice_devlink_port_fn_state_set,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
index 479d2b976745..d60efc340945 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.h
@@ -11,22 +11,29 @@
  * struct ice_dynamic_port - Track dynamically added devlink port instance
  * @hw_addr: the HW address for this port
  * @active: true if the port has been activated
+ * @attached: true it the prot is attached
  * @devlink_port: the associated devlink port structure
  * @pf: pointer to the PF private structure
  * @vsi: the VSI associated with this port
  * @repr_id: the representor ID
  * @sfnum: the subfunction ID
+ * @sf_dev: pointer to the subfunction device
  *
  * An instance of a dynamically added devlink port. Each port flavour
  */
 struct ice_dynamic_port {
 	u8 hw_addr[ETH_ALEN];
 	u8 active: 1;
+	u8 attached: 1;
 	struct devlink_port devlink_port;
 	struct ice_pf *pf;
 	struct ice_vsi *vsi;
 	unsigned long repr_id;
 	u32 sfnum;
+	/* Flavour-specific implementation data */
+	union {
+		struct ice_sf_dev *sf_dev;
+	};
 };
 
 void ice_dealloc_all_dynamic_ports(struct ice_pf *pf);
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index e90546aea729..d00389c405c4 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -151,6 +151,8 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev,
 	devl_register(devlink);
 	devl_unlock(devlink);
 
+	dyn_port->attached = true;
+
 	return 0;
 
 err_netdev_decfg:
@@ -189,6 +191,8 @@ static void ice_sf_dev_remove(struct auxiliary_device *adev)
 	devl_unlock(devlink);
 	devlink_free(devlink);
 	ice_vsi_decfg(vsi);
+
+	dyn_port->attached = false;
 }
 
 static const struct auxiliary_device_id ice_sf_dev_id_table[] = {
@@ -205,6 +209,8 @@ static struct auxiliary_driver ice_sf_driver = {
 	.id_table = ice_sf_dev_id_table
 };
 
+static DEFINE_XARRAY_ALLOC1(ice_sf_aux_id);
+
 /**
  * ice_sf_driver_register - Register new auxiliary subfunction driver
  *
@@ -223,3 +229,101 @@ void ice_sf_driver_unregister(void)
 {
 	auxiliary_driver_unregister(&ice_sf_driver);
 }
+
+/**
+ * ice_sf_dev_release - Release device associated with auxiliary device
+ * @device: pointer to the device
+ *
+ * Since most of the code for subfunction deactivation is handled in
+ * the remove handler, here just free tracking resources.
+ */
+static void ice_sf_dev_release(struct device *device)
+{
+	struct auxiliary_device *adev = to_auxiliary_dev(device);
+	struct ice_sf_dev *sf_dev = ice_adev_to_sf_dev(adev);
+
+	xa_erase(&ice_sf_aux_id, adev->id);
+	kfree(sf_dev);
+}
+
+/**
+ * ice_sf_eth_activate - Activate Ethernet subfunction port
+ * @dyn_port: the dynamic port instance for this subfunction
+ * @extack: extack for reporting error messages
+ *
+ * Activate the dynamic port as an Ethernet subfunction. Setup the netdev
+ * resources associated and initialize the auxiliary device.
+ *
+ * Return: zero on success or an error code on failure.
+ */
+int
+ice_sf_eth_activate(struct ice_dynamic_port *dyn_port,
+		    struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = dyn_port->pf;
+	struct ice_sf_dev *sf_dev;
+	struct pci_dev *pdev;
+	int err;
+	u32 id;
+
+	err = xa_alloc(&ice_sf_aux_id, &id, NULL, xa_limit_32b,
+		       GFP_KERNEL);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Could not allocate SF ID");
+		return err;
+	}
+
+	sf_dev = kzalloc(sizeof(*sf_dev), GFP_KERNEL);
+	if (!sf_dev) {
+		err = -ENOMEM;
+		NL_SET_ERR_MSG_MOD(extack, "Could not allocate SF memory");
+		goto xa_erase;
+	}
+	pdev = pf->pdev;
+
+	sf_dev->dyn_port = dyn_port;
+	sf_dev->adev.id = id;
+	sf_dev->adev.name = "sf";
+	sf_dev->adev.dev.release = ice_sf_dev_release;
+	sf_dev->adev.dev.parent = &pdev->dev;
+
+	err = auxiliary_device_init(&sf_dev->adev);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to initialize SF device");
+		goto sf_dev_free;
+	}
+
+	err = auxiliary_device_add(&sf_dev->adev);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to add SF device");
+		goto aux_dev_uninit;
+	}
+
+	dyn_port->sf_dev = sf_dev;
+
+	return 0;
+
+aux_dev_uninit:
+	auxiliary_device_uninit(&sf_dev->adev);
+sf_dev_free:
+	kfree(sf_dev);
+xa_erase:
+	xa_erase(&ice_sf_aux_id, id);
+
+	return err;
+}
+
+/**
+ * ice_sf_eth_deactivate - Deactivate Ethernet subfunction port
+ * @dyn_port: the dynamic port instance for this subfunction
+ *
+ * Deactivate the Ethernet subfunction, removing its auxiliary device and the
+ * associated resources.
+ */
+void ice_sf_eth_deactivate(struct ice_dynamic_port *dyn_port)
+{
+	struct ice_sf_dev *sf_dev = dyn_port->sf_dev;
+
+	auxiliary_device_delete(&sf_dev->adev);
+	auxiliary_device_uninit(&sf_dev->adev);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.h b/drivers/net/ethernet/intel/ice/ice_sf_eth.h
index e972c50f96c9..c558cad0a183 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.h
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.h
@@ -27,4 +27,7 @@ ice_sf_dev *ice_adev_to_sf_dev(struct auxiliary_device *adev)
 int ice_sf_driver_register(void);
 void ice_sf_driver_unregister(void);
 
+int ice_sf_eth_activate(struct ice_dynamic_port *dyn_port,
+			struct netlink_ext_ack *extack);
+void ice_sf_eth_deactivate(struct ice_dynamic_port *dyn_port);
 #endif /* _ICE_SF_ETH_H_ */
-- 
cgit v1.3-3-g829e


From aac0484423b7429808ca40a5017d603c14c1da1e Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 16:08:45 +0800
Subject: net: atlantic: convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240904080845.1353144-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index f7433abd6591..f21de0c21e52 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -557,7 +557,7 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi,
 				}
 
 				frag_cnt++;
-				next_ = buff_->next,
+				next_ = buff_->next;
 				buff_ = &self->buff_ring[next_];
 				is_rsc_completed =
 					aq_ring_dx_in_range(self->sw_head,
@@ -583,7 +583,7 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi,
 						err = -EIO;
 						goto err_exit;
 					}
-					next_ = buff_->next,
+					next_ = buff_->next;
 					buff_ = &self->buff_ring[next_];
 
 					buff_->is_cleaned = true;
-- 
cgit v1.3-3-g829e


From 62c9f50eabe080cb07ed5e6c55d1fd38ad04201b Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 16:17:28 +0800
Subject: ionic: Convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20240904081728.1353260-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
index 1ee2f285cb42..528114877677 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c
@@ -312,8 +312,8 @@ static int ionic_lif_filter_add(struct ionic_lif *lif,
 	int err = 0;
 
 	ctx.cmd.rx_filter_add = *ac;
-	ctx.cmd.rx_filter_add.opcode = IONIC_CMD_RX_FILTER_ADD,
-	ctx.cmd.rx_filter_add.lif_index = cpu_to_le16(lif->index),
+	ctx.cmd.rx_filter_add.opcode = IONIC_CMD_RX_FILTER_ADD;
+	ctx.cmd.rx_filter_add.lif_index = cpu_to_le16(lif->index);
 
 	spin_lock_bh(&lif->rx_filters.lock);
 	f = ionic_rx_filter_find(lif, &ctx.cmd.rx_filter_add);
-- 
cgit v1.3-3-g829e


From 96487cb211ce9561df5176a923dc5855cd75444e Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 16:40:34 +0800
Subject: sfc/siena: Convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20240904084034.1353404-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/siena/ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/siena/ptp.c b/drivers/net/ethernet/sfc/siena/ptp.c
index c473a4b6dd44..85005196b4c5 100644
--- a/drivers/net/ethernet/sfc/siena/ptp.c
+++ b/drivers/net/ethernet/sfc/siena/ptp.c
@@ -897,7 +897,7 @@ static void efx_ptp_read_timeset(MCDI_DECLARE_STRUCT_PTR(data),
 	timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART);
 	timeset->major = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MAJOR);
 	timeset->minor = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MINOR);
-	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND),
+	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND);
 	timeset->wait = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS);
 
 	/* Ignore seconds */
-- 
cgit v1.3-3-g829e


From be8a17fe994dbffd2dfa0ad83bae9bbeef54c076 Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 16:49:51 +0800
Subject: sfc: convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20240904084951.1353518-1-nichen@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 6fd2fdbaa418..aaacdcfa54ae 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -884,7 +884,7 @@ static void efx_ptp_read_timeset(MCDI_DECLARE_STRUCT_PTR(data),
 	timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART);
 	timeset->major = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MAJOR);
 	timeset->minor = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MINOR);
-	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND),
+	timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND);
 	timeset->wait = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS);
 
 	/* Ignore seconds */
-- 
cgit v1.3-3-g829e


From cecbe5c8c8039b2965c9fc27c802db6b9ec9dcb7 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 4 Sep 2024 17:32:39 +0800
Subject: net/ipv4: make use of the helper macro LIST_HEAD()

list_head can be initialized automatically with LIST_HEAD()
instead of calling INIT_LIST_HEAD(). Here we can simplify
the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240904093243.3345012-2-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_input.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index d6fbcbd2358a..b6e7d4921309 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -596,9 +596,8 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 {
 	struct sk_buff *skb, *next, *hint = NULL;
 	struct dst_entry *curr_dst = NULL;
-	struct list_head sublist;
+	LIST_HEAD(sublist);
 
-	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct net_device *dev = skb->dev;
 		struct dst_entry *dst;
@@ -646,9 +645,8 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 	struct net_device *curr_dev = NULL;
 	struct net *curr_net = NULL;
 	struct sk_buff *skb, *next;
-	struct list_head sublist;
+	LIST_HEAD(sublist);
 
-	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct net_device *dev = skb->dev;
 		struct net *net = dev_net(dev);
-- 
cgit v1.3-3-g829e


From e636ba1a15e764f72ecb3c2a689feaa6c9fdd058 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 4 Sep 2024 17:32:40 +0800
Subject: net/tipc: make use of the helper macro LIST_HEAD()

list_head can be initialized automatically with LIST_HEAD()
instead of calling INIT_LIST_HEAD(). Here we can simplify
the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240904093243.3345012-3-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/socket.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 1a0cd06f0eae..65dcbb54f55d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1009,12 +1009,11 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
 	struct tipc_member *mbr = NULL;
 	struct net *net = sock_net(sk);
 	u32 node, port, exclude;
-	struct list_head dsts;
+	LIST_HEAD(dsts);
 	int lookups = 0;
 	int dstcnt, rc;
 	bool cong;
 
-	INIT_LIST_HEAD(&dsts);
 	ua->sa.type = msg_nametype(hdr);
 	ua->scope = msg_lookup_scope(hdr);
 
@@ -1161,10 +1160,9 @@ static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
 	struct tipc_group *grp = tsk->group;
 	struct tipc_msg *hdr = &tsk->phdr;
 	struct net *net = sock_net(sk);
-	struct list_head dsts;
 	u32 dstcnt, exclude;
+	LIST_HEAD(dsts);
 
-	INIT_LIST_HEAD(&dsts);
 	ua->sa.type = msg_nametype(hdr);
 	ua->scope = msg_lookup_scope(hdr);
 	exclude = tipc_group_exclude(grp);
-- 
cgit v1.3-3-g829e


From 8b51455bbd45e1b2d6980536698be4f4f332b385 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 4 Sep 2024 17:32:41 +0800
Subject: net/netfilter: make use of the helper macro LIST_HEAD()

list_head can be initialized automatically with LIST_HEAD()
instead of calling INIT_LIST_HEAD(). Here we can simplify
the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Reviewed-by: Pablo Neira Ayuso <pablo@netfilter.org>
Link: https://patch.msgid.link/20240904093243.3345012-4-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netfilter/core.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index b00fc285b334..b9f551f02c81 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -655,11 +655,9 @@ void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state,
 		       const struct nf_hook_entries *e)
 {
 	struct sk_buff *skb, *next;
-	struct list_head sublist;
+	LIST_HEAD(sublist);
 	int ret;
 
-	INIT_LIST_HEAD(&sublist);
-
 	list_for_each_entry_safe(skb, next, head, list) {
 		skb_list_del_init(skb);
 		ret = nf_hook_slow(skb, state, e, 0);
-- 
cgit v1.3-3-g829e


From 2a7dd251b6fee7bcd2a3978600eaa98dd2b7b481 Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 4 Sep 2024 17:32:42 +0800
Subject: net/ipv6: make use of the helper macro LIST_HEAD()

list_head can be initialized automatically with LIST_HEAD()
instead of calling INIT_LIST_HEAD(). Here we can simplify
the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240904093243.3345012-5-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_input.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 133610a49da6..70c0e16c0ae6 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -111,9 +111,8 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
 {
 	struct sk_buff *skb, *next, *hint = NULL;
 	struct dst_entry *curr_dst = NULL;
-	struct list_head sublist;
+	LIST_HEAD(sublist);
 
-	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct dst_entry *dst;
 
@@ -327,9 +326,8 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
 	struct net_device *curr_dev = NULL;
 	struct net *curr_net = NULL;
 	struct sk_buff *skb, *next;
-	struct list_head sublist;
+	LIST_HEAD(sublist);
 
-	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct net_device *dev = skb->dev;
 		struct net *net = dev_net(dev);
-- 
cgit v1.3-3-g829e


From 17f01391903de08c8a33407de9f502fc1cc8b5ff Mon Sep 17 00:00:00 2001
From: Hongbo Li <lihongbo22@huawei.com>
Date: Wed, 4 Sep 2024 17:32:43 +0800
Subject: net/core: make use of the helper macro LIST_HEAD()

list_head can be initialized automatically with LIST_HEAD()
instead of calling INIT_LIST_HEAD(). Here we can simplify
the code.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20240904093243.3345012-6-lihongbo22@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 98bb5f890b88..22c3f14d9287 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5727,10 +5727,9 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 	struct packet_type *pt_curr = NULL;
 	/* Current (common) orig_dev of sublist */
 	struct net_device *od_curr = NULL;
-	struct list_head sublist;
 	struct sk_buff *skb, *next;
+	LIST_HEAD(sublist);
 
-	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct net_device *orig_dev = skb->dev;
 		struct packet_type *pt_prev = NULL;
@@ -5868,9 +5867,8 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 void netif_receive_skb_list_internal(struct list_head *head)
 {
 	struct sk_buff *skb, *next;
-	struct list_head sublist;
+	LIST_HEAD(sublist);
 
-	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue),
 				    skb);
-- 
cgit v1.3-3-g829e


From 54001d0f2fdbc7852136a00f3e6fc395a9547ae5 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Wed, 4 Sep 2024 14:17:41 +0200
Subject: net: tls: wait for async completion on last message

When asynchronous encryption is used KTLS sends out the final data at
proto->close time. This becomes problematic when the task calling
close() receives a signal. In this case it can happen that
tcp_sendmsg_locked() called at close time returns -ERESTARTSYS and the
final data is not sent.

The described situation happens when KTLS is used in conjunction with
io_uring, as io_uring uses task_work_add() to add work to the current
userspace task. A discussion of the problem along with a reproducer can
be found in [1] and [2]

Fix this by waiting for the asynchronous encryption to be completed on
the final message. With this there is no data left to be sent at close
time.

[1] https://lore.kernel.org/all/20231010141932.GD3114228@pengutronix.de/
[2] https://lore.kernel.org/all/20240315100159.3898944-1-s.hauer@pengutronix.de/

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Link: https://patch.msgid.link/20240904-ktls-wait-async-v1-1-a62892833110@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 305a412785f5..bbf26cc4f6ee 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1201,7 +1201,7 @@ trim_sgl:
 
 	if (!num_async) {
 		goto send_end;
-	} else if (num_zc) {
+	} else if (num_zc || eor) {
 		int err;
 
 		/* Wait for pending encryptions to get completed */
-- 
cgit v1.3-3-g829e


From 517c29247557bf4a28065cb758a59ad545fe925d Mon Sep 17 00:00:00 2001
From: Vasileios Amoiridis <vassilisamir@gmail.com>
Date: Wed, 4 Sep 2024 17:10:16 +0200
Subject: net: dsa: realtek: rtl8365mb: Make use of irq_get_trigger_type()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert irqd_get_trigger_type(irq_get_irq_data(irq)) cases to the more
simple irq_get_trigger_type(irq).

Signed-off-by: Vasileios Amoiridis <vassilisamir@gmail.com>
Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk>
Link: https://patch.msgid.link/20240904151018.71967-2-vassilisamir@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8365mb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c
index b9674f68b756..ad7044b295ec 100644
--- a/drivers/net/dsa/realtek/rtl8365mb.c
+++ b/drivers/net/dsa/realtek/rtl8365mb.c
@@ -1740,7 +1740,7 @@ static int rtl8365mb_irq_setup(struct realtek_priv *priv)
 	}
 
 	/* Configure chip interrupt signal polarity */
-	irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
+	irq_trig = irq_get_trigger_type(irq);
 	switch (irq_trig) {
 	case IRQF_TRIGGER_RISING:
 	case IRQF_TRIGGER_HIGH:
-- 
cgit v1.3-3-g829e


From 36a5faec5658736e8d3d9047c1387a69ffda3354 Mon Sep 17 00:00:00 2001
From: Vasileios Amoiridis <vassilisamir@gmail.com>
Date: Wed, 4 Sep 2024 17:10:17 +0200
Subject: net: dsa: realtek: rtl8366rb: Make use of irq_get_trigger_type()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert irqd_get_trigger_type(irq_get_irq_data(irq)) cases to the more
simple irq_get_trigger_type(irq).

Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk>
Signed-off-by: Vasileios Amoiridis <vassilisamir@gmail.com>
Link: https://patch.msgid.link/20240904151018.71967-3-vassilisamir@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/realtek/rtl8366rb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 11243f89c98a..c7a8cd060587 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -599,7 +599,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_priv *priv)
 	}
 
 	/* Fetch IRQ edge information from the descriptor */
-	irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
+	irq_trig = irq_get_trigger_type(irq);
 	switch (irq_trig) {
 	case IRQF_TRIGGER_RISING:
 	case IRQF_TRIGGER_HIGH:
-- 
cgit v1.3-3-g829e


From f4bbf496f5fd66603f75a32a27c6075e0868c76b Mon Sep 17 00:00:00 2001
From: Vasileios Amoiridis <vassilisamir@gmail.com>
Date: Wed, 4 Sep 2024 17:10:18 +0200
Subject: net: smc91x: Make use of irq_get_trigger_type()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert irqd_get_trigger_type(irq_get_irq_data(irq)) cases to the more
simple irq_get_trigger_type(irq).

Signed-off-by: Vasileios Amoiridis <vassilisamir@gmail.com>
Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk>
Link: https://patch.msgid.link/20240904151018.71967-4-vassilisamir@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/smsc/smc91x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 907498848028..a5e23e2da90f 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2355,7 +2355,7 @@ static int smc_drv_probe(struct platform_device *pdev)
 	 * the resource supplies a trigger, override the irqflags with
 	 * the trigger flags from the resource.
 	 */
-	irq_resflags = irqd_get_trigger_type(irq_get_irq_data(ndev->irq));
+	irq_resflags = irq_get_trigger_type(ndev->irq);
 	if (irq_flags == -1 || irq_resflags & IRQF_TRIGGER_MASK)
 		irq_flags = irq_resflags & IRQF_TRIGGER_MASK;
 
-- 
cgit v1.3-3-g829e


From 32b81e4f0e5d8a50c2bd34e9d61dd52b5d82856f Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Wed, 4 Sep 2024 19:11:56 +0100
Subject: sfc: siena: rip out rss-context dead code

Siena hardware does not support custom RSS contexts, but when the
 driver was forked from sfc.ko, some of the plumbing for them was
 copied across from the common code.  Actually trying to use them
 would lead to EOPNOTSUPP as the relevant efx_nic_type methods were
 not populated.
Remove this dead code from the Siena driver.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240904181156.1993666-1-edward.cree@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/siena/efx_common.c     |   7 --
 drivers/net/ethernet/sfc/siena/ethtool.c        |   1 -
 drivers/net/ethernet/sfc/siena/ethtool_common.c | 125 +-----------------------
 drivers/net/ethernet/sfc/siena/net_driver.h     |  26 +----
 drivers/net/ethernet/sfc/siena/rx_common.c      |  56 -----------
 drivers/net/ethernet/sfc/siena/rx_common.h      |   4 -
 6 files changed, 8 insertions(+), 211 deletions(-)

diff --git a/drivers/net/ethernet/sfc/siena/efx_common.c b/drivers/net/ethernet/sfc/siena/efx_common.c
index cf195162e270..a0966f879664 100644
--- a/drivers/net/ethernet/sfc/siena/efx_common.c
+++ b/drivers/net/ethernet/sfc/siena/efx_common.c
@@ -725,7 +725,6 @@ void efx_siena_reset_down(struct efx_nic *efx, enum reset_type method)
 
 	mutex_lock(&efx->mac_lock);
 	down_write(&efx->filter_sem);
-	mutex_lock(&efx->rss_lock);
 	efx->type->fini(efx);
 }
 
@@ -786,9 +785,6 @@ int efx_siena_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 			   " VFs may not function\n", rc);
 #endif
 
-	if (efx->type->rx_restore_rss_contexts)
-		efx->type->rx_restore_rss_contexts(efx);
-	mutex_unlock(&efx->rss_lock);
 	efx->type->filter_table_restore(efx);
 	up_write(&efx->filter_sem);
 	if (efx->type->sriov_reset)
@@ -806,7 +802,6 @@ int efx_siena_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 fail:
 	efx->port_initialized = false;
 
-	mutex_unlock(&efx->rss_lock);
 	up_write(&efx->filter_sem);
 	mutex_unlock(&efx->mac_lock);
 
@@ -1016,9 +1011,7 @@ int efx_siena_init_struct(struct efx_nic *efx,
 		efx->type->rx_hash_offset - efx->type->rx_prefix_size;
 	efx->rx_packet_ts_offset =
 		efx->type->rx_ts_offset - efx->type->rx_prefix_size;
-	INIT_LIST_HEAD(&efx->rss_context.list);
 	efx->rss_context.context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
-	mutex_init(&efx->rss_lock);
 	efx->vport_id = EVB_PORT_ID_ASSIGNED;
 	spin_lock_init(&efx->stats_lock);
 	efx->vi_stride = EFX_DEFAULT_VI_STRIDE;
diff --git a/drivers/net/ethernet/sfc/siena/ethtool.c b/drivers/net/ethernet/sfc/siena/ethtool.c
index 4c182d4edfc2..88ddc226b012 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool.c
@@ -240,7 +240,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 }
 
 const struct ethtool_ops efx_siena_ethtool_ops = {
-	.cap_rss_ctx_supported	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USECS_IRQ |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
diff --git a/drivers/net/ethernet/sfc/siena/ethtool_common.c b/drivers/net/ethernet/sfc/siena/ethtool_common.c
index 5f0a8127e967..075fef64de68 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool_common.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool_common.c
@@ -820,27 +820,16 @@ int efx_siena_ethtool_get_rxnfc(struct net_device *net_dev,
 		return 0;
 
 	case ETHTOOL_GRXFH: {
-		struct efx_rss_context *ctx = &efx->rss_context;
 		__u64 data;
 
-		mutex_lock(&efx->rss_lock);
-		if (info->flow_type & FLOW_RSS && info->rss_context) {
-			ctx = efx_siena_find_rss_context_entry(efx,
-							info->rss_context);
-			if (!ctx) {
-				rc = -ENOENT;
-				goto out_unlock;
-			}
-		}
-
 		data = 0;
-		if (!efx_rss_active(ctx)) /* No RSS */
-			goto out_setdata_unlock;
+		if (!efx_rss_active(&efx->rss_context)) /* No RSS */
+			goto out_setdata;
 
-		switch (info->flow_type & ~FLOW_RSS) {
+		switch (info->flow_type) {
 		case UDP_V4_FLOW:
 		case UDP_V6_FLOW:
-			if (ctx->rx_hash_udp_4tuple)
+			if (efx->rss_context.rx_hash_udp_4tuple)
 				data = (RXH_L4_B_0_1 | RXH_L4_B_2_3 |
 					RXH_IP_SRC | RXH_IP_DST);
 			else
@@ -862,10 +851,8 @@ int efx_siena_ethtool_get_rxnfc(struct net_device *net_dev,
 		default:
 			break;
 		}
-out_setdata_unlock:
+out_setdata:
 		info->data = data;
-out_unlock:
-		mutex_unlock(&efx->rss_lock);
 		return rc;
 	}
 
@@ -1164,47 +1151,12 @@ u32 efx_siena_ethtool_get_rxfh_key_size(struct net_device *net_dev)
 	return efx->type->rx_hash_key_size;
 }
 
-static int efx_siena_ethtool_get_rxfh_context(struct net_device *net_dev,
-					      struct ethtool_rxfh_param *rxfh)
-{
-	struct efx_nic *efx = netdev_priv(net_dev);
-	struct efx_rss_context *ctx;
-	int rc = 0;
-
-	if (!efx->type->rx_pull_rss_context_config)
-		return -EOPNOTSUPP;
-
-	mutex_lock(&efx->rss_lock);
-	ctx = efx_siena_find_rss_context_entry(efx, rxfh->rss_context);
-	if (!ctx) {
-		rc = -ENOENT;
-		goto out_unlock;
-	}
-	rc = efx->type->rx_pull_rss_context_config(efx, ctx);
-	if (rc)
-		goto out_unlock;
-
-	rxfh->hfunc = ETH_RSS_HASH_TOP;
-	if (rxfh->indir)
-		memcpy(rxfh->indir, ctx->rx_indir_table,
-		       sizeof(ctx->rx_indir_table));
-	if (rxfh->key)
-		memcpy(rxfh->key, ctx->rx_hash_key,
-		       efx->type->rx_hash_key_size);
-out_unlock:
-	mutex_unlock(&efx->rss_lock);
-	return rc;
-}
-
 int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
 			       struct ethtool_rxfh_param *rxfh)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 	int rc;
 
-	if (rxfh->rss_context)
-		return efx_siena_ethtool_get_rxfh_context(net_dev, rxfh);
-
 	rc = efx->type->rx_pull_rss_config(efx);
 	if (rc)
 		return rc;
@@ -1219,70 +1171,6 @@ int efx_siena_ethtool_get_rxfh(struct net_device *net_dev,
 	return 0;
 }
 
-static int efx_siena_ethtool_set_rxfh_context(struct net_device *net_dev,
-					      struct ethtool_rxfh_param *rxfh,
-					      struct netlink_ext_ack *extack)
-{
-	struct efx_nic *efx = netdev_priv(net_dev);
-	u32 *rss_context = &rxfh->rss_context;
-	struct efx_rss_context *ctx;
-	u32 *indir = rxfh->indir;
-	bool allocated = false;
-	u8 *key = rxfh->key;
-	int rc;
-
-	if (!efx->type->rx_push_rss_context_config)
-		return -EOPNOTSUPP;
-
-	mutex_lock(&efx->rss_lock);
-
-	if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
-		if (rxfh->rss_delete) {
-			/* alloc + delete == Nothing to do */
-			rc = -EINVAL;
-			goto out_unlock;
-		}
-		ctx = efx_siena_alloc_rss_context_entry(efx);
-		if (!ctx) {
-			rc = -ENOMEM;
-			goto out_unlock;
-		}
-		ctx->context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
-		/* Initialise indir table and key to defaults */
-		efx_siena_set_default_rx_indir_table(efx, ctx);
-		netdev_rss_key_fill(ctx->rx_hash_key, sizeof(ctx->rx_hash_key));
-		allocated = true;
-	} else {
-		ctx = efx_siena_find_rss_context_entry(efx, *rss_context);
-		if (!ctx) {
-			rc = -ENOENT;
-			goto out_unlock;
-		}
-	}
-
-	if (rxfh->rss_delete) {
-		/* delete this context */
-		rc = efx->type->rx_push_rss_context_config(efx, ctx, NULL, NULL);
-		if (!rc)
-			efx_siena_free_rss_context_entry(ctx);
-		goto out_unlock;
-	}
-
-	if (!key)
-		key = ctx->rx_hash_key;
-	if (!indir)
-		indir = ctx->rx_indir_table;
-
-	rc = efx->type->rx_push_rss_context_config(efx, ctx, indir, key);
-	if (rc && allocated)
-		efx_siena_free_rss_context_entry(ctx);
-	else
-		*rss_context = ctx->user_id;
-out_unlock:
-	mutex_unlock(&efx->rss_lock);
-	return rc;
-}
-
 int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
 			       struct ethtool_rxfh_param *rxfh,
 			       struct netlink_ext_ack *extack)
@@ -1296,9 +1184,6 @@ int efx_siena_ethtool_set_rxfh(struct net_device *net_dev,
 	    rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (rxfh->rss_context)
-		efx_siena_ethtool_set_rxfh_context(net_dev, rxfh, extack);
-
 	if (!indir && !key)
 		return 0;
 
diff --git a/drivers/net/ethernet/sfc/siena/net_driver.h b/drivers/net/ethernet/sfc/siena/net_driver.h
index 94152f595acd..3fa7c652ae9b 100644
--- a/drivers/net/ethernet/sfc/siena/net_driver.h
+++ b/drivers/net/ethernet/sfc/siena/net_driver.h
@@ -707,20 +707,14 @@ struct vfdi_status;
 /* The reserved RSS context value */
 #define EFX_MCDI_RSS_CONTEXT_INVALID	0xffffffff
 /**
- * struct efx_rss_context - A user-defined RSS context for filtering
- * @list: node of linked list on which this struct is stored
- * @context_id: the RSS_CONTEXT_ID returned by MC firmware, or
- *	%EFX_MCDI_RSS_CONTEXT_INVALID if this context is not present on the NIC.
- *	For Siena, 0 if RSS is active, else %EFX_MCDI_RSS_CONTEXT_INVALID.
- * @user_id: the rss_context ID exposed to userspace over ethtool.
+ * struct efx_rss_context - An RSS context for filtering
+ * @context_id: 0 if RSS is active, else %EFX_MCDI_RSS_CONTEXT_INVALID.
  * @rx_hash_udp_4tuple: UDP 4-tuple hashing enabled
  * @rx_hash_key: Toeplitz hash key for this RSS context
  * @indir_table: Indirection table for this RSS context
  */
 struct efx_rss_context {
-	struct list_head list;
 	u32 context_id;
-	u32 user_id;
 	bool rx_hash_udp_4tuple;
 	u8 rx_hash_key[40];
 	u32 rx_indir_table[128];
@@ -851,9 +845,7 @@ enum efx_xdp_tx_queues_mode {
  * @rx_packet_ts_offset: Offset of timestamp from start of packet data
  *	(valid only if channel->sync_timestamps_enabled; always negative)
  * @rx_scatter: Scatter mode enabled for receives
- * @rss_context: Main RSS context.  Its @list member is the head of the list of
- *	RSS contexts created by user requests
- * @rss_lock: Protects custom RSS context software state in @rss_context.list
+ * @rss_context: Main RSS context
  * @vport_id: The function's vport ID, only relevant for PFs
  * @int_error_count: Number of internal errors seen recently
  * @int_error_expire: Time at which error count will be expired
@@ -1018,7 +1010,6 @@ struct efx_nic {
 	int rx_packet_ts_offset;
 	bool rx_scatter;
 	struct efx_rss_context rss_context;
-	struct mutex rss_lock;
 	u32 vport_id;
 
 	unsigned int_error_count;
@@ -1220,10 +1211,6 @@ struct efx_udp_tunnel {
  * @tx_enqueue: Add an SKB to TX queue
  * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC
  * @rx_pull_rss_config: Read RSS hash key and indirection table back from the NIC
- * @rx_push_rss_context_config: Write RSS hash key and indirection table for
- *	user RSS context to the NIC
- * @rx_pull_rss_context_config: Read RSS hash key and indirection table for user
- *	RSS context back from the NIC
  * @rx_probe: Allocate resources for RX queue
  * @rx_init: Initialise RX queue on the NIC
  * @rx_remove: Free resources for RX queue
@@ -1366,13 +1353,6 @@ struct efx_nic_type {
 	int (*rx_push_rss_config)(struct efx_nic *efx, bool user,
 				  const u32 *rx_indir_table, const u8 *key);
 	int (*rx_pull_rss_config)(struct efx_nic *efx);
-	int (*rx_push_rss_context_config)(struct efx_nic *efx,
-					  struct efx_rss_context *ctx,
-					  const u32 *rx_indir_table,
-					  const u8 *key);
-	int (*rx_pull_rss_context_config)(struct efx_nic *efx,
-					  struct efx_rss_context *ctx);
-	void (*rx_restore_rss_contexts)(struct efx_nic *efx);
 	int (*rx_probe)(struct efx_rx_queue *rx_queue);
 	void (*rx_init)(struct efx_rx_queue *rx_queue);
 	void (*rx_remove)(struct efx_rx_queue *rx_queue);
diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c
index 219fb358a646..082e35c6caaa 100644
--- a/drivers/net/ethernet/sfc/siena/rx_common.c
+++ b/drivers/net/ethernet/sfc/siena/rx_common.c
@@ -558,62 +558,6 @@ efx_siena_rx_packet_gro(struct efx_channel *channel,
 	napi_gro_frags(napi);
 }
 
-/* RSS contexts.  We're using linked lists and crappy O(n) algorithms, because
- * (a) this is an infrequent control-plane operation and (b) n is small (max 64)
- */
-struct efx_rss_context *efx_siena_alloc_rss_context_entry(struct efx_nic *efx)
-{
-	struct list_head *head = &efx->rss_context.list;
-	struct efx_rss_context *ctx, *new;
-	u32 id = 1; /* Don't use zero, that refers to the master RSS context */
-
-	WARN_ON(!mutex_is_locked(&efx->rss_lock));
-
-	/* Search for first gap in the numbering */
-	list_for_each_entry(ctx, head, list) {
-		if (ctx->user_id != id)
-			break;
-		id++;
-		/* Check for wrap.  If this happens, we have nearly 2^32
-		 * allocated RSS contexts, which seems unlikely.
-		 */
-		if (WARN_ON_ONCE(!id))
-			return NULL;
-	}
-
-	/* Create the new entry */
-	new = kmalloc(sizeof(*new), GFP_KERNEL);
-	if (!new)
-		return NULL;
-	new->context_id = EFX_MCDI_RSS_CONTEXT_INVALID;
-	new->rx_hash_udp_4tuple = false;
-
-	/* Insert the new entry into the gap */
-	new->user_id = id;
-	list_add_tail(&new->list, &ctx->list);
-	return new;
-}
-
-struct efx_rss_context *efx_siena_find_rss_context_entry(struct efx_nic *efx,
-							 u32 id)
-{
-	struct list_head *head = &efx->rss_context.list;
-	struct efx_rss_context *ctx;
-
-	WARN_ON(!mutex_is_locked(&efx->rss_lock));
-
-	list_for_each_entry(ctx, head, list)
-		if (ctx->user_id == id)
-			return ctx;
-	return NULL;
-}
-
-void efx_siena_free_rss_context_entry(struct efx_rss_context *ctx)
-{
-	list_del(&ctx->list);
-	kfree(ctx);
-}
-
 void efx_siena_set_default_rx_indir_table(struct efx_nic *efx,
 					  struct efx_rss_context *ctx)
 {
diff --git a/drivers/net/ethernet/sfc/siena/rx_common.h b/drivers/net/ethernet/sfc/siena/rx_common.h
index 6b37f83ecb30..f90a8320d396 100644
--- a/drivers/net/ethernet/sfc/siena/rx_common.h
+++ b/drivers/net/ethernet/sfc/siena/rx_common.h
@@ -78,10 +78,6 @@ efx_siena_rx_packet_gro(struct efx_channel *channel,
 			struct efx_rx_buffer *rx_buf,
 			unsigned int n_frags, u8 *eh, __wsum csum);
 
-struct efx_rss_context *efx_siena_alloc_rss_context_entry(struct efx_nic *efx);
-struct efx_rss_context *efx_siena_find_rss_context_entry(struct efx_nic *efx,
-							 u32 id);
-void efx_siena_free_rss_context_entry(struct efx_rss_context *ctx);
 void efx_siena_set_default_rx_indir_table(struct efx_nic *efx,
 					  struct efx_rss_context *ctx);
 
-- 
cgit v1.3-3-g829e


From cca0d69baf950e5a82c21d09917b4cc654c83fe9 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 4 Sep 2024 13:56:59 -0700
Subject: net: phy: qca83xx: use PHY_ID_MATCH_EXACT

No need for the mask when there's already a macro for this.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240904205659.7470-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca83xx.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/phy/qcom/qca83xx.c b/drivers/net/phy/qcom/qca83xx.c
index 5d083ef0250e..a05d0df6fa16 100644
--- a/drivers/net/phy/qcom/qca83xx.c
+++ b/drivers/net/phy/qcom/qca83xx.c
@@ -15,7 +15,6 @@
 #define QCA8327_A_PHY_ID			0x004dd033
 #define QCA8327_B_PHY_ID			0x004dd034
 #define QCA8337_PHY_ID				0x004dd036
-#define QCA8K_PHY_ID_MASK			0xffffffff
 
 #define QCA8K_DEVFLAGS_REVISION_MASK		GENMASK(2, 0)
 
@@ -216,8 +215,7 @@ static int qca8327_suspend(struct phy_device *phydev)
 static struct phy_driver qca83xx_driver[] = {
 {
 	/* QCA8337 */
-	.phy_id			= QCA8337_PHY_ID,
-	.phy_id_mask		= QCA8K_PHY_ID_MASK,
+	PHY_ID_MATCH_EXACT(QCA8337_PHY_ID),
 	.name			= "Qualcomm Atheros 8337 internal PHY",
 	/* PHY_GBIT_FEATURES */
 	.probe			= qca83xx_probe,
@@ -231,8 +229,7 @@ static struct phy_driver qca83xx_driver[] = {
 	.resume			= qca83xx_resume,
 }, {
 	/* QCA8327-A from switch QCA8327-AL1A */
-	.phy_id			= QCA8327_A_PHY_ID,
-	.phy_id_mask		= QCA8K_PHY_ID_MASK,
+	PHY_ID_MATCH_EXACT(QCA8327_A_PHY_ID),
 	.name			= "Qualcomm Atheros 8327-A internal PHY",
 	/* PHY_GBIT_FEATURES */
 	.link_change_notify	= qca83xx_link_change_notify,
@@ -247,8 +244,7 @@ static struct phy_driver qca83xx_driver[] = {
 	.resume			= qca83xx_resume,
 }, {
 	/* QCA8327-B from switch QCA8327-BL1A */
-	.phy_id			= QCA8327_B_PHY_ID,
-	.phy_id_mask		= QCA8K_PHY_ID_MASK,
+	PHY_ID_MATCH_EXACT(QCA8327_B_PHY_ID),
 	.name			= "Qualcomm Atheros 8327-B internal PHY",
 	/* PHY_GBIT_FEATURES */
 	.link_change_notify	= qca83xx_link_change_notify,
-- 
cgit v1.3-3-g829e


From 92218f108f510ac66715a7700479acacb18335f5 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 4 Sep 2024 19:29:36 +0100
Subject: octeontx2-af: Pass string literal as format argument of
 alloc_workqueue()

Recently I noticed that both gcc-14 and clang-18 report that passing
a non-string literal as the format argument of alloc_workqueue()
is potentially insecure.

E.g. clang-18 says:

.../rvu.c:2493:32: warning: format string is not a string literal (potentially insecure) [-Wformat-security]
 2493 |         mw->mbox_wq = alloc_workqueue(name,
      |                                       ^~~~
.../rvu.c:2493:32: note: treat the string as an argument to avoid this
 2493 |         mw->mbox_wq = alloc_workqueue(name,
      |                                       ^
      |                                       "%s",

It is always the case where the contents of name is safe to pass as the
format argument. That is, in my understanding, it never contains any
format escape sequences.

But, it seems better to be safe than sorry. And, as a bonus, compiler
output becomes less verbose by addressing this issue as suggested by
clang-18.

Compile tested only by author.

Tested-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240904-octeontx2-sparse-v2-1-14f2305fe4b2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index ac7ee3f3598c..1a97fb9032fa 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -2479,9 +2479,9 @@ static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
 		goto free_regions;
 	}
 
-	mw->mbox_wq = alloc_workqueue(name,
+	mw->mbox_wq = alloc_workqueue("%s",
 				      WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
-				      num);
+				      num, name);
 	if (!mw->mbox_wq) {
 		err = -ENOMEM;
 		goto unmap_regions;
-- 
cgit v1.3-3-g829e


From 7baa90c616e54defe0dc645d2f2cdcc77b05855f Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 4 Sep 2024 19:29:37 +0100
Subject: octeontx2-pf: Make iplen __be16 in otx2_sqe_add_ext()

In otx2_sqe_add_ext() iplen is used to hold a 16-bit big-endian value,
but it's type is u16, indicating a host byte order integer.

Address this mismatch by changing the type of iplen to __be16.

Flagged by Sparse as:

.../otx2_txrx.c:699:31: warning: incorrect type in assignment (different base types)
.../otx2_txrx.c:699:31:    expected unsigned short [usertype] iplen
.../otx2_txrx.c:699:31:    got restricted __be16 [usertype]
.../otx2_txrx.c:701:54: warning: incorrect type in assignment (different base types)
.../otx2_txrx.c:701:54:    expected restricted __be16 [usertype] tot_len
.../otx2_txrx.c:701:54:    got unsigned short [usertype] iplen
.../otx2_txrx.c:704:60: warning: incorrect type in assignment (different base types)
.../otx2_txrx.c:704:60:    expected restricted __be16 [usertype] payload_len
.../otx2_txrx.c:704:60:    got unsigned short [usertype] iplen

Introduced in
commit dc1a9bf2c816 ("octeontx2-pf: Add UDP segmentation offload support")

No functional change intended.
Compile tested only by author.

Tested-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240904-octeontx2-sparse-v2-2-14f2305fe4b2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 3eb85949677a..933e18ba2fb2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -687,7 +687,7 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq,
 		} else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
 			__be16 l3_proto = vlan_get_protocol(skb);
 			struct udphdr *udph = udp_hdr(skb);
-			u16 iplen;
+			__be16 iplen;
 
 			ext->lso_sb = skb_transport_offset(skb) +
 					sizeof(struct udphdr);
-- 
cgit v1.3-3-g829e


From 9a95eedc81deb86af1ac56f2c2bfe8306b27b82a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 5 Sep 2024 08:49:09 +0000
Subject: netpoll: remove netpoll_srcu

netpoll_srcu is currently used from netpoll_poll_disable() and
__netpoll_cleanup()

Both functions run under RTNL, using netpoll_srcu adds confusion
and no additional protection.

Moreover the synchronize_srcu() call in __netpoll_cleanup() is
performed before clearing np->dev->npinfo, which violates RCU rules.

After this patch, netpoll_poll_disable() and netpoll_poll_enable()
simply use rtnl_dereference().

This saves a big chunk of memory (more than 192KB on platforms
with 512 cpus)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20240905084909.2082486-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netpoll.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e0720ee6fa62..ca52cbe0f63c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -48,8 +48,6 @@
 
 static struct sk_buff_head skb_pool;
 
-DEFINE_STATIC_SRCU(netpoll_srcu);
-
 #define USEC_PER_POLL	50
 
 #define MAX_SKB_SIZE							\
@@ -220,23 +218,20 @@ EXPORT_SYMBOL(netpoll_poll_dev);
 void netpoll_poll_disable(struct net_device *dev)
 {
 	struct netpoll_info *ni;
-	int idx;
+
 	might_sleep();
-	idx = srcu_read_lock(&netpoll_srcu);
-	ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
+	ni = rtnl_dereference(dev->npinfo);
 	if (ni)
 		down(&ni->dev_lock);
-	srcu_read_unlock(&netpoll_srcu, idx);
 }
 
 void netpoll_poll_enable(struct net_device *dev)
 {
 	struct netpoll_info *ni;
-	rcu_read_lock();
-	ni = rcu_dereference(dev->npinfo);
+
+	ni = rtnl_dereference(dev->npinfo);
 	if (ni)
 		up(&ni->dev_lock);
-	rcu_read_unlock();
 }
 
 static void refill_skbs(void)
@@ -829,8 +824,6 @@ void __netpoll_cleanup(struct netpoll *np)
 	if (!npinfo)
 		return;
 
-	synchronize_srcu(&netpoll_srcu);
-
 	if (refcount_dec_and_test(&npinfo->refcnt)) {
 		const struct net_device_ops *ops;
 
-- 
cgit v1.3-3-g829e


From aa05fe67bcd641378454ca9d15b539125eb0933a Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Date: Thu, 5 Sep 2024 14:00:28 +0000
Subject: ptp: ocp: Improve PCIe delay estimation

The PCIe bus can be pretty busy during boot and probe function can
see excessive delays. Let's find the minimal value out of several
tests and use it as estimated value.

Signed-off-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20240905140028.560454-1-vadim.fedorenko@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_ocp.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index e7479b9b90cb..5feecaadde8e 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -1558,22 +1558,24 @@ ptp_ocp_watchdog(struct timer_list *t)
 static void
 ptp_ocp_estimate_pci_timing(struct ptp_ocp *bp)
 {
-	ktime_t start, end;
-	ktime_t delay;
+	ktime_t start, end, delay = U64_MAX;
 	u32 ctrl;
+	int i;
 
-	ctrl = ioread32(&bp->reg->ctrl);
-	ctrl = OCP_CTRL_READ_TIME_REQ | OCP_CTRL_ENABLE;
+	for (i = 0; i < 3; i++) {
+		ctrl = ioread32(&bp->reg->ctrl);
+		ctrl = OCP_CTRL_READ_TIME_REQ | OCP_CTRL_ENABLE;
 
-	iowrite32(ctrl, &bp->reg->ctrl);
+		iowrite32(ctrl, &bp->reg->ctrl);
 
-	start = ktime_get_ns();
+		start = ktime_get_raw_ns();
 
-	ctrl = ioread32(&bp->reg->ctrl);
+		ctrl = ioread32(&bp->reg->ctrl);
 
-	end = ktime_get_ns();
+		end = ktime_get_raw_ns();
 
-	delay = end - start;
+		delay = min(delay, end - start);
+	}
 	bp->ts_window_adjust = (delay >> 5) * 3;
 }
 
-- 
cgit v1.3-3-g829e


From d5c4546062fd6f5dbce575c7ea52ad66d1968678 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 4 Sep 2024 14:54:01 +0300
Subject: net: sched: consistently use rcu_replace_pointer() in taprio_change()

According to Vinicius (and carefully looking through the whole
https://syzkaller.appspot.com/bug?extid=b65e0af58423fc8a73aa
once again), txtime branch of 'taprio_change()' is not going to
race against 'advance_sched()'. But using 'rcu_replace_pointer()'
in the former may be a good idea as well.

Suggested-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index cc2df9f8c14a..8498d0606b24 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1952,7 +1952,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			goto unlock;
 		}
 
-		rcu_assign_pointer(q->admin_sched, new_admin);
+		/* Not going to race against advance_sched(), but still */
+		admin = rcu_replace_pointer(q->admin_sched, new_admin,
+					    lockdep_rtnl_is_held());
 		if (admin)
 			call_rcu(&admin->rcu, taprio_free_sched_cb);
 	} else {
-- 
cgit v1.3-3-g829e


From c259acab839e57eab0318f32da4ae803a8d59397 Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Wed, 4 Sep 2024 07:13:05 -0700
Subject: ptp/ioctl: support MONOTONIC{,_RAW} timestamps for
 PTP_SYS_OFFSET_EXTENDED

The ability to read the PHC (Physical Hardware Clock) alongside
multiple system clocks is currently dependent on the specific
hardware architecture. This limitation restricts the use of
PTP_SYS_OFFSET_PRECISE to certain hardware configurations.

The generic soultion which would work across all architectures
is to read the PHC along with the latency to perform PHC-read as
offered by PTP_SYS_OFFSET_EXTENDED which provides pre and post
timestamps.  However, these timestamps are currently limited
to the CLOCK_REALTIME timebase. Since CLOCK_REALTIME is affected
by NTP (or similar time synchronization services), it can
experience significant jumps forward or backward. This hinders
the precise latency measurements that PTP_SYS_OFFSET_EXTENDED
is designed to provide.

This problem could be addressed by supporting MONOTONIC_RAW
timestamps within PTP_SYS_OFFSET_EXTENDED. Unlike CLOCK_REALTIME
or CLOCK_MONOTONIC, the MONOTONIC_RAW timebase is unaffected
by NTP adjustments.

This enhancement can be implemented by utilizing one of the three
reserved words within the PTP_SYS_OFFSET_EXTENDED struct to pass
the clock-id for timestamps.  The current behavior aligns with
clock-id for CLOCK_REALTIME timebase (value of 0), ensuring
backward compatibility of the UAPI.

Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: Vadim Fedorenko <vadfed@meta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c        |  8 ++++++--
 include/linux/ptp_clock_kernel.h | 36 ++++++++++++++++++++++++++++++++----
 include/uapi/linux/ptp_clock.h   | 24 ++++++++++++++++++------
 3 files changed, 56 insertions(+), 12 deletions(-)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 2067b0120d08..ea96a14d72d1 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -359,11 +359,15 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 			extoff = NULL;
 			break;
 		}
-		if (extoff->n_samples > PTP_MAX_SAMPLES
-		    || extoff->rsv[0] || extoff->rsv[1] || extoff->rsv[2]) {
+		if (extoff->n_samples > PTP_MAX_SAMPLES ||
+		    extoff->rsv[0] || extoff->rsv[1] ||
+		    (extoff->clockid != CLOCK_REALTIME &&
+		     extoff->clockid != CLOCK_MONOTONIC &&
+		     extoff->clockid != CLOCK_MONOTONIC_RAW)) {
 			err = -EINVAL;
 			break;
 		}
+		sts.clockid = extoff->clockid;
 		for (i = 0; i < extoff->n_samples; i++) {
 			err = ptp->info->gettimex64(ptp->info, &ts, &sts);
 			if (err)
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 6e4b8206c7d0..c892d22ce0a7 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -47,10 +47,12 @@ struct system_device_crosststamp;
  * struct ptp_system_timestamp - system time corresponding to a PHC timestamp
  * @pre_ts: system timestamp before capturing PHC
  * @post_ts: system timestamp after capturing PHC
+ * @clockid: clock-base used for capturing the system timestamps
  */
 struct ptp_system_timestamp {
 	struct timespec64 pre_ts;
 	struct timespec64 post_ts;
+	clockid_t clockid;
 };
 
 /**
@@ -457,14 +459,40 @@ static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp,
 
 static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts)
 {
-	if (sts)
-		ktime_get_real_ts64(&sts->pre_ts);
+	if (sts) {
+		switch (sts->clockid) {
+		case CLOCK_REALTIME:
+			ktime_get_real_ts64(&sts->pre_ts);
+			break;
+		case CLOCK_MONOTONIC:
+			ktime_get_ts64(&sts->pre_ts);
+			break;
+		case CLOCK_MONOTONIC_RAW:
+			ktime_get_raw_ts64(&sts->pre_ts);
+			break;
+		default:
+			break;
+		}
+	}
 }
 
 static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts)
 {
-	if (sts)
-		ktime_get_real_ts64(&sts->post_ts);
+	if (sts) {
+		switch (sts->clockid) {
+		case CLOCK_REALTIME:
+			ktime_get_real_ts64(&sts->post_ts);
+			break;
+		case CLOCK_MONOTONIC:
+			ktime_get_ts64(&sts->post_ts);
+			break;
+		case CLOCK_MONOTONIC_RAW:
+			ktime_get_raw_ts64(&sts->post_ts);
+			break;
+		default:
+			break;
+		}
+	}
 }
 
 #endif
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index 053b40d642de..18eefa6d93d6 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -155,13 +155,25 @@ struct ptp_sys_offset {
 	struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
 };
 
+/*
+ * ptp_sys_offset_extended - data structure for IOCTL operation
+ *			     PTP_SYS_OFFSET_EXTENDED
+ *
+ * @n_samples:	Desired number of measurements.
+ * @clockid:	clockid of a clock-base used for pre/post timestamps.
+ * @rsv:	Reserved for future use.
+ * @ts:		Array of samples in the form [pre-TS, PHC, post-TS]. The
+ *		kernel provides @n_samples.
+ *
+ * Starting from kernel 6.12 and onwards, the first word of the reserved-field
+ * is used for @clockid. That's backward compatible since previous kernel
+ * expect all three reserved words (@rsv[3]) to be 0 while the clockid (first
+ * word in the new structure) for CLOCK_REALTIME is '0'.
+ */
 struct ptp_sys_offset_extended {
-	unsigned int n_samples; /* Desired number of measurements. */
-	unsigned int rsv[3];    /* Reserved for future use. */
-	/*
-	 * Array of [system, phc, system] time stamps. The kernel will provide
-	 * 3*n_samples time stamps.
-	 */
+	unsigned int n_samples;
+	__kernel_clockid_t clockid;
+	unsigned int rsv[2];
 	struct ptp_clock_time ts[PTP_MAX_SAMPLES][3];
 };
 
-- 
cgit v1.3-3-g829e


From dfb970cc5f612a95fdf142f34610fccb3b2fc18c Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Tue, 3 Sep 2024 08:57:30 -0500
Subject: net: can: cc770: Simplify parsing DT properties

Use of the typed property accessors is preferred over of_get_property().
The existing code doesn't work on little endian systems either. Replace
the of_get_property() calls with of_property_read_bool() and
of_property_read_u32().

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20240903135731.405635-1-robh@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/cc770/cc770_platform.c | 32 +++++++++++---------------------
 1 file changed, 11 insertions(+), 21 deletions(-)

diff --git a/drivers/net/can/cc770/cc770_platform.c b/drivers/net/can/cc770/cc770_platform.c
index 13bcfba05f18..f2424fe58612 100644
--- a/drivers/net/can/cc770/cc770_platform.c
+++ b/drivers/net/can/cc770/cc770_platform.c
@@ -70,17 +70,10 @@ static void cc770_platform_write_reg(const struct cc770_priv *priv, int reg,
 static int cc770_get_of_node_data(struct platform_device *pdev,
 				  struct cc770_priv *priv)
 {
+	u32 clkext = CC770_PLATFORM_CAN_CLOCK, clkout = 0;
 	struct device_node *np = pdev->dev.of_node;
-	const u32 *prop;
-	int prop_size;
-	u32 clkext;
-
-	prop = of_get_property(np, "bosch,external-clock-frequency",
-			       &prop_size);
-	if (prop && (prop_size ==  sizeof(u32)))
-		clkext = *prop;
-	else
-		clkext = CC770_PLATFORM_CAN_CLOCK; /* default */
+
+	of_property_read_u32(np, "bosch,external-clock-frequency", &clkext);
 	priv->can.clock.freq = clkext;
 
 	/* The system clock may not exceed 10 MHz */
@@ -98,7 +91,7 @@ static int cc770_get_of_node_data(struct platform_device *pdev,
 	if (of_property_read_bool(np, "bosch,iso-low-speed-mux"))
 		priv->cpu_interface |= CPUIF_MUX;
 
-	if (!of_get_property(np, "bosch,no-comperator-bypass", NULL))
+	if (!of_property_read_bool(np, "bosch,no-comperator-bypass"))
 		priv->bus_config |= BUSCFG_CBY;
 	if (of_property_read_bool(np, "bosch,disconnect-rx0-input"))
 		priv->bus_config |= BUSCFG_DR0;
@@ -109,25 +102,22 @@ static int cc770_get_of_node_data(struct platform_device *pdev,
 	if (of_property_read_bool(np, "bosch,polarity-dominant"))
 		priv->bus_config |= BUSCFG_POL;
 
-	prop = of_get_property(np, "bosch,clock-out-frequency", &prop_size);
-	if (prop && (prop_size == sizeof(u32)) && *prop > 0) {
-		u32 cdv = clkext / *prop;
-		int slew;
+	of_property_read_u32(np, "bosch,clock-out-frequency", &clkout);
+	if (clkout > 0) {
+		u32 cdv = clkext / clkout;
 
 		if (cdv > 0 && cdv < 16) {
+			u32 slew;
+
 			priv->cpu_interface |= CPUIF_CEN;
 			priv->clkout |= (cdv - 1) & CLKOUT_CD_MASK;
 
-			prop = of_get_property(np, "bosch,slew-rate",
-					       &prop_size);
-			if (prop && (prop_size == sizeof(u32))) {
-				slew = *prop;
-			} else {
+			if (of_property_read_u32(np, "bosch,slew-rate", &slew)) {
 				/* Determine default slew rate */
 				slew = (CLKOUT_SL_MASK >>
 					CLKOUT_SL_SHIFT) -
 					((cdv * clkext - 1) / 8000000);
-				if (slew < 0)
+				if (slew > (CLKOUT_SL_MASK >> CLKOUT_SL_SHIFT))
 					slew = 0;
 			}
 			priv->clkout |= (slew << CLKOUT_SL_SHIFT) &
-- 
cgit v1.3-3-g829e


From 9a0e4c18cdec39b1d724703180e29156d86bb94b Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 6 Sep 2024 13:26:41 -0700
Subject: can: rockchip_canfd: fix return type of rkcanfd_start_xmit()

With clang's kernel control flow integrity (kCFI, CONFIG_CFI_CLANG),
indirect call targets are validated against the expected function
pointer prototype to make sure the call target is valid to help mitigate
ROP attacks. If they are not identical, there is a failure at run time,
which manifests as either a kernel panic or thread getting killed. A
warning in clang aims to catch these at compile time, which reveals:

  drivers/net/can/rockchip/rockchip_canfd-core.c:770:20: error: incompatible function pointer types initializing 'netdev_tx_t (*)(struct sk_buff *, struct net_device *)' (aka 'enum netdev_tx (*)(struct sk_buff *, struct net_device *)') with an expression of type 'int (struct sk_buff *, struct net_device *)' [-Werror,-Wincompatible-function-pointer-types-strict]
    770 |         .ndo_start_xmit = rkcanfd_start_xmit,
        |                           ^~~~~~~~~~~~~~~~~~

->ndo_start_xmit() in 'struct net_device_ops' expects a return type of
'netdev_tx_t', not 'int' (although the types are ABI compatible). Adjust
the return type of rkcanfd_start_xmit() to match the prototype's to
resolve the warning.

Fixes: ff60bfbaf67f ("can: rockchip_canfd: add driver for Rockchip CAN-FD controller")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://patch.msgid.link/20240906-rockchip-canfd-wifpts-v1-1-b1398da865b7@kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 2 +-
 drivers/net/can/rockchip/rockchip_canfd.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index f954f38b955f..865a15e033a9 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -63,7 +63,7 @@ void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
 }
 
-int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct rkcanfd_priv *priv = netdev_priv(ndev);
 	u32 reg_frameinfo, reg_id, reg_cmd;
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 3efd7f174e14..93131c7d7f54 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -546,7 +546,7 @@ void rkcanfd_timestamp_stop_sync(struct rkcanfd_priv *priv);
 
 unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv);
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv);
-int rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 				unsigned int *frame_len_p);
 
-- 
cgit v1.3-3-g829e


From 9c100bc3ec13914f9911a937ec5b38182a5c3d64 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sun, 8 Sep 2024 17:00:00 +0200
Subject: can: rockchip_canfd: rkcanfd_timestamp_init(): fix 64 bit division on
 32 bit platforms

On some 32-bit platforms (at least on parisc), the compiler generates
a call to __divdi3() from the u32 by 3 division in
rkcanfd_timestamp_init(), which results in the following linker
error:

| ERROR: modpost: "__divdi3" [drivers/net/can/rockchip/rockchip_canfd.ko] undefined!

As this code doesn't run in the hot path, a 64 bit by 32 bit division
is OK, even on 32 bit platforms. Use an explicit call to div_u64() to
fix linking.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202409072304.lCQWyNLU-lkp@intel.com/
Link: https://patch.msgid.link/20240909-can-rockchip_canfd-fix-64-bit-division-v1-1-2748d9422b00@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-timestamp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
index 81cccc5fd838..fb1a8f4e6217 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -71,7 +71,7 @@ void rkcanfd_timestamp_init(struct rkcanfd_priv *priv)
 
 	max_cycles = div_u64(ULLONG_MAX, cc->mult);
 	max_cycles = min(max_cycles, cc->mask);
-	work_delay_ns = clocksource_cyc2ns(max_cycles, cc->mult, cc->shift) / 3;
+	work_delay_ns = div_u64(clocksource_cyc2ns(max_cycles, cc->mult, cc->shift), 3);
 	priv->work_delay_jiffies = nsecs_to_jiffies(work_delay_ns);
 	INIT_DELAYED_WORK(&priv->timestamp, rkcanfd_timestamp_work);
 
-- 
cgit v1.3-3-g829e


From 4e1b5586051f0e9aef9b0ca375ef2cd1a8987e0c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 9 Sep 2024 11:03:08 +0200
Subject: wifi: cfg80211: fix kernel-doc for per-link data

There cannot be brackets in kernel-doc, remove them.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 62c16f219a73 ("wifi: cfg80211: move DFS related members to links[] in wireless_dev")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index efdea667cb92..69ec1eb41a09 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6217,11 +6217,11 @@ enum ieee80211_ap_reg_power {
  *	unprotected beacon report
  * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr
  *	@ap and @client for each link
- * @links[].cac_started: true if DFS channel availability check has been
+ * @links.cac_started: true if DFS channel availability check has been
  *	started
- * @links[].cac_start_time: timestamp (jiffies) when the dfs state was
+ * @links.cac_start_time: timestamp (jiffies) when the dfs state was
  *	entered.
- * @links[].cac_time_ms: CAC time in ms
+ * @links.cac_time_ms: CAC time in ms
  * @valid_links: bitmap describing what elements of @links are valid
  */
 struct wireless_dev {
-- 
cgit v1.3-3-g829e


From 30ba6d2f3463ee296243cbcb628f7122c49db4a7 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:14 +0200
Subject: net: ethernet: fs_enet: convert to SPDX

The ENET driver has SPDX tags in the header files, but they were missing
in the C files. Change the licence information to SPDX format.

Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 5 +----
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c      | 5 +----
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c      | 5 +----
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c      | 5 +----
 drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c  | 5 +----
 drivers/net/ethernet/freescale/fs_enet/mii-fec.c      | 5 +----
 6 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index cf392faa6105..5bfdd43ffdeb 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Combined Ethernet driver for Motorola MPC8xx and MPC82xx.
  *
@@ -9,10 +10,6 @@
  *
  * Heavily based on original FEC driver by Dan Malek <dan@embeddededge.com>
  * and modifications by Joakim Tjernlund <joakim.tjernlund@lumentis.se>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index e2ffac9eb2ad..add062928d99 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * FCC driver for Motorola MPC82xx (PQ2).
  *
@@ -6,10 +7,6 @@
  *
  * 2005 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index cdc89d83cf07..f75acb3b358f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Freescale Ethernet controllers
  *
@@ -6,10 +7,6 @@
  *
  * 2005 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 9e89ac2b6ce3..29ba0048396b 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Ethernet on Serial Communications Controller (SCC) driver for Motorola MPC8xx and MPC82xx.
  *
@@ -6,10 +7,6 @@
  *
  * 2005 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
index f965a2329055..2e210a003558 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Combined Ethernet driver for Motorola MPC8xx and MPC82xx.
  *
@@ -6,10 +7,6 @@
  *
  * 2005 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index 7bb69727952a..93d91e8ad0de 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Combined Ethernet driver for Motorola MPC8xx and MPC82xx.
  *
@@ -6,10 +7,6 @@
  *
  * 2005 (c) MontaVista Software, Inc.
  * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #include <linux/module.h>
-- 
cgit v1.3-3-g829e


From 2b29ac68e786d8d16772bb92eee88ed7beda5d0d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:15 +0200
Subject: net: ethernet: fs_enet: cosmetic cleanups

Due to the age of the driver and the slow recent activity on it, the code
has taken some layers of dust. Clean the main driver file up so that it
passes checkpatch and also conforms with the net coding style.

Changes include :
 - Re-ordering of the variable declarations for RCT
 - Fixing the comment styles to either one-line comments, or net-style
   comments
 - Adding braces around single-statement 'else' clauses
 - Aligning function/macro parameters on the opening parenthesis
 - Simplifying checks for NULL pointers
 - Splitting cascaded assignments into individual assignments
 - Fixing some typos
 - Fixing whitespace issues

This is a cosmetic change and doesn't introduce any change in behaviour.

Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/freescale/fs_enet/fs_enet-main.c  | 220 +++++++++------------
 1 file changed, 89 insertions(+), 131 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 5bfdd43ffdeb..2b48a2a5e32d 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -81,15 +81,14 @@ static void skb_align(struct sk_buff *skb, int align)
 static int fs_enet_napi(struct napi_struct *napi, int budget)
 {
 	struct fs_enet_private *fep = container_of(napi, struct fs_enet_private, napi);
-	struct net_device *dev = fep->ndev;
 	const struct fs_platform_info *fpi = fep->fpi;
-	cbd_t __iomem *bdp;
+	struct net_device *dev = fep->ndev;
+	int curidx, dirtyidx, received = 0;
+	int do_wake = 0, do_restart = 0;
+	int tx_left = TX_RING_SIZE;
 	struct sk_buff *skb, *skbn;
-	int received = 0;
+	cbd_t __iomem *bdp;
 	u16 pkt_len, sc;
-	int curidx;
-	int dirtyidx, do_wake, do_restart;
-	int tx_left = TX_RING_SIZE;
 
 	spin_lock(&fep->tx_lock);
 	bdp = fep->dirty_tx;
@@ -97,7 +96,6 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 	/* clear status bits for napi*/
 	(*fep->ops->napi_clear_event)(dev);
 
-	do_wake = do_restart = 0;
 	while (((sc = CBDR_SC(bdp)) & BD_ENET_TX_READY) == 0 && tx_left) {
 		dirtyidx = bdp - fep->tx_bd_base;
 
@@ -106,12 +104,9 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 
 		skb = fep->tx_skbuff[dirtyidx];
 
-		/*
-		 * Check for errors.
-		 */
+		 /* Check for errors. */
 		if (sc & (BD_ENET_TX_HB | BD_ENET_TX_LC |
 			  BD_ENET_TX_RL | BD_ENET_TX_UN | BD_ENET_TX_CSL)) {
-
 			if (sc & BD_ENET_TX_HB)	/* No heartbeat */
 				dev->stats.tx_heartbeat_errors++;
 			if (sc & BD_ENET_TX_LC)	/* Late collision */
@@ -127,16 +122,16 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 				dev->stats.tx_errors++;
 				do_restart = 1;
 			}
-		} else
+		} else {
 			dev->stats.tx_packets++;
+		}
 
 		if (sc & BD_ENET_TX_READY) {
 			dev_warn(fep->dev,
 				 "HEY! Enet xmit interrupt and TX_READY.\n");
 		}
 
-		/*
-		 * Deferred means some collisions occurred during transmit,
+		/* Deferred means some collisions occurred during transmit,
 		 * but we eventually sent the packet OK.
 		 */
 		if (sc & BD_ENET_TX_DEF)
@@ -150,25 +145,20 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 			dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp),
 					 CBDR_DATLEN(bdp), DMA_TO_DEVICE);
 
-		/*
-		 * Free the sk buffer associated with this last transmit.
-		 */
+		/* Free the sk buffer associated with this last transmit. */
 		if (skb) {
 			dev_kfree_skb(skb);
 			fep->tx_skbuff[dirtyidx] = NULL;
 		}
 
-		/*
-		 * Update pointer to next buffer descriptor to be transmitted.
+		/* Update pointer to next buffer descriptor to be transmitted.
 		 */
 		if ((sc & BD_ENET_TX_WRAP) == 0)
 			bdp++;
 		else
 			bdp = fep->tx_bd_base;
 
-		/*
-		 * Since we have freed up a buffer, the ring is no longer
-		 * full.
+		/* Since we have freed up a buffer, the ring is no longer full.
 		 */
 		if (++fep->tx_free == MAX_SKB_FRAGS)
 			do_wake = 1;
@@ -185,8 +175,7 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 	if (do_wake)
 		netif_wake_queue(dev);
 
-	/*
-	 * First, grab all of the stats for the incoming packet.
+	/* First, grab all of the stats for the incoming packet.
 	 * These get messed up if we get called due to a busy condition.
 	 */
 	bdp = fep->cur_rx;
@@ -195,16 +184,13 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 	       received < budget) {
 		curidx = bdp - fep->rx_bd_base;
 
-		/*
-		 * Since we have allocated space to hold a complete frame,
+		/* Since we have allocated space to hold a complete frame,
 		 * the last indicator should be set.
 		 */
 		if ((sc & BD_ENET_RX_LAST) == 0)
 			dev_warn(fep->dev, "rcv is not +last\n");
 
-		/*
-		 * Check for errors.
-		 */
+		/* Check for errors. */
 		if (sc & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_CL |
 			  BD_ENET_RX_NO | BD_ENET_RX_CR | BD_ENET_RX_OV)) {
 			dev->stats.rx_errors++;
@@ -225,9 +211,7 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 		} else {
 			skb = fep->rx_skbuff[curidx];
 
-			/*
-			 * Process the incoming frame.
-			 */
+			/* Process the incoming frame */
 			dev->stats.rx_packets++;
 			pkt_len = CBDR_DATLEN(bdp) - 4;	/* remove CRC */
 			dev->stats.rx_bytes += pkt_len + 4;
@@ -235,15 +219,15 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 			if (pkt_len <= fpi->rx_copybreak) {
 				/* +2 to make IP header L1 cache aligned */
 				skbn = netdev_alloc_skb(dev, pkt_len + 2);
-				if (skbn != NULL) {
+				if (skbn) {
 					skb_reserve(skbn, 2);	/* align IP header */
-					skb_copy_from_linear_data(skb,
-						      skbn->data, pkt_len);
+					skb_copy_from_linear_data(skb, skbn->data,
+								  pkt_len);
 					swap(skb, skbn);
 					dma_sync_single_for_cpu(fep->dev,
-						CBDR_BUFADDR(bdp),
-						L1_CACHE_ALIGN(pkt_len),
-						DMA_FROM_DEVICE);
+								CBDR_BUFADDR(bdp),
+								L1_CACHE_ALIGN(pkt_len),
+								DMA_FROM_DEVICE);
 				}
 			} else {
 				skbn = netdev_alloc_skb(dev, ENET_RX_FRSIZE);
@@ -253,20 +237,18 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 
 					skb_align(skbn, ENET_RX_ALIGN);
 
-					dma_unmap_single(fep->dev,
-						CBDR_BUFADDR(bdp),
-						L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-						DMA_FROM_DEVICE);
+					dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp),
+							 L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
+							 DMA_FROM_DEVICE);
 
-					dma = dma_map_single(fep->dev,
-						skbn->data,
-						L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-						DMA_FROM_DEVICE);
+					dma = dma_map_single(fep->dev, skbn->data,
+							     L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
+							     DMA_FROM_DEVICE);
 					CBDW_BUFADDR(bdp, dma);
 				}
 			}
 
-			if (skbn != NULL) {
+			if (skbn) {
 				skb_put(skb, pkt_len);	/* Make room */
 				skb->protocol = eth_type_trans(skb, dev);
 				received++;
@@ -281,9 +263,7 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 		CBDW_DATLEN(bdp, 0);
 		CBDW_SC(bdp, (sc & ~BD_ENET_RX_STATS) | BD_ENET_RX_EMPTY);
 
-		/*
-		 * Update BD pointer to next entry.
-		 */
+		/* Update BD pointer to next entry */
 		if ((sc & BD_ENET_RX_WRAP) == 0)
 			bdp++;
 		else
@@ -305,19 +285,16 @@ static int fs_enet_napi(struct napi_struct *napi, int budget)
 	return budget;
 }
 
-/*
- * The interrupt handler.
+/* The interrupt handler.
  * This is called from the MPC core interrupt.
  */
 static irqreturn_t
 fs_enet_interrupt(int irq, void *dev_id)
 {
 	struct net_device *dev = dev_id;
+	u32 int_events, int_clr_events;
 	struct fs_enet_private *fep;
-	u32 int_events;
-	u32 int_clr_events;
-	int nr, napi_ok;
-	int handled;
+	int nr, napi_ok, handled;
 
 	fep = netdev_priv(dev);
 
@@ -339,12 +316,12 @@ fs_enet_interrupt(int irq, void *dev_id)
 			(*fep->ops->napi_disable)(dev);
 			(*fep->ops->clear_int_events)(dev, fep->ev_napi);
 
-			/* NOTE: it is possible for FCCs in NAPI mode    */
-			/* to submit a spurious interrupt while in poll  */
+			/* NOTE: it is possible for FCCs in NAPI mode
+			 * to submit a spurious interrupt while in poll
+			 */
 			if (napi_ok)
 				__napi_schedule(&fep->napi);
 		}
-
 	}
 
 	handled = nr > 0;
@@ -354,45 +331,40 @@ fs_enet_interrupt(int irq, void *dev_id)
 void fs_init_bds(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
-	cbd_t __iomem *bdp;
 	struct sk_buff *skb;
+	cbd_t __iomem *bdp;
 	int i;
 
 	fs_cleanup_bds(dev);
 
-	fep->dirty_tx = fep->cur_tx = fep->tx_bd_base;
+	fep->dirty_tx = fep->tx_bd_base;
+	fep->cur_tx = fep->tx_bd_base;
 	fep->tx_free = fep->tx_ring;
 	fep->cur_rx = fep->rx_bd_base;
 
-	/*
-	 * Initialize the receive buffer descriptors.
-	 */
+	/* Initialize the receive buffer descriptors */
 	for (i = 0, bdp = fep->rx_bd_base; i < fep->rx_ring; i++, bdp++) {
 		skb = netdev_alloc_skb(dev, ENET_RX_FRSIZE);
-		if (skb == NULL)
+		if (!skb)
 			break;
 
 		skb_align(skb, ENET_RX_ALIGN);
 		fep->rx_skbuff[i] = skb;
-		CBDW_BUFADDR(bdp,
-			dma_map_single(fep->dev, skb->data,
-				L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-				DMA_FROM_DEVICE));
+		CBDW_BUFADDR(bdp, dma_map_single(fep->dev, skb->data,
+						 L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
+						 DMA_FROM_DEVICE));
 		CBDW_DATLEN(bdp, 0);	/* zero */
 		CBDW_SC(bdp, BD_ENET_RX_EMPTY |
 			((i < fep->rx_ring - 1) ? 0 : BD_SC_WRAP));
 	}
-	/*
-	 * if we failed, fillup remainder
-	 */
+
+	/* if we failed, fillup remainder */
 	for (; i < fep->rx_ring; i++, bdp++) {
 		fep->rx_skbuff[i] = NULL;
 		CBDW_SC(bdp, (i < fep->rx_ring - 1) ? 0 : BD_SC_WRAP);
 	}
 
-	/*
-	 * ...and the same for transmit.
-	 */
+	/* ...and the same for transmit. */
 	for (i = 0, bdp = fep->tx_bd_base; i < fep->tx_ring; i++, bdp++) {
 		fep->tx_skbuff[i] = NULL;
 		CBDW_BUFADDR(bdp, 0);
@@ -408,32 +380,30 @@ void fs_cleanup_bds(struct net_device *dev)
 	cbd_t __iomem *bdp;
 	int i;
 
-	/*
-	 * Reset SKB transmit buffers.
-	 */
+	/* Reset SKB transmit buffers. */
 	for (i = 0, bdp = fep->tx_bd_base; i < fep->tx_ring; i++, bdp++) {
-		if ((skb = fep->tx_skbuff[i]) == NULL)
+		skb = fep->tx_skbuff[i];
+		if (!skb)
 			continue;
 
 		/* unmap */
 		dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp),
-				skb->len, DMA_TO_DEVICE);
+				 skb->len, DMA_TO_DEVICE);
 
 		fep->tx_skbuff[i] = NULL;
 		dev_kfree_skb(skb);
 	}
 
-	/*
-	 * Reset SKB receive buffers
-	 */
+	/* Reset SKB receive buffers */
 	for (i = 0, bdp = fep->rx_bd_base; i < fep->rx_ring; i++, bdp++) {
-		if ((skb = fep->rx_skbuff[i]) == NULL)
+		skb = fep->rx_skbuff[i];
+		if (!skb)
 			continue;
 
 		/* unmap */
 		dma_unmap_single(fep->dev, CBDR_BUFADDR(bdp),
-			L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
-			DMA_FROM_DEVICE);
+				 L1_CACHE_ALIGN(PKT_MAXBUF_SIZE),
+				 DMA_FROM_DEVICE);
 
 		fep->rx_skbuff[i] = NULL;
 
@@ -441,12 +411,8 @@ void fs_cleanup_bds(struct net_device *dev)
 	}
 }
 
-/**********************************************************************************/
-
 #ifdef CONFIG_FS_ENET_MPC5121_FEC
-/*
- * MPC5121 FEC requeries 4-byte alignment for TX data buffer!
- */
+/* MPC5121 FEC requires 4-byte alignment for TX data buffer! */
 static struct sk_buff *tx_skb_align_workaround(struct net_device *dev,
 					       struct sk_buff *skb)
 {
@@ -478,15 +444,12 @@ static netdev_tx_t
 fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
+	int curidx, nr_frags, len;
 	cbd_t __iomem *bdp;
-	int curidx;
-	u16 sc;
-	int nr_frags;
 	skb_frag_t *frag;
-	int len;
+	u16 sc;
 #ifdef CONFIG_FS_ENET_MPC5121_FEC
-	int is_aligned = 1;
-	int i;
+	int i, is_aligned = 1;
 
 	if (!IS_ALIGNED((unsigned long)skb->data, 4)) {
 		is_aligned = 0;
@@ -504,8 +467,7 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!is_aligned) {
 		skb = tx_skb_align_workaround(dev, skb);
 		if (!skb) {
-			/*
-			 * We have lost packet due to memory allocation error
+			/* We have lost packet due to memory allocation error
 			 * in tx_skb_align_workaround(). Hopefully original
 			 * skb is still valid, so try transmit it later.
 			 */
@@ -516,9 +478,7 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	spin_lock(&fep->tx_lock);
 
-	/*
-	 * Fill in a Tx ring entry
-	 */
+	/* Fill in a Tx ring entry */
 	bdp = fep->cur_tx;
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
@@ -526,8 +486,7 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		netif_stop_queue(dev);
 		spin_unlock(&fep->tx_lock);
 
-		/*
-		 * Ooops.  All transmit buffers are full.  Bail out.
+		/* Ooops.  All transmit buffers are full.  Bail out.
 		 * This should not happen, since the tx queue should be stopped.
 		 */
 		dev_warn(fep->dev, "tx queue full!.\n");
@@ -540,12 +499,12 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_bytes += len;
 	if (nr_frags)
 		len -= skb->data_len;
+
 	fep->tx_free -= nr_frags + 1;
-	/*
-	 * Push the data cache so the CPM does not get stale memory data.
+	/* Push the data cache so the CPM does not get stale memory data.
 	 */
 	CBDW_BUFADDR(bdp, dma_map_single(fep->dev,
-				skb->data, len, DMA_TO_DEVICE));
+					 skb->data, len, DMA_TO_DEVICE));
 	CBDW_DATLEN(bdp, len);
 
 	fep->mapped_as_page[curidx] = 0;
@@ -582,9 +541,11 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* note that while FEC does not have this bit
 	 * it marks it as available for software use
-	 * yay for hw reuse :) */
+	 * yay for hw reuse :)
+	 */
 	if (skb->len <= 60)
 		sc |= BD_ENET_TX_PAD;
+
 	CBDC_SC(bdp, BD_ENET_TX_STATS);
 	CBDS_SC(bdp, sc);
 
@@ -596,6 +557,7 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		bdp++;
 	else
 		bdp = fep->tx_bd_base;
+
 	fep->cur_tx = bdp;
 
 	if (fep->tx_free < MAX_SKB_FRAGS)
@@ -644,9 +606,7 @@ static void fs_timeout(struct net_device *dev, unsigned int txqueue)
 	schedule_work(&fep->timeout_work);
 }
 
-/*-----------------------------------------------------------------------------
- *  generic link-change handler - should be sufficient for most cases
- *-----------------------------------------------------------------------------*/
+/* generic link-change handler - should be sufficient for most cases */
 static void generic_adjust_link(struct  net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
@@ -683,7 +643,6 @@ static void generic_adjust_link(struct  net_device *dev)
 		phy_print_status(phydev);
 }
 
-
 static void fs_adjust_link(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
@@ -691,7 +650,7 @@ static void fs_adjust_link(struct net_device *dev)
 
 	spin_lock_irqsave(&fep->lock, flags);
 
-	if(fep->ops->adjust_link)
+	if (fep->ops->adjust_link)
 		fep->ops->adjust_link(dev);
 	else
 		generic_adjust_link(dev);
@@ -728,8 +687,9 @@ static int fs_enet_open(struct net_device *dev)
 	int r;
 	int err;
 
-	/* to initialize the fep->cur_rx,... */
-	/* not doing this, will cause a crash in fs_enet_napi */
+	/* to initialize the fep->cur_rx,...
+	 * not doing this, will cause a crash in fs_enet_napi
+	 */
 	fs_init_bds(fep->ndev);
 
 	napi_enable(&fep->napi);
@@ -780,10 +740,8 @@ static int fs_enet_close(struct net_device *dev)
 	return 0;
 }
 
-/*************************************************************************/
-
 static void fs_get_drvinfo(struct net_device *dev,
-			    struct ethtool_drvinfo *info)
+			   struct ethtool_drvinfo *info)
 {
 	strscpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 }
@@ -796,7 +754,7 @@ static int fs_get_regs_len(struct net_device *dev)
 }
 
 static void fs_get_regs(struct net_device *dev, struct ethtool_regs *regs,
-			 void *p)
+			void *p)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
 	unsigned long flags;
@@ -815,12 +773,14 @@ static void fs_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 static u32 fs_get_msglevel(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
+
 	return fep->msg_enable;
 }
 
 static void fs_set_msglevel(struct net_device *dev, u32 value)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
+
 	fep->msg_enable = value;
 }
 
@@ -877,8 +837,6 @@ static const struct ethtool_ops fs_ethtool_ops = {
 	.set_tunable = fs_set_tunable,
 };
 
-/**************************************************************************************/
-
 #ifdef CONFIG_FS_ENET_HAS_FEC
 #define IS_FEC(ops) ((ops) == &fs_fec_ops)
 #else
@@ -901,15 +859,14 @@ static const struct net_device_ops fs_enet_netdev_ops = {
 
 static int fs_enet_probe(struct platform_device *ofdev)
 {
+	int err, privsize, len, ret = -ENODEV;
+	const char *phy_connection_type;
+	struct fs_platform_info *fpi;
+	struct fs_enet_private *fep;
 	const struct fs_ops *ops;
 	struct net_device *ndev;
-	struct fs_enet_private *fep;
-	struct fs_platform_info *fpi;
 	const u32 *data;
 	struct clk *clk;
-	int err;
-	const char *phy_connection_type;
-	int privsize, len, ret = -ENODEV;
 
 	ops = device_get_match_data(&ofdev->dev);
 	if (!ops)
@@ -945,7 +902,8 @@ static int fs_enet_probe(struct platform_device *ofdev)
 
 	if (of_device_is_compatible(ofdev->dev.of_node, "fsl,mpc5125-fec")) {
 		phy_connection_type = of_get_property(ofdev->dev.of_node,
-						"phy-connection-type", NULL);
+						      "phy-connection-type",
+						      NULL);
 		if (phy_connection_type && !strcmp("rmii", phy_connection_type))
 			fpi->use_rmii = 1;
 	}
@@ -964,7 +922,7 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	}
 
 	privsize = sizeof(*fep) +
-	           sizeof(struct sk_buff **) *
+		   sizeof(struct sk_buff **) *
 		     (fpi->rx_ring + fpi->tx_ring) +
 		   sizeof(char) * fpi->tx_ring;
 
@@ -1111,9 +1069,9 @@ static struct platform_driver fs_enet_driver = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void fs_enet_netpoll(struct net_device *dev)
 {
-       disable_irq(dev->irq);
-       fs_enet_interrupt(dev->irq, dev);
-       enable_irq(dev->irq);
+	disable_irq(dev->irq);
+	fs_enet_interrupt(dev->irq, dev);
+	enable_irq(dev->irq);
 }
 #endif
 
-- 
cgit v1.3-3-g829e


From 96bf0c4e9f485e286fef7c6677f16f37e7a7ff7c Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:16 +0200
Subject: net: ethernet: fs_enet: drop the .adjust_link custom fs_ops

There's no in-tree user for the fs_ops .adjust_link() function, so we
can always use the generic one in fe_enet-main.

Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 7 +------
 drivers/net/ethernet/freescale/fs_enet/fs_enet.h      | 1 -
 2 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 2b48a2a5e32d..caca81b3ccb6 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -649,12 +649,7 @@ static void fs_adjust_link(struct net_device *dev)
 	unsigned long flags;
 
 	spin_lock_irqsave(&fep->lock, flags);
-
-	if (fep->ops->adjust_link)
-		fep->ops->adjust_link(dev);
-	else
-		generic_adjust_link(dev);
-
+	generic_adjust_link(dev);
 	spin_unlock_irqrestore(&fep->lock, flags);
 }
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index 21c07ac05225..abe4dc97e52a 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -77,7 +77,6 @@ struct fs_ops {
 	void (*free_bd)(struct net_device *dev);
 	void (*cleanup_data)(struct net_device *dev);
 	void (*set_multicast_list)(struct net_device *dev);
-	void (*adjust_link)(struct net_device *dev);
 	void (*restart)(struct net_device *dev);
 	void (*stop)(struct net_device *dev);
 	void (*napi_clear_event)(struct net_device *dev);
-- 
cgit v1.3-3-g829e


From aa3672be731d473f65619ad198664a90771ab3d5 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:17 +0200
Subject: net: ethernet: fs_enet: only protect the .restart() call in
 .adjust_link

When .adjust_link() gets called, it runs in thread context, with the
phydev->lock held. We only need to protect the fep->fecp/fccp/sccp
register that are accessed within the .restart() function from
concurrent access from the interrupts.

These registers are being protected by the fep->lock spinlock, so we can
move the spinlock protection around the .restart() call instead of the
entire adjust_link() call. By doing so, we can simplify further the
.adjust_link() callback and avoid the intermediate helper.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index caca81b3ccb6..b320e55dcb81 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -607,10 +607,11 @@ static void fs_timeout(struct net_device *dev, unsigned int txqueue)
 }
 
 /* generic link-change handler - should be sufficient for most cases */
-static void generic_adjust_link(struct  net_device *dev)
+static void fs_adjust_link(struct  net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
 	struct phy_device *phydev = dev->phydev;
+	unsigned long flags;
 	int new_state = 0;
 
 	if (phydev->link) {
@@ -630,8 +631,11 @@ static void generic_adjust_link(struct  net_device *dev)
 			fep->oldlink = 1;
 		}
 
-		if (new_state)
+		if (new_state) {
+			spin_lock_irqsave(&fep->lock, flags);
 			fep->ops->restart(dev);
+			spin_unlock_irqrestore(&fep->lock, flags);
+		}
 	} else if (fep->oldlink) {
 		new_state = 1;
 		fep->oldlink = 0;
@@ -643,16 +647,6 @@ static void generic_adjust_link(struct  net_device *dev)
 		phy_print_status(phydev);
 }
 
-static void fs_adjust_link(struct net_device *dev)
-{
-	struct fs_enet_private *fep = netdev_priv(dev);
-	unsigned long flags;
-
-	spin_lock_irqsave(&fep->lock, flags);
-	generic_adjust_link(dev);
-	spin_unlock_irqrestore(&fep->lock, flags);
-}
-
 static int fs_init_phy(struct net_device *dev)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
-- 
cgit v1.3-3-g829e


From 6b576b2d44303cad06273ea2e2d5fc08907ff845 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:18 +0200
Subject: net: ethernet: fs_enet: drop unused phy_info and mii_if_info

There's no user of the struct phy_info, the 'phy' field and the
mii_if_info in the fs_enet driver, probably dating back when phylib
wasn't as widely used.  Drop these from the driver code.

As the definition for struct mii_if_info is no longer required, drop the
include for linux/mii.h altogether in the driver.

Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c |  1 -
 drivers/net/ethernet/freescale/fs_enet/fs_enet.h      | 12 ------------
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c      |  1 -
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c      |  1 -
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c      |  1 -
 5 files changed, 16 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index b320e55dcb81..c96a6b9e1445 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -26,7 +26,6 @@
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
-#include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/bitops.h>
 #include <linux/fs.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index abe4dc97e52a..ee49749a3202 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -3,7 +3,6 @@
 #define FS_ENET_H
 
 #include <linux/clk.h>
-#include <linux/mii.h>
 #include <linux/netdevice.h>
 #include <linux/types.h>
 #include <linux/list.h>
@@ -92,14 +91,6 @@ struct fs_ops {
 	void (*tx_restart)(struct net_device *dev);
 };
 
-struct phy_info {
-	unsigned int id;
-	const char *name;
-	void (*startup) (struct net_device * dev);
-	void (*shutdown) (struct net_device * dev);
-	void (*ack_int) (struct net_device * dev);
-};
-
 /* The FEC stores dest/src/type, data, and checksum for receive packets.
  */
 #define MAX_MTU 1508		/* Allow fullsized pppoe packets over VLAN */
@@ -153,10 +144,7 @@ struct fs_enet_private {
 	cbd_t __iomem *cur_rx;
 	cbd_t __iomem *cur_tx;
 	int tx_free;
-	const struct phy_info *phy;
 	u32 msg_enable;
-	struct mii_if_info mii_if;
-	unsigned int last_mii_status;
 	int interrupt;
 
 	int oldduplex, oldspeed, oldlink;	/* current settings */
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index add062928d99..159a384813b3 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -22,7 +22,6 @@
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
-#include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/bitops.h>
 #include <linux/fs.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index f75acb3b358f..cf4c49e884ba 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -23,7 +23,6 @@
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
-#include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/bitops.h>
 #include <linux/fs.h>
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 29ba0048396b..6edc9f66ae83 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -22,7 +22,6 @@
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
-#include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/bitops.h>
 #include <linux/fs.h>
-- 
cgit v1.3-3-g829e


From 21c6321459aaf712c48d8f96730bbefd07b7959c Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:19 +0200
Subject: net: ethernet: fs_enet: use macros for speed and duplex values

The PHY speed and duplex should be manipulated using the SPEED_XXX and
DUPLEX_XXX macros available. Use it in the fcc, fec and scc MAC for
fs_enet.

Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c | 4 ++--
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c | 2 +-
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 159a384813b3..666a54d6e667 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -360,7 +360,7 @@ static void restart(struct net_device *dev)
 
 	/* adjust to speed (for RMII mode) */
 	if (fpi->use_rmii) {
-		if (dev->phydev->speed == 100)
+		if (dev->phydev->speed == SPEED_100)
 			C8(fcccp, fcc_gfemr, 0x20);
 		else
 			S8(fcccp, fcc_gfemr, 0x20);
@@ -386,7 +386,7 @@ static void restart(struct net_device *dev)
 		S32(fccp, fcc_fpsmr, FCC_PSMR_RMII);
 
 	/* adjust to duplex mode */
-	if (dev->phydev->duplex)
+	if (dev->phydev->duplex == DUPLEX_FULL)
 		S32(fccp, fcc_fpsmr, FCC_PSMR_FDE | FCC_PSMR_LPB);
 	else
 		C32(fccp, fcc_fpsmr, FCC_PSMR_FDE | FCC_PSMR_LPB);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index cf4c49e884ba..c1b7877178b9 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -308,7 +308,7 @@ static void restart(struct net_device *dev)
 	/*
 	 * adjust to duplex mode
 	 */
-	if (dev->phydev->duplex) {
+	if (dev->phydev->duplex == DUPLEX_FULL) {
 		FC(fecp, r_cntrl, FEC_RCNTRL_DRT);
 		FS(fecp, x_cntrl, FEC_TCNTRL_FDEN);	/* FD enable */
 	} else {
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index 6edc9f66ae83..d061092ced6c 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -337,7 +337,7 @@ static void restart(struct net_device *dev)
 	W16(sccp, scc_psmr, SCC_PSMR_ENCRC | SCC_PSMR_NIB22);
 
 	/* Set full duplex mode if needed */
-	if (dev->phydev->duplex)
+	if (dev->phydev->duplex == DUPLEX_FULL)
 		S16(sccp, scc_psmr, SCC_PSMR_LPB | SCC_PSMR_FDE);
 
 	/* Restore multicast and promiscuous settings */
-- 
cgit v1.3-3-g829e


From c614acf6e8e175694db7ea21f3ddca6e075680fd Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:20 +0200
Subject: net: ethernet: fs_enet: simplify clock handling with devm accessors

devm_clock_get_enabled() can be used to simplify clock handling for the
PER register clock.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 16 ++++------------
 drivers/net/ethernet/freescale/fs_enet/fs_enet.h      |  2 --
 2 files changed, 4 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index c96a6b9e1445..ec43b71c0eba 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -900,14 +900,9 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	 * but require enable to succeed when a clock was specified/found,
 	 * keep a reference to the clock upon successful acquisition
 	 */
-	clk = devm_clk_get(&ofdev->dev, "per");
-	if (!IS_ERR(clk)) {
-		ret = clk_prepare_enable(clk);
-		if (ret)
-			goto out_deregister_fixed_link;
-
-		fpi->clk_per = clk;
-	}
+	clk = devm_clk_get_enabled(&ofdev->dev, "per");
+	if (IS_ERR(clk))
+		goto out_deregister_fixed_link;
 
 	privsize = sizeof(*fep) +
 		   sizeof(struct sk_buff **) *
@@ -917,7 +912,7 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	ndev = alloc_etherdev(privsize);
 	if (!ndev) {
 		ret = -ENOMEM;
-		goto out_put;
+		goto out_deregister_fixed_link;
 	}
 
 	SET_NETDEV_DEV(ndev, &ofdev->dev);
@@ -979,8 +974,6 @@ out_cleanup_data:
 	fep->ops->cleanup_data(ndev);
 out_free_dev:
 	free_netdev(ndev);
-out_put:
-	clk_disable_unprepare(fpi->clk_per);
 out_deregister_fixed_link:
 	of_node_put(fpi->phy_node);
 	if (of_phy_is_fixed_link(ofdev->dev.of_node))
@@ -1001,7 +994,6 @@ static void fs_enet_remove(struct platform_device *ofdev)
 	fep->ops->cleanup_data(ndev);
 	dev_set_drvdata(fep->dev, NULL);
 	of_node_put(fep->fpi->phy_node);
-	clk_disable_unprepare(fep->fpi->clk_per);
 	if (of_phy_is_fixed_link(ofdev->dev.of_node))
 		of_phy_deregister_fixed_link(ofdev->dev.of_node);
 	free_netdev(ndev);
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index ee49749a3202..6ebb1b4404c7 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -119,8 +119,6 @@ struct fs_platform_info {
 	int napi_weight;	/* NAPI weight			*/
 
 	int use_rmii;		/* use RMII mode		*/
-
-	struct clk *clk_per;	/* 'per' clock for register access */
 };
 
 struct fs_enet_private {
-- 
cgit v1.3-3-g829e


From 41f5fbffd177785e9432e7b2d30bc83b06e6e65d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Wed, 4 Sep 2024 19:18:21 +0200
Subject: net: ethernet: fs_enet: phylink conversion

fs_enet is a quite old but still used Ethernet driver found on some NXP
devices. It has support for 10/100 Mbps ethernet, with half and full
duplex. Some variants of it can use RMII, while other integrations are
MII-only.

Add phylink support, thus removing custom fixed-link hanldling.

This also allows removing some internal flags such as the use_rmii flag.

Acked-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/Kconfig     |   2 +-
 .../net/ethernet/freescale/fs_enet/fs_enet-main.c  | 215 +++++++++++----------
 drivers/net/ethernet/freescale/fs_enet/fs_enet.h   |  12 +-
 drivers/net/ethernet/freescale/fs_enet/mac-fcc.c   |  11 +-
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c   |   9 +-
 drivers/net/ethernet/freescale/fs_enet/mac-scc.c   |   5 +-
 6 files changed, 132 insertions(+), 122 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/Kconfig b/drivers/net/ethernet/freescale/fs_enet/Kconfig
index 7f20840fde07..57013bf14d7c 100644
--- a/drivers/net/ethernet/freescale/fs_enet/Kconfig
+++ b/drivers/net/ethernet/freescale/fs_enet/Kconfig
@@ -3,7 +3,7 @@ config FS_ENET
 	tristate "Freescale Ethernet Driver"
 	depends on NET_VENDOR_FREESCALE && (CPM1 || CPM2 || PPC_MPC512x)
 	select MII
-	select PHYLIB
+	select PHYLINK
 
 config FS_ENET_MPC5121_FEC
 	def_bool y if (FS_ENET && PPC_MPC512x)
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index ec43b71c0eba..d300b01859a1 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -31,11 +31,13 @@
 #include <linux/fs.h>
 #include <linux/platform_device.h>
 #include <linux/phy.h>
+#include <linux/phylink.h>
 #include <linux/property.h>
 #include <linux/of.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/pgtable.h>
+#include <linux/rtnetlink.h>
 
 #include <linux/vmalloc.h>
 #include <asm/irq.h>
@@ -68,6 +70,13 @@ static void fs_set_multicast_list(struct net_device *dev)
 	(*fep->ops->set_multicast_list)(dev);
 }
 
+static int fs_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+	struct fs_enet_private *fep = netdev_priv(dev);
+
+	return phylink_mii_ioctl(fep->phylink, ifr, cmd);
+}
+
 static void skb_align(struct sk_buff *skb, int align)
 {
 	int off = ((unsigned long)skb->data) & (align - 1);
@@ -581,15 +590,21 @@ static void fs_timeout_work(struct work_struct *work)
 
 	dev->stats.tx_errors++;
 
-	spin_lock_irqsave(&fep->lock, flags);
+	/* In the event a timeout was detected, but the netdev is brought down
+	 * shortly after, it no longer makes sense to try to recover from the
+	 * timeout. netif_running() will return false when called from the
+	 * .ndo_close() callback. Calling the following recovery code while
+	 * called from .ndo_close() could deadlock on rtnl.
+	 */
+	if (!netif_running(dev))
+		return;
 
-	if (dev->flags & IFF_UP) {
-		phy_stop(dev->phydev);
-		(*fep->ops->stop)(dev);
-		(*fep->ops->restart)(dev);
-	}
+	rtnl_lock();
+	phylink_stop(fep->phylink);
+	phylink_start(fep->phylink);
+	rtnl_unlock();
 
-	phy_start(dev->phydev);
+	spin_lock_irqsave(&fep->lock, flags);
 	wake = fep->tx_free >= MAX_SKB_FRAGS &&
 	       !(CBDR_SC(fep->cur_tx) & BD_ENET_TX_READY);
 	spin_unlock_irqrestore(&fep->lock, flags);
@@ -605,68 +620,37 @@ static void fs_timeout(struct net_device *dev, unsigned int txqueue)
 	schedule_work(&fep->timeout_work);
 }
 
-/* generic link-change handler - should be sufficient for most cases */
-static void fs_adjust_link(struct  net_device *dev)
+static void fs_mac_link_up(struct phylink_config *config,
+			   struct phy_device *phy,
+			   unsigned int mode, phy_interface_t interface,
+			   int speed, int duplex,
+			   bool tx_pause, bool rx_pause)
 {
-	struct fs_enet_private *fep = netdev_priv(dev);
-	struct phy_device *phydev = dev->phydev;
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct fs_enet_private *fep = netdev_priv(ndev);
 	unsigned long flags;
-	int new_state = 0;
-
-	if (phydev->link) {
-		/* adjust to duplex mode */
-		if (phydev->duplex != fep->oldduplex) {
-			new_state = 1;
-			fep->oldduplex = phydev->duplex;
-		}
-
-		if (phydev->speed != fep->oldspeed) {
-			new_state = 1;
-			fep->oldspeed = phydev->speed;
-		}
-
-		if (!fep->oldlink) {
-			new_state = 1;
-			fep->oldlink = 1;
-		}
-
-		if (new_state) {
-			spin_lock_irqsave(&fep->lock, flags);
-			fep->ops->restart(dev);
-			spin_unlock_irqrestore(&fep->lock, flags);
-		}
-	} else if (fep->oldlink) {
-		new_state = 1;
-		fep->oldlink = 0;
-		fep->oldspeed = 0;
-		fep->oldduplex = -1;
-	}
 
-	if (new_state && netif_msg_link(fep))
-		phy_print_status(phydev);
+	spin_lock_irqsave(&fep->lock, flags);
+	fep->ops->restart(ndev, interface, speed, duplex);
+	spin_unlock_irqrestore(&fep->lock, flags);
 }
 
-static int fs_init_phy(struct net_device *dev)
+static void fs_mac_link_down(struct phylink_config *config,
+			     unsigned int mode, phy_interface_t interface)
 {
-	struct fs_enet_private *fep = netdev_priv(dev);
-	struct phy_device *phydev;
-	phy_interface_t iface;
-
-	fep->oldlink = 0;
-	fep->oldspeed = 0;
-	fep->oldduplex = -1;
-
-	iface = fep->fpi->use_rmii ?
-		PHY_INTERFACE_MODE_RMII : PHY_INTERFACE_MODE_MII;
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct fs_enet_private *fep = netdev_priv(ndev);
+	unsigned long flags;
 
-	phydev = of_phy_connect(dev, fep->fpi->phy_node, &fs_adjust_link, 0,
-				iface);
-	if (!phydev) {
-		dev_err(&dev->dev, "Could not attach to PHY\n");
-		return -ENODEV;
-	}
+	spin_lock_irqsave(&fep->lock, flags);
+	fep->ops->stop(ndev);
+	spin_unlock_irqrestore(&fep->lock, flags);
+}
 
-	return 0;
+static void fs_mac_config(struct phylink_config *config, unsigned int mode,
+			  const struct phylink_link_state *state)
+{
+	/* Nothing to do */
 }
 
 static int fs_enet_open(struct net_device *dev)
@@ -691,13 +675,13 @@ static int fs_enet_open(struct net_device *dev)
 		return -EINVAL;
 	}
 
-	err = fs_init_phy(dev);
+	err = phylink_of_phy_connect(fep->phylink, fep->dev->of_node, 0);
 	if (err) {
 		free_irq(fep->interrupt, dev);
 		napi_disable(&fep->napi);
 		return err;
 	}
-	phy_start(dev->phydev);
+	phylink_start(fep->phylink);
 
 	netif_start_queue(dev);
 
@@ -710,19 +694,18 @@ static int fs_enet_close(struct net_device *dev)
 	unsigned long flags;
 
 	netif_stop_queue(dev);
-	netif_carrier_off(dev);
 	napi_disable(&fep->napi);
-	cancel_work_sync(&fep->timeout_work);
-	phy_stop(dev->phydev);
+	cancel_work(&fep->timeout_work);
+	phylink_stop(fep->phylink);
 
 	spin_lock_irqsave(&fep->lock, flags);
 	spin_lock(&fep->tx_lock);
 	(*fep->ops->stop)(dev);
 	spin_unlock(&fep->tx_lock);
 	spin_unlock_irqrestore(&fep->lock, flags);
+	phylink_disconnect_phy(fep->phylink);
 
 	/* release any irqs */
-	phy_disconnect(dev->phydev);
 	free_irq(fep->interrupt, dev);
 
 	return 0;
@@ -810,6 +793,22 @@ static int fs_set_tunable(struct net_device *dev,
 	return ret;
 }
 
+static int fs_ethtool_set_link_ksettings(struct net_device *dev,
+					 const struct ethtool_link_ksettings *cmd)
+{
+	struct fs_enet_private *fep = netdev_priv(dev);
+
+	return phylink_ethtool_ksettings_set(fep->phylink, cmd);
+}
+
+static int fs_ethtool_get_link_ksettings(struct net_device *dev,
+					 struct ethtool_link_ksettings *cmd)
+{
+	struct fs_enet_private *fep = netdev_priv(dev);
+
+	return phylink_ethtool_ksettings_get(fep->phylink, cmd);
+}
+
 static const struct ethtool_ops fs_ethtool_ops = {
 	.get_drvinfo = fs_get_drvinfo,
 	.get_regs_len = fs_get_regs_len,
@@ -819,8 +818,8 @@ static const struct ethtool_ops fs_ethtool_ops = {
 	.set_msglevel = fs_set_msglevel,
 	.get_regs = fs_get_regs,
 	.get_ts_info = ethtool_op_get_ts_info,
-	.get_link_ksettings = phy_ethtool_get_link_ksettings,
-	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+	.get_link_ksettings = fs_ethtool_get_link_ksettings,
+	.set_link_ksettings = fs_ethtool_set_link_ksettings,
 	.get_tunable = fs_get_tunable,
 	.set_tunable = fs_set_tunable,
 };
@@ -837,7 +836,7 @@ static const struct net_device_ops fs_enet_netdev_ops = {
 	.ndo_start_xmit		= fs_enet_start_xmit,
 	.ndo_tx_timeout		= fs_timeout,
 	.ndo_set_rx_mode	= fs_set_multicast_list,
-	.ndo_eth_ioctl		= phy_do_ioctl_running,
+	.ndo_eth_ioctl		= fs_eth_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -845,14 +844,21 @@ static const struct net_device_ops fs_enet_netdev_ops = {
 #endif
 };
 
+static const struct phylink_mac_ops fs_enet_phylink_mac_ops = {
+	.mac_config = fs_mac_config,
+	.mac_link_down = fs_mac_link_down,
+	.mac_link_up = fs_mac_link_up,
+};
+
 static int fs_enet_probe(struct platform_device *ofdev)
 {
-	int err, privsize, len, ret = -ENODEV;
-	const char *phy_connection_type;
+	int privsize, len, ret = -ENODEV;
 	struct fs_platform_info *fpi;
 	struct fs_enet_private *fep;
+	phy_interface_t phy_mode;
 	const struct fs_ops *ops;
 	struct net_device *ndev;
+	struct phylink *phylink;
 	const u32 *data;
 	struct clk *clk;
 
@@ -872,29 +878,18 @@ static int fs_enet_probe(struct platform_device *ofdev)
 		fpi->cp_command = *data;
 	}
 
+	ret = of_get_phy_mode(ofdev->dev.of_node, &phy_mode);
+	if (ret) {
+		/* For compatibility, if the mode isn't specified in DT,
+		 * assume MII
+		 */
+		phy_mode = PHY_INTERFACE_MODE_MII;
+	}
+
 	fpi->rx_ring = RX_RING_SIZE;
 	fpi->tx_ring = TX_RING_SIZE;
 	fpi->rx_copybreak = 240;
 	fpi->napi_weight = 17;
-	fpi->phy_node = of_parse_phandle(ofdev->dev.of_node, "phy-handle", 0);
-	if (!fpi->phy_node && of_phy_is_fixed_link(ofdev->dev.of_node)) {
-		err = of_phy_register_fixed_link(ofdev->dev.of_node);
-		if (err)
-			goto out_free_fpi;
-
-		/* In the case of a fixed PHY, the DT node associated
-		 * to the PHY is the Ethernet MAC DT node.
-		 */
-		fpi->phy_node = of_node_get(ofdev->dev.of_node);
-	}
-
-	if (of_device_is_compatible(ofdev->dev.of_node, "fsl,mpc5125-fec")) {
-		phy_connection_type = of_get_property(ofdev->dev.of_node,
-						      "phy-connection-type",
-						      NULL);
-		if (phy_connection_type && !strcmp("rmii", phy_connection_type))
-			fpi->use_rmii = 1;
-	}
 
 	/* make clock lookup non-fatal (the driver is shared among platforms),
 	 * but require enable to succeed when a clock was specified/found,
@@ -902,7 +897,7 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	 */
 	clk = devm_clk_get_enabled(&ofdev->dev, "per");
 	if (IS_ERR(clk))
-		goto out_deregister_fixed_link;
+		goto out_free_fpi;
 
 	privsize = sizeof(*fep) +
 		   sizeof(struct sk_buff **) *
@@ -912,7 +907,7 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	ndev = alloc_etherdev(privsize);
 	if (!ndev) {
 		ret = -ENOMEM;
-		goto out_deregister_fixed_link;
+		goto out_free_fpi;
 	}
 
 	SET_NETDEV_DEV(ndev, &ofdev->dev);
@@ -924,9 +919,29 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	fep->fpi = fpi;
 	fep->ops = ops;
 
+	fep->phylink_config.dev = &ndev->dev;
+	fep->phylink_config.type = PHYLINK_NETDEV;
+	fep->phylink_config.mac_capabilities = MAC_10 | MAC_100;
+
+	__set_bit(PHY_INTERFACE_MODE_MII,
+		  fep->phylink_config.supported_interfaces);
+
+	if (of_device_is_compatible(ofdev->dev.of_node, "fsl,mpc5125-fec"))
+		__set_bit(PHY_INTERFACE_MODE_RMII,
+			  fep->phylink_config.supported_interfaces);
+
+	phylink = phylink_create(&fep->phylink_config, dev_fwnode(fep->dev),
+				 phy_mode, &fs_enet_phylink_mac_ops);
+	if (IS_ERR(phylink)) {
+		ret = PTR_ERR(phylink);
+		goto out_free_dev;
+	}
+
+	fep->phylink = phylink;
+
 	ret = fep->ops->setup_data(ndev);
 	if (ret)
-		goto out_free_dev;
+		goto out_phylink;
 
 	fep->rx_skbuff = (struct sk_buff **)&fep[1];
 	fep->tx_skbuff = fep->rx_skbuff + fpi->rx_ring;
@@ -956,8 +971,6 @@ static int fs_enet_probe(struct platform_device *ofdev)
 
 	ndev->ethtool_ops = &fs_ethtool_ops;
 
-	netif_carrier_off(ndev);
-
 	ndev->features |= NETIF_F_SG;
 
 	ret = register_netdev(ndev);
@@ -972,12 +985,10 @@ out_free_bd:
 	fep->ops->free_bd(ndev);
 out_cleanup_data:
 	fep->ops->cleanup_data(ndev);
+out_phylink:
+	phylink_destroy(fep->phylink);
 out_free_dev:
 	free_netdev(ndev);
-out_deregister_fixed_link:
-	of_node_put(fpi->phy_node);
-	if (of_phy_is_fixed_link(ofdev->dev.of_node))
-		of_phy_deregister_fixed_link(ofdev->dev.of_node);
 out_free_fpi:
 	kfree(fpi);
 	return ret;
@@ -993,9 +1004,7 @@ static void fs_enet_remove(struct platform_device *ofdev)
 	fep->ops->free_bd(ndev);
 	fep->ops->cleanup_data(ndev);
 	dev_set_drvdata(fep->dev, NULL);
-	of_node_put(fep->fpi->phy_node);
-	if (of_phy_is_fixed_link(ofdev->dev.of_node))
-		of_phy_deregister_fixed_link(ofdev->dev.of_node);
+	phylink_destroy(fep->phylink);
 	free_netdev(ndev);
 }
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
index 6ebb1b4404c7..36e4fcc29e36 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/phy.h>
+#include <linux/phylink.h>
 #include <linux/dma-mapping.h>
 
 #ifdef CONFIG_CPM1
@@ -76,7 +77,8 @@ struct fs_ops {
 	void (*free_bd)(struct net_device *dev);
 	void (*cleanup_data)(struct net_device *dev);
 	void (*set_multicast_list)(struct net_device *dev);
-	void (*restart)(struct net_device *dev);
+	void (*restart)(struct net_device *dev, phy_interface_t interface,
+			int speed, int duplex);
 	void (*stop)(struct net_device *dev);
 	void (*napi_clear_event)(struct net_device *dev);
 	void (*napi_enable)(struct net_device *dev);
@@ -112,13 +114,9 @@ struct fs_platform_info {
 
 	u32 dpram_offset;
 
-	struct device_node *phy_node;
-
 	int rx_ring, tx_ring;	/* number of buffers on rx	*/
 	int rx_copybreak;	/* limit we copy small frames	*/
 	int napi_weight;	/* NAPI weight			*/
-
-	int use_rmii;		/* use RMII mode		*/
 };
 
 struct fs_enet_private {
@@ -143,10 +141,10 @@ struct fs_enet_private {
 	cbd_t __iomem *cur_tx;
 	int tx_free;
 	u32 msg_enable;
+	struct phylink *phylink;
+	struct phylink_config phylink_config;
 	int interrupt;
 
-	int oldduplex, oldspeed, oldlink;	/* current settings */
-
 	/* event masks */
 	u32 ev_napi;		/* mask of NAPI events */
 	u32 ev;			/* event mask          */
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 666a54d6e667..be63293511d9 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -235,7 +235,8 @@ static void set_multicast_list(struct net_device *dev)
 		set_promiscuous_mode(dev);
 }
 
-static void restart(struct net_device *dev)
+static void restart(struct net_device *dev, phy_interface_t interface,
+		    int speed, int duplex)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
 	const struct fs_platform_info *fpi = fep->fpi;
@@ -359,8 +360,8 @@ static void restart(struct net_device *dev)
 	fs_init_bds(dev);
 
 	/* adjust to speed (for RMII mode) */
-	if (fpi->use_rmii) {
-		if (dev->phydev->speed == SPEED_100)
+	if (interface == PHY_INTERFACE_MODE_RMII) {
+		if (speed == SPEED_100)
 			C8(fcccp, fcc_gfemr, 0x20);
 		else
 			S8(fcccp, fcc_gfemr, 0x20);
@@ -382,11 +383,11 @@ static void restart(struct net_device *dev)
 
 	W32(fccp, fcc_fpsmr, FCC_PSMR_ENCRC);
 
-	if (fpi->use_rmii)
+	if (interface == PHY_INTERFACE_MODE_RMII)
 		S32(fccp, fcc_fpsmr, FCC_PSMR_RMII);
 
 	/* adjust to duplex mode */
-	if (dev->phydev->duplex == DUPLEX_FULL)
+	if (duplex == DUPLEX_FULL)
 		S32(fccp, fcc_fpsmr, FCC_PSMR_FDE | FCC_PSMR_LPB);
 	else
 		C32(fccp, fcc_fpsmr, FCC_PSMR_FDE | FCC_PSMR_LPB);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index c1b7877178b9..f2ecd20027cf 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -220,7 +220,8 @@ static void set_multicast_list(struct net_device *dev)
 		set_promiscuous_mode(dev);
 }
 
-static void restart(struct net_device *dev)
+static void restart(struct net_device *dev, phy_interface_t interface,
+		    int speed, int duplex)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
 	struct fec __iomem *fecp = fep->fec.fecp;
@@ -302,13 +303,13 @@ static void restart(struct net_device *dev)
 	 * Only set MII/RMII mode - do not touch maximum frame length
 	 * configured before.
 	 */
-	FS(fecp, r_cntrl, fpi->use_rmii ?
-			FEC_RCNTRL_RMII_MODE : FEC_RCNTRL_MII_MODE);
+	FS(fecp, r_cntrl, interface == PHY_INTERFACE_MODE_RMII ?
+			  FEC_RCNTRL_RMII_MODE : FEC_RCNTRL_MII_MODE);
 #endif
 	/*
 	 * adjust to duplex mode
 	 */
-	if (dev->phydev->duplex == DUPLEX_FULL) {
+	if (duplex == DUPLEX_FULL) {
 		FC(fecp, r_cntrl, FEC_RCNTRL_DRT);
 		FS(fecp, x_cntrl, FEC_TCNTRL_FDEN);	/* FD enable */
 	} else {
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
index d061092ced6c..6c97191649de 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c
@@ -226,7 +226,8 @@ static void set_multicast_list(struct net_device *dev)
  * change.  This only happens when switching between half and full
  * duplex.
  */
-static void restart(struct net_device *dev)
+static void restart(struct net_device *dev, phy_interface_t interface,
+		    int speed, int duplex)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
 	scc_t __iomem *sccp = fep->scc.sccp;
@@ -337,7 +338,7 @@ static void restart(struct net_device *dev)
 	W16(sccp, scc_psmr, SCC_PSMR_ENCRC | SCC_PSMR_NIB22);
 
 	/* Set full duplex mode if needed */
-	if (dev->phydev->duplex == DUPLEX_FULL)
+	if (duplex == DUPLEX_FULL)
 		S16(sccp, scc_psmr, SCC_PSMR_LPB | SCC_PSMR_FDE);
 
 	/* Restore multicast and promiscuous settings */
-- 
cgit v1.3-3-g829e


From 8f088541991bc1716a5ed570456d218241303851 Mon Sep 17 00:00:00 2001
From: Zijun Hu <quic_zijuhu@quicinc.com>
Date: Thu, 5 Sep 2024 07:35:38 +0800
Subject: net: sysfs: Fix weird usage of class's namespace relevant fields

Device class has two namespace relevant fields which are associated by
the following usage:

struct class {
	...
	const struct kobj_ns_type_operations *ns_type;
	const void *(*namespace)(const struct device *dev);
	...
}
if (dev->class && dev->class->ns_type)
	dev->class->namespace(dev);

The usage looks weird since it checks @ns_type but calls namespace()
it is found for all existing class definitions that the other filed is
also assigned once one is assigned in current kernel tree, so fix this
weird usage by checking @namespace to call namespace().

Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 0648dbf0e234..05cf5347f25e 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1060,7 +1060,7 @@ static const void *rx_queue_namespace(const struct kobject *kobj)
 	struct device *dev = &queue->dev->dev;
 	const void *ns = NULL;
 
-	if (dev->class && dev->class->ns_type)
+	if (dev->class && dev->class->namespace)
 		ns = dev->class->namespace(dev);
 
 	return ns;
@@ -1744,7 +1744,7 @@ static const void *netdev_queue_namespace(const struct kobject *kobj)
 	struct device *dev = &queue->dev->dev;
 	const void *ns = NULL;
 
-	if (dev->class && dev->class->ns_type)
+	if (dev->class && dev->class->namespace)
 		ns = dev->class->namespace(dev);
 
 	return ns;
-- 
cgit v1.3-3-g829e


From 15ea13b1b1fbf6364d4cd568e65e4c8479632999 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 9 Sep 2024 12:08:06 +0300
Subject: wifi: cfg80211: fix two more possible UBSAN-detected off-by-one
 errors

Although not reproduced in practice, these two cases may be
considered by UBSAN as off-by-one errors. So fix them in the
same way as in commit a26a5107bc52 ("wifi: cfg80211: fix UBSAN
noise in cfg80211_wext_siwscan()").

Fixes: 807f8a8c3004 ("cfg80211/nl80211: add support for scheduled scans")
Fixes: 5ba63533bbf6 ("cfg80211: fix alignment problem in scan request")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://patch.msgid.link/20240909090806.1091956-1-dmantipov@yandex.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 3 ++-
 net/wireless/sme.c     | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8bad3c6db39d..9ab777e0bd4d 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -9778,7 +9778,8 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 		return ERR_PTR(-ENOMEM);
 
 	if (n_ssids)
-		request->ssids = (void *)&request->channels[n_channels];
+		request->ssids = (void *)request +
+			struct_size(request, channels, n_channels);
 	request->n_ssids = n_ssids;
 	if (ie_len) {
 		if (n_ssids)
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index d9d7bf8bb5c1..431da30817a6 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -115,7 +115,8 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev)
 		n_channels = i;
 	}
 	request->n_channels = n_channels;
-	request->ssids = (void *)&request->channels[n_channels];
+	request->ssids = (void *)request +
+		struct_size(request, channels, n_channels);
 	request->n_ssids = 1;
 
 	memcpy(request->ssids[0].ssid, wdev->conn->params.ssid,
-- 
cgit v1.3-3-g829e


From 69716a3babe1165a9ab1b3770b55d303d5bb5fa3 Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Mon, 9 Sep 2024 11:43:39 +0200
Subject: Revert "xfrm: add SA information to the offloaded packet"

This reverts commit e7cd191f83fd899c233dfbe7dc6d96ef703dcbbd.

While supporting xfrm interfaces in the packet offload API
is needed, this patch does not do the right thing. There are
more things to do to really support xfrm interfaces, so revert
it for now.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_output.c | 21 ---------------------
 1 file changed, 21 deletions(-)

diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index a12588e7b060..e5722c95b8bb 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -706,8 +706,6 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 	struct xfrm_state *x = skb_dst(skb)->xfrm;
 	int family;
 	int err;
-	struct xfrm_offload *xo;
-	struct sec_path *sp;
 
 	family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family
 		: skb_dst(skb)->ops->family;
@@ -730,25 +728,6 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 			kfree_skb(skb);
 			return -EHOSTUNREACH;
 		}
-		sp = secpath_set(skb);
-		if (!sp) {
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
-			kfree_skb(skb);
-			return -ENOMEM;
-		}
-
-		sp->olen++;
-		sp->xvec[sp->len++] = x;
-		xfrm_state_hold(x);
-
-		xo = xfrm_offload(skb);
-		if (!xo) {
-			secpath_reset(skb);
-			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
-			kfree_skb(skb);
-			return -EINVAL;
-		}
-		xo->flags |= XFRM_XMIT;
 
 		return xfrm_output_resume(sk, skb, 0);
 	}
-- 
cgit v1.3-3-g829e


From 9d301de12da6e1bb069a9835c38359b8e8135121 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Fri, 6 Sep 2024 15:31:51 +0300
Subject: wifi: mac80211: use two-phase skb reclamation in ieee80211_do_stop()

Since '__dev_queue_xmit()' should be called with interrupts enabled,
the following backtrace:

ieee80211_do_stop()
 ...
 spin_lock_irqsave(&local->queue_stop_reason_lock, flags)
 ...
 ieee80211_free_txskb()
  ieee80211_report_used_skb()
   ieee80211_report_ack_skb()
    cfg80211_mgmt_tx_status_ext()
     nl80211_frame_tx_status()
      genlmsg_multicast_netns()
       genlmsg_multicast_netns_filtered()
        nlmsg_multicast_filtered()
	 netlink_broadcast_filtered()
	  do_one_broadcast()
	   netlink_broadcast_deliver()
	    __netlink_sendskb()
	     netlink_deliver_tap()
	      __netlink_deliver_tap_skb()
	       dev_queue_xmit()
	        __dev_queue_xmit() ; with IRQS disabled
 ...
 spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags)

issues the warning (as reported by syzbot reproducer):

WARNING: CPU: 2 PID: 5128 at kernel/softirq.c:362 __local_bh_enable_ip+0xc3/0x120

Fix this by implementing a two-phase skb reclamation in
'ieee80211_do_stop()', where actual work is performed
outside of a section with interrupts disabled.

Fixes: 5061b0c2b906 ("mac80211: cooperate more with network namespaces")
Reported-by: syzbot+1a3986bbd3169c307819@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=1a3986bbd3169c307819
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Link: https://patch.msgid.link/20240906123151.351647-1-dmantipov@yandex.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/iface.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index e074de893ed6..6ef0990d3d29 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -462,6 +462,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 {
 	struct ieee80211_local *local = sdata->local;
 	unsigned long flags;
+	struct sk_buff_head freeq;
 	struct sk_buff *skb, *tmp;
 	u32 hw_reconf_flags = 0;
 	int i, flushed;
@@ -637,18 +638,32 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 		skb_queue_purge(&sdata->status_queue);
 	}
 
+	/*
+	 * Since ieee80211_free_txskb() may issue __dev_queue_xmit()
+	 * which should be called with interrupts enabled, reclamation
+	 * is done in two phases:
+	 */
+	__skb_queue_head_init(&freeq);
+
+	/* unlink from local queues... */
 	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 	for (i = 0; i < IEEE80211_MAX_QUEUES; i++) {
 		skb_queue_walk_safe(&local->pending[i], skb, tmp) {
 			struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 			if (info->control.vif == &sdata->vif) {
 				__skb_unlink(skb, &local->pending[i]);
-				ieee80211_free_txskb(&local->hw, skb);
+				__skb_queue_tail(&freeq, skb);
 			}
 		}
 	}
 	spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
+	/* ... and perform actual reclamation with interrupts enabled. */
+	skb_queue_walk_safe(&freeq, skb, tmp) {
+		__skb_unlink(skb, &freeq);
+		ieee80211_free_txskb(&local->hw, skb);
+	}
+
 	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		ieee80211_txq_remove_vlan(local, sdata);
 
-- 
cgit v1.3-3-g829e


From 498365e52bebcbc36a93279fe7e9d6aec8479cee Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 21 Aug 2024 15:23:51 -0600
Subject: wifi: mwifiex: Fix memcpy() field-spanning write warning in
 mwifiex_cmd_802_11_scan_ext()

Replace one-element array with a flexible-array member in
`struct host_cmd_ds_802_11_scan_ext`.

With this, fix the following warning:

elo 16 17:51:58 surfacebook kernel: ------------[ cut here ]------------
elo 16 17:51:58 surfacebook kernel: memcpy: detected field-spanning write (size 243) of single field "ext_scan->tlv_buffer" at drivers/net/wireless/marvell/mwifiex/scan.c:2239 (size 1)
elo 16 17:51:58 surfacebook kernel: WARNING: CPU: 0 PID: 498 at drivers/net/wireless/marvell/mwifiex/scan.c:2239 mwifiex_cmd_802_11_scan_ext+0x83/0x90 [mwifiex]

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Closes: https://lore.kernel.org/linux-hardening/ZsZNgfnEwOcPdCly@black.fi.intel.com/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/ZsZa5xRcsLq9D+RX@elsanto
---
 drivers/net/wireless/marvell/mwifiex/fw.h   | 2 +-
 drivers/net/wireless/marvell/mwifiex/scan.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index e91def0afa14..d03129d5d24e 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -1627,7 +1627,7 @@ struct host_cmd_ds_802_11_scan_rsp {
 
 struct host_cmd_ds_802_11_scan_ext {
 	u32   reserved;
-	u8    tlv_buffer[1];
+	u8    tlv_buffer[];
 } __packed;
 
 struct mwifiex_ie_types_bss_mode {
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 010e6ff91457..cab889af4c4a 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -2534,8 +2534,7 @@ int mwifiex_ret_802_11_scan_ext(struct mwifiex_private *priv,
 	ext_scan_resp = &resp->params.ext_scan;
 
 	tlv = (void *)ext_scan_resp->tlv_buffer;
-	buf_left = le16_to_cpu(resp->size) - (sizeof(*ext_scan_resp) + S_DS_GEN
-					      - 1);
+	buf_left = le16_to_cpu(resp->size) - (sizeof(*ext_scan_resp) + S_DS_GEN);
 
 	while (buf_left >= sizeof(struct mwifiex_ie_types_header)) {
 		type = le16_to_cpu(tlv->type);
-- 
cgit v1.3-3-g829e


From 6d7c6ae1efb1ff68bc01d79d94fdf0388f86cdd8 Mon Sep 17 00:00:00 2001
From: Jiawei Ye <jiawei.ye@foxmail.com>
Date: Thu, 29 Aug 2024 08:17:09 +0000
Subject: wifi: wilc1000: fix potential RCU dereference issue in
 wilc_parse_join_bss_param
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the `wilc_parse_join_bss_param` function, the TSF field of the `ies`
structure is accessed after the RCU read-side critical section is
unlocked. According to RCU usage rules, this is illegal. Reusing this
pointer can lead to unpredictable behavior, including accessing memory
that has been updated or causing use-after-free issues.

This possible bug was identified using a static analysis tool developed
by myself, specifically designed to detect RCU-related issues.

To address this, the TSF value is now stored in a local variable
`ies_tsf` before the RCU lock is released. The `param->tsf_lo` field is
then assigned using this local variable, ensuring that the TSF value is
safely accessed.

Fixes: 205c50306acf ("wifi: wilc1000: fix RCU usage in connect path")
Signed-off-by: Jiawei Ye <jiawei.ye@foxmail.com>
Reviewed-by: Alexis Lothoré <alexis.lothore@bootlin.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/tencent_466225AA599BA49627FB26F707EE17BC5407@qq.com
---
 drivers/net/wireless/microchip/wilc1000/hif.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
index 3c48e1a57b24..bba53307b960 100644
--- a/drivers/net/wireless/microchip/wilc1000/hif.c
+++ b/drivers/net/wireless/microchip/wilc1000/hif.c
@@ -384,6 +384,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss,
 	struct wilc_join_bss_param *param;
 	u8 rates_len = 0;
 	int ies_len;
+	u64 ies_tsf;
 	int ret;
 
 	param = kzalloc(sizeof(*param), GFP_KERNEL);
@@ -399,6 +400,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss,
 		return NULL;
 	}
 	ies_len = ies->len;
+	ies_tsf = ies->tsf;
 	rcu_read_unlock();
 
 	param->beacon_period = cpu_to_le16(bss->beacon_interval);
@@ -454,7 +456,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss,
 				    IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
 				    (u8 *)&noa_attr, sizeof(noa_attr));
 	if (ret > 0) {
-		param->tsf_lo = cpu_to_le32(ies->tsf);
+		param->tsf_lo = cpu_to_le32(ies_tsf);
 		param->noa_enabled = 1;
 		param->idx = noa_attr.index;
 		if (noa_attr.oppps_ctwindow & IEEE80211_P2P_OPPPS_ENABLE_BIT) {
-- 
cgit v1.3-3-g829e


From 554475248177894513bbb495de577836e67a57c0 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 3 Sep 2024 19:02:04 +0800
Subject: wifi: wilc1000: Convert using devm_clk_get_optional_enabled() in
 wilc_sdio_probe()

Use devm_clk_get_optional_enabled() instead of devm_clk_get_optional() +
clk_prepare_enable(), which can make the clk consistent with the device
life cycle and reduce the risk of unreleased clk resources. Since the
device framework has automatically released the clk resource, there is
no need to execute clk_disable_unprepare(clk) on the error path, drop
the clk_disable_unprepare label, and the original error process can change
to dispose_irq.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240903110205.4127706-2-lizetao1@huawei.com
---
 drivers/net/wireless/microchip/wilc1000/sdio.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/sdio.c b/drivers/net/wireless/microchip/wilc1000/sdio.c
index 683a35c682a8..b4da05d5a498 100644
--- a/drivers/net/wireless/microchip/wilc1000/sdio.c
+++ b/drivers/net/wireless/microchip/wilc1000/sdio.c
@@ -174,19 +174,18 @@ static int wilc_sdio_probe(struct sdio_func *func,
 	wilc->bus_data = sdio_priv;
 	wilc->dev = &func->dev;
 
-	wilc->rtc_clk = devm_clk_get_optional(&func->card->dev, "rtc");
+	wilc->rtc_clk = devm_clk_get_optional_enabled(&func->card->dev, "rtc");
 	if (IS_ERR(wilc->rtc_clk)) {
 		ret = PTR_ERR(wilc->rtc_clk);
 		goto dispose_irq;
 	}
-	clk_prepare_enable(wilc->rtc_clk);
 
 	wilc_sdio_init(wilc, false);
 
 	ret = wilc_load_mac_from_nv(wilc);
 	if (ret) {
 		pr_err("Can not retrieve MAC address from chip\n");
-		goto clk_disable_unprepare;
+		goto dispose_irq;
 	}
 
 	wilc_sdio_deinit(wilc);
@@ -195,14 +194,12 @@ static int wilc_sdio_probe(struct sdio_func *func,
 				   NL80211_IFTYPE_STATION, false);
 	if (IS_ERR(vif)) {
 		ret = PTR_ERR(vif);
-		goto clk_disable_unprepare;
+		goto dispose_irq;
 	}
 
 	dev_info(&func->dev, "Driver Initializing success\n");
 	return 0;
 
-clk_disable_unprepare:
-	clk_disable_unprepare(wilc->rtc_clk);
 dispose_irq:
 	irq_dispose_mapping(wilc->dev_irq_num);
 	wilc_netdev_cleanup(wilc);
@@ -217,7 +214,6 @@ static void wilc_sdio_remove(struct sdio_func *func)
 	struct wilc *wilc = sdio_get_drvdata(func);
 	struct wilc_sdio *sdio_priv = wilc->bus_data;
 
-	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_netdev_cleanup(wilc);
 	kfree(sdio_priv->cmd53_buf);
 	kfree(sdio_priv);
-- 
cgit v1.3-3-g829e


From ff63a5c727821bd1069a384695bb4557eaddb1a1 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Tue, 3 Sep 2024 19:02:05 +0800
Subject: wifi: wilc1000: Convert using devm_clk_get_optional_enabled() in
 wilc_bus_probe()

Use devm_clk_get_optional_enabled() instead of devm_clk_get_optional() +
clk_prepare_enable(), which can make the clk consistent with the device
life cycle and reduce the risk of unreleased clk resources. Since the
device framework has automatically released the clk resource, there is
no need to execute clk_disable_unprepare(clk) on the error path.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240903110205.4127706-3-lizetao1@huawei.com
---
 drivers/net/wireless/microchip/wilc1000/spi.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c
index 5ff940c53ad9..05b577b1068e 100644
--- a/drivers/net/wireless/microchip/wilc1000/spi.c
+++ b/drivers/net/wireless/microchip/wilc1000/spi.c
@@ -228,12 +228,11 @@ static int wilc_bus_probe(struct spi_device *spi)
 	if (ret < 0)
 		goto netdev_cleanup;
 
-	wilc->rtc_clk = devm_clk_get_optional(&spi->dev, "rtc");
+	wilc->rtc_clk = devm_clk_get_optional_enabled(&spi->dev, "rtc");
 	if (IS_ERR(wilc->rtc_clk)) {
 		ret = PTR_ERR(wilc->rtc_clk);
 		goto netdev_cleanup;
 	}
-	clk_prepare_enable(wilc->rtc_clk);
 
 	dev_info(&spi->dev, "Selected CRC config: crc7=%s, crc16=%s\n",
 		 enable_crc7 ? "on" : "off", enable_crc16 ? "on" : "off");
@@ -266,7 +265,6 @@ static int wilc_bus_probe(struct spi_device *spi)
 	return 0;
 
 power_down:
-	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_wlan_power(wilc, false);
 netdev_cleanup:
 	wilc_netdev_cleanup(wilc);
@@ -280,7 +278,6 @@ static void wilc_bus_remove(struct spi_device *spi)
 	struct wilc *wilc = spi_get_drvdata(spi);
 	struct wilc_spi *spi_priv = wilc->bus_data;
 
-	clk_disable_unprepare(wilc->rtc_clk);
 	wilc_netdev_cleanup(wilc);
 	kfree(spi_priv);
 }
-- 
cgit v1.3-3-g829e


From 54c9b9735246fd32dd020a6196d8128967bb3ff3 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 3 Sep 2024 19:58:11 +0800
Subject: wifi: libertas: Cleanup unused declarations

There is no caller and implementation in tree.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240903115811.958692-1-yuehaibing@huawei.com
---
 drivers/net/wireless/marvell/libertas/cmd.h            | 5 -----
 drivers/net/wireless/marvell/libertas_tf/libertas_tf.h | 3 ---
 2 files changed, 8 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/cmd.h b/drivers/net/wireless/marvell/libertas/cmd.h
index 3c193074662b..d7be232f5739 100644
--- a/drivers/net/wireless/marvell/libertas/cmd.h
+++ b/drivers/net/wireless/marvell/libertas/cmd.h
@@ -116,11 +116,6 @@ int lbs_set_power_adapt_cfg(struct lbs_private *priv, int enable, int8_t p0,
 int lbs_set_tpc_cfg(struct lbs_private *priv, int enable, int8_t p0, int8_t p1,
 		int8_t p2, int usesnr);
 
-int lbs_set_data_rate(struct lbs_private *priv, u8 rate);
-
-int lbs_cmd_802_11_rate_adapt_rateset(struct lbs_private *priv,
-				      uint16_t cmd_action);
-
 int lbs_set_tx_power(struct lbs_private *priv, s16 dbm);
 
 int lbs_set_deep_sleep(struct lbs_private *priv, int deep_sleep);
diff --git a/drivers/net/wireless/marvell/libertas_tf/libertas_tf.h b/drivers/net/wireless/marvell/libertas_tf/libertas_tf.h
index 631b5da09f86..a5d4c09fb918 100644
--- a/drivers/net/wireless/marvell/libertas_tf/libertas_tf.h
+++ b/drivers/net/wireless/marvell/libertas_tf/libertas_tf.h
@@ -484,12 +484,9 @@ void lbtf_complete_command(struct lbtf_private *priv, struct cmd_ctrl_node *cmd,
 void lbtf_cmd_response_rx(struct lbtf_private *priv);
 
 /* main.c */
-struct chan_freq_power *lbtf_get_region_cfp_table(u8 region,
-	int *cfp_no);
 struct lbtf_private *lbtf_add_card(void *card, struct device *dmdev,
 				   const struct lbtf_ops *ops);
 int lbtf_remove_card(struct lbtf_private *priv);
-int lbtf_start_card(struct lbtf_private *priv);
 int lbtf_rx(struct lbtf_private *priv, struct sk_buff *skb);
 void lbtf_send_tx_feedback(struct lbtf_private *priv, u8 retrycnt, u8 fail);
 void lbtf_bcn_sent(struct lbtf_private *priv);
-- 
cgit v1.3-3-g829e


From eeccaa46cb6f8bdf635dc38b84e66ddb9fbbcee7 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 3 Sep 2024 22:10:32 +0200
Subject: wifi: rsi: Remove an unused field in struct rsi_debugfs

dfs_get_ops has apparently never been used since its introduction by
commit dad0d04fa7ba ("rsi: Add RS9113 wireless driver") in 2014-03.

More-over struct rsi_dbg_ops is not defined.

Remove the unused field from struct rsi_debugfs.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/15b0609d7b1569ec6c500a175caef4c9189f33e2.1725394207.git.christophe.jaillet@wanadoo.fr
---
 drivers/net/wireless/rsi/rsi_debugfs.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_debugfs.h b/drivers/net/wireless/rsi/rsi_debugfs.h
index a6a28640ad40..bbc1200dbb62 100644
--- a/drivers/net/wireless/rsi/rsi_debugfs.h
+++ b/drivers/net/wireless/rsi/rsi_debugfs.h
@@ -39,7 +39,6 @@ struct rsi_dbg_files {
 
 struct rsi_debugfs {
 	struct dentry *subdir;
-	struct rsi_dbg_ops *dfs_get_ops;
 	struct dentry *rsi_files[MAX_DEBUGFS_ENTRIES];
 };
 int rsi_init_dbgfs(struct rsi_hw *adapter);
-- 
cgit v1.3-3-g829e


From 4f0568492fc446b25b5538ba2e3a85c2dbe0ab5d Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Wed, 4 Sep 2024 15:46:37 +0800
Subject: wifi: brcmfmac: cfg80211: Convert comma to semicolon

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects.
Although that is not the case here, it is seems best to use ';'
unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20240904074637.1352864-1-nichen@iscas.ac.cn
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 815f6b3c79fc..349aa3439502 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -1135,7 +1135,7 @@ static void brcmf_escan_prep(struct brcmf_cfg80211_info *cfg,
 		offset = offsetof(struct brcmf_scan_params_v2_le, channel_list) +
 				n_channels * sizeof(u16);
 		offset = roundup(offset, sizeof(u32));
-		length += sizeof(ssid_le) * n_ssids,
+		length += sizeof(ssid_le) * n_ssids;
 		ptr = (char *)params_le + offset;
 		for (i = 0; i < n_ssids; i++) {
 			memset(&ssid_le, 0, sizeof(ssid_le));
-- 
cgit v1.3-3-g829e


From 1f23a1909d7f5f7c5fa6809816d61712de1a2d5b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:29 +0300
Subject: netfilter: br_netfilter: Unmask upper DSCP bits in
 br_nf_pre_routing_finish()

Unmask upper DSCP bits when calling ip_route_output() so that in the
future it could perform the FIB lookup according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_netfilter_hooks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 8f9c19d992ac..0e8bc0ea6175 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -36,6 +36,7 @@
 #include <net/route.h>
 #include <net/netfilter/br_netfilter.h>
 #include <net/netns/generic.h>
+#include <net/inet_dscp.h>
 
 #include <linux/uaccess.h>
 #include "br_private.h"
@@ -402,7 +403,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_
 				goto free_skb;
 
 			rt = ip_route_output(net, iph->daddr, 0,
-					     RT_TOS(iph->tos), 0,
+					     iph->tos & INET_DSCP_MASK, 0,
 					     RT_SCOPE_UNIVERSE);
 			if (!IS_ERR(rt)) {
 				/* - Bridged-and-DNAT'ed traffic doesn't
-- 
cgit v1.3-3-g829e


From 25376a890119b616d5982c8cb59f805138ab81fa Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:30 +0300
Subject: ipv4: ip_gre: Unmask upper DSCP bits in ipgre_open()

Unmask the upper DSCP bits when calling ip_route_output_gre() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index b54c41f3ae3c..5f6fd382af38 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -44,6 +44,7 @@
 #include <net/gre.h>
 #include <net/dst_metadata.h>
 #include <net/erspan.h>
+#include <net/inet_dscp.h>
 
 /*
    Problems & solutions
@@ -930,7 +931,7 @@ static int ipgre_open(struct net_device *dev)
 					 t->parms.iph.daddr,
 					 t->parms.iph.saddr,
 					 t->parms.o_key,
-					 RT_TOS(t->parms.iph.tos),
+					 t->parms.iph.tos & INET_DSCP_MASK,
 					 t->parms.link);
 		if (IS_ERR(rt))
 			return -EADDRNOTAVAIL;
-- 
cgit v1.3-3-g829e


From b3899830aa47333fa73e7f23eddc856003fd8bda Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:31 +0300
Subject: bpf: lwtunnel: Unmask upper DSCP bits in bpf_lwt_xmit_reroute()

Unmask the upper DSCP bits when calling ip_route_output_key() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/lwt_bpf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index afb05f58b64c..1a14f915b7a4 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -12,6 +12,7 @@
 #include <net/gre.h>
 #include <net/ip6_route.h>
 #include <net/ipv6_stubs.h>
+#include <net/inet_dscp.h>
 
 struct bpf_lwt_prog {
 	struct bpf_prog *prog;
@@ -205,7 +206,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
 		fl4.flowi4_oif = oif;
 		fl4.flowi4_mark = skb->mark;
 		fl4.flowi4_uid = sock_net_uid(net, sk);
-		fl4.flowi4_tos = RT_TOS(iph->tos);
+		fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 		fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 		fl4.flowi4_proto = iph->protocol;
 		fl4.daddr = iph->daddr;
-- 
cgit v1.3-3-g829e


From 848789d552bbfb47077993bb35ca99c854c37556 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:32 +0300
Subject: ipv4: icmp: Unmask upper DSCP bits in icmp_reply()

Unmask the upper DSCP bits when calling ip_route_output_key() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/icmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d2463b6e390e..e1384e7331d8 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -445,7 +445,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.saddr = saddr;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
-	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
+	fl4.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK;
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
 	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
-- 
cgit v1.3-3-g829e


From e7191e517a03d025405c7df730b400ad4118474e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:33 +0300
Subject: ipv4: ip_tunnel: Unmask upper DSCP bits in ip_tunnel_bind_dev()

Unmask the upper DSCP bits when initializing an IPv4 flow key via
ip_tunnel_init_flow() before passing it to ip_route_output_key() so that
in the future we could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 18964394d6bd..b632c128ecb7 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -293,7 +293,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
 				    iph->saddr, tunnel->parms.o_key,
-				    RT_TOS(iph->tos), dev_net(dev),
+				    iph->tos & INET_DSCP_MASK, dev_net(dev),
 				    tunnel->parms.link, tunnel->fwmark, 0, 0);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
-- 
cgit v1.3-3-g829e


From c34cfe72bb260fc49660d9e6a9ba95ba01669ae2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:34 +0300
Subject: ipv4: ip_tunnel: Unmask upper DSCP bits in ip_md_tunnel_xmit()

Unmask the upper DSCP bits when initializing an IPv4 flow key via
ip_tunnel_init_flow() before passing it to ip_route_output_key() so that
in the future we could perform the FIB lookup according to the full DSCP
value.

Note that the 'tos' variable includes the full DS field. Either the one
specified via the tunnel key or the one inherited from the inner packet.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index b632c128ecb7..09e0effcd034 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -43,6 +43,7 @@
 #include <net/rtnetlink.h>
 #include <net/udp.h>
 #include <net/dst_metadata.h>
+#include <net/inet_dscp.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
@@ -609,9 +610,9 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 	}
 	ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
-			    tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
-			    dev_net(dev), 0, skb->mark, skb_get_hash(skb),
-			    key->flow_flags);
+			    tunnel_id_to_key32(key->tun_id),
+			    tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark,
+			    skb_get_hash(skb), key->flow_flags);
 
 	if (!tunnel_hlen)
 		tunnel_hlen = ip_encap_hlen(&tun_info->encap);
-- 
cgit v1.3-3-g829e


From c2b639f9f3b7a058ca9c7349b096f355773f2cd8 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:35 +0300
Subject: ipv4: ip_tunnel: Unmask upper DSCP bits in ip_tunnel_xmit()

Unmask the upper DSCP bits when initializing an IPv4 flow key via
ip_tunnel_init_flow() before passing it to ip_route_output_key() so that
in the future we could perform the FIB lookup according to the full DSCP
value.

Note that the 'tos' variable includes the full DS field. Either the one
specified as part of the tunnel parameters or the one inherited from the
inner packet.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_tunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 09e0effcd034..d591c73e2c0e 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -773,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
-			    tunnel->parms.o_key, RT_TOS(tos),
+			    tunnel->parms.o_key, tos & INET_DSCP_MASK,
 			    dev_net(dev), READ_ONCE(tunnel->parms.link),
 			    tunnel->fwmark, skb_get_hash(skb), 0);
 
-- 
cgit v1.3-3-g829e


From 4f0880766a971409684eeac0aa39378036d17cb4 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:36 +0300
Subject: ipv4: netfilter: Unmask upper DSCP bits in ip_route_me_harder()

Unmask the upper DSCP bits when calling ip_route_output_key() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/netfilter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 591a2737808e..e0aab66cd925 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -14,6 +14,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#include <net/inet_dscp.h>
 #include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
@@ -43,7 +44,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un
 	 */
 	fl4.daddr = iph->daddr;
 	fl4.saddr = saddr;
-	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 	fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
 	fl4.flowi4_l3mdev = l3mdev_master_ifindex(dev);
 	fl4.flowi4_mark = skb->mark;
-- 
cgit v1.3-3-g829e


From b7172768abfd8aecdc6af05c60403af1664a4976 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:37 +0300
Subject: netfilter: nft_flow_offload: Unmask upper DSCP bits in
 nft_flow_route()

Unmask the upper DSCP bits when calling nf_route() which eventually
calls ip_route_output_key() so that in the future it could perform the
FIB lookup according to the full DSCP value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netfilter/nft_flow_offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 9dcd1548df9d..2f732fae5a83 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -9,6 +9,7 @@
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/ip.h> /* for ipv4 options. */
+#include <net/inet_dscp.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_conntrack_core.h>
@@ -235,7 +236,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 		fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip;
 		fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
 		fl.u.ip4.flowi4_iif = this_dst->dev->ifindex;
-		fl.u.ip4.flowi4_tos = RT_TOS(ip_hdr(pkt->skb)->tos);
+		fl.u.ip4.flowi4_tos = ip_hdr(pkt->skb)->tos & INET_DSCP_MASK;
 		fl.u.ip4.flowi4_mark = pkt->skb->mark;
 		fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 		break;
-- 
cgit v1.3-3-g829e


From 345663e6a727f6baa70989a8412c2c047389ca65 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:38 +0300
Subject: netfilter: nf_dup4: Unmask upper DSCP bits in nf_dup_ipv4_route()

Unmask the upper DSCP bits when calling ip_route_output_key() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/netfilter/nf_dup_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index 6cc5743c553a..f4aed0789d69 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -15,6 +15,7 @@
 #include <net/icmp.h>
 #include <net/ip.h>
 #include <net/route.h>
+#include <net/inet_dscp.h>
 #include <net/netfilter/ipv4/nf_dup_ipv4.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
@@ -32,7 +33,7 @@ static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb,
 		fl4.flowi4_oif = oif;
 
 	fl4.daddr = gw->s_addr;
-	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_tos = iph->tos & INET_DSCP_MASK;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH;
 	rt = ip_route_output_key(net, &fl4);
-- 
cgit v1.3-3-g829e


From 2c60fc9ca21636e4bbb30357562dc1abb577f5fb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:39 +0300
Subject: ipv4: udp_tunnel: Unmask upper DSCP bits in udp_tunnel_dst_lookup()

Unmask the upper DSCP bits when calling ip_route_output_key() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Note that callers of udp_tunnel_dst_lookup() pass the entire DS field in
the 'tos' argument.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp_tunnel_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index e4e0fa869fa4..619a53eb672d 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -6,6 +6,7 @@
 #include <net/dst_metadata.h>
 #include <net/udp.h>
 #include <net/udp_tunnel.h>
+#include <net/inet_dscp.h>
 
 int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 		     struct socket **sockp)
@@ -232,7 +233,7 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb,
 	fl4.saddr = key->u.ipv4.src;
 	fl4.fl4_dport = dport;
 	fl4.fl4_sport = sport;
-	fl4.flowi4_tos = RT_TOS(tos);
+	fl4.flowi4_tos = tos & INET_DSCP_MASK;
 	fl4.flowi4_flags = key->flow_flags;
 
 	rt = ip_route_output_key(net, &fl4);
-- 
cgit v1.3-3-g829e


From 8b6d13cc8b3855862af583fed83d60b1df6f9ba2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 5 Sep 2024 19:51:40 +0300
Subject: sctp: Unmask upper DSCP bits in sctp_v4_get_dst()

Unmask the upper DSCP bits when calling ip_route_output_key() so that in
the future it could perform the FIB lookup according to the full DSCP
value.

Note that the 'tos' variable holds the full DS field.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/protocol.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 5a7436a13b74..39ca5403d4d7 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -44,6 +44,7 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 #include <net/udp_tunnel.h>
+#include <net/inet_dscp.h>
 
 #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
 
@@ -435,7 +436,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
-		fl4->flowi4_tos = RT_TOS(tos);
+		fl4->flowi4_tos = tos & INET_DSCP_MASK;
 		fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk);
 		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
 		fl4->fl4_sport = htons(asoc->base.bind_addr.port);
-- 
cgit v1.3-3-g829e


From 6a13f5afd39d17320316dbb8dd533fe7c6a613e6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 30 Aug 2024 16:39:10 +0200
Subject: xfrm: policy: fix null dereference

Julian Wiedmann says:
> +     if (!xfrm_pol_hold_rcu(ret))

Coverity spotted that ^^^ needs a s/ret/pol fix-up:

> CID 1599386:  Null pointer dereferences  (FORWARD_NULL)
> Passing null pointer "ret" to "xfrm_pol_hold_rcu", which dereferences it.

Ditch the bogus 'ret' variable.

Fixes: 563d5ca93e88 ("xfrm: switch migrate to xfrm_policy_lookup_bytype")
Reported-by: Julian Wiedmann <jwiedmann.dev@gmail.com>
Closes: https://lore.kernel.org/netdev/06dc2499-c095-4bd4-aee3-a1d0e3ec87c4@gmail.com/
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 6336baa8a93c..31c14457fdaf 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4429,7 +4429,7 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete);
 static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel,
 						    u8 dir, u8 type, struct net *net, u32 if_id)
 {
-	struct xfrm_policy *pol, *ret = NULL;
+	struct xfrm_policy *pol;
 	struct flowi fl;
 
 	memset(&fl, 0, sizeof(fl));
@@ -4465,7 +4465,7 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *
 	if (IS_ERR_OR_NULL(pol))
 		goto out_unlock;
 
-	if (!xfrm_pol_hold_rcu(ret))
+	if (!xfrm_pol_hold_rcu(pol))
 		pol = NULL;
 out_unlock:
 	rcu_read_unlock();
-- 
cgit v1.3-3-g829e


From e62d39332d4b9400a69ba902797aa17a1a0037e7 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 29 Aug 2024 11:14:54 -0700
Subject: xfrm: policy: Restore dir assignments in xfrm_hash_rebuild()

Clang warns (or errors with CONFIG_WERROR):

  net/xfrm/xfrm_policy.c:1286:8: error: variable 'dir' is uninitialized when used here [-Werror,-Wuninitialized]
   1286 |                 if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
        |                      ^~~
  net/xfrm/xfrm_policy.c:1257:9: note: initialize the variable 'dir' to silence this warning
   1257 |         int dir;
        |                ^
        |                 = 0
  1 error generated.

A recent refactoring removed some assignments to dir because
xfrm_policy_is_dead_or_sk() has a dir assignment in it. However, dir is
used elsewhere in xfrm_hash_rebuild(), including within loops where it
needs to be reloaded for each policy. Restore the assignments before the
first use of dir to fix the warning and ensure dir is properly
initialized throughout the function.

Fixes: 08c2182cf0b4 ("xfrm: policy: use recently added helper in more places")
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 31c14457fdaf..428ee83fe298 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1283,6 +1283,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		if (xfrm_policy_is_dead_or_sk(policy))
 			continue;
 
+		dir = xfrm_policy_id2dir(policy->index);
 		if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
 			if (policy->family == AF_INET) {
 				dbits = rbits4;
@@ -1337,6 +1338,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 		hlist_del_rcu(&policy->bydst);
 
 		newpos = NULL;
+		dir = xfrm_policy_id2dir(policy->index);
 		chain = policy_hash_bysel(net, &policy->selector,
 					  policy->family, dir);
 
-- 
cgit v1.3-3-g829e


From 34c626c3004a73ee7da5072be48ddff9c2902902 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Mon, 16 Jan 2023 01:16:43 +0200
Subject: net/mlx5: Added missing mlx5_ifc definition for HW Steering

Add mlx5_ifc definitions that are required for HWS support.

Note that due to change in the mlx5_ifc_flow_table_context_bits
structure that now includes both SWS and HWS bits in a union,
this patch also includes small change in one of SWS files that
was required for compilation.

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/steering/dr_cmd.c  |  12 +-
 include/linux/mlx5/mlx5_ifc.h                      | 189 ++++++++++++++++++---
 2 files changed, 167 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
index 8c2a34a0d6be..baefb9a3fa05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c
@@ -251,9 +251,9 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev,
 	output->level = MLX5_GET(query_flow_table_out, out, flow_table_context.level);
 
 	output->sw_owner_icm_root_1 = MLX5_GET64(query_flow_table_out, out,
-						 flow_table_context.sw_owner_icm_root_1);
+						 flow_table_context.sws.sw_owner_icm_root_1);
 	output->sw_owner_icm_root_0 = MLX5_GET64(query_flow_table_out, out,
-						 flow_table_context.sw_owner_icm_root_0);
+						 flow_table_context.sws.sw_owner_icm_root_0);
 
 	return 0;
 }
@@ -480,15 +480,15 @@ int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
 		 */
 		if (attr->table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) {
 			MLX5_SET64(flow_table_context, ft_mdev,
-				   sw_owner_icm_root_0, attr->icm_addr_rx);
+				   sws.sw_owner_icm_root_0, attr->icm_addr_rx);
 		} else if (attr->table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) {
 			MLX5_SET64(flow_table_context, ft_mdev,
-				   sw_owner_icm_root_0, attr->icm_addr_tx);
+				   sws.sw_owner_icm_root_0, attr->icm_addr_tx);
 		} else if (attr->table_type == MLX5_FLOW_TABLE_TYPE_FDB) {
 			MLX5_SET64(flow_table_context, ft_mdev,
-				   sw_owner_icm_root_0, attr->icm_addr_rx);
+				   sws.sw_owner_icm_root_0, attr->icm_addr_rx);
 			MLX5_SET64(flow_table_context, ft_mdev,
-				   sw_owner_icm_root_1, attr->icm_addr_tx);
+				   sws.sw_owner_icm_root_1, attr->icm_addr_tx);
 		}
 	}
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 234ad6f16e92..b6f8e3834bd3 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -80,23 +80,15 @@ enum {
 
 enum {
 	MLX5_OBJ_TYPE_SW_ICM = 0x0008,
-	MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT  = 0x23,
-};
-
-enum {
-	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
-	MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
-	MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13),
-	MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT =
-		(1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT),
-	MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39),
-};
-
-enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
 	MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d,
 	MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c,
 	MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018,
+	MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT  = 0x23,
+	MLX5_OBJ_TYPE_STC = 0x0040,
+	MLX5_OBJ_TYPE_RTC = 0x0041,
+	MLX5_OBJ_TYPE_STE = 0x0042,
+	MLX5_OBJ_TYPE_MODIFY_HDR_PATTERN = 0x0043,
 	MLX5_OBJ_TYPE_PAGE_TRACK = 0x46,
 	MLX5_OBJ_TYPE_MKEY = 0xff01,
 	MLX5_OBJ_TYPE_QP = 0xff02,
@@ -112,6 +104,16 @@ enum {
 	MLX5_OBJ_TYPE_RQT = 0xff0e,
 	MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f,
 	MLX5_OBJ_TYPE_CQ = 0xff10,
+	MLX5_OBJ_TYPE_FT_ALIAS = 0xff15,
+};
+
+enum {
+	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
+	MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
+	MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13),
+	MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT =
+		(1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT),
+	MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39),
 };
 
 enum {
@@ -313,6 +315,7 @@ enum {
 	MLX5_CMD_OP_MODIFY_VHCA_STATE             = 0xb0e,
 	MLX5_CMD_OP_SYNC_CRYPTO                   = 0xb12,
 	MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS       = 0xb16,
+	MLX5_CMD_OP_GENERATE_WQE                  = 0xb17,
 	MLX5_CMD_OP_MAX
 };
 
@@ -485,7 +488,13 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         reserved_at_66[0x2];
 	u8         reformat_add_macsec[0x1];
 	u8         reformat_remove_macsec[0x1];
-	u8         reserved_at_6a[0xe];
+	u8         reparse[0x1];
+	u8         reserved_at_6b[0x1];
+	u8         cross_vhca_object[0x1];
+	u8         reformat_l2_to_l3_audp_tunnel[0x1];
+	u8         reformat_l3_audp_tunnel_to_l2[0x1];
+	u8         ignore_flow_level_rtc_valid[0x1];
+	u8         reserved_at_70[0x8];
 	u8         log_max_ft_num[0x8];
 
 	u8         reserved_at_80[0x10];
@@ -522,7 +531,15 @@ struct mlx5_ifc_ipv6_layout_bits {
 	u8         ipv6[16][0x8];
 };
 
+struct mlx5_ifc_ipv6_simple_layout_bits {
+	u8         ipv6_127_96[0x20];
+	u8         ipv6_95_64[0x20];
+	u8         ipv6_63_32[0x20];
+	u8         ipv6_31_0[0x20];
+};
+
 union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits {
+	struct mlx5_ifc_ipv6_simple_layout_bits ipv6_simple_layout;
 	struct mlx5_ifc_ipv6_layout_bits ipv6_layout;
 	struct mlx5_ifc_ipv4_layout_bits ipv4_layout;
 	u8         reserved_at_0[0x80];
@@ -911,7 +928,9 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      reserved_at_8[0x5];
 	u8      fdb_uplink_hairpin[0x1];
 	u8      fdb_multi_path_any_table_limit_regc[0x1];
-	u8      reserved_at_f[0x3];
+	u8      reserved_at_f[0x1];
+	u8      fdb_dynamic_tunnel[0x1];
+	u8      reserved_at_11[0x1];
 	u8      fdb_multi_path_any_table[0x1];
 	u8      reserved_at_13[0x2];
 	u8      fdb_modify_header_fwd_to_table[0x1];
@@ -950,6 +969,73 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      reserved_at_1900[0x6700];
 };
 
+struct mlx5_ifc_wqe_based_flow_table_cap_bits {
+	u8         reserved_at_0[0x3];
+	u8         log_max_num_ste[0x5];
+	u8         reserved_at_8[0x3];
+	u8         log_max_num_stc[0x5];
+	u8         reserved_at_10[0x3];
+	u8         log_max_num_rtc[0x5];
+	u8         reserved_at_18[0x3];
+	u8         log_max_num_header_modify_pattern[0x5];
+
+	u8         rtc_hash_split_table[0x1];
+	u8         rtc_linear_lookup_table[0x1];
+	u8         reserved_at_22[0x1];
+	u8         stc_alloc_log_granularity[0x5];
+	u8         reserved_at_28[0x3];
+	u8         stc_alloc_log_max[0x5];
+	u8         reserved_at_30[0x3];
+	u8         ste_alloc_log_granularity[0x5];
+	u8         reserved_at_38[0x3];
+	u8         ste_alloc_log_max[0x5];
+
+	u8         reserved_at_40[0xb];
+	u8         rtc_reparse_mode[0x5];
+	u8         reserved_at_50[0x3];
+	u8         rtc_index_mode[0x5];
+	u8         reserved_at_58[0x3];
+	u8         rtc_log_depth_max[0x5];
+
+	u8         reserved_at_60[0x10];
+	u8         ste_format[0x10];
+
+	u8         stc_action_type[0x80];
+
+	u8         header_insert_type[0x10];
+	u8         header_remove_type[0x10];
+
+	u8         trivial_match_definer[0x20];
+
+	u8         reserved_at_140[0x1b];
+	u8         rtc_max_num_hash_definer_gen_wqe[0x5];
+
+	u8         reserved_at_160[0x18];
+	u8         access_index_mode[0x8];
+
+	u8         reserved_at_180[0x10];
+	u8         ste_format_gen_wqe[0x10];
+
+	u8         linear_match_definer_reg_c3[0x20];
+
+	u8         fdb_jump_to_tir_stc[0x1];
+	u8         reserved_at_1c1[0x1f];
+};
+
+struct mlx5_ifc_esw_cap_bits {
+	u8         reserved_at_0[0x1d];
+	u8         merged_eswitch[0x1];
+	u8         reserved_at_1e[0x2];
+
+	u8         reserved_at_20[0x40];
+
+	u8         esw_manager_vport_number_valid[0x1];
+	u8         reserved_at_61[0xf];
+	u8         esw_manager_vport_number[0x10];
+
+	u8         reserved_at_80[0x780];
+};
+
 enum {
 	MLX5_COUNTER_SOURCE_ESWITCH = 0x0,
 	MLX5_COUNTER_FLOW_ESWITCH   = 0x1,
@@ -1443,9 +1529,13 @@ enum {
 };
 
 enum {
+	MLX5_FLEX_IPV4_OVER_VXLAN_ENABLED	= 1 << 0,
+	MLX5_FLEX_IPV6_OVER_VXLAN_ENABLED	= 1 << 1,
+	MLX5_FLEX_IPV6_OVER_IP_ENABLED		= 1 << 2,
 	MLX5_FLEX_PARSER_GENEVE_ENABLED		= 1 << 3,
 	MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED	= 1 << 4,
 	MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED	= 1 << 5,
+	MLX5_FLEX_P_BIT_VXLAN_GPE_ENABLED	= 1 << 6,
 	MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED	= 1 << 7,
 	MLX5_FLEX_PARSER_ICMP_V4_ENABLED	= 1 << 8,
 	MLX5_FLEX_PARSER_ICMP_V6_ENABLED	= 1 << 9,
@@ -1650,7 +1740,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         pci_sync_for_fw_update_event[0x1];
 	u8         reserved_at_1f2[0x6];
 	u8         init2_lag_tx_port_affinity[0x1];
-	u8         reserved_at_1fa[0x3];
+	u8         reserved_at_1fa[0x2];
+	u8         wqe_based_flow_table_update_cap[0x1];
 	u8         cqe_version[0x4];
 
 	u8         compact_address_vector[0x1];
@@ -1959,7 +2050,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_760[0x3];
 	u8         log_max_num_header_modify_argument[0x5];
-	u8         reserved_at_768[0x4];
+	u8         log_header_modify_argument_granularity_offset[0x4];
 	u8         log_header_modify_argument_granularity[0x4];
 	u8         reserved_at_770[0x3];
 	u8         log_header_modify_argument_max_alloc[0x5];
@@ -2006,7 +2097,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_140[0x60];
 
 	u8	   flow_table_type_2_type[0x8];
-	u8	   reserved_at_1a8[0x3];
+	u8	   reserved_at_1a8[0x2];
+	u8         format_select_dw_8_6_ext[0x1];
 	u8	   log_min_mkey_entity_size[0x5];
 	u8	   reserved_at_1b0[0x10];
 
@@ -2022,6 +2114,16 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_250[0x10];
 
 	u8	   reserved_at_260[0x120];
+
+	u8	   format_select_dw_gtpu_dw_0[0x8];
+	u8	   format_select_dw_gtpu_dw_1[0x8];
+	u8	   format_select_dw_gtpu_dw_2[0x8];
+	u8	   format_select_dw_gtpu_first_ext_dw_0[0x8];
+
+	u8	   generate_wqe_type[0x20];
+
+	u8	   reserved_at_2c0[0xc0];
+
 	u8	   reserved_at_380[0xb];
 	u8	   min_mkey_log_entity_size_fixed_buffer[0x5];
 	u8	   ec_vf_vport_base[0x10];
@@ -2037,9 +2139,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 
 	u8	   reserved_at_400[0x1];
 	u8	   min_mkey_log_entity_size_fixed_buffer_valid[0x1];
-	u8	   reserved_at_402[0x1e];
+	u8	   reserved_at_402[0xe];
+	u8	   return_reg_id[0x10];
 
-	u8	   reserved_at_420[0x20];
+	u8	   reserved_at_420[0x1c];
+	u8	   flow_table_hash_type[0x4];
 
 	u8	   reserved_at_440[0x8];
 	u8	   max_num_eqs_24b[0x18];
@@ -2086,7 +2190,7 @@ struct mlx5_ifc_extended_dest_format_bits {
 	u8         reserved_at_60[0x20];
 };
 
-union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits {
+union mlx5_ifc_dest_format_flow_counter_list_auto_bits {
 	struct mlx5_ifc_extended_dest_format_bits extended_dest_format;
 	struct mlx5_ifc_flow_counter_list_bits flow_counter_list;
 };
@@ -2178,7 +2282,10 @@ struct mlx5_ifc_wq_bits {
 	u8         reserved_at_139[0x4];
 	u8         log_wqe_stride_size[0x3];
 
-	u8         reserved_at_140[0x80];
+	u8         dbr_umem_id[0x20];
+	u8         wq_umem_id[0x20];
+
+	u8         wq_umem_offset[0x40];
 
 	u8         headers_mkey[0x20];
 
@@ -3562,6 +3669,8 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps;
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
+	struct mlx5_ifc_wqe_based_flow_table_cap_bits wqe_based_flow_table_cap;
+	struct mlx5_ifc_esw_cap_bits esw_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	struct mlx5_ifc_port_selection_cap_bits port_selection_cap;
 	struct mlx5_ifc_qos_cap_bits qos_cap;
@@ -3678,7 +3787,7 @@ struct mlx5_ifc_flow_context_bits {
 
 	u8         reserved_at_1300[0x500];
 
-	union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[];
+	union mlx5_ifc_dest_format_flow_counter_list_auto_bits destination[];
 };
 
 enum {
@@ -3919,7 +4028,8 @@ struct mlx5_ifc_sqc_bits {
 	u8         reg_umr[0x1];
 	u8         allow_swp[0x1];
 	u8         hairpin[0x1];
-	u8         reserved_at_f[0xb];
+	u8         non_wire[0x1];
+	u8         reserved_at_10[0xa];
 	u8	   ts_format[0x2];
 	u8	   reserved_at_1c[0x4];
 
@@ -4961,6 +5071,16 @@ struct mlx5_ifc_set_fte_in_bits {
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
 
+struct mlx5_ifc_dest_format_bits {
+	u8         destination_type[0x8];
+	u8         destination_id[0x18];
+
+	u8         destination_eswitch_owner_vhca_id_valid[0x1];
+	u8         packet_reformat[0x1];
+	u8         reserved_at_22[0xe];
+	u8         destination_eswitch_owner_vhca_id[0x10];
+};
+
 struct mlx5_ifc_rts2rts_qp_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6127,7 +6247,8 @@ struct mlx5_ifc_flow_table_context_bits {
 	u8         termination_table[0x1];
 	u8         table_miss_action[0x4];
 	u8         level[0x8];
-	u8         reserved_at_10[0x8];
+	u8         rtc_valid[0x1];
+	u8         reserved_at_11[0x7];
 	u8         log_size[0x8];
 
 	u8         reserved_at_20[0x8];
@@ -6137,11 +6258,21 @@ struct mlx5_ifc_flow_table_context_bits {
 	u8         lag_master_next_table_id[0x18];
 
 	u8         reserved_at_60[0x60];
+	union {
+		struct {
+			u8         sw_owner_icm_root_1[0x40];
+
+			u8         sw_owner_icm_root_0[0x40];
+		} sws;
+		struct {
+			u8         rtc_id_0[0x20];
 
-	u8         sw_owner_icm_root_1[0x40];
+			u8         rtc_id_1[0x20];
 
-	u8         sw_owner_icm_root_0[0x40];
+			u8         reserved_at_100[0x40];
 
+		} hws;
+	};
 };
 
 struct mlx5_ifc_query_flow_table_out_bits {
@@ -8923,7 +9054,9 @@ struct mlx5_ifc_create_qp_in_bits {
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_at_800[0x60];
+	u8         wq_umem_offset[0x40];
+
+	u8         wq_umem_id[0x20];
 
 	u8         wq_umem_valid[0x1];
 	u8         reserved_at_861[0x1f];
-- 
cgit v1.3-3-g829e


From 00b9f0daefd7670356e592d418c890acf9179c94 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Tue, 17 Jan 2023 17:14:51 +0200
Subject: net/mlx5: Added missing definitions in preparation for HW Steering

As part of preparation for HWS, added missing definitions
in qp.h and fs_core.h:

 - FS_FT_FDB_RX/TX table types that are used by HWS in addition
   to an existing FS_FT_FDB
 - MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE that is used by HWS to
   require fence in WQE

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 8 ++++++--
 include/linux/mlx5/qp.h                           | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 78eb6b7097e1..6201647d6156 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -110,7 +110,9 @@ enum fs_flow_table_type {
 	FS_FT_RDMA_RX		= 0X7,
 	FS_FT_RDMA_TX		= 0X8,
 	FS_FT_PORT_SEL		= 0X9,
-	FS_FT_MAX_TYPE = FS_FT_PORT_SEL,
+	FS_FT_FDB_RX		= 0xa,
+	FS_FT_FDB_TX		= 0xb,
+	FS_FT_MAX_TYPE = FS_FT_FDB_TX,
 };
 
 enum fs_flow_table_op_mod {
@@ -368,7 +370,9 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 	(type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) :		\
 	(type == FS_FT_RDMA_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) :      \
 	(type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) :      \
-	(BUILD_BUG_ON_ZERO(FS_FT_PORT_SEL != FS_FT_MAX_TYPE))\
+	(type == FS_FT_FDB_RX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
+	(type == FS_FT_FDB_TX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
+	(BUILD_BUG_ON_ZERO(FS_FT_FDB_TX != FS_FT_MAX_TYPE))\
 	)
 
 #endif
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index ad1ce650146c..fc7eeff99a8a 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -149,6 +149,7 @@ enum {
 	MLX5_WQE_CTRL_CQ_UPDATE		= 2 << 2,
 	MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE	= 3 << 2,
 	MLX5_WQE_CTRL_SOLICITED		= 1 << 1,
+	MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE = 1 << 5,
 };
 
 enum {
-- 
cgit v1.3-3-g829e


From 504e536d90104c850731840d3fbc95acf251f11b Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:31:59 +0300
Subject: net/mlx5: HWS, added actions handling

When a packet matches a flow, the actions specified for the flow are
applied. The supported actions include (but not limited to) the following:
 - drop: packet processing is stopped
 - go to vport: packet is forwarded to a specified vport
 - go to flow table: packet is forwarded to a specified table
   and processing continues there
 - push/pop vlan: add/remove vlan header respectively to/from the packet
 - insert/remove header: add/remove a user-defined header to/from
   the packet
 - counter: count the packet bytes in the specified counter
 - tag: tag the matching flow with a provided tag value
 - reformat: change the packet format by adding or removing some
   of its headers
 - modify header: modify the value of the packet headers with
   set/add/copy ops
 - range: match packet on range of values

Reviewed-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_action.c        | 2604 ++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_action.h        |  307 +++
 2 files changed, 2911 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.c
new file mode 100644
index 000000000000..b27bb4106532
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.c
@@ -0,0 +1,2604 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+#define MLX5HWS_ACTION_METER_INIT_COLOR_OFFSET 1
+
+/* Header removal size limited to 128B (64 words) */
+#define MLX5HWS_ACTION_REMOVE_HEADER_MAX_SIZE 128
+
+/* This is the longest supported action sequence for FDB table:
+ * DECAP, POP_VLAN, MODIFY, CTR, ASO, PUSH_VLAN, MODIFY, ENCAP, Term.
+ */
+static const u32 action_order_arr[MLX5HWS_TABLE_TYPE_MAX][MLX5HWS_ACTION_TYP_MAX] = {
+	[MLX5HWS_TABLE_TYPE_FDB] = {
+		BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
+		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
+		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
+		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+		BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
+		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
+		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
+		BIT(MLX5HWS_ACTION_TYP_CTR),
+		BIT(MLX5HWS_ACTION_TYP_TAG),
+		BIT(MLX5HWS_ACTION_TYP_ASO_METER),
+		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+		BIT(MLX5HWS_ACTION_TYP_TBL) |
+		BIT(MLX5HWS_ACTION_TYP_VPORT) |
+		BIT(MLX5HWS_ACTION_TYP_DROP) |
+		BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
+		BIT(MLX5HWS_ACTION_TYP_RANGE) |
+		BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
+		BIT(MLX5HWS_ACTION_TYP_LAST),
+	},
+};
+
+static const char * const mlx5hws_action_type_str[] = {
+	[MLX5HWS_ACTION_TYP_LAST] = "LAST",
+	[MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2] = "TNL_L2_TO_L2",
+	[MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2] = "L2_TO_TNL_L2",
+	[MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2] = "TNL_L3_TO_L2",
+	[MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3] = "L2_TO_TNL_L3",
+	[MLX5HWS_ACTION_TYP_DROP] = "DROP",
+	[MLX5HWS_ACTION_TYP_TBL] = "TBL",
+	[MLX5HWS_ACTION_TYP_CTR] = "CTR",
+	[MLX5HWS_ACTION_TYP_TAG] = "TAG",
+	[MLX5HWS_ACTION_TYP_MODIFY_HDR] = "MODIFY_HDR",
+	[MLX5HWS_ACTION_TYP_VPORT] = "VPORT",
+	[MLX5HWS_ACTION_TYP_MISS] = "DEFAULT_MISS",
+	[MLX5HWS_ACTION_TYP_POP_VLAN] = "POP_VLAN",
+	[MLX5HWS_ACTION_TYP_PUSH_VLAN] = "PUSH_VLAN",
+	[MLX5HWS_ACTION_TYP_ASO_METER] = "ASO_METER",
+	[MLX5HWS_ACTION_TYP_DEST_ARRAY] = "DEST_ARRAY",
+	[MLX5HWS_ACTION_TYP_INSERT_HEADER] = "INSERT_HEADER",
+	[MLX5HWS_ACTION_TYP_REMOVE_HEADER] = "REMOVE_HEADER",
+	[MLX5HWS_ACTION_TYP_SAMPLER] = "SAMPLER",
+	[MLX5HWS_ACTION_TYP_RANGE] = "RANGE",
+};
+
+static_assert(ARRAY_SIZE(mlx5hws_action_type_str) == MLX5HWS_ACTION_TYP_MAX,
+	      "Missing mlx5hws_action_type_str");
+
+const char *mlx5hws_action_type_to_str(enum mlx5hws_action_type action_type)
+{
+	return mlx5hws_action_type_str[action_type];
+}
+
+enum mlx5hws_action_type mlx5hws_action_get_type(struct mlx5hws_action *action)
+{
+	return action->type;
+}
+
+static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
+					 enum mlx5hws_context_shared_stc_type stc_type,
+					 u8 tbl_type)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_action_shared_stc *shared_stc;
+	int ret;
+
+	mutex_lock(&ctx->ctrl_lock);
+	if (ctx->common_res[tbl_type].shared_stc[stc_type]) {
+		ctx->common_res[tbl_type].shared_stc[stc_type]->refcount++;
+		mutex_unlock(&ctx->ctrl_lock);
+		return 0;
+	}
+
+	shared_stc = kzalloc(sizeof(*shared_stc), GFP_KERNEL);
+	if (!shared_stc) {
+		ret = -ENOMEM;
+		goto unlock_and_out;
+	}
+	switch (stc_type) {
+	case MLX5HWS_CONTEXT_SHARED_STC_DECAP_L3:
+		stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_HEADER_REMOVE;
+		stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+		stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+		stc_attr.remove_header.decap = 0;
+		stc_attr.remove_header.start_anchor = MLX5_HEADER_ANCHOR_PACKET_START;
+		stc_attr.remove_header.end_anchor = MLX5_HEADER_ANCHOR_IPV6_IPV4;
+		break;
+	case MLX5HWS_CONTEXT_SHARED_STC_DOUBLE_POP:
+		stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_REMOVE_WORDS;
+		stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+		stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+		stc_attr.remove_words.start_anchor = MLX5_HEADER_ANCHOR_FIRST_VLAN_START;
+		stc_attr.remove_words.num_of_words = MLX5HWS_ACTION_HDR_LEN_L2_VLAN;
+		break;
+	default:
+		mlx5hws_err(ctx, "No such stc_type: %d\n", stc_type);
+		pr_warn("HWS: Invalid stc_type: %d\n", stc_type);
+		ret = -EINVAL;
+		goto unlock_and_out;
+	}
+
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
+					      &shared_stc->stc_chunk);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate shared decap l2 STC\n");
+		goto free_shared_stc;
+	}
+
+	ctx->common_res[tbl_type].shared_stc[stc_type] = shared_stc;
+	ctx->common_res[tbl_type].shared_stc[stc_type]->refcount = 1;
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return 0;
+
+free_shared_stc:
+	kfree(shared_stc);
+unlock_and_out:
+	mutex_unlock(&ctx->ctrl_lock);
+	return ret;
+}
+
+static int hws_action_get_shared_stc(struct mlx5hws_action *action,
+				     enum mlx5hws_context_shared_stc_type stc_type)
+{
+	struct mlx5hws_context *ctx = action->ctx;
+	int ret;
+
+	if (stc_type >= MLX5HWS_CONTEXT_SHARED_STC_MAX) {
+		pr_warn("HWS: Invalid shared stc_type: %d\n", stc_type);
+		return -EINVAL;
+	}
+
+	if (unlikely(!(action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB))) {
+		pr_warn("HWS: Invalid action->flags: %d\n", action->flags);
+		return -EINVAL;
+	}
+
+	ret = hws_action_get_shared_stc_nic(ctx, stc_type, MLX5HWS_TABLE_TYPE_FDB);
+	if (ret) {
+		mlx5hws_err(ctx,
+			    "Failed to allocate memory for FDB shared STCs (type: %d)\n",
+			    stc_type);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void hws_action_put_shared_stc(struct mlx5hws_action *action,
+				      enum mlx5hws_context_shared_stc_type stc_type)
+{
+	enum mlx5hws_table_type tbl_type = MLX5HWS_TABLE_TYPE_FDB;
+	struct mlx5hws_action_shared_stc *shared_stc;
+	struct mlx5hws_context *ctx = action->ctx;
+
+	if (stc_type >= MLX5HWS_CONTEXT_SHARED_STC_MAX) {
+		pr_warn("HWS: Invalid shared stc_type: %d\n", stc_type);
+		return;
+	}
+
+	mutex_lock(&ctx->ctrl_lock);
+	if (--ctx->common_res[tbl_type].shared_stc[stc_type]->refcount) {
+		mutex_unlock(&ctx->ctrl_lock);
+		return;
+	}
+
+	shared_stc = ctx->common_res[tbl_type].shared_stc[stc_type];
+
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &shared_stc->stc_chunk);
+	kfree(shared_stc);
+	ctx->common_res[tbl_type].shared_stc[stc_type] = NULL;
+	mutex_unlock(&ctx->ctrl_lock);
+}
+
+static void hws_action_print_combo(struct mlx5hws_context *ctx,
+				   enum mlx5hws_action_type *user_actions)
+{
+	mlx5hws_err(ctx, "Invalid action_type sequence");
+	while (*user_actions != MLX5HWS_ACTION_TYP_LAST) {
+		mlx5hws_err(ctx, " %s", mlx5hws_action_type_to_str(*user_actions));
+		user_actions++;
+	}
+	mlx5hws_err(ctx, "\n");
+}
+
+bool mlx5hws_action_check_combo(struct mlx5hws_context *ctx,
+				enum mlx5hws_action_type *user_actions,
+				enum mlx5hws_table_type table_type)
+{
+	const u32 *order_arr = action_order_arr[table_type];
+	u8 order_idx = 0;
+	u8 user_idx = 0;
+	bool valid_combo;
+
+	if (table_type >= MLX5HWS_TABLE_TYPE_MAX) {
+		mlx5hws_err(ctx, "Invalid table_type %d", table_type);
+		return false;
+	}
+
+	while (order_arr[order_idx] != BIT(MLX5HWS_ACTION_TYP_LAST)) {
+		/* User action order validated move to next user action */
+		if (BIT(user_actions[user_idx]) & order_arr[order_idx])
+			user_idx++;
+
+		/* Iterate to the next supported action in the order */
+		order_idx++;
+	}
+
+	/* Combination is valid if all user action were processed */
+	valid_combo = user_actions[user_idx] == MLX5HWS_ACTION_TYP_LAST;
+	if (!valid_combo)
+		hws_action_print_combo(ctx, user_actions);
+
+	return valid_combo;
+}
+
+static bool
+hws_action_fixup_stc_attr(struct mlx5hws_context *ctx,
+			  struct mlx5hws_cmd_stc_modify_attr *stc_attr,
+			  struct mlx5hws_cmd_stc_modify_attr *fixup_stc_attr,
+			  enum mlx5hws_table_type table_type,
+			  bool is_mirror)
+{
+	bool use_fixup = false;
+	u32 fw_tbl_type;
+	u32 base_id;
+
+	fw_tbl_type = mlx5hws_table_get_res_fw_ft_type(table_type, is_mirror);
+
+	switch (stc_attr->action_type) {
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE:
+		if (is_mirror && stc_attr->ste_table.ignore_tx) {
+			fixup_stc_attr->action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
+			fixup_stc_attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+			fixup_stc_attr->stc_offset = stc_attr->stc_offset;
+			use_fixup = true;
+			break;
+		}
+		if (!is_mirror)
+			base_id = mlx5hws_pool_chunk_get_base_id(stc_attr->ste_table.ste_pool,
+								 &stc_attr->ste_table.ste);
+		else
+			base_id =
+				mlx5hws_pool_chunk_get_base_mirror_id(stc_attr->ste_table.ste_pool,
+								      &stc_attr->ste_table.ste);
+
+		*fixup_stc_attr = *stc_attr;
+		fixup_stc_attr->ste_table.ste_obj_id = base_id;
+		use_fixup = true;
+		break;
+
+	case MLX5_IFC_STC_ACTION_TYPE_TAG:
+		if (fw_tbl_type == FS_FT_FDB_TX) {
+			fixup_stc_attr->action_type = MLX5_IFC_STC_ACTION_TYPE_NOP;
+			fixup_stc_attr->action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+			fixup_stc_attr->stc_offset = stc_attr->stc_offset;
+			use_fixup = true;
+		}
+		break;
+
+	case MLX5_IFC_STC_ACTION_TYPE_ALLOW:
+		if (fw_tbl_type == FS_FT_FDB_TX || fw_tbl_type == FS_FT_FDB_RX) {
+			fixup_stc_attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_VPORT;
+			fixup_stc_attr->action_offset = stc_attr->action_offset;
+			fixup_stc_attr->stc_offset = stc_attr->stc_offset;
+			fixup_stc_attr->vport.esw_owner_vhca_id = ctx->caps->vhca_id;
+			fixup_stc_attr->vport.vport_num = ctx->caps->eswitch_manager_vport_number;
+			fixup_stc_attr->vport.eswitch_owner_vhca_id_valid =
+				ctx->caps->merged_eswitch;
+			use_fixup = true;
+		}
+		break;
+
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_VPORT:
+		if (stc_attr->vport.vport_num != MLX5_VPORT_UPLINK)
+			break;
+
+		if (fw_tbl_type == FS_FT_FDB_TX || fw_tbl_type == FS_FT_FDB_RX) {
+			/* The FW doesn't allow to go to wire in the TX/RX by JUMP_TO_VPORT */
+			fixup_stc_attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_UPLINK;
+			fixup_stc_attr->action_offset = stc_attr->action_offset;
+			fixup_stc_attr->stc_offset = stc_attr->stc_offset;
+			fixup_stc_attr->vport.vport_num = 0;
+			fixup_stc_attr->vport.esw_owner_vhca_id = stc_attr->vport.esw_owner_vhca_id;
+			fixup_stc_attr->vport.eswitch_owner_vhca_id_valid =
+				stc_attr->vport.eswitch_owner_vhca_id_valid;
+		}
+		use_fixup = true;
+		break;
+
+	default:
+		break;
+	}
+
+	return use_fixup;
+}
+
+int mlx5hws_action_alloc_single_stc(struct mlx5hws_context *ctx,
+				    struct mlx5hws_cmd_stc_modify_attr *stc_attr,
+				    u32 table_type,
+				    struct mlx5hws_pool_chunk *stc)
+__must_hold(&ctx->ctrl_lock)
+{
+	struct mlx5hws_cmd_stc_modify_attr cleanup_stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
+	struct mlx5hws_cmd_stc_modify_attr fixup_stc_attr = {0};
+	bool use_fixup;
+	u32 obj_0_id;
+	int ret;
+
+	ret = mlx5hws_pool_chunk_alloc(stc_pool, stc);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate single action STC\n");
+		return ret;
+	}
+
+	stc_attr->stc_offset = stc->offset;
+
+	/* Dynamic reparse not supported, overwrite and use default */
+	if (!mlx5hws_context_cap_dynamic_reparse(ctx))
+		stc_attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+
+	obj_0_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+
+	/* According to table/action limitation change the stc_attr */
+	use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr, &fixup_stc_attr, table_type, false);
+	ret = mlx5hws_cmd_stc_modify(ctx->mdev, obj_0_id,
+				     use_fixup ? &fixup_stc_attr : stc_attr);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to modify STC action_type %d tbl_type %d\n",
+			    stc_attr->action_type, table_type);
+		goto free_chunk;
+	}
+
+	/* Modify the FDB peer */
+	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
+		u32 obj_1_id;
+
+		obj_1_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+
+		use_fixup = hws_action_fixup_stc_attr(ctx, stc_attr,
+						      &fixup_stc_attr,
+						      table_type, true);
+		ret = mlx5hws_cmd_stc_modify(ctx->mdev, obj_1_id,
+					     use_fixup ? &fixup_stc_attr : stc_attr);
+		if (ret) {
+			mlx5hws_err(ctx,
+				    "Failed to modify peer STC action_type %d tbl_type %d\n",
+				    stc_attr->action_type, table_type);
+			goto clean_obj_0;
+		}
+	}
+
+	return 0;
+
+clean_obj_0:
+	cleanup_stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
+	cleanup_stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	cleanup_stc_attr.stc_offset = stc->offset;
+	mlx5hws_cmd_stc_modify(ctx->mdev, obj_0_id, &cleanup_stc_attr);
+free_chunk:
+	mlx5hws_pool_chunk_free(stc_pool, stc);
+	return ret;
+}
+
+void mlx5hws_action_free_single_stc(struct mlx5hws_context *ctx,
+				    u32 table_type,
+				    struct mlx5hws_pool_chunk *stc)
+__must_hold(&ctx->ctrl_lock)
+{
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	u32 obj_id;
+
+	/* Modify the STC not to point to an object */
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.stc_offset = stc->offset;
+	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, stc);
+	mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
+
+	if (table_type == MLX5HWS_TABLE_TYPE_FDB) {
+		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, stc);
+		mlx5hws_cmd_stc_modify(ctx->mdev, obj_id, &stc_attr);
+	}
+
+	mlx5hws_pool_chunk_free(stc_pool, stc);
+}
+
+static u32 hws_action_get_mh_stc_type(struct mlx5hws_context *ctx,
+				      __be64 pattern)
+{
+	u8 action_type = MLX5_GET(set_action_in, &pattern, action_type);
+
+	switch (action_type) {
+	case MLX5_MODIFICATION_TYPE_SET:
+		return MLX5_IFC_STC_ACTION_TYPE_SET;
+	case MLX5_MODIFICATION_TYPE_ADD:
+		return MLX5_IFC_STC_ACTION_TYPE_ADD;
+	case MLX5_MODIFICATION_TYPE_COPY:
+		return MLX5_IFC_STC_ACTION_TYPE_COPY;
+	case MLX5_MODIFICATION_TYPE_ADD_FIELD:
+		return MLX5_IFC_STC_ACTION_TYPE_ADD_FIELD;
+	default:
+		mlx5hws_err(ctx, "Unsupported action type: 0x%x\n", action_type);
+		return MLX5_IFC_STC_ACTION_TYPE_NOP;
+	}
+}
+
+static void hws_action_fill_stc_attr(struct mlx5hws_action *action,
+				     u32 obj_id,
+				     struct mlx5hws_cmd_stc_modify_attr *attr)
+{
+	attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+
+	switch (action->type) {
+	case MLX5HWS_ACTION_TYP_TAG:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_TAG;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+		break;
+	case MLX5HWS_ACTION_TYP_DROP:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_DROP;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+		break;
+	case MLX5HWS_ACTION_TYP_MISS:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_ALLOW;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+		break;
+	case MLX5HWS_ACTION_TYP_CTR:
+		attr->id = obj_id;
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_COUNTER;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW0;
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
+	case MLX5HWS_ACTION_TYP_MODIFY_HDR:
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW6;
+		attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+		if (action->modify_header.require_reparse)
+			attr->reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+
+		if (action->modify_header.num_of_actions == 1) {
+			attr->modify_action.data = action->modify_header.single_action;
+			attr->action_type = hws_action_get_mh_stc_type(action->ctx,
+								       attr->modify_action.data);
+
+			if (attr->action_type == MLX5_IFC_STC_ACTION_TYPE_ADD ||
+			    attr->action_type == MLX5_IFC_STC_ACTION_TYPE_SET)
+				MLX5_SET(set_action_in, &attr->modify_action.data, data, 0);
+		} else {
+			attr->action_type = MLX5_IFC_STC_ACTION_TYPE_ACC_MODIFY_LIST;
+			attr->modify_header.arg_id = action->modify_header.arg_id;
+			attr->modify_header.pattern_id = action->modify_header.pat_id;
+		}
+		break;
+	case MLX5HWS_ACTION_TYP_TBL:
+	case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+		attr->dest_table_id = obj_id;
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_HEADER_REMOVE;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+		attr->reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+		attr->remove_header.decap = 1;
+		attr->remove_header.start_anchor = MLX5_HEADER_ANCHOR_PACKET_START;
+		attr->remove_header.end_anchor = MLX5_HEADER_ANCHOR_INNER_MAC;
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2:
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3:
+	case MLX5HWS_ACTION_TYP_INSERT_HEADER:
+		attr->reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+		if (!action->reformat.require_reparse)
+			attr->reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_HEADER_INSERT;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW6;
+		attr->insert_header.encap = action->reformat.encap;
+		attr->insert_header.insert_anchor = action->reformat.anchor;
+		attr->insert_header.arg_id = action->reformat.arg_id;
+		attr->insert_header.header_size = action->reformat.header_size;
+		attr->insert_header.insert_offset = action->reformat.offset;
+		break;
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW6;
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_ASO;
+		attr->aso.aso_type = ASO_OPC_MOD_POLICER;
+		attr->aso.devx_obj_id = obj_id;
+		attr->aso.return_reg_id = action->aso.return_reg_id;
+		break;
+	case MLX5HWS_ACTION_TYP_VPORT:
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_VPORT;
+		attr->vport.vport_num = action->vport.vport_num;
+		attr->vport.esw_owner_vhca_id =	action->vport.esw_owner_vhca_id;
+		attr->vport.eswitch_owner_vhca_id_valid = action->vport.esw_owner_vhca_id_valid;
+		break;
+	case MLX5HWS_ACTION_TYP_POP_VLAN:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_REMOVE_WORDS;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+		attr->reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+		attr->remove_words.start_anchor = MLX5_HEADER_ANCHOR_FIRST_VLAN_START;
+		attr->remove_words.num_of_words = MLX5HWS_ACTION_HDR_LEN_L2_VLAN / 2;
+		break;
+	case MLX5HWS_ACTION_TYP_PUSH_VLAN:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_HEADER_INSERT;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW6;
+		attr->reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+		attr->insert_header.encap = 0;
+		attr->insert_header.is_inline = 1;
+		attr->insert_header.insert_anchor = MLX5_HEADER_ANCHOR_PACKET_START;
+		attr->insert_header.insert_offset = MLX5HWS_ACTION_HDR_LEN_L2_MACS;
+		attr->insert_header.header_size = MLX5HWS_ACTION_HDR_LEN_L2_VLAN;
+		break;
+	case MLX5HWS_ACTION_TYP_REMOVE_HEADER:
+		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_REMOVE_WORDS;
+		attr->remove_header.decap = 0; /* the mode we support decap is 0 */
+		attr->remove_words.start_anchor = action->remove_header.anchor;
+		/* the size is in already in words */
+		attr->remove_words.num_of_words = action->remove_header.size;
+		attr->action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+		attr->reparse_mode = MLX5_IFC_STC_REPARSE_ALWAYS;
+		break;
+	default:
+		mlx5hws_err(action->ctx, "Invalid action type %d\n", action->type);
+	}
+}
+
+static int
+hws_action_create_stcs(struct mlx5hws_action *action, u32 obj_id)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_context *ctx = action->ctx;
+	int ret;
+
+	hws_action_fill_stc_attr(action, obj_id, &stc_attr);
+
+	/* Block unsupported parallel obj modify over the same base */
+	mutex_lock(&ctx->ctrl_lock);
+
+	/* Allocate STC for FDB */
+	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB) {
+		ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
+						      MLX5HWS_TABLE_TYPE_FDB,
+						      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+		if (ret)
+			goto out_err;
+	}
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return 0;
+
+out_err:
+	mutex_unlock(&ctx->ctrl_lock);
+	return ret;
+}
+
+static void
+hws_action_destroy_stcs(struct mlx5hws_action *action)
+{
+	struct mlx5hws_context *ctx = action->ctx;
+
+	/* Block unsupported parallel obj modify over the same base */
+	mutex_lock(&ctx->ctrl_lock);
+
+	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB)
+		mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
+					       &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+
+	mutex_unlock(&ctx->ctrl_lock);
+}
+
+static bool hws_action_is_flag_hws_fdb(u32 flags)
+{
+	return flags & MLX5HWS_ACTION_FLAG_HWS_FDB;
+}
+
+static bool
+hws_action_validate_hws_action(struct mlx5hws_context *ctx, u32 flags)
+{
+	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT)) {
+		mlx5hws_err(ctx, "Cannot create HWS action since HWS is not supported\n");
+		return false;
+	}
+
+	if ((flags & MLX5HWS_ACTION_FLAG_HWS_FDB) && !ctx->caps->eswitch_manager) {
+		mlx5hws_err(ctx, "Cannot create HWS action for FDB for non-eswitch-manager\n");
+		return false;
+	}
+
+	return true;
+}
+
+static struct mlx5hws_action *
+hws_action_create_generic_bulk(struct mlx5hws_context *ctx,
+			       u32 flags,
+			       enum mlx5hws_action_type action_type,
+			       u8 bulk_sz)
+{
+	struct mlx5hws_action *action;
+	int i;
+
+	if (!hws_action_is_flag_hws_fdb(flags)) {
+		mlx5hws_err(ctx,
+			    "Action (type: %d) flags must specify only HWS FDB\n", action_type);
+		return NULL;
+	}
+
+	if (!hws_action_validate_hws_action(ctx, flags))
+		return NULL;
+
+	action = kcalloc(bulk_sz, sizeof(*action), GFP_KERNEL);
+	if (!action)
+		return NULL;
+
+	for (i = 0; i < bulk_sz; i++) {
+		action[i].ctx = ctx;
+		action[i].flags = flags;
+		action[i].type = action_type;
+	}
+
+	return action;
+}
+
+static struct mlx5hws_action *
+hws_action_create_generic(struct mlx5hws_context *ctx,
+			  u32 flags,
+			  enum mlx5hws_action_type action_type)
+{
+	return hws_action_create_generic_bulk(ctx, flags, action_type, 1);
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_dest_table_num(struct mlx5hws_context *ctx,
+				     u32 table_id,
+				     u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_TBL);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_create_stcs(action, table_id);
+	if (ret)
+		goto free_action;
+
+	action->dest_obj.obj_id = table_id;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_dest_table(struct mlx5hws_context *ctx,
+				 struct mlx5hws_table *tbl,
+				 u32 flags)
+{
+	return mlx5hws_action_create_dest_table_num(ctx, tbl->ft_id, flags);
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_dest_drop(struct mlx5hws_context *ctx, u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_DROP);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_create_stcs(action, 0);
+	if (ret)
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_default_miss(struct mlx5hws_context *ctx, u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_MISS);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_create_stcs(action, 0);
+	if (ret)
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_tag(struct mlx5hws_context *ctx, u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_TAG);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_create_stcs(action, 0);
+	if (ret)
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+static struct mlx5hws_action *
+hws_action_create_aso(struct mlx5hws_context *ctx,
+		      enum mlx5hws_action_type action_type,
+		      u32 obj_id,
+		      u8 return_reg_id,
+		      u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, action_type);
+	if (!action)
+		return NULL;
+
+	action->aso.obj_id = obj_id;
+	action->aso.return_reg_id = return_reg_id;
+
+	ret = hws_action_create_stcs(action, obj_id);
+	if (ret)
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_aso_meter(struct mlx5hws_context *ctx,
+				u32 obj_id,
+				u8 return_reg_id,
+				u32 flags)
+{
+	return hws_action_create_aso(ctx, MLX5HWS_ACTION_TYP_ASO_METER,
+				     obj_id, return_reg_id, flags);
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_counter(struct mlx5hws_context *ctx,
+			      u32 obj_id,
+			      u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_CTR);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_create_stcs(action, obj_id);
+	if (ret)
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_dest_vport(struct mlx5hws_context *ctx,
+				 u16 vport_num,
+				 bool vhca_id_valid,
+				 u16 vhca_id,
+				 u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	if (!(flags & MLX5HWS_ACTION_FLAG_HWS_FDB)) {
+		mlx5hws_err(ctx, "Vport action is supported for FDB only\n");
+		return NULL;
+	}
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_VPORT);
+	if (!action)
+		return NULL;
+
+	if (!ctx->caps->merged_eswitch && vhca_id_valid && vhca_id != ctx->caps->vhca_id) {
+		mlx5hws_err(ctx, "Non merged eswitch cannot send to other vhca\n");
+		goto free_action;
+	}
+
+	action->vport.vport_num = vport_num;
+	action->vport.esw_owner_vhca_id_valid = vhca_id_valid;
+
+	if (vhca_id_valid)
+		action->vport.esw_owner_vhca_id = vhca_id;
+
+	ret = hws_action_create_stcs(action, 0);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed creating stc for vport %d\n", vport_num);
+		goto free_action;
+	}
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_push_vlan(struct mlx5hws_context *ctx, u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_PUSH_VLAN);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_create_stcs(action, 0);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed creating stc for push vlan\n");
+		goto free_action;
+	}
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_pop_vlan(struct mlx5hws_context *ctx, u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_POP_VLAN);
+	if (!action)
+		return NULL;
+
+	ret = hws_action_get_shared_stc(action, MLX5HWS_CONTEXT_SHARED_STC_DOUBLE_POP);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create remove stc for reformat\n");
+		goto free_action;
+	}
+
+	ret = hws_action_create_stcs(action, 0);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed creating stc for pop vlan\n");
+		goto free_shared;
+	}
+
+	return action;
+
+free_shared:
+	hws_action_put_shared_stc(action, MLX5HWS_CONTEXT_SHARED_STC_DOUBLE_POP);
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+static int
+hws_action_handle_insert_with_ptr(struct mlx5hws_action *action,
+				  u8 num_of_hdrs,
+				  struct mlx5hws_action_reformat_header *hdrs,
+				  u32 log_bulk_sz)
+{
+	size_t max_sz = 0;
+	u32 arg_id;
+	int ret, i;
+
+	for (i = 0; i < num_of_hdrs; i++) {
+		if (hdrs[i].sz % W_SIZE != 0) {
+			mlx5hws_err(action->ctx,
+				    "Header data size should be in WORD granularity\n");
+			return -EINVAL;
+		}
+		max_sz = max(hdrs[i].sz, max_sz);
+	}
+
+	/* Allocate single shared arg object for all headers */
+	ret = mlx5hws_arg_create(action->ctx,
+				 hdrs->data,
+				 max_sz,
+				 log_bulk_sz,
+				 action->flags & MLX5HWS_ACTION_FLAG_SHARED,
+				 &arg_id);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_of_hdrs; i++) {
+		action[i].reformat.arg_id = arg_id;
+		action[i].reformat.header_size = hdrs[i].sz;
+		action[i].reformat.num_of_hdrs = num_of_hdrs;
+		action[i].reformat.max_hdr_sz = max_sz;
+		action[i].reformat.require_reparse = true;
+
+		if (action[i].type == MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2 ||
+		    action[i].type == MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3) {
+			action[i].reformat.anchor = MLX5_HEADER_ANCHOR_PACKET_START;
+			action[i].reformat.offset = 0;
+			action[i].reformat.encap = 1;
+		}
+
+		ret = hws_action_create_stcs(&action[i], 0);
+		if (ret) {
+			mlx5hws_err(action->ctx, "Failed to create stc for reformat\n");
+			goto free_stc;
+		}
+	}
+
+	return 0;
+
+free_stc:
+	while (i--)
+		hws_action_destroy_stcs(&action[i]);
+
+	mlx5hws_arg_destroy(action->ctx, arg_id);
+	return ret;
+}
+
+static int
+hws_action_handle_l2_to_tunnel_l3(struct mlx5hws_action *action,
+				  u8 num_of_hdrs,
+				  struct mlx5hws_action_reformat_header *hdrs,
+				  u32 log_bulk_sz)
+{
+	int ret;
+
+	/* The action is remove-l2-header + insert-l3-header */
+	ret = hws_action_get_shared_stc(action, MLX5HWS_CONTEXT_SHARED_STC_DECAP_L3);
+	if (ret) {
+		mlx5hws_err(action->ctx, "Failed to create remove stc for reformat\n");
+		return ret;
+	}
+
+	/* Reuse the insert with pointer for the L2L3 header */
+	ret = hws_action_handle_insert_with_ptr(action,
+						num_of_hdrs,
+						hdrs,
+						log_bulk_sz);
+	if (ret)
+		goto put_shared_stc;
+
+	return 0;
+
+put_shared_stc:
+	hws_action_put_shared_stc(action, MLX5HWS_CONTEXT_SHARED_STC_DECAP_L3);
+	return ret;
+}
+
+static void hws_action_prepare_decap_l3_actions(size_t data_sz,
+						u8 *mh_data,
+						int *num_of_actions)
+{
+	int actions;
+	u32 i;
+
+	/* Remove L2L3 outer headers */
+	MLX5_SET(stc_ste_param_remove, mh_data, action_type,
+		 MLX5_MODIFICATION_TYPE_REMOVE);
+	MLX5_SET(stc_ste_param_remove, mh_data, decap, 0x1);
+	MLX5_SET(stc_ste_param_remove, mh_data, remove_start_anchor,
+		 MLX5_HEADER_ANCHOR_PACKET_START);
+	MLX5_SET(stc_ste_param_remove, mh_data, remove_end_anchor,
+		 MLX5_HEADER_ANCHOR_INNER_IPV6_IPV4);
+	mh_data += MLX5HWS_ACTION_DOUBLE_SIZE; /* Assume every action is 2 dw */
+	actions = 1;
+
+	/* Add the new header using inline action 4Byte at a time, the header
+	 * is added in reversed order to the beginning of the packet to avoid
+	 * incorrect parsing by the HW. Since header is 14B or 18B an extra
+	 * two bytes are padded and later removed.
+	 */
+	for (i = 0; i < data_sz / MLX5HWS_ACTION_INLINE_DATA_SIZE + 1; i++) {
+		MLX5_SET(stc_ste_param_insert, mh_data, action_type,
+			 MLX5_MODIFICATION_TYPE_INSERT);
+		MLX5_SET(stc_ste_param_insert, mh_data, inline_data, 0x1);
+		MLX5_SET(stc_ste_param_insert, mh_data, insert_anchor,
+			 MLX5_HEADER_ANCHOR_PACKET_START);
+		MLX5_SET(stc_ste_param_insert, mh_data, insert_size, 2);
+		mh_data += MLX5HWS_ACTION_DOUBLE_SIZE;
+		actions++;
+	}
+
+	/* Remove first 2 extra bytes */
+	MLX5_SET(stc_ste_param_remove_words, mh_data, action_type,
+		 MLX5_MODIFICATION_TYPE_REMOVE_WORDS);
+	MLX5_SET(stc_ste_param_remove_words, mh_data, remove_start_anchor,
+		 MLX5_HEADER_ANCHOR_PACKET_START);
+	/* The hardware expects here size in words (2 bytes) */
+	MLX5_SET(stc_ste_param_remove_words, mh_data, remove_size, 1);
+	actions++;
+
+	*num_of_actions = actions;
+}
+
+static int
+hws_action_handle_tunnel_l3_to_l2(struct mlx5hws_action *action,
+				  u8 num_of_hdrs,
+				  struct mlx5hws_action_reformat_header *hdrs,
+				  u32 log_bulk_sz)
+{
+	u8 mh_data[MLX5HWS_ACTION_REFORMAT_DATA_SIZE] = {0};
+	struct mlx5hws_context *ctx = action->ctx;
+	u32 arg_id, pat_id;
+	int num_of_actions;
+	int mh_data_size;
+	int ret, i;
+
+	for (i = 0; i < num_of_hdrs; i++) {
+		if (hdrs[i].sz != MLX5HWS_ACTION_HDR_LEN_L2 &&
+		    hdrs[i].sz != MLX5HWS_ACTION_HDR_LEN_L2_W_VLAN) {
+			mlx5hws_err(ctx, "Data size is not supported for decap-l3\n");
+			return -EINVAL;
+		}
+	}
+
+	/* Create a full modify header action list in case shared */
+	hws_action_prepare_decap_l3_actions(hdrs->sz, mh_data, &num_of_actions);
+	if (action->flags & MLX5HWS_ACTION_FLAG_SHARED)
+		mlx5hws_action_prepare_decap_l3_data(hdrs->data, mh_data, num_of_actions);
+
+	/* All DecapL3 cases require the same max arg size */
+	ret = mlx5hws_arg_create_modify_header_arg(ctx,
+						   (__be64 *)mh_data,
+						   num_of_actions,
+						   log_bulk_sz,
+						   action->flags & MLX5HWS_ACTION_FLAG_SHARED,
+						   &arg_id);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_of_hdrs; i++) {
+		memset(mh_data, 0, MLX5HWS_ACTION_REFORMAT_DATA_SIZE);
+		hws_action_prepare_decap_l3_actions(hdrs[i].sz, mh_data, &num_of_actions);
+		mh_data_size = num_of_actions * MLX5HWS_MODIFY_ACTION_SIZE;
+
+		ret = mlx5hws_pat_get_pattern(ctx, (__be64 *)mh_data, mh_data_size, &pat_id);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to allocate pattern for DecapL3\n");
+			goto free_stc_and_pat;
+		}
+
+		action[i].modify_header.max_num_of_actions = num_of_actions;
+		action[i].modify_header.num_of_actions = num_of_actions;
+		action[i].modify_header.num_of_patterns = num_of_hdrs;
+		action[i].modify_header.arg_id = arg_id;
+		action[i].modify_header.pat_id = pat_id;
+		action[i].modify_header.require_reparse =
+			mlx5hws_pat_require_reparse((__be64 *)mh_data, num_of_actions);
+
+		ret = hws_action_create_stcs(&action[i], 0);
+		if (ret) {
+			mlx5hws_pat_put_pattern(ctx, pat_id);
+			goto free_stc_and_pat;
+		}
+	}
+
+	return 0;
+
+free_stc_and_pat:
+	while (i--) {
+		hws_action_destroy_stcs(&action[i]);
+		mlx5hws_pat_put_pattern(ctx, action[i].modify_header.pat_id);
+	}
+
+	mlx5hws_arg_destroy(action->ctx, arg_id);
+	return ret;
+}
+
+static int
+hws_action_create_reformat_hws(struct mlx5hws_action *action,
+			       u8 num_of_hdrs,
+			       struct mlx5hws_action_reformat_header *hdrs,
+			       u32 bulk_size)
+{
+	int ret;
+
+	switch (action->type) {
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2:
+		ret = hws_action_create_stcs(action, 0);
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2:
+		ret = hws_action_handle_insert_with_ptr(action, num_of_hdrs, hdrs, bulk_size);
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3:
+		ret = hws_action_handle_l2_to_tunnel_l3(action, num_of_hdrs, hdrs, bulk_size);
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
+		ret = hws_action_handle_tunnel_l3_to_l2(action, num_of_hdrs, hdrs, bulk_size);
+		break;
+	default:
+		mlx5hws_err(action->ctx, "Invalid HWS reformat action type\n");
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_reformat(struct mlx5hws_context *ctx,
+			       enum mlx5hws_action_type reformat_type,
+			       u8 num_of_hdrs,
+			       struct mlx5hws_action_reformat_header *hdrs,
+			       u32 log_bulk_size,
+			       u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	if (!num_of_hdrs) {
+		mlx5hws_err(ctx, "Reformat num_of_hdrs cannot be zero\n");
+		return NULL;
+	}
+
+	action = hws_action_create_generic_bulk(ctx, flags, reformat_type, num_of_hdrs);
+	if (!action)
+		return NULL;
+
+	if ((flags & MLX5HWS_ACTION_FLAG_SHARED) && (log_bulk_size || num_of_hdrs > 1)) {
+		mlx5hws_err(ctx, "Reformat flags don't fit HWS (flags: 0x%x)\n", flags);
+		goto free_action;
+	}
+
+	ret = hws_action_create_reformat_hws(action, num_of_hdrs, hdrs, log_bulk_size);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create HWS reformat action\n");
+		goto free_action;
+	}
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+static int
+hws_action_create_modify_header_hws(struct mlx5hws_action *action,
+				    u8 num_of_patterns,
+				    struct mlx5hws_action_mh_pattern *pattern,
+				    u32 log_bulk_size)
+{
+	struct mlx5hws_context *ctx = action->ctx;
+	u16 num_actions, max_mh_actions = 0;
+	int i, ret, size_in_bytes;
+	u32 pat_id, arg_id = 0;
+	__be64 *new_pattern;
+	size_t pat_max_sz;
+
+	pat_max_sz = MLX5HWS_ARG_CHUNK_SIZE_MAX * MLX5HWS_ARG_DATA_SIZE;
+	size_in_bytes = pat_max_sz * sizeof(__be64);
+	new_pattern = kcalloc(num_of_patterns, size_in_bytes, GFP_KERNEL);
+	if (!new_pattern)
+		return -ENOMEM;
+
+	/* Calculate maximum number of mh actions for shared arg allocation */
+	for (i = 0; i < num_of_patterns; i++) {
+		size_t new_num_actions;
+		size_t cur_num_actions;
+		u32 nope_location;
+
+		cur_num_actions = pattern[i].sz / MLX5HWS_MODIFY_ACTION_SIZE;
+
+		mlx5hws_pat_calc_nope(pattern[i].data, cur_num_actions,
+				      pat_max_sz / MLX5HWS_MODIFY_ACTION_SIZE,
+				      &new_num_actions, &nope_location,
+				      &new_pattern[i * pat_max_sz]);
+
+		action[i].modify_header.nope_locations = nope_location;
+		action[i].modify_header.num_of_actions = new_num_actions;
+
+		max_mh_actions = max(max_mh_actions, new_num_actions);
+	}
+
+	if (mlx5hws_arg_get_arg_log_size(max_mh_actions) >= MLX5HWS_ARG_CHUNK_SIZE_MAX) {
+		mlx5hws_err(ctx, "Num of actions (%d) bigger than allowed\n",
+			    max_mh_actions);
+		ret = -EINVAL;
+		goto free_new_pat;
+	}
+
+	/* Allocate single shared arg for all patterns based on the max size */
+	if (max_mh_actions > 1) {
+		ret = mlx5hws_arg_create_modify_header_arg(ctx,
+							   pattern->data,
+							   max_mh_actions,
+							   log_bulk_size,
+							   action->flags &
+							   MLX5HWS_ACTION_FLAG_SHARED,
+							   &arg_id);
+		if (ret)
+			goto free_new_pat;
+	}
+
+	for (i = 0; i < num_of_patterns; i++) {
+		if (!mlx5hws_pat_verify_actions(ctx, pattern[i].data, pattern[i].sz)) {
+			mlx5hws_err(ctx, "Fail to verify pattern modify actions\n");
+			ret = -EINVAL;
+			goto free_stc_and_pat;
+		}
+		num_actions = pattern[i].sz / MLX5HWS_MODIFY_ACTION_SIZE;
+		action[i].modify_header.num_of_patterns = num_of_patterns;
+		action[i].modify_header.max_num_of_actions = max_mh_actions;
+
+		action[i].modify_header.require_reparse =
+			mlx5hws_pat_require_reparse(pattern[i].data, num_actions);
+
+		if (num_actions == 1) {
+			pat_id = 0;
+			/* Optimize single modify action to be used inline */
+			action[i].modify_header.single_action = pattern[i].data[0];
+			action[i].modify_header.single_action_type =
+				MLX5_GET(set_action_in, pattern[i].data, action_type);
+		} else {
+			/* Multiple modify actions require a pattern */
+			if (unlikely(action[i].modify_header.nope_locations)) {
+				size_t pattern_sz;
+
+				pattern_sz = action[i].modify_header.num_of_actions *
+					     MLX5HWS_MODIFY_ACTION_SIZE;
+				ret =
+				mlx5hws_pat_get_pattern(ctx,
+							&new_pattern[i * pat_max_sz],
+							pattern_sz, &pat_id);
+			} else {
+				ret = mlx5hws_pat_get_pattern(ctx,
+							      pattern[i].data,
+							      pattern[i].sz,
+							      &pat_id);
+			}
+			if (ret) {
+				mlx5hws_err(ctx,
+					    "Failed to allocate pattern for modify header\n");
+				goto free_stc_and_pat;
+			}
+
+			action[i].modify_header.arg_id = arg_id;
+			action[i].modify_header.pat_id = pat_id;
+		}
+		/* Allocate STC for each action representing a header */
+		ret = hws_action_create_stcs(&action[i], 0);
+		if (ret) {
+			if (pat_id)
+				mlx5hws_pat_put_pattern(ctx, pat_id);
+			goto free_stc_and_pat;
+		}
+	}
+
+	kfree(new_pattern);
+	return 0;
+
+free_stc_and_pat:
+	while (i--) {
+		hws_action_destroy_stcs(&action[i]);
+		if (action[i].modify_header.pat_id)
+			mlx5hws_pat_put_pattern(ctx, action[i].modify_header.pat_id);
+	}
+
+	if (arg_id)
+		mlx5hws_arg_destroy(ctx, arg_id);
+free_new_pat:
+	kfree(new_pattern);
+	return ret;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_modify_header(struct mlx5hws_context *ctx,
+				    u8 num_of_patterns,
+				    struct mlx5hws_action_mh_pattern *patterns,
+				    u32 log_bulk_size,
+				    u32 flags)
+{
+	struct mlx5hws_action *action;
+	int ret;
+
+	if (!num_of_patterns) {
+		mlx5hws_err(ctx, "Invalid number of patterns\n");
+		return NULL;
+	}
+	action = hws_action_create_generic_bulk(ctx, flags,
+						MLX5HWS_ACTION_TYP_MODIFY_HDR,
+						num_of_patterns);
+	if (!action)
+		return NULL;
+
+	if ((flags & MLX5HWS_ACTION_FLAG_SHARED) && (log_bulk_size || num_of_patterns > 1)) {
+		mlx5hws_err(ctx, "Action cannot be shared with requested pattern or size\n");
+		goto free_action;
+	}
+
+	ret = hws_action_create_modify_header_hws(action,
+						  num_of_patterns,
+						  patterns,
+						  log_bulk_size);
+	if (ret)
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
+				 size_t num_dest,
+				 struct mlx5hws_action_dest_attr *dests,
+				 bool ignore_flow_level,
+				 u32 flow_source,
+				 u32 flags)
+{
+	struct mlx5hws_cmd_set_fte_dest *dest_list = NULL;
+	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
+	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
+	struct mlx5hws_cmd_forward_tbl *fw_island;
+	struct mlx5hws_action *action;
+	u32 i /*, packet_reformat_id*/;
+	int ret;
+
+	if (num_dest <= 1) {
+		mlx5hws_err(ctx, "Action must have multiple dests\n");
+		return NULL;
+	}
+
+	if (flags == (MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED)) {
+		ft_attr.type = FS_FT_FDB;
+		ft_attr.level = ctx->caps->fdb_ft.max_level - 1;
+	} else {
+		mlx5hws_err(ctx, "Action flags not supported\n");
+		return NULL;
+	}
+
+	dest_list = kcalloc(num_dest, sizeof(*dest_list), GFP_KERNEL);
+	if (!dest_list)
+		return NULL;
+
+	for (i = 0; i < num_dest; i++) {
+		enum mlx5hws_action_type action_type = dests[i].dest->type;
+		struct mlx5hws_action *reformat_action = dests[i].reformat;
+
+		switch (action_type) {
+		case MLX5HWS_ACTION_TYP_TBL:
+			dest_list[i].destination_type =
+				MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+			dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id;
+			fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+			fte_attr.ignore_flow_level = ignore_flow_level;
+			/* ToDo: In SW steering we have a handling of 'go to WIRE'
+			 * destination here by upper layer setting 'is_wire_ft' flag
+			 * if the destination is wire.
+			 * This is because uplink should be last dest in the list.
+			 */
+			break;
+		case MLX5HWS_ACTION_TYP_VPORT:
+			dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+			dest_list[i].destination_id = dests[i].dest->vport.vport_num;
+			fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+			if (ctx->caps->merged_eswitch) {
+				dest_list[i].ext_flags |=
+					MLX5HWS_CMD_EXT_DEST_ESW_OWNER_VHCA_ID;
+				dest_list[i].esw_owner_vhca_id =
+					dests[i].dest->vport.esw_owner_vhca_id;
+			}
+			break;
+		default:
+			mlx5hws_err(ctx, "Unsupported action in dest_array\n");
+			goto free_dest_list;
+		}
+
+		if (reformat_action) {
+			mlx5hws_err(ctx, "dest_array with reformat action - unsupported\n");
+			goto free_dest_list;
+		}
+	}
+
+	fte_attr.dests_num = num_dest;
+	fte_attr.dests = dest_list;
+
+	fw_island = mlx5hws_cmd_forward_tbl_create(ctx->mdev, &ft_attr, &fte_attr);
+	if (!fw_island)
+		goto free_dest_list;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_DEST_ARRAY);
+	if (!action)
+		goto destroy_fw_island;
+
+	ret = hws_action_create_stcs(action, fw_island->ft_id);
+	if (ret)
+		goto free_action;
+
+	action->dest_array.fw_island = fw_island;
+	action->dest_array.num_dest = num_dest;
+	action->dest_array.dest_list = dest_list;
+
+	return action;
+
+free_action:
+	kfree(action);
+destroy_fw_island:
+	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, fw_island);
+free_dest_list:
+	for (i = 0; i < num_dest; i++) {
+		if (dest_list[i].ext_reformat_id)
+			mlx5hws_cmd_packet_reformat_destroy(ctx->mdev,
+							    dest_list[i].ext_reformat_id);
+	}
+	kfree(dest_list);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_insert_header(struct mlx5hws_context *ctx,
+				    u8 num_of_hdrs,
+				    struct mlx5hws_action_insert_header *hdrs,
+				    u32 log_bulk_size,
+				    u32 flags)
+{
+	struct mlx5hws_action_reformat_header *reformat_hdrs;
+	struct mlx5hws_action *action;
+	int ret;
+	int i;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_INSERT_HEADER);
+	if (!action)
+		return NULL;
+
+	reformat_hdrs = kcalloc(num_of_hdrs, sizeof(*reformat_hdrs), GFP_KERNEL);
+	if (!reformat_hdrs)
+		goto free_action;
+
+	for (i = 0; i < num_of_hdrs; i++) {
+		if (hdrs[i].offset % W_SIZE != 0) {
+			mlx5hws_err(ctx, "Header offset should be in WORD granularity\n");
+			goto free_reformat_hdrs;
+		}
+
+		action[i].reformat.anchor = hdrs[i].anchor;
+		action[i].reformat.encap = hdrs[i].encap;
+		action[i].reformat.offset = hdrs[i].offset;
+
+		reformat_hdrs[i].sz = hdrs[i].hdr.sz;
+		reformat_hdrs[i].data = hdrs[i].hdr.data;
+	}
+
+	ret = hws_action_handle_insert_with_ptr(action, num_of_hdrs,
+						reformat_hdrs, log_bulk_size);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create HWS reformat action\n");
+		goto free_reformat_hdrs;
+	}
+
+	kfree(reformat_hdrs);
+
+	return action;
+
+free_reformat_hdrs:
+	kfree(reformat_hdrs);
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_remove_header(struct mlx5hws_context *ctx,
+				    struct mlx5hws_action_remove_header_attr *attr,
+				    u32 flags)
+{
+	struct mlx5hws_action *action;
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_REMOVE_HEADER);
+	if (!action)
+		return NULL;
+
+	/* support only remove anchor with size */
+	if (attr->size % W_SIZE != 0) {
+		mlx5hws_err(ctx,
+			    "Invalid size, HW supports header remove in WORD granularity\n");
+		goto free_action;
+	}
+
+	if (attr->size > MLX5HWS_ACTION_REMOVE_HEADER_MAX_SIZE) {
+		mlx5hws_err(ctx, "Header removal size limited to %u bytes\n",
+			    MLX5HWS_ACTION_REMOVE_HEADER_MAX_SIZE);
+		goto free_action;
+	}
+
+	action->remove_header.anchor = attr->anchor;
+	action->remove_header.size = attr->size / W_SIZE;
+
+	if (hws_action_create_stcs(action, 0))
+		goto free_action;
+
+	return action;
+
+free_action:
+	kfree(action);
+	return NULL;
+}
+
+static struct mlx5hws_definer *
+hws_action_create_dest_match_range_definer(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_definer *definer;
+	__be32 *tag;
+	int ret;
+
+	definer = kzalloc(sizeof(*definer), GFP_KERNEL);
+	if (!definer)
+		return NULL;
+
+	definer->dw_selector[0] = MLX5_IFC_DEFINER_FORMAT_OFFSET_OUTER_ETH_PKT_LEN / 4;
+	/* Set DW0 tag mask */
+	tag = (__force __be32 *)definer->mask.jumbo;
+	tag[MLX5HWS_RULE_JUMBO_MATCH_TAG_OFFSET_DW0] = htonl(0xffffUL << 16);
+
+	mutex_lock(&ctx->ctrl_lock);
+
+	ret = mlx5hws_definer_get_obj(ctx, definer);
+	if (ret < 0) {
+		mutex_unlock(&ctx->ctrl_lock);
+		kfree(definer);
+		return NULL;
+	}
+
+	mutex_unlock(&ctx->ctrl_lock);
+	definer->obj_id = ret;
+
+	return definer;
+}
+
+static struct mlx5hws_matcher_action_ste *
+hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
+					 struct mlx5hws_definer *definer,
+					 u32 miss_ft_id)
+{
+	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
+	struct mlx5hws_action_default_stc *default_stc;
+	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_pool_attr pool_attr = {0};
+	struct mlx5hws_pool *ste_pool, *stc_pool;
+	struct mlx5hws_pool_chunk *ste;
+	u32 *rtc_0_id, *rtc_1_id;
+	u32 obj_id;
+	int ret;
+
+	/* Check if STE range is supported */
+	if (!IS_BIT_SET(ctx->caps->supp_ste_format_gen_wqe, MLX5_IFC_RTC_STE_FORMAT_RANGE)) {
+		mlx5hws_err(ctx, "Range STE format not supported\n");
+		return NULL;
+	}
+
+	table_ste = kzalloc(sizeof(*table_ste), GFP_KERNEL);
+	if (!table_ste)
+		return NULL;
+
+	mutex_lock(&ctx->ctrl_lock);
+
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
+	pool_attr.alloc_log_sz = 1;
+	table_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!table_ste->pool) {
+		mlx5hws_err(ctx, "Failed to allocate memory ste pool\n");
+		goto free_ste;
+	}
+
+	/* Allocate RTC */
+	rtc_0_id = &table_ste->rtc_0_id;
+	rtc_1_id = &table_ste->rtc_1_id;
+	ste_pool = table_ste->pool;
+	ste = &table_ste->ste;
+	ste->order = 1;
+
+	rtc_attr.log_size = 0;
+	rtc_attr.log_depth = 0;
+	rtc_attr.miss_ft_id = miss_ft_id;
+	rtc_attr.num_hash_definer = 1;
+	rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
+	rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
+	rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
+	rtc_attr.fw_gen_wqe = true;
+	rtc_attr.is_scnd_range = true;
+
+	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+
+	rtc_attr.pd = ctx->pd_num;
+	rtc_attr.ste_base = obj_id;
+	rtc_attr.ste_offset = ste->offset;
+	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
+	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, false);
+
+	/* STC is a single resource (obj_id), use any STC for the ID */
+	stc_pool = ctx->stc_pool[MLX5HWS_TABLE_TYPE_FDB];
+	default_stc = ctx->common_res[MLX5HWS_TABLE_TYPE_FDB].default_stc;
+	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	rtc_attr.stc_base = obj_id;
+
+	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create RTC");
+		goto pool_destroy;
+	}
+
+	/* Create mirror RTC */
+	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+	rtc_attr.ste_base = obj_id;
+	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, true);
+
+	obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+	rtc_attr.stc_base = obj_id;
+
+	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create mirror RTC");
+		goto destroy_rtc_0;
+	}
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return table_ste;
+
+destroy_rtc_0:
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, *rtc_0_id);
+pool_destroy:
+	mlx5hws_pool_destroy(table_ste->pool);
+free_ste:
+	mutex_unlock(&ctx->ctrl_lock);
+	kfree(table_ste);
+	return NULL;
+}
+
+static void
+hws_action_destroy_dest_match_range_table(struct mlx5hws_context *ctx,
+					  struct mlx5hws_matcher_action_ste *table_ste)
+{
+	mutex_lock(&ctx->ctrl_lock);
+
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, table_ste->rtc_1_id);
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, table_ste->rtc_0_id);
+	mlx5hws_pool_destroy(table_ste->pool);
+	kfree(table_ste);
+
+	mutex_unlock(&ctx->ctrl_lock);
+}
+
+static int
+hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
+					      struct mlx5hws_matcher_action_ste *table_ste,
+					      struct mlx5hws_action *hit_ft_action,
+					      struct mlx5hws_definer *range_definer,
+					      u32 min, u32 max)
+{
+	struct mlx5hws_wqe_gta_data_seg_ste match_wqe_data = {0};
+	struct mlx5hws_wqe_gta_data_seg_ste range_wqe_data = {0};
+	struct mlx5hws_wqe_gta_ctrl_seg wqe_ctrl = {0};
+	u32 no_use, used_rtc_0_id, used_rtc_1_id, ret;
+	struct mlx5hws_context_common_res *common_res;
+	struct mlx5hws_send_ste_attr ste_attr = {0};
+	struct mlx5hws_send_engine *queue;
+	__be32 *wqe_data_arr;
+
+	mutex_lock(&ctx->ctrl_lock);
+
+	/* Get the control queue */
+	queue = &ctx->send_queue[ctx->queues - 1];
+	if (unlikely(mlx5hws_send_engine_err(queue))) {
+		ret = -EIO;
+		goto error;
+	}
+
+	/* Init default send STE attributes */
+	ste_attr.gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE;
+	ste_attr.send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	ste_attr.send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	ste_attr.send_attr.len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+	ste_attr.send_attr.user_data = &no_use;
+	ste_attr.send_attr.rule = NULL;
+	ste_attr.send_attr.fence = 1;
+	ste_attr.send_attr.notify_hw = true;
+	ste_attr.rtc_0 = table_ste->rtc_0_id;
+	ste_attr.rtc_1 = table_ste->rtc_1_id;
+	ste_attr.used_id_rtc_0 = &used_rtc_0_id;
+	ste_attr.used_id_rtc_1 = &used_rtc_1_id;
+
+	common_res = &ctx->common_res[MLX5HWS_TABLE_TYPE_FDB];
+
+	/* init an empty match STE which will always hit */
+	ste_attr.wqe_ctrl = &wqe_ctrl;
+	ste_attr.wqe_data = &match_wqe_data;
+	ste_attr.send_attr.match_definer_id = ctx->caps->trivial_match_definer;
+
+	/* Fill WQE control data */
+	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] =
+		htonl(common_res->default_stc->nop_ctr.offset);
+	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_DW5] =
+		htonl(common_res->default_stc->nop_dw5.offset);
+	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] =
+		htonl(common_res->default_stc->nop_dw6.offset);
+	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] =
+		htonl(common_res->default_stc->nop_dw7.offset);
+	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] |=
+		htonl(MLX5HWS_ACTION_STC_IDX_LAST_COMBO2 << 29);
+	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] =
+		htonl(hit_ft_action->stc[MLX5HWS_TABLE_TYPE_FDB].offset);
+
+	wqe_data_arr = (__force __be32 *)&range_wqe_data;
+
+	ste_attr.range_wqe_data = &range_wqe_data;
+	ste_attr.send_attr.len += MLX5HWS_WQE_SZ_GTA_DATA;
+	ste_attr.send_attr.range_definer_id = mlx5hws_definer_get_id(range_definer);
+
+	/* Fill range matching fields,
+	 * min/max_value_2 corresponds to match_dw_0 in its definer,
+	 * min_value_2 sets in DW0 in the STE and max_value_2 sets in DW1 in the STE.
+	 */
+	wqe_data_arr[MLX5HWS_MATCHER_OFFSET_TAG_DW0] = htonl(min << 16);
+	wqe_data_arr[MLX5HWS_MATCHER_OFFSET_TAG_DW1] = htonl(max << 16);
+
+	/* Send WQEs to FW */
+	mlx5hws_send_stes_fw(ctx, queue, &ste_attr);
+
+	/* Poll for completion */
+	ret = mlx5hws_send_queue_action(ctx, ctx->queues - 1,
+					MLX5HWS_SEND_QUEUE_ACTION_DRAIN_SYNC);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to drain control queue");
+		goto error;
+	}
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return 0;
+
+error:
+	mutex_unlock(&ctx->ctrl_lock);
+	return ret;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
+				       u32 field,
+				       struct mlx5_flow_table *hit_ft,
+				       struct mlx5_flow_table *miss_ft,
+				       u32 min, u32 max, u32 flags)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_matcher_action_ste *table_ste;
+	struct mlx5hws_action *hit_ft_action;
+	struct mlx5hws_definer *definer;
+	struct mlx5hws_action *action;
+	u32 miss_ft_id = miss_ft->id;
+	u32 hit_ft_id = hit_ft->id;
+	int ret;
+
+	if (field != MLX5_FLOW_DEST_RANGE_FIELD_PKT_LEN ||
+	    min > 0xffff || max > 0xffff) {
+		mlx5hws_err(ctx, "Invalid match range parameters\n");
+		return NULL;
+	}
+
+	action = hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_RANGE);
+	if (!action)
+		return NULL;
+
+	definer = hws_action_create_dest_match_range_definer(ctx);
+	if (!definer)
+		goto free_action;
+
+	table_ste = hws_action_create_dest_match_range_table(ctx, definer, miss_ft_id);
+	if (!table_ste)
+		goto destroy_definer;
+
+	hit_ft_action = mlx5hws_action_create_dest_table_num(ctx, hit_ft_id, flags);
+	if (!hit_ft_action)
+		goto destroy_table_ste;
+
+	ret = hws_action_create_dest_match_range_fill_table(ctx, table_ste,
+							    hit_ft_action,
+							    definer, min, max);
+	if (ret)
+		goto destroy_hit_ft_action;
+
+	action->range.table_ste = table_ste;
+	action->range.definer = definer;
+	action->range.hit_ft_action = hit_ft_action;
+
+	/* Allocate STC for jumps to STE */
+	mutex_lock(&ctx->ctrl_lock);
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
+	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+	stc_attr.ste_table.ste = table_ste->ste;
+	stc_attr.ste_table.ste_pool = table_ste->pool;
+	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
+
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, MLX5HWS_TABLE_TYPE_FDB,
+					      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+	if (ret)
+		goto error_unlock;
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return action;
+
+error_unlock:
+	mutex_unlock(&ctx->ctrl_lock);
+destroy_hit_ft_action:
+	mlx5hws_action_destroy(hit_ft_action);
+destroy_table_ste:
+	hws_action_destroy_dest_match_range_table(ctx, table_ste);
+destroy_definer:
+	mlx5hws_definer_free(ctx, definer);
+free_action:
+	kfree(action);
+	mlx5hws_err(ctx, "Failed to create action dest match range");
+	return NULL;
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_last(struct mlx5hws_context *ctx, u32 flags)
+{
+	return hws_action_create_generic(ctx, flags, MLX5HWS_ACTION_TYP_LAST);
+}
+
+struct mlx5hws_action *
+mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx,
+				   u32 sampler_id, u32 flags)
+{
+	mlx5hws_err(ctx, "Flow sampler action - unsupported\n");
+	return NULL;
+}
+
+static void hws_action_destroy_hws(struct mlx5hws_action *action)
+{
+	u32 ext_reformat_id;
+	bool shared_arg;
+	u32 obj_id;
+	u32 i;
+
+	switch (action->type) {
+	case MLX5HWS_ACTION_TYP_MISS:
+	case MLX5HWS_ACTION_TYP_TAG:
+	case MLX5HWS_ACTION_TYP_DROP:
+	case MLX5HWS_ACTION_TYP_CTR:
+	case MLX5HWS_ACTION_TYP_TBL:
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2:
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+	case MLX5HWS_ACTION_TYP_PUSH_VLAN:
+	case MLX5HWS_ACTION_TYP_REMOVE_HEADER:
+	case MLX5HWS_ACTION_TYP_VPORT:
+		hws_action_destroy_stcs(action);
+		break;
+	case MLX5HWS_ACTION_TYP_POP_VLAN:
+		hws_action_destroy_stcs(action);
+		hws_action_put_shared_stc(action, MLX5HWS_CONTEXT_SHARED_STC_DOUBLE_POP);
+		break;
+	case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+		hws_action_destroy_stcs(action);
+		mlx5hws_cmd_forward_tbl_destroy(action->ctx->mdev, action->dest_array.fw_island);
+		for (i = 0; i < action->dest_array.num_dest; i++) {
+			ext_reformat_id = action->dest_array.dest_list[i].ext_reformat_id;
+			if (ext_reformat_id)
+				mlx5hws_cmd_packet_reformat_destroy(action->ctx->mdev,
+								    ext_reformat_id);
+		}
+		kfree(action->dest_array.dest_list);
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
+	case MLX5HWS_ACTION_TYP_MODIFY_HDR:
+		shared_arg = false;
+		for (i = 0; i < action->modify_header.num_of_patterns; i++) {
+			hws_action_destroy_stcs(&action[i]);
+			if (action[i].modify_header.num_of_actions > 1) {
+				mlx5hws_pat_put_pattern(action[i].ctx,
+							action[i].modify_header.pat_id);
+				/* Save shared arg object to be freed after */
+				obj_id = action[i].modify_header.arg_id;
+				shared_arg = true;
+			}
+		}
+		if (shared_arg)
+			mlx5hws_arg_destroy(action->ctx, obj_id);
+		break;
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3:
+		hws_action_put_shared_stc(action, MLX5HWS_CONTEXT_SHARED_STC_DECAP_L3);
+		for (i = 0; i < action->reformat.num_of_hdrs; i++)
+			hws_action_destroy_stcs(&action[i]);
+		mlx5hws_arg_destroy(action->ctx, action->reformat.arg_id);
+		break;
+	case MLX5HWS_ACTION_TYP_INSERT_HEADER:
+	case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2:
+		for (i = 0; i < action->reformat.num_of_hdrs; i++)
+			hws_action_destroy_stcs(&action[i]);
+		mlx5hws_arg_destroy(action->ctx, action->reformat.arg_id);
+		break;
+	case MLX5HWS_ACTION_TYP_RANGE:
+		hws_action_destroy_stcs(action);
+		hws_action_destroy_dest_match_range_table(action->ctx, action->range.table_ste);
+		mlx5hws_definer_free(action->ctx, action->range.definer);
+		mlx5hws_action_destroy(action->range.hit_ft_action);
+		break;
+	case MLX5HWS_ACTION_TYP_LAST:
+		break;
+	default:
+		pr_warn("HWS: Invalid action type: %d\n", action->type);
+	}
+}
+
+int mlx5hws_action_destroy(struct mlx5hws_action *action)
+{
+	hws_action_destroy_hws(action);
+
+	kfree(action);
+	return 0;
+}
+
+int mlx5hws_action_get_default_stc(struct mlx5hws_context *ctx, u8 tbl_type)
+__must_hold(&ctx->ctrl_lock)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_action_default_stc *default_stc;
+	int ret;
+
+	if (ctx->common_res[tbl_type].default_stc) {
+		ctx->common_res[tbl_type].default_stc->refcount++;
+		return 0;
+	}
+
+	default_stc = kzalloc(sizeof(*default_stc), GFP_KERNEL);
+	if (!default_stc)
+		return -ENOMEM;
+
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_NOP;
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_DW0;
+	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
+					      &default_stc->nop_ctr);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate default counter STC\n");
+		goto free_default_stc;
+	}
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_DW5;
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
+					      &default_stc->nop_dw5);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate default NOP DW5 STC\n");
+		goto free_nop_ctr;
+	}
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_DW6;
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
+					      &default_stc->nop_dw6);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate default NOP DW6 STC\n");
+		goto free_nop_dw5;
+	}
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_DW7;
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
+					      &default_stc->nop_dw7);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate default NOP DW7 STC\n");
+		goto free_nop_dw6;
+	}
+
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_ALLOW;
+
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl_type,
+					      &default_stc->default_hit);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate default allow STC\n");
+		goto free_nop_dw7;
+	}
+
+	ctx->common_res[tbl_type].default_stc = default_stc;
+	ctx->common_res[tbl_type].default_stc->refcount++;
+
+	return 0;
+
+free_nop_dw7:
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw7);
+free_nop_dw6:
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw6);
+free_nop_dw5:
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw5);
+free_nop_ctr:
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_ctr);
+free_default_stc:
+	kfree(default_stc);
+	return ret;
+}
+
+void mlx5hws_action_put_default_stc(struct mlx5hws_context *ctx, u8 tbl_type)
+__must_hold(&ctx->ctrl_lock)
+{
+	struct mlx5hws_action_default_stc *default_stc;
+
+	default_stc = ctx->common_res[tbl_type].default_stc;
+
+	default_stc = ctx->common_res[tbl_type].default_stc;
+	if (--default_stc->refcount)
+		return;
+
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->default_hit);
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw7);
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw6);
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw5);
+	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_ctr);
+	kfree(default_stc);
+	ctx->common_res[tbl_type].default_stc = NULL;
+}
+
+static void hws_action_modify_write(struct mlx5hws_send_engine *queue,
+				    u32 arg_idx,
+				    u8 *arg_data,
+				    u16 num_of_actions,
+				    u32 nope_locations)
+{
+	u8 *new_arg_data = NULL;
+	int i, j;
+
+	if (unlikely(nope_locations)) {
+		new_arg_data = kcalloc(num_of_actions,
+				       MLX5HWS_MODIFY_ACTION_SIZE, GFP_KERNEL);
+		if (unlikely(!new_arg_data))
+			return;
+
+		for (i = 0, j = 0; i < num_of_actions; i++, j++) {
+			memcpy(&new_arg_data[j], arg_data, MLX5HWS_MODIFY_ACTION_SIZE);
+			if (BIT(i) & nope_locations)
+				j++;
+		}
+	}
+
+	mlx5hws_arg_write(queue, NULL, arg_idx,
+			  new_arg_data ? new_arg_data : arg_data,
+			  num_of_actions * MLX5HWS_MODIFY_ACTION_SIZE);
+
+	kfree(new_arg_data);
+}
+
+void mlx5hws_action_prepare_decap_l3_data(u8 *src, u8 *dst, u16 num_of_actions)
+{
+	u8 *e_src;
+	int i;
+
+	/* num_of_actions = remove l3l2 + 4/5 inserts + remove extra 2 bytes
+	 * copy from end of src to the start of dst.
+	 * move to the end, 2 is the leftover from 14B or 18B
+	 */
+	if (num_of_actions == DECAP_L3_NUM_ACTIONS_W_NO_VLAN)
+		e_src = src + MLX5HWS_ACTION_HDR_LEN_L2;
+	else
+		e_src = src + MLX5HWS_ACTION_HDR_LEN_L2_W_VLAN;
+
+	/* Move dst over the first remove action + zero data */
+	dst += MLX5HWS_ACTION_DOUBLE_SIZE;
+	/* Move dst over the first insert ctrl action */
+	dst += MLX5HWS_ACTION_DOUBLE_SIZE / 2;
+	/* Actions:
+	 * no vlan: r_h-insert_4b-insert_4b-insert_4b-insert_4b-remove_2b.
+	 * with vlan: r_h-insert_4b-insert_4b-insert_4b-insert_4b-insert_4b-remove_2b.
+	 * the loop is without the last insertion.
+	 */
+	for (i = 0; i < num_of_actions - 3; i++) {
+		e_src -= MLX5HWS_ACTION_INLINE_DATA_SIZE;
+		memcpy(dst, e_src, MLX5HWS_ACTION_INLINE_DATA_SIZE); /* data */
+		dst += MLX5HWS_ACTION_DOUBLE_SIZE;
+	}
+	/* Copy the last 2 bytes after a gap of 2 bytes which will be removed */
+	e_src -= MLX5HWS_ACTION_INLINE_DATA_SIZE / 2;
+	dst += MLX5HWS_ACTION_INLINE_DATA_SIZE / 2;
+	memcpy(dst, e_src, 2);
+}
+
+static int
+hws_action_get_shared_stc_offset(struct mlx5hws_context_common_res *common_res,
+				 enum mlx5hws_context_shared_stc_type stc_type)
+{
+	return common_res->shared_stc[stc_type]->stc_chunk.offset;
+}
+
+static struct mlx5hws_actions_wqe_setter *
+hws_action_setter_find_first(struct mlx5hws_actions_wqe_setter *setter,
+			     u8 req_flags)
+{
+	/* Use a new setter if requested flags are taken */
+	while (setter->flags & req_flags)
+		setter++;
+
+	/* Use current setter in required flags are not used */
+	return setter;
+}
+
+static void
+hws_action_apply_stc(struct mlx5hws_actions_apply_data *apply,
+		     enum mlx5hws_action_stc_idx stc_idx,
+		     u8 action_idx)
+{
+	struct mlx5hws_action *action = apply->rule_action[action_idx].action;
+
+	apply->wqe_ctrl->stc_ix[stc_idx] =
+		htonl(action->stc[apply->tbl_type].offset);
+}
+
+static void
+hws_action_setter_push_vlan(struct mlx5hws_actions_apply_data *apply,
+			    struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+
+	rule_action = &apply->rule_action[setter->idx_double];
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = rule_action->push_vlan.vlan_hdr;
+
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_DW6, setter->idx_double);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
+}
+
+static void
+hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
+				struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+	struct mlx5hws_action *action;
+	u32 arg_sz, arg_idx;
+	u8 *single_action;
+	__be32 stc_idx;
+
+	rule_action = &apply->rule_action[setter->idx_double];
+	action = rule_action->action;
+
+	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
+
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
+
+	if (action->modify_header.num_of_actions == 1) {
+		if (action->modify_header.single_action_type ==
+		    MLX5_MODIFICATION_TYPE_COPY ||
+		    action->modify_header.single_action_type ==
+		    MLX5_MODIFICATION_TYPE_ADD_FIELD) {
+			apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = 0;
+			return;
+		}
+
+		if (action->flags & MLX5HWS_ACTION_FLAG_SHARED)
+			single_action = (u8 *)&action->modify_header.single_action;
+		else
+			single_action = rule_action->modify_header.data;
+
+		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] =
+			*(__be32 *)MLX5_ADDR_OF(set_action_in, single_action, data);
+	} else {
+		/* Argument offset multiple with number of args per these actions */
+		arg_sz = mlx5hws_arg_get_arg_size(action->modify_header.max_num_of_actions);
+		arg_idx = rule_action->modify_header.offset * arg_sz;
+
+		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
+
+		if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
+			apply->require_dep = 1;
+			hws_action_modify_write(apply->queue,
+						action->modify_header.arg_id + arg_idx,
+						rule_action->modify_header.data,
+						action->modify_header.num_of_actions,
+						action->modify_header.nope_locations);
+		}
+	}
+}
+
+static void
+hws_action_setter_insert_ptr(struct mlx5hws_actions_apply_data *apply,
+			     struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+	struct mlx5hws_action *action;
+	u32 arg_idx, arg_sz;
+	__be32 stc_idx;
+
+	rule_action = &apply->rule_action[setter->idx_double];
+	action = rule_action->action + rule_action->reformat.hdr_idx;
+
+	/* Argument offset multiple on args required for header size */
+	arg_sz = mlx5hws_arg_data_size_to_arg_size(action->reformat.max_hdr_sz);
+	arg_idx = rule_action->reformat.offset * arg_sz;
+
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
+
+	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
+
+	if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
+		apply->require_dep = 1;
+		mlx5hws_arg_write(apply->queue, NULL,
+				  action->reformat.arg_id + arg_idx,
+				  rule_action->reformat.data,
+				  action->reformat.header_size);
+	}
+}
+
+static void
+hws_action_setter_tnl_l3_to_l2(struct mlx5hws_actions_apply_data *apply,
+			       struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+	struct mlx5hws_action *action;
+	u32 arg_sz, arg_idx;
+	__be32 stc_idx;
+
+	rule_action = &apply->rule_action[setter->idx_double];
+	action = rule_action->action + rule_action->reformat.hdr_idx;
+
+	/* Argument offset multiple on args required for num of actions */
+	arg_sz = mlx5hws_arg_get_arg_size(action->modify_header.max_num_of_actions);
+	arg_idx = rule_action->reformat.offset * arg_sz;
+
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
+
+	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
+
+	if (!(action->flags & MLX5HWS_ACTION_FLAG_SHARED)) {
+		apply->require_dep = 1;
+		mlx5hws_arg_decapl3_write(apply->queue,
+					  action->modify_header.arg_id + arg_idx,
+					  rule_action->reformat.data,
+					  action->modify_header.num_of_actions);
+	}
+}
+
+static void
+hws_action_setter_aso(struct mlx5hws_actions_apply_data *apply,
+		      struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+	u32 exe_aso_ctrl;
+	u32 offset;
+
+	rule_action = &apply->rule_action[setter->idx_double];
+
+	switch (rule_action->action->type) {
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		/* exe_aso_ctrl format:
+		 * [STC only and reserved bits 29b][init_color 2b][meter_id 1b]
+		 */
+		offset = rule_action->aso_meter.offset / MLX5_ASO_METER_NUM_PER_OBJ;
+		exe_aso_ctrl = rule_action->aso_meter.offset % MLX5_ASO_METER_NUM_PER_OBJ;
+		exe_aso_ctrl |= rule_action->aso_meter.init_color <<
+				MLX5HWS_ACTION_METER_INIT_COLOR_OFFSET;
+		break;
+	default:
+		mlx5hws_err(rule_action->action->ctx,
+			    "Unsupported ASO action type: %d\n", rule_action->action->type);
+		return;
+	}
+
+	/* aso_object_offset format: [24B] */
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = htonl(offset);
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(exe_aso_ctrl);
+
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_DW6, setter->idx_double);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
+}
+
+static void
+hws_action_setter_tag(struct mlx5hws_actions_apply_data *apply,
+		      struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+
+	rule_action = &apply->rule_action[setter->idx_single];
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW5] = htonl(rule_action->tag.value);
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_DW5, setter->idx_single);
+}
+
+static void
+hws_action_setter_ctrl_ctr(struct mlx5hws_actions_apply_data *apply,
+			   struct mlx5hws_actions_wqe_setter *setter)
+{
+	struct mlx5hws_rule_action *rule_action;
+
+	rule_action = &apply->rule_action[setter->idx_ctr];
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW0] = htonl(rule_action->counter.offset);
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_CTRL, setter->idx_ctr);
+}
+
+static void
+hws_action_setter_single(struct mlx5hws_actions_apply_data *apply,
+			 struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW5] = 0;
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_DW5, setter->idx_single);
+}
+
+static void
+hws_action_setter_single_double_pop(struct mlx5hws_actions_apply_data *apply,
+				    struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW5] = 0;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW5] =
+		htonl(hws_action_get_shared_stc_offset(apply->common_res,
+						       MLX5HWS_CONTEXT_SHARED_STC_DOUBLE_POP));
+}
+
+static void
+hws_action_setter_hit(struct mlx5hws_actions_apply_data *apply,
+		      struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_HIT_LSB] = 0;
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_HIT, setter->idx_hit);
+}
+
+static void
+hws_action_setter_default_hit(struct mlx5hws_actions_apply_data *apply,
+			      struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_HIT_LSB] = 0;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] =
+		htonl(apply->common_res->default_stc->default_hit.offset);
+}
+
+static void
+hws_action_setter_hit_next_action(struct mlx5hws_actions_apply_data *apply,
+				  struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_HIT_LSB] = htonl(apply->next_direct_idx << 6);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] = htonl(apply->jump_to_action_stc);
+}
+
+static void
+hws_action_setter_common_decap(struct mlx5hws_actions_apply_data *apply,
+			       struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW5] = 0;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW5] =
+		htonl(hws_action_get_shared_stc_offset(apply->common_res,
+						       MLX5HWS_CONTEXT_SHARED_STC_DECAP_L3));
+}
+
+static void
+hws_action_setter_range(struct mlx5hws_actions_apply_data *apply,
+			struct mlx5hws_actions_wqe_setter *setter)
+{
+	/* Always jump to index zero */
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_HIT_LSB] = 0;
+	hws_action_apply_stc(apply, MLX5HWS_ACTION_STC_IDX_HIT, setter->idx_hit);
+}
+
+int mlx5hws_action_template_process(struct mlx5hws_action_template *at)
+{
+	struct mlx5hws_actions_wqe_setter *start_setter = at->setters + 1;
+	enum mlx5hws_action_type *action_type = at->action_type_arr;
+	struct mlx5hws_actions_wqe_setter *setter = at->setters;
+	struct mlx5hws_actions_wqe_setter *pop_setter = NULL;
+	struct mlx5hws_actions_wqe_setter *last_setter;
+	int i;
+
+	/* Note: Given action combination must be valid */
+
+	/* Check if action were already processed */
+	if (at->num_of_action_stes)
+		return 0;
+
+	for (i = 0; i < MLX5HWS_ACTION_MAX_STE; i++)
+		setter[i].set_hit = &hws_action_setter_hit_next_action;
+
+	/* The same action template setters can be used with jumbo or match
+	 * STE, to support both cases we reserve the first setter for cases
+	 * with jumbo STE to allow jump to the first action STE.
+	 * This extra setter can be reduced in some cases on rule creation.
+	 */
+	setter = start_setter;
+	last_setter = start_setter;
+
+	for (i = 0; i < at->num_actions; i++) {
+		switch (action_type[i]) {
+		case MLX5HWS_ACTION_TYP_DROP:
+		case MLX5HWS_ACTION_TYP_TBL:
+		case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+		case MLX5HWS_ACTION_TYP_VPORT:
+		case MLX5HWS_ACTION_TYP_MISS:
+			/* Hit action */
+			last_setter->flags |= ASF_HIT;
+			last_setter->set_hit = &hws_action_setter_hit;
+			last_setter->idx_hit = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_RANGE:
+			last_setter->flags |= ASF_HIT;
+			last_setter->set_hit = &hws_action_setter_range;
+			last_setter->idx_hit = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_POP_VLAN:
+			/* Single remove header to header */
+			if (pop_setter) {
+				/* We have 2 pops, use the shared */
+				pop_setter->set_single = &hws_action_setter_single_double_pop;
+				break;
+			}
+			setter = hws_action_setter_find_first(last_setter,
+							      ASF_SINGLE1 | ASF_MODIFY |
+							      ASF_INSERT);
+			setter->flags |= ASF_SINGLE1 | ASF_REMOVE;
+			setter->set_single = &hws_action_setter_single;
+			setter->idx_single = i;
+			pop_setter = setter;
+			break;
+
+		case MLX5HWS_ACTION_TYP_PUSH_VLAN:
+			/* Double insert inline */
+			setter = hws_action_setter_find_first(last_setter, ASF_DOUBLE | ASF_REMOVE);
+			setter->flags |= ASF_DOUBLE | ASF_INSERT;
+			setter->set_double = &hws_action_setter_push_vlan;
+			setter->idx_double = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_MODIFY_HDR:
+			/* Double modify header list */
+			setter = hws_action_setter_find_first(last_setter, ASF_DOUBLE | ASF_REMOVE);
+			setter->flags |= ASF_DOUBLE | ASF_MODIFY;
+			setter->set_double = &hws_action_setter_modify_header;
+			setter->idx_double = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_ASO_METER:
+			/* Double ASO action */
+			setter = hws_action_setter_find_first(last_setter, ASF_DOUBLE);
+			setter->flags |= ASF_DOUBLE;
+			setter->set_double = &hws_action_setter_aso;
+			setter->idx_double = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_REMOVE_HEADER:
+		case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2:
+			/* Single remove header to header */
+			setter = hws_action_setter_find_first(last_setter,
+							      ASF_SINGLE1 | ASF_MODIFY);
+			setter->flags |= ASF_SINGLE1 | ASF_REMOVE;
+			setter->set_single = &hws_action_setter_single;
+			setter->idx_single = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_INSERT_HEADER:
+		case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2:
+			/* Double insert header with pointer */
+			setter = hws_action_setter_find_first(last_setter, ASF_DOUBLE | ASF_REMOVE);
+			setter->flags |= ASF_DOUBLE | ASF_INSERT;
+			setter->set_double = &hws_action_setter_insert_ptr;
+			setter->idx_double = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3:
+			/* Single remove + Double insert header with pointer */
+			setter = hws_action_setter_find_first(last_setter,
+							      ASF_SINGLE1 | ASF_DOUBLE);
+			setter->flags |= ASF_SINGLE1 | ASF_DOUBLE;
+			setter->set_double = &hws_action_setter_insert_ptr;
+			setter->idx_double = i;
+			setter->set_single = &hws_action_setter_common_decap;
+			setter->idx_single = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
+			/* Double modify header list with remove and push inline */
+			setter = hws_action_setter_find_first(last_setter, ASF_DOUBLE | ASF_REMOVE);
+			setter->flags |= ASF_DOUBLE | ASF_MODIFY | ASF_INSERT;
+			setter->set_double = &hws_action_setter_tnl_l3_to_l2;
+			setter->idx_double = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_TAG:
+			/* Single TAG action, search for any room from the start */
+			setter = hws_action_setter_find_first(start_setter, ASF_SINGLE1);
+			setter->flags |= ASF_SINGLE1;
+			setter->set_single = &hws_action_setter_tag;
+			setter->idx_single = i;
+			break;
+
+		case MLX5HWS_ACTION_TYP_CTR:
+			/* Control counter action
+			 * TODO: Current counter executed first. Support is needed
+			 *	 for single ation counter action which is done last.
+			 *	 Example: Decap + CTR
+			 */
+			setter = hws_action_setter_find_first(start_setter, ASF_CTR);
+			setter->flags |= ASF_CTR;
+			setter->set_ctr = &hws_action_setter_ctrl_ctr;
+			setter->idx_ctr = i;
+			break;
+		default:
+			pr_warn("HWS: Invalid action type in processingaction template: action_type[%d]=%d\n",
+				i, action_type[i]);
+			return -EOPNOTSUPP;
+		}
+
+		last_setter = max(setter, last_setter);
+	}
+
+	/* Set default hit on the last STE if no hit action provided */
+	if (!(last_setter->flags & ASF_HIT))
+		last_setter->set_hit = &hws_action_setter_default_hit;
+
+	at->num_of_action_stes = last_setter - start_setter + 1;
+
+	/* Check if action template doesn't require any action DWs */
+	at->only_term = (at->num_of_action_stes == 1) &&
+		!(last_setter->flags & ~(ASF_CTR | ASF_HIT));
+
+	return 0;
+}
+
+struct mlx5hws_action_template *
+mlx5hws_action_template_create(enum mlx5hws_action_type action_type[])
+{
+	struct mlx5hws_action_template *at;
+	u8 num_actions = 0;
+	int i;
+
+	at = kzalloc(sizeof(*at), GFP_KERNEL);
+	if (!at)
+		return NULL;
+
+	while (action_type[num_actions++] != MLX5HWS_ACTION_TYP_LAST)
+		;
+
+	at->num_actions = num_actions - 1;
+	at->action_type_arr = kcalloc(num_actions, sizeof(*action_type), GFP_KERNEL);
+	if (!at->action_type_arr)
+		goto free_at;
+
+	for (i = 0; i < num_actions; i++)
+		at->action_type_arr[i] = action_type[i];
+
+	return at;
+
+free_at:
+	kfree(at);
+	return NULL;
+}
+
+int mlx5hws_action_template_destroy(struct mlx5hws_action_template *at)
+{
+	kfree(at->action_type_arr);
+	kfree(at);
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.h
new file mode 100644
index 000000000000..bf5c1b241006
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_action.h
@@ -0,0 +1,307 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_ACTION_H_
+#define MLX5HWS_ACTION_H_
+
+/* Max number of STEs needed for a rule (including match) */
+#define MLX5HWS_ACTION_MAX_STE 20
+
+/* Max number of internal subactions of ipv6_ext */
+#define MLX5HWS_ACTION_IPV6_EXT_MAX_SA 4
+
+enum mlx5hws_action_stc_idx {
+	MLX5HWS_ACTION_STC_IDX_CTRL = 0,
+	MLX5HWS_ACTION_STC_IDX_HIT = 1,
+	MLX5HWS_ACTION_STC_IDX_DW5 = 2,
+	MLX5HWS_ACTION_STC_IDX_DW6 = 3,
+	MLX5HWS_ACTION_STC_IDX_DW7 = 4,
+	MLX5HWS_ACTION_STC_IDX_MAX = 5,
+	/* STC Jumvo STE combo: CTR, Hit */
+	MLX5HWS_ACTION_STC_IDX_LAST_JUMBO_STE = 1,
+	/* STC combo1: CTR, SINGLE, DOUBLE, Hit */
+	MLX5HWS_ACTION_STC_IDX_LAST_COMBO1 = 3,
+	/* STC combo2: CTR, 3 x SINGLE, Hit */
+	MLX5HWS_ACTION_STC_IDX_LAST_COMBO2 = 4,
+	/* STC combo2: CTR, TRIPLE, Hit */
+	MLX5HWS_ACTION_STC_IDX_LAST_COMBO3 = 2,
+};
+
+enum mlx5hws_action_offset {
+	MLX5HWS_ACTION_OFFSET_DW0 = 0,
+	MLX5HWS_ACTION_OFFSET_DW5 = 5,
+	MLX5HWS_ACTION_OFFSET_DW6 = 6,
+	MLX5HWS_ACTION_OFFSET_DW7 = 7,
+	MLX5HWS_ACTION_OFFSET_HIT = 3,
+	MLX5HWS_ACTION_OFFSET_HIT_LSB = 4,
+};
+
+enum {
+	MLX5HWS_ACTION_DOUBLE_SIZE = 8,
+	MLX5HWS_ACTION_INLINE_DATA_SIZE = 4,
+	MLX5HWS_ACTION_HDR_LEN_L2_MACS = 12,
+	MLX5HWS_ACTION_HDR_LEN_L2_VLAN = 4,
+	MLX5HWS_ACTION_HDR_LEN_L2_ETHER = 2,
+	MLX5HWS_ACTION_HDR_LEN_L2 = (MLX5HWS_ACTION_HDR_LEN_L2_MACS +
+				     MLX5HWS_ACTION_HDR_LEN_L2_ETHER),
+	MLX5HWS_ACTION_HDR_LEN_L2_W_VLAN = (MLX5HWS_ACTION_HDR_LEN_L2 +
+					    MLX5HWS_ACTION_HDR_LEN_L2_VLAN),
+	MLX5HWS_ACTION_REFORMAT_DATA_SIZE = 64,
+	DECAP_L3_NUM_ACTIONS_W_NO_VLAN = 6,
+	DECAP_L3_NUM_ACTIONS_W_VLAN = 7,
+};
+
+enum mlx5hws_action_setter_flag {
+	ASF_SINGLE1 = 1 << 0,
+	ASF_SINGLE2 = 1 << 1,
+	ASF_SINGLE3 = 1 << 2,
+	ASF_DOUBLE = ASF_SINGLE2 | ASF_SINGLE3,
+	ASF_TRIPLE = ASF_SINGLE1 | ASF_DOUBLE,
+	ASF_INSERT = 1 << 3,
+	ASF_REMOVE = 1 << 4,
+	ASF_MODIFY = 1 << 5,
+	ASF_CTR = 1 << 6,
+	ASF_HIT = 1 << 7,
+};
+
+struct mlx5hws_action_default_stc {
+	struct mlx5hws_pool_chunk nop_ctr;
+	struct mlx5hws_pool_chunk nop_dw5;
+	struct mlx5hws_pool_chunk nop_dw6;
+	struct mlx5hws_pool_chunk nop_dw7;
+	struct mlx5hws_pool_chunk default_hit;
+	u32 refcount;
+};
+
+struct mlx5hws_action_shared_stc {
+	struct mlx5hws_pool_chunk stc_chunk;
+	u32 refcount;
+};
+
+struct mlx5hws_actions_apply_data {
+	struct mlx5hws_send_engine *queue;
+	struct mlx5hws_rule_action *rule_action;
+	__be32 *wqe_data;
+	struct mlx5hws_wqe_gta_ctrl_seg *wqe_ctrl;
+	u32 jump_to_action_stc;
+	struct mlx5hws_context_common_res *common_res;
+	enum mlx5hws_table_type tbl_type;
+	u32 next_direct_idx;
+	u8 require_dep;
+};
+
+struct mlx5hws_actions_wqe_setter;
+
+typedef void (*mlx5hws_action_setter_fp)(struct mlx5hws_actions_apply_data *apply,
+					 struct mlx5hws_actions_wqe_setter *setter);
+
+struct mlx5hws_actions_wqe_setter {
+	mlx5hws_action_setter_fp set_single;
+	mlx5hws_action_setter_fp set_double;
+	mlx5hws_action_setter_fp set_triple;
+	mlx5hws_action_setter_fp set_hit;
+	mlx5hws_action_setter_fp set_ctr;
+	u8 idx_single;
+	u8 idx_double;
+	u8 idx_triple;
+	u8 idx_ctr;
+	u8 idx_hit;
+	u8 stage_idx;
+	u8 flags;
+};
+
+struct mlx5hws_action_template {
+	struct mlx5hws_actions_wqe_setter setters[MLX5HWS_ACTION_MAX_STE];
+	enum mlx5hws_action_type *action_type_arr;
+	u8 num_of_action_stes;
+	u8 num_actions;
+	u8 only_term;
+};
+
+struct mlx5hws_action {
+	u8 type;
+	u8 flags;
+	struct mlx5hws_context *ctx;
+	union {
+		struct {
+			struct mlx5hws_pool_chunk stc[MLX5HWS_TABLE_TYPE_MAX];
+			union {
+				struct {
+					u32 pat_id;
+					u32 arg_id;
+					__be64 single_action;
+					u32 nope_locations;
+					u8 num_of_patterns;
+					u8 single_action_type;
+					u8 num_of_actions;
+					u8 max_num_of_actions;
+					u8 require_reparse;
+				} modify_header;
+				struct {
+					u32 arg_id;
+					u32 header_size;
+					u16 max_hdr_sz;
+					u8 num_of_hdrs;
+					u8 anchor;
+					u8 e_anchor;
+					u8 offset;
+					bool encap;
+					u8 require_reparse;
+				} reformat;
+				struct {
+					u32 obj_id;
+					u8 return_reg_id;
+				} aso;
+				struct {
+					u16 vport_num;
+					u16 esw_owner_vhca_id;
+					bool esw_owner_vhca_id_valid;
+				} vport;
+				struct {
+					u32 obj_id;
+				} dest_obj;
+				struct {
+					struct mlx5hws_cmd_forward_tbl *fw_island;
+					size_t num_dest;
+					struct mlx5hws_cmd_set_fte_dest *dest_list;
+				} dest_array;
+				struct {
+					u8 type;
+					u8 start_anchor;
+					u8 end_anchor;
+					u8 num_of_words;
+					bool decap;
+				} insert_hdr;
+				struct {
+					/* PRM start anchor from which header will be removed */
+					u8 anchor;
+					/* Header remove offset in bytes, from the start
+					 * anchor to the location where remove header starts.
+					 */
+					u8 offset;
+					/* Indicates the removed header size in bytes */
+					size_t size;
+				} remove_header;
+				struct {
+					struct mlx5hws_matcher_action_ste *table_ste;
+					struct mlx5hws_action *hit_ft_action;
+					struct mlx5hws_definer *definer;
+				} range;
+			};
+		};
+
+		struct ibv_flow_action *flow_action;
+		u32 obj_id;
+		struct ibv_qp *qp;
+	};
+};
+
+const char *mlx5hws_action_type_to_str(enum mlx5hws_action_type action_type);
+
+int mlx5hws_action_get_default_stc(struct mlx5hws_context *ctx,
+				   u8 tbl_type);
+
+void mlx5hws_action_put_default_stc(struct mlx5hws_context *ctx,
+				    u8 tbl_type);
+
+void mlx5hws_action_prepare_decap_l3_data(u8 *src, u8 *dst,
+					  u16 num_of_actions);
+
+int mlx5hws_action_template_process(struct mlx5hws_action_template *at);
+
+bool mlx5hws_action_check_combo(struct mlx5hws_context *ctx,
+				enum mlx5hws_action_type *user_actions,
+				enum mlx5hws_table_type table_type);
+
+int mlx5hws_action_alloc_single_stc(struct mlx5hws_context *ctx,
+				    struct mlx5hws_cmd_stc_modify_attr *stc_attr,
+				    u32 table_type,
+				    struct mlx5hws_pool_chunk *stc);
+
+void mlx5hws_action_free_single_stc(struct mlx5hws_context *ctx,
+				    u32 table_type,
+				    struct mlx5hws_pool_chunk *stc);
+
+static inline void
+mlx5hws_action_setter_default_single(struct mlx5hws_actions_apply_data *apply,
+				     struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW5] = 0;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW5] =
+		htonl(apply->common_res->default_stc->nop_dw5.offset);
+}
+
+static inline void
+mlx5hws_action_setter_default_double(struct mlx5hws_actions_apply_data *apply,
+				     struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = 0;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] =
+		htonl(apply->common_res->default_stc->nop_dw6.offset);
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] =
+		htonl(apply->common_res->default_stc->nop_dw7.offset);
+}
+
+static inline void
+mlx5hws_action_setter_default_ctr(struct mlx5hws_actions_apply_data *apply,
+				  struct mlx5hws_actions_wqe_setter *setter)
+{
+	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW0] = 0;
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] =
+		htonl(apply->common_res->default_stc->nop_ctr.offset);
+}
+
+static inline void
+mlx5hws_action_apply_setter(struct mlx5hws_actions_apply_data *apply,
+			    struct mlx5hws_actions_wqe_setter *setter,
+			    bool is_jumbo)
+{
+	u8 num_of_actions;
+
+	/* Set control counter */
+	if (setter->set_ctr)
+		setter->set_ctr(apply, setter);
+	else
+		mlx5hws_action_setter_default_ctr(apply, setter);
+
+	if (!is_jumbo) {
+		if (unlikely(setter->set_triple)) {
+			/* Set triple on match */
+			setter->set_triple(apply, setter);
+			num_of_actions = MLX5HWS_ACTION_STC_IDX_LAST_COMBO3;
+		} else {
+			/* Set single and double on match */
+			if (setter->set_single)
+				setter->set_single(apply, setter);
+			else
+				mlx5hws_action_setter_default_single(apply, setter);
+
+			if (setter->set_double)
+				setter->set_double(apply, setter);
+			else
+				mlx5hws_action_setter_default_double(apply, setter);
+
+			num_of_actions = setter->set_double ?
+				MLX5HWS_ACTION_STC_IDX_LAST_COMBO1 :
+				MLX5HWS_ACTION_STC_IDX_LAST_COMBO2;
+		}
+	} else {
+		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW5] = 0;
+		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
+		apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = 0;
+		apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW5] = 0;
+		apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = 0;
+		apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
+		num_of_actions = MLX5HWS_ACTION_STC_IDX_LAST_JUMBO_STE;
+	}
+
+	/* Set next/final hit action */
+	setter->set_hit(apply, setter);
+
+	/* Set number of actions */
+	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] |=
+		htonl(num_of_actions << 29);
+}
+
+#endif /* MLX5HWS_ACTION_H_ */
-- 
cgit v1.3-3-g829e


From 71a1372b8275dd1c57db045d4a710a5b8f124f52 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:32:28 +0300
Subject: net/mlx5: HWS, added tables handling

Flow tables are SW objects that are comprised of list of matchers,
that in turn define the properties of a flow to match on and set
of actions to perform on the flows in case of match hit or miss.

Reviewed-by: Itamar Gozlan <igozlan@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_table.c         | 493 +++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_table.h         |  68 +++
 2 files changed, 561 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c
new file mode 100644
index 000000000000..9dbc3e9da5ea
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c
@@ -0,0 +1,493 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl)
+{
+	return tbl->ft_id;
+}
+
+static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl,
+					struct mlx5hws_cmd_ft_create_attr *ft_attr)
+{
+	ft_attr->type = tbl->fw_ft_type;
+	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB)
+		ft_attr->level = tbl->ctx->caps->fdb_ft.max_level - 1;
+	else
+		ft_attr->level = tbl->ctx->caps->nic_ft.max_level - 1;
+	ft_attr->rtc_valid = true;
+}
+
+static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,
+				   struct mlx5hws_cmd_ft_create_attr *ft_attr)
+{
+	/* Enabling reformat_en or decap_en for the first flow table
+	 * must be done when all VFs are down.
+	 * However, HWS doesn't know when it is required to create the first FT.
+	 * On the other hand, HWS doesn't use all these FT capabilities at all
+	 * (the API doesn't even provide a way to specify these flags), so we'll
+	 * just set these caps on all the flow tables.
+	 * If HCA_CAP.fdb_dynamic_tunnel is set, this constraint is N/A.
+	 */
+	if (!MLX5_CAP_ESW_FLOWTABLE(tbl->ctx->mdev, fdb_dynamic_tunnel)) {
+		ft_attr->reformat_en = true;
+		ft_attr->decap_en = true;
+	}
+}
+
+static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+{
+	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
+	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
+	struct mlx5hws_cmd_forward_tbl *default_miss;
+	struct mlx5hws_cmd_set_fte_dest dest = {0};
+	struct mlx5hws_context *ctx = tbl->ctx;
+	u8 tbl_type = tbl->type;
+
+	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
+		return 0;
+
+	if (ctx->common_res[tbl_type].default_miss) {
+		ctx->common_res[tbl_type].default_miss->refcount++;
+		return 0;
+	}
+
+	ft_attr.type = tbl->fw_ft_type;
+	ft_attr.level = tbl->ctx->caps->fdb_ft.max_level; /* The last level */
+	ft_attr.rtc_valid = false;
+
+	dest.destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.destination_id = ctx->caps->eswitch_manager_vport_number;
+
+	fte_attr.action_flags = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	fte_attr.dests_num = 1;
+	fte_attr.dests = &dest;
+
+	default_miss = mlx5hws_cmd_forward_tbl_create(ctx->mdev, &ft_attr, &fte_attr);
+	if (!default_miss) {
+		mlx5hws_err(ctx, "Failed to default miss table type: 0x%x\n", tbl_type);
+		return -EINVAL;
+	}
+
+	/* ctx->ctrl_lock must be held here */
+	ctx->common_res[tbl_type].default_miss = default_miss;
+	ctx->common_res[tbl_type].default_miss->refcount++;
+
+	return 0;
+}
+
+/* Called under ctx->ctrl_lock */
+static void hws_table_down_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+{
+	struct mlx5hws_cmd_forward_tbl *default_miss;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	u8 tbl_type = tbl->type;
+
+	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
+		return;
+
+	default_miss = ctx->common_res[tbl_type].default_miss;
+	if (--default_miss->refcount)
+		return;
+
+	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, default_miss);
+	ctx->common_res[tbl_type].default_miss = NULL;
+}
+
+static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 ft_id)
+{
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+	int ret;
+
+	if (unlikely(tbl->type != MLX5HWS_TABLE_TYPE_FDB))
+		pr_warn("HWS: invalid table type %d\n", tbl->type);
+
+	mlx5hws_cmd_set_attr_connect_miss_tbl(tbl->ctx,
+					      tbl->fw_ft_type,
+					      tbl->type,
+					      &ft_attr);
+
+	ret = mlx5hws_cmd_flow_table_modify(tbl->ctx->mdev, &ft_attr, ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Failed to connect FT to default FDB FT\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
+				    struct mlx5hws_table *tbl,
+				    u32 *ft_id)
+{
+	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
+	int ret;
+
+	hws_table_init_next_ft_attr(tbl, &ft_attr);
+	hws_table_set_cap_attr(tbl, &ft_attr);
+
+	ret = mlx5hws_cmd_flow_table_create(mdev, &ft_attr, ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Failed creating default ft\n");
+		return ret;
+	}
+
+	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
+		/* Take/create ref over the default miss */
+		ret = hws_table_up_default_fdb_miss_tbl(tbl);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Failed to get default fdb miss\n");
+			goto free_ft_obj;
+		}
+		ret = hws_table_connect_to_default_miss_tbl(tbl, *ft_id);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Failed connecting to default miss tbl\n");
+			goto down_miss_tbl;
+		}
+	}
+
+	return 0;
+
+down_miss_tbl:
+	hws_table_down_default_fdb_miss_tbl(tbl);
+free_ft_obj:
+	mlx5hws_cmd_flow_table_destroy(mdev, ft_attr.type, *ft_id);
+	return ret;
+}
+
+void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl,
+				      u32 ft_id)
+{
+	mlx5hws_cmd_flow_table_destroy(tbl->ctx->mdev, tbl->fw_ft_type, ft_id);
+	hws_table_down_default_fdb_miss_tbl(tbl);
+}
+
+static int hws_table_init_check_hws_support(struct mlx5hws_context *ctx,
+					    struct mlx5hws_table *tbl)
+{
+	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT)) {
+		mlx5hws_err(ctx, "HWS not supported, cannot create mlx5hws_table\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int hws_table_init(struct mlx5hws_table *tbl)
+{
+	struct mlx5hws_context *ctx = tbl->ctx;
+	int ret;
+
+	ret = hws_table_init_check_hws_support(ctx, tbl);
+	if (ret)
+		return ret;
+
+	if (mlx5hws_table_get_fw_ft_type(tbl->type, (u8 *)&tbl->fw_ft_type)) {
+		pr_warn("HWS: invalid table type %d\n", tbl->type);
+		return -EOPNOTSUPP;
+	}
+
+	mutex_lock(&ctx->ctrl_lock);
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Failed to create flow table object\n");
+		mutex_unlock(&ctx->ctrl_lock);
+		return ret;
+	}
+
+	ret = mlx5hws_action_get_default_stc(ctx, tbl->type);
+	if (ret)
+		goto tbl_destroy;
+
+	INIT_LIST_HEAD(&tbl->matchers_list);
+	INIT_LIST_HEAD(&tbl->default_miss.head);
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return 0;
+
+tbl_destroy:
+	mlx5hws_table_destroy_default_ft(tbl, tbl->ft_id);
+	mutex_unlock(&ctx->ctrl_lock);
+	return ret;
+}
+
+static void hws_table_uninit(struct mlx5hws_table *tbl)
+{
+	mutex_lock(&tbl->ctx->ctrl_lock);
+	mlx5hws_action_put_default_stc(tbl->ctx, tbl->type);
+	mlx5hws_table_destroy_default_ft(tbl, tbl->ft_id);
+	mutex_unlock(&tbl->ctx->ctrl_lock);
+}
+
+struct mlx5hws_table *mlx5hws_table_create(struct mlx5hws_context *ctx,
+					   struct mlx5hws_table_attr *attr)
+{
+	struct mlx5hws_table *tbl;
+	int ret;
+
+	if (attr->type > MLX5HWS_TABLE_TYPE_FDB) {
+		mlx5hws_err(ctx, "Invalid table type %d\n", attr->type);
+		return NULL;
+	}
+
+	tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+	if (!tbl)
+		return NULL;
+
+	tbl->ctx = ctx;
+	tbl->type = attr->type;
+	tbl->level = attr->level;
+
+	ret = hws_table_init(tbl);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to initialise table\n");
+		goto free_tbl;
+	}
+
+	mutex_lock(&ctx->ctrl_lock);
+	list_add(&tbl->tbl_list_node, &ctx->tbl_list);
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return tbl;
+
+free_tbl:
+	kfree(tbl);
+	return NULL;
+}
+
+int mlx5hws_table_destroy(struct mlx5hws_table *tbl)
+{
+	struct mlx5hws_context *ctx = tbl->ctx;
+	int ret;
+
+	mutex_lock(&ctx->ctrl_lock);
+	if (!list_empty(&tbl->matchers_list)) {
+		mlx5hws_err(tbl->ctx, "Cannot destroy table containing matchers\n");
+		ret = -EBUSY;
+		goto unlock_err;
+	}
+
+	if (!list_empty(&tbl->default_miss.head)) {
+		mlx5hws_err(tbl->ctx, "Cannot destroy table pointed by default miss\n");
+		ret = -EBUSY;
+		goto unlock_err;
+	}
+
+	list_del_init(&tbl->tbl_list_node);
+	mutex_unlock(&ctx->ctrl_lock);
+
+	hws_table_uninit(tbl);
+	kfree(tbl);
+
+	return 0;
+
+unlock_err:
+	mutex_unlock(&ctx->ctrl_lock);
+	return ret;
+}
+
+static u32 hws_table_get_last_ft(struct mlx5hws_table *tbl)
+{
+	struct mlx5hws_matcher *matcher;
+
+	if (list_empty(&tbl->matchers_list))
+		return tbl->ft_id;
+
+	matcher = list_last_entry(&tbl->matchers_list, struct mlx5hws_matcher, list_node);
+	return matcher->end_ft_id;
+}
+
+int mlx5hws_table_ft_set_default_next_ft(struct mlx5hws_table *tbl, u32 ft_id)
+{
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+	int ret;
+
+	/* Due to FW limitation, resetting the flow table to default action will
+	 * disconnect RTC when ignore_flow_level_rtc_valid is not supported.
+	 */
+	if (!tbl->ctx->caps->nic_ft.ignore_flow_level_rtc_valid)
+		return 0;
+
+	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB)
+		return hws_table_connect_to_default_miss_tbl(tbl, ft_id);
+
+	ft_attr.type = tbl->fw_ft_type;
+	ft_attr.modify_fs = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION;
+	ft_attr.table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_DEFAULT;
+
+	ret = mlx5hws_cmd_flow_table_modify(tbl->ctx->mdev, &ft_attr, ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Failed to set FT default miss action\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
+				  u32 ft_id,
+				  u32 fw_ft_type,
+				  u32 rtc_0_id,
+				  u32 rtc_1_id)
+{
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+
+	ft_attr.modify_fs = MLX5_IFC_MODIFY_FLOW_TABLE_RTC_ID;
+	ft_attr.type = fw_ft_type;
+	ft_attr.rtc_id_0 = rtc_0_id;
+	ft_attr.rtc_id_1 = rtc_1_id;
+
+	return mlx5hws_cmd_flow_table_modify(ctx->mdev, &ft_attr, ft_id);
+}
+
+static int hws_table_ft_set_next_ft(struct mlx5hws_context *ctx,
+				    u32 ft_id,
+				    u32 fw_ft_type,
+				    u32 next_ft_id)
+{
+	struct mlx5hws_cmd_ft_modify_attr ft_attr = {0};
+
+	ft_attr.modify_fs = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION;
+	ft_attr.table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL;
+	ft_attr.type = fw_ft_type;
+	ft_attr.table_miss_id = next_ft_id;
+
+	return mlx5hws_cmd_flow_table_modify(ctx->mdev, &ft_attr, ft_id);
+}
+
+int mlx5hws_table_update_connected_miss_tables(struct mlx5hws_table *dst_tbl)
+{
+	struct mlx5hws_table *src_tbl;
+	int ret;
+
+	if (list_empty(&dst_tbl->default_miss.head))
+		return 0;
+
+	list_for_each_entry(src_tbl, &dst_tbl->default_miss.head, default_miss.next) {
+		ret = mlx5hws_table_connect_to_miss_table(src_tbl, dst_tbl);
+		if (ret) {
+			mlx5hws_err(dst_tbl->ctx,
+				    "Failed to update source miss table, unexpected behavior\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+int mlx5hws_table_connect_to_miss_table(struct mlx5hws_table *src_tbl,
+					struct mlx5hws_table *dst_tbl)
+{
+	struct mlx5hws_matcher *matcher;
+	u32 last_ft_id;
+	int ret;
+
+	last_ft_id = hws_table_get_last_ft(src_tbl);
+
+	if (dst_tbl) {
+		if (list_empty(&dst_tbl->matchers_list)) {
+			/* Connect src_tbl last_ft to dst_tbl start anchor */
+			ret = hws_table_ft_set_next_ft(src_tbl->ctx,
+						       last_ft_id,
+						       src_tbl->fw_ft_type,
+						       dst_tbl->ft_id);
+			if (ret)
+				return ret;
+
+			/* Reset last_ft RTC to default RTC */
+			ret = mlx5hws_table_ft_set_next_rtc(src_tbl->ctx,
+							    last_ft_id,
+							    src_tbl->fw_ft_type,
+							    0, 0);
+			if (ret)
+				return ret;
+		} else {
+			/* Connect src_tbl last_ft to first matcher RTC */
+			matcher = list_first_entry(&dst_tbl->matchers_list,
+						   struct mlx5hws_matcher,
+						   list_node);
+			ret = mlx5hws_table_ft_set_next_rtc(src_tbl->ctx,
+							    last_ft_id,
+							    src_tbl->fw_ft_type,
+							    matcher->match_ste.rtc_0_id,
+							    matcher->match_ste.rtc_1_id);
+			if (ret)
+				return ret;
+
+			/* Reset next miss FT to default */
+			ret = mlx5hws_table_ft_set_default_next_ft(src_tbl, last_ft_id);
+			if (ret)
+				return ret;
+		}
+	} else {
+		/* Reset next miss FT to default */
+		ret = mlx5hws_table_ft_set_default_next_ft(src_tbl, last_ft_id);
+		if (ret)
+			return ret;
+
+		/* Reset last_ft RTC to default RTC */
+		ret = mlx5hws_table_ft_set_next_rtc(src_tbl->ctx,
+						    last_ft_id,
+						    src_tbl->fw_ft_type,
+						    0, 0);
+		if (ret)
+			return ret;
+	}
+
+	src_tbl->default_miss.miss_tbl = dst_tbl;
+
+	return 0;
+}
+
+static int hws_table_set_default_miss_not_valid(struct mlx5hws_table *tbl,
+						struct mlx5hws_table *miss_tbl)
+{
+	if (!tbl->ctx->caps->nic_ft.ignore_flow_level_rtc_valid) {
+		mlx5hws_err(tbl->ctx, "Default miss table is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if ((miss_tbl && miss_tbl->type != tbl->type)) {
+		mlx5hws_err(tbl->ctx, "Invalid arguments\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
+				   struct mlx5hws_table *miss_tbl)
+{
+	struct mlx5hws_context *ctx = tbl->ctx;
+	struct mlx5hws_table *old_miss_tbl;
+	int ret;
+
+	ret = hws_table_set_default_miss_not_valid(tbl, miss_tbl);
+	if (ret)
+		return ret;
+
+	mutex_lock(&ctx->ctrl_lock);
+
+	old_miss_tbl = tbl->default_miss.miss_tbl;
+	ret = mlx5hws_table_connect_to_miss_table(tbl, miss_tbl);
+	if (ret)
+		goto out;
+
+	if (old_miss_tbl)
+		list_del_init(&tbl->default_miss.next);
+
+	old_miss_tbl = tbl->default_miss.miss_tbl;
+	if (old_miss_tbl)
+		list_del_init(&old_miss_tbl->default_miss.head);
+
+	if (miss_tbl)
+		list_add(&tbl->default_miss.next, &miss_tbl->default_miss.head);
+
+	mutex_unlock(&ctx->ctrl_lock);
+	return 0;
+out:
+	mutex_unlock(&ctx->ctrl_lock);
+	return -ret;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.h
new file mode 100644
index 000000000000..dd50420eec9e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_TABLE_H_
+#define MLX5HWS_TABLE_H_
+
+struct mlx5hws_default_miss {
+	/* My miss table */
+	struct mlx5hws_table *miss_tbl;
+	struct list_head next;
+	/* Tables missing to my table */
+	struct list_head head;
+};
+
+struct mlx5hws_table {
+	struct mlx5hws_context *ctx;
+	u32 ft_id;
+	enum mlx5hws_table_type type;
+	u32 fw_ft_type;
+	u32 level;
+	struct list_head matchers_list;
+	struct list_head tbl_list_node;
+	struct mlx5hws_default_miss default_miss;
+};
+
+static inline
+u32 mlx5hws_table_get_fw_ft_type(enum mlx5hws_table_type type,
+				 u8 *ret_type)
+{
+	if (type != MLX5HWS_TABLE_TYPE_FDB)
+		return -EOPNOTSUPP;
+
+	*ret_type = FS_FT_FDB;
+
+	return 0;
+}
+
+static inline
+u32 mlx5hws_table_get_res_fw_ft_type(enum mlx5hws_table_type tbl_type,
+				     bool is_mirror)
+{
+	if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
+		return is_mirror ? FS_FT_FDB_TX : FS_FT_FDB_RX;
+
+	return 0;
+}
+
+int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev,
+				    struct mlx5hws_table *tbl,
+				    u32 *ft_id);
+
+void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl,
+				      u32 ft_id);
+
+int mlx5hws_table_connect_to_miss_table(struct mlx5hws_table *src_tbl,
+					struct mlx5hws_table *dst_tbl);
+
+int mlx5hws_table_update_connected_miss_tables(struct mlx5hws_table *dst_tbl);
+
+int mlx5hws_table_ft_set_default_next_ft(struct mlx5hws_table *tbl, u32 ft_id);
+
+int mlx5hws_table_ft_set_next_rtc(struct mlx5hws_context *ctx,
+				  u32 ft_id,
+				  u32 fw_ft_type,
+				  u32 rtc_0_id,
+				  u32 rtc_1_id);
+
+#endif /* MLX5HWS_TABLE_H_ */
-- 
cgit v1.3-3-g829e


From 49674803542c162a465819c1a5ca66b494ecf367 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:33:11 +0300
Subject: net/mlx5: HWS, added rules handling

Steering rule is a concept that includes match parameters for a flow,
and actions to perform on the flows that match these parameters.
This patch adds rules handling part of HW Steering.

Reviewed-by: Itamar Gozlan <igozlan@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/steering/hws/mlx5hws_rule.c | 780 +++++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_rule.h |  84 +++
 2 files changed, 864 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c
new file mode 100644
index 000000000000..c79ee70edf03
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c
@@ -0,0 +1,780 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+static void hws_rule_skip(struct mlx5hws_matcher *matcher,
+			  struct mlx5hws_match_template *mt,
+			  u32 flow_source,
+			  bool *skip_rx, bool *skip_tx)
+{
+	/* By default FDB rules are added to both RX and TX */
+	*skip_rx = false;
+	*skip_tx = false;
+
+	if (flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT) {
+		*skip_rx = true;
+	} else if (flow_source == MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK) {
+		*skip_tx = true;
+	} else {
+		/* If no flow source was set for current rule,
+		 * check for flow source in matcher attributes.
+		 */
+		if (matcher->attr.optimize_flow_src) {
+			*skip_tx =
+				matcher->attr.optimize_flow_src == MLX5HWS_MATCHER_FLOW_SRC_WIRE;
+			*skip_rx =
+				matcher->attr.optimize_flow_src == MLX5HWS_MATCHER_FLOW_SRC_VPORT;
+			return;
+		}
+	}
+}
+
+static void
+hws_rule_update_copy_tag(struct mlx5hws_rule *rule,
+			 struct mlx5hws_wqe_gta_data_seg_ste *wqe_data,
+			 bool is_jumbo)
+{
+	struct mlx5hws_rule_match_tag *tag;
+
+	if (!mlx5hws_matcher_is_resizable(rule->matcher)) {
+		tag = &rule->tag;
+	} else {
+		struct mlx5hws_wqe_gta_data_seg_ste *data_seg =
+			(struct mlx5hws_wqe_gta_data_seg_ste *)(void *)rule->resize_info->data_seg;
+		tag = (struct mlx5hws_rule_match_tag *)(void *)data_seg->action;
+	}
+
+	if (is_jumbo)
+		memcpy(wqe_data->jumbo, tag->jumbo, MLX5HWS_JUMBO_TAG_SZ);
+	else
+		memcpy(wqe_data->tag, tag->match, MLX5HWS_MATCH_TAG_SZ);
+}
+
+static void hws_rule_init_dep_wqe(struct mlx5hws_send_ring_dep_wqe *dep_wqe,
+				  struct mlx5hws_rule *rule,
+				  struct mlx5hws_match_template *mt,
+				  struct mlx5hws_rule_attr *attr)
+{
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	bool skip_rx, skip_tx;
+
+	dep_wqe->rule = rule;
+	dep_wqe->user_data = attr->user_data;
+	dep_wqe->direct_index = mlx5hws_matcher_is_insert_by_idx(matcher) ?
+				attr->rule_idx : 0;
+
+	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
+		hws_rule_skip(matcher, mt, attr->flow_source, &skip_rx, &skip_tx);
+
+		if (!skip_rx) {
+			dep_wqe->rtc_0 = matcher->match_ste.rtc_0_id;
+			dep_wqe->retry_rtc_0 = matcher->col_matcher ?
+					       matcher->col_matcher->match_ste.rtc_0_id : 0;
+		} else {
+			dep_wqe->rtc_0 = 0;
+			dep_wqe->retry_rtc_0 = 0;
+		}
+
+		if (!skip_tx) {
+			dep_wqe->rtc_1 = matcher->match_ste.rtc_1_id;
+			dep_wqe->retry_rtc_1 = matcher->col_matcher ?
+					       matcher->col_matcher->match_ste.rtc_1_id : 0;
+		} else {
+			dep_wqe->rtc_1 = 0;
+			dep_wqe->retry_rtc_1 = 0;
+		}
+	} else {
+		pr_warn("HWS: invalid tbl->type: %d\n", tbl->type);
+	}
+}
+
+static void hws_rule_move_get_rtc(struct mlx5hws_rule *rule,
+				  struct mlx5hws_send_ste_attr *ste_attr)
+{
+	struct mlx5hws_matcher *dst_matcher = rule->matcher->resize_dst;
+
+	if (rule->resize_info->rtc_0) {
+		ste_attr->rtc_0 = dst_matcher->match_ste.rtc_0_id;
+		ste_attr->retry_rtc_0 = dst_matcher->col_matcher ?
+					dst_matcher->col_matcher->match_ste.rtc_0_id : 0;
+	}
+	if (rule->resize_info->rtc_1) {
+		ste_attr->rtc_1 = dst_matcher->match_ste.rtc_1_id;
+		ste_attr->retry_rtc_1 = dst_matcher->col_matcher ?
+					dst_matcher->col_matcher->match_ste.rtc_1_id : 0;
+	}
+}
+
+static void hws_rule_gen_comp(struct mlx5hws_send_engine *queue,
+			      struct mlx5hws_rule *rule,
+			      bool err,
+			      void *user_data,
+			      enum mlx5hws_rule_status rule_status_on_succ)
+{
+	enum mlx5hws_flow_op_status comp_status;
+
+	if (!err) {
+		comp_status = MLX5HWS_FLOW_OP_SUCCESS;
+		rule->status = rule_status_on_succ;
+	} else {
+		comp_status = MLX5HWS_FLOW_OP_ERROR;
+		rule->status = MLX5HWS_RULE_STATUS_FAILED;
+	}
+
+	mlx5hws_send_engine_inc_rule(queue);
+	mlx5hws_send_engine_gen_comp(queue, user_data, comp_status);
+}
+
+static void
+hws_rule_save_resize_info(struct mlx5hws_rule *rule,
+			  struct mlx5hws_send_ste_attr *ste_attr,
+			  bool is_update)
+{
+	if (!mlx5hws_matcher_is_resizable(rule->matcher))
+		return;
+
+	if (likely(!is_update)) {
+		rule->resize_info = kzalloc(sizeof(*rule->resize_info), GFP_KERNEL);
+		if (unlikely(!rule->resize_info)) {
+			pr_warn("HWS: resize info isn't allocated for rule\n");
+			return;
+		}
+
+		rule->resize_info->max_stes =
+			rule->matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes;
+		rule->resize_info->action_ste_pool[0] = rule->matcher->action_ste[0].max_stes ?
+							rule->matcher->action_ste[0].pool :
+							NULL;
+		rule->resize_info->action_ste_pool[1] = rule->matcher->action_ste[1].max_stes ?
+							rule->matcher->action_ste[1].pool :
+							NULL;
+	}
+
+	memcpy(rule->resize_info->ctrl_seg, ste_attr->wqe_ctrl,
+	       sizeof(rule->resize_info->ctrl_seg));
+	memcpy(rule->resize_info->data_seg, ste_attr->wqe_data,
+	       sizeof(rule->resize_info->data_seg));
+}
+
+void mlx5hws_rule_clear_resize_info(struct mlx5hws_rule *rule)
+{
+	if (mlx5hws_matcher_is_resizable(rule->matcher) &&
+	    rule->resize_info) {
+		kfree(rule->resize_info);
+		rule->resize_info = NULL;
+	}
+}
+
+static void
+hws_rule_save_delete_info(struct mlx5hws_rule *rule,
+			  struct mlx5hws_send_ste_attr *ste_attr)
+{
+	struct mlx5hws_match_template *mt = rule->matcher->mt;
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
+
+	if (mlx5hws_matcher_is_resizable(rule->matcher))
+		return;
+
+	if (is_jumbo)
+		memcpy(&rule->tag.jumbo, ste_attr->wqe_data->jumbo, MLX5HWS_JUMBO_TAG_SZ);
+	else
+		memcpy(&rule->tag.match, ste_attr->wqe_data->tag, MLX5HWS_MATCH_TAG_SZ);
+}
+
+static void
+hws_rule_clear_delete_info(struct mlx5hws_rule *rule)
+{
+	/* nothing to do here */
+}
+
+static void
+hws_rule_load_delete_info(struct mlx5hws_rule *rule,
+			  struct mlx5hws_send_ste_attr *ste_attr)
+{
+	if (unlikely(!mlx5hws_matcher_is_resizable(rule->matcher))) {
+		ste_attr->wqe_tag = &rule->tag;
+	} else {
+		struct mlx5hws_wqe_gta_data_seg_ste *data_seg =
+			(struct mlx5hws_wqe_gta_data_seg_ste *)(void *)rule->resize_info->data_seg;
+		struct mlx5hws_rule_match_tag *tag =
+			(struct mlx5hws_rule_match_tag *)(void *)data_seg->action;
+		ste_attr->wqe_tag = tag;
+	}
+}
+
+static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule,
+					 u8 action_ste_selector)
+{
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_matcher_action_ste *action_ste;
+	struct mlx5hws_pool_chunk ste = {0};
+	int ret;
+
+	action_ste = &matcher->action_ste[action_ste_selector];
+	ste.order = ilog2(roundup_pow_of_two(action_ste->max_stes));
+	ret = mlx5hws_pool_chunk_alloc(action_ste->pool, &ste);
+	if (unlikely(ret)) {
+		mlx5hws_err(matcher->tbl->ctx,
+			    "Failed to allocate STE for rule actions");
+		return ret;
+	}
+	rule->action_ste_idx = ste.offset;
+
+	return 0;
+}
+
+static void hws_rule_free_action_ste_idx(struct mlx5hws_rule *rule,
+					 u8 action_ste_selector)
+{
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_pool_chunk ste = {0};
+	struct mlx5hws_pool *pool;
+	u8 max_stes;
+
+	if (mlx5hws_matcher_is_resizable(matcher)) {
+		/* Free the original action pool if rule was resized */
+		max_stes = rule->resize_info->max_stes;
+		pool = rule->resize_info->action_ste_pool[action_ste_selector];
+	} else {
+		max_stes = matcher->action_ste[action_ste_selector].max_stes;
+		pool = matcher->action_ste[action_ste_selector].pool;
+	}
+
+	/* This release is safe only when the rule match part was deleted */
+	ste.order = ilog2(roundup_pow_of_two(max_stes));
+	ste.offset = rule->action_ste_idx;
+
+	mlx5hws_pool_chunk_free(pool, &ste);
+}
+
+static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule,
+				     struct mlx5hws_rule_attr *attr)
+{
+	int action_ste_idx;
+	int ret;
+
+	ret = hws_rule_alloc_action_ste_idx(rule, 0);
+	if (unlikely(ret))
+		return ret;
+
+	action_ste_idx = rule->action_ste_idx;
+
+	ret = hws_rule_alloc_action_ste_idx(rule, 1);
+	if (unlikely(ret)) {
+		hws_rule_free_action_ste_idx(rule, 0);
+		return ret;
+	}
+
+	/* Both pools have to return the same index */
+	if (unlikely(rule->action_ste_idx != action_ste_idx)) {
+		pr_warn("HWS: allocation of action STE failed - pool indexes mismatch\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule)
+{
+	if (rule->action_ste_idx > -1) {
+		hws_rule_free_action_ste_idx(rule, 1);
+		hws_rule_free_action_ste_idx(rule, 0);
+	}
+}
+
+static void hws_rule_create_init(struct mlx5hws_rule *rule,
+				 struct mlx5hws_send_ste_attr *ste_attr,
+				 struct mlx5hws_actions_apply_data *apply,
+				 bool is_update)
+{
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+
+	/* Init rule before reuse */
+	if (!is_update) {
+		/* In update we use these rtc's */
+		rule->rtc_0 = 0;
+		rule->rtc_1 = 0;
+		rule->action_ste_selector = 0;
+	} else {
+		rule->action_ste_selector = !rule->action_ste_selector;
+	}
+
+	rule->pending_wqes = 0;
+	rule->action_ste_idx = -1;
+	rule->status = MLX5HWS_RULE_STATUS_CREATING;
+
+	/* Init default send STE attributes */
+	ste_attr->gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE;
+	ste_attr->send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	ste_attr->send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	ste_attr->send_attr.len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+
+	/* Init default action apply */
+	apply->tbl_type = tbl->type;
+	apply->common_res = &ctx->common_res[tbl->type];
+	apply->jump_to_action_stc = matcher->action_ste[0].stc.offset;
+	apply->require_dep = 0;
+}
+
+static void hws_rule_move_init(struct mlx5hws_rule *rule,
+			       struct mlx5hws_rule_attr *attr)
+{
+	/* Save the old RTC IDs to be later used in match STE delete */
+	rule->resize_info->rtc_0 = rule->rtc_0;
+	rule->resize_info->rtc_1 = rule->rtc_1;
+	rule->resize_info->rule_idx = attr->rule_idx;
+
+	rule->rtc_0 = 0;
+	rule->rtc_1 = 0;
+
+	rule->pending_wqes = 0;
+	rule->action_ste_idx = -1;
+	rule->action_ste_selector = 0;
+	rule->status = MLX5HWS_RULE_STATUS_CREATING;
+	rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_WRITING;
+}
+
+bool mlx5hws_rule_move_in_progress(struct mlx5hws_rule *rule)
+{
+	return mlx5hws_matcher_is_in_resize(rule->matcher) &&
+	       rule->resize_info &&
+	       rule->resize_info->state != MLX5HWS_RULE_RESIZE_STATE_IDLE;
+}
+
+static int hws_rule_create_hws(struct mlx5hws_rule *rule,
+			       struct mlx5hws_rule_attr *attr,
+			       u8 mt_idx,
+			       u32 *match_param,
+			       u8 at_idx,
+			       struct mlx5hws_rule_action rule_actions[])
+{
+	struct mlx5hws_action_template *at = &rule->matcher->at[at_idx];
+	struct mlx5hws_match_template *mt = &rule->matcher->mt[mt_idx];
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	struct mlx5hws_send_ste_attr ste_attr = {0};
+	struct mlx5hws_send_ring_dep_wqe *dep_wqe;
+	struct mlx5hws_actions_wqe_setter *setter;
+	struct mlx5hws_actions_apply_data apply;
+	struct mlx5hws_send_engine *queue;
+	u8 total_stes, action_stes;
+	bool is_update;
+	int i, ret;
+
+	is_update = !match_param;
+
+	setter = &at->setters[at->num_of_action_stes];
+	total_stes = at->num_of_action_stes + (is_jumbo && !at->only_term);
+	action_stes = total_stes - 1;
+
+	queue = &ctx->send_queue[attr->queue_id];
+	if (unlikely(mlx5hws_send_engine_err(queue)))
+		return -EIO;
+
+	hws_rule_create_init(rule, &ste_attr, &apply, is_update);
+
+	/* Allocate dependent match WQE since rule might have dependent writes.
+	 * The queued dependent WQE can be later aborted or kept as a dependency.
+	 * dep_wqe buffers (ctrl, data) are also reused for all STE writes.
+	 */
+	dep_wqe = mlx5hws_send_add_new_dep_wqe(queue);
+	hws_rule_init_dep_wqe(dep_wqe, rule, mt, attr);
+
+	ste_attr.wqe_ctrl = &dep_wqe->wqe_ctrl;
+	ste_attr.wqe_data = &dep_wqe->wqe_data;
+	apply.wqe_ctrl = &dep_wqe->wqe_ctrl;
+	apply.wqe_data = (__force __be32 *)&dep_wqe->wqe_data;
+	apply.rule_action = rule_actions;
+	apply.queue = queue;
+
+	if (action_stes) {
+		/* Allocate action STEs for rules that need more than match STE */
+		if (!is_update) {
+			ret = hws_rule_alloc_action_ste(rule, attr);
+			if (ret) {
+				mlx5hws_err(ctx, "Failed to allocate action memory %d", ret);
+				mlx5hws_send_abort_new_dep_wqe(queue);
+				return ret;
+			}
+		}
+		/* Skip RX/TX based on the dep_wqe init */
+		ste_attr.rtc_0 = dep_wqe->rtc_0 ?
+				 matcher->action_ste[rule->action_ste_selector].rtc_0_id : 0;
+		ste_attr.rtc_1 = dep_wqe->rtc_1 ?
+				 matcher->action_ste[rule->action_ste_selector].rtc_1_id : 0;
+		/* Action STEs are written to a specific index last to first */
+		ste_attr.direct_index = rule->action_ste_idx + action_stes;
+		apply.next_direct_idx = ste_attr.direct_index;
+	} else {
+		apply.next_direct_idx = 0;
+	}
+
+	for (i = total_stes; i-- > 0;) {
+		mlx5hws_action_apply_setter(&apply, setter--, !i && is_jumbo);
+
+		if (i == 0) {
+			/* Handle last match STE.
+			 * For hash split / linear lookup RTCs, packets reaching any STE
+			 * will always match and perform the specified actions, which
+			 * makes the tag irrelevant.
+			 */
+			if (likely(!mlx5hws_matcher_is_insert_by_idx(matcher) && !is_update))
+				mlx5hws_definer_create_tag(match_param, mt->fc, mt->fc_sz,
+							   (u8 *)dep_wqe->wqe_data.action);
+			else if (is_update)
+				hws_rule_update_copy_tag(rule, &dep_wqe->wqe_data, is_jumbo);
+
+			/* Rule has dependent WQEs, match dep_wqe is queued */
+			if (action_stes || apply.require_dep)
+				break;
+
+			/* Rule has no dependencies, abort dep_wqe and send WQE now */
+			mlx5hws_send_abort_new_dep_wqe(queue);
+			ste_attr.wqe_tag_is_jumbo = is_jumbo;
+			ste_attr.send_attr.notify_hw = !attr->burst;
+			ste_attr.send_attr.user_data = dep_wqe->user_data;
+			ste_attr.send_attr.rule = dep_wqe->rule;
+			ste_attr.rtc_0 = dep_wqe->rtc_0;
+			ste_attr.rtc_1 = dep_wqe->rtc_1;
+			ste_attr.used_id_rtc_0 = &rule->rtc_0;
+			ste_attr.used_id_rtc_1 = &rule->rtc_1;
+			ste_attr.retry_rtc_0 = dep_wqe->retry_rtc_0;
+			ste_attr.retry_rtc_1 = dep_wqe->retry_rtc_1;
+			ste_attr.direct_index = dep_wqe->direct_index;
+		} else {
+			apply.next_direct_idx = --ste_attr.direct_index;
+		}
+
+		mlx5hws_send_ste(queue, &ste_attr);
+	}
+
+	/* Backup TAG on the rule for deletion and resize info for
+	 * moving rules to a new matcher, only after insertion.
+	 */
+	if (!is_update)
+		hws_rule_save_delete_info(rule, &ste_attr);
+
+	hws_rule_save_resize_info(rule, &ste_attr, is_update);
+	mlx5hws_send_engine_inc_rule(queue);
+
+	if (!attr->burst)
+		mlx5hws_send_all_dep_wqe(queue);
+
+	return 0;
+}
+
+static void hws_rule_destroy_failed_hws(struct mlx5hws_rule *rule,
+					struct mlx5hws_rule_attr *attr)
+{
+	struct mlx5hws_context *ctx = rule->matcher->tbl->ctx;
+	struct mlx5hws_send_engine *queue;
+
+	queue = &ctx->send_queue[attr->queue_id];
+
+	hws_rule_gen_comp(queue, rule, false,
+			  attr->user_data, MLX5HWS_RULE_STATUS_DELETED);
+
+	/* Rule failed now we can safely release action STEs */
+	mlx5hws_rule_free_action_ste(rule);
+
+	/* Clear complex tag */
+	hws_rule_clear_delete_info(rule);
+
+	/* Clear info that was saved for resizing */
+	mlx5hws_rule_clear_resize_info(rule);
+
+	/* If a rule that was indicated as burst (need to trigger HW) has failed
+	 * insertion we won't ring the HW as nothing is being written to the WQ.
+	 * In such case update the last WQE and ring the HW with that work
+	 */
+	if (attr->burst)
+		return;
+
+	mlx5hws_send_all_dep_wqe(queue);
+	mlx5hws_send_engine_flush_queue(queue);
+}
+
+static int hws_rule_destroy_hws(struct mlx5hws_rule *rule,
+				struct mlx5hws_rule_attr *attr)
+{
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(rule->matcher->mt);
+	struct mlx5hws_context *ctx = rule->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_wqe_gta_ctrl_seg wqe_ctrl = {0};
+	struct mlx5hws_send_ste_attr ste_attr = {0};
+	struct mlx5hws_send_engine *queue;
+
+	queue = &ctx->send_queue[attr->queue_id];
+
+	if (unlikely(mlx5hws_send_engine_err(queue))) {
+		hws_rule_destroy_failed_hws(rule, attr);
+		return 0;
+	}
+
+	/* Rule is not completed yet */
+	if (rule->status == MLX5HWS_RULE_STATUS_CREATING)
+		return -EBUSY;
+
+	/* Rule failed and doesn't require cleanup */
+	if (rule->status == MLX5HWS_RULE_STATUS_FAILED) {
+		hws_rule_destroy_failed_hws(rule, attr);
+		return 0;
+	}
+
+	if (rule->skip_delete) {
+		/* Rule shouldn't be deleted in HW.
+		 * Generate completion as if write succeeded, and we can
+		 * safely release action STEs and clear resize info.
+		 */
+		hws_rule_gen_comp(queue, rule, false,
+				  attr->user_data, MLX5HWS_RULE_STATUS_DELETED);
+
+		mlx5hws_rule_free_action_ste(rule);
+		mlx5hws_rule_clear_resize_info(rule);
+		return 0;
+	}
+
+	mlx5hws_send_engine_inc_rule(queue);
+
+	/* Send dependent WQE */
+	if (!attr->burst)
+		mlx5hws_send_all_dep_wqe(queue);
+
+	rule->status = MLX5HWS_RULE_STATUS_DELETING;
+
+	ste_attr.send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	ste_attr.send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	ste_attr.send_attr.len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+
+	ste_attr.send_attr.rule = rule;
+	ste_attr.send_attr.notify_hw = !attr->burst;
+	ste_attr.send_attr.user_data = attr->user_data;
+
+	ste_attr.rtc_0 = rule->rtc_0;
+	ste_attr.rtc_1 = rule->rtc_1;
+	ste_attr.used_id_rtc_0 = &rule->rtc_0;
+	ste_attr.used_id_rtc_1 = &rule->rtc_1;
+	ste_attr.wqe_ctrl = &wqe_ctrl;
+	ste_attr.wqe_tag_is_jumbo = is_jumbo;
+	ste_attr.gta_opcode = MLX5HWS_WQE_GTA_OP_DEACTIVATE;
+	if (unlikely(mlx5hws_matcher_is_insert_by_idx(matcher)))
+		ste_attr.direct_index = attr->rule_idx;
+
+	hws_rule_load_delete_info(rule, &ste_attr);
+	mlx5hws_send_ste(queue, &ste_attr);
+	hws_rule_clear_delete_info(rule);
+
+	return 0;
+}
+
+static int hws_rule_enqueue_precheck(struct mlx5hws_rule *rule,
+				     struct mlx5hws_rule_attr *attr)
+{
+	struct mlx5hws_context *ctx = rule->matcher->tbl->ctx;
+
+	if (unlikely(!attr->user_data))
+		return -EINVAL;
+
+	/* Check if there is room in queue */
+	if (unlikely(mlx5hws_send_engine_full(&ctx->send_queue[attr->queue_id])))
+		return -EBUSY;
+
+	return 0;
+}
+
+static int hws_rule_enqueue_precheck_move(struct mlx5hws_rule *rule,
+					  struct mlx5hws_rule_attr *attr)
+{
+	if (unlikely(rule->status != MLX5HWS_RULE_STATUS_CREATED))
+		return -EINVAL;
+
+	return hws_rule_enqueue_precheck(rule, attr);
+}
+
+static int hws_rule_enqueue_precheck_create(struct mlx5hws_rule *rule,
+					    struct mlx5hws_rule_attr *attr)
+{
+	if (unlikely(mlx5hws_matcher_is_in_resize(rule->matcher)))
+		/* Matcher in resize - new rules are not allowed */
+		return -EAGAIN;
+
+	return hws_rule_enqueue_precheck(rule, attr);
+}
+
+static int hws_rule_enqueue_precheck_update(struct mlx5hws_rule *rule,
+					    struct mlx5hws_rule_attr *attr)
+{
+	struct mlx5hws_matcher *matcher = rule->matcher;
+
+	if (unlikely(!mlx5hws_matcher_is_resizable(rule->matcher) &&
+		     !matcher->attr.optimize_using_rule_idx &&
+		     !mlx5hws_matcher_is_insert_by_idx(matcher))) {
+		return -EOPNOTSUPP;
+	}
+
+	if (unlikely(rule->status != MLX5HWS_RULE_STATUS_CREATED))
+		return -EBUSY;
+
+	return hws_rule_enqueue_precheck_create(rule, attr);
+}
+
+int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule,
+				 void *queue_ptr,
+				 void *user_data)
+{
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(rule->matcher->mt);
+	struct mlx5hws_wqe_gta_ctrl_seg empty_wqe_ctrl = {0};
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_send_engine *queue = queue_ptr;
+	struct mlx5hws_send_ste_attr ste_attr = {0};
+
+	mlx5hws_send_all_dep_wqe(queue);
+
+	rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_DELETING;
+
+	ste_attr.send_attr.fence = 0;
+	ste_attr.send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	ste_attr.send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	ste_attr.send_attr.len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+	ste_attr.send_attr.rule = rule;
+	ste_attr.send_attr.notify_hw = 1;
+	ste_attr.send_attr.user_data = user_data;
+	ste_attr.rtc_0 = rule->resize_info->rtc_0;
+	ste_attr.rtc_1 = rule->resize_info->rtc_1;
+	ste_attr.used_id_rtc_0 = &rule->resize_info->rtc_0;
+	ste_attr.used_id_rtc_1 = &rule->resize_info->rtc_1;
+	ste_attr.wqe_ctrl = &empty_wqe_ctrl;
+	ste_attr.wqe_tag_is_jumbo = is_jumbo;
+	ste_attr.gta_opcode = MLX5HWS_WQE_GTA_OP_DEACTIVATE;
+
+	if (unlikely(mlx5hws_matcher_is_insert_by_idx(matcher)))
+		ste_attr.direct_index = rule->resize_info->rule_idx;
+
+	hws_rule_load_delete_info(rule, &ste_attr);
+	mlx5hws_send_ste(queue, &ste_attr);
+
+	return 0;
+}
+
+int mlx5hws_rule_move_hws_add(struct mlx5hws_rule *rule,
+			      struct mlx5hws_rule_attr *attr)
+{
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(rule->matcher->mt);
+	struct mlx5hws_context *ctx = rule->matcher->tbl->ctx;
+	struct mlx5hws_matcher *matcher = rule->matcher;
+	struct mlx5hws_send_ste_attr ste_attr = {0};
+	struct mlx5hws_send_engine *queue;
+	int ret;
+
+	ret = hws_rule_enqueue_precheck_move(rule, attr);
+	if (unlikely(ret))
+		return ret;
+
+	queue = &ctx->send_queue[attr->queue_id];
+
+	ret = mlx5hws_send_engine_err(queue);
+	if (ret)
+		return ret;
+
+	hws_rule_move_init(rule, attr);
+	hws_rule_move_get_rtc(rule, &ste_attr);
+
+	ste_attr.send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	ste_attr.send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	ste_attr.send_attr.len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+	ste_attr.gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE;
+	ste_attr.wqe_tag_is_jumbo = is_jumbo;
+
+	ste_attr.send_attr.rule = rule;
+	ste_attr.send_attr.fence = 0;
+	ste_attr.send_attr.notify_hw = !attr->burst;
+	ste_attr.send_attr.user_data = attr->user_data;
+
+	ste_attr.used_id_rtc_0 = &rule->rtc_0;
+	ste_attr.used_id_rtc_1 = &rule->rtc_1;
+	ste_attr.wqe_ctrl = (struct mlx5hws_wqe_gta_ctrl_seg *)rule->resize_info->ctrl_seg;
+	ste_attr.wqe_data = (struct mlx5hws_wqe_gta_data_seg_ste *)rule->resize_info->data_seg;
+	ste_attr.direct_index = mlx5hws_matcher_is_insert_by_idx(matcher) ?
+				attr->rule_idx : 0;
+
+	mlx5hws_send_ste(queue, &ste_attr);
+	mlx5hws_send_engine_inc_rule(queue);
+
+	if (!attr->burst)
+		mlx5hws_send_all_dep_wqe(queue);
+
+	return 0;
+}
+
+int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
+			u8 mt_idx,
+			u32 *match_param,
+			u8 at_idx,
+			struct mlx5hws_rule_action rule_actions[],
+			struct mlx5hws_rule_attr *attr,
+			struct mlx5hws_rule *rule_handle)
+{
+	int ret;
+
+	rule_handle->matcher = matcher;
+
+	ret = hws_rule_enqueue_precheck_create(rule_handle, attr);
+	if (unlikely(ret))
+		return ret;
+
+	if (unlikely(!(matcher->num_of_mt >= mt_idx) ||
+		     !(matcher->num_of_at >= at_idx) ||
+		     !match_param)) {
+		pr_warn("HWS: Invalid rule creation parameters (MTs, ATs or match params)\n");
+		return -EINVAL;
+	}
+
+	ret = hws_rule_create_hws(rule_handle,
+				  attr,
+				  mt_idx,
+				  match_param,
+				  at_idx,
+				  rule_actions);
+
+	return ret;
+}
+
+int mlx5hws_rule_destroy(struct mlx5hws_rule *rule,
+			 struct mlx5hws_rule_attr *attr)
+{
+	int ret;
+
+	ret = hws_rule_enqueue_precheck(rule, attr);
+	if (unlikely(ret))
+		return -ret;
+
+	ret = hws_rule_destroy_hws(rule, attr);
+
+	return -ret;
+}
+
+int mlx5hws_rule_action_update(struct mlx5hws_rule *rule,
+			       u8 at_idx,
+			       struct mlx5hws_rule_action rule_actions[],
+			       struct mlx5hws_rule_attr *attr)
+{
+	int ret;
+
+	ret = hws_rule_enqueue_precheck_update(rule, attr);
+	if (unlikely(ret))
+		return -ret;
+
+	ret = hws_rule_create_hws(rule,
+				  attr,
+				  0,
+				  NULL,
+				  at_idx,
+				  rule_actions);
+
+	return -ret;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.h
new file mode 100644
index 000000000000..495cdd17e9f3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_RULE_H_
+#define MLX5HWS_RULE_H_
+
+enum {
+	MLX5HWS_STE_CTRL_SZ = 20,
+	MLX5HWS_ACTIONS_SZ = 12,
+	MLX5HWS_MATCH_TAG_SZ = 32,
+	MLX5HWS_JUMBO_TAG_SZ = 44,
+};
+
+enum mlx5hws_rule_status {
+	MLX5HWS_RULE_STATUS_UNKNOWN,
+	MLX5HWS_RULE_STATUS_CREATING,
+	MLX5HWS_RULE_STATUS_CREATED,
+	MLX5HWS_RULE_STATUS_DELETING,
+	MLX5HWS_RULE_STATUS_DELETED,
+	MLX5HWS_RULE_STATUS_FAILING,
+	MLX5HWS_RULE_STATUS_FAILED,
+};
+
+enum mlx5hws_rule_move_state {
+	MLX5HWS_RULE_RESIZE_STATE_IDLE,
+	MLX5HWS_RULE_RESIZE_STATE_WRITING,
+	MLX5HWS_RULE_RESIZE_STATE_DELETING,
+};
+
+enum mlx5hws_rule_jumbo_match_tag_offset {
+	MLX5HWS_RULE_JUMBO_MATCH_TAG_OFFSET_DW0 = 8,
+};
+
+struct mlx5hws_rule_match_tag {
+	union {
+		u8 jumbo[MLX5HWS_JUMBO_TAG_SZ];
+		struct {
+			u8 reserved[MLX5HWS_ACTIONS_SZ];
+			u8 match[MLX5HWS_MATCH_TAG_SZ];
+		};
+	};
+};
+
+struct mlx5hws_rule_resize_info {
+	struct mlx5hws_pool *action_ste_pool[2];
+	u32 rtc_0;
+	u32 rtc_1;
+	u32 rule_idx;
+	u8 state;
+	u8 max_stes;
+	u8 ctrl_seg[MLX5HWS_WQE_SZ_GTA_CTRL]; /* Ctrl segment of STE: 48 bytes */
+	u8 data_seg[MLX5HWS_WQE_SZ_GTA_DATA]; /* Data segment of STE: 64 bytes */
+};
+
+struct mlx5hws_rule {
+	struct mlx5hws_matcher *matcher;
+	union {
+		struct mlx5hws_rule_match_tag tag;
+		struct mlx5hws_rule_resize_info *resize_info;
+	};
+	u32 rtc_0; /* The RTC into which the STE was inserted */
+	u32 rtc_1; /* The RTC into which the STE was inserted */
+	int action_ste_idx; /* STE array index */
+	u8 status; /* enum mlx5hws_rule_status */
+	u8 action_ste_selector; /* For rule update - which action STE is in use */
+	u8 pending_wqes;
+	bool skip_delete; /* For complex rules - another rule with same tag
+			   * still exists, so don't actually delete this rule.
+			   */
+};
+
+void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule);
+
+int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule,
+				 void *queue, void *user_data);
+
+int mlx5hws_rule_move_hws_add(struct mlx5hws_rule *rule,
+			      struct mlx5hws_rule_attr *attr);
+
+bool mlx5hws_rule_move_in_progress(struct mlx5hws_rule *rule);
+
+void mlx5hws_rule_clear_resize_info(struct mlx5hws_rule *rule);
+
+#endif /* MLX5HWS_RULE_H_ */
-- 
cgit v1.3-3-g829e


From 74a778b4a63faef9ff02aad0d332b209835f93e1 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:36:51 +0300
Subject: net/mlx5: HWS, added definers handling

The Match Definer combines packet fields and a mask,
creating a key which can be used for packet matching
during steering flow processing.
This patch adds handling of definer objects in HWS.

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_definer.c       | 2146 ++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_definer.h       |  834 ++++++++
 2 files changed, 2980 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c
new file mode 100644
index 000000000000..3bdb5c90efff
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.c
@@ -0,0 +1,2146 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+/* Pattern tunnel Layer bits. */
+#define MLX5_FLOW_LAYER_VXLAN      BIT(12)
+#define MLX5_FLOW_LAYER_VXLAN_GPE  BIT(13)
+#define MLX5_FLOW_LAYER_GRE        BIT(14)
+#define MLX5_FLOW_LAYER_MPLS       BIT(15)
+
+/* Pattern tunnel Layer bits (continued). */
+#define MLX5_FLOW_LAYER_IPIP       BIT(23)
+#define MLX5_FLOW_LAYER_IPV6_ENCAP BIT(24)
+#define MLX5_FLOW_LAYER_NVGRE      BIT(25)
+#define MLX5_FLOW_LAYER_GENEVE     BIT(26)
+
+#define MLX5_FLOW_ITEM_FLEX_TUNNEL BIT_ULL(39)
+
+/* Tunnel Masks. */
+#define MLX5_FLOW_LAYER_TUNNEL \
+	(MLX5_FLOW_LAYER_VXLAN | MLX5_FLOW_LAYER_VXLAN_GPE | \
+	 MLX5_FLOW_LAYER_GRE | MLX5_FLOW_LAYER_NVGRE | MLX5_FLOW_LAYER_MPLS | \
+	 MLX5_FLOW_LAYER_IPIP | MLX5_FLOW_LAYER_IPV6_ENCAP | \
+	 MLX5_FLOW_LAYER_GENEVE | MLX5_FLOW_LAYER_GTP | \
+	 MLX5_FLOW_ITEM_FLEX_TUNNEL)
+
+#define GTP_PDU_SC	0x85
+#define BAD_PORT	0xBAD
+#define ETH_TYPE_IPV4_VXLAN	0x0800
+#define ETH_TYPE_IPV6_VXLAN	0x86DD
+#define UDP_GTPU_PORT	2152
+#define UDP_PORT_MPLS	6635
+#define UDP_GENEVE_PORT 6081
+#define UDP_ROCEV2_PORT	4791
+#define HWS_FLOW_LAYER_TUNNEL_NO_MPLS (MLX5_FLOW_LAYER_TUNNEL & ~MLX5_FLOW_LAYER_MPLS)
+
+#define STE_NO_VLAN	0x0
+#define STE_SVLAN	0x1
+#define STE_CVLAN	0x2
+#define STE_NO_L3	0x0
+#define STE_IPV4	0x1
+#define STE_IPV6	0x2
+#define STE_NO_L4	0x0
+#define STE_TCP		0x1
+#define STE_UDP		0x2
+#define STE_ICMP	0x3
+#define STE_ESP		0x3
+
+#define IPV4 0x4
+#define IPV6 0x6
+
+/* Setter function based on bit offset and mask, for 32bit DW */
+#define _HWS_SET32(p, v, byte_off, bit_off, mask) \
+	do { \
+		u32 _v = v; \
+		*((__be32 *)(p) + ((byte_off) / 4)) = \
+		cpu_to_be32((be32_to_cpu(*((__be32 *)(p) + \
+			     ((byte_off) / 4))) & \
+			     (~((mask) << (bit_off)))) | \
+			    (((_v) & (mask)) << \
+			      (bit_off))); \
+	} while (0)
+
+/* Setter function based on bit offset and mask, for unaligned 32bit DW */
+#define HWS_SET32(p, v, byte_off, bit_off, mask) \
+	do { \
+		if (unlikely((bit_off) < 0)) { \
+			u32 _bit_off = -1 * (bit_off); \
+			u32 second_dw_mask = (mask) & ((1 << _bit_off) - 1); \
+			_HWS_SET32(p, (v) >> _bit_off, byte_off, 0, (mask) >> _bit_off); \
+			_HWS_SET32(p, (v) & second_dw_mask, (byte_off) + DW_SIZE, \
+				    (bit_off) % BITS_IN_DW, second_dw_mask); \
+		} else { \
+			_HWS_SET32(p, v, byte_off, (bit_off), (mask)); \
+		} \
+	} while (0)
+
+/* Getter for up to aligned 32bit DW */
+#define HWS_GET32(p, byte_off, bit_off, mask) \
+	((be32_to_cpu(*((__be32 *)(p) + ((byte_off) / 4))) >> (bit_off)) & (mask))
+
+#define HWS_CALC_FNAME(field, inner) \
+	((inner) ? MLX5HWS_DEFINER_FNAME_##field##_I : \
+		   MLX5HWS_DEFINER_FNAME_##field##_O)
+
+#define HWS_GET_MATCH_PARAM(match_param, hdr) \
+	MLX5_GET(fte_match_param, match_param, hdr)
+
+#define HWS_IS_FLD_SET(match_param, hdr) \
+	(!!(HWS_GET_MATCH_PARAM(match_param, hdr)))
+
+#define HWS_IS_FLD_SET_DW_ARR(match_param, hdr, sz_in_bits) ({ \
+		BUILD_BUG_ON((sz_in_bits) % 32); \
+		u32 sz = sz_in_bits; \
+		u32 res = 0; \
+		u32 dw_off = __mlx5_dw_off(fte_match_param, hdr); \
+		while (!res && sz >= 32) { \
+			res = *((match_param) + (dw_off++)); \
+			sz -= 32; \
+		} \
+		res; \
+	})
+
+#define HWS_IS_FLD_SET_SZ(match_param, hdr, sz_in_bits) \
+	(((sz_in_bits) > 32) ? HWS_IS_FLD_SET_DW_ARR(match_param, hdr, sz_in_bits) : \
+			       !!(HWS_GET_MATCH_PARAM(match_param, hdr)))
+
+#define HWS_GET64_MATCH_PARAM(match_param, hdr) \
+	MLX5_GET64(fte_match_param, match_param, hdr)
+
+#define HWS_IS_FLD64_SET(match_param, hdr) \
+	(!!(HWS_GET64_MATCH_PARAM(match_param, hdr)))
+
+#define HWS_CALC_HDR_SRC(fc, s_hdr) \
+	do { \
+		(fc)->s_bit_mask = __mlx5_mask(fte_match_param, s_hdr); \
+		(fc)->s_bit_off = __mlx5_dw_bit_off(fte_match_param, s_hdr); \
+		(fc)->s_byte_off = MLX5_BYTE_OFF(fte_match_param, s_hdr); \
+	} while (0)
+
+#define HWS_CALC_HDR_DST(fc, d_hdr) \
+	do { \
+		(fc)->bit_mask = __mlx5_mask(definer_hl, d_hdr); \
+		(fc)->bit_off = __mlx5_dw_bit_off(definer_hl, d_hdr); \
+		(fc)->byte_off = MLX5_BYTE_OFF(definer_hl, d_hdr); \
+	} while (0)
+
+#define HWS_CALC_HDR(fc, s_hdr, d_hdr) \
+	do { \
+		HWS_CALC_HDR_SRC(fc, s_hdr); \
+		HWS_CALC_HDR_DST(fc, d_hdr); \
+		(fc)->tag_set = &hws_definer_generic_set; \
+	} while (0)
+
+#define HWS_SET_HDR(fc_arr, match_param, fname, s_hdr, d_hdr) \
+	do { \
+		if (HWS_IS_FLD_SET(match_param, s_hdr)) \
+			HWS_CALC_HDR(&(fc_arr)[MLX5HWS_DEFINER_FNAME_##fname], s_hdr, d_hdr); \
+	} while (0)
+
+struct mlx5hws_definer_sel_ctrl {
+	u8 allowed_full_dw; /* Full DW selectors cover all offsets */
+	u8 allowed_lim_dw;  /* Limited DW selectors cover offset < 64 */
+	u8 allowed_bytes;   /* Bytes selectors, up to offset 255 */
+	u8 used_full_dw;
+	u8 used_lim_dw;
+	u8 used_bytes;
+	u8 full_dw_selector[DW_SELECTORS];
+	u8 lim_dw_selector[DW_SELECTORS_LIMITED];
+	u8 byte_selector[BYTE_SELECTORS];
+};
+
+struct mlx5hws_definer_conv_data {
+	struct mlx5hws_context *ctx;
+	struct mlx5hws_definer_fc *fc;
+	/* enum mlx5hws_definer_match_flag */
+	u32 match_flags;
+};
+
+static void
+hws_definer_ones_set(struct mlx5hws_definer_fc *fc,
+		     void *match_param,
+		     u8 *tag)
+{
+	HWS_SET32(tag, -1, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_generic_set(struct mlx5hws_definer_fc *fc,
+			void *match_param,
+			u8 *tag)
+{
+	/* Can be optimized */
+	u32 val = HWS_GET32(match_param, fc->s_byte_off, fc->s_bit_off, fc->s_bit_mask);
+
+	HWS_SET32(tag, val, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_outer_vlan_type_set(struct mlx5hws_definer_fc *fc,
+				void *match_param,
+				u8 *tag)
+{
+	if (HWS_GET_MATCH_PARAM(match_param, outer_headers.cvlan_tag))
+		HWS_SET32(tag, STE_CVLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else if (HWS_GET_MATCH_PARAM(match_param, outer_headers.svlan_tag))
+		HWS_SET32(tag, STE_SVLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else
+		HWS_SET32(tag, STE_NO_VLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_inner_vlan_type_set(struct mlx5hws_definer_fc *fc,
+				void *match_param,
+				u8 *tag)
+{
+	if (HWS_GET_MATCH_PARAM(match_param, inner_headers.cvlan_tag))
+		HWS_SET32(tag, STE_CVLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else if (HWS_GET_MATCH_PARAM(match_param, inner_headers.svlan_tag))
+		HWS_SET32(tag, STE_SVLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else
+		HWS_SET32(tag, STE_NO_VLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_second_vlan_type_set(struct mlx5hws_definer_fc *fc,
+				 void *match_param,
+				 u8 *tag,
+				 bool inner)
+{
+	u32 second_cvlan_tag = inner ?
+		HWS_GET_MATCH_PARAM(match_param, misc_parameters.inner_second_cvlan_tag) :
+		HWS_GET_MATCH_PARAM(match_param, misc_parameters.outer_second_cvlan_tag);
+	u32 second_svlan_tag = inner ?
+		HWS_GET_MATCH_PARAM(match_param, misc_parameters.inner_second_svlan_tag) :
+		HWS_GET_MATCH_PARAM(match_param, misc_parameters.outer_second_svlan_tag);
+
+	if (second_cvlan_tag)
+		HWS_SET32(tag, STE_CVLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else if (second_svlan_tag)
+		HWS_SET32(tag, STE_SVLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else
+		HWS_SET32(tag, STE_NO_VLAN, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_inner_second_vlan_type_set(struct mlx5hws_definer_fc *fc,
+				       void *match_param,
+				       u8 *tag)
+{
+	hws_definer_second_vlan_type_set(fc, match_param, tag, true);
+}
+
+static void
+hws_definer_outer_second_vlan_type_set(struct mlx5hws_definer_fc *fc,
+				       void *match_param,
+				       u8 *tag)
+{
+	hws_definer_second_vlan_type_set(fc, match_param, tag, false);
+}
+
+static void hws_definer_icmp_dw1_set(struct mlx5hws_definer_fc *fc,
+				     void *match_param,
+				     u8 *tag)
+{
+	u32 code = HWS_GET_MATCH_PARAM(match_param, misc_parameters_3.icmp_code);
+	u32 type = HWS_GET_MATCH_PARAM(match_param, misc_parameters_3.icmp_type);
+	u32 dw = (type << __mlx5_dw_bit_off(header_icmp, type)) |
+		 (code << __mlx5_dw_bit_off(header_icmp, code));
+
+	HWS_SET32(tag, dw, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_icmpv6_dw1_set(struct mlx5hws_definer_fc *fc,
+			   void *match_param,
+			   u8 *tag)
+{
+	u32 code = HWS_GET_MATCH_PARAM(match_param, misc_parameters_3.icmpv6_code);
+	u32 type = HWS_GET_MATCH_PARAM(match_param, misc_parameters_3.icmpv6_type);
+	u32 dw = (type << __mlx5_dw_bit_off(header_icmp, type)) |
+		 (code << __mlx5_dw_bit_off(header_icmp, code));
+
+	HWS_SET32(tag, dw, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_l3_type_set(struct mlx5hws_definer_fc *fc,
+			void *match_param,
+			u8 *tag)
+{
+	u32 val = HWS_GET32(match_param, fc->s_byte_off, fc->s_bit_off, fc->s_bit_mask);
+
+	if (val == IPV4)
+		HWS_SET32(tag, STE_IPV4, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else if (val == IPV6)
+		HWS_SET32(tag, STE_IPV6, fc->byte_off, fc->bit_off, fc->bit_mask);
+	else
+		HWS_SET32(tag, STE_NO_L3, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_set_source_port_gvmi(struct mlx5hws_definer_fc *fc,
+				 void *match_param,
+				 u8 *tag,
+				 struct mlx5hws_context *peer_ctx)
+{
+	u16 source_port = HWS_GET_MATCH_PARAM(match_param, misc_parameters.source_port);
+	u16 vport_gvmi = 0;
+	int ret;
+
+	ret = mlx5hws_vport_get_gvmi(peer_ctx, source_port, &vport_gvmi);
+	if (ret) {
+		HWS_SET32(tag, BAD_PORT, fc->byte_off, fc->bit_off, fc->bit_mask);
+		mlx5hws_err(fc->ctx, "Vport 0x%x is disabled or invalid\n", source_port);
+		return;
+	}
+
+	if (vport_gvmi)
+		HWS_SET32(tag, vport_gvmi, fc->byte_off, fc->bit_off, fc->bit_mask);
+}
+
+static void
+hws_definer_set_source_gvmi_vhca_id(struct mlx5hws_definer_fc *fc,
+				    void *match_param,
+				    u8 *tag)
+__must_hold(&fc->ctx->ctrl_lock)
+{
+	int id = HWS_GET_MATCH_PARAM(match_param, misc_parameters.source_eswitch_owner_vhca_id);
+	struct mlx5hws_context *peer_ctx;
+
+	if (id == fc->ctx->caps->vhca_id)
+		peer_ctx = fc->ctx;
+	else
+		peer_ctx = xa_load(&fc->ctx->peer_ctx_xa, id);
+
+	if (!peer_ctx) {
+		HWS_SET32(tag, BAD_PORT, fc->byte_off, fc->bit_off, fc->bit_mask);
+		mlx5hws_err(fc->ctx, "Invalid vhca_id provided 0x%x\n", id);
+		return;
+	}
+
+	hws_definer_set_source_port_gvmi(fc, match_param, tag, peer_ctx);
+}
+
+static void
+hws_definer_set_source_gvmi(struct mlx5hws_definer_fc *fc,
+			    void *match_param,
+			    u8 *tag)
+{
+	hws_definer_set_source_port_gvmi(fc, match_param, tag, fc->ctx);
+}
+
+static struct mlx5hws_definer_fc *
+hws_definer_flex_parser_steering_ok_bits_handler(struct mlx5hws_definer_conv_data *cd,
+						 u8 parser_id)
+{
+	struct mlx5hws_definer_fc *fc;
+
+	switch (parser_id) {
+	case 0:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER0_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser0_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 1:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER1_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser1_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 2:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER2_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser2_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 3:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER3_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser3_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 4:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER4_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser4_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 5:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER5_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser5_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 6:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER6_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser6_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 7:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER7_OK];
+		HWS_CALC_HDR_DST(fc, oks1.flex_parser7_steering_ok);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	default:
+		mlx5hws_err(cd->ctx, "Unsupported flex parser steering ok index %u\n", parser_id);
+		return NULL;
+	}
+
+	return fc;
+}
+
+static struct mlx5hws_definer_fc *
+hws_definer_flex_parser_handler(struct mlx5hws_definer_conv_data *cd,
+				u8 parser_id)
+{
+	struct mlx5hws_definer_fc *fc;
+
+	switch (parser_id) {
+	case 0:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_0);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 1:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_1);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 2:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_2);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 3:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_3);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 4:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_4);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 5:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_5);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 6:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_6);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	case 7:
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7];
+		HWS_CALC_HDR_DST(fc, flex_parser.flex_parser_7);
+		fc->tag_set = &hws_definer_generic_set;
+		break;
+	default:
+		mlx5hws_err(cd->ctx, "Unsupported flex parser %u\n", parser_id);
+		return NULL;
+	}
+
+	return fc;
+}
+
+static struct mlx5hws_definer_fc *
+hws_definer_misc4_fields_handler(struct mlx5hws_definer_conv_data *cd,
+				 bool *parser_is_used,
+				 u32 id,
+				 u32 value)
+{
+	if (id || value) {
+		if (id >= HWS_NUM_OF_FLEX_PARSERS) {
+			mlx5hws_err(cd->ctx, "Unsupported parser id\n");
+			return NULL;
+		}
+
+		if (parser_is_used[id]) {
+			mlx5hws_err(cd->ctx, "Parser id have been used\n");
+			return NULL;
+		}
+	}
+
+	parser_is_used[id] = true;
+
+	return hws_definer_flex_parser_handler(cd, id);
+}
+
+static int
+hws_definer_check_match_flags(struct mlx5hws_definer_conv_data *cd)
+{
+	u32 flags;
+
+	flags = cd->match_flags & (MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN_GPE |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_0_1);
+	if (flags & (flags - 1))
+		goto err_conflict;
+
+	flags = cd->match_flags & (MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE_OPT_KEY |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_2);
+
+	if (flags & (flags - 1))
+		goto err_conflict;
+
+	flags = cd->match_flags & (MLX5HWS_DEFINER_MATCH_FLAG_TNL_MPLS_OVER_GRE |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_MPLS_OVER_UDP);
+	if (flags & (flags - 1))
+		goto err_conflict;
+
+	flags = cd->match_flags & (MLX5HWS_DEFINER_MATCH_FLAG_ICMPV4 |
+				   MLX5HWS_DEFINER_MATCH_FLAG_ICMPV6 |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TCP_O |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TCP_I);
+	if (flags & (flags - 1))
+		goto err_conflict;
+
+	return 0;
+
+err_conflict:
+	mlx5hws_err(cd->ctx, "Invalid definer fields combination\n");
+	return -EINVAL;
+}
+
+static int
+hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
+		       u32 *match_param)
+{
+	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	struct mlx5hws_definer_fc *fc = cd->fc;
+	struct mlx5hws_definer_fc *curr_fc;
+	u32 *s_ipv6, *d_ipv6;
+
+	if (HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type, 0x2) ||
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c2, 0xe) ||
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c4, 0x4)) {
+		mlx5hws_err(cd->ctx, "Unsupported outer parameters set\n");
+		return -EINVAL;
+	}
+
+	/* L2 Check ethertype */
+	HWS_SET_HDR(fc, match_param, ETH_TYPE_O,
+		    outer_headers.ethertype,
+		    eth_l2_outer.l3_ethertype);
+	/* L2 Check SMAC 47_16 */
+	HWS_SET_HDR(fc, match_param, ETH_SMAC_47_16_O,
+		    outer_headers.smac_47_16, eth_l2_src_outer.smac_47_16);
+	/* L2 Check SMAC 15_0 */
+	HWS_SET_HDR(fc, match_param, ETH_SMAC_15_0_O,
+		    outer_headers.smac_15_0, eth_l2_src_outer.smac_15_0);
+	/* L2 Check DMAC 47_16 */
+	HWS_SET_HDR(fc, match_param, ETH_DMAC_47_16_O,
+		    outer_headers.dmac_47_16, eth_l2_outer.dmac_47_16);
+	/* L2 Check DMAC 15_0 */
+	HWS_SET_HDR(fc, match_param, ETH_DMAC_15_0_O,
+		    outer_headers.dmac_15_0, eth_l2_outer.dmac_15_0);
+
+	/* L2 VLAN */
+	HWS_SET_HDR(fc, match_param, VLAN_FIRST_PRIO_O,
+		    outer_headers.first_prio, eth_l2_outer.first_priority);
+	HWS_SET_HDR(fc, match_param, VLAN_CFI_O,
+		    outer_headers.first_cfi, eth_l2_outer.first_cfi);
+	HWS_SET_HDR(fc, match_param, VLAN_ID_O,
+		    outer_headers.first_vid, eth_l2_outer.first_vlan_id);
+
+	/* L2 CVLAN and SVLAN */
+	if (HWS_GET_MATCH_PARAM(match_param, outer_headers.cvlan_tag) ||
+	    HWS_GET_MATCH_PARAM(match_param, outer_headers.svlan_tag)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VLAN_TYPE_O];
+		HWS_CALC_HDR_DST(curr_fc, eth_l2_outer.first_vlan_qualifier);
+		curr_fc->tag_set = &hws_definer_outer_vlan_type_set;
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+	}
+
+	/* L3 Check IP header */
+	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
+		    outer_headers.ip_protocol,
+		    eth_l3_outer.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_TTL_O,
+		    outer_headers.ttl_hoplimit,
+		    eth_l3_outer.time_to_live_hop_limit);
+
+	/* L3 Check IPv4/IPv6 addresses */
+	s_ipv6 = MLX5_ADDR_OF(fte_match_param, match_param,
+			      outer_headers.src_ipv4_src_ipv6.ipv6_layout);
+	d_ipv6 = MLX5_ADDR_OF(fte_match_param, match_param,
+			      outer_headers.dst_ipv4_dst_ipv6.ipv6_layout);
+
+	/* Assume IPv6 is used if ipv6 bits are set */
+	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
+	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+
+	if (is_s_ipv6) {
+		/* Handle IPv6 source address */
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
+			    ipv6_src_outer.ipv6_address_127_96);
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_95_64_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_95_64,
+			    ipv6_src_outer.ipv6_address_95_64);
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_63_32_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_63_32,
+			    ipv6_src_outer.ipv6_address_63_32);
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv6_src_outer.ipv6_address_31_0);
+	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_O,
+			    outer_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_outer.source_address);
+	}
+	if (is_d_ipv6) {
+		/* Handle IPv6 destination address */
+		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_O,
+			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
+			    ipv6_dst_outer.ipv6_address_127_96);
+		HWS_SET_HDR(fc, match_param, IPV6_DST_95_64_O,
+			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_95_64,
+			    ipv6_dst_outer.ipv6_address_95_64);
+		HWS_SET_HDR(fc, match_param, IPV6_DST_63_32_O,
+			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_63_32,
+			    ipv6_dst_outer.ipv6_address_63_32);
+		HWS_SET_HDR(fc, match_param, IPV6_DST_31_0_O,
+			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv6_dst_outer.ipv6_address_31_0);
+	} else {
+		/* Handle IPv4 destination address */
+		HWS_SET_HDR(fc, match_param, IPV4_DST_O,
+			    outer_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_outer.destination_address);
+	}
+
+	/* L4 Handle TCP/UDP */
+	HWS_SET_HDR(fc, match_param, L4_SPORT_O,
+		    outer_headers.tcp_sport, eth_l4_outer.source_port);
+	HWS_SET_HDR(fc, match_param, L4_DPORT_O,
+		    outer_headers.tcp_dport, eth_l4_outer.destination_port);
+	HWS_SET_HDR(fc, match_param, L4_SPORT_O,
+		    outer_headers.udp_sport, eth_l4_outer.source_port);
+	HWS_SET_HDR(fc, match_param, L4_DPORT_O,
+		    outer_headers.udp_dport, eth_l4_outer.destination_port);
+	HWS_SET_HDR(fc, match_param, TCP_FLAGS_O,
+		    outer_headers.tcp_flags, eth_l4_outer.tcp_flags);
+
+	/* L3 Handle DSCP, ECN and IHL  */
+	HWS_SET_HDR(fc, match_param, IP_DSCP_O,
+		    outer_headers.ip_dscp, eth_l3_outer.dscp);
+	HWS_SET_HDR(fc, match_param, IP_ECN_O,
+		    outer_headers.ip_ecn, eth_l3_outer.ecn);
+	HWS_SET_HDR(fc, match_param, IPV4_IHL_O,
+		    outer_headers.ipv4_ihl, eth_l3_outer.ihl);
+
+	/* Set IP fragmented bit */
+	if (HWS_IS_FLD_SET(match_param, outer_headers.frag)) {
+		smac_set = HWS_IS_FLD_SET(match_param, outer_headers.smac_15_0) ||
+				HWS_IS_FLD_SET(match_param, outer_headers.smac_47_16);
+		dmac_set = HWS_IS_FLD_SET(match_param, outer_headers.dmac_15_0) ||
+				HWS_IS_FLD_SET(match_param, outer_headers.dmac_47_16);
+		if (smac_set == dmac_set) {
+			HWS_SET_HDR(fc, match_param, IP_FRAG_O,
+				    outer_headers.frag, eth_l4_outer.ip_fragmented);
+		} else {
+			HWS_SET_HDR(fc, match_param, IP_FRAG_O,
+				    outer_headers.frag, eth_l2_src_outer.ip_fragmented);
+		}
+	}
+
+	/* L3_type set */
+	if (HWS_IS_FLD_SET(match_param, outer_headers.ip_version)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O];
+		HWS_CALC_HDR_DST(curr_fc, eth_l2_outer.l3_type);
+		curr_fc->tag_set = &hws_definer_l3_type_set;
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+		HWS_CALC_HDR_SRC(curr_fc, outer_headers.ip_version);
+	}
+
+	return 0;
+}
+
+static int
+hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
+		       u32 *match_param)
+{
+	bool is_s_ipv6, is_d_ipv6, smac_set, dmac_set;
+	struct mlx5hws_definer_fc *fc = cd->fc;
+	struct mlx5hws_definer_fc *curr_fc;
+	u32 *s_ipv6, *d_ipv6;
+
+	if (HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type, 0x2) ||
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c2, 0xe) ||
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c4, 0x4)) {
+		mlx5hws_err(cd->ctx, "Unsupported inner parameters set\n");
+		return -EINVAL;
+	}
+
+	/* L2 Check ethertype */
+	HWS_SET_HDR(fc, match_param, ETH_TYPE_I,
+		    inner_headers.ethertype,
+		    eth_l2_inner.l3_ethertype);
+	/* L2 Check SMAC 47_16 */
+	HWS_SET_HDR(fc, match_param, ETH_SMAC_47_16_I,
+		    inner_headers.smac_47_16, eth_l2_src_inner.smac_47_16);
+	/* L2 Check SMAC 15_0 */
+	HWS_SET_HDR(fc, match_param, ETH_SMAC_15_0_I,
+		    inner_headers.smac_15_0, eth_l2_src_inner.smac_15_0);
+	/* L2 Check DMAC 47_16 */
+	HWS_SET_HDR(fc, match_param, ETH_DMAC_47_16_I,
+		    inner_headers.dmac_47_16, eth_l2_inner.dmac_47_16);
+	/* L2 Check DMAC 15_0 */
+	HWS_SET_HDR(fc, match_param, ETH_DMAC_15_0_I,
+		    inner_headers.dmac_15_0, eth_l2_inner.dmac_15_0);
+
+	/* L2 VLAN */
+	HWS_SET_HDR(fc, match_param, VLAN_FIRST_PRIO_I,
+		    inner_headers.first_prio, eth_l2_inner.first_priority);
+	HWS_SET_HDR(fc, match_param, VLAN_CFI_I,
+		    inner_headers.first_cfi, eth_l2_inner.first_cfi);
+	HWS_SET_HDR(fc, match_param, VLAN_ID_I,
+		    inner_headers.first_vid, eth_l2_inner.first_vlan_id);
+
+	/* L2 CVLAN and SVLAN */
+	if (HWS_GET_MATCH_PARAM(match_param, inner_headers.cvlan_tag) ||
+	    HWS_GET_MATCH_PARAM(match_param, inner_headers.svlan_tag)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VLAN_TYPE_I];
+		HWS_CALC_HDR_DST(curr_fc, eth_l2_inner.first_vlan_qualifier);
+		curr_fc->tag_set = &hws_definer_inner_vlan_type_set;
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+	}
+	/* L3 Check IP header */
+	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_I,
+		    inner_headers.ip_protocol,
+		    eth_l3_inner.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_VERSION_I,
+		    inner_headers.ip_version,
+		    eth_l3_inner.ip_version);
+	HWS_SET_HDR(fc, match_param, IP_TTL_I,
+		    inner_headers.ttl_hoplimit,
+		    eth_l3_inner.time_to_live_hop_limit);
+
+	/* L3 Check IPv4/IPv6 addresses */
+	s_ipv6 = MLX5_ADDR_OF(fte_match_param, match_param,
+			      inner_headers.src_ipv4_src_ipv6.ipv6_layout);
+	d_ipv6 = MLX5_ADDR_OF(fte_match_param, match_param,
+			      inner_headers.dst_ipv4_dst_ipv6.ipv6_layout);
+
+	/* Assume IPv6 is used if ipv6 bits are set */
+	is_s_ipv6 = s_ipv6[0] || s_ipv6[1] || s_ipv6[2];
+	is_d_ipv6 = d_ipv6[0] || d_ipv6[1] || d_ipv6[2];
+
+	if (is_s_ipv6) {
+		/* Handle IPv6 source address */
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_127_96_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_127_96,
+			    ipv6_src_inner.ipv6_address_127_96);
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_95_64_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_95_64,
+			    ipv6_src_inner.ipv6_address_95_64);
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_63_32_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_63_32,
+			    ipv6_src_inner.ipv6_address_63_32);
+		HWS_SET_HDR(fc, match_param, IPV6_SRC_31_0_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv6_src_inner.ipv6_address_31_0);
+	} else {
+		/* Handle IPv4 source address */
+		HWS_SET_HDR(fc, match_param, IPV4_SRC_I,
+			    inner_headers.src_ipv4_src_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_inner.source_address);
+	}
+	if (is_d_ipv6) {
+		/* Handle IPv6 destination address */
+		HWS_SET_HDR(fc, match_param, IPV6_DST_127_96_I,
+			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_127_96,
+			    ipv6_dst_inner.ipv6_address_127_96);
+		HWS_SET_HDR(fc, match_param, IPV6_DST_95_64_I,
+			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_95_64,
+			    ipv6_dst_inner.ipv6_address_95_64);
+		HWS_SET_HDR(fc, match_param, IPV6_DST_63_32_I,
+			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_63_32,
+			    ipv6_dst_inner.ipv6_address_63_32);
+		HWS_SET_HDR(fc, match_param, IPV6_DST_31_0_I,
+			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv6_dst_inner.ipv6_address_31_0);
+	} else {
+		/* Handle IPv4 destination address */
+		HWS_SET_HDR(fc, match_param, IPV4_DST_I,
+			    inner_headers.dst_ipv4_dst_ipv6.ipv6_simple_layout.ipv6_31_0,
+			    ipv4_src_dest_inner.destination_address);
+	}
+
+	/* L4 Handle TCP/UDP */
+	HWS_SET_HDR(fc, match_param, L4_SPORT_I,
+		    inner_headers.tcp_sport, eth_l4_inner.source_port);
+	HWS_SET_HDR(fc, match_param, L4_DPORT_I,
+		    inner_headers.tcp_dport, eth_l4_inner.destination_port);
+	HWS_SET_HDR(fc, match_param, L4_SPORT_I,
+		    inner_headers.udp_sport, eth_l4_inner.source_port);
+	HWS_SET_HDR(fc, match_param, L4_DPORT_I,
+		    inner_headers.udp_dport, eth_l4_inner.destination_port);
+	HWS_SET_HDR(fc, match_param, TCP_FLAGS_I,
+		    inner_headers.tcp_flags, eth_l4_inner.tcp_flags);
+
+	/* L3 Handle DSCP, ECN and IHL  */
+	HWS_SET_HDR(fc, match_param, IP_DSCP_I,
+		    inner_headers.ip_dscp, eth_l3_inner.dscp);
+	HWS_SET_HDR(fc, match_param, IP_ECN_I,
+		    inner_headers.ip_ecn, eth_l3_inner.ecn);
+	HWS_SET_HDR(fc, match_param, IPV4_IHL_I,
+		    inner_headers.ipv4_ihl, eth_l3_inner.ihl);
+
+	/* Set IP fragmented bit */
+	if (HWS_IS_FLD_SET(match_param, inner_headers.frag)) {
+		if (HWS_IS_FLD_SET(match_param, misc_parameters.vxlan_vni)) {
+			HWS_SET_HDR(fc, match_param, IP_FRAG_I,
+				    inner_headers.frag, eth_l2_inner.ip_fragmented);
+		} else {
+			smac_set = HWS_IS_FLD_SET(match_param, inner_headers.smac_15_0) ||
+				   HWS_IS_FLD_SET(match_param, inner_headers.smac_47_16);
+			dmac_set = HWS_IS_FLD_SET(match_param, inner_headers.dmac_15_0) ||
+				   HWS_IS_FLD_SET(match_param, inner_headers.dmac_47_16);
+			if (smac_set == dmac_set) {
+				HWS_SET_HDR(fc, match_param, IP_FRAG_I,
+					    inner_headers.frag, eth_l4_inner.ip_fragmented);
+			} else {
+				HWS_SET_HDR(fc, match_param, IP_FRAG_I,
+					    inner_headers.frag, eth_l2_src_inner.ip_fragmented);
+			}
+		}
+	}
+
+	/* L3_type set */
+	if (HWS_IS_FLD_SET(match_param, inner_headers.ip_version)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I];
+		HWS_CALC_HDR_DST(curr_fc, eth_l2_inner.l3_type);
+		curr_fc->tag_set = &hws_definer_l3_type_set;
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+		HWS_CALC_HDR_SRC(curr_fc, inner_headers.ip_version);
+	}
+
+	return 0;
+}
+
+static int
+hws_definer_conv_misc(struct mlx5hws_definer_conv_data *cd,
+		      u32 *match_param)
+{
+	struct mlx5hws_cmd_query_caps *caps = cd->ctx->caps;
+	struct mlx5hws_definer_fc *fc = cd->fc;
+	struct mlx5hws_definer_fc *curr_fc;
+
+	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_1, 0x1) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_64, 0xc) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_d8, 0x6) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_e0, 0xc) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_100, 0xc) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_120, 0xa) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_140, 0x8) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters.bth_dst_qp) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters.bth_opcode) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters.inner_esp_spi) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters.outer_esp_spi) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters.source_vhca_port) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters.reserved_at_1a0, 0x60)) {
+		mlx5hws_err(cd->ctx, "Unsupported misc parameters set\n");
+		return -EINVAL;
+	}
+
+	/* Check GRE related fields */
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.gre_c_present)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GRE_C];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.gre_c_present,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_gre, gre_c_present);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_gre, gre_c_present);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.gre_k_present)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GRE_K];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.gre_k_present,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_gre, gre_k_present);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_gre, gre_k_present);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.gre_s_present)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GRE_S];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.gre_s_present,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_gre, gre_s_present);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_gre, gre_s_present);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.gre_protocol)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.gre_protocol,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_gre, gre_protocol);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_gre, gre_protocol);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.gre_key.key)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE |
+				   MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE_OPT_KEY;
+		HWS_SET_HDR(fc, match_param, GRE_OPT_KEY,
+			    misc_parameters.gre_key.key, tunnel_header.tunnel_header_2);
+	}
+
+	/* Check GENEVE related fields */
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.geneve_vni)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GENEVE_VNI];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.geneve_vni,
+			     tunnel_header.tunnel_header_1);
+		curr_fc->bit_mask = __mlx5_mask(header_geneve, vni);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_geneve, vni);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.geneve_opt_len)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GENEVE_OPT_LEN];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.geneve_opt_len,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_geneve, opt_len);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_geneve, opt_len);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.geneve_protocol_type)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GENEVE_PROTO];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.geneve_protocol_type,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_geneve, protocol_type);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_geneve, protocol_type);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters.geneve_oam)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GENEVE_OAM];
+		HWS_CALC_HDR(curr_fc,
+			     misc_parameters.geneve_oam,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_geneve, o_flag);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_geneve, o_flag);
+	}
+
+	HWS_SET_HDR(fc, match_param, SOURCE_QP,
+		    misc_parameters.source_sqn, source_qp_gvmi.source_qp);
+	HWS_SET_HDR(fc, match_param, IPV6_FLOW_LABEL_O,
+		    misc_parameters.outer_ipv6_flow_label, eth_l3_outer.flow_label);
+	HWS_SET_HDR(fc, match_param, IPV6_FLOW_LABEL_I,
+		    misc_parameters.inner_ipv6_flow_label, eth_l3_inner.flow_label);
+
+	/* L2 Second VLAN */
+	HWS_SET_HDR(fc, match_param, VLAN_SECOND_PRIO_O,
+		    misc_parameters.outer_second_prio, eth_l2_outer.second_priority);
+	HWS_SET_HDR(fc, match_param, VLAN_SECOND_PRIO_I,
+		    misc_parameters.inner_second_prio, eth_l2_inner.second_priority);
+	HWS_SET_HDR(fc, match_param, VLAN_SECOND_CFI_O,
+		    misc_parameters.outer_second_cfi, eth_l2_outer.second_cfi);
+	HWS_SET_HDR(fc, match_param, VLAN_SECOND_CFI_I,
+		    misc_parameters.inner_second_cfi, eth_l2_inner.second_cfi);
+	HWS_SET_HDR(fc, match_param, VLAN_SECOND_ID_O,
+		    misc_parameters.outer_second_vid, eth_l2_outer.second_vlan_id);
+	HWS_SET_HDR(fc, match_param, VLAN_SECOND_ID_I,
+		    misc_parameters.inner_second_vid, eth_l2_inner.second_vlan_id);
+
+	/* L2 Second CVLAN and SVLAN */
+	if (HWS_GET_MATCH_PARAM(match_param, misc_parameters.outer_second_cvlan_tag) ||
+	    HWS_GET_MATCH_PARAM(match_param, misc_parameters.outer_second_svlan_tag)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_O];
+		HWS_CALC_HDR_DST(curr_fc, eth_l2_outer.second_vlan_qualifier);
+		curr_fc->tag_set = &hws_definer_outer_second_vlan_type_set;
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+	}
+
+	if (HWS_GET_MATCH_PARAM(match_param, misc_parameters.inner_second_cvlan_tag) ||
+	    HWS_GET_MATCH_PARAM(match_param, misc_parameters.inner_second_svlan_tag)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_I];
+		HWS_CALC_HDR_DST(curr_fc, eth_l2_inner.second_vlan_qualifier);
+		curr_fc->tag_set = &hws_definer_inner_second_vlan_type_set;
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+	}
+
+	/* VXLAN VNI  */
+	if (HWS_GET_MATCH_PARAM(match_param, misc_parameters.vxlan_vni)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN;
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VXLAN_VNI];
+		HWS_CALC_HDR(curr_fc, misc_parameters.vxlan_vni, tunnel_header.tunnel_header_1);
+		curr_fc->bit_mask = __mlx5_mask(header_vxlan, vni);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_vxlan, vni);
+	}
+
+	/* Flex protocol steering ok bits */
+	if (HWS_GET_MATCH_PARAM(match_param, misc_parameters.geneve_tlv_option_0_exist)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE;
+
+		if (!caps->flex_parser_ok_bits_supp) {
+			mlx5hws_err(cd->ctx, "Unsupported flex_parser_ok_bits_supp capability\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = hws_definer_flex_parser_steering_ok_bits_handler(
+				cd, caps->flex_parser_id_geneve_tlv_option_0);
+		if (!curr_fc)
+			return -EINVAL;
+
+		HWS_CALC_HDR_SRC(fc, misc_parameters.geneve_tlv_option_0_exist);
+	}
+
+	if (HWS_GET_MATCH_PARAM(match_param, misc_parameters.source_port)) {
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_SOURCE_GVMI];
+		HWS_CALC_HDR_DST(curr_fc, source_qp_gvmi.source_gvmi);
+		curr_fc->tag_mask_set = &hws_definer_ones_set;
+		curr_fc->tag_set = HWS_IS_FLD_SET(match_param,
+						  misc_parameters.source_eswitch_owner_vhca_id) ?
+						  &hws_definer_set_source_gvmi_vhca_id :
+						  &hws_definer_set_source_gvmi;
+	} else {
+		if (HWS_IS_FLD_SET(match_param, misc_parameters.source_eswitch_owner_vhca_id)) {
+			mlx5hws_err(cd->ctx,
+				    "Unsupported source_eswitch_owner_vhca_id field usage\n");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static int
+hws_definer_conv_misc2(struct mlx5hws_definer_conv_data *cd,
+		       u32 *match_param)
+{
+	struct mlx5hws_cmd_query_caps *caps = cd->ctx->caps;
+	struct mlx5hws_definer_fc *fc = cd->fc;
+	struct mlx5hws_definer_fc *curr_fc;
+
+	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1a0, 0x8) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1b8, 0x8) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1c0, 0x40) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_2.macsec_syndrome) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_2.ipsec_syndrome)) {
+		mlx5hws_err(cd->ctx, "Unsupported misc2 parameters set\n");
+		return -EINVAL;
+	}
+
+	HWS_SET_HDR(fc, match_param, MPLS0_O,
+		    misc_parameters_2.outer_first_mpls, mpls_outer.mpls0_label);
+	HWS_SET_HDR(fc, match_param, MPLS0_I,
+		    misc_parameters_2.inner_first_mpls, mpls_inner.mpls0_label);
+	HWS_SET_HDR(fc, match_param, REG_0,
+		    misc_parameters_2.metadata_reg_c_0, registers.register_c_0);
+	HWS_SET_HDR(fc, match_param, REG_1,
+		    misc_parameters_2.metadata_reg_c_1, registers.register_c_1);
+	HWS_SET_HDR(fc, match_param, REG_2,
+		    misc_parameters_2.metadata_reg_c_2, registers.register_c_2);
+	HWS_SET_HDR(fc, match_param, REG_3,
+		    misc_parameters_2.metadata_reg_c_3, registers.register_c_3);
+	HWS_SET_HDR(fc, match_param, REG_4,
+		    misc_parameters_2.metadata_reg_c_4, registers.register_c_4);
+	HWS_SET_HDR(fc, match_param, REG_5,
+		    misc_parameters_2.metadata_reg_c_5, registers.register_c_5);
+	HWS_SET_HDR(fc, match_param, REG_6,
+		    misc_parameters_2.metadata_reg_c_6, registers.register_c_6);
+	HWS_SET_HDR(fc, match_param, REG_7,
+		    misc_parameters_2.metadata_reg_c_7, registers.register_c_7);
+	HWS_SET_HDR(fc, match_param, REG_A,
+		    misc_parameters_2.metadata_reg_a, metadata.general_purpose);
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_2.outer_first_mpls_over_gre)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_MPLS_OVER_GRE;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported misc2 first mpls over gre parameters set\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = hws_definer_flex_parser_handler(cd, caps->flex_parser_id_mpls_over_gre);
+		if (!curr_fc)
+			return -EINVAL;
+
+		HWS_CALC_HDR_SRC(fc, misc_parameters_2.outer_first_mpls_over_gre);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_2.outer_first_mpls_over_udp)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_MPLS_OVER_UDP;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported misc2 first mpls over udp parameters set\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = hws_definer_flex_parser_handler(cd, caps->flex_parser_id_mpls_over_udp);
+		if (!curr_fc)
+			return -EINVAL;
+
+		HWS_CALC_HDR_SRC(fc, misc_parameters_2.outer_first_mpls_over_udp);
+	}
+
+	return 0;
+}
+
+static int
+hws_definer_conv_misc3(struct mlx5hws_definer_conv_data *cd, u32 *match_param)
+{
+	struct mlx5hws_cmd_query_caps *caps = cd->ctx->caps;
+	struct mlx5hws_definer_fc *fc = cd->fc;
+	struct mlx5hws_definer_fc *curr_fc;
+	bool vxlan_gpe_flex_parser_enabled;
+
+	/* Check reserved and unsupported fields */
+	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_3.reserved_at_80, 0x8) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_3.reserved_at_b0, 0x10) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_3.reserved_at_170, 0x10) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_3.reserved_at_1e0, 0x20)) {
+		mlx5hws_err(cd->ctx, "Unsupported misc3 parameters set\n");
+		return -EINVAL;
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.inner_tcp_seq_num) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_3.inner_tcp_ack_num)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TCP_I;
+		HWS_SET_HDR(fc, match_param, TCP_SEQ_NUM,
+			    misc_parameters_3.inner_tcp_seq_num, tcp_icmp.tcp_seq);
+		HWS_SET_HDR(fc, match_param, TCP_ACK_NUM,
+			    misc_parameters_3.inner_tcp_ack_num, tcp_icmp.tcp_ack);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.outer_tcp_seq_num) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_3.outer_tcp_ack_num)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TCP_O;
+		HWS_SET_HDR(fc, match_param, TCP_SEQ_NUM,
+			    misc_parameters_3.outer_tcp_seq_num, tcp_icmp.tcp_seq);
+		HWS_SET_HDR(fc, match_param, TCP_ACK_NUM,
+			    misc_parameters_3.outer_tcp_ack_num, tcp_icmp.tcp_ack);
+	}
+
+	vxlan_gpe_flex_parser_enabled = caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.outer_vxlan_gpe_vni)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN_GPE;
+
+		if (!vxlan_gpe_flex_parser_enabled) {
+			mlx5hws_err(cd->ctx, "Unsupported VXLAN GPE flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VXLAN_GPE_VNI];
+		HWS_CALC_HDR(curr_fc, misc_parameters_3.outer_vxlan_gpe_vni,
+			     tunnel_header.tunnel_header_1);
+		curr_fc->bit_mask = __mlx5_mask(header_vxlan_gpe, vni);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_vxlan_gpe, vni);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.outer_vxlan_gpe_next_protocol)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN_GPE;
+
+		if (!vxlan_gpe_flex_parser_enabled) {
+			mlx5hws_err(cd->ctx, "Unsupported VXLAN GPE flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VXLAN_GPE_PROTO];
+		HWS_CALC_HDR(curr_fc, misc_parameters_3.outer_vxlan_gpe_next_protocol,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->byte_off += MLX5_BYTE_OFF(header_vxlan_gpe, protocol);
+		curr_fc->bit_mask = __mlx5_mask(header_vxlan_gpe, protocol);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_vxlan_gpe, protocol);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.outer_vxlan_gpe_flags)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN_GPE;
+
+		if (!vxlan_gpe_flex_parser_enabled) {
+			mlx5hws_err(cd->ctx, "Unsupported VXLAN GPE flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_VXLAN_GPE_FLAGS];
+		HWS_CALC_HDR(curr_fc, misc_parameters_3.outer_vxlan_gpe_flags,
+			     tunnel_header.tunnel_header_0);
+		curr_fc->bit_mask = __mlx5_mask(header_vxlan_gpe, flags);
+		curr_fc->bit_off = __mlx5_dw_bit_off(header_vxlan_gpe, flags);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.icmp_header_data) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_3.icmp_type) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_3.icmp_code)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_ICMPV4;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported ICMPv4 flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		HWS_SET_HDR(fc, match_param, ICMP_DW3,
+			    misc_parameters_3.icmp_header_data, tcp_icmp.icmp_dw3);
+
+		if (HWS_IS_FLD_SET(match_param, misc_parameters_3.icmp_type) ||
+		    HWS_IS_FLD_SET(match_param, misc_parameters_3.icmp_code)) {
+			curr_fc = &fc[MLX5HWS_DEFINER_FNAME_ICMP_DW1];
+			HWS_CALC_HDR_DST(curr_fc, tcp_icmp.icmp_dw1);
+			curr_fc->tag_set = &hws_definer_icmp_dw1_set;
+		}
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.icmpv6_header_data) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_3.icmpv6_type) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_3.icmpv6_code)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_ICMPV6;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported ICMPv6 parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		HWS_SET_HDR(fc, match_param, ICMP_DW3,
+			    misc_parameters_3.icmpv6_header_data, tcp_icmp.icmp_dw3);
+
+		if (HWS_IS_FLD_SET(match_param, misc_parameters_3.icmpv6_type) ||
+		    HWS_IS_FLD_SET(match_param, misc_parameters_3.icmpv6_code)) {
+			curr_fc = &fc[MLX5HWS_DEFINER_FNAME_ICMP_DW1];
+			HWS_CALC_HDR_DST(curr_fc, tcp_icmp.icmp_dw1);
+			curr_fc->tag_set = &hws_definer_icmpv6_dw1_set;
+		}
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.geneve_tlv_option_0_data)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE;
+
+		curr_fc =
+			hws_definer_flex_parser_handler(cd,
+							caps->flex_parser_id_geneve_tlv_option_0);
+		if (!curr_fc)
+			return -EINVAL;
+
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.geneve_tlv_option_0_data);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.gtpu_teid)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_GTPU_TEID_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported GTPU TEID flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_GTP_TEID];
+		fc->tag_set = &hws_definer_generic_set;
+		fc->bit_mask = __mlx5_mask(header_gtp, teid);
+		fc->byte_off = caps->format_select_gtpu_dw_1 * DW_SIZE;
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.gtpu_teid);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.gtpu_msg_type)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_GTPU_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported GTPU flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_GTP_MSG_TYPE];
+		fc->tag_set = &hws_definer_generic_set;
+		fc->bit_mask = __mlx5_mask(header_gtp, msg_type);
+		fc->bit_off = __mlx5_dw_bit_off(header_gtp, msg_type);
+		fc->byte_off = caps->format_select_gtpu_dw_0 * DW_SIZE;
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.gtpu_msg_type);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.gtpu_msg_flags)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_GTPU_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported GTPU flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		fc = &cd->fc[MLX5HWS_DEFINER_FNAME_GTP_MSG_TYPE];
+		fc->tag_set = &hws_definer_generic_set;
+		fc->bit_mask = __mlx5_mask(header_gtp, msg_flags);
+		fc->bit_off = __mlx5_dw_bit_off(header_gtp, msg_flags);
+		fc->byte_off = caps->format_select_gtpu_dw_0 * DW_SIZE;
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.gtpu_msg_flags);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.gtpu_dw_2)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_GTPU_DW_2_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported GTPU DW2 flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GTPU_DW2];
+		curr_fc->tag_set = &hws_definer_generic_set;
+		curr_fc->bit_mask = -1;
+		curr_fc->byte_off = caps->format_select_gtpu_dw_2 * DW_SIZE;
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.gtpu_dw_2);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.gtpu_first_ext_dw_0)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_GTPU_FIRST_EXT_DW_0_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported GTPU first EXT DW0 flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GTPU_FIRST_EXT_DW0];
+		curr_fc->tag_set = &hws_definer_generic_set;
+		curr_fc->bit_mask = -1;
+		curr_fc->byte_off = caps->format_select_gtpu_ext_dw_0 * DW_SIZE;
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.gtpu_first_ext_dw_0);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_3.gtpu_dw_0)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU;
+
+		if (!(caps->flex_protocols & MLX5_FLEX_PARSER_GTPU_DW_0_ENABLED)) {
+			mlx5hws_err(cd->ctx, "Unsupported GTPU DW0 flex parser\n");
+			return -EOPNOTSUPP;
+		}
+
+		curr_fc = &fc[MLX5HWS_DEFINER_FNAME_GTPU_DW0];
+		curr_fc->tag_set = &hws_definer_generic_set;
+		curr_fc->bit_mask = -1;
+		curr_fc->byte_off = caps->format_select_gtpu_dw_0 * DW_SIZE;
+		HWS_CALC_HDR_SRC(fc, misc_parameters_3.gtpu_dw_0);
+	}
+
+	return 0;
+}
+
+static int
+hws_definer_conv_misc4(struct mlx5hws_definer_conv_data *cd,
+		       u32 *match_param)
+{
+	bool parser_is_used[HWS_NUM_OF_FLEX_PARSERS] = {};
+	struct mlx5hws_definer_fc *fc;
+	u32 id, value;
+
+	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_4.reserved_at_100, 0x100)) {
+		mlx5hws_err(cd->ctx, "Unsupported misc4 parameters set\n");
+		return -EINVAL;
+	}
+
+	id = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_id_0);
+	value = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_value_0);
+	fc = hws_definer_misc4_fields_handler(cd, parser_is_used, id, value);
+	if (!fc)
+		return -EINVAL;
+
+	HWS_CALC_HDR_SRC(fc, misc_parameters_4.prog_sample_field_value_0);
+
+	id = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_id_1);
+	value = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_value_1);
+	fc = hws_definer_misc4_fields_handler(cd, parser_is_used, id, value);
+	if (!fc)
+		return -EINVAL;
+
+	HWS_CALC_HDR_SRC(fc, misc_parameters_4.prog_sample_field_value_1);
+
+	id = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_id_2);
+	value = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_value_2);
+	fc = hws_definer_misc4_fields_handler(cd, parser_is_used, id, value);
+	if (!fc)
+		return -EINVAL;
+
+	HWS_CALC_HDR_SRC(fc, misc_parameters_4.prog_sample_field_value_2);
+
+	id = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_id_3);
+	value = HWS_GET_MATCH_PARAM(match_param, misc_parameters_4.prog_sample_field_value_3);
+	fc = hws_definer_misc4_fields_handler(cd, parser_is_used, id, value);
+	if (!fc)
+		return -EINVAL;
+
+	HWS_CALC_HDR_SRC(fc, misc_parameters_4.prog_sample_field_value_3);
+
+	return 0;
+}
+
+static int
+hws_definer_conv_misc5(struct mlx5hws_definer_conv_data *cd,
+		       u32 *match_param)
+{
+	struct mlx5hws_definer_fc *fc = cd->fc;
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_5.macsec_tag_0) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_5.macsec_tag_1) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_5.macsec_tag_2) ||
+	    HWS_IS_FLD_SET(match_param, misc_parameters_5.macsec_tag_3) ||
+	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_5.reserved_at_100, 0x100)) {
+		mlx5hws_err(cd->ctx, "Unsupported misc5 parameters set\n");
+		return -EINVAL;
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_5.tunnel_header_0)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_0_1;
+		HWS_SET_HDR(fc, match_param, TNL_HDR_0,
+			    misc_parameters_5.tunnel_header_0, tunnel_header.tunnel_header_0);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_5.tunnel_header_1)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_0_1;
+		HWS_SET_HDR(fc, match_param, TNL_HDR_1,
+			    misc_parameters_5.tunnel_header_1, tunnel_header.tunnel_header_1);
+	}
+
+	if (HWS_IS_FLD_SET(match_param, misc_parameters_5.tunnel_header_2)) {
+		cd->match_flags |= MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_2;
+		HWS_SET_HDR(fc, match_param, TNL_HDR_2,
+			    misc_parameters_5.tunnel_header_2, tunnel_header.tunnel_header_2);
+	}
+
+	HWS_SET_HDR(fc, match_param, TNL_HDR_3,
+		    misc_parameters_5.tunnel_header_3, tunnel_header.tunnel_header_3);
+
+	return 0;
+}
+
+static int hws_definer_get_fc_size(struct mlx5hws_definer_fc *fc)
+{
+	u32 fc_sz = 0;
+	int i;
+
+	/* For empty matcher, ZERO_SIZE_PTR is returned */
+	if (fc == ZERO_SIZE_PTR)
+		return 0;
+
+	for (i = 0; i < MLX5HWS_DEFINER_FNAME_MAX; i++)
+		if (fc[i].tag_set)
+			fc_sz++;
+	return fc_sz;
+}
+
+static struct mlx5hws_definer_fc *
+hws_definer_alloc_compressed_fc(struct mlx5hws_definer_fc *fc)
+{
+	struct mlx5hws_definer_fc *compressed_fc = NULL;
+	u32 definer_size = hws_definer_get_fc_size(fc);
+	u32 fc_sz = 0;
+	int i;
+
+	compressed_fc = kcalloc(definer_size, sizeof(*compressed_fc), GFP_KERNEL);
+	if (!compressed_fc)
+		return NULL;
+
+	/* For empty matcher, ZERO_SIZE_PTR is returned */
+	if (!definer_size)
+		return compressed_fc;
+
+	for (i = 0, fc_sz = 0; i < MLX5HWS_DEFINER_FNAME_MAX; i++) {
+		if (!fc[i].tag_set)
+			continue;
+
+		fc[i].fname = i;
+		memcpy(&compressed_fc[fc_sz++], &fc[i], sizeof(*compressed_fc));
+	}
+
+	return compressed_fc;
+}
+
+static void
+hws_definer_set_hl(u8 *hl, struct mlx5hws_definer_fc *fc)
+{
+	int i;
+
+	/* nothing to do for empty matcher */
+	if (fc == ZERO_SIZE_PTR)
+		return;
+
+	for (i = 0; i < MLX5HWS_DEFINER_FNAME_MAX; i++) {
+		if (!fc[i].tag_set)
+			continue;
+
+		HWS_SET32(hl, -1, fc[i].byte_off, fc[i].bit_off, fc[i].bit_mask);
+	}
+}
+
+static struct mlx5hws_definer_fc *
+hws_definer_alloc_fc(struct mlx5hws_context *ctx,
+		     size_t len)
+{
+	struct mlx5hws_definer_fc *fc;
+	int i;
+
+	fc = kcalloc(len, sizeof(*fc), GFP_KERNEL);
+	if (!fc)
+		return NULL;
+
+	for (i = 0; i < len; i++)
+		fc[i].ctx = ctx;
+
+	return fc;
+}
+
+static int
+hws_definer_conv_match_params_to_hl(struct mlx5hws_context *ctx,
+				    struct mlx5hws_match_template *mt,
+				    u8 *hl)
+{
+	struct mlx5hws_definer_conv_data cd = {0};
+	struct mlx5hws_definer_fc *fc;
+	int ret;
+
+	fc = hws_definer_alloc_fc(ctx, MLX5HWS_DEFINER_FNAME_MAX);
+	if (!fc)
+		return -ENOMEM;
+
+	cd.fc = fc;
+	cd.ctx = ctx;
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC6) {
+		mlx5hws_err(ctx, "Unsupported match_criteria_enable provided\n");
+		ret = -EOPNOTSUPP;
+		goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_OUTER) {
+		ret = hws_definer_conv_outer(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_INNER) {
+		ret = hws_definer_conv_inner(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC) {
+		ret = hws_definer_conv_misc(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2) {
+		ret = hws_definer_conv_misc2(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC3) {
+		ret = hws_definer_conv_misc3(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC4) {
+		ret = hws_definer_conv_misc4(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (mt->match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC5) {
+		ret = hws_definer_conv_misc5(&cd, mt->match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	/* Check there is no conflicted fields set together */
+	ret = hws_definer_check_match_flags(&cd);
+	if (ret)
+		goto err_free_fc;
+
+	/* Allocate fc array on mt */
+	mt->fc = hws_definer_alloc_compressed_fc(fc);
+	if (!mt->fc) {
+		mlx5hws_err(ctx,
+			    "Convert match params: failed to set field copy to match template\n");
+		ret = -ENOMEM;
+		goto err_free_fc;
+	}
+	mt->fc_sz = hws_definer_get_fc_size(fc);
+
+	/* Fill in headers layout */
+	hws_definer_set_hl(hl, fc);
+
+	kfree(fc);
+	return 0;
+
+err_free_fc:
+	kfree(fc);
+	return ret;
+}
+
+struct mlx5hws_definer_fc *
+mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx,
+						   u8 match_criteria_enable,
+						   u32 *match_param,
+						   int *fc_sz)
+{
+	struct mlx5hws_definer_fc *compressed_fc = NULL;
+	struct mlx5hws_definer_conv_data cd = {0};
+	struct mlx5hws_definer_fc *fc;
+	int ret;
+
+	fc = hws_definer_alloc_fc(ctx, MLX5HWS_DEFINER_FNAME_MAX);
+	if (!fc)
+		return NULL;
+
+	cd.fc = fc;
+	cd.ctx = ctx;
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_OUTER) {
+		ret = hws_definer_conv_outer(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_INNER) {
+		ret = hws_definer_conv_inner(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC) {
+		ret = hws_definer_conv_misc(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2) {
+		ret = hws_definer_conv_misc2(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC3) {
+		ret = hws_definer_conv_misc3(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC4) {
+		ret = hws_definer_conv_misc4(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	if (match_criteria_enable & MLX5HWS_DEFINER_MATCH_CRITERIA_MISC5) {
+		ret = hws_definer_conv_misc5(&cd, match_param);
+		if (ret)
+			goto err_free_fc;
+	}
+
+	/* Allocate fc array on mt */
+	compressed_fc = hws_definer_alloc_compressed_fc(fc);
+	if (!compressed_fc) {
+		mlx5hws_err(ctx,
+			    "Convert to compressed fc: failed to set field copy to match template\n");
+		goto err_free_fc;
+	}
+	*fc_sz = hws_definer_get_fc_size(fc);
+
+err_free_fc:
+	kfree(fc);
+	return compressed_fc;
+}
+
+static int
+hws_definer_find_byte_in_tag(struct mlx5hws_definer *definer,
+			     u32 hl_byte_off,
+			     u32 *tag_byte_off)
+{
+	int i, dw_to_scan;
+	u8 byte_offset;
+
+	/* Avoid accessing unused DW selectors */
+	dw_to_scan = mlx5hws_definer_is_jumbo(definer) ?
+		DW_SELECTORS : DW_SELECTORS_MATCH;
+
+	/* Add offset since each DW covers multiple BYTEs */
+	byte_offset = hl_byte_off % DW_SIZE;
+	for (i = 0; i < dw_to_scan; i++) {
+		if (definer->dw_selector[i] == hl_byte_off / DW_SIZE) {
+			*tag_byte_off = byte_offset + DW_SIZE * (DW_SELECTORS - i - 1);
+			return 0;
+		}
+	}
+
+	/* Add offset to skip DWs in definer */
+	byte_offset = DW_SIZE * DW_SELECTORS;
+	/* Iterate in reverse since the code uses bytes from 7 -> 0 */
+	for (i = BYTE_SELECTORS; i-- > 0 ;) {
+		if (definer->byte_selector[i] == hl_byte_off) {
+			*tag_byte_off = byte_offset + (BYTE_SELECTORS - i - 1);
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int
+hws_definer_fc_bind(struct mlx5hws_definer *definer,
+		    struct mlx5hws_definer_fc *fc,
+		    u32 fc_sz)
+{
+	u32 tag_offset = 0;
+	int ret, byte_diff;
+	u32 i;
+
+	for (i = 0; i < fc_sz; i++) {
+		/* Map header layout byte offset to byte offset in tag */
+		ret = hws_definer_find_byte_in_tag(definer, fc->byte_off, &tag_offset);
+		if (ret)
+			return ret;
+
+		/* Move setter based on the location in the definer */
+		byte_diff = fc->byte_off % DW_SIZE - tag_offset % DW_SIZE;
+		fc->bit_off = fc->bit_off + byte_diff * BITS_IN_BYTE;
+
+		/* Update offset in headers layout to offset in tag */
+		fc->byte_off = tag_offset;
+		fc++;
+	}
+
+	return 0;
+}
+
+static bool
+hws_definer_best_hl_fit_recu(struct mlx5hws_definer_sel_ctrl *ctrl,
+			     u32 cur_dw,
+			     u32 *data)
+{
+	u8 bytes_set;
+	int byte_idx;
+	bool ret;
+	int i;
+
+	/* Reached end, nothing left to do */
+	if (cur_dw == MLX5_ST_SZ_DW(definer_hl))
+		return true;
+
+	/* No data set, can skip to next DW */
+	while (!*data) {
+		cur_dw++;
+		data++;
+
+		/* Reached end, nothing left to do */
+		if (cur_dw == MLX5_ST_SZ_DW(definer_hl))
+			return true;
+	}
+
+	/* Used all DW selectors and Byte selectors, no possible solution */
+	if (ctrl->allowed_full_dw == ctrl->used_full_dw &&
+	    ctrl->allowed_lim_dw == ctrl->used_lim_dw &&
+	    ctrl->allowed_bytes == ctrl->used_bytes)
+		return false;
+
+	/* Try to use limited DW selectors */
+	if (ctrl->allowed_lim_dw > ctrl->used_lim_dw && cur_dw < 64) {
+		ctrl->lim_dw_selector[ctrl->used_lim_dw++] = cur_dw;
+
+		ret = hws_definer_best_hl_fit_recu(ctrl, cur_dw + 1, data + 1);
+		if (ret)
+			return ret;
+
+		ctrl->lim_dw_selector[--ctrl->used_lim_dw] = 0;
+	}
+
+	/* Try to use DW selectors */
+	if (ctrl->allowed_full_dw > ctrl->used_full_dw) {
+		ctrl->full_dw_selector[ctrl->used_full_dw++] = cur_dw;
+
+		ret = hws_definer_best_hl_fit_recu(ctrl, cur_dw + 1, data + 1);
+		if (ret)
+			return ret;
+
+		ctrl->full_dw_selector[--ctrl->used_full_dw] = 0;
+	}
+
+	/* No byte selector for offset bigger than 255 */
+	if (cur_dw * DW_SIZE > 255)
+		return false;
+
+	bytes_set = !!(0x000000ff & *data) +
+		    !!(0x0000ff00 & *data) +
+		    !!(0x00ff0000 & *data) +
+		    !!(0xff000000 & *data);
+
+	/* Check if there are enough byte selectors left */
+	if (bytes_set + ctrl->used_bytes > ctrl->allowed_bytes)
+		return false;
+
+	/* Try to use Byte selectors */
+	for (i = 0; i < DW_SIZE; i++)
+		if ((0xff000000 >> (i * BITS_IN_BYTE)) & be32_to_cpu((__force __be32)*data)) {
+			/* Use byte selectors high to low */
+			byte_idx = ctrl->allowed_bytes - ctrl->used_bytes - 1;
+			ctrl->byte_selector[byte_idx] = cur_dw * DW_SIZE + i;
+			ctrl->used_bytes++;
+		}
+
+	ret = hws_definer_best_hl_fit_recu(ctrl, cur_dw + 1, data + 1);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < DW_SIZE; i++)
+		if ((0xff << (i * BITS_IN_BYTE)) & be32_to_cpu((__force __be32)*data)) {
+			ctrl->used_bytes--;
+			byte_idx = ctrl->allowed_bytes - ctrl->used_bytes - 1;
+			ctrl->byte_selector[byte_idx] = 0;
+		}
+
+	return false;
+}
+
+static void
+hws_definer_copy_sel_ctrl(struct mlx5hws_definer_sel_ctrl *ctrl,
+			  struct mlx5hws_definer *definer)
+{
+	memcpy(definer->byte_selector, ctrl->byte_selector, ctrl->allowed_bytes);
+	memcpy(definer->dw_selector, ctrl->full_dw_selector, ctrl->allowed_full_dw);
+	memcpy(definer->dw_selector + ctrl->allowed_full_dw,
+	       ctrl->lim_dw_selector, ctrl->allowed_lim_dw);
+}
+
+static int
+hws_definer_find_best_match_fit(struct mlx5hws_context *ctx,
+				struct mlx5hws_definer *definer,
+				u8 *hl)
+{
+	struct mlx5hws_definer_sel_ctrl ctrl = {0};
+	bool found;
+
+	/* Try to create a match definer */
+	ctrl.allowed_full_dw = DW_SELECTORS_MATCH;
+	ctrl.allowed_lim_dw = 0;
+	ctrl.allowed_bytes = BYTE_SELECTORS;
+
+	found = hws_definer_best_hl_fit_recu(&ctrl, 0, (u32 *)hl);
+	if (found) {
+		hws_definer_copy_sel_ctrl(&ctrl, definer);
+		definer->type = MLX5HWS_DEFINER_TYPE_MATCH;
+		return 0;
+	}
+
+	/* Try to create a full/limited jumbo definer */
+	ctrl.allowed_full_dw = ctx->caps->full_dw_jumbo_support ? DW_SELECTORS :
+								  DW_SELECTORS_MATCH;
+	ctrl.allowed_lim_dw = ctx->caps->full_dw_jumbo_support ? 0 :
+								 DW_SELECTORS_LIMITED;
+	ctrl.allowed_bytes = BYTE_SELECTORS;
+
+	found = hws_definer_best_hl_fit_recu(&ctrl, 0, (u32 *)hl);
+	if (found) {
+		hws_definer_copy_sel_ctrl(&ctrl, definer);
+		definer->type = MLX5HWS_DEFINER_TYPE_JUMBO;
+		return 0;
+	}
+
+	return E2BIG;
+}
+
+static void
+hws_definer_create_tag_mask(u32 *match_param,
+			    struct mlx5hws_definer_fc *fc,
+			    u32 fc_sz,
+			    u8 *tag)
+{
+	u32 i;
+
+	for (i = 0; i < fc_sz; i++) {
+		if (fc->tag_mask_set)
+			fc->tag_mask_set(fc, match_param, tag);
+		else
+			fc->tag_set(fc, match_param, tag);
+		fc++;
+	}
+}
+
+void mlx5hws_definer_create_tag(u32 *match_param,
+				struct mlx5hws_definer_fc *fc,
+				u32 fc_sz,
+				u8 *tag)
+{
+	u32 i;
+
+	for (i = 0; i < fc_sz; i++) {
+		fc->tag_set(fc, match_param, tag);
+		fc++;
+	}
+}
+
+int mlx5hws_definer_get_id(struct mlx5hws_definer *definer)
+{
+	return definer->obj_id;
+}
+
+int mlx5hws_definer_compare(struct mlx5hws_definer *definer_a,
+			    struct mlx5hws_definer *definer_b)
+{
+	int i;
+
+	/* Future: Optimize by comparing selectors with valid mask only */
+	for (i = 0; i < BYTE_SELECTORS; i++)
+		if (definer_a->byte_selector[i] != definer_b->byte_selector[i])
+			return 1;
+
+	for (i = 0; i < DW_SELECTORS; i++)
+		if (definer_a->dw_selector[i] != definer_b->dw_selector[i])
+			return 1;
+
+	for (i = 0; i < MLX5HWS_JUMBO_TAG_SZ; i++)
+		if (definer_a->mask.jumbo[i] != definer_b->mask.jumbo[i])
+			return 1;
+
+	return 0;
+}
+
+int
+mlx5hws_definer_calc_layout(struct mlx5hws_context *ctx,
+			    struct mlx5hws_match_template *mt,
+			    struct mlx5hws_definer *match_definer)
+{
+	u8 *match_hl;
+	int ret;
+
+	/* Union header-layout (hl) is used for creating a single definer
+	 * field layout used with different bitmasks for hash and match.
+	 */
+	match_hl = kzalloc(MLX5_ST_SZ_BYTES(definer_hl), GFP_KERNEL);
+	if (!match_hl)
+		return -ENOMEM;
+
+	/* Convert all mt items to header layout (hl)
+	 * and allocate the match and range field copy array (fc & fcr).
+	 */
+	ret = hws_definer_conv_match_params_to_hl(ctx, mt, match_hl);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to convert items to header layout\n");
+		goto free_fc;
+	}
+
+	/* Find the match definer layout for header layout match union */
+	ret = hws_definer_find_best_match_fit(ctx, match_definer, match_hl);
+	if (ret) {
+		if (ret == E2BIG)
+			mlx5hws_dbg(ctx,
+				    "Failed to create match definer from header layout - E2BIG\n");
+		else
+			mlx5hws_err(ctx,
+				    "Failed to create match definer from header layout (%d)\n",
+				    ret);
+		goto free_fc;
+	}
+
+	kfree(match_hl);
+	return 0;
+
+free_fc:
+	kfree(mt->fc);
+
+	kfree(match_hl);
+	return ret;
+}
+
+int mlx5hws_definer_init_cache(struct mlx5hws_definer_cache **cache)
+{
+	struct mlx5hws_definer_cache *new_cache;
+
+	new_cache = kzalloc(sizeof(*new_cache), GFP_KERNEL);
+	if (!new_cache)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&new_cache->list_head);
+	*cache = new_cache;
+
+	return 0;
+}
+
+void mlx5hws_definer_uninit_cache(struct mlx5hws_definer_cache *cache)
+{
+	kfree(cache);
+}
+
+int mlx5hws_definer_get_obj(struct mlx5hws_context *ctx,
+			    struct mlx5hws_definer *definer)
+{
+	struct mlx5hws_definer_cache *cache = ctx->definer_cache;
+	struct mlx5hws_cmd_definer_create_attr def_attr = {0};
+	struct mlx5hws_definer_cache_item *cached_definer;
+	u32 obj_id;
+	int ret;
+
+	/* Search definer cache for requested definer */
+	list_for_each_entry(cached_definer, &cache->list_head, list_node) {
+		if (mlx5hws_definer_compare(&cached_definer->definer, definer))
+			continue;
+
+		/* Reuse definer and set LRU (move to be first in the list) */
+		list_del_init(&cached_definer->list_node);
+		list_add(&cached_definer->list_node, &cache->list_head);
+		cached_definer->refcount++;
+		return cached_definer->definer.obj_id;
+	}
+
+	/* Allocate and create definer based on the bitmask tag */
+	def_attr.match_mask = definer->mask.jumbo;
+	def_attr.dw_selector = definer->dw_selector;
+	def_attr.byte_selector = definer->byte_selector;
+
+	ret = mlx5hws_cmd_definer_create(ctx->mdev, &def_attr, &obj_id);
+	if (ret)
+		return -1;
+
+	cached_definer = kzalloc(sizeof(*cached_definer), GFP_KERNEL);
+	if (!cached_definer)
+		goto free_definer_obj;
+
+	memcpy(&cached_definer->definer, definer, sizeof(*definer));
+	cached_definer->definer.obj_id = obj_id;
+	cached_definer->refcount = 1;
+	list_add(&cached_definer->list_node, &cache->list_head);
+
+	return obj_id;
+
+free_definer_obj:
+	mlx5hws_cmd_definer_destroy(ctx->mdev, obj_id);
+	return -1;
+}
+
+static void
+hws_definer_put_obj(struct mlx5hws_context *ctx, u32 obj_id)
+{
+	struct mlx5hws_definer_cache_item *cached_definer;
+
+	list_for_each_entry(cached_definer, &ctx->definer_cache->list_head, list_node) {
+		if (cached_definer->definer.obj_id != obj_id)
+			continue;
+
+		/* Object found */
+		if (--cached_definer->refcount)
+			return;
+
+		list_del_init(&cached_definer->list_node);
+		mlx5hws_cmd_definer_destroy(ctx->mdev, cached_definer->definer.obj_id);
+		kfree(cached_definer);
+		return;
+	}
+
+	/* Programming error, object must be part of cache */
+	pr_warn("HWS: failed putting definer object\n");
+}
+
+static struct mlx5hws_definer *
+hws_definer_alloc(struct mlx5hws_context *ctx,
+		  struct mlx5hws_definer_fc *fc,
+		  int fc_sz,
+		  u32 *match_param,
+		  struct mlx5hws_definer *layout,
+		  bool bind_fc)
+{
+	struct mlx5hws_definer *definer;
+	int ret;
+
+	definer = kmemdup(layout, sizeof(*definer), GFP_KERNEL);
+	if (!definer)
+		return NULL;
+
+	/* Align field copy array based on given layout */
+	if (bind_fc) {
+		ret = hws_definer_fc_bind(definer, fc, fc_sz);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to bind field copy to definer\n");
+			goto free_definer;
+		}
+	}
+
+	/* Create the tag mask used for definer creation */
+	hws_definer_create_tag_mask(match_param, fc, fc_sz, definer->mask.jumbo);
+
+	ret = mlx5hws_definer_get_obj(ctx, definer);
+	if (ret < 0)
+		goto free_definer;
+
+	definer->obj_id = ret;
+	return definer;
+
+free_definer:
+	kfree(definer);
+	return NULL;
+}
+
+void mlx5hws_definer_free(struct mlx5hws_context *ctx,
+			  struct mlx5hws_definer *definer)
+{
+	hws_definer_put_obj(ctx, definer->obj_id);
+	kfree(definer);
+}
+
+static int
+hws_definer_mt_match_init(struct mlx5hws_context *ctx,
+			  struct mlx5hws_match_template *mt,
+			  struct mlx5hws_definer *match_layout)
+{
+	/* Create mandatory match definer */
+	mt->definer = hws_definer_alloc(ctx,
+					mt->fc,
+					mt->fc_sz,
+					mt->match_param,
+					match_layout,
+					true);
+	if (!mt->definer) {
+		mlx5hws_err(ctx, "Failed to create match definer\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+hws_definer_mt_match_uninit(struct mlx5hws_context *ctx,
+			    struct mlx5hws_match_template *mt)
+{
+	mlx5hws_definer_free(ctx, mt->definer);
+}
+
+int mlx5hws_definer_mt_init(struct mlx5hws_context *ctx,
+			    struct mlx5hws_match_template *mt)
+{
+	struct mlx5hws_definer match_layout = {0};
+	int ret;
+
+	ret = mlx5hws_definer_calc_layout(ctx, mt, &match_layout);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to calculate matcher definer layout\n");
+		return ret;
+	}
+
+	/* Calculate definers needed for exact match */
+	ret = hws_definer_mt_match_init(ctx, mt, &match_layout);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to init match definers\n");
+		goto free_fc;
+	}
+
+	return 0;
+
+free_fc:
+	kfree(mt->fc);
+	return ret;
+}
+
+void mlx5hws_definer_mt_uninit(struct mlx5hws_context *ctx,
+			       struct mlx5hws_match_template *mt)
+{
+	hws_definer_mt_match_uninit(ctx, mt);
+	kfree(mt->fc);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.h
new file mode 100644
index 000000000000..2f6a7df4021c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_definer.h
@@ -0,0 +1,834 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_DEFINER_H_
+#define MLX5HWS_DEFINER_H_
+
+/* Max available selecotrs */
+#define DW_SELECTORS 9
+#define BYTE_SELECTORS 8
+
+/* Selectors based on match TAG */
+#define DW_SELECTORS_MATCH 6
+#define DW_SELECTORS_LIMITED 3
+
+/* Selectors based on range TAG */
+#define DW_SELECTORS_RANGE 2
+#define BYTE_SELECTORS_RANGE 8
+
+#define HWS_NUM_OF_FLEX_PARSERS 8
+
+enum mlx5hws_definer_fname {
+	MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_O,
+	MLX5HWS_DEFINER_FNAME_ETH_SMAC_47_16_I,
+	MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_O,
+	MLX5HWS_DEFINER_FNAME_ETH_SMAC_15_0_I,
+	MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_O,
+	MLX5HWS_DEFINER_FNAME_ETH_DMAC_47_16_I,
+	MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_O,
+	MLX5HWS_DEFINER_FNAME_ETH_DMAC_15_0_I,
+	MLX5HWS_DEFINER_FNAME_ETH_TYPE_O,
+	MLX5HWS_DEFINER_FNAME_ETH_TYPE_I,
+	MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_O,
+	MLX5HWS_DEFINER_FNAME_ETH_L3_TYPE_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_TYPE_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_TYPE_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_FIRST_PRIO_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_FIRST_PRIO_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_CFI_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_CFI_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_ID_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_ID_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_TYPE_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_PRIO_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_PRIO_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_CFI_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_CFI_I,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_ID_O,
+	MLX5HWS_DEFINER_FNAME_VLAN_SECOND_ID_I,
+	MLX5HWS_DEFINER_FNAME_IPV4_IHL_O,
+	MLX5HWS_DEFINER_FNAME_IPV4_IHL_I,
+	MLX5HWS_DEFINER_FNAME_IP_DSCP_O,
+	MLX5HWS_DEFINER_FNAME_IP_DSCP_I,
+	MLX5HWS_DEFINER_FNAME_IP_ECN_O,
+	MLX5HWS_DEFINER_FNAME_IP_ECN_I,
+	MLX5HWS_DEFINER_FNAME_IP_TTL_O,
+	MLX5HWS_DEFINER_FNAME_IP_TTL_I,
+	MLX5HWS_DEFINER_FNAME_IPV4_DST_O,
+	MLX5HWS_DEFINER_FNAME_IPV4_DST_I,
+	MLX5HWS_DEFINER_FNAME_IPV4_SRC_O,
+	MLX5HWS_DEFINER_FNAME_IPV4_SRC_I,
+	MLX5HWS_DEFINER_FNAME_IP_VERSION_O,
+	MLX5HWS_DEFINER_FNAME_IP_VERSION_I,
+	MLX5HWS_DEFINER_FNAME_IP_FRAG_O,
+	MLX5HWS_DEFINER_FNAME_IP_FRAG_I,
+	MLX5HWS_DEFINER_FNAME_IP_LEN_O,
+	MLX5HWS_DEFINER_FNAME_IP_LEN_I,
+	MLX5HWS_DEFINER_FNAME_IP_TOS_O,
+	MLX5HWS_DEFINER_FNAME_IP_TOS_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_FLOW_LABEL_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_FLOW_LABEL_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_127_96_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_95_64_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_63_32_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_DST_31_0_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_O,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_127_96_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_95_64_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_63_32_I,
+	MLX5HWS_DEFINER_FNAME_IPV6_SRC_31_0_I,
+	MLX5HWS_DEFINER_FNAME_IP_PROTOCOL_O,
+	MLX5HWS_DEFINER_FNAME_IP_PROTOCOL_I,
+	MLX5HWS_DEFINER_FNAME_L4_SPORT_O,
+	MLX5HWS_DEFINER_FNAME_L4_SPORT_I,
+	MLX5HWS_DEFINER_FNAME_L4_DPORT_O,
+	MLX5HWS_DEFINER_FNAME_L4_DPORT_I,
+	MLX5HWS_DEFINER_FNAME_TCP_FLAGS_I,
+	MLX5HWS_DEFINER_FNAME_TCP_FLAGS_O,
+	MLX5HWS_DEFINER_FNAME_TCP_SEQ_NUM,
+	MLX5HWS_DEFINER_FNAME_TCP_ACK_NUM,
+	MLX5HWS_DEFINER_FNAME_GTP_TEID,
+	MLX5HWS_DEFINER_FNAME_GTP_MSG_TYPE,
+	MLX5HWS_DEFINER_FNAME_GTP_EXT_FLAG,
+	MLX5HWS_DEFINER_FNAME_GTP_NEXT_EXT_HDR,
+	MLX5HWS_DEFINER_FNAME_GTP_EXT_HDR_PDU,
+	MLX5HWS_DEFINER_FNAME_GTP_EXT_HDR_QFI,
+	MLX5HWS_DEFINER_FNAME_GTPU_DW0,
+	MLX5HWS_DEFINER_FNAME_GTPU_FIRST_EXT_DW0,
+	MLX5HWS_DEFINER_FNAME_GTPU_DW2,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_0,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_1,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_2,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_3,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_4,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_5,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_6,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER_7,
+	MLX5HWS_DEFINER_FNAME_VPORT_REG_C_0,
+	MLX5HWS_DEFINER_FNAME_VXLAN_FLAGS,
+	MLX5HWS_DEFINER_FNAME_VXLAN_VNI,
+	MLX5HWS_DEFINER_FNAME_VXLAN_GPE_FLAGS,
+	MLX5HWS_DEFINER_FNAME_VXLAN_GPE_RSVD0,
+	MLX5HWS_DEFINER_FNAME_VXLAN_GPE_PROTO,
+	MLX5HWS_DEFINER_FNAME_VXLAN_GPE_VNI,
+	MLX5HWS_DEFINER_FNAME_VXLAN_GPE_RSVD1,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_LEN,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OAM,
+	MLX5HWS_DEFINER_FNAME_GENEVE_PROTO,
+	MLX5HWS_DEFINER_FNAME_GENEVE_VNI,
+	MLX5HWS_DEFINER_FNAME_SOURCE_QP,
+	MLX5HWS_DEFINER_FNAME_SOURCE_GVMI,
+	MLX5HWS_DEFINER_FNAME_REG_0,
+	MLX5HWS_DEFINER_FNAME_REG_1,
+	MLX5HWS_DEFINER_FNAME_REG_2,
+	MLX5HWS_DEFINER_FNAME_REG_3,
+	MLX5HWS_DEFINER_FNAME_REG_4,
+	MLX5HWS_DEFINER_FNAME_REG_5,
+	MLX5HWS_DEFINER_FNAME_REG_6,
+	MLX5HWS_DEFINER_FNAME_REG_7,
+	MLX5HWS_DEFINER_FNAME_REG_8,
+	MLX5HWS_DEFINER_FNAME_REG_9,
+	MLX5HWS_DEFINER_FNAME_REG_10,
+	MLX5HWS_DEFINER_FNAME_REG_11,
+	MLX5HWS_DEFINER_FNAME_REG_A,
+	MLX5HWS_DEFINER_FNAME_REG_B,
+	MLX5HWS_DEFINER_FNAME_GRE_KEY_PRESENT,
+	MLX5HWS_DEFINER_FNAME_GRE_C,
+	MLX5HWS_DEFINER_FNAME_GRE_K,
+	MLX5HWS_DEFINER_FNAME_GRE_S,
+	MLX5HWS_DEFINER_FNAME_GRE_PROTOCOL,
+	MLX5HWS_DEFINER_FNAME_GRE_OPT_KEY,
+	MLX5HWS_DEFINER_FNAME_GRE_OPT_SEQ,
+	MLX5HWS_DEFINER_FNAME_GRE_OPT_CHECKSUM,
+	MLX5HWS_DEFINER_FNAME_INTEGRITY_O,
+	MLX5HWS_DEFINER_FNAME_INTEGRITY_I,
+	MLX5HWS_DEFINER_FNAME_ICMP_DW1,
+	MLX5HWS_DEFINER_FNAME_ICMP_DW2,
+	MLX5HWS_DEFINER_FNAME_ICMP_DW3,
+	MLX5HWS_DEFINER_FNAME_IPSEC_SPI,
+	MLX5HWS_DEFINER_FNAME_IPSEC_SEQUENCE_NUMBER,
+	MLX5HWS_DEFINER_FNAME_IPSEC_SYNDROME,
+	MLX5HWS_DEFINER_FNAME_MPLS0_O,
+	MLX5HWS_DEFINER_FNAME_MPLS1_O,
+	MLX5HWS_DEFINER_FNAME_MPLS2_O,
+	MLX5HWS_DEFINER_FNAME_MPLS3_O,
+	MLX5HWS_DEFINER_FNAME_MPLS4_O,
+	MLX5HWS_DEFINER_FNAME_MPLS0_I,
+	MLX5HWS_DEFINER_FNAME_MPLS1_I,
+	MLX5HWS_DEFINER_FNAME_MPLS2_I,
+	MLX5HWS_DEFINER_FNAME_MPLS3_I,
+	MLX5HWS_DEFINER_FNAME_MPLS4_I,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER0_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER1_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER2_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER3_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER4_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER5_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER6_OK,
+	MLX5HWS_DEFINER_FNAME_FLEX_PARSER7_OK,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS0_O,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS1_O,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS2_O,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS3_O,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS4_O,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS0_I,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS1_I,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS2_I,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS3_I,
+	MLX5HWS_DEFINER_FNAME_OKS2_MPLS4_I,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_0,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_1,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_2,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_3,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_4,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_5,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_6,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_OK_7,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_0,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_1,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_2,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_3,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_4,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_5,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_6,
+	MLX5HWS_DEFINER_FNAME_GENEVE_OPT_DW_7,
+	MLX5HWS_DEFINER_FNAME_IB_L4_OPCODE,
+	MLX5HWS_DEFINER_FNAME_IB_L4_QPN,
+	MLX5HWS_DEFINER_FNAME_IB_L4_A,
+	MLX5HWS_DEFINER_FNAME_RANDOM_NUM,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L2_O,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L2_I,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L3_O,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L3_I,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L4_O,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L4_I,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L4_EXT_O,
+	MLX5HWS_DEFINER_FNAME_PTYPE_L4_EXT_I,
+	MLX5HWS_DEFINER_FNAME_PTYPE_FRAG_O,
+	MLX5HWS_DEFINER_FNAME_PTYPE_FRAG_I,
+	MLX5HWS_DEFINER_FNAME_TNL_HDR_0,
+	MLX5HWS_DEFINER_FNAME_TNL_HDR_1,
+	MLX5HWS_DEFINER_FNAME_TNL_HDR_2,
+	MLX5HWS_DEFINER_FNAME_TNL_HDR_3,
+	MLX5HWS_DEFINER_FNAME_MAX,
+};
+
+enum mlx5hws_definer_match_criteria {
+	MLX5HWS_DEFINER_MATCH_CRITERIA_EMPTY = 0,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_OUTER = 1 << 0,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_MISC = 1 << 1,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_INNER = 1 << 2,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_MISC2 = 1 << 3,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_MISC3 = 1 << 4,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_MISC4 = 1 << 5,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_MISC5 = 1 << 6,
+	MLX5HWS_DEFINER_MATCH_CRITERIA_MISC6 = 1 << 7,
+};
+
+enum mlx5hws_definer_type {
+	MLX5HWS_DEFINER_TYPE_MATCH,
+	MLX5HWS_DEFINER_TYPE_JUMBO,
+};
+
+enum mlx5hws_definer_match_flag {
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN_GPE = 1 << 0,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_GENEVE = 1 << 1,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_GTPU = 1 << 2,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE = 1 << 3,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_VXLAN = 1 << 4,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_0_1 = 1 << 5,
+
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_GRE_OPT_KEY = 1 << 6,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_HEADER_2 = 1 << 7,
+
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_MPLS_OVER_GRE = 1 << 8,
+	MLX5HWS_DEFINER_MATCH_FLAG_TNL_MPLS_OVER_UDP = 1 << 9,
+
+	MLX5HWS_DEFINER_MATCH_FLAG_ICMPV4 = 1 << 10,
+	MLX5HWS_DEFINER_MATCH_FLAG_ICMPV6 = 1 << 11,
+	MLX5HWS_DEFINER_MATCH_FLAG_TCP_O = 1 << 12,
+	MLX5HWS_DEFINER_MATCH_FLAG_TCP_I = 1 << 13,
+};
+
+struct mlx5hws_definer_fc {
+	struct mlx5hws_context *ctx;
+	/* Source */
+	u32 s_byte_off;
+	int s_bit_off;
+	u32 s_bit_mask;
+	/* Destination */
+	u32 byte_off;
+	int bit_off;
+	u32 bit_mask;
+	enum mlx5hws_definer_fname fname;
+	void (*tag_set)(struct mlx5hws_definer_fc *fc,
+			void *mach_param,
+			u8 *tag);
+	void (*tag_mask_set)(struct mlx5hws_definer_fc *fc,
+			     void *mach_param,
+			     u8 *tag);
+};
+
+struct mlx5_ifc_definer_hl_eth_l2_bits {
+	u8 dmac_47_16[0x20];
+	u8 dmac_15_0[0x10];
+	u8 l3_ethertype[0x10];
+	u8 reserved_at_40[0x1];
+	u8 sx_sniffer[0x1];
+	u8 functional_lb[0x1];
+	u8 ip_fragmented[0x1];
+	u8 qp_type[0x2];
+	u8 encap_type[0x2];
+	u8 port_number[0x2];
+	u8 l3_type[0x2];
+	u8 l4_type_bwc[0x2];
+	u8 first_vlan_qualifier[0x2];
+	u8 first_priority[0x3];
+	u8 first_cfi[0x1];
+	u8 first_vlan_id[0xc];
+	u8 l4_type[0x4];
+	u8 reserved_at_64[0x2];
+	u8 ipsec_layer[0x2];
+	u8 l2_type[0x2];
+	u8 force_lb[0x1];
+	u8 l2_ok[0x1];
+	u8 l3_ok[0x1];
+	u8 l4_ok[0x1];
+	u8 second_vlan_qualifier[0x2];
+	u8 second_priority[0x3];
+	u8 second_cfi[0x1];
+	u8 second_vlan_id[0xc];
+};
+
+struct mlx5_ifc_definer_hl_eth_l2_src_bits {
+	u8 smac_47_16[0x20];
+	u8 smac_15_0[0x10];
+	u8 loopback_syndrome[0x8];
+	u8 l3_type[0x2];
+	u8 l4_type_bwc[0x2];
+	u8 first_vlan_qualifier[0x2];
+	u8 ip_fragmented[0x1];
+	u8 functional_lb[0x1];
+};
+
+struct mlx5_ifc_definer_hl_ib_l2_bits {
+	u8 sx_sniffer[0x1];
+	u8 force_lb[0x1];
+	u8 functional_lb[0x1];
+	u8 reserved_at_3[0x3];
+	u8 port_number[0x2];
+	u8 sl[0x4];
+	u8 qp_type[0x2];
+	u8 lnh[0x2];
+	u8 dlid[0x10];
+	u8 vl[0x4];
+	u8 lrh_packet_length[0xc];
+	u8 slid[0x10];
+};
+
+struct mlx5_ifc_definer_hl_eth_l3_bits {
+	u8 ip_version[0x4];
+	u8 ihl[0x4];
+	union {
+		u8 tos[0x8];
+		struct {
+			u8 dscp[0x6];
+			u8 ecn[0x2];
+		};
+	};
+	u8 time_to_live_hop_limit[0x8];
+	u8 protocol_next_header[0x8];
+	u8 identification[0x10];
+	union {
+		u8 ipv4_frag[0x10];
+		struct {
+			u8 flags[0x3];
+			u8 fragment_offset[0xd];
+		};
+	};
+	u8 ipv4_total_length[0x10];
+	u8 checksum[0x10];
+	u8 reserved_at_60[0xc];
+	u8 flow_label[0x14];
+	u8 packet_length[0x10];
+	u8 ipv6_payload_length[0x10];
+};
+
+struct mlx5_ifc_definer_hl_eth_l4_bits {
+	u8 source_port[0x10];
+	u8 destination_port[0x10];
+	u8 data_offset[0x4];
+	u8 l4_ok[0x1];
+	u8 l3_ok[0x1];
+	u8 ip_fragmented[0x1];
+	u8 tcp_ns[0x1];
+	union {
+		u8 tcp_flags[0x8];
+		struct {
+			u8 tcp_cwr[0x1];
+			u8 tcp_ece[0x1];
+			u8 tcp_urg[0x1];
+			u8 tcp_ack[0x1];
+			u8 tcp_psh[0x1];
+			u8 tcp_rst[0x1];
+			u8 tcp_syn[0x1];
+			u8 tcp_fin[0x1];
+		};
+	};
+	u8 first_fragment[0x1];
+	u8 reserved_at_31[0xf];
+};
+
+struct mlx5_ifc_definer_hl_src_qp_gvmi_bits {
+	u8 loopback_syndrome[0x8];
+	u8 l3_type[0x2];
+	u8 l4_type_bwc[0x2];
+	u8 first_vlan_qualifier[0x2];
+	u8 reserved_at_e[0x1];
+	u8 functional_lb[0x1];
+	u8 source_gvmi[0x10];
+	u8 force_lb[0x1];
+	u8 ip_fragmented[0x1];
+	u8 source_is_requestor[0x1];
+	u8 reserved_at_23[0x5];
+	u8 source_qp[0x18];
+};
+
+struct mlx5_ifc_definer_hl_ib_l4_bits {
+	u8 opcode[0x8];
+	u8 qp[0x18];
+	u8 se[0x1];
+	u8 migreq[0x1];
+	u8 ackreq[0x1];
+	u8 fecn[0x1];
+	u8 becn[0x1];
+	u8 bth[0x1];
+	u8 deth[0x1];
+	u8 dcceth[0x1];
+	u8 reserved_at_28[0x2];
+	u8 pad_count[0x2];
+	u8 tver[0x4];
+	u8 p_key[0x10];
+	u8 reserved_at_40[0x8];
+	u8 deth_source_qp[0x18];
+};
+
+enum mlx5hws_integrity_ok1_bits {
+	MLX5HWS_DEFINER_OKS1_FIRST_L4_OK = 24,
+	MLX5HWS_DEFINER_OKS1_FIRST_L3_OK = 25,
+	MLX5HWS_DEFINER_OKS1_SECOND_L4_OK = 26,
+	MLX5HWS_DEFINER_OKS1_SECOND_L3_OK = 27,
+	MLX5HWS_DEFINER_OKS1_FIRST_L4_CSUM_OK = 28,
+	MLX5HWS_DEFINER_OKS1_FIRST_IPV4_CSUM_OK = 29,
+	MLX5HWS_DEFINER_OKS1_SECOND_L4_CSUM_OK = 30,
+	MLX5HWS_DEFINER_OKS1_SECOND_IPV4_CSUM_OK = 31,
+};
+
+struct mlx5_ifc_definer_hl_oks1_bits {
+	union {
+		u8 oks1_bits[0x20];
+		struct {
+			u8 second_ipv4_checksum_ok[0x1];
+			u8 second_l4_checksum_ok[0x1];
+			u8 first_ipv4_checksum_ok[0x1];
+			u8 first_l4_checksum_ok[0x1];
+			u8 second_l3_ok[0x1];
+			u8 second_l4_ok[0x1];
+			u8 first_l3_ok[0x1];
+			u8 first_l4_ok[0x1];
+			u8 flex_parser7_steering_ok[0x1];
+			u8 flex_parser6_steering_ok[0x1];
+			u8 flex_parser5_steering_ok[0x1];
+			u8 flex_parser4_steering_ok[0x1];
+			u8 flex_parser3_steering_ok[0x1];
+			u8 flex_parser2_steering_ok[0x1];
+			u8 flex_parser1_steering_ok[0x1];
+			u8 flex_parser0_steering_ok[0x1];
+			u8 second_ipv6_extension_header_vld[0x1];
+			u8 first_ipv6_extension_header_vld[0x1];
+			u8 l3_tunneling_ok[0x1];
+			u8 l2_tunneling_ok[0x1];
+			u8 second_tcp_ok[0x1];
+			u8 second_udp_ok[0x1];
+			u8 second_ipv4_ok[0x1];
+			u8 second_ipv6_ok[0x1];
+			u8 second_l2_ok[0x1];
+			u8 vxlan_ok[0x1];
+			u8 gre_ok[0x1];
+			u8 first_tcp_ok[0x1];
+			u8 first_udp_ok[0x1];
+			u8 first_ipv4_ok[0x1];
+			u8 first_ipv6_ok[0x1];
+			u8 first_l2_ok[0x1];
+		};
+	};
+};
+
+struct mlx5_ifc_definer_hl_oks2_bits {
+	u8 reserved_at_0[0xa];
+	u8 second_mpls_ok[0x1];
+	u8 second_mpls4_s_bit[0x1];
+	u8 second_mpls4_qualifier[0x1];
+	u8 second_mpls3_s_bit[0x1];
+	u8 second_mpls3_qualifier[0x1];
+	u8 second_mpls2_s_bit[0x1];
+	u8 second_mpls2_qualifier[0x1];
+	u8 second_mpls1_s_bit[0x1];
+	u8 second_mpls1_qualifier[0x1];
+	u8 second_mpls0_s_bit[0x1];
+	u8 second_mpls0_qualifier[0x1];
+	u8 first_mpls_ok[0x1];
+	u8 first_mpls4_s_bit[0x1];
+	u8 first_mpls4_qualifier[0x1];
+	u8 first_mpls3_s_bit[0x1];
+	u8 first_mpls3_qualifier[0x1];
+	u8 first_mpls2_s_bit[0x1];
+	u8 first_mpls2_qualifier[0x1];
+	u8 first_mpls1_s_bit[0x1];
+	u8 first_mpls1_qualifier[0x1];
+	u8 first_mpls0_s_bit[0x1];
+	u8 first_mpls0_qualifier[0x1];
+};
+
+struct mlx5_ifc_definer_hl_voq_bits {
+	u8 reserved_at_0[0x18];
+	u8 ecn_ok[0x1];
+	u8 congestion[0x1];
+	u8 profile[0x2];
+	u8 internal_prio[0x4];
+};
+
+struct mlx5_ifc_definer_hl_ipv4_src_dst_bits {
+	u8 source_address[0x20];
+	u8 destination_address[0x20];
+};
+
+struct mlx5_ifc_definer_hl_random_number_bits {
+	u8 random_number[0x10];
+	u8 reserved[0x10];
+};
+
+struct mlx5_ifc_definer_hl_ipv6_addr_bits {
+	u8 ipv6_address_127_96[0x20];
+	u8 ipv6_address_95_64[0x20];
+	u8 ipv6_address_63_32[0x20];
+	u8 ipv6_address_31_0[0x20];
+};
+
+struct mlx5_ifc_definer_tcp_icmp_header_bits {
+	union {
+		struct {
+			u8 icmp_dw1[0x20];
+			u8 icmp_dw2[0x20];
+			u8 icmp_dw3[0x20];
+		};
+		struct {
+			u8 tcp_seq[0x20];
+			u8 tcp_ack[0x20];
+			u8 tcp_win_urg[0x20];
+		};
+	};
+};
+
+struct mlx5_ifc_definer_hl_tunnel_header_bits {
+	u8 tunnel_header_0[0x20];
+	u8 tunnel_header_1[0x20];
+	u8 tunnel_header_2[0x20];
+	u8 tunnel_header_3[0x20];
+};
+
+struct mlx5_ifc_definer_hl_ipsec_bits {
+	u8 spi[0x20];
+	u8 sequence_number[0x20];
+	u8 reserved[0x10];
+	u8 ipsec_syndrome[0x8];
+	u8 next_header[0x8];
+};
+
+struct mlx5_ifc_definer_hl_metadata_bits {
+	u8 metadata_to_cqe[0x20];
+	u8 general_purpose[0x20];
+	u8 acomulated_hash[0x20];
+};
+
+struct mlx5_ifc_definer_hl_flex_parser_bits {
+	u8 flex_parser_7[0x20];
+	u8 flex_parser_6[0x20];
+	u8 flex_parser_5[0x20];
+	u8 flex_parser_4[0x20];
+	u8 flex_parser_3[0x20];
+	u8 flex_parser_2[0x20];
+	u8 flex_parser_1[0x20];
+	u8 flex_parser_0[0x20];
+};
+
+struct mlx5_ifc_definer_hl_registers_bits {
+	u8 register_c_10[0x20];
+	u8 register_c_11[0x20];
+	u8 register_c_8[0x20];
+	u8 register_c_9[0x20];
+	u8 register_c_6[0x20];
+	u8 register_c_7[0x20];
+	u8 register_c_4[0x20];
+	u8 register_c_5[0x20];
+	u8 register_c_2[0x20];
+	u8 register_c_3[0x20];
+	u8 register_c_0[0x20];
+	u8 register_c_1[0x20];
+};
+
+struct mlx5_ifc_definer_hl_mpls_bits {
+	u8 mpls0_label[0x20];
+	u8 mpls1_label[0x20];
+	u8 mpls2_label[0x20];
+	u8 mpls3_label[0x20];
+	u8 mpls4_label[0x20];
+};
+
+struct mlx5_ifc_definer_hl_bits {
+	struct mlx5_ifc_definer_hl_eth_l2_bits eth_l2_outer;
+	struct mlx5_ifc_definer_hl_eth_l2_bits eth_l2_inner;
+	struct mlx5_ifc_definer_hl_eth_l2_src_bits eth_l2_src_outer;
+	struct mlx5_ifc_definer_hl_eth_l2_src_bits eth_l2_src_inner;
+	struct mlx5_ifc_definer_hl_ib_l2_bits ib_l2;
+	struct mlx5_ifc_definer_hl_eth_l3_bits eth_l3_outer;
+	struct mlx5_ifc_definer_hl_eth_l3_bits eth_l3_inner;
+	struct mlx5_ifc_definer_hl_eth_l4_bits eth_l4_outer;
+	struct mlx5_ifc_definer_hl_eth_l4_bits eth_l4_inner;
+	struct mlx5_ifc_definer_hl_src_qp_gvmi_bits source_qp_gvmi;
+	struct mlx5_ifc_definer_hl_ib_l4_bits ib_l4;
+	struct mlx5_ifc_definer_hl_oks1_bits oks1;
+	struct mlx5_ifc_definer_hl_oks2_bits oks2;
+	struct mlx5_ifc_definer_hl_voq_bits voq;
+	u8 reserved_at_480[0x380];
+	struct mlx5_ifc_definer_hl_ipv4_src_dst_bits ipv4_src_dest_outer;
+	struct mlx5_ifc_definer_hl_ipv4_src_dst_bits ipv4_src_dest_inner;
+	struct mlx5_ifc_definer_hl_ipv6_addr_bits ipv6_dst_outer;
+	struct mlx5_ifc_definer_hl_ipv6_addr_bits ipv6_dst_inner;
+	struct mlx5_ifc_definer_hl_ipv6_addr_bits ipv6_src_outer;
+	struct mlx5_ifc_definer_hl_ipv6_addr_bits ipv6_src_inner;
+	u8 unsupported_dest_ib_l3[0x80];
+	u8 unsupported_source_ib_l3[0x80];
+	u8 unsupported_udp_misc_outer[0x20];
+	u8 unsupported_udp_misc_inner[0x20];
+	struct mlx5_ifc_definer_tcp_icmp_header_bits tcp_icmp;
+	struct mlx5_ifc_definer_hl_tunnel_header_bits tunnel_header;
+	struct mlx5_ifc_definer_hl_mpls_bits mpls_outer;
+	struct mlx5_ifc_definer_hl_mpls_bits mpls_inner;
+	u8 unsupported_config_headers_outer[0x80];
+	u8 unsupported_config_headers_inner[0x80];
+	struct mlx5_ifc_definer_hl_random_number_bits random_number;
+	struct mlx5_ifc_definer_hl_ipsec_bits ipsec;
+	struct mlx5_ifc_definer_hl_metadata_bits metadata;
+	u8 unsupported_utc_timestamp[0x40];
+	u8 unsupported_free_running_timestamp[0x40];
+	struct mlx5_ifc_definer_hl_flex_parser_bits flex_parser;
+	struct mlx5_ifc_definer_hl_registers_bits registers;
+	/* Reserved in case header layout on future HW */
+	u8 unsupported_reserved[0xd40];
+};
+
+enum mlx5hws_definer_gtp {
+	MLX5HWS_DEFINER_GTP_EXT_HDR_BIT = 0x04,
+};
+
+struct mlx5_ifc_header_gtp_bits {
+	u8 version[0x3];
+	u8 proto_type[0x1];
+	u8 reserved1[0x1];
+	union {
+		u8 msg_flags[0x3];
+		struct {
+			u8 ext_hdr_flag[0x1];
+			u8 seq_num_flag[0x1];
+			u8 pdu_flag[0x1];
+		};
+	};
+	u8 msg_type[0x8];
+	u8 msg_len[0x8];
+	u8 teid[0x20];
+};
+
+struct mlx5_ifc_header_opt_gtp_bits {
+	u8 seq_num[0x10];
+	u8 pdu_num[0x8];
+	u8 next_ext_hdr_type[0x8];
+};
+
+struct mlx5_ifc_header_gtp_psc_bits {
+	u8 len[0x8];
+	u8 pdu_type[0x4];
+	u8 flags[0x4];
+	u8 qfi[0x8];
+	u8 reserved2[0x8];
+};
+
+struct mlx5_ifc_header_ipv6_vtc_bits {
+	u8 version[0x4];
+	union {
+		u8 tos[0x8];
+		struct {
+			u8 dscp[0x6];
+			u8 ecn[0x2];
+		};
+	};
+	u8 flow_label[0x14];
+};
+
+struct mlx5_ifc_header_ipv6_routing_ext_bits {
+	u8 next_hdr[0x8];
+	u8 hdr_len[0x8];
+	u8 type[0x8];
+	u8 segments_left[0x8];
+	union {
+		u8 flags[0x20];
+		struct {
+			u8 last_entry[0x8];
+			u8 flag[0x8];
+			u8 tag[0x10];
+		};
+	};
+};
+
+struct mlx5_ifc_header_vxlan_bits {
+	u8 flags[0x8];
+	u8 reserved1[0x18];
+	u8 vni[0x18];
+	u8 reserved2[0x8];
+};
+
+struct mlx5_ifc_header_vxlan_gpe_bits {
+	u8 flags[0x8];
+	u8 rsvd0[0x10];
+	u8 protocol[0x8];
+	u8 vni[0x18];
+	u8 rsvd1[0x8];
+};
+
+struct mlx5_ifc_header_gre_bits {
+	union {
+		u8 c_rsvd0_ver[0x10];
+		struct {
+			u8 gre_c_present[0x1];
+			u8 reserved_at_1[0x1];
+			u8 gre_k_present[0x1];
+			u8 gre_s_present[0x1];
+			u8 reserved_at_4[0x9];
+			u8 version[0x3];
+		};
+	};
+	u8 gre_protocol[0x10];
+	u8 checksum[0x10];
+	u8 reserved_at_30[0x10];
+};
+
+struct mlx5_ifc_header_geneve_bits {
+	union {
+		u8 ver_opt_len_o_c_rsvd[0x10];
+		struct {
+			u8 version[0x2];
+			u8 opt_len[0x6];
+			u8 o_flag[0x1];
+			u8 c_flag[0x1];
+			u8 reserved_at_a[0x6];
+		};
+	};
+	u8 protocol_type[0x10];
+	u8 vni[0x18];
+	u8 reserved_at_38[0x8];
+};
+
+struct mlx5_ifc_header_geneve_opt_bits {
+	u8 class[0x10];
+	u8 type[0x8];
+	u8 reserved[0x3];
+	u8 len[0x5];
+};
+
+struct mlx5_ifc_header_icmp_bits {
+	union {
+		u8 icmp_dw1[0x20];
+		struct {
+			u8 type[0x8];
+			u8 code[0x8];
+			u8 cksum[0x10];
+		};
+	};
+	union {
+		u8 icmp_dw2[0x20];
+		struct {
+			u8 ident[0x10];
+			u8 seq_nb[0x10];
+		};
+	};
+};
+
+struct mlx5hws_definer {
+	enum mlx5hws_definer_type type;
+	u8 dw_selector[DW_SELECTORS];
+	u8 byte_selector[BYTE_SELECTORS];
+	struct mlx5hws_rule_match_tag mask;
+	u32 obj_id;
+};
+
+struct mlx5hws_definer_cache {
+	struct list_head list_head;
+};
+
+struct mlx5hws_definer_cache_item {
+	struct mlx5hws_definer definer;
+	u32 refcount;
+	struct list_head list_node;
+};
+
+static inline bool
+mlx5hws_definer_is_jumbo(struct mlx5hws_definer *definer)
+{
+	return (definer->type == MLX5HWS_DEFINER_TYPE_JUMBO);
+}
+
+void mlx5hws_definer_create_tag(u32 *match_param,
+				struct mlx5hws_definer_fc *fc,
+				u32 fc_sz,
+				u8 *tag);
+
+int mlx5hws_definer_get_id(struct mlx5hws_definer *definer);
+
+int mlx5hws_definer_mt_init(struct mlx5hws_context *ctx,
+			    struct mlx5hws_match_template *mt);
+
+void mlx5hws_definer_mt_uninit(struct mlx5hws_context *ctx,
+			       struct mlx5hws_match_template *mt);
+
+int mlx5hws_definer_init_cache(struct mlx5hws_definer_cache **cache);
+
+void mlx5hws_definer_uninit_cache(struct mlx5hws_definer_cache *cache);
+
+int mlx5hws_definer_compare(struct mlx5hws_definer *definer_a,
+			    struct mlx5hws_definer *definer_b);
+
+int mlx5hws_definer_get_obj(struct mlx5hws_context *ctx,
+			    struct mlx5hws_definer *definer);
+
+void mlx5hws_definer_free(struct mlx5hws_context *ctx,
+			  struct mlx5hws_definer *definer);
+
+int mlx5hws_definer_calc_layout(struct mlx5hws_context *ctx,
+				struct mlx5hws_match_template *mt,
+				struct mlx5hws_definer *match_definer);
+
+struct mlx5hws_definer_fc *
+mlx5hws_definer_conv_match_params_to_compressed_fc(struct mlx5hws_context *ctx,
+						   u8 match_criteria_enable,
+						   u32 *match_param,
+						   int *fc_sz);
+
+#endif /* MLX5HWS_DEFINER_H_ */
-- 
cgit v1.3-3-g829e


From 472dd792348f6601ccaa97d5626ee4faff891901 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:37:18 +0300
Subject: net/mlx5: HWS, added matchers functionality

Matcher object encompasses all the building blocks that are
needed in order to perform flow steering of a given flow:
 - flow table that serves as entering point of this matcher
 - Rule Table Context (RTC) objects to hold ll the Steering
   Table Entries (STEs), both for matching the flow and for
   performing actions
 - rules that describe the set of matching parameters for a
   flow and actions to perform in case of a hit.
This patch adds implementation of matchers handling in HWS.

Reviewed-by: Itamar Gozlan <igozlan@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_matcher.c       | 1216 ++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_matcher.h       |  107 ++
 2 files changed, 1323 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c
new file mode 100644
index 000000000000..1964261415aa
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c
@@ -0,0 +1,1216 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+enum mlx5hws_matcher_rtc_type {
+	HWS_MATCHER_RTC_TYPE_MATCH,
+	HWS_MATCHER_RTC_TYPE_STE_ARRAY,
+	HWS_MATCHER_RTC_TYPE_MAX,
+};
+
+static const char * const mlx5hws_matcher_rtc_type_str[] = {
+	[HWS_MATCHER_RTC_TYPE_MATCH] = "MATCH",
+	[HWS_MATCHER_RTC_TYPE_STE_ARRAY] = "STE_ARRAY",
+	[HWS_MATCHER_RTC_TYPE_MAX] = "UNKNOWN",
+};
+
+static const char *hws_matcher_rtc_type_to_str(enum mlx5hws_matcher_rtc_type rtc_type)
+{
+	if (rtc_type > HWS_MATCHER_RTC_TYPE_MAX)
+		rtc_type = HWS_MATCHER_RTC_TYPE_MAX;
+	return mlx5hws_matcher_rtc_type_str[rtc_type];
+}
+
+static bool hws_matcher_requires_col_tbl(u8 log_num_of_rules)
+{
+	/* Collision table concatenation is done only for large rule tables */
+	return log_num_of_rules > MLX5HWS_MATCHER_ASSURED_RULES_TH;
+}
+
+static u8 hws_matcher_rules_to_tbl_depth(u8 log_num_of_rules)
+{
+	if (hws_matcher_requires_col_tbl(log_num_of_rules))
+		return MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH;
+
+	/* For small rule tables we use a single deep table to assure insertion */
+	return min(log_num_of_rules, MLX5HWS_MATCHER_ASSURED_COL_TBL_DEPTH);
+}
+
+static void hws_matcher_destroy_end_ft(struct mlx5hws_matcher *matcher)
+{
+	mlx5hws_table_destroy_default_ft(matcher->tbl, matcher->end_ft_id);
+}
+
+static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	int ret;
+
+	ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &matcher->end_ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Failed to create matcher end flow table\n");
+		return ret;
+	}
+	return 0;
+}
+
+static int hws_matcher_connect(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	struct mlx5hws_matcher *prev = NULL;
+	struct mlx5hws_matcher *next = NULL;
+	struct mlx5hws_matcher *tmp_matcher;
+	int ret;
+
+	/* Find location in matcher list */
+	if (list_empty(&tbl->matchers_list)) {
+		list_add(&matcher->list_node, &tbl->matchers_list);
+		goto connect;
+	}
+
+	list_for_each_entry(tmp_matcher, &tbl->matchers_list, list_node) {
+		if (tmp_matcher->attr.priority > matcher->attr.priority) {
+			next = tmp_matcher;
+			break;
+		}
+		prev = tmp_matcher;
+	}
+
+	if (next)
+		/* insert before next */
+		list_add_tail(&matcher->list_node, &next->list_node);
+	else
+		/* insert after prev */
+		list_add(&matcher->list_node, &prev->list_node);
+
+connect:
+	if (next) {
+		/* Connect to next RTC */
+		ret = mlx5hws_table_ft_set_next_rtc(ctx,
+						    matcher->end_ft_id,
+						    tbl->fw_ft_type,
+						    next->match_ste.rtc_0_id,
+						    next->match_ste.rtc_1_id);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to connect new matcher to next RTC\n");
+			goto remove_from_list;
+		}
+	} else {
+		/* Connect last matcher to next miss_tbl if exists */
+		ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed connect new matcher to miss_tbl\n");
+			goto remove_from_list;
+		}
+	}
+
+	/* Connect to previous FT */
+	ret = mlx5hws_table_ft_set_next_rtc(ctx,
+					    prev ? prev->end_ft_id : tbl->ft_id,
+					    tbl->fw_ft_type,
+					    matcher->match_ste.rtc_0_id,
+					    matcher->match_ste.rtc_1_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to connect new matcher to previous FT\n");
+		goto remove_from_list;
+	}
+
+	/* Reset prev matcher FT default miss (drop refcount) */
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev ? prev->end_ft_id : tbl->ft_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to reset matcher ft default miss\n");
+		goto remove_from_list;
+	}
+
+	if (!prev) {
+		/* Update tables missing to current matcher in the table */
+		ret = mlx5hws_table_update_connected_miss_tables(tbl);
+		if (ret) {
+			mlx5hws_err(ctx, "Fatal error, failed to update connected miss table\n");
+			goto remove_from_list;
+		}
+	}
+
+	return 0;
+
+remove_from_list:
+	list_del_init(&matcher->list_node);
+	return ret;
+}
+
+static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher *next = NULL, *prev = NULL;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	u32 prev_ft_id = tbl->ft_id;
+	int ret;
+
+	if (!list_is_first(&matcher->list_node, &tbl->matchers_list)) {
+		prev = list_prev_entry(matcher, list_node);
+		prev_ft_id = prev->end_ft_id;
+	}
+
+	if (!list_is_last(&matcher->list_node, &tbl->matchers_list))
+		next = list_next_entry(matcher, list_node);
+
+	list_del_init(&matcher->list_node);
+
+	if (next) {
+		/* Connect previous end FT to next RTC */
+		ret = mlx5hws_table_ft_set_next_rtc(tbl->ctx,
+						    prev_ft_id,
+						    tbl->fw_ft_type,
+						    next->match_ste.rtc_0_id,
+						    next->match_ste.rtc_1_id);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Failed to disconnect matcher\n");
+			goto matcher_reconnect;
+		}
+	} else {
+		ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Failed to disconnect last matcher\n");
+			goto matcher_reconnect;
+		}
+	}
+
+	/* Removing first matcher, update connected miss tables if exists */
+	if (prev_ft_id == tbl->ft_id) {
+		ret = mlx5hws_table_update_connected_miss_tables(tbl);
+		if (ret) {
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to update connected miss table\n");
+			goto matcher_reconnect;
+		}
+	}
+
+	ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev_ft_id);
+	if (ret) {
+		mlx5hws_err(tbl->ctx, "Fatal error, failed to restore matcher ft default miss\n");
+		goto matcher_reconnect;
+	}
+
+	return 0;
+
+matcher_reconnect:
+	if (list_empty(&tbl->matchers_list) || !prev)
+		list_add(&matcher->list_node, &tbl->matchers_list);
+	else
+		/* insert after prev matcher */
+		list_add(&matcher->list_node, &prev->list_node);
+
+	return ret;
+}
+
+static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher,
+					struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
+					enum mlx5hws_matcher_rtc_type rtc_type,
+					bool is_mirror)
+{
+	struct mlx5hws_pool_chunk *ste = &matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].ste;
+	enum mlx5hws_matcher_flow_src flow_src = matcher->attr.optimize_flow_src;
+	bool is_match_rtc = rtc_type == HWS_MATCHER_RTC_TYPE_MATCH;
+
+	if ((flow_src == MLX5HWS_MATCHER_FLOW_SRC_VPORT && !is_mirror) ||
+	    (flow_src == MLX5HWS_MATCHER_FLOW_SRC_WIRE && is_mirror)) {
+		/* Optimize FDB RTC */
+		rtc_attr->log_size = 0;
+		rtc_attr->log_depth = 0;
+	} else {
+		/* Keep original values */
+		rtc_attr->log_size = is_match_rtc ? matcher->attr.table.sz_row_log : ste->order;
+		rtc_attr->log_depth = is_match_rtc ? matcher->attr.table.sz_col_log : 0;
+	}
+}
+
+static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
+				  enum mlx5hws_matcher_rtc_type rtc_type,
+				  u8 action_ste_selector)
+{
+	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+	struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0};
+	struct mlx5hws_match_template *mt = matcher->mt;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	struct mlx5hws_action_default_stc *default_stc;
+	struct mlx5hws_matcher_action_ste *action_ste;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_pool *ste_pool, *stc_pool;
+	struct mlx5hws_pool_chunk *ste;
+	u32 *rtc_0_id, *rtc_1_id;
+	u32 obj_id;
+	int ret;
+
+	switch (rtc_type) {
+	case HWS_MATCHER_RTC_TYPE_MATCH:
+		rtc_0_id = &matcher->match_ste.rtc_0_id;
+		rtc_1_id = &matcher->match_ste.rtc_1_id;
+		ste_pool = matcher->match_ste.pool;
+		ste = &matcher->match_ste.ste;
+		ste->order = attr->table.sz_col_log + attr->table.sz_row_log;
+
+		rtc_attr.log_size = attr->table.sz_row_log;
+		rtc_attr.log_depth = attr->table.sz_col_log;
+		rtc_attr.is_frst_jumbo = mlx5hws_matcher_mt_is_jumbo(mt);
+		rtc_attr.is_scnd_range = 0;
+		rtc_attr.miss_ft_id = matcher->end_ft_id;
+
+		if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH) {
+			/* The usual Hash Table */
+			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH;
+
+			/* The first mt is used since all share the same definer */
+			rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
+		} else if (attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX) {
+			rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+			rtc_attr.num_hash_definer = 1;
+
+			if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
+				/* Hash Split Table */
+				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH;
+				rtc_attr.match_definer_0 = mlx5hws_definer_get_id(mt->definer);
+			} else if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
+				/* Linear Lookup Table */
+				rtc_attr.access_index_mode = MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR;
+				rtc_attr.match_definer_0 = ctx->caps->linear_match_definer;
+			}
+		}
+
+		/* Match pool requires implicit allocation */
+		ret = mlx5hws_pool_chunk_alloc(ste_pool, ste);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to allocate STE for %s RTC",
+				    hws_matcher_rtc_type_to_str(rtc_type));
+			return ret;
+		}
+		break;
+
+	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
+		action_ste = &matcher->action_ste[action_ste_selector];
+
+		rtc_0_id = &action_ste->rtc_0_id;
+		rtc_1_id = &action_ste->rtc_1_id;
+		ste_pool = action_ste->pool;
+		ste = &action_ste->ste;
+		ste->order = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
+			     attr->table.sz_row_log;
+		rtc_attr.log_size = ste->order;
+		rtc_attr.log_depth = 0;
+		rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET;
+		/* The action STEs use the default always hit definer */
+		rtc_attr.match_definer_0 = ctx->caps->trivial_match_definer;
+		rtc_attr.is_frst_jumbo = false;
+		rtc_attr.miss_ft_id = 0;
+		break;
+
+	default:
+		mlx5hws_err(ctx, "HWS Invalid RTC type\n");
+		return -EINVAL;
+	}
+
+	obj_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+
+	rtc_attr.pd = ctx->pd_num;
+	rtc_attr.ste_base = obj_id;
+	rtc_attr.ste_offset = ste->offset;
+	rtc_attr.reparse_mode = mlx5hws_context_get_reparse_mode(ctx);
+	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, false);
+	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, false);
+
+	/* STC is a single resource (obj_id), use any STC for the ID */
+	stc_pool = ctx->stc_pool[tbl->type];
+	default_stc = ctx->common_res[tbl->type].default_stc;
+	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
+	rtc_attr.stc_base = obj_id;
+
+	ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_0_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create matcher RTC of type %s",
+			    hws_matcher_rtc_type_to_str(rtc_type));
+		goto free_ste;
+	}
+
+	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
+		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+		rtc_attr.ste_base = obj_id;
+		rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(tbl->type, true);
+
+		obj_id = mlx5hws_pool_chunk_get_base_mirror_id(stc_pool, &default_stc->default_hit);
+		rtc_attr.stc_base = obj_id;
+		hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, true);
+
+		ret = mlx5hws_cmd_rtc_create(ctx->mdev, &rtc_attr, rtc_1_id);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed to create peer matcher RTC of type %s",
+				    hws_matcher_rtc_type_to_str(rtc_type));
+			goto destroy_rtc_0;
+		}
+	}
+
+	return 0;
+
+destroy_rtc_0:
+	mlx5hws_cmd_rtc_destroy(ctx->mdev, *rtc_0_id);
+free_ste:
+	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
+		mlx5hws_pool_chunk_free(ste_pool, ste);
+	return ret;
+}
+
+static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher,
+				    enum mlx5hws_matcher_rtc_type rtc_type,
+				    u8 action_ste_selector)
+{
+	struct mlx5hws_matcher_action_ste *action_ste;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_pool_chunk *ste;
+	struct mlx5hws_pool *ste_pool;
+	u32 rtc_0_id, rtc_1_id;
+
+	switch (rtc_type) {
+	case HWS_MATCHER_RTC_TYPE_MATCH:
+		rtc_0_id = matcher->match_ste.rtc_0_id;
+		rtc_1_id = matcher->match_ste.rtc_1_id;
+		ste_pool = matcher->match_ste.pool;
+		ste = &matcher->match_ste.ste;
+		break;
+	case HWS_MATCHER_RTC_TYPE_STE_ARRAY:
+		action_ste = &matcher->action_ste[action_ste_selector];
+		rtc_0_id = action_ste->rtc_0_id;
+		rtc_1_id = action_ste->rtc_1_id;
+		ste_pool = action_ste->pool;
+		ste = &action_ste->ste;
+		break;
+	default:
+		return;
+	}
+
+	if (tbl->type == MLX5HWS_TABLE_TYPE_FDB)
+		mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_1_id);
+
+	mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, rtc_0_id);
+	if (rtc_type == HWS_MATCHER_RTC_TYPE_MATCH)
+		mlx5hws_pool_chunk_free(ste_pool, ste);
+}
+
+static int
+hws_matcher_check_attr_sz(struct mlx5hws_cmd_query_caps *caps,
+			  struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+
+	if (attr->table.sz_col_log > caps->rtc_log_depth_max) {
+		mlx5hws_err(matcher->tbl->ctx, "Matcher depth exceeds limit %d\n",
+			    caps->rtc_log_depth_max);
+		return -EOPNOTSUPP;
+	}
+
+	if (attr->table.sz_col_log + attr->table.sz_row_log > caps->ste_alloc_log_max) {
+		mlx5hws_err(matcher->tbl->ctx, "Total matcher size exceeds limit %d\n",
+			    caps->ste_alloc_log_max);
+		return -EOPNOTSUPP;
+	}
+
+	if (attr->table.sz_col_log + attr->table.sz_row_log < caps->ste_alloc_log_gran) {
+		mlx5hws_err(matcher->tbl->ctx, "Total matcher size below limit %d\n",
+			    caps->ste_alloc_log_gran);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void hws_matcher_set_pool_attr(struct mlx5hws_pool_attr *attr,
+				      struct mlx5hws_matcher *matcher)
+{
+	switch (matcher->attr.optimize_flow_src) {
+	case MLX5HWS_MATCHER_FLOW_SRC_VPORT:
+		attr->opt_type = MLX5HWS_POOL_OPTIMIZE_ORIG;
+		break;
+	case MLX5HWS_MATCHER_FLOW_SRC_WIRE:
+		attr->opt_type = MLX5HWS_POOL_OPTIMIZE_MIRROR;
+		break;
+	default:
+		break;
+	}
+}
+
+static int hws_matcher_check_and_process_at(struct mlx5hws_matcher *matcher,
+					    struct mlx5hws_action_template *at)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	bool valid;
+	int ret;
+
+	valid = mlx5hws_action_check_combo(ctx, at->action_type_arr, matcher->tbl->type);
+	if (!valid) {
+		mlx5hws_err(ctx, "Invalid combination in action template\n");
+		return -EINVAL;
+	}
+
+	/* Process action template to setters */
+	ret = mlx5hws_action_template_process(at);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to process action template\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hws_matcher_resize_init(struct mlx5hws_matcher *src_matcher)
+{
+	struct mlx5hws_matcher_resize_data *resize_data;
+
+	resize_data = kzalloc(sizeof(*resize_data), GFP_KERNEL);
+	if (!resize_data)
+		return -ENOMEM;
+
+	resize_data->max_stes = src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes;
+
+	resize_data->action_ste[0].stc = src_matcher->action_ste[0].stc;
+	resize_data->action_ste[0].rtc_0_id = src_matcher->action_ste[0].rtc_0_id;
+	resize_data->action_ste[0].rtc_1_id = src_matcher->action_ste[0].rtc_1_id;
+	resize_data->action_ste[0].pool = src_matcher->action_ste[0].max_stes ?
+					  src_matcher->action_ste[0].pool :
+					  NULL;
+	resize_data->action_ste[1].stc = src_matcher->action_ste[1].stc;
+	resize_data->action_ste[1].rtc_0_id = src_matcher->action_ste[1].rtc_0_id;
+	resize_data->action_ste[1].rtc_1_id = src_matcher->action_ste[1].rtc_1_id;
+	resize_data->action_ste[1].pool = src_matcher->action_ste[1].max_stes ?
+					  src_matcher->action_ste[1].pool :
+					   NULL;
+
+	/* Place the new resized matcher on the dst matcher's list */
+	list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
+
+	/* Move all the previous resized matchers to the dst matcher's list */
+	while (!list_empty(&src_matcher->resize_data)) {
+		resize_data = list_first_entry(&src_matcher->resize_data,
+					       struct mlx5hws_matcher_resize_data,
+					       list_node);
+		list_del_init(&resize_data->list_node);
+		list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data);
+	}
+
+	return 0;
+}
+
+static void hws_matcher_resize_uninit(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher_resize_data *resize_data;
+
+	if (!mlx5hws_matcher_is_resizable(matcher))
+		return;
+
+	while (!list_empty(&matcher->resize_data)) {
+		resize_data = list_first_entry(&matcher->resize_data,
+					       struct mlx5hws_matcher_resize_data,
+					       list_node);
+		list_del_init(&resize_data->list_node);
+
+		if (resize_data->max_stes) {
+			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
+						       matcher->tbl->type,
+						       &resize_data->action_ste[1].stc);
+			mlx5hws_action_free_single_stc(matcher->tbl->ctx,
+						       matcher->tbl->type,
+						       &resize_data->action_ste[0].stc);
+
+			if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) {
+				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
+							resize_data->action_ste[1].rtc_1_id);
+				mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
+							resize_data->action_ste[0].rtc_1_id);
+			}
+			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
+						resize_data->action_ste[1].rtc_0_id);
+			mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev,
+						resize_data->action_ste[0].rtc_0_id);
+			if (resize_data->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].pool) {
+				mlx5hws_pool_destroy(resize_data->action_ste[1].pool);
+				mlx5hws_pool_destroy(resize_data->action_ste[0].pool);
+			}
+		}
+
+		kfree(resize_data);
+	}
+}
+
+static int
+hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector)
+{
+	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_matcher_action_ste *action_ste;
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_pool_attr pool_attr = {0};
+	struct mlx5hws_context *ctx = tbl->ctx;
+	int ret;
+
+	action_ste = &matcher->action_ste[action_ste_selector];
+
+	/* Allocate action STE mempool */
+	pool_attr.table_type = tbl->type;
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL;
+	pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) +
+				 matcher->attr.table.sz_row_log;
+	hws_matcher_set_pool_attr(&pool_attr, matcher);
+	action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!action_ste->pool) {
+		mlx5hws_err(ctx, "Failed to create action ste pool\n");
+		return -EINVAL;
+	}
+
+	/* Allocate action RTC */
+	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create action RTC\n");
+		goto free_ste_pool;
+	}
+
+	/* Allocate STC for jumps to STE */
+	stc_attr.action_offset = MLX5HWS_ACTION_OFFSET_HIT;
+	stc_attr.action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE;
+	stc_attr.reparse_mode = MLX5_IFC_STC_REPARSE_IGNORE;
+	stc_attr.ste_table.ste = action_ste->ste;
+	stc_attr.ste_table.ste_pool = action_ste->pool;
+	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
+
+	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, tbl->type,
+					      &action_ste->stc);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create action jump to table STC\n");
+		goto free_rtc;
+	}
+
+	return 0;
+
+free_rtc:
+	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
+free_ste_pool:
+	mlx5hws_pool_destroy(action_ste->pool);
+	return ret;
+}
+
+static void hws_matcher_unbind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector)
+{
+	struct mlx5hws_matcher_action_ste *action_ste;
+	struct mlx5hws_table *tbl = matcher->tbl;
+
+	action_ste = &matcher->action_ste[action_ste_selector];
+
+	if (!action_ste->max_stes ||
+	    matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION ||
+	    mlx5hws_matcher_is_in_resize(matcher))
+		return;
+
+	mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc);
+	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector);
+	mlx5hws_pool_destroy(action_ste->pool);
+}
+
+static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher)
+{
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
+	struct mlx5hws_table *tbl = matcher->tbl;
+	struct mlx5hws_context *ctx = tbl->ctx;
+	u32 required_stes;
+	u8 max_stes = 0;
+	int i, ret;
+
+	if (matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION)
+		return 0;
+
+	for (i = 0; i < matcher->num_of_at; i++) {
+		struct mlx5hws_action_template *at = &matcher->at[i];
+
+		ret = hws_matcher_check_and_process_at(matcher, at);
+		if (ret) {
+			mlx5hws_err(ctx, "Invalid at %d", i);
+			return ret;
+		}
+
+		required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term);
+		max_stes = max(max_stes, required_stes);
+
+		/* Future: Optimize reparse */
+	}
+
+	/* There are no additional STEs required for matcher */
+	if (!max_stes)
+		return 0;
+
+	matcher->action_ste[0].max_stes = max_stes;
+	matcher->action_ste[1].max_stes = max_stes;
+
+	ret = hws_matcher_bind_at_idx(matcher, 0);
+	if (ret)
+		return ret;
+
+	ret = hws_matcher_bind_at_idx(matcher, 1);
+	if (ret)
+		goto free_at_0;
+
+	return 0;
+
+free_at_0:
+	hws_matcher_unbind_at_idx(matcher, 0);
+	return ret;
+}
+
+static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher)
+{
+	hws_matcher_unbind_at_idx(matcher, 1);
+	hws_matcher_unbind_at_idx(matcher, 0);
+}
+
+static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	struct mlx5hws_pool_attr pool_attr = {0};
+	int ret;
+
+	/* Calculate match, range and hash definers */
+	if (!(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION)) {
+		ret = mlx5hws_definer_mt_init(ctx, matcher->mt);
+		if (ret) {
+			if (ret == E2BIG)
+				mlx5hws_err(ctx, "Failed to set matcher templates with match definers\n");
+			return ret;
+		}
+	}
+
+	/* Create an STE pool per matcher*/
+	pool_attr.table_type = matcher->tbl->type;
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE;
+	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL;
+	pool_attr.alloc_log_sz = matcher->attr.table.sz_col_log +
+				 matcher->attr.table.sz_row_log;
+	hws_matcher_set_pool_attr(&pool_attr, matcher);
+
+	matcher->match_ste.pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!matcher->match_ste.pool) {
+		mlx5hws_err(ctx, "Failed to allocate matcher STE pool\n");
+		ret = -EOPNOTSUPP;
+		goto uninit_match_definer;
+	}
+
+	return 0;
+
+uninit_match_definer:
+	if (!(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
+		mlx5hws_definer_mt_uninit(ctx, matcher->mt);
+	return ret;
+}
+
+static void hws_matcher_unbind_mt(struct mlx5hws_matcher *matcher)
+{
+	mlx5hws_pool_destroy(matcher->match_ste.pool);
+	if (!(matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION))
+		mlx5hws_definer_mt_uninit(matcher->tbl->ctx, matcher->mt);
+}
+
+static int
+hws_matcher_validate_insert_mode(struct mlx5hws_cmd_query_caps *caps,
+				 struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+
+	switch (attr->insert_mode) {
+	case MLX5HWS_MATCHER_INSERT_BY_HASH:
+		if (matcher->attr.distribute_mode != MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
+			mlx5hws_err(ctx, "Invalid matcher distribute mode\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	case MLX5HWS_MATCHER_INSERT_BY_INDEX:
+		if (attr->table.sz_col_log) {
+			mlx5hws_err(ctx, "Matcher with INSERT_BY_INDEX supports only Nx1 table size\n");
+			return -EOPNOTSUPP;
+		}
+
+		if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH) {
+			/* Hash Split Table */
+			if (!caps->rtc_hash_split_table) {
+				mlx5hws_err(ctx, "FW doesn't support insert by index and hash distribute\n");
+				return -EOPNOTSUPP;
+			}
+		} else if (attr->distribute_mode == MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR) {
+			/* Linear Lookup Table */
+			if (!caps->rtc_linear_lookup_table ||
+			    !IS_BIT_SET(caps->access_index_mode,
+					MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR)) {
+				mlx5hws_err(ctx, "FW doesn't support insert by index and linear distribute\n");
+				return -EOPNOTSUPP;
+			}
+
+			if (attr->table.sz_row_log > MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX) {
+				mlx5hws_err(ctx, "Matcher with linear distribute: rows exceed limit %d",
+					    MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX);
+				return -EOPNOTSUPP;
+			}
+		} else {
+			mlx5hws_err(ctx, "Matcher has unsupported distribute mode\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		mlx5hws_err(ctx, "Matcher has unsupported insert mode\n");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+hws_matcher_process_attr(struct mlx5hws_cmd_query_caps *caps,
+			 struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+
+	if (hws_matcher_validate_insert_mode(caps, matcher))
+		return -EOPNOTSUPP;
+
+	if (matcher->tbl->type != MLX5HWS_TABLE_TYPE_FDB && attr->optimize_flow_src) {
+		mlx5hws_err(matcher->tbl->ctx, "NIC domain doesn't support flow_src\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Convert number of rules to the required depth */
+	if (attr->mode == MLX5HWS_MATCHER_RESOURCE_MODE_RULE &&
+	    attr->insert_mode == MLX5HWS_MATCHER_INSERT_BY_HASH)
+		attr->table.sz_col_log = hws_matcher_rules_to_tbl_depth(attr->rule.num_log);
+
+	matcher->flags |= attr->resizable ? MLX5HWS_MATCHER_FLAGS_RESIZABLE : 0;
+
+	return hws_matcher_check_attr_sz(caps, matcher);
+}
+
+static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher)
+{
+	int ret;
+
+	/* Select and create the definers for current matcher */
+	ret = hws_matcher_bind_mt(matcher);
+	if (ret)
+		return ret;
+
+	/* Calculate and verify action combination */
+	ret = hws_matcher_bind_at(matcher);
+	if (ret)
+		goto unbind_mt;
+
+	/* Create matcher end flow table anchor */
+	ret = hws_matcher_create_end_ft(matcher);
+	if (ret)
+		goto unbind_at;
+
+	/* Allocate the RTC for the new matcher */
+	ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	if (ret)
+		goto destroy_end_ft;
+
+	/* Connect the matcher to the matcher list */
+	ret = hws_matcher_connect(matcher);
+	if (ret)
+		goto destroy_rtc;
+
+	return 0;
+
+destroy_rtc:
+	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+destroy_end_ft:
+	hws_matcher_destroy_end_ft(matcher);
+unbind_at:
+	hws_matcher_unbind_at(matcher);
+unbind_mt:
+	hws_matcher_unbind_mt(matcher);
+	return ret;
+}
+
+static void hws_matcher_destroy_and_disconnect(struct mlx5hws_matcher *matcher)
+{
+	hws_matcher_resize_uninit(matcher);
+	hws_matcher_disconnect(matcher);
+	hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0);
+	hws_matcher_destroy_end_ft(matcher);
+	hws_matcher_unbind_at(matcher);
+	hws_matcher_unbind_mt(matcher);
+}
+
+static int
+hws_matcher_create_col_matcher(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	struct mlx5hws_matcher *col_matcher;
+	int ret;
+
+	if (matcher->attr.mode != MLX5HWS_MATCHER_RESOURCE_MODE_RULE ||
+	    matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX)
+		return 0;
+
+	if (!hws_matcher_requires_col_tbl(matcher->attr.rule.num_log))
+		return 0;
+
+	col_matcher = kzalloc(sizeof(*matcher), GFP_KERNEL);
+	if (!col_matcher)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&col_matcher->resize_data);
+
+	col_matcher->tbl = matcher->tbl;
+	col_matcher->mt = matcher->mt;
+	col_matcher->at = matcher->at;
+	col_matcher->num_of_at = matcher->num_of_at;
+	col_matcher->num_of_mt = matcher->num_of_mt;
+	col_matcher->attr.priority = matcher->attr.priority;
+	col_matcher->flags = matcher->flags;
+	col_matcher->flags |= MLX5HWS_MATCHER_FLAGS_COLLISION;
+	col_matcher->attr.mode = MLX5HWS_MATCHER_RESOURCE_MODE_HTABLE;
+	col_matcher->attr.optimize_flow_src = matcher->attr.optimize_flow_src;
+	col_matcher->attr.table.sz_row_log = matcher->attr.rule.num_log;
+	col_matcher->attr.table.sz_col_log = MLX5HWS_MATCHER_ASSURED_COL_TBL_DEPTH;
+	if (col_matcher->attr.table.sz_row_log > MLX5HWS_MATCHER_ASSURED_ROW_RATIO)
+		col_matcher->attr.table.sz_row_log -= MLX5HWS_MATCHER_ASSURED_ROW_RATIO;
+
+	col_matcher->attr.max_num_of_at_attach = matcher->attr.max_num_of_at_attach;
+
+	ret = hws_matcher_process_attr(ctx->caps, col_matcher);
+	if (ret)
+		goto free_col_matcher;
+
+	ret = hws_matcher_create_and_connect(col_matcher);
+	if (ret)
+		goto free_col_matcher;
+
+	matcher->col_matcher = col_matcher;
+
+	return 0;
+
+free_col_matcher:
+	kfree(col_matcher);
+	mlx5hws_err(ctx, "Failed to create assured collision matcher\n");
+	return ret;
+}
+
+static void
+hws_matcher_destroy_col_matcher(struct mlx5hws_matcher *matcher)
+{
+	if (matcher->attr.mode != MLX5HWS_MATCHER_RESOURCE_MODE_RULE ||
+	    matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX)
+		return;
+
+	if (matcher->col_matcher) {
+		hws_matcher_destroy_and_disconnect(matcher->col_matcher);
+		kfree(matcher->col_matcher);
+	}
+}
+
+static int hws_matcher_init(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	int ret;
+
+	INIT_LIST_HEAD(&matcher->resize_data);
+
+	mutex_lock(&ctx->ctrl_lock);
+
+	/* Allocate matcher resource and connect to the packet pipe */
+	ret = hws_matcher_create_and_connect(matcher);
+	if (ret)
+		goto unlock_err;
+
+	/* Create additional matcher for collision handling */
+	ret = hws_matcher_create_col_matcher(matcher);
+	if (ret)
+		goto destory_and_disconnect;
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return 0;
+
+destory_and_disconnect:
+	hws_matcher_destroy_and_disconnect(matcher);
+unlock_err:
+	mutex_unlock(&ctx->ctrl_lock);
+	return ret;
+}
+
+static int hws_matcher_uninit(struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+
+	mutex_lock(&ctx->ctrl_lock);
+	hws_matcher_destroy_col_matcher(matcher);
+	hws_matcher_destroy_and_disconnect(matcher);
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return 0;
+}
+
+int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
+			      struct mlx5hws_action_template *at)
+{
+	bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt);
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	u32 required_stes;
+	int ret;
+
+	if (!matcher->attr.max_num_of_at_attach) {
+		mlx5hws_dbg(ctx, "Num of current at (%d) exceed allowed value\n",
+			    matcher->num_of_at);
+		return -EOPNOTSUPP;
+	}
+
+	ret = hws_matcher_check_and_process_at(matcher, at);
+	if (ret)
+		return -ret;
+
+	required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term);
+	if (matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes < required_stes) {
+		mlx5hws_dbg(ctx, "Required STEs [%d] exceeds initial action template STE [%d]\n",
+			    required_stes,
+			    matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes);
+		return -ENOMEM;
+	}
+
+	matcher->at[matcher->num_of_at] = *at;
+	matcher->num_of_at += 1;
+	matcher->attr.max_num_of_at_attach -= 1;
+
+	if (matcher->col_matcher)
+		matcher->col_matcher->num_of_at = matcher->num_of_at;
+
+	return 0;
+}
+
+static int
+hws_matcher_set_templates(struct mlx5hws_matcher *matcher,
+			  struct mlx5hws_match_template *mt[],
+			  u8 num_of_mt,
+			  struct mlx5hws_action_template *at[],
+			  u8 num_of_at)
+{
+	struct mlx5hws_context *ctx = matcher->tbl->ctx;
+	int ret = 0;
+	int i;
+
+	if (!num_of_mt || !num_of_at) {
+		mlx5hws_err(ctx, "Number of action/match template cannot be zero\n");
+		return -EOPNOTSUPP;
+	}
+
+	matcher->mt = kcalloc(num_of_mt, sizeof(*matcher->mt), GFP_KERNEL);
+	if (!matcher->mt)
+		return -ENOMEM;
+
+	matcher->at = kcalloc(num_of_at + matcher->attr.max_num_of_at_attach,
+			      sizeof(*matcher->at),
+			      GFP_KERNEL);
+	if (!matcher->at) {
+		mlx5hws_err(ctx, "Failed to allocate action template array\n");
+		ret = -ENOMEM;
+		goto free_mt;
+	}
+
+	for (i = 0; i < num_of_mt; i++)
+		matcher->mt[i] = *mt[i];
+
+	for (i = 0; i < num_of_at; i++)
+		matcher->at[i] = *at[i];
+
+	matcher->num_of_mt = num_of_mt;
+	matcher->num_of_at = num_of_at;
+
+	return 0;
+
+free_mt:
+	kfree(matcher->mt);
+	return ret;
+}
+
+static void
+hws_matcher_unset_templates(struct mlx5hws_matcher *matcher)
+{
+	kfree(matcher->at);
+	kfree(matcher->mt);
+}
+
+struct mlx5hws_matcher *
+mlx5hws_matcher_create(struct mlx5hws_table *tbl,
+		       struct mlx5hws_match_template *mt[],
+		       u8 num_of_mt,
+		       struct mlx5hws_action_template *at[],
+		       u8 num_of_at,
+		       struct mlx5hws_matcher_attr *attr)
+{
+	struct mlx5hws_context *ctx = tbl->ctx;
+	struct mlx5hws_matcher *matcher;
+	int ret;
+
+	matcher = kzalloc(sizeof(*matcher), GFP_KERNEL);
+	if (!matcher)
+		return NULL;
+
+	matcher->tbl = tbl;
+	matcher->attr = *attr;
+
+	ret = hws_matcher_process_attr(tbl->ctx->caps, matcher);
+	if (ret)
+		goto free_matcher;
+
+	ret = hws_matcher_set_templates(matcher, mt, num_of_mt, at, num_of_at);
+	if (ret)
+		goto free_matcher;
+
+	ret = hws_matcher_init(matcher);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to initialise matcher: %d\n", ret);
+		goto unset_templates;
+	}
+
+	return matcher;
+
+unset_templates:
+	hws_matcher_unset_templates(matcher);
+free_matcher:
+	kfree(matcher);
+	return NULL;
+}
+
+int mlx5hws_matcher_destroy(struct mlx5hws_matcher *matcher)
+{
+	hws_matcher_uninit(matcher);
+	hws_matcher_unset_templates(matcher);
+	kfree(matcher);
+	return 0;
+}
+
+struct mlx5hws_match_template *
+mlx5hws_match_template_create(struct mlx5hws_context *ctx,
+			      u32 *match_param,
+			      u32 match_param_sz,
+			      u8 match_criteria_enable)
+{
+	struct mlx5hws_match_template *mt;
+
+	mt = kzalloc(sizeof(*mt), GFP_KERNEL);
+	if (!mt)
+		return NULL;
+
+	mt->match_param = kzalloc(MLX5_ST_SZ_BYTES(fte_match_param), GFP_KERNEL);
+	if (!mt->match_param)
+		goto free_template;
+
+	memcpy(mt->match_param, match_param, match_param_sz);
+	mt->match_criteria_enable = match_criteria_enable;
+
+	return mt;
+
+free_template:
+	kfree(mt);
+	return NULL;
+}
+
+int mlx5hws_match_template_destroy(struct mlx5hws_match_template *mt)
+{
+	kfree(mt->match_param);
+	kfree(mt);
+	return 0;
+}
+
+static int hws_matcher_resize_precheck(struct mlx5hws_matcher *src_matcher,
+				       struct mlx5hws_matcher *dst_matcher)
+{
+	struct mlx5hws_context *ctx = src_matcher->tbl->ctx;
+	int i;
+
+	if (src_matcher->tbl->type != dst_matcher->tbl->type) {
+		mlx5hws_err(ctx, "Table type mismatch for src/dst matchers\n");
+		return -EINVAL;
+	}
+
+	if (!mlx5hws_matcher_is_resizable(src_matcher) ||
+	    !mlx5hws_matcher_is_resizable(dst_matcher)) {
+		mlx5hws_err(ctx, "Src/dst matcher is not resizable\n");
+		return -EINVAL;
+	}
+
+	if (mlx5hws_matcher_is_insert_by_idx(src_matcher) !=
+	    mlx5hws_matcher_is_insert_by_idx(dst_matcher)) {
+		mlx5hws_err(ctx, "Src/dst matchers insert mode mismatch\n");
+		return -EINVAL;
+	}
+
+	if (mlx5hws_matcher_is_in_resize(src_matcher) ||
+	    mlx5hws_matcher_is_in_resize(dst_matcher)) {
+		mlx5hws_err(ctx, "Src/dst matcher is already in resize\n");
+		return -EINVAL;
+	}
+
+	/* Compare match templates - make sure the definers are equivalent */
+	if (src_matcher->num_of_mt != dst_matcher->num_of_mt) {
+		mlx5hws_err(ctx, "Src/dst matcher match templates mismatch\n");
+		return -EINVAL;
+	}
+
+	if (src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes >
+	    dst_matcher->action_ste[0].max_stes) {
+		mlx5hws_err(ctx, "Src/dst matcher max STEs mismatch\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < src_matcher->num_of_mt; i++) {
+		if (mlx5hws_definer_compare(src_matcher->mt[i].definer,
+					    dst_matcher->mt[i].definer)) {
+			mlx5hws_err(ctx, "Src/dst matcher definers mismatch\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+int mlx5hws_matcher_resize_set_target(struct mlx5hws_matcher *src_matcher,
+				      struct mlx5hws_matcher *dst_matcher)
+{
+	int ret = 0;
+
+	mutex_lock(&src_matcher->tbl->ctx->ctrl_lock);
+
+	ret = hws_matcher_resize_precheck(src_matcher, dst_matcher);
+	if (ret)
+		goto out;
+
+	src_matcher->resize_dst = dst_matcher;
+
+	ret = hws_matcher_resize_init(src_matcher);
+	if (ret)
+		src_matcher->resize_dst = NULL;
+
+out:
+	mutex_unlock(&src_matcher->tbl->ctx->ctrl_lock);
+	return ret;
+}
+
+int mlx5hws_matcher_resize_rule_move(struct mlx5hws_matcher *src_matcher,
+				     struct mlx5hws_rule *rule,
+				     struct mlx5hws_rule_attr *attr)
+{
+	struct mlx5hws_context *ctx = src_matcher->tbl->ctx;
+
+	if (unlikely(!mlx5hws_matcher_is_in_resize(src_matcher))) {
+		mlx5hws_err(ctx, "Matcher is not resizable or not in resize\n");
+		return -EINVAL;
+	}
+
+	if (unlikely(src_matcher != rule->matcher)) {
+		mlx5hws_err(ctx, "Rule doesn't belong to src matcher\n");
+		return -EINVAL;
+	}
+
+	return mlx5hws_rule_move_hws_add(rule, attr);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.h
new file mode 100644
index 000000000000..125391d1a114
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_MATCHER_H_
+#define MLX5HWS_MATCHER_H_
+
+/* We calculated that concatenating a collision table to the main table with
+ * 3% of the main table rows will be enough resources for high insertion
+ * success probability.
+ *
+ * The calculation: log2(2^x * 3 / 100) = log2(2^x) + log2(3/100) = x - 5.05 ~ 5
+ */
+#define MLX5HWS_MATCHER_ASSURED_ROW_RATIO 5
+/* Threshold to determine if amount of rules require a collision table */
+#define MLX5HWS_MATCHER_ASSURED_RULES_TH 10
+/* Required depth of an assured collision table */
+#define MLX5HWS_MATCHER_ASSURED_COL_TBL_DEPTH 4
+/* Required depth of the main large table */
+#define MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH 2
+
+enum mlx5hws_matcher_offset {
+	MLX5HWS_MATCHER_OFFSET_TAG_DW1 = 12,
+	MLX5HWS_MATCHER_OFFSET_TAG_DW0 = 13,
+};
+
+enum mlx5hws_matcher_flags {
+	MLX5HWS_MATCHER_FLAGS_COLLISION = 1 << 2,
+	MLX5HWS_MATCHER_FLAGS_RESIZABLE	= 1 << 3,
+};
+
+struct mlx5hws_match_template {
+	struct mlx5hws_definer *definer;
+	struct mlx5hws_definer_fc *fc;
+	u32 *match_param;
+	u8 match_criteria_enable;
+	u16 fc_sz;
+};
+
+struct mlx5hws_matcher_match_ste {
+	struct mlx5hws_pool_chunk ste;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+	struct mlx5hws_pool *pool;
+};
+
+struct mlx5hws_matcher_action_ste {
+	struct mlx5hws_pool_chunk ste;
+	struct mlx5hws_pool_chunk stc;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+	struct mlx5hws_pool *pool;
+	u8 max_stes;
+};
+
+struct mlx5hws_matcher_resize_data_node {
+	struct mlx5hws_pool_chunk stc;
+	u32 rtc_0_id;
+	u32 rtc_1_id;
+	struct mlx5hws_pool *pool;
+};
+
+struct mlx5hws_matcher_resize_data {
+	struct mlx5hws_matcher_resize_data_node action_ste[2];
+	u8 max_stes;
+	struct list_head list_node;
+};
+
+struct mlx5hws_matcher {
+	struct mlx5hws_table *tbl;
+	struct mlx5hws_matcher_attr attr;
+	struct mlx5hws_match_template *mt;
+	struct mlx5hws_action_template *at;
+	u8 num_of_at;
+	u8 num_of_mt;
+	/* enum mlx5hws_matcher_flags */
+	u8 flags;
+	u32 end_ft_id;
+	struct mlx5hws_matcher *col_matcher;
+	struct mlx5hws_matcher *resize_dst;
+	struct mlx5hws_matcher_match_ste match_ste;
+	struct mlx5hws_matcher_action_ste action_ste[2];
+	struct list_head list_node;
+	struct list_head resize_data;
+};
+
+static inline bool
+mlx5hws_matcher_mt_is_jumbo(struct mlx5hws_match_template *mt)
+{
+	return mlx5hws_definer_is_jumbo(mt->definer);
+}
+
+static inline bool mlx5hws_matcher_is_resizable(struct mlx5hws_matcher *matcher)
+{
+	return !!(matcher->flags & MLX5HWS_MATCHER_FLAGS_RESIZABLE);
+}
+
+static inline bool mlx5hws_matcher_is_in_resize(struct mlx5hws_matcher *matcher)
+{
+	return !!matcher->resize_dst;
+}
+
+static inline bool mlx5hws_matcher_is_insert_by_idx(struct mlx5hws_matcher *matcher)
+{
+	return matcher->attr.insert_mode == MLX5HWS_MATCHER_INSERT_BY_INDEX;
+}
+
+#endif /* MLX5HWS_MATCHER_H_ */
-- 
cgit v1.3-3-g829e


From 0869701cba3d4c9865a019d23b0d159aee90d23f Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:38:22 +0300
Subject: net/mlx5: HWS, added FW commands handling

This patch adds implementation of FW object handling, such
as creation/destruction, modification, and querying.

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c  | 1300 ++++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h  |  361 ++++++
 2 files changed, 1661 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c
new file mode 100644
index 000000000000..2c7b14172049
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.c
@@ -0,0 +1,1300 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+static enum mlx5_ifc_flow_destination_type
+hws_cmd_dest_type_to_ifc_dest_type(enum mlx5_flow_destination_type type)
+{
+	switch (type) {
+	case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+		return MLX5_IFC_FLOW_DESTINATION_TYPE_VPORT;
+	case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+		return MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	case MLX5_FLOW_DESTINATION_TYPE_TIR:
+		return MLX5_IFC_FLOW_DESTINATION_TYPE_TIR;
+	case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+		return MLX5_IFC_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
+	case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
+		return MLX5_IFC_FLOW_DESTINATION_TYPE_UPLINK;
+	case MLX5_FLOW_DESTINATION_TYPE_TABLE_TYPE:
+		return MLX5_IFC_FLOW_DESTINATION_TYPE_TABLE_TYPE;
+	case MLX5_FLOW_DESTINATION_TYPE_NONE:
+	case MLX5_FLOW_DESTINATION_TYPE_PORT:
+	case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
+	case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
+	case MLX5_FLOW_DESTINATION_TYPE_RANGE:
+	default:
+		pr_warn("HWS: unknown flow dest type %d\n", type);
+		return 0;
+	}
+};
+
+static int hws_cmd_general_obj_destroy(struct mlx5_core_dev *mdev,
+				       u32 object_type,
+				       u32 object_id)
+{
+	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, object_type);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, object_id);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev,
+				  struct mlx5hws_cmd_ft_create_attr *ft_attr,
+				  u32 *table_id)
+{
+	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {0};
+	void *ft_ctx;
+	int ret;
+
+	MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
+	MLX5_SET(create_flow_table_in, in, table_type, ft_attr->type);
+
+	ft_ctx = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
+	MLX5_SET(flow_table_context, ft_ctx, level, ft_attr->level);
+	MLX5_SET(flow_table_context, ft_ctx, rtc_valid, ft_attr->rtc_valid);
+	MLX5_SET(flow_table_context, ft_ctx, reformat_en, ft_attr->reformat_en);
+	MLX5_SET(flow_table_context, ft_ctx, decap_en, ft_attr->decap_en);
+
+	ret = mlx5_cmd_exec_inout(mdev, create_flow_table, in, out);
+	if (ret)
+		return ret;
+
+	*table_id = MLX5_GET(create_flow_table_out, out, table_id);
+
+	return 0;
+}
+
+int mlx5hws_cmd_flow_table_modify(struct mlx5_core_dev *mdev,
+				  struct mlx5hws_cmd_ft_modify_attr *ft_attr,
+				  u32 table_id)
+{
+	u32 in[MLX5_ST_SZ_DW(modify_flow_table_in)] = {0};
+	void *ft_ctx;
+
+	MLX5_SET(modify_flow_table_in, in, opcode, MLX5_CMD_OP_MODIFY_FLOW_TABLE);
+	MLX5_SET(modify_flow_table_in, in, table_type, ft_attr->type);
+	MLX5_SET(modify_flow_table_in, in, modify_field_select, ft_attr->modify_fs);
+	MLX5_SET(modify_flow_table_in, in, table_id, table_id);
+
+	ft_ctx = MLX5_ADDR_OF(modify_flow_table_in, in, flow_table_context);
+
+	MLX5_SET(flow_table_context, ft_ctx, table_miss_action, ft_attr->table_miss_action);
+	MLX5_SET(flow_table_context, ft_ctx, table_miss_id, ft_attr->table_miss_id);
+	MLX5_SET(flow_table_context, ft_ctx, hws.rtc_id_0, ft_attr->rtc_id_0);
+	MLX5_SET(flow_table_context, ft_ctx, hws.rtc_id_1, ft_attr->rtc_id_1);
+
+	return mlx5_cmd_exec_in(mdev, modify_flow_table, in);
+}
+
+int mlx5hws_cmd_flow_table_query(struct mlx5_core_dev *mdev,
+				 u32 table_id,
+				 struct mlx5hws_cmd_ft_query_attr *ft_attr,
+				 u64 *icm_addr_0, u64 *icm_addr_1)
+{
+	u32 out[MLX5_ST_SZ_DW(query_flow_table_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(query_flow_table_in)] = {0};
+	void *ft_ctx;
+	int ret;
+
+	MLX5_SET(query_flow_table_in, in, opcode, MLX5_CMD_OP_QUERY_FLOW_TABLE);
+	MLX5_SET(query_flow_table_in, in, table_type, ft_attr->type);
+	MLX5_SET(query_flow_table_in, in, table_id, table_id);
+
+	ret = mlx5_cmd_exec_inout(mdev, query_flow_table, in, out);
+	if (ret)
+		return ret;
+
+	ft_ctx = MLX5_ADDR_OF(query_flow_table_out, out, flow_table_context);
+	*icm_addr_0 = MLX5_GET64(flow_table_context, ft_ctx, sws.sw_owner_icm_root_0);
+	*icm_addr_1 = MLX5_GET64(flow_table_context, ft_ctx, sws.sw_owner_icm_root_1);
+
+	return ret;
+}
+
+int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
+				   u8 fw_ft_type, u32 table_id)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {0};
+
+	MLX5_SET(destroy_flow_table_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_TABLE);
+	MLX5_SET(destroy_flow_table_in, in, table_type, fw_ft_type);
+	MLX5_SET(destroy_flow_table_in, in, table_id, table_id);
+
+	return mlx5_cmd_exec_in(mdev, destroy_flow_table, in);
+}
+
+void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
+					  u32 table_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_FT_ALIAS, table_id);
+}
+
+static int hws_cmd_flow_group_create(struct mlx5_core_dev *mdev,
+				     struct mlx5hws_cmd_fg_attr *fg_attr,
+				     u32 *group_id)
+{
+	u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {0};
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	u32 *in;
+	int ret;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP);
+	MLX5_SET(create_flow_group_in, in, table_type, fg_attr->table_type);
+	MLX5_SET(create_flow_group_in, in, table_id, fg_attr->table_id);
+
+	ret = mlx5_cmd_exec_inout(mdev, create_flow_group, in, out);
+	if (ret)
+		goto out;
+
+	*group_id = MLX5_GET(create_flow_group_out, out, group_id);
+
+out:
+	kvfree(in);
+	return ret;
+}
+
+static int hws_cmd_flow_group_destroy(struct mlx5_core_dev *mdev,
+				      u32 ft_id, u32 fg_id, u8 ft_type)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {};
+
+	MLX5_SET(destroy_flow_group_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP);
+	MLX5_SET(destroy_flow_group_in, in, table_type, ft_type);
+	MLX5_SET(destroy_flow_group_in, in, table_id, ft_id);
+	MLX5_SET(destroy_flow_group_in, in, group_id, fg_id);
+
+	return mlx5_cmd_exec_in(mdev, destroy_flow_group, in);
+}
+
+int mlx5hws_cmd_set_fte(struct mlx5_core_dev *mdev,
+			u32 table_type,
+			u32 table_id,
+			u32 group_id,
+			struct mlx5hws_cmd_set_fte_attr *fte_attr)
+{
+	u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {0};
+	void *in_flow_context;
+	u32 dest_entry_sz;
+	u32 total_dest_sz;
+	u32 action_flags;
+	u8 *in_dests;
+	u32 inlen;
+	u32 *in;
+	int ret;
+	u32 i;
+
+	dest_entry_sz = fte_attr->extended_dest ?
+			MLX5_ST_SZ_BYTES(extended_dest_format) :
+			MLX5_ST_SZ_BYTES(dest_format);
+	total_dest_sz = dest_entry_sz * fte_attr->dests_num;
+	inlen = align((MLX5_ST_SZ_BYTES(set_fte_in) + total_dest_sz), DW_SIZE);
+	in = kzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY);
+	MLX5_SET(set_fte_in, in, table_type, table_type);
+	MLX5_SET(set_fte_in, in, table_id, table_id);
+
+	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
+	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
+	MLX5_SET(flow_context, in_flow_context, flow_source, fte_attr->flow_source);
+	MLX5_SET(flow_context, in_flow_context, extended_destination, fte_attr->extended_dest);
+	MLX5_SET(set_fte_in, in, ignore_flow_level, fte_attr->ignore_flow_level);
+
+	action_flags = fte_attr->action_flags;
+	MLX5_SET(flow_context, in_flow_context, action, action_flags);
+
+	if (action_flags & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+		MLX5_SET(flow_context, in_flow_context,
+			 packet_reformat_id, fte_attr->packet_reformat_id);
+	}
+
+	if (action_flags & (MLX5_FLOW_CONTEXT_ACTION_DECRYPT | MLX5_FLOW_CONTEXT_ACTION_ENCRYPT)) {
+		MLX5_SET(flow_context, in_flow_context,
+			 encrypt_decrypt_type, fte_attr->encrypt_decrypt_type);
+		MLX5_SET(flow_context, in_flow_context,
+			 encrypt_decrypt_obj_id, fte_attr->encrypt_decrypt_obj_id);
+	}
+
+	if (action_flags & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+		in_dests = (u8 *)MLX5_ADDR_OF(flow_context, in_flow_context, destination);
+
+		for (i = 0; i < fte_attr->dests_num; i++) {
+			struct mlx5hws_cmd_set_fte_dest *dest = &fte_attr->dests[i];
+			enum mlx5_ifc_flow_destination_type ifc_dest_type =
+				hws_cmd_dest_type_to_ifc_dest_type(dest->destination_type);
+
+			switch (dest->destination_type) {
+			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+				if (dest->ext_flags & MLX5HWS_CMD_EXT_DEST_ESW_OWNER_VHCA_ID) {
+					MLX5_SET(dest_format, in_dests,
+						 destination_eswitch_owner_vhca_id_valid, 1);
+					MLX5_SET(dest_format, in_dests,
+						 destination_eswitch_owner_vhca_id,
+						 dest->esw_owner_vhca_id);
+				}
+				fallthrough;
+			case MLX5_FLOW_DESTINATION_TYPE_TIR:
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+				MLX5_SET(dest_format, in_dests, destination_type, ifc_dest_type);
+				MLX5_SET(dest_format, in_dests, destination_id,
+					 dest->destination_id);
+				if (dest->ext_flags & MLX5HWS_CMD_EXT_DEST_REFORMAT) {
+					MLX5_SET(dest_format, in_dests, packet_reformat, 1);
+					MLX5_SET(extended_dest_format, in_dests, packet_reformat_id,
+						 dest->ext_reformat_id);
+				}
+				break;
+			default:
+				ret = -EOPNOTSUPP;
+				goto out;
+			}
+
+			in_dests = in_dests + dest_entry_sz;
+		}
+		MLX5_SET(flow_context, in_flow_context, destination_list_size, fte_attr->dests_num);
+	}
+
+	ret = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	if (ret)
+		mlx5_core_err(mdev, "Failed creating FLOW_TABLE_ENTRY\n");
+
+out:
+	kfree(in);
+	return ret;
+}
+
+int mlx5hws_cmd_delete_fte(struct mlx5_core_dev *mdev,
+			   u32 table_type,
+			   u32 table_id)
+{
+	u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {};
+
+	MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
+	MLX5_SET(delete_fte_in, in, table_type, table_type);
+	MLX5_SET(delete_fte_in, in, table_id, table_id);
+
+	return mlx5_cmd_exec_in(mdev, delete_fte, in);
+}
+
+struct mlx5hws_cmd_forward_tbl *
+mlx5hws_cmd_forward_tbl_create(struct mlx5_core_dev *mdev,
+			       struct mlx5hws_cmd_ft_create_attr *ft_attr,
+			       struct mlx5hws_cmd_set_fte_attr *fte_attr)
+{
+	struct mlx5hws_cmd_fg_attr fg_attr = {0};
+	struct mlx5hws_cmd_forward_tbl *tbl;
+	int ret;
+
+	tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+	if (!tbl)
+		return NULL;
+
+	ret = mlx5hws_cmd_flow_table_create(mdev, ft_attr, &tbl->ft_id);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create FT\n");
+		goto free_tbl;
+	}
+
+	fg_attr.table_id = tbl->ft_id;
+	fg_attr.table_type = ft_attr->type;
+
+	ret = hws_cmd_flow_group_create(mdev, &fg_attr, &tbl->fg_id);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create FG\n");
+		goto free_ft;
+	}
+
+	ret = mlx5hws_cmd_set_fte(mdev, ft_attr->type,
+				  tbl->ft_id, tbl->fg_id, fte_attr);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create FTE\n");
+		goto free_fg;
+	}
+
+	tbl->type = ft_attr->type;
+	return tbl;
+
+free_fg:
+	hws_cmd_flow_group_destroy(mdev, tbl->ft_id, tbl->fg_id, ft_attr->type);
+free_ft:
+	mlx5hws_cmd_flow_table_destroy(mdev, ft_attr->type, tbl->ft_id);
+free_tbl:
+	kfree(tbl);
+	return NULL;
+}
+
+void mlx5hws_cmd_forward_tbl_destroy(struct mlx5_core_dev *mdev,
+				     struct mlx5hws_cmd_forward_tbl *tbl)
+{
+	mlx5hws_cmd_delete_fte(mdev, tbl->type, tbl->ft_id);
+	hws_cmd_flow_group_destroy(mdev, tbl->ft_id, tbl->fg_id, tbl->type);
+	mlx5hws_cmd_flow_table_destroy(mdev, tbl->type, tbl->ft_id);
+	kfree(tbl);
+}
+
+void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
+					   u32 fw_ft_type,
+					   enum mlx5hws_table_type type,
+					   struct mlx5hws_cmd_ft_modify_attr *ft_attr)
+{
+	u32 default_miss_tbl;
+
+	if (type != MLX5HWS_TABLE_TYPE_FDB)
+		return;
+
+	ft_attr->modify_fs = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION;
+	ft_attr->type = fw_ft_type;
+	ft_attr->table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL;
+
+	default_miss_tbl = ctx->common_res[type].default_miss->ft_id;
+	if (!default_miss_tbl) {
+		pr_warn("HWS: no flow table ID for default miss\n");
+		return;
+	}
+
+	ft_attr->table_miss_id = default_miss_tbl;
+}
+
+int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
+			   u32 *rtc_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_rtc_in)] = {0};
+	void *attr;
+	int ret;
+
+	attr = MLX5_ADDR_OF(create_rtc_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, MLX5_OBJ_TYPE_RTC);
+
+	attr = MLX5_ADDR_OF(create_rtc_in, in, rtc);
+	MLX5_SET(rtc, attr, ste_format_0, rtc_attr->is_frst_jumbo ?
+		 MLX5_IFC_RTC_STE_FORMAT_11DW :
+		 MLX5_IFC_RTC_STE_FORMAT_8DW);
+
+	if (rtc_attr->is_scnd_range) {
+		MLX5_SET(rtc, attr, ste_format_1, MLX5_IFC_RTC_STE_FORMAT_RANGE);
+		MLX5_SET(rtc, attr, num_match_ste, 2);
+	}
+
+	MLX5_SET(rtc, attr, pd, rtc_attr->pd);
+	MLX5_SET(rtc, attr, update_method, rtc_attr->fw_gen_wqe);
+	MLX5_SET(rtc, attr, update_index_mode, rtc_attr->update_index_mode);
+	MLX5_SET(rtc, attr, access_index_mode, rtc_attr->access_index_mode);
+	MLX5_SET(rtc, attr, num_hash_definer, rtc_attr->num_hash_definer);
+	MLX5_SET(rtc, attr, log_depth, rtc_attr->log_depth);
+	MLX5_SET(rtc, attr, log_hash_size, rtc_attr->log_size);
+	MLX5_SET(rtc, attr, table_type, rtc_attr->table_type);
+	MLX5_SET(rtc, attr, num_hash_definer, rtc_attr->num_hash_definer);
+	MLX5_SET(rtc, attr, match_definer_0, rtc_attr->match_definer_0);
+	MLX5_SET(rtc, attr, match_definer_1, rtc_attr->match_definer_1);
+	MLX5_SET(rtc, attr, stc_id, rtc_attr->stc_base);
+	MLX5_SET(rtc, attr, ste_table_base_id, rtc_attr->ste_base);
+	MLX5_SET(rtc, attr, ste_table_offset, rtc_attr->ste_offset);
+	MLX5_SET(rtc, attr, miss_flow_table_id, rtc_attr->miss_ft_id);
+	MLX5_SET(rtc, attr, reparse_mode, rtc_attr->reparse_mode);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create RTC\n");
+		goto out;
+	}
+
+	*rtc_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+void mlx5hws_cmd_rtc_destroy(struct mlx5_core_dev *mdev, u32 rtc_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_RTC, rtc_id);
+}
+
+int mlx5hws_cmd_stc_create(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_stc_create_attr *stc_attr,
+			   u32 *stc_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_stc_in)] = {0};
+	void *attr;
+	int ret;
+
+	attr = MLX5_ADDR_OF(create_stc_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, MLX5_OBJ_TYPE_STC);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, op_param.create.log_obj_range, stc_attr->log_obj_range);
+
+	attr = MLX5_ADDR_OF(create_stc_in, in, stc);
+	MLX5_SET(stc, attr, table_type, stc_attr->table_type);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create STC\n");
+		goto out;
+	}
+
+	*stc_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+void mlx5hws_cmd_stc_destroy(struct mlx5_core_dev *mdev, u32 stc_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_STC, stc_id);
+}
+
+static int
+hws_cmd_stc_modify_set_stc_param(struct mlx5_core_dev *mdev,
+				 struct mlx5hws_cmd_stc_modify_attr *stc_attr,
+				 void *stc_param)
+{
+	switch (stc_attr->action_type) {
+	case MLX5_IFC_STC_ACTION_TYPE_COUNTER:
+		MLX5_SET(stc_ste_param_flow_counter, stc_param, flow_counter_id, stc_attr->id);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_TIR:
+		MLX5_SET(stc_ste_param_tir, stc_param, tirn, stc_attr->dest_tir_num);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT:
+		MLX5_SET(stc_ste_param_table, stc_param, table_id, stc_attr->dest_table_id);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_ACC_MODIFY_LIST:
+		MLX5_SET(stc_ste_param_header_modify_list, stc_param,
+			 header_modify_pattern_id, stc_attr->modify_header.pattern_id);
+		MLX5_SET(stc_ste_param_header_modify_list, stc_param,
+			 header_modify_argument_id, stc_attr->modify_header.arg_id);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_HEADER_REMOVE:
+		MLX5_SET(stc_ste_param_remove, stc_param, action_type,
+			 MLX5_MODIFICATION_TYPE_REMOVE);
+		MLX5_SET(stc_ste_param_remove, stc_param, decap,
+			 stc_attr->remove_header.decap);
+		MLX5_SET(stc_ste_param_remove, stc_param, remove_start_anchor,
+			 stc_attr->remove_header.start_anchor);
+		MLX5_SET(stc_ste_param_remove, stc_param, remove_end_anchor,
+			 stc_attr->remove_header.end_anchor);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_HEADER_INSERT:
+		MLX5_SET(stc_ste_param_insert, stc_param, action_type,
+			 MLX5_MODIFICATION_TYPE_INSERT);
+		MLX5_SET(stc_ste_param_insert, stc_param, encap,
+			 stc_attr->insert_header.encap);
+		MLX5_SET(stc_ste_param_insert, stc_param, inline_data,
+			 stc_attr->insert_header.is_inline);
+		MLX5_SET(stc_ste_param_insert, stc_param, insert_anchor,
+			 stc_attr->insert_header.insert_anchor);
+		/* HW gets the next 2 sizes in words */
+		MLX5_SET(stc_ste_param_insert, stc_param, insert_size,
+			 stc_attr->insert_header.header_size / W_SIZE);
+		MLX5_SET(stc_ste_param_insert, stc_param, insert_offset,
+			 stc_attr->insert_header.insert_offset / W_SIZE);
+		MLX5_SET(stc_ste_param_insert, stc_param, insert_argument,
+			 stc_attr->insert_header.arg_id);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_COPY:
+	case MLX5_IFC_STC_ACTION_TYPE_SET:
+	case MLX5_IFC_STC_ACTION_TYPE_ADD:
+	case MLX5_IFC_STC_ACTION_TYPE_ADD_FIELD:
+		*(__be64 *)stc_param = stc_attr->modify_action.data;
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_VPORT:
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_UPLINK:
+		MLX5_SET(stc_ste_param_vport, stc_param, vport_number,
+			 stc_attr->vport.vport_num);
+		MLX5_SET(stc_ste_param_vport, stc_param, eswitch_owner_vhca_id,
+			 stc_attr->vport.esw_owner_vhca_id);
+		MLX5_SET(stc_ste_param_vport, stc_param, eswitch_owner_vhca_id_valid,
+			 stc_attr->vport.eswitch_owner_vhca_id_valid);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_DROP:
+	case MLX5_IFC_STC_ACTION_TYPE_NOP:
+	case MLX5_IFC_STC_ACTION_TYPE_TAG:
+	case MLX5_IFC_STC_ACTION_TYPE_ALLOW:
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_ASO:
+		MLX5_SET(stc_ste_param_execute_aso, stc_param, aso_object_id,
+			 stc_attr->aso.devx_obj_id);
+		MLX5_SET(stc_ste_param_execute_aso, stc_param, return_reg_id,
+			 stc_attr->aso.return_reg_id);
+		MLX5_SET(stc_ste_param_execute_aso, stc_param, aso_type,
+			 stc_attr->aso.aso_type);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE:
+		MLX5_SET(stc_ste_param_ste_table, stc_param, ste_obj_id,
+			 stc_attr->ste_table.ste_obj_id);
+		MLX5_SET(stc_ste_param_ste_table, stc_param, match_definer_id,
+			 stc_attr->ste_table.match_definer_id);
+		MLX5_SET(stc_ste_param_ste_table, stc_param, log_hash_size,
+			 stc_attr->ste_table.log_hash_size);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_REMOVE_WORDS:
+		MLX5_SET(stc_ste_param_remove_words, stc_param, action_type,
+			 MLX5_MODIFICATION_TYPE_REMOVE_WORDS);
+		MLX5_SET(stc_ste_param_remove_words, stc_param, remove_start_anchor,
+			 stc_attr->remove_words.start_anchor);
+		MLX5_SET(stc_ste_param_remove_words, stc_param,
+			 remove_size, stc_attr->remove_words.num_of_words);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_CRYPTO_IPSEC_ENCRYPTION:
+		MLX5_SET(stc_ste_param_ipsec_encrypt, stc_param, ipsec_object_id,
+			 stc_attr->id);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_CRYPTO_IPSEC_DECRYPTION:
+		MLX5_SET(stc_ste_param_ipsec_decrypt, stc_param, ipsec_object_id,
+			 stc_attr->id);
+		break;
+	case MLX5_IFC_STC_ACTION_TYPE_TRAILER:
+		MLX5_SET(stc_ste_param_trailer, stc_param, command,
+			 stc_attr->reformat_trailer.op);
+		MLX5_SET(stc_ste_param_trailer, stc_param, type,
+			 stc_attr->reformat_trailer.type);
+		MLX5_SET(stc_ste_param_trailer, stc_param, length,
+			 stc_attr->reformat_trailer.size);
+		break;
+	default:
+		mlx5_core_err(mdev, "Not supported type %d\n", stc_attr->action_type);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int mlx5hws_cmd_stc_modify(struct mlx5_core_dev *mdev,
+			   u32 stc_id,
+			   struct mlx5hws_cmd_stc_modify_attr *stc_attr)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_stc_in)] = {0};
+	void *stc_param;
+	void *attr;
+	int ret;
+
+	attr = MLX5_ADDR_OF(create_stc_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_MODIFY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, MLX5_OBJ_TYPE_STC);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, stc_id);
+	MLX5_SET(general_obj_in_cmd_hdr, in,
+		 op_param.query.obj_offset, stc_attr->stc_offset);
+
+	attr = MLX5_ADDR_OF(create_stc_in, in, stc);
+	MLX5_SET(stc, attr, ste_action_offset, stc_attr->action_offset);
+	MLX5_SET(stc, attr, action_type, stc_attr->action_type);
+	MLX5_SET(stc, attr, reparse_mode, stc_attr->reparse_mode);
+	MLX5_SET64(stc, attr, modify_field_select,
+		   MLX5_IFC_MODIFY_STC_FIELD_SELECT_NEW_STC);
+
+	/* Set destination TIRN, TAG, FT ID, STE ID */
+	stc_param = MLX5_ADDR_OF(stc, attr, stc_param);
+	ret = hws_cmd_stc_modify_set_stc_param(mdev, stc_attr, stc_param);
+	if (ret)
+		return ret;
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret)
+		mlx5_core_err(mdev, "Failed to modify STC FW action_type %d\n",
+			      stc_attr->action_type);
+
+	return ret;
+}
+
+int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
+			   u16 log_obj_range,
+			   u32 pd,
+			   u32 *arg_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_arg_in)] = {0};
+	void *attr;
+	int ret;
+
+	attr = MLX5_ADDR_OF(create_arg_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, op_param.create.log_obj_range, log_obj_range);
+
+	attr = MLX5_ADDR_OF(create_arg_in, in, arg);
+	MLX5_SET(arg, attr, access_pd, pd);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create ARG\n");
+		goto out;
+	}
+
+	*arg_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+void mlx5hws_cmd_arg_destroy(struct mlx5_core_dev *mdev,
+			     u32 arg_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT, arg_id);
+}
+
+int mlx5hws_cmd_header_modify_pattern_create(struct mlx5_core_dev *mdev,
+					     u32 pattern_length,
+					     u8 *actions,
+					     u32 *ptrn_id)
+{
+	u32 in[MLX5_ST_SZ_DW(create_header_modify_pattern_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	int num_of_actions;
+	u64 *pattern_data;
+	void *pattern;
+	void *attr;
+	int ret;
+	int i;
+
+	if (pattern_length > MLX5_MAX_ACTIONS_DATA_IN_HEADER_MODIFY) {
+		mlx5_core_err(mdev, "Pattern length %d exceeds limit %d\n",
+			      pattern_length, MLX5_MAX_ACTIONS_DATA_IN_HEADER_MODIFY);
+		return -EINVAL;
+	}
+
+	attr = MLX5_ADDR_OF(create_header_modify_pattern_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, MLX5_OBJ_TYPE_MODIFY_HDR_PATTERN);
+
+	pattern = MLX5_ADDR_OF(create_header_modify_pattern_in, in, pattern);
+	/* Pattern_length is in ddwords */
+	MLX5_SET(header_modify_pattern_in, pattern, pattern_length, pattern_length / (2 * DW_SIZE));
+
+	pattern_data = (u64 *)MLX5_ADDR_OF(header_modify_pattern_in, pattern, pattern_data);
+	memcpy(pattern_data, actions, pattern_length);
+
+	num_of_actions = pattern_length / MLX5HWS_MODIFY_ACTION_SIZE;
+	for (i = 0; i < num_of_actions; i++) {
+		int type;
+
+		type = MLX5_GET(set_action_in, &pattern_data[i], action_type);
+		if (type != MLX5_MODIFICATION_TYPE_COPY &&
+		    type != MLX5_MODIFICATION_TYPE_ADD_FIELD)
+			/* Action typ-copy use all bytes for control */
+			MLX5_SET(set_action_in, &pattern_data[i], data, 0);
+	}
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create header_modify_pattern\n");
+		goto out;
+	}
+
+	*ptrn_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+void mlx5hws_cmd_header_modify_pattern_destroy(struct mlx5_core_dev *mdev,
+					       u32 ptrn_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_MODIFY_HDR_PATTERN, ptrn_id);
+}
+
+int mlx5hws_cmd_ste_create(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_ste_create_attr *ste_attr,
+			   u32 *ste_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_ste_in)] = {0};
+	void *attr;
+	int ret;
+
+	attr = MLX5_ADDR_OF(create_ste_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, MLX5_OBJ_TYPE_STE);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, op_param.create.log_obj_range, ste_attr->log_obj_range);
+
+	attr = MLX5_ADDR_OF(create_ste_in, in, ste);
+	MLX5_SET(ste, attr, table_type, ste_attr->table_type);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create STE\n");
+		goto out;
+	}
+
+	*ste_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+void mlx5hws_cmd_ste_destroy(struct mlx5_core_dev *mdev, u32 ste_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_STE, ste_id);
+}
+
+int mlx5hws_cmd_definer_create(struct mlx5_core_dev *mdev,
+			       struct mlx5hws_cmd_definer_create_attr *def_attr,
+			       u32 *definer_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_definer_in)] = {0};
+	void *ptr;
+	int ret;
+
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 in, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 in, obj_type, MLX5_OBJ_TYPE_MATCH_DEFINER);
+
+	ptr = MLX5_ADDR_OF(create_definer_in, in, definer);
+	MLX5_SET(definer, ptr, format_id, MLX5_IFC_DEFINER_FORMAT_ID_SELECT);
+
+	MLX5_SET(definer, ptr, format_select_dw0, def_attr->dw_selector[0]);
+	MLX5_SET(definer, ptr, format_select_dw1, def_attr->dw_selector[1]);
+	MLX5_SET(definer, ptr, format_select_dw2, def_attr->dw_selector[2]);
+	MLX5_SET(definer, ptr, format_select_dw3, def_attr->dw_selector[3]);
+	MLX5_SET(definer, ptr, format_select_dw4, def_attr->dw_selector[4]);
+	MLX5_SET(definer, ptr, format_select_dw5, def_attr->dw_selector[5]);
+	MLX5_SET(definer, ptr, format_select_dw6, def_attr->dw_selector[6]);
+	MLX5_SET(definer, ptr, format_select_dw7, def_attr->dw_selector[7]);
+	MLX5_SET(definer, ptr, format_select_dw8, def_attr->dw_selector[8]);
+
+	MLX5_SET(definer, ptr, format_select_byte0, def_attr->byte_selector[0]);
+	MLX5_SET(definer, ptr, format_select_byte1, def_attr->byte_selector[1]);
+	MLX5_SET(definer, ptr, format_select_byte2, def_attr->byte_selector[2]);
+	MLX5_SET(definer, ptr, format_select_byte3, def_attr->byte_selector[3]);
+	MLX5_SET(definer, ptr, format_select_byte4, def_attr->byte_selector[4]);
+	MLX5_SET(definer, ptr, format_select_byte5, def_attr->byte_selector[5]);
+	MLX5_SET(definer, ptr, format_select_byte6, def_attr->byte_selector[6]);
+	MLX5_SET(definer, ptr, format_select_byte7, def_attr->byte_selector[7]);
+
+	ptr = MLX5_ADDR_OF(definer, ptr, match_mask);
+	memcpy(ptr, def_attr->match_mask, MLX5_FLD_SZ_BYTES(definer, match_mask));
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create Definer\n");
+		goto out;
+	}
+
+	*definer_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+void mlx5hws_cmd_definer_destroy(struct mlx5_core_dev *mdev,
+				 u32 definer_id)
+{
+	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_MATCH_DEFINER, definer_id);
+}
+
+int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
+				       struct mlx5hws_cmd_packet_reformat_create_attr *attr,
+				       u32 *reformat_id)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_out)] = {0};
+	size_t insz, cmd_data_sz, cmd_total_sz;
+	void *prctx;
+	void *pdata;
+	void *in;
+	int ret;
+
+	cmd_total_sz = MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in);
+	cmd_total_sz += MLX5_ST_SZ_BYTES(packet_reformat_context_in);
+	cmd_data_sz = MLX5_FLD_SZ_BYTES(packet_reformat_context_in, reformat_data);
+	insz = align(cmd_total_sz + attr->data_sz - cmd_data_sz, DW_SIZE);
+	in = kzalloc(insz, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(alloc_packet_reformat_context_in, in, opcode,
+		 MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT);
+
+	prctx = MLX5_ADDR_OF(alloc_packet_reformat_context_in, in,
+			     packet_reformat_context);
+	pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data);
+
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_type, attr->type);
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_param_0, attr->reformat_param_0);
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, attr->data_sz);
+	memcpy(pdata, attr->data, attr->data_sz);
+
+	ret = mlx5_cmd_exec(mdev, in, insz, out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create packet reformat\n");
+		goto out;
+	}
+
+	*reformat_id = MLX5_GET(alloc_packet_reformat_out, out, packet_reformat_id);
+out:
+	kfree(in);
+	return ret;
+}
+
+int mlx5hws_cmd_packet_reformat_destroy(struct mlx5_core_dev *mdev,
+					u32 reformat_id)
+{
+	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_in)] = {0};
+	int ret;
+
+	MLX5_SET(dealloc_packet_reformat_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
+	MLX5_SET(dealloc_packet_reformat_in, in,
+		 packet_reformat_id, reformat_id);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret)
+		mlx5_core_err(mdev, "Failed to destroy packet_reformat\n");
+
+	return ret;
+}
+
+int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_sq_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(modify_sq_in)] = {0};
+	void *sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
+	int ret;
+
+	MLX5_SET(modify_sq_in, in, opcode, MLX5_CMD_OP_MODIFY_SQ);
+	MLX5_SET(modify_sq_in, in, sqn, sqn);
+	MLX5_SET(modify_sq_in, in, sq_state, MLX5_SQC_STATE_RST);
+	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RDY);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret)
+		mlx5_core_err(mdev, "Failed to modify SQ\n");
+
+	return ret;
+}
+
+int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
+					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr)
+{
+	u32 out[MLX5_ST_SZ_DW(allow_other_vhca_access_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(allow_other_vhca_access_in)] = {0};
+	void *key;
+	int ret;
+
+	MLX5_SET(allow_other_vhca_access_in,
+		 in, opcode, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS);
+	MLX5_SET(allow_other_vhca_access_in,
+		 in, object_type_to_be_accessed, attr->obj_type);
+	MLX5_SET(allow_other_vhca_access_in,
+		 in, object_id_to_be_accessed, attr->obj_id);
+
+	key = MLX5_ADDR_OF(allow_other_vhca_access_in, in, access_key);
+	memcpy(key, attr->access_key, sizeof(attr->access_key));
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret)
+		mlx5_core_err(mdev, "Failed to execute ALLOW_OTHER_VHCA_ACCESS command\n");
+
+	return ret;
+}
+
+int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
+				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
+				 u32 *obj_id)
+{
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
+	u32 in[MLX5_ST_SZ_DW(create_alias_obj_in)] = {0};
+	void *attr;
+	void *key;
+	int ret;
+
+	attr = MLX5_ADDR_OF(create_alias_obj_in, in, hdr);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr,
+		 attr, obj_type, alias_attr->obj_type);
+	MLX5_SET(general_obj_in_cmd_hdr, attr, op_param.create.alias_object, 1);
+
+	attr = MLX5_ADDR_OF(create_alias_obj_in, in, alias_ctx);
+	MLX5_SET(alias_context, attr, vhca_id_to_be_accessed, alias_attr->vhca_id);
+	MLX5_SET(alias_context, attr, object_id_to_be_accessed, alias_attr->obj_id);
+
+	key = MLX5_ADDR_OF(alias_context, attr, access_key);
+	memcpy(key, alias_attr->access_key, sizeof(alias_attr->access_key));
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to create ALIAS OBJ\n");
+		goto out;
+	}
+
+	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+out:
+	return ret;
+}
+
+int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
+				  u16 obj_type,
+				  u32 obj_id)
+{
+	return hws_cmd_general_obj_destroy(mdev, obj_type, obj_id);
+}
+
+int mlx5hws_cmd_generate_wqe(struct mlx5_core_dev *mdev,
+			     struct mlx5hws_cmd_generate_wqe_attr *attr,
+			     struct mlx5_cqe64 *ret_cqe)
+{
+	u32 out[MLX5_ST_SZ_DW(generate_wqe_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(generate_wqe_in)] = {0};
+	u8 status;
+	void *ptr;
+	int ret;
+
+	MLX5_SET(generate_wqe_in, in, opcode, MLX5_CMD_OP_GENERATE_WQE);
+	MLX5_SET(generate_wqe_in, in, pdn, attr->pdn);
+
+	ptr = MLX5_ADDR_OF(generate_wqe_in, in, wqe_ctrl);
+	memcpy(ptr, attr->wqe_ctrl, MLX5_FLD_SZ_BYTES(generate_wqe_in, wqe_ctrl));
+
+	ptr = MLX5_ADDR_OF(generate_wqe_in, in, wqe_gta_ctrl);
+	memcpy(ptr, attr->gta_ctrl, MLX5_FLD_SZ_BYTES(generate_wqe_in, wqe_gta_ctrl));
+
+	ptr = MLX5_ADDR_OF(generate_wqe_in, in, wqe_gta_data_0);
+	memcpy(ptr, attr->gta_data_0, MLX5_FLD_SZ_BYTES(generate_wqe_in, wqe_gta_data_0));
+
+	if (attr->gta_data_1) {
+		ptr = MLX5_ADDR_OF(generate_wqe_in, in, wqe_gta_data_1);
+		memcpy(ptr, attr->gta_data_1, MLX5_FLD_SZ_BYTES(generate_wqe_in, wqe_gta_data_1));
+	}
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to write GTA WQE using FW\n");
+		return ret;
+	}
+
+	status = MLX5_GET(generate_wqe_out, out, status);
+	if (status) {
+		mlx5_core_err(mdev, "Invalid FW CQE status %d\n", status);
+		return -EINVAL;
+	}
+
+	ptr = MLX5_ADDR_OF(generate_wqe_out, out, cqe_data);
+	memcpy(ret_cqe, ptr, sizeof(*ret_cqe));
+
+	return ret;
+}
+
+int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_query_caps *caps)
+{
+	u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {0};
+	u32 out_size;
+	u32 *out;
+	int ret;
+
+	out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	out = kzalloc(out_size, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+	MLX5_SET(query_hca_cap_in, in, op_mod,
+		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE | HCA_CAP_OPMOD_GET_CUR);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to query device caps\n");
+		goto out;
+	}
+
+	caps->wqe_based_update =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap.wqe_based_flow_table_update_cap);
+
+	caps->eswitch_manager = MLX5_GET(query_hca_cap_out, out,
+					 capability.cmd_hca_cap.eswitch_manager);
+
+	caps->flex_protocols = MLX5_GET(query_hca_cap_out, out,
+					capability.cmd_hca_cap.flex_parser_protocols);
+
+	if (caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_TLV_OPTION_0_ENABLED)
+		caps->flex_parser_id_geneve_tlv_option_0 =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.cmd_hca_cap.flex_parser_id_geneve_tlv_option_0);
+
+	if (caps->flex_protocols & MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED)
+		caps->flex_parser_id_mpls_over_gre =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.cmd_hca_cap.flex_parser_id_outer_first_mpls_over_gre);
+
+	if (caps->flex_protocols & MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED)
+		caps->flex_parser_id_mpls_over_udp =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.cmd_hca_cap.flex_parser_id_outer_first_mpls_over_udp_label);
+
+	caps->log_header_modify_argument_granularity =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap.log_header_modify_argument_granularity);
+
+	caps->log_header_modify_argument_granularity -=
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap.log_header_modify_argument_granularity_offset);
+
+	caps->log_header_modify_argument_max_alloc =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap.log_header_modify_argument_max_alloc);
+
+	caps->definer_format_sup =
+		MLX5_GET64(query_hca_cap_out, out,
+			   capability.cmd_hca_cap.match_definer_format_supported);
+
+	caps->vhca_id = MLX5_GET(query_hca_cap_out, out,
+				 capability.cmd_hca_cap.vhca_id);
+
+	caps->sq_ts_format = MLX5_GET(query_hca_cap_out, out,
+				      capability.cmd_hca_cap.sq_ts_format);
+
+	caps->ipsec_offload = MLX5_GET(query_hca_cap_out, out,
+				       capability.cmd_hca_cap.ipsec_offload);
+
+	MLX5_SET(query_hca_cap_in, in, op_mod,
+		 MLX5_GET_HCA_CAP_OP_MOD_GENERAL_DEVICE_2 | HCA_CAP_OPMOD_GET_CUR);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to query device caps 2\n");
+		goto out;
+	}
+
+	caps->full_dw_jumbo_support =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.format_select_dw_8_6_ext);
+
+	caps->format_select_gtpu_dw_0 =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.format_select_dw_gtpu_dw_0);
+
+	caps->format_select_gtpu_dw_1 =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.format_select_dw_gtpu_dw_1);
+
+	caps->format_select_gtpu_dw_2 =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.format_select_dw_gtpu_dw_2);
+
+	caps->format_select_gtpu_ext_dw_0 =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.format_select_dw_gtpu_first_ext_dw_0);
+
+	caps->supp_type_gen_wqe =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.generate_wqe_type);
+
+	caps->flow_table_hash_type =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.cmd_hca_cap_2.flow_table_hash_type);
+
+	MLX5_SET(query_hca_cap_in, in, op_mod,
+		 MLX5_GET_HCA_CAP_OP_MOD_NIC_FLOW_TABLE | HCA_CAP_OPMOD_GET_CUR);
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to query flow table caps\n");
+		goto out;
+	}
+
+	caps->nic_ft.max_level =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.flow_table_nic_cap.flow_table_properties_nic_receive.max_ft_level);
+
+	caps->nic_ft.reparse =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.flow_table_nic_cap.flow_table_properties_nic_receive.reparse);
+
+	caps->nic_ft.ignore_flow_level_rtc_valid =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.flow_table_nic_cap.flow_table_properties_nic_receive.ignore_flow_level_rtc_valid);
+
+	caps->flex_parser_ok_bits_supp =
+		MLX5_GET(query_hca_cap_out, out,
+			 capability.flow_table_nic_cap.flow_table_properties_nic_receive.ft_field_support.geneve_tlv_option_0_exist);
+
+	if (caps->wqe_based_update) {
+		MLX5_SET(query_hca_cap_in, in, op_mod,
+			 MLX5_GET_HCA_CAP_OP_MOD_WQE_BASED_FLOW_TABLE | HCA_CAP_OPMOD_GET_CUR);
+
+		ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+		if (ret) {
+			mlx5_core_err(mdev, "Failed to query WQE based FT caps\n");
+			goto out;
+		}
+
+		caps->rtc_reparse_mode =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.rtc_reparse_mode);
+
+		caps->ste_format =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.ste_format);
+
+		caps->rtc_index_mode =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.rtc_index_mode);
+
+		caps->rtc_log_depth_max =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.rtc_log_depth_max);
+
+		caps->ste_alloc_log_max =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.ste_alloc_log_max);
+
+		caps->ste_alloc_log_gran =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.ste_alloc_log_granularity);
+
+		caps->trivial_match_definer =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.trivial_match_definer);
+
+		caps->stc_alloc_log_max =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.stc_alloc_log_max);
+
+		caps->stc_alloc_log_gran =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.stc_alloc_log_granularity);
+
+		caps->rtc_hash_split_table =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.rtc_hash_split_table);
+
+		caps->rtc_linear_lookup_table =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.rtc_linear_lookup_table);
+
+		caps->access_index_mode =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.access_index_mode);
+
+		caps->linear_match_definer =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.linear_match_definer_reg_c3);
+
+		caps->rtc_max_hash_def_gen_wqe =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.rtc_max_num_hash_definer_gen_wqe);
+
+		caps->supp_ste_format_gen_wqe =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.ste_format_gen_wqe);
+
+		caps->fdb_tir_stc =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.wqe_based_flow_table_cap.fdb_jump_to_tir_stc);
+	}
+
+	if (caps->eswitch_manager) {
+		MLX5_SET(query_hca_cap_in, in, op_mod,
+			 MLX5_GET_HCA_CAP_OP_MOD_ESW_FLOW_TABLE | HCA_CAP_OPMOD_GET_CUR);
+
+		ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+		if (ret) {
+			mlx5_core_err(mdev, "Failed to query flow table esw caps\n");
+			goto out;
+		}
+
+		caps->fdb_ft.max_level =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.flow_table_nic_cap.flow_table_properties_nic_receive.max_ft_level);
+
+		caps->fdb_ft.reparse =
+			MLX5_GET(query_hca_cap_out, out,
+				 capability.flow_table_nic_cap.flow_table_properties_nic_receive.reparse);
+
+		MLX5_SET(query_hca_cap_in, in, op_mod,
+			 MLX5_SET_HCA_CAP_OP_MOD_ESW | HCA_CAP_OPMOD_GET_CUR);
+
+		ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+		if (ret) {
+			mlx5_core_err(mdev, "Failed to query eswitch capabilities\n");
+			goto out;
+		}
+
+		if (MLX5_GET(query_hca_cap_out, out,
+			     capability.esw_cap.esw_manager_vport_number_valid))
+			caps->eswitch_manager_vport_number =
+				MLX5_GET(query_hca_cap_out, out,
+					 capability.esw_cap.esw_manager_vport_number);
+
+		caps->merged_eswitch = MLX5_GET(query_hca_cap_out, out,
+						capability.esw_cap.merged_eswitch);
+	}
+
+	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to query device attributes\n");
+		goto out;
+	}
+
+	snprintf(caps->fw_ver, sizeof(caps->fw_ver), "%d.%d.%d",
+		 fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev));
+
+	caps->is_ecpf = mlx5_core_is_ecpf_esw_manager(mdev);
+
+out:
+	kfree(out);
+	return ret;
+}
+
+int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function,
+			   u16 vport_number, u16 *gvmi)
+{
+	bool ec_vf_func = other_function ? mlx5_core_is_ec_vf_vport(mdev, vport_number) : false;
+	u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {};
+	int out_size;
+	void *out;
+	int err;
+
+	out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	out = kzalloc(out_size, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+	MLX5_SET(query_hca_cap_in, in, other_function, other_function);
+	MLX5_SET(query_hca_cap_in, in, function_id,
+		 mlx5_vport_to_func_id(mdev, vport_number, ec_vf_func));
+	MLX5_SET(query_hca_cap_in, in, ec_vf_function, ec_vf_func);
+	MLX5_SET(query_hca_cap_in, in, op_mod,
+		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 | HCA_CAP_OPMOD_GET_CUR);
+
+	err = mlx5_cmd_exec_inout(mdev, query_hca_cap, in, out);
+	if (err) {
+		kfree(out);
+		return err;
+	}
+
+	*gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id);
+
+	kfree(out);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h
new file mode 100644
index 000000000000..2fbcf4ff571a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_cmd.h
@@ -0,0 +1,361 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_CMD_H_
+#define MLX5HWS_CMD_H_
+
+#define WIRE_PORT 0xFFFF
+
+#define ACCESS_KEY_LEN	32
+
+enum mlx5hws_cmd_ext_dest_flags {
+	MLX5HWS_CMD_EXT_DEST_REFORMAT = 1 << 0,
+	MLX5HWS_CMD_EXT_DEST_ESW_OWNER_VHCA_ID = 1 << 1,
+};
+
+struct mlx5hws_cmd_set_fte_dest {
+	u8 destination_type;
+	u32 destination_id;
+	enum mlx5hws_cmd_ext_dest_flags ext_flags;
+	u32 ext_reformat_id;
+	u16 esw_owner_vhca_id;
+};
+
+struct mlx5hws_cmd_set_fte_attr {
+	u32 action_flags;
+	bool ignore_flow_level;
+	u8 flow_source;
+	u8 extended_dest;
+	u8 encrypt_decrypt_type;
+	u32 encrypt_decrypt_obj_id;
+	u32 packet_reformat_id;
+	u32 dests_num;
+	struct mlx5hws_cmd_set_fte_dest *dests;
+};
+
+struct mlx5hws_cmd_ft_create_attr {
+	u8 type;
+	u8 level;
+	bool rtc_valid;
+	bool decap_en;
+	bool reformat_en;
+};
+
+struct mlx5hws_cmd_ft_modify_attr {
+	u8 type;
+	u32 rtc_id_0;
+	u32 rtc_id_1;
+	u32 table_miss_id;
+	u8 table_miss_action;
+	u64 modify_fs;
+};
+
+struct mlx5hws_cmd_ft_query_attr {
+	u8 type;
+};
+
+struct mlx5hws_cmd_fg_attr {
+	u32 table_id;
+	u32 table_type;
+};
+
+struct mlx5hws_cmd_forward_tbl {
+	u8 type;
+	u32 ft_id;
+	u32 fg_id;
+	u32 refcount;
+};
+
+struct mlx5hws_cmd_rtc_create_attr {
+	u32 pd;
+	u32 stc_base;
+	u32 ste_base;
+	u32 ste_offset;
+	u32 miss_ft_id;
+	bool fw_gen_wqe;
+	u8 update_index_mode;
+	u8 access_index_mode;
+	u8 num_hash_definer;
+	u8 log_depth;
+	u8 log_size;
+	u8 table_type;
+	u8 match_definer_0;
+	u8 match_definer_1;
+	u8 reparse_mode;
+	bool is_frst_jumbo;
+	bool is_scnd_range;
+};
+
+struct mlx5hws_cmd_alias_obj_create_attr {
+	u32 obj_id;
+	u16 vhca_id;
+	u16 obj_type;
+	u8 access_key[ACCESS_KEY_LEN];
+};
+
+struct mlx5hws_cmd_stc_create_attr {
+	u8 log_obj_range;
+	u8 table_type;
+};
+
+struct mlx5hws_cmd_stc_modify_attr {
+	u32 stc_offset;
+	u8 action_offset;
+	u8 reparse_mode;
+	enum mlx5_ifc_stc_action_type action_type;
+	union {
+		u32 id; /* TIRN, TAG, FT ID, STE ID, CRYPTO */
+		struct {
+			u8 decap;
+			u16 start_anchor;
+			u16 end_anchor;
+		} remove_header;
+		struct {
+			u32 arg_id;
+			u32 pattern_id;
+		} modify_header;
+		struct {
+			__be64 data;
+		} modify_action;
+		struct {
+			u32 arg_id;
+			u32 header_size;
+			u8 is_inline;
+			u8 encap;
+			u16 insert_anchor;
+			u16 insert_offset;
+		} insert_header;
+		struct {
+			u8 aso_type;
+			u32 devx_obj_id;
+			u8 return_reg_id;
+		} aso;
+		struct {
+			u16 vport_num;
+			u16 esw_owner_vhca_id;
+			u8 eswitch_owner_vhca_id_valid;
+		} vport;
+		struct {
+			struct mlx5hws_pool_chunk ste;
+			struct mlx5hws_pool *ste_pool;
+			u32 ste_obj_id; /* Internal */
+			u32 match_definer_id;
+			u8 log_hash_size;
+			bool ignore_tx;
+		} ste_table;
+		struct {
+			u16 start_anchor;
+			u16 num_of_words;
+		} remove_words;
+		struct {
+			u8 type;
+			u8 op;
+			u8 size;
+		} reformat_trailer;
+
+		u32 dest_table_id;
+		u32 dest_tir_num;
+	};
+};
+
+struct mlx5hws_cmd_ste_create_attr {
+	u8 log_obj_range;
+	u8 table_type;
+};
+
+struct mlx5hws_cmd_definer_create_attr {
+	u8 *dw_selector;
+	u8 *byte_selector;
+	u8 *match_mask;
+};
+
+struct mlx5hws_cmd_allow_other_vhca_access_attr {
+	u16 obj_type;
+	u32 obj_id;
+	u8 access_key[ACCESS_KEY_LEN];
+};
+
+struct mlx5hws_cmd_packet_reformat_create_attr {
+	u8 type;
+	size_t data_sz;
+	void *data;
+	u8 reformat_param_0;
+};
+
+struct mlx5hws_cmd_query_ft_caps {
+	u8 max_level;
+	u8 reparse;
+	u8 ignore_flow_level_rtc_valid;
+};
+
+struct mlx5hws_cmd_generate_wqe_attr {
+	u8 *wqe_ctrl;
+	u8 *gta_ctrl;
+	u8 *gta_data_0;
+	u8 *gta_data_1;
+	u32 pdn;
+};
+
+struct mlx5hws_cmd_query_caps {
+	u32 flex_protocols;
+	u8 wqe_based_update;
+	u8 rtc_reparse_mode;
+	u16 ste_format;
+	u8 rtc_index_mode;
+	u8 ste_alloc_log_max;
+	u8 ste_alloc_log_gran;
+	u8 stc_alloc_log_max;
+	u8 stc_alloc_log_gran;
+	u8 rtc_log_depth_max;
+	u8 format_select_gtpu_dw_0;
+	u8 format_select_gtpu_dw_1;
+	u8 flow_table_hash_type;
+	u8 format_select_gtpu_dw_2;
+	u8 format_select_gtpu_ext_dw_0;
+	u8 access_index_mode;
+	u32 linear_match_definer;
+	bool full_dw_jumbo_support;
+	bool rtc_hash_split_table;
+	bool rtc_linear_lookup_table;
+	u32 supp_type_gen_wqe;
+	u8 rtc_max_hash_def_gen_wqe;
+	u16 supp_ste_format_gen_wqe;
+	struct mlx5hws_cmd_query_ft_caps nic_ft;
+	struct mlx5hws_cmd_query_ft_caps fdb_ft;
+	bool eswitch_manager;
+	bool merged_eswitch;
+	u32 eswitch_manager_vport_number;
+	u8 log_header_modify_argument_granularity;
+	u8 log_header_modify_argument_max_alloc;
+	u8 sq_ts_format;
+	u8 fdb_tir_stc;
+	u64 definer_format_sup;
+	u32 trivial_match_definer;
+	u32 vhca_id;
+	u32 shared_vhca_id;
+	char fw_ver[64];
+	bool ipsec_offload;
+	bool is_ecpf;
+	u8 flex_parser_ok_bits_supp;
+	u8 flex_parser_id_geneve_tlv_option_0;
+	u8 flex_parser_id_mpls_over_gre;
+	u8 flex_parser_id_mpls_over_udp;
+};
+
+int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev,
+				  struct mlx5hws_cmd_ft_create_attr *ft_attr,
+				  u32 *table_id);
+
+int mlx5hws_cmd_flow_table_modify(struct mlx5_core_dev *mdev,
+				  struct mlx5hws_cmd_ft_modify_attr *ft_attr,
+				  u32 table_id);
+
+int mlx5hws_cmd_flow_table_query(struct mlx5_core_dev *mdev,
+				 u32 obj_id,
+				 struct mlx5hws_cmd_ft_query_attr *ft_attr,
+				 u64 *icm_addr_0, u64 *icm_addr_1);
+
+int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
+				   u8 fw_ft_type, u32 table_id);
+
+void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
+					  u32 table_id);
+
+int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
+			   u32 *rtc_id);
+
+void mlx5hws_cmd_rtc_destroy(struct mlx5_core_dev *mdev, u32 rtc_id);
+
+int mlx5hws_cmd_stc_create(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_stc_create_attr *stc_attr,
+			   u32 *stc_id);
+
+int mlx5hws_cmd_stc_modify(struct mlx5_core_dev *mdev,
+			   u32 stc_id,
+			   struct mlx5hws_cmd_stc_modify_attr *stc_attr);
+
+void mlx5hws_cmd_stc_destroy(struct mlx5_core_dev *mdev, u32 stc_id);
+
+int mlx5hws_cmd_generate_wqe(struct mlx5_core_dev *mdev,
+			     struct mlx5hws_cmd_generate_wqe_attr *attr,
+			     struct mlx5_cqe64 *ret_cqe);
+
+int mlx5hws_cmd_ste_create(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_ste_create_attr *ste_attr,
+			   u32 *ste_id);
+
+void mlx5hws_cmd_ste_destroy(struct mlx5_core_dev *mdev, u32 ste_id);
+
+int mlx5hws_cmd_definer_create(struct mlx5_core_dev *mdev,
+			       struct mlx5hws_cmd_definer_create_attr *def_attr,
+			       u32 *definer_id);
+
+void mlx5hws_cmd_definer_destroy(struct mlx5_core_dev *mdev,
+				 u32 definer_id);
+
+int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
+			   u16 log_obj_range,
+			   u32 pd,
+			   u32 *arg_id);
+
+void mlx5hws_cmd_arg_destroy(struct mlx5_core_dev *mdev,
+			     u32 arg_id);
+
+int mlx5hws_cmd_header_modify_pattern_create(struct mlx5_core_dev *mdev,
+					     u32 pattern_length,
+					     u8 *actions,
+					     u32 *ptrn_id);
+
+void mlx5hws_cmd_header_modify_pattern_destroy(struct mlx5_core_dev *mdev,
+					       u32 ptrn_id);
+
+int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
+				       struct mlx5hws_cmd_packet_reformat_create_attr *attr,
+				       u32 *reformat_id);
+
+int mlx5hws_cmd_packet_reformat_destroy(struct mlx5_core_dev *mdev,
+					u32 reformat_id);
+
+int mlx5hws_cmd_set_fte(struct mlx5_core_dev *mdev,
+			u32 table_type,
+			u32 table_id,
+			u32 group_id,
+			struct mlx5hws_cmd_set_fte_attr *fte_attr);
+
+int mlx5hws_cmd_delete_fte(struct mlx5_core_dev *mdev,
+			   u32 table_type, u32 table_id);
+
+struct mlx5hws_cmd_forward_tbl *
+mlx5hws_cmd_forward_tbl_create(struct mlx5_core_dev *mdev,
+			       struct mlx5hws_cmd_ft_create_attr *ft_attr,
+			       struct mlx5hws_cmd_set_fte_attr *fte_attr);
+
+void mlx5hws_cmd_forward_tbl_destroy(struct mlx5_core_dev *mdev,
+				     struct mlx5hws_cmd_forward_tbl *tbl);
+
+int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
+				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
+				 u32 *obj_id);
+
+int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
+				  u16 obj_type,
+				  u32 obj_id);
+
+int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn);
+
+int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev,
+			   struct mlx5hws_cmd_query_caps *caps);
+
+void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
+					   u32 fw_ft_type,
+					   enum mlx5hws_table_type type,
+					   struct mlx5hws_cmd_ft_modify_attr *ft_attr);
+
+int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
+					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr);
+
+int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function,
+			   u16 vport_number, u16 *gvmi);
+
+#endif /* MLX5HWS_CMD_H_ */
-- 
cgit v1.3-3-g829e


From aefc15a0fa1cfab233f490a4675167e5ca5c42b2 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:39:00 +0300
Subject: net/mlx5: HWS, added modify header pattern and args handling

Packet headers/metadta manipulations are split into two parts:
 - Header Modify Pattern: an object that describes which fields
   will be modified and in which way
 - Header Modify Argument: an object that provides the values
   to be used for header modification

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_pat_arg.c       | 579 +++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_pat_arg.h       | 101 ++++
 2 files changed, 680 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.c
new file mode 100644
index 000000000000..e084a5cbf81f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.c
@@ -0,0 +1,579 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+enum mlx5hws_arg_chunk_size
+mlx5hws_arg_data_size_to_arg_log_size(u16 data_size)
+{
+	/* Return the roundup of log2(data_size) */
+	if (data_size <= MLX5HWS_ARG_DATA_SIZE)
+		return MLX5HWS_ARG_CHUNK_SIZE_1;
+	if (data_size <= MLX5HWS_ARG_DATA_SIZE * 2)
+		return MLX5HWS_ARG_CHUNK_SIZE_2;
+	if (data_size <= MLX5HWS_ARG_DATA_SIZE * 4)
+		return MLX5HWS_ARG_CHUNK_SIZE_3;
+	if (data_size <= MLX5HWS_ARG_DATA_SIZE * 8)
+		return MLX5HWS_ARG_CHUNK_SIZE_4;
+
+	return MLX5HWS_ARG_CHUNK_SIZE_MAX;
+}
+
+u32 mlx5hws_arg_data_size_to_arg_size(u16 data_size)
+{
+	return BIT(mlx5hws_arg_data_size_to_arg_log_size(data_size));
+}
+
+enum mlx5hws_arg_chunk_size
+mlx5hws_arg_get_arg_log_size(u16 num_of_actions)
+{
+	return mlx5hws_arg_data_size_to_arg_log_size(num_of_actions *
+						    MLX5HWS_MODIFY_ACTION_SIZE);
+}
+
+u32 mlx5hws_arg_get_arg_size(u16 num_of_actions)
+{
+	return BIT(mlx5hws_arg_get_arg_log_size(num_of_actions));
+}
+
+bool mlx5hws_pat_require_reparse(__be64 *actions, u16 num_of_actions)
+{
+	u16 i, field;
+	u8 action_id;
+
+	for (i = 0; i < num_of_actions; i++) {
+		action_id = MLX5_GET(set_action_in, &actions[i], action_type);
+
+		switch (action_id) {
+		case MLX5_MODIFICATION_TYPE_NOP:
+			field = MLX5_MODI_OUT_NONE;
+			break;
+
+		case MLX5_MODIFICATION_TYPE_SET:
+		case MLX5_MODIFICATION_TYPE_ADD:
+			field = MLX5_GET(set_action_in, &actions[i], field);
+			break;
+
+		case MLX5_MODIFICATION_TYPE_COPY:
+		case MLX5_MODIFICATION_TYPE_ADD_FIELD:
+			field = MLX5_GET(copy_action_in, &actions[i], dst_field);
+			break;
+
+		default:
+			/* Insert/Remove/Unknown actions require reparse */
+			return true;
+		}
+
+		/* Below fields can change packet structure require a reparse */
+		if (field == MLX5_MODI_OUT_ETHERTYPE ||
+		    field == MLX5_MODI_OUT_IPV6_NEXT_HDR)
+			return true;
+	}
+
+	return false;
+}
+
+/* Cache and cache element handling */
+int mlx5hws_pat_init_pattern_cache(struct mlx5hws_pattern_cache **cache)
+{
+	struct mlx5hws_pattern_cache *new_cache;
+
+	new_cache = kzalloc(sizeof(*new_cache), GFP_KERNEL);
+	if (!new_cache)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&new_cache->ptrn_list);
+	mutex_init(&new_cache->lock);
+
+	*cache = new_cache;
+
+	return 0;
+}
+
+void mlx5hws_pat_uninit_pattern_cache(struct mlx5hws_pattern_cache *cache)
+{
+	mutex_destroy(&cache->lock);
+	kfree(cache);
+}
+
+static bool mlx5hws_pat_compare_pattern(int cur_num_of_actions,
+					__be64 cur_actions[],
+					int num_of_actions,
+					__be64 actions[])
+{
+	int i;
+
+	if (cur_num_of_actions != num_of_actions)
+		return false;
+
+	for (i = 0; i < num_of_actions; i++) {
+		u8 action_id =
+			MLX5_GET(set_action_in, &actions[i], action_type);
+
+		if (action_id == MLX5_MODIFICATION_TYPE_COPY ||
+		    action_id == MLX5_MODIFICATION_TYPE_ADD_FIELD) {
+			if (actions[i] != cur_actions[i])
+				return false;
+		} else {
+			/* Compare just the control, not the values */
+			if ((__force __be32)actions[i] !=
+			    (__force __be32)cur_actions[i])
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static struct mlx5hws_pattern_cache_item *
+mlx5hws_pat_find_cached_pattern(struct mlx5hws_pattern_cache *cache,
+				u16 num_of_actions,
+				__be64 *actions)
+{
+	struct mlx5hws_pattern_cache_item *cached_pat = NULL;
+
+	list_for_each_entry(cached_pat, &cache->ptrn_list, ptrn_list_node) {
+		if (mlx5hws_pat_compare_pattern(cached_pat->mh_data.num_of_actions,
+						(__be64 *)cached_pat->mh_data.data,
+						num_of_actions,
+						actions))
+			return cached_pat;
+	}
+
+	return NULL;
+}
+
+static struct mlx5hws_pattern_cache_item *
+mlx5hws_pat_get_existing_cached_pattern(struct mlx5hws_pattern_cache *cache,
+					u16 num_of_actions,
+					__be64 *actions)
+{
+	struct mlx5hws_pattern_cache_item *cached_pattern;
+
+	cached_pattern = mlx5hws_pat_find_cached_pattern(cache, num_of_actions, actions);
+	if (cached_pattern) {
+		/* LRU: move it to be first in the list */
+		list_del_init(&cached_pattern->ptrn_list_node);
+		list_add(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
+		cached_pattern->refcount++;
+	}
+
+	return cached_pattern;
+}
+
+static struct mlx5hws_pattern_cache_item *
+mlx5hws_pat_add_pattern_to_cache(struct mlx5hws_pattern_cache *cache,
+				 u32 pattern_id,
+				 u16 num_of_actions,
+				 __be64 *actions)
+{
+	struct mlx5hws_pattern_cache_item *cached_pattern;
+
+	cached_pattern = kzalloc(sizeof(*cached_pattern), GFP_KERNEL);
+	if (!cached_pattern)
+		return NULL;
+
+	cached_pattern->mh_data.num_of_actions = num_of_actions;
+	cached_pattern->mh_data.pattern_id = pattern_id;
+	cached_pattern->mh_data.data =
+		kmemdup(actions, num_of_actions * MLX5HWS_MODIFY_ACTION_SIZE, GFP_KERNEL);
+	if (!cached_pattern->mh_data.data)
+		goto free_cached_obj;
+
+	list_add(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
+	cached_pattern->refcount = 1;
+
+	return cached_pattern;
+
+free_cached_obj:
+	kfree(cached_pattern);
+	return NULL;
+}
+
+static struct mlx5hws_pattern_cache_item *
+mlx5hws_pat_find_cached_pattern_by_id(struct mlx5hws_pattern_cache *cache,
+				      u32 ptrn_id)
+{
+	struct mlx5hws_pattern_cache_item *cached_pattern = NULL;
+
+	list_for_each_entry(cached_pattern, &cache->ptrn_list, ptrn_list_node) {
+		if (cached_pattern->mh_data.pattern_id == ptrn_id)
+			return cached_pattern;
+	}
+
+	return NULL;
+}
+
+static void
+mlx5hws_pat_remove_pattern(struct mlx5hws_pattern_cache_item *cached_pattern)
+{
+	list_del_init(&cached_pattern->ptrn_list_node);
+
+	kfree(cached_pattern->mh_data.data);
+	kfree(cached_pattern);
+}
+
+void mlx5hws_pat_put_pattern(struct mlx5hws_context *ctx, u32 ptrn_id)
+{
+	struct mlx5hws_pattern_cache *cache = ctx->pattern_cache;
+	struct mlx5hws_pattern_cache_item *cached_pattern;
+
+	mutex_lock(&cache->lock);
+	cached_pattern = mlx5hws_pat_find_cached_pattern_by_id(cache, ptrn_id);
+	if (!cached_pattern) {
+		mlx5hws_err(ctx, "Failed to find cached pattern with provided ID\n");
+		pr_warn("HWS: pattern ID %d is not found\n", ptrn_id);
+		goto out;
+	}
+
+	if (--cached_pattern->refcount)
+		goto out;
+
+	mlx5hws_pat_remove_pattern(cached_pattern);
+	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, ptrn_id);
+
+out:
+	mutex_unlock(&cache->lock);
+}
+
+int mlx5hws_pat_get_pattern(struct mlx5hws_context *ctx,
+			    __be64 *pattern, size_t pattern_sz,
+			    u32 *pattern_id)
+{
+	u16 num_of_actions = pattern_sz / MLX5HWS_MODIFY_ACTION_SIZE;
+	struct mlx5hws_pattern_cache_item *cached_pattern;
+	u32 ptrn_id = 0;
+	int ret = 0;
+
+	mutex_lock(&ctx->pattern_cache->lock);
+
+	cached_pattern = mlx5hws_pat_get_existing_cached_pattern(ctx->pattern_cache,
+								 num_of_actions,
+								 pattern);
+	if (cached_pattern) {
+		*pattern_id = cached_pattern->mh_data.pattern_id;
+		goto out_unlock;
+	}
+
+	ret = mlx5hws_cmd_header_modify_pattern_create(ctx->mdev,
+						       pattern_sz,
+						       (u8 *)pattern,
+						       &ptrn_id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to create pattern FW object\n");
+		goto out_unlock;
+	}
+
+	cached_pattern = mlx5hws_pat_add_pattern_to_cache(ctx->pattern_cache,
+							  ptrn_id,
+							  num_of_actions,
+							  pattern);
+	if (!cached_pattern) {
+		mlx5hws_err(ctx, "Failed to add pattern to cache\n");
+		ret = -EINVAL;
+		goto clean_pattern;
+	}
+
+	mutex_unlock(&ctx->pattern_cache->lock);
+	*pattern_id = ptrn_id;
+
+	return ret;
+
+clean_pattern:
+	mlx5hws_cmd_header_modify_pattern_destroy(ctx->mdev, *pattern_id);
+out_unlock:
+	mutex_unlock(&ctx->pattern_cache->lock);
+	return ret;
+}
+
+static void
+mlx5d_arg_init_send_attr(struct mlx5hws_send_engine_post_attr *send_attr,
+			 void *comp_data,
+			 u32 arg_idx)
+{
+	send_attr->opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	send_attr->opmod = MLX5HWS_WQE_GTA_OPMOD_MOD_ARG;
+	send_attr->len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+	send_attr->id = arg_idx;
+	send_attr->user_data = comp_data;
+}
+
+void mlx5hws_arg_decapl3_write(struct mlx5hws_send_engine *queue,
+			       u32 arg_idx,
+			       u8 *arg_data,
+			       u16 num_of_actions)
+{
+	struct mlx5hws_send_engine_post_attr send_attr = {0};
+	struct mlx5hws_wqe_gta_data_seg_arg *wqe_arg = NULL;
+	struct mlx5hws_wqe_gta_ctrl_seg *wqe_ctrl = NULL;
+	struct mlx5hws_send_engine_post_ctrl ctrl;
+	size_t wqe_len;
+
+	mlx5d_arg_init_send_attr(&send_attr, NULL, arg_idx);
+
+	ctrl = mlx5hws_send_engine_post_start(queue);
+	mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
+	memset(wqe_ctrl, 0, wqe_len);
+	mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len);
+	mlx5hws_action_prepare_decap_l3_data(arg_data, (u8 *)wqe_arg,
+					     num_of_actions);
+	mlx5hws_send_engine_post_end(&ctrl, &send_attr);
+}
+
+void mlx5hws_arg_write(struct mlx5hws_send_engine *queue,
+		       void *comp_data,
+		       u32 arg_idx,
+		       u8 *arg_data,
+		       size_t data_size)
+{
+	struct mlx5hws_send_engine_post_attr send_attr = {0};
+	struct mlx5hws_wqe_gta_data_seg_arg *wqe_arg;
+	struct mlx5hws_send_engine_post_ctrl ctrl;
+	struct mlx5hws_wqe_gta_ctrl_seg *wqe_ctrl;
+	int i, full_iter, leftover;
+	size_t wqe_len;
+
+	mlx5d_arg_init_send_attr(&send_attr, comp_data, arg_idx);
+
+	/* Each WQE can hold 64B of data, it might require multiple iteration */
+	full_iter = data_size / MLX5HWS_ARG_DATA_SIZE;
+	leftover = data_size & (MLX5HWS_ARG_DATA_SIZE - 1);
+
+	for (i = 0; i < full_iter; i++) {
+		ctrl = mlx5hws_send_engine_post_start(queue);
+		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
+		memset(wqe_ctrl, 0, wqe_len);
+		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len);
+		memcpy(wqe_arg, arg_data, wqe_len);
+		send_attr.id = arg_idx++;
+		mlx5hws_send_engine_post_end(&ctrl, &send_attr);
+
+		/* Move to next argument data */
+		arg_data += MLX5HWS_ARG_DATA_SIZE;
+	}
+
+	if (leftover) {
+		ctrl = mlx5hws_send_engine_post_start(queue);
+		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
+		memset(wqe_ctrl, 0, wqe_len);
+		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len);
+		memcpy(wqe_arg, arg_data, leftover);
+		send_attr.id = arg_idx;
+		mlx5hws_send_engine_post_end(&ctrl, &send_attr);
+	}
+}
+
+int mlx5hws_arg_write_inline_arg_data(struct mlx5hws_context *ctx,
+				      u32 arg_idx,
+				      u8 *arg_data,
+				      size_t data_size)
+{
+	struct mlx5hws_send_engine *queue;
+	int ret;
+
+	mutex_lock(&ctx->ctrl_lock);
+
+	/* Get the control queue */
+	queue = &ctx->send_queue[ctx->queues - 1];
+
+	mlx5hws_arg_write(queue, arg_data, arg_idx, arg_data, data_size);
+
+	mlx5hws_send_engine_flush_queue(queue);
+
+	/* Poll for completion */
+	ret = mlx5hws_send_queue_action(ctx, ctx->queues - 1,
+					MLX5HWS_SEND_QUEUE_ACTION_DRAIN_SYNC);
+
+	if (ret)
+		mlx5hws_err(ctx, "Failed to drain arg queue\n");
+
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return ret;
+}
+
+bool mlx5hws_arg_is_valid_arg_request_size(struct mlx5hws_context *ctx,
+					   u32 arg_size)
+{
+	if (arg_size < ctx->caps->log_header_modify_argument_granularity ||
+	    arg_size > ctx->caps->log_header_modify_argument_max_alloc) {
+		return false;
+	}
+	return true;
+}
+
+int mlx5hws_arg_create(struct mlx5hws_context *ctx,
+		       u8 *data,
+		       size_t data_sz,
+		       u32 log_bulk_sz,
+		       bool write_data,
+		       u32 *arg_id)
+{
+	u16 single_arg_log_sz;
+	u16 multi_arg_log_sz;
+	int ret;
+	u32 id;
+
+	single_arg_log_sz = mlx5hws_arg_data_size_to_arg_log_size(data_sz);
+	multi_arg_log_sz = single_arg_log_sz + log_bulk_sz;
+
+	if (single_arg_log_sz >= MLX5HWS_ARG_CHUNK_SIZE_MAX) {
+		mlx5hws_err(ctx, "Requested single arg %u not supported\n", single_arg_log_sz);
+		return -EOPNOTSUPP;
+	}
+
+	if (!mlx5hws_arg_is_valid_arg_request_size(ctx, multi_arg_log_sz)) {
+		mlx5hws_err(ctx, "Argument log size %d not supported by FW\n", multi_arg_log_sz);
+		return -EOPNOTSUPP;
+	}
+
+	/* Alloc bulk of args */
+	ret = mlx5hws_cmd_arg_create(ctx->mdev, multi_arg_log_sz, ctx->pd_num, &id);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed allocating arg in order: %d\n", multi_arg_log_sz);
+		return ret;
+	}
+
+	if (write_data) {
+		ret = mlx5hws_arg_write_inline_arg_data(ctx, id,
+							data, data_sz);
+		if (ret) {
+			mlx5hws_err(ctx, "Failed writing arg data\n");
+			mlx5hws_cmd_arg_destroy(ctx->mdev, id);
+			return ret;
+		}
+	}
+
+	*arg_id = id;
+	return ret;
+}
+
+void mlx5hws_arg_destroy(struct mlx5hws_context *ctx, u32 arg_id)
+{
+	mlx5hws_cmd_arg_destroy(ctx->mdev, arg_id);
+}
+
+int mlx5hws_arg_create_modify_header_arg(struct mlx5hws_context *ctx,
+					 __be64 *data,
+					 u8 num_of_actions,
+					 u32 log_bulk_sz,
+					 bool write_data,
+					 u32 *arg_id)
+{
+	size_t data_sz = num_of_actions * MLX5HWS_MODIFY_ACTION_SIZE;
+	int ret;
+
+	ret = mlx5hws_arg_create(ctx,
+				 (u8 *)data,
+				 data_sz,
+				 log_bulk_sz,
+				 write_data,
+				 arg_id);
+	if (ret)
+		mlx5hws_err(ctx, "Failed creating modify header arg\n");
+
+	return ret;
+}
+
+static int
+hws_action_modify_check_field_limitation(u8 action_type, __be64 *pattern)
+{
+	/* Need to check field limitation here, but for now - return OK */
+	return 0;
+}
+
+#define INVALID_FIELD 0xffff
+
+static void
+hws_action_modify_get_target_fields(u8 action_type, __be64 *pattern,
+				    u16 *src_field, u16 *dst_field)
+{
+	switch (action_type) {
+	case MLX5_ACTION_TYPE_SET:
+	case MLX5_ACTION_TYPE_ADD:
+		*src_field = MLX5_GET(set_action_in, pattern, field);
+		*dst_field = INVALID_FIELD;
+		break;
+	case MLX5_ACTION_TYPE_COPY:
+		*src_field = MLX5_GET(copy_action_in, pattern, src_field);
+		*dst_field = MLX5_GET(copy_action_in, pattern, dst_field);
+		break;
+	default:
+		pr_warn("HWS: invalid modify header action type %d\n", action_type);
+	}
+}
+
+bool mlx5hws_pat_verify_actions(struct mlx5hws_context *ctx, __be64 pattern[], size_t sz)
+{
+	size_t i;
+
+	for (i = 0; i < sz / MLX5HWS_MODIFY_ACTION_SIZE; i++) {
+		u8 action_type =
+			MLX5_GET(set_action_in, &pattern[i], action_type);
+		if (action_type >= MLX5_MODIFICATION_TYPE_MAX) {
+			mlx5hws_err(ctx, "Unsupported action id %d\n", action_type);
+			return false;
+		}
+		if (hws_action_modify_check_field_limitation(action_type, &pattern[i])) {
+			mlx5hws_err(ctx, "Unsupported action number %zu\n", i);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions,
+			   size_t max_actions, size_t *new_size,
+			   u32 *nope_location, __be64 *new_pat)
+{
+	u16 prev_src_field = 0, prev_dst_field = 0;
+	u16 src_field, dst_field;
+	u8 action_type;
+	size_t i, j;
+
+	*new_size = num_actions;
+	*nope_location = 0;
+
+	if (num_actions == 1)
+		return;
+
+	for (i = 0, j = 0; i < num_actions; i++, j++) {
+		action_type = MLX5_GET(set_action_in, &pattern[i], action_type);
+
+		hws_action_modify_get_target_fields(action_type, &pattern[i],
+						    &src_field, &dst_field);
+		if (i % 2) {
+			if (action_type == MLX5_ACTION_TYPE_COPY &&
+			    (prev_src_field == src_field ||
+			     prev_dst_field == dst_field)) {
+				/* need Nope */
+				*new_size += 1;
+				*nope_location |= BIT(i);
+				memset(&new_pat[j], 0, MLX5HWS_MODIFY_ACTION_SIZE);
+				MLX5_SET(set_action_in, &new_pat[j],
+					 action_type,
+					 MLX5_MODIFICATION_TYPE_NOP);
+				j++;
+			} else if (prev_src_field == src_field) {
+				/* need Nope*/
+				*new_size += 1;
+				*nope_location |= BIT(i);
+				MLX5_SET(set_action_in, &new_pat[j],
+					 action_type,
+					 MLX5_MODIFICATION_TYPE_NOP);
+				j++;
+			}
+		}
+		memcpy(&new_pat[j], &pattern[i], MLX5HWS_MODIFY_ACTION_SIZE);
+		/* check if no more space */
+		if (j > max_actions) {
+			*new_size = num_actions;
+			*nope_location = 0;
+			return;
+		}
+
+		prev_src_field = src_field;
+		prev_dst_field = dst_field;
+	}
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.h
new file mode 100644
index 000000000000..27ca93385b08
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pat_arg.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_PAT_ARG_H_
+#define MLX5HWS_PAT_ARG_H_
+
+/* Modify-header arg pool */
+enum mlx5hws_arg_chunk_size {
+	MLX5HWS_ARG_CHUNK_SIZE_1,
+	/* Keep MIN updated when changing */
+	MLX5HWS_ARG_CHUNK_SIZE_MIN = MLX5HWS_ARG_CHUNK_SIZE_1,
+	MLX5HWS_ARG_CHUNK_SIZE_2,
+	MLX5HWS_ARG_CHUNK_SIZE_3,
+	MLX5HWS_ARG_CHUNK_SIZE_4,
+	MLX5HWS_ARG_CHUNK_SIZE_MAX,
+};
+
+enum {
+	MLX5HWS_MODIFY_ACTION_SIZE = 8,
+	MLX5HWS_ARG_DATA_SIZE = 64,
+};
+
+struct mlx5hws_pattern_cache {
+	struct mutex lock; /* Protect pattern list */
+	struct list_head ptrn_list;
+};
+
+struct mlx5hws_pattern_cache_item {
+	struct {
+		u32 pattern_id;
+		u8 *data;
+		u16 num_of_actions;
+	} mh_data;
+	u32 refcount;
+	struct list_head ptrn_list_node;
+};
+
+enum mlx5hws_arg_chunk_size
+mlx5hws_arg_get_arg_log_size(u16 num_of_actions);
+
+u32 mlx5hws_arg_get_arg_size(u16 num_of_actions);
+
+enum mlx5hws_arg_chunk_size
+mlx5hws_arg_data_size_to_arg_log_size(u16 data_size);
+
+u32 mlx5hws_arg_data_size_to_arg_size(u16 data_size);
+
+int mlx5hws_pat_init_pattern_cache(struct mlx5hws_pattern_cache **cache);
+
+void mlx5hws_pat_uninit_pattern_cache(struct mlx5hws_pattern_cache *cache);
+
+bool mlx5hws_pat_verify_actions(struct mlx5hws_context *ctx, __be64 pattern[], size_t sz);
+
+int mlx5hws_arg_create(struct mlx5hws_context *ctx,
+		       u8 *data,
+		       size_t data_sz,
+		       u32 log_bulk_sz,
+		       bool write_data,
+		       u32 *arg_id);
+
+void mlx5hws_arg_destroy(struct mlx5hws_context *ctx, u32 arg_id);
+
+int mlx5hws_arg_create_modify_header_arg(struct mlx5hws_context *ctx,
+					 __be64 *data,
+					 u8 num_of_actions,
+					 u32 log_bulk_sz,
+					 bool write_data,
+					 u32 *modify_hdr_arg_id);
+
+int mlx5hws_pat_get_pattern(struct mlx5hws_context *ctx,
+			    __be64 *pattern,
+			    size_t pattern_sz,
+			    u32 *ptrn_id);
+
+void mlx5hws_pat_put_pattern(struct mlx5hws_context *ctx,
+			     u32 ptrn_id);
+
+bool mlx5hws_arg_is_valid_arg_request_size(struct mlx5hws_context *ctx,
+					   u32 arg_size);
+
+bool mlx5hws_pat_require_reparse(__be64 *actions, u16 num_of_actions);
+
+void mlx5hws_arg_write(struct mlx5hws_send_engine *queue,
+		       void *comp_data,
+		       u32 arg_idx,
+		       u8 *arg_data,
+		       size_t data_size);
+
+void mlx5hws_arg_decapl3_write(struct mlx5hws_send_engine *queue,
+			       u32 arg_idx,
+			       u8 *arg_data,
+			       u16 num_of_actions);
+
+int mlx5hws_arg_write_inline_arg_data(struct mlx5hws_context *ctx,
+				      u32 arg_idx,
+				      u8 *arg_data,
+				      size_t data_size);
+
+void mlx5hws_pat_calc_nope(__be64 *pattern, size_t num_actions, size_t max_actions,
+			   size_t *new_size, u32 *nope_location, __be64 *new_pat);
+#endif /* MLX5HWS_PAT_ARG_H_ */
-- 
cgit v1.3-3-g829e


From 6c5e68254027e7a82cb4580fd1a28cda3d417a97 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Mon, 12 Aug 2024 02:10:56 +0300
Subject: net/mlx5: HWS, added vport handling

Vport is a virtual eswitch port that is associated with its virtual
function (VF), physical function (PF) or sub-function (SF).
This patch adds handling of vports in HWS.

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_vport.c         | 86 ++++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_vport.h         | 13 ++++
 2 files changed, 99 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.c
new file mode 100644
index 000000000000..faf42421c43f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+int mlx5hws_vport_init_vports(struct mlx5hws_context *ctx)
+{
+	int ret;
+
+	if (!ctx->caps->eswitch_manager)
+		return 0;
+
+	xa_init(&ctx->vports.vport_gvmi_xa);
+
+	/* Set gvmi for eswitch manager and uplink vports only. Rest of the vports
+	 * (vport 0 of other function, VFs and SFs) will be queried dynamically.
+	 */
+
+	ret = mlx5hws_cmd_query_gvmi(ctx->mdev, false, 0, &ctx->vports.esw_manager_gvmi);
+	if (ret)
+		return ret;
+
+	ctx->vports.uplink_gvmi = 0;
+	return 0;
+}
+
+void mlx5hws_vport_uninit_vports(struct mlx5hws_context *ctx)
+{
+	if (ctx->caps->eswitch_manager)
+		xa_destroy(&ctx->vports.vport_gvmi_xa);
+}
+
+static int hws_vport_add_gvmi(struct mlx5hws_context *ctx, u16 vport)
+{
+	u16 vport_gvmi;
+	int ret;
+
+	ret = mlx5hws_cmd_query_gvmi(ctx->mdev, true, vport, &vport_gvmi);
+	if (ret)
+		return -EINVAL;
+
+	ret = xa_insert(&ctx->vports.vport_gvmi_xa, vport,
+			xa_mk_value(vport_gvmi), GFP_KERNEL);
+	if (ret)
+		mlx5hws_dbg(ctx, "Couldn't insert new vport gvmi into xarray (%d)\n", ret);
+
+	return ret;
+}
+
+static bool hws_vport_is_esw_mgr_vport(struct mlx5hws_context *ctx, u16 vport)
+{
+	return ctx->caps->is_ecpf ? vport == MLX5_VPORT_ECPF :
+				    vport == MLX5_VPORT_PF;
+}
+
+int mlx5hws_vport_get_gvmi(struct mlx5hws_context *ctx, u16 vport, u16 *vport_gvmi)
+{
+	void *entry;
+	int ret;
+
+	if (!ctx->caps->eswitch_manager)
+		return -EINVAL;
+
+	if (hws_vport_is_esw_mgr_vport(ctx, vport)) {
+		*vport_gvmi = ctx->vports.esw_manager_gvmi;
+		return 0;
+	}
+
+	if (vport == MLX5_VPORT_UPLINK) {
+		*vport_gvmi = ctx->vports.uplink_gvmi;
+		return 0;
+	}
+
+load_entry:
+	entry = xa_load(&ctx->vports.vport_gvmi_xa, vport);
+
+	if (!xa_is_value(entry)) {
+		ret = hws_vport_add_gvmi(ctx, vport);
+		if (ret && ret != -EBUSY)
+			return ret;
+		goto load_entry;
+	}
+
+	*vport_gvmi = (u16)xa_to_value(entry);
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.h
new file mode 100644
index 000000000000..0912fc166b3a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_vport.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_VPORT_H_
+#define MLX5HWS_VPORT_H_
+
+int mlx5hws_vport_init_vports(struct mlx5hws_context *ctx);
+
+void mlx5hws_vport_uninit_vports(struct mlx5hws_context *ctx);
+
+int mlx5hws_vport_get_gvmi(struct mlx5hws_context *ctx, u16 vport, u16 *vport_gvmi);
+
+#endif /* MLX5HWS_VPORT_H_ */
-- 
cgit v1.3-3-g829e


From c61afff94373641695cc81999e9bb10408ea84d5 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:34:22 +0300
Subject: net/mlx5: HWS, added memory management handling

Added object pools and buddy allocator functionality.

Reviewed-by: Itamar Gozlan <igozlan@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_buddy.c         | 149 +++++
 .../mlx5/core/steering/hws/mlx5hws_buddy.h         |  21 +
 .../mellanox/mlx5/core/steering/hws/mlx5hws_pool.c | 640 +++++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_pool.h | 151 +++++
 4 files changed, 961 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.c
new file mode 100644
index 000000000000..e6ed66202a40
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+#include "mlx5hws_buddy.h"
+
+static int hws_buddy_init(struct mlx5hws_buddy_mem *buddy, u32 max_order)
+{
+	int i, s, ret = 0;
+
+	buddy->max_order = max_order;
+
+	buddy->bitmap = kcalloc(buddy->max_order + 1,
+				sizeof(*buddy->bitmap),
+				GFP_KERNEL);
+	if (!buddy->bitmap)
+		return -ENOMEM;
+
+	buddy->num_free = kcalloc(buddy->max_order + 1,
+				  sizeof(*buddy->num_free),
+				  GFP_KERNEL);
+	if (!buddy->num_free) {
+		ret = -ENOMEM;
+		goto err_out_free_bits;
+	}
+
+	for (i = 0; i <= (int)buddy->max_order; ++i) {
+		s = 1 << (buddy->max_order - i);
+
+		buddy->bitmap[i] = bitmap_zalloc(s, GFP_KERNEL);
+		if (!buddy->bitmap[i]) {
+			ret = -ENOMEM;
+			goto err_out_free_num_free;
+		}
+	}
+
+	bitmap_set(buddy->bitmap[buddy->max_order], 0, 1);
+	buddy->num_free[buddy->max_order] = 1;
+
+	return 0;
+
+err_out_free_num_free:
+	for (i = 0; i <= (int)buddy->max_order; ++i)
+		bitmap_free(buddy->bitmap[i]);
+
+	kfree(buddy->num_free);
+
+err_out_free_bits:
+	kfree(buddy->bitmap);
+	return ret;
+}
+
+struct mlx5hws_buddy_mem *mlx5hws_buddy_create(u32 max_order)
+{
+	struct mlx5hws_buddy_mem *buddy;
+
+	buddy = kzalloc(sizeof(*buddy), GFP_KERNEL);
+	if (!buddy)
+		return NULL;
+
+	if (hws_buddy_init(buddy, max_order))
+		goto free_buddy;
+
+	return buddy;
+
+free_buddy:
+	kfree(buddy);
+	return NULL;
+}
+
+void mlx5hws_buddy_cleanup(struct mlx5hws_buddy_mem *buddy)
+{
+	int i;
+
+	for (i = 0; i <= (int)buddy->max_order; ++i)
+		bitmap_free(buddy->bitmap[i]);
+
+	kfree(buddy->num_free);
+	kfree(buddy->bitmap);
+}
+
+static int hws_buddy_find_free_seg(struct mlx5hws_buddy_mem *buddy,
+				   u32 start_order,
+				   u32 *segment,
+				   u32 *order)
+{
+	unsigned int seg, order_iter, m;
+
+	for (order_iter = start_order;
+	     order_iter <= buddy->max_order; ++order_iter) {
+		if (!buddy->num_free[order_iter])
+			continue;
+
+		m = 1 << (buddy->max_order - order_iter);
+		seg = find_first_bit(buddy->bitmap[order_iter], m);
+
+		if (WARN(seg >= m,
+			 "ICM Buddy: failed finding free mem for order %d\n",
+			 order_iter))
+			return -ENOMEM;
+
+		break;
+	}
+
+	if (order_iter > buddy->max_order)
+		return -ENOMEM;
+
+	*segment = seg;
+	*order = order_iter;
+	return 0;
+}
+
+int mlx5hws_buddy_alloc_mem(struct mlx5hws_buddy_mem *buddy, u32 order)
+{
+	u32 seg, order_iter, err;
+
+	err = hws_buddy_find_free_seg(buddy, order, &seg, &order_iter);
+	if (err)
+		return err;
+
+	bitmap_clear(buddy->bitmap[order_iter], seg, 1);
+	--buddy->num_free[order_iter];
+
+	while (order_iter > order) {
+		--order_iter;
+		seg <<= 1;
+		bitmap_set(buddy->bitmap[order_iter], seg ^ 1, 1);
+		++buddy->num_free[order_iter];
+	}
+
+	seg <<= order;
+
+	return seg;
+}
+
+void mlx5hws_buddy_free_mem(struct mlx5hws_buddy_mem *buddy, u32 seg, u32 order)
+{
+	seg >>= order;
+
+	while (test_bit(seg ^ 1, buddy->bitmap[order])) {
+		bitmap_clear(buddy->bitmap[order], seg ^ 1, 1);
+		--buddy->num_free[order];
+		seg >>= 1;
+		++order;
+	}
+
+	bitmap_set(buddy->bitmap[order], seg, 1);
+	++buddy->num_free[order];
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.h
new file mode 100644
index 000000000000..338c44bbedaf
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_buddy.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_BUDDY_H_
+#define MLX5HWS_BUDDY_H_
+
+struct mlx5hws_buddy_mem {
+	unsigned long **bitmap;
+	unsigned int *num_free;
+	u32 max_order;
+};
+
+struct mlx5hws_buddy_mem *mlx5hws_buddy_create(u32 max_order);
+
+void mlx5hws_buddy_cleanup(struct mlx5hws_buddy_mem *buddy);
+
+int mlx5hws_buddy_alloc_mem(struct mlx5hws_buddy_mem *buddy, u32 order);
+
+void mlx5hws_buddy_free_mem(struct mlx5hws_buddy_mem *buddy, u32 seg, u32 order);
+
+#endif /* MLX5HWS_BUDDY_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.c
new file mode 100644
index 000000000000..a8a63e3278be
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.c
@@ -0,0 +1,640 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+#include "mlx5hws_buddy.h"
+
+static void hws_pool_free_one_resource(struct mlx5hws_pool_resource *resource)
+{
+	switch (resource->pool->type) {
+	case MLX5HWS_POOL_TYPE_STE:
+		mlx5hws_cmd_ste_destroy(resource->pool->ctx->mdev, resource->base_id);
+		break;
+	case MLX5HWS_POOL_TYPE_STC:
+		mlx5hws_cmd_stc_destroy(resource->pool->ctx->mdev, resource->base_id);
+		break;
+	default:
+		break;
+	}
+
+	kfree(resource);
+}
+
+static void hws_pool_resource_free(struct mlx5hws_pool *pool,
+				   int resource_idx)
+{
+	hws_pool_free_one_resource(pool->resource[resource_idx]);
+	pool->resource[resource_idx] = NULL;
+
+	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
+		hws_pool_free_one_resource(pool->mirror_resource[resource_idx]);
+		pool->mirror_resource[resource_idx] = NULL;
+	}
+}
+
+static struct mlx5hws_pool_resource *
+hws_pool_create_one_resource(struct mlx5hws_pool *pool, u32 log_range,
+			     u32 fw_ft_type)
+{
+	struct mlx5hws_cmd_ste_create_attr ste_attr;
+	struct mlx5hws_cmd_stc_create_attr stc_attr;
+	struct mlx5hws_pool_resource *resource;
+	u32 obj_id = 0;
+	int ret;
+
+	resource = kzalloc(sizeof(*resource), GFP_KERNEL);
+	if (!resource)
+		return NULL;
+
+	switch (pool->type) {
+	case MLX5HWS_POOL_TYPE_STE:
+		ste_attr.log_obj_range = log_range;
+		ste_attr.table_type = fw_ft_type;
+		ret = mlx5hws_cmd_ste_create(pool->ctx->mdev, &ste_attr, &obj_id);
+		break;
+	case MLX5HWS_POOL_TYPE_STC:
+		stc_attr.log_obj_range = log_range;
+		stc_attr.table_type = fw_ft_type;
+		ret = mlx5hws_cmd_stc_create(pool->ctx->mdev, &stc_attr, &obj_id);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret) {
+		mlx5hws_err(pool->ctx, "Failed to allocate resource objects\n");
+		goto free_resource;
+	}
+
+	resource->pool = pool;
+	resource->range = 1 << log_range;
+	resource->base_id = obj_id;
+
+	return resource;
+
+free_resource:
+	kfree(resource);
+	return NULL;
+}
+
+static int
+hws_pool_resource_alloc(struct mlx5hws_pool *pool, u32 log_range, int idx)
+{
+	struct mlx5hws_pool_resource *resource;
+	u32 fw_ft_type, opt_log_range;
+
+	fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, false);
+	opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_ORIG ? 0 : log_range;
+	resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
+	if (!resource) {
+		mlx5hws_err(pool->ctx, "Failed allocating resource\n");
+		return -EINVAL;
+	}
+
+	pool->resource[idx] = resource;
+
+	if (pool->tbl_type == MLX5HWS_TABLE_TYPE_FDB) {
+		struct mlx5hws_pool_resource *mirror_resource;
+
+		fw_ft_type = mlx5hws_table_get_res_fw_ft_type(pool->tbl_type, true);
+		opt_log_range = pool->opt_type == MLX5HWS_POOL_OPTIMIZE_MIRROR ? 0 : log_range;
+		mirror_resource = hws_pool_create_one_resource(pool, opt_log_range, fw_ft_type);
+		if (!mirror_resource) {
+			mlx5hws_err(pool->ctx, "Failed allocating mirrored resource\n");
+			hws_pool_free_one_resource(resource);
+			pool->resource[idx] = NULL;
+			return -EINVAL;
+		}
+		pool->mirror_resource[idx] = mirror_resource;
+	}
+
+	return 0;
+}
+
+static unsigned long *hws_pool_create_and_init_bitmap(u32 log_range)
+{
+	unsigned long *cur_bmp;
+
+	cur_bmp = bitmap_zalloc(1 << log_range, GFP_KERNEL);
+	if (!cur_bmp)
+		return NULL;
+
+	bitmap_fill(cur_bmp, 1 << log_range);
+
+	return cur_bmp;
+}
+
+static void hws_pool_buddy_db_put_chunk(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk)
+{
+	struct mlx5hws_buddy_mem *buddy;
+
+	buddy = pool->db.buddy_manager->buddies[chunk->resource_idx];
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "No such buddy (%d)\n", chunk->resource_idx);
+		return;
+	}
+
+	mlx5hws_buddy_free_mem(buddy, chunk->offset, chunk->order);
+}
+
+static struct mlx5hws_buddy_mem *
+hws_pool_buddy_get_next_buddy(struct mlx5hws_pool *pool, int idx,
+			      u32 order, bool *is_new_buddy)
+{
+	static struct mlx5hws_buddy_mem *buddy;
+	u32 new_buddy_size;
+
+	buddy = pool->db.buddy_manager->buddies[idx];
+	if (buddy)
+		return buddy;
+
+	new_buddy_size = max(pool->alloc_log_sz, order);
+	*is_new_buddy = true;
+	buddy = mlx5hws_buddy_create(new_buddy_size);
+	if (!buddy) {
+		mlx5hws_err(pool->ctx, "Failed to create buddy order: %d index: %d\n",
+			    new_buddy_size, idx);
+		return NULL;
+	}
+
+	if (hws_pool_resource_alloc(pool, new_buddy_size, idx) != 0) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
+			    pool->type, new_buddy_size, idx);
+		mlx5hws_buddy_cleanup(buddy);
+		return NULL;
+	}
+
+	pool->db.buddy_manager->buddies[idx] = buddy;
+
+	return buddy;
+}
+
+static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool,
+					int order,
+					u32 *buddy_idx,
+					int *seg)
+{
+	struct mlx5hws_buddy_mem *buddy;
+	bool new_mem = false;
+	int ret = 0;
+	int i;
+
+	*seg = -1;
+
+	/* Find the next free place from the buddy array */
+	while (*seg == -1) {
+		for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
+			buddy = hws_pool_buddy_get_next_buddy(pool, i,
+							      order,
+							      &new_mem);
+			if (!buddy) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			*seg = mlx5hws_buddy_alloc_mem(buddy, order);
+			if (*seg != -1)
+				goto found;
+
+			if (pool->flags & MLX5HWS_POOL_FLAGS_ONE_RESOURCE) {
+				mlx5hws_err(pool->ctx,
+					    "Fail to allocate seg for one resource pool\n");
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			if (new_mem) {
+				/* We have new memory pool, should be place for us */
+				mlx5hws_err(pool->ctx,
+					    "No memory for order: %d with buddy no: %d\n",
+					    order, i);
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+	}
+
+found:
+	*buddy_idx = i;
+out:
+	return ret;
+}
+
+static int hws_pool_buddy_db_get_chunk(struct mlx5hws_pool *pool,
+				       struct mlx5hws_pool_chunk *chunk)
+{
+	int ret = 0;
+
+	/* Go over the buddies and find next free slot */
+	ret = hws_pool_buddy_get_mem_chunk(pool, chunk->order,
+					   &chunk->resource_idx,
+					   &chunk->offset);
+	if (ret)
+		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
+			    chunk->order);
+
+	return ret;
+}
+
+static void hws_pool_buddy_db_uninit(struct mlx5hws_pool *pool)
+{
+	struct mlx5hws_buddy_mem *buddy;
+	int i;
+
+	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
+		buddy = pool->db.buddy_manager->buddies[i];
+		if (buddy) {
+			mlx5hws_buddy_cleanup(buddy);
+			kfree(buddy);
+			pool->db.buddy_manager->buddies[i] = NULL;
+		}
+	}
+
+	kfree(pool->db.buddy_manager);
+}
+
+static int hws_pool_buddy_db_init(struct mlx5hws_pool *pool, u32 log_range)
+{
+	pool->db.buddy_manager = kzalloc(sizeof(*pool->db.buddy_manager), GFP_KERNEL);
+	if (!pool->db.buddy_manager)
+		return -ENOMEM;
+
+	if (pool->flags & MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE) {
+		bool new_buddy;
+
+		if (!hws_pool_buddy_get_next_buddy(pool, 0, log_range, &new_buddy)) {
+			mlx5hws_err(pool->ctx,
+				    "Failed allocating memory on create log_sz: %d\n", log_range);
+			kfree(pool->db.buddy_manager);
+			return -ENOMEM;
+		}
+	}
+
+	pool->p_db_uninit = &hws_pool_buddy_db_uninit;
+	pool->p_get_chunk = &hws_pool_buddy_db_get_chunk;
+	pool->p_put_chunk = &hws_pool_buddy_db_put_chunk;
+
+	return 0;
+}
+
+static int hws_pool_create_resource_on_index(struct mlx5hws_pool *pool,
+					     u32 alloc_size, int idx)
+{
+	int ret = hws_pool_resource_alloc(pool, alloc_size, idx);
+
+	if (ret) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
+			    pool->type, alloc_size, idx);
+		return ret;
+	}
+
+	return 0;
+}
+
+static struct mlx5hws_pool_elements *
+hws_pool_element_create_new_elem(struct mlx5hws_pool *pool, u32 order, int idx)
+{
+	struct mlx5hws_pool_elements *elem;
+	u32 alloc_size;
+
+	alloc_size = pool->alloc_log_sz;
+
+	elem = kzalloc(sizeof(*elem), GFP_KERNEL);
+	if (!elem)
+		return NULL;
+
+	/* Sharing the same resource, also means that all the elements are with size 1 */
+	if ((pool->flags & MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS) &&
+	    !(pool->flags & MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK)) {
+		 /* Currently all chunks in size 1 */
+		elem->bitmap = hws_pool_create_and_init_bitmap(alloc_size - order);
+		if (!elem->bitmap) {
+			mlx5hws_err(pool->ctx,
+				    "Failed to create bitmap type: %d: size %d index: %d\n",
+				    pool->type, alloc_size, idx);
+			goto free_elem;
+		}
+
+		elem->log_size = alloc_size - order;
+	}
+
+	if (hws_pool_create_resource_on_index(pool, alloc_size, idx)) {
+		mlx5hws_err(pool->ctx, "Failed to create resource type: %d: size %d index: %d\n",
+			    pool->type, alloc_size, idx);
+		goto free_db;
+	}
+
+	pool->db.element_manager->elements[idx] = elem;
+
+	return elem;
+
+free_db:
+	bitmap_free(elem->bitmap);
+free_elem:
+	kfree(elem);
+	return NULL;
+}
+
+static int hws_pool_element_find_seg(struct mlx5hws_pool_elements *elem, int *seg)
+{
+	unsigned int segment, size;
+
+	size = 1 << elem->log_size;
+
+	segment = find_first_bit(elem->bitmap, size);
+	if (segment >= size) {
+		elem->is_full = true;
+		return -ENOMEM;
+	}
+
+	bitmap_clear(elem->bitmap, segment, 1);
+	*seg = segment;
+	return 0;
+}
+
+static int
+hws_pool_onesize_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
+				       u32 *idx, int *seg)
+{
+	struct mlx5hws_pool_elements *elem;
+
+	elem = pool->db.element_manager->elements[0];
+	if (!elem)
+		elem = hws_pool_element_create_new_elem(pool, order, 0);
+	if (!elem)
+		goto err_no_elem;
+
+	if (hws_pool_element_find_seg(elem, seg) != 0) {
+		mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
+		return -ENOMEM;
+	}
+
+	*idx = 0;
+	elem->num_of_elements++;
+	return 0;
+
+err_no_elem:
+	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
+	return -ENOMEM;
+}
+
+static int
+hws_pool_general_element_get_mem_chunk(struct mlx5hws_pool *pool, u32 order,
+				       u32 *idx, int *seg)
+{
+	int ret, i;
+
+	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
+		if (!pool->resource[i]) {
+			ret = hws_pool_create_resource_on_index(pool, order, i);
+			if (ret)
+				goto err_no_res;
+			*idx = i;
+			*seg = 0; /* One memory slot in that element */
+			return 0;
+		}
+	}
+
+	mlx5hws_err(pool->ctx, "No more resources (last request order: %d)\n", order);
+	return -ENOMEM;
+
+err_no_res:
+	mlx5hws_err(pool->ctx, "Failed to allocate element for order: %d\n", order);
+	return -ENOMEM;
+}
+
+static int hws_pool_general_element_db_get_chunk(struct mlx5hws_pool *pool,
+						 struct mlx5hws_pool_chunk *chunk)
+{
+	int ret;
+
+	/* Go over all memory elements and find/allocate free slot */
+	ret = hws_pool_general_element_get_mem_chunk(pool, chunk->order,
+						     &chunk->resource_idx,
+						     &chunk->offset);
+	if (ret)
+		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
+			    chunk->order);
+
+	return ret;
+}
+
+static void hws_pool_general_element_db_put_chunk(struct mlx5hws_pool *pool,
+						  struct mlx5hws_pool_chunk *chunk)
+{
+	if (unlikely(!pool->resource[chunk->resource_idx]))
+		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
+
+	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE)
+		hws_pool_resource_free(pool, chunk->resource_idx);
+}
+
+static void hws_pool_general_element_db_uninit(struct mlx5hws_pool *pool)
+{
+	(void)pool;
+}
+
+/* This memory management works as the following:
+ * - At start doesn't allocate no mem at all.
+ * - When new request for chunk arrived:
+ *	allocate resource and give it.
+ * - When free that chunk:
+ *	the resource is freed.
+ */
+static int hws_pool_general_element_db_init(struct mlx5hws_pool *pool)
+{
+	pool->p_db_uninit = &hws_pool_general_element_db_uninit;
+	pool->p_get_chunk = &hws_pool_general_element_db_get_chunk;
+	pool->p_put_chunk = &hws_pool_general_element_db_put_chunk;
+
+	return 0;
+}
+
+static void hws_onesize_element_db_destroy_element(struct mlx5hws_pool *pool,
+						   struct mlx5hws_pool_elements *elem,
+						   struct mlx5hws_pool_chunk *chunk)
+{
+	if (unlikely(!pool->resource[chunk->resource_idx]))
+		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
+
+	hws_pool_resource_free(pool, chunk->resource_idx);
+	kfree(elem);
+	pool->db.element_manager->elements[chunk->resource_idx] = NULL;
+}
+
+static void hws_onesize_element_db_put_chunk(struct mlx5hws_pool *pool,
+					     struct mlx5hws_pool_chunk *chunk)
+{
+	struct mlx5hws_pool_elements *elem;
+
+	if (unlikely(chunk->resource_idx))
+		pr_warn("HWS: invalid resource with index %d\n", chunk->resource_idx);
+
+	elem = pool->db.element_manager->elements[chunk->resource_idx];
+	if (!elem) {
+		mlx5hws_err(pool->ctx, "No such element (%d)\n", chunk->resource_idx);
+		return;
+	}
+
+	bitmap_set(elem->bitmap, chunk->offset, 1);
+	elem->is_full = false;
+	elem->num_of_elements--;
+
+	if (pool->flags & MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE &&
+	    !elem->num_of_elements)
+		hws_onesize_element_db_destroy_element(pool, elem, chunk);
+}
+
+static int hws_onesize_element_db_get_chunk(struct mlx5hws_pool *pool,
+					    struct mlx5hws_pool_chunk *chunk)
+{
+	int ret = 0;
+
+	/* Go over all memory elements and find/allocate free slot */
+	ret = hws_pool_onesize_element_get_mem_chunk(pool, chunk->order,
+						     &chunk->resource_idx,
+						     &chunk->offset);
+	if (ret)
+		mlx5hws_err(pool->ctx, "Failed to get free slot for chunk with order: %d\n",
+			    chunk->order);
+
+	return ret;
+}
+
+static void hws_onesize_element_db_uninit(struct mlx5hws_pool *pool)
+{
+	struct mlx5hws_pool_elements *elem;
+	int i;
+
+	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
+		elem = pool->db.element_manager->elements[i];
+		if (elem) {
+			bitmap_free(elem->bitmap);
+			kfree(elem);
+			pool->db.element_manager->elements[i] = NULL;
+		}
+	}
+	kfree(pool->db.element_manager);
+}
+
+/* This memory management works as the following:
+ * - At start doesn't allocate no mem at all.
+ * - When new request for chunk arrived:
+ *  aloocate the first and only slot of memory/resource
+ *  when it ended return error.
+ */
+static int hws_pool_onesize_element_db_init(struct mlx5hws_pool *pool)
+{
+	pool->db.element_manager = kzalloc(sizeof(*pool->db.element_manager), GFP_KERNEL);
+	if (!pool->db.element_manager)
+		return -ENOMEM;
+
+	pool->p_db_uninit = &hws_onesize_element_db_uninit;
+	pool->p_get_chunk = &hws_onesize_element_db_get_chunk;
+	pool->p_put_chunk = &hws_onesize_element_db_put_chunk;
+
+	return 0;
+}
+
+static int hws_pool_db_init(struct mlx5hws_pool *pool,
+			    enum mlx5hws_db_type db_type)
+{
+	int ret;
+
+	if (db_type == MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE)
+		ret = hws_pool_general_element_db_init(pool);
+	else if (db_type == MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE)
+		ret = hws_pool_onesize_element_db_init(pool);
+	else
+		ret = hws_pool_buddy_db_init(pool, pool->alloc_log_sz);
+
+	if (ret) {
+		mlx5hws_err(pool->ctx, "Failed to init general db : %d (ret: %d)\n", db_type, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void hws_pool_db_unint(struct mlx5hws_pool *pool)
+{
+	pool->p_db_uninit(pool);
+}
+
+int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
+			     struct mlx5hws_pool_chunk *chunk)
+{
+	int ret;
+
+	mutex_lock(&pool->lock);
+	ret = pool->p_get_chunk(pool, chunk);
+	mutex_unlock(&pool->lock);
+
+	return ret;
+}
+
+void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
+			     struct mlx5hws_pool_chunk *chunk)
+{
+	mutex_lock(&pool->lock);
+	pool->p_put_chunk(pool, chunk);
+	mutex_unlock(&pool->lock);
+}
+
+struct mlx5hws_pool *
+mlx5hws_pool_create(struct mlx5hws_context *ctx, struct mlx5hws_pool_attr *pool_attr)
+{
+	enum mlx5hws_db_type res_db_type;
+	struct mlx5hws_pool *pool;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return NULL;
+
+	pool->ctx = ctx;
+	pool->type = pool_attr->pool_type;
+	pool->alloc_log_sz = pool_attr->alloc_log_sz;
+	pool->flags = pool_attr->flags;
+	pool->tbl_type = pool_attr->table_type;
+	pool->opt_type = pool_attr->opt_type;
+
+	/* Support general db */
+	if (pool->flags == (MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
+			    MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK))
+		res_db_type = MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE;
+	else if (pool->flags == (MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
+				 MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS))
+		res_db_type = MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE;
+	else
+		res_db_type = MLX5HWS_POOL_DB_TYPE_BUDDY;
+
+	pool->alloc_log_sz = pool_attr->alloc_log_sz;
+
+	if (hws_pool_db_init(pool, res_db_type))
+		goto free_pool;
+
+	mutex_init(&pool->lock);
+
+	return pool;
+
+free_pool:
+	kfree(pool);
+	return NULL;
+}
+
+int mlx5hws_pool_destroy(struct mlx5hws_pool *pool)
+{
+	int i;
+
+	mutex_destroy(&pool->lock);
+
+	for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++)
+		if (pool->resource[i])
+			hws_pool_resource_free(pool, i);
+
+	hws_pool_db_unint(pool);
+
+	kfree(pool);
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.h
new file mode 100644
index 000000000000..621298b352b2
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_pool.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_POOL_H_
+#define MLX5HWS_POOL_H_
+
+#define MLX5HWS_POOL_STC_LOG_SZ 15
+
+#define MLX5HWS_POOL_RESOURCE_ARR_SZ 100
+
+enum mlx5hws_pool_type {
+	MLX5HWS_POOL_TYPE_STE,
+	MLX5HWS_POOL_TYPE_STC,
+};
+
+struct mlx5hws_pool_chunk {
+	u32 resource_idx;
+	/* Internal offset, relative to base index */
+	int offset;
+	int order;
+};
+
+struct mlx5hws_pool_resource {
+	struct mlx5hws_pool *pool;
+	u32 base_id;
+	u32 range;
+};
+
+enum mlx5hws_pool_flags {
+	/* Only a one resource in that pool */
+	MLX5HWS_POOL_FLAGS_ONE_RESOURCE = 1 << 0,
+	MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE = 1 << 1,
+	/* No sharing resources between chunks */
+	MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK = 1 << 2,
+	/* All objects are in the same size */
+	MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS = 1 << 3,
+	/* Managed by buddy allocator */
+	MLX5HWS_POOL_FLAGS_BUDDY_MANAGED = 1 << 4,
+	/* Allocate pool_type memory on pool creation */
+	MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE = 1 << 5,
+
+	/* These values should be used by the caller */
+	MLX5HWS_POOL_FLAGS_FOR_STC_POOL =
+		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
+		MLX5HWS_POOL_FLAGS_FIXED_SIZE_OBJECTS,
+	MLX5HWS_POOL_FLAGS_FOR_MATCHER_STE_POOL =
+		MLX5HWS_POOL_FLAGS_RELEASE_FREE_RESOURCE |
+		MLX5HWS_POOL_FLAGS_RESOURCE_PER_CHUNK,
+	MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL =
+		MLX5HWS_POOL_FLAGS_ONE_RESOURCE |
+		MLX5HWS_POOL_FLAGS_BUDDY_MANAGED |
+		MLX5HWS_POOL_FLAGS_ALLOC_MEM_ON_CREATE,
+};
+
+enum mlx5hws_pool_optimize {
+	MLX5HWS_POOL_OPTIMIZE_NONE = 0x0,
+	MLX5HWS_POOL_OPTIMIZE_ORIG = 0x1,
+	MLX5HWS_POOL_OPTIMIZE_MIRROR = 0x2,
+};
+
+struct mlx5hws_pool_attr {
+	enum mlx5hws_pool_type pool_type;
+	enum mlx5hws_table_type table_type;
+	enum mlx5hws_pool_flags flags;
+	enum mlx5hws_pool_optimize opt_type;
+	/* Allocation size once memory is depleted */
+	size_t alloc_log_sz;
+};
+
+enum mlx5hws_db_type {
+	/* Uses for allocating chunk of big memory, each element has its own resource in the FW*/
+	MLX5HWS_POOL_DB_TYPE_GENERAL_SIZE,
+	/* One resource only, all the elements are with same one size */
+	MLX5HWS_POOL_DB_TYPE_ONE_SIZE_RESOURCE,
+	/* Many resources, the memory allocated with buddy mechanism */
+	MLX5HWS_POOL_DB_TYPE_BUDDY,
+};
+
+struct mlx5hws_buddy_manager {
+	struct mlx5hws_buddy_mem *buddies[MLX5HWS_POOL_RESOURCE_ARR_SZ];
+};
+
+struct mlx5hws_pool_elements {
+	u32 num_of_elements;
+	unsigned long *bitmap;
+	u32 log_size;
+	bool is_full;
+};
+
+struct mlx5hws_element_manager {
+	struct mlx5hws_pool_elements *elements[MLX5HWS_POOL_RESOURCE_ARR_SZ];
+};
+
+struct mlx5hws_pool_db {
+	enum mlx5hws_db_type type;
+	union {
+		struct mlx5hws_element_manager *element_manager;
+		struct mlx5hws_buddy_manager *buddy_manager;
+	};
+};
+
+typedef int (*mlx5hws_pool_db_get_chunk)(struct mlx5hws_pool *pool,
+					struct mlx5hws_pool_chunk *chunk);
+typedef void (*mlx5hws_pool_db_put_chunk)(struct mlx5hws_pool *pool,
+					 struct mlx5hws_pool_chunk *chunk);
+typedef void (*mlx5hws_pool_unint_db)(struct mlx5hws_pool *pool);
+
+struct mlx5hws_pool {
+	struct mlx5hws_context *ctx;
+	enum mlx5hws_pool_type type;
+	enum mlx5hws_pool_flags flags;
+	struct mutex lock; /* protect the pool */
+	size_t alloc_log_sz;
+	enum mlx5hws_table_type tbl_type;
+	enum mlx5hws_pool_optimize opt_type;
+	struct mlx5hws_pool_resource *resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
+	struct mlx5hws_pool_resource *mirror_resource[MLX5HWS_POOL_RESOURCE_ARR_SZ];
+	/* DB */
+	struct mlx5hws_pool_db db;
+	/* Functions */
+	mlx5hws_pool_unint_db p_db_uninit;
+	mlx5hws_pool_db_get_chunk p_get_chunk;
+	mlx5hws_pool_db_put_chunk p_put_chunk;
+};
+
+struct mlx5hws_pool *
+mlx5hws_pool_create(struct mlx5hws_context *ctx,
+		    struct mlx5hws_pool_attr *pool_attr);
+
+int mlx5hws_pool_destroy(struct mlx5hws_pool *pool);
+
+int mlx5hws_pool_chunk_alloc(struct mlx5hws_pool *pool,
+			     struct mlx5hws_pool_chunk *chunk);
+
+void mlx5hws_pool_chunk_free(struct mlx5hws_pool *pool,
+			     struct mlx5hws_pool_chunk *chunk);
+
+static inline u32
+mlx5hws_pool_chunk_get_base_id(struct mlx5hws_pool *pool,
+			       struct mlx5hws_pool_chunk *chunk)
+{
+	return pool->resource[chunk->resource_idx]->base_id;
+}
+
+static inline u32
+mlx5hws_pool_chunk_get_base_mirror_id(struct mlx5hws_pool *pool,
+				      struct mlx5hws_pool_chunk *chunk)
+{
+	return pool->mirror_resource[chunk->resource_idx]->base_id;
+}
+#endif /* MLX5HWS_POOL_H_ */
-- 
cgit v1.3-3-g829e


From 2111bb970c787b16b002dc726c1d296ce87a00fb Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:43:36 +0300
Subject: net/mlx5: HWS, added backward-compatible API handling

Added implementation of backward-compatible (BWC) steering API.
Native HWS API is very different from SWS API:
 - SWS is synchronous (rule creation/deletion API call returns when
   the rule is created/deleted), while HWS is asynchronous (it
   requires polling for completion in order to know when the rule
   creation/deletion happened)
 - SWS manages its own memory (it allocates/frees all the needed
   memory for steering rules, while HWS requires the rules memory
   to be allocated/freed outside the API

In order to make HWS fit the existing fs-core steering API paradigm,
this patch adds implementation of backward-compatible (BWC) steering
API that has the bahaviour similar to SWS: among others, it encompasses
all the rules' memory management and completion polling, presenting
the usual synchronous API for the upper layer.

A user that wishes to utilize the full speed potential of HWS can
call the HWS async API and have rule insertion/deletion batching,
lower memory management overhead, and lower CPU utilization.
Such approach will be taken by the future Connection Tracking.

Note that BWC steering doesn't support yet rules that require more
than one match STE - complex rules.
This support will be added later on.

Reviewed-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c  | 997 +++++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h  |  73 ++
 .../mlx5/core/steering/hws/mlx5hws_bwc_complex.c   |  86 ++
 .../mlx5/core/steering/hws/mlx5hws_bwc_complex.h   |  29 +
 4 files changed, 1185 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c
new file mode 100644
index 000000000000..bd52b05db367
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.c
@@ -0,0 +1,997 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+static u16 hws_bwc_gen_queue_idx(struct mlx5hws_context *ctx)
+{
+	/* assign random queue */
+	return get_random_u8() % mlx5hws_bwc_queues(ctx);
+}
+
+static u16
+hws_bwc_get_burst_th(struct mlx5hws_context *ctx, u16 queue_id)
+{
+	return min(ctx->send_queue[queue_id].num_entries / 2,
+		   MLX5HWS_BWC_MATCHER_REHASH_BURST_TH);
+}
+
+static struct mutex *
+hws_bwc_get_queue_lock(struct mlx5hws_context *ctx, u16 idx)
+{
+	return &ctx->bwc_send_queue_locks[idx];
+}
+
+static void hws_bwc_lock_all_queues(struct mlx5hws_context *ctx)
+{
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mutex *queue_lock; /* Protect the queue */
+	int i;
+
+	for (i = 0; i < bwc_queues; i++) {
+		queue_lock = hws_bwc_get_queue_lock(ctx, i);
+		mutex_lock(queue_lock);
+	}
+}
+
+static void hws_bwc_unlock_all_queues(struct mlx5hws_context *ctx)
+{
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mutex *queue_lock; /* Protect the queue */
+	int i = bwc_queues;
+
+	while (i--) {
+		queue_lock = hws_bwc_get_queue_lock(ctx, i);
+		mutex_unlock(queue_lock);
+	}
+}
+
+static void hws_bwc_matcher_init_attr(struct mlx5hws_matcher_attr *attr,
+				      u32 priority,
+				      u8 size_log)
+{
+	memset(attr, 0, sizeof(*attr));
+
+	attr->priority = priority;
+	attr->optimize_using_rule_idx = 0;
+	attr->mode = MLX5HWS_MATCHER_RESOURCE_MODE_RULE;
+	attr->optimize_flow_src = MLX5HWS_MATCHER_FLOW_SRC_ANY;
+	attr->insert_mode = MLX5HWS_MATCHER_INSERT_BY_HASH;
+	attr->distribute_mode = MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH;
+	attr->rule.num_log = size_log;
+	attr->resizable = true;
+	attr->max_num_of_at_attach = MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM;
+}
+
+int mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
+				      struct mlx5hws_table *table,
+				      u32 priority,
+				      u8 match_criteria_enable,
+				      struct mlx5hws_match_parameters *mask,
+				      enum mlx5hws_action_type action_types[])
+{
+	enum mlx5hws_action_type init_action_types[1] = { MLX5HWS_ACTION_TYP_LAST };
+	struct mlx5hws_context *ctx = table->ctx;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_matcher_attr attr = {0};
+	int i;
+
+	bwc_matcher->rules = kcalloc(bwc_queues, sizeof(*bwc_matcher->rules), GFP_KERNEL);
+	if (!bwc_matcher->rules)
+		goto err;
+
+	for (i = 0; i < bwc_queues; i++)
+		INIT_LIST_HEAD(&bwc_matcher->rules[i]);
+
+	hws_bwc_matcher_init_attr(&attr,
+				  priority,
+				  MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG);
+
+	bwc_matcher->priority = priority;
+	bwc_matcher->size_log = MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG;
+
+	/* create dummy action template */
+	bwc_matcher->at[0] =
+		mlx5hws_action_template_create(action_types ?
+					       action_types : init_action_types);
+	if (!bwc_matcher->at[0]) {
+		mlx5hws_err(table->ctx, "BWC matcher: failed creating action template\n");
+		goto free_bwc_matcher_rules;
+	}
+
+	bwc_matcher->num_of_at = 1;
+
+	bwc_matcher->mt = mlx5hws_match_template_create(ctx,
+							mask->match_buf,
+							mask->match_sz,
+							match_criteria_enable);
+	if (!bwc_matcher->mt) {
+		mlx5hws_err(table->ctx, "BWC matcher: failed creating match template\n");
+		goto free_at;
+	}
+
+	bwc_matcher->matcher = mlx5hws_matcher_create(table,
+						      &bwc_matcher->mt, 1,
+						      &bwc_matcher->at[0],
+						      bwc_matcher->num_of_at,
+						      &attr);
+	if (!bwc_matcher->matcher) {
+		mlx5hws_err(table->ctx, "BWC matcher: failed creating HWS matcher\n");
+		goto free_mt;
+	}
+
+	return 0;
+
+free_mt:
+	mlx5hws_match_template_destroy(bwc_matcher->mt);
+free_at:
+	mlx5hws_action_template_destroy(bwc_matcher->at[0]);
+free_bwc_matcher_rules:
+	kfree(bwc_matcher->rules);
+err:
+	return -EINVAL;
+}
+
+struct mlx5hws_bwc_matcher *
+mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
+			   u32 priority,
+			   u8 match_criteria_enable,
+			   struct mlx5hws_match_parameters *mask)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher;
+	bool is_complex;
+	int ret;
+
+	if (!mlx5hws_context_bwc_supported(table->ctx)) {
+		mlx5hws_err(table->ctx,
+			    "BWC matcher: context created w/o BWC API compatibility\n");
+		return NULL;
+	}
+
+	bwc_matcher = kzalloc(sizeof(*bwc_matcher), GFP_KERNEL);
+	if (!bwc_matcher)
+		return NULL;
+
+	/* Check if the required match params can be all matched
+	 * in single STE, otherwise complex matcher is needed.
+	 */
+
+	is_complex = mlx5hws_bwc_match_params_is_complex(table->ctx, match_criteria_enable, mask);
+	if (is_complex)
+		ret = mlx5hws_bwc_matcher_create_complex(bwc_matcher,
+							 table,
+							 priority,
+							 match_criteria_enable,
+							 mask);
+	else
+		ret = mlx5hws_bwc_matcher_create_simple(bwc_matcher,
+							table,
+							priority,
+							match_criteria_enable,
+							mask,
+							NULL);
+	if (ret)
+		goto free_bwc_matcher;
+
+	return bwc_matcher;
+
+free_bwc_matcher:
+	kfree(bwc_matcher);
+
+	return NULL;
+}
+
+int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	int i;
+
+	mlx5hws_matcher_destroy(bwc_matcher->matcher);
+	bwc_matcher->matcher = NULL;
+
+	for (i = 0; i < bwc_matcher->num_of_at; i++)
+		mlx5hws_action_template_destroy(bwc_matcher->at[i]);
+
+	mlx5hws_match_template_destroy(bwc_matcher->mt);
+	kfree(bwc_matcher->rules);
+
+	return 0;
+}
+
+int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	if (bwc_matcher->num_of_rules)
+		mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
+			    "BWC matcher destroy: matcher still has %d rules\n",
+			    bwc_matcher->num_of_rules);
+
+	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
+
+	kfree(bwc_matcher);
+	return 0;
+}
+
+static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
+			      u16 queue_id,
+			      u32 *pending_rules,
+			      bool drain)
+{
+	struct mlx5hws_flow_op_result comp[MLX5HWS_BWC_MATCHER_REHASH_BURST_TH];
+	u16 burst_th = hws_bwc_get_burst_th(ctx, queue_id);
+	bool got_comp = *pending_rules >= burst_th;
+	bool queue_full;
+	int err = 0;
+	int ret;
+	int i;
+
+	/* Check if there are any completions at all */
+	if (!got_comp && !drain)
+		return 0;
+
+	queue_full = mlx5hws_send_engine_full(&ctx->send_queue[queue_id]);
+	while (queue_full || ((got_comp || drain) && *pending_rules)) {
+		ret = mlx5hws_send_queue_poll(ctx, queue_id, comp, burst_th);
+		if (unlikely(ret < 0)) {
+			mlx5hws_err(ctx, "BWC poll error: polling queue %d returned %d\n",
+				    queue_id, ret);
+			return -EINVAL;
+		}
+
+		if (ret) {
+			(*pending_rules) -= ret;
+			for (i = 0; i < ret; i++) {
+				if (unlikely(comp[i].status != MLX5HWS_FLOW_OP_SUCCESS)) {
+					mlx5hws_err(ctx,
+						    "BWC poll error: polling queue %d returned completion with error\n",
+						    queue_id);
+					err = -EINVAL;
+				}
+			}
+			queue_full = false;
+		}
+
+		got_comp = !!ret;
+	}
+
+	return err;
+}
+
+void
+mlx5hws_bwc_rule_fill_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
+			   u16 bwc_queue_idx,
+			   u32 flow_source,
+			   struct mlx5hws_rule_attr *rule_attr)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+
+	/* no use of INSERT_BY_INDEX in bwc rule */
+	rule_attr->rule_idx = 0;
+
+	/* notify HW at each rule insertion/deletion */
+	rule_attr->burst = 0;
+
+	/* We don't need user data, but the API requires it to exist */
+	rule_attr->user_data = (void *)0xFACADE;
+
+	rule_attr->queue_id = mlx5hws_bwc_get_queue_id(ctx, bwc_queue_idx);
+	rule_attr->flow_source = flow_source;
+}
+
+struct mlx5hws_bwc_rule *
+mlx5hws_bwc_rule_alloc(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_bwc_rule *bwc_rule;
+
+	bwc_rule = kzalloc(sizeof(*bwc_rule), GFP_KERNEL);
+	if (unlikely(!bwc_rule))
+		goto out_err;
+
+	bwc_rule->rule = kzalloc(sizeof(*bwc_rule->rule), GFP_KERNEL);
+	if (unlikely(!bwc_rule->rule))
+		goto free_rule;
+
+	bwc_rule->bwc_matcher = bwc_matcher;
+	return bwc_rule;
+
+free_rule:
+	kfree(bwc_rule);
+out_err:
+	return NULL;
+}
+
+void mlx5hws_bwc_rule_free(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	if (likely(bwc_rule->rule))
+		kfree(bwc_rule->rule);
+	kfree(bwc_rule);
+}
+
+static void hws_bwc_rule_list_add(struct mlx5hws_bwc_rule *bwc_rule, u16 idx)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+
+	bwc_matcher->num_of_rules++;
+	bwc_rule->bwc_queue_idx = idx;
+	list_add(&bwc_rule->list_node, &bwc_matcher->rules[idx]);
+}
+
+static void hws_bwc_rule_list_remove(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+
+	bwc_matcher->num_of_rules--;
+	list_del_init(&bwc_rule->list_node);
+}
+
+static int
+hws_bwc_rule_destroy_hws_async(struct mlx5hws_bwc_rule *bwc_rule,
+			       struct mlx5hws_rule_attr *attr)
+{
+	return mlx5hws_rule_destroy(bwc_rule->rule, attr);
+}
+
+static int
+hws_bwc_rule_destroy_hws_sync(struct mlx5hws_bwc_rule *bwc_rule,
+			      struct mlx5hws_rule_attr *rule_attr)
+{
+	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_flow_op_result completion;
+	int ret;
+
+	ret = hws_bwc_rule_destroy_hws_async(bwc_rule, rule_attr);
+	if (unlikely(ret))
+		return ret;
+
+	do {
+		ret = mlx5hws_send_queue_poll(ctx, rule_attr->queue_id, &completion, 1);
+	} while (ret != 1);
+
+	if (unlikely(completion.status != MLX5HWS_FLOW_OP_SUCCESS ||
+		     (bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
+		      bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING))) {
+		mlx5hws_err(ctx, "Failed destroying BWC rule: completion %d, rule status %d\n",
+			    completion.status, bwc_rule->rule->status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	u16 idx = bwc_rule->bwc_queue_idx;
+	struct mlx5hws_rule_attr attr;
+	struct mutex *queue_lock; /* Protect the queue */
+	int ret;
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, idx, 0, &attr);
+
+	queue_lock = hws_bwc_get_queue_lock(ctx, idx);
+
+	mutex_lock(queue_lock);
+
+	ret = hws_bwc_rule_destroy_hws_sync(bwc_rule, &attr);
+	hws_bwc_rule_list_remove(bwc_rule);
+
+	mutex_unlock(queue_lock);
+
+	return ret;
+}
+
+int mlx5hws_bwc_rule_destroy(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	int ret;
+
+	ret = mlx5hws_bwc_rule_destroy_simple(bwc_rule);
+
+	mlx5hws_bwc_rule_free(bwc_rule);
+	return ret;
+}
+
+static int
+hws_bwc_rule_create_async(struct mlx5hws_bwc_rule *bwc_rule,
+			  u32 *match_param,
+			  u8 at_idx,
+			  struct mlx5hws_rule_action rule_actions[],
+			  struct mlx5hws_rule_attr *rule_attr)
+{
+	return mlx5hws_rule_create(bwc_rule->bwc_matcher->matcher,
+				   0, /* only one match template supported */
+				   match_param,
+				   at_idx,
+				   rule_actions,
+				   rule_attr,
+				   bwc_rule->rule);
+}
+
+static int
+hws_bwc_rule_create_sync(struct mlx5hws_bwc_rule *bwc_rule,
+			 u32 *match_param,
+			 u8 at_idx,
+			 struct mlx5hws_rule_action rule_actions[],
+			 struct mlx5hws_rule_attr *rule_attr)
+
+{
+	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
+	u32 expected_completions = 1;
+	int ret;
+
+	ret = hws_bwc_rule_create_async(bwc_rule, match_param,
+					at_idx, rule_actions,
+					rule_attr);
+	if (unlikely(ret))
+		return ret;
+
+	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+
+	return ret;
+}
+
+static int
+hws_bwc_rule_update_sync(struct mlx5hws_bwc_rule *bwc_rule,
+			 u8 at_idx,
+			 struct mlx5hws_rule_action rule_actions[],
+			 struct mlx5hws_rule_attr *rule_attr)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	u32 expected_completions = 1;
+	int ret;
+
+	ret = mlx5hws_rule_action_update(bwc_rule->rule,
+					 at_idx,
+					 rule_actions,
+					 rule_attr);
+	if (unlikely(ret))
+		return ret;
+
+	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+	if (unlikely(ret))
+		mlx5hws_err(ctx, "Failed updating BWC rule (%d)\n", ret);
+
+	return ret;
+}
+
+static bool
+hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_cmd_query_caps *caps = bwc_matcher->matcher->tbl->ctx->caps;
+
+	return bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH >=
+	       caps->ste_alloc_log_max - 1;
+}
+
+static bool
+hws_bwc_matcher_rehash_size_needed(struct mlx5hws_bwc_matcher *bwc_matcher,
+				   u32 num_of_rules)
+{
+	if (unlikely(hws_bwc_matcher_size_maxed_out(bwc_matcher)))
+		return false;
+
+	if (unlikely((num_of_rules * 100 / MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH) >=
+		     (1UL << bwc_matcher->size_log)))
+		return true;
+
+	return false;
+}
+
+static void
+hws_bwc_rule_actions_to_action_types(struct mlx5hws_rule_action rule_actions[],
+				     enum mlx5hws_action_type action_types[])
+{
+	int i = 0;
+
+	for (i = 0;
+	     rule_actions[i].action && (rule_actions[i].action->type != MLX5HWS_ACTION_TYP_LAST);
+	     i++) {
+		action_types[i] = (enum mlx5hws_action_type)rule_actions[i].action->type;
+	}
+
+	action_types[i] = MLX5HWS_ACTION_TYP_LAST;
+}
+
+static int
+hws_bwc_matcher_extend_at(struct mlx5hws_bwc_matcher *bwc_matcher,
+			  struct mlx5hws_rule_action rule_actions[])
+{
+	enum mlx5hws_action_type action_types[MLX5HWS_BWC_MAX_ACTS];
+
+	hws_bwc_rule_actions_to_action_types(rule_actions, action_types);
+
+	bwc_matcher->at[bwc_matcher->num_of_at] =
+		mlx5hws_action_template_create(action_types);
+
+	if (unlikely(!bwc_matcher->at[bwc_matcher->num_of_at]))
+		return -ENOMEM;
+
+	bwc_matcher->num_of_at++;
+	return 0;
+}
+
+static int
+hws_bwc_matcher_extend_size(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_cmd_query_caps *caps = ctx->caps;
+
+	if (unlikely(hws_bwc_matcher_size_maxed_out(bwc_matcher))) {
+		mlx5hws_err(ctx, "Can't resize matcher: depth exceeds limit %d\n",
+			    caps->rtc_log_depth_max);
+		return -ENOMEM;
+	}
+
+	bwc_matcher->size_log =
+		min(bwc_matcher->size_log + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
+		    caps->ste_alloc_log_max - MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH);
+
+	return 0;
+}
+
+static int
+hws_bwc_matcher_find_at(struct mlx5hws_bwc_matcher *bwc_matcher,
+			struct mlx5hws_rule_action rule_actions[])
+{
+	enum mlx5hws_action_type *action_type_arr;
+	int i, j;
+
+	/* start from index 1 - first action template is a dummy */
+	for (i = 1; i < bwc_matcher->num_of_at; i++) {
+		j = 0;
+		action_type_arr = bwc_matcher->at[i]->action_type_arr;
+
+		while (rule_actions[j].action &&
+		       rule_actions[j].action->type != MLX5HWS_ACTION_TYP_LAST) {
+			if (action_type_arr[j] != rule_actions[j].action->type)
+				break;
+			j++;
+		}
+
+		if (action_type_arr[j] == MLX5HWS_ACTION_TYP_LAST &&
+		    (!rule_actions[j].action ||
+		     rule_actions[j].action->type == MLX5HWS_ACTION_TYP_LAST))
+			return i;
+	}
+
+	return -1;
+}
+
+static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	u16 bwc_queues = mlx5hws_bwc_queues(ctx);
+	struct mlx5hws_bwc_rule **bwc_rules;
+	struct mlx5hws_rule_attr rule_attr;
+	u32 *pending_rules;
+	int i, j, ret = 0;
+	bool all_done;
+	u16 burst_th;
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr);
+
+	pending_rules = kcalloc(bwc_queues, sizeof(*pending_rules), GFP_KERNEL);
+	if (!pending_rules)
+		return -ENOMEM;
+
+	bwc_rules = kcalloc(bwc_queues, sizeof(*bwc_rules), GFP_KERNEL);
+	if (!bwc_rules) {
+		ret = -ENOMEM;
+		goto free_pending_rules;
+	}
+
+	for (i = 0; i < bwc_queues; i++) {
+		if (list_empty(&bwc_matcher->rules[i]))
+			bwc_rules[i] = NULL;
+		else
+			bwc_rules[i] = list_first_entry(&bwc_matcher->rules[i],
+							struct mlx5hws_bwc_rule,
+							list_node);
+	}
+
+	do {
+		all_done = true;
+
+		for (i = 0; i < bwc_queues; i++) {
+			rule_attr.queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+			burst_th = hws_bwc_get_burst_th(ctx, rule_attr.queue_id);
+
+			for (j = 0; j < burst_th && bwc_rules[i]; j++) {
+				rule_attr.burst = !!((j + 1) % burst_th);
+				ret = mlx5hws_matcher_resize_rule_move(bwc_matcher->matcher,
+								       bwc_rules[i]->rule,
+								       &rule_attr);
+				if (unlikely(ret)) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule failed during rehash (%d)\n",
+						    ret);
+					goto free_bwc_rules;
+				}
+
+				all_done = false;
+				pending_rules[i]++;
+				bwc_rules[i] = list_is_last(&bwc_rules[i]->list_node,
+							    &bwc_matcher->rules[i]) ?
+					       NULL : list_next_entry(bwc_rules[i], list_node);
+
+				ret = hws_bwc_queue_poll(ctx, rule_attr.queue_id,
+							 &pending_rules[i], false);
+				if (unlikely(ret))
+					goto free_bwc_rules;
+			}
+		}
+	} while (!all_done);
+
+	/* drain all the bwc queues */
+	for (i = 0; i < bwc_queues; i++) {
+		if (pending_rules[i]) {
+			u16 queue_id = mlx5hws_bwc_get_queue_id(ctx, i);
+
+			mlx5hws_send_engine_flush_queue(&ctx->send_queue[queue_id]);
+			ret = hws_bwc_queue_poll(ctx, queue_id,
+						 &pending_rules[i], true);
+			if (unlikely(ret))
+				goto free_bwc_rules;
+		}
+	}
+
+free_bwc_rules:
+	kfree(bwc_rules);
+free_pending_rules:
+	kfree(pending_rules);
+
+	return ret;
+}
+
+static int hws_bwc_matcher_move_all(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	return hws_bwc_matcher_move_all_simple(bwc_matcher);
+}
+
+static int hws_bwc_matcher_move(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_matcher_attr matcher_attr = {0};
+	struct mlx5hws_matcher *old_matcher;
+	struct mlx5hws_matcher *new_matcher;
+	int ret;
+
+	hws_bwc_matcher_init_attr(&matcher_attr,
+				  bwc_matcher->priority,
+				  bwc_matcher->size_log);
+
+	old_matcher = bwc_matcher->matcher;
+	new_matcher = mlx5hws_matcher_create(old_matcher->tbl,
+					     &bwc_matcher->mt, 1,
+					     bwc_matcher->at,
+					     bwc_matcher->num_of_at,
+					     &matcher_attr);
+	if (!new_matcher) {
+		mlx5hws_err(ctx, "Rehash error: matcher creation failed\n");
+		return -ENOMEM;
+	}
+
+	ret = mlx5hws_matcher_resize_set_target(old_matcher, new_matcher);
+	if (ret) {
+		mlx5hws_err(ctx, "Rehash error: failed setting resize target\n");
+		return ret;
+	}
+
+	ret = hws_bwc_matcher_move_all(bwc_matcher);
+	if (ret) {
+		mlx5hws_err(ctx, "Rehash error: moving rules failed\n");
+		return -ENOMEM;
+	}
+
+	bwc_matcher->matcher = new_matcher;
+	mlx5hws_matcher_destroy(old_matcher);
+
+	return 0;
+}
+
+static int
+hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	u32 num_of_rules;
+	int ret;
+
+	/* If the current matcher size is already at its max size, we can't
+	 * do the rehash. Skip it and try adding the rule again - perhaps
+	 * there was some change.
+	 */
+	if (hws_bwc_matcher_size_maxed_out(bwc_matcher))
+		return 0;
+
+	/* It is possible that other rule has already performed rehash.
+	 * Need to check again if we really need rehash.
+	 * If the reason for rehash was size, but not any more - skip rehash.
+	 */
+	num_of_rules = __atomic_load_n(&bwc_matcher->num_of_rules, __ATOMIC_RELAXED);
+	if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))
+		return 0;
+
+	/* Now we're done all the checking - do the rehash:
+	 *  - extend match RTC size
+	 *  - create new matcher
+	 *  - move all the rules to the new matcher
+	 *  - destroy the old matcher
+	 */
+
+	ret = hws_bwc_matcher_extend_size(bwc_matcher);
+	if (ret)
+		return ret;
+
+	return hws_bwc_matcher_move(bwc_matcher);
+}
+
+static int
+hws_bwc_matcher_rehash_at(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	/* Rehash by action template doesn't require any additional checking.
+	 * The bwc_matcher already contains the new action template.
+	 * Just do the usual rehash:
+	 *  - create new matcher
+	 *  - move all the rules to the new matcher
+	 *  - destroy the old matcher
+	 */
+	return hws_bwc_matcher_move(bwc_matcher);
+}
+
+int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
+				   u32 *match_param,
+				   struct mlx5hws_rule_action rule_actions[],
+				   u32 flow_source,
+				   u16 bwc_queue_idx)
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_rule_attr rule_attr;
+	struct mutex *queue_lock; /* Protect the queue */
+	u32 num_of_rules;
+	int ret = 0;
+	int at_idx;
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, bwc_queue_idx, flow_source, &rule_attr);
+
+	queue_lock = hws_bwc_get_queue_lock(ctx, bwc_queue_idx);
+
+	mutex_lock(queue_lock);
+
+	/* check if rehash needed due to missing action template */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (unlikely(at_idx < 0)) {
+		/* we need to extend BWC matcher action templates array */
+		mutex_unlock(queue_lock);
+		hws_bwc_lock_all_queues(ctx);
+
+		ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
+		if (unlikely(ret)) {
+			hws_bwc_unlock_all_queues(ctx);
+			return ret;
+		}
+
+		/* action templates array was extended, we need the last idx */
+		at_idx = bwc_matcher->num_of_at - 1;
+
+		ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
+						bwc_matcher->at[at_idx]);
+		if (unlikely(ret)) {
+			/* Action template attach failed, possibly due to
+			 * requiring more action STEs.
+			 * Need to attempt creating new matcher with all
+			 * the action templates, including the new one.
+			 */
+			ret = hws_bwc_matcher_rehash_at(bwc_matcher);
+			if (unlikely(ret)) {
+				mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
+				bwc_matcher->at[at_idx] = NULL;
+				bwc_matcher->num_of_at--;
+
+				hws_bwc_unlock_all_queues(ctx);
+
+				mlx5hws_err(ctx,
+					    "BWC rule insertion: rehash AT failed (%d)\n", ret);
+				return ret;
+			}
+		}
+
+		hws_bwc_unlock_all_queues(ctx);
+		mutex_lock(queue_lock);
+	}
+
+	/* check if number of rules require rehash */
+	num_of_rules = bwc_matcher->num_of_rules;
+
+	if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))) {
+		mutex_unlock(queue_lock);
+
+		hws_bwc_lock_all_queues(ctx);
+		ret = hws_bwc_matcher_rehash_size(bwc_matcher);
+		hws_bwc_unlock_all_queues(ctx);
+
+		if (ret) {
+			mlx5hws_err(ctx, "BWC rule insertion: rehash size [%d -> %d] failed (%d)\n",
+				    bwc_matcher->size_log - MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP,
+				    bwc_matcher->size_log,
+				    ret);
+			return ret;
+		}
+
+		mutex_lock(queue_lock);
+	}
+
+	ret = hws_bwc_rule_create_sync(bwc_rule,
+				       match_param,
+				       at_idx,
+				       rule_actions,
+				       &rule_attr);
+	if (likely(!ret)) {
+		hws_bwc_rule_list_add(bwc_rule, bwc_queue_idx);
+		mutex_unlock(queue_lock);
+		return 0; /* rule inserted successfully */
+	}
+
+	/* At this point the rule wasn't added.
+	 * It could be because there was collision, or some other problem.
+	 * If we don't dive deeper than API, the only thing we know is that
+	 * the status of completion is RTE_FLOW_OP_ERROR.
+	 * Try rehash by size and insert rule again - last chance.
+	 */
+
+	mutex_unlock(queue_lock);
+
+	hws_bwc_lock_all_queues(ctx);
+	ret = hws_bwc_matcher_rehash_size(bwc_matcher);
+	hws_bwc_unlock_all_queues(ctx);
+
+	if (ret) {
+		mlx5hws_err(ctx, "BWC rule insertion: rehash failed (%d)\n", ret);
+		return ret;
+	}
+
+	/* Rehash done, but we still have that pesky rule to add */
+	mutex_lock(queue_lock);
+
+	ret = hws_bwc_rule_create_sync(bwc_rule,
+				       match_param,
+				       at_idx,
+				       rule_actions,
+				       &rule_attr);
+
+	if (unlikely(ret)) {
+		mutex_unlock(queue_lock);
+		mlx5hws_err(ctx, "BWC rule insertion failed (%d)\n", ret);
+		return ret;
+	}
+
+	hws_bwc_rule_list_add(bwc_rule, bwc_queue_idx);
+	mutex_unlock(queue_lock);
+
+	return 0;
+}
+
+struct mlx5hws_bwc_rule *
+mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+			struct mlx5hws_match_parameters *params,
+			u32 flow_source,
+			struct mlx5hws_rule_action rule_actions[])
+{
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_bwc_rule *bwc_rule;
+	u16 bwc_queue_idx;
+	int ret;
+
+	if (unlikely(!mlx5hws_context_bwc_supported(ctx))) {
+		mlx5hws_err(ctx, "BWC rule: Context created w/o BWC API compatibility\n");
+		return NULL;
+	}
+
+	bwc_rule = mlx5hws_bwc_rule_alloc(bwc_matcher);
+	if (unlikely(!bwc_rule))
+		return NULL;
+
+	bwc_queue_idx = hws_bwc_gen_queue_idx(ctx);
+
+	ret = mlx5hws_bwc_rule_create_simple(bwc_rule,
+					     params->match_buf,
+					     rule_actions,
+					     flow_source,
+					     bwc_queue_idx);
+	if (unlikely(ret)) {
+		mlx5hws_bwc_rule_free(bwc_rule);
+		return NULL;
+	}
+
+	return bwc_rule;
+}
+
+static int
+hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
+			   struct mlx5hws_rule_action rule_actions[])
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+	struct mlx5hws_rule_attr rule_attr;
+	struct mutex *queue_lock; /* Protect the queue */
+	int at_idx, ret;
+	u16 idx;
+
+	idx = bwc_rule->bwc_queue_idx;
+
+	mlx5hws_bwc_rule_fill_attr(bwc_matcher, idx, 0, &rule_attr);
+	queue_lock = hws_bwc_get_queue_lock(ctx, idx);
+
+	mutex_lock(queue_lock);
+
+	/* check if rehash needed due to missing action template */
+	at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+	if (unlikely(at_idx < 0)) {
+		/* we need to extend BWC matcher action templates array */
+		mutex_unlock(queue_lock);
+		hws_bwc_lock_all_queues(ctx);
+
+		/* check again - perhaps other thread already did extend_at */
+		at_idx = hws_bwc_matcher_find_at(bwc_matcher, rule_actions);
+		if (likely(at_idx < 0)) {
+			ret = hws_bwc_matcher_extend_at(bwc_matcher, rule_actions);
+			if (unlikely(ret)) {
+				hws_bwc_unlock_all_queues(ctx);
+				mlx5hws_err(ctx, "BWC rule update: failed extending AT (%d)", ret);
+				return -EINVAL;
+			}
+
+			/* action templates array was extended, we need the last idx */
+			at_idx = bwc_matcher->num_of_at - 1;
+
+			ret = mlx5hws_matcher_attach_at(bwc_matcher->matcher,
+							bwc_matcher->at[at_idx]);
+			if (unlikely(ret)) {
+				/* Action template attach failed, possibly due to
+				 * requiring more action STEs.
+				 * Need to attempt creating new matcher with all
+				 * the action templates, including the new one.
+				 */
+				ret = hws_bwc_matcher_rehash_at(bwc_matcher);
+				if (unlikely(ret)) {
+					mlx5hws_action_template_destroy(bwc_matcher->at[at_idx]);
+					bwc_matcher->at[at_idx] = NULL;
+					bwc_matcher->num_of_at--;
+
+					hws_bwc_unlock_all_queues(ctx);
+
+					mlx5hws_err(ctx,
+						    "BWC rule update: rehash AT failed (%d)\n",
+						    ret);
+					return ret;
+				}
+			}
+		}
+
+		hws_bwc_unlock_all_queues(ctx);
+		mutex_lock(queue_lock);
+	}
+
+	ret = hws_bwc_rule_update_sync(bwc_rule,
+				       at_idx,
+				       rule_actions,
+				       &rule_attr);
+	mutex_unlock(queue_lock);
+
+	if (unlikely(ret))
+		mlx5hws_err(ctx, "BWC rule: update failed (%d)\n", ret);
+
+	return ret;
+}
+
+int mlx5hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_rule_action rule_actions[])
+{
+	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
+	struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
+
+	if (unlikely(!mlx5hws_context_bwc_supported(ctx))) {
+		mlx5hws_err(ctx, "BWC rule: Context created w/o BWC API compatibility\n");
+		return -EINVAL;
+	}
+
+	return hws_bwc_rule_action_update(bwc_rule, rule_actions);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h
new file mode 100644
index 000000000000..4fe8c32d8fbe
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_BWC_H_
+#define MLX5HWS_BWC_H_
+
+#define MLX5HWS_BWC_MATCHER_INIT_SIZE_LOG 1
+#define MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP 1
+#define MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH 70
+#define MLX5HWS_BWC_MATCHER_REHASH_BURST_TH 32
+#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 255
+
+#define MLX5HWS_BWC_MAX_ACTS 16
+
+struct mlx5hws_bwc_matcher {
+	struct mlx5hws_matcher *matcher;
+	struct mlx5hws_match_template *mt;
+	struct mlx5hws_action_template *at[MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM];
+	u8 num_of_at;
+	u16 priority;
+	u8 size_log;
+	u32 num_of_rules; /* atomically accessed */
+	struct list_head *rules;
+};
+
+struct mlx5hws_bwc_rule {
+	struct mlx5hws_bwc_matcher *bwc_matcher;
+	struct mlx5hws_rule *rule;
+	u16 bwc_queue_idx;
+	struct list_head list_node;
+};
+
+int
+mlx5hws_bwc_matcher_create_simple(struct mlx5hws_bwc_matcher *bwc_matcher,
+				  struct mlx5hws_table *table,
+				  u32 priority,
+				  u8 match_criteria_enable,
+				  struct mlx5hws_match_parameters *mask,
+				  enum mlx5hws_action_type action_types[]);
+
+int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher);
+
+struct mlx5hws_bwc_rule *mlx5hws_bwc_rule_alloc(struct mlx5hws_bwc_matcher *bwc_matcher);
+
+void mlx5hws_bwc_rule_free(struct mlx5hws_bwc_rule *bwc_rule);
+
+int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
+				   u32 *match_param,
+				   struct mlx5hws_rule_action rule_actions[],
+				   u32 flow_source,
+				   u16 bwc_queue_idx);
+
+int mlx5hws_bwc_rule_destroy_simple(struct mlx5hws_bwc_rule *bwc_rule);
+
+void mlx5hws_bwc_rule_fill_attr(struct mlx5hws_bwc_matcher *bwc_matcher,
+				u16 bwc_queue_idx,
+				u32 flow_source,
+				struct mlx5hws_rule_attr *rule_attr);
+
+static inline u16 mlx5hws_bwc_queues(struct mlx5hws_context *ctx)
+{
+	/* Besides the control queue, half of the queues are
+	 * reguler HWS queues, and the other half are BWC queues.
+	 */
+	return (ctx->queues - 1) / 2;
+}
+
+static inline u16 mlx5hws_bwc_get_queue_id(struct mlx5hws_context *ctx, u16 idx)
+{
+	return idx + mlx5hws_bwc_queues(ctx);
+}
+
+#endif /* MLX5HWS_BWC_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c
new file mode 100644
index 000000000000..bb563f50ef09
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+
+bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
+					 u8 match_criteria_enable,
+					 struct mlx5hws_match_parameters *mask)
+{
+	struct mlx5hws_definer match_layout = {0};
+	struct mlx5hws_match_template *mt;
+	bool is_complex = false;
+	int ret;
+
+	if (!match_criteria_enable)
+		return false; /* empty matcher */
+
+	mt = mlx5hws_match_template_create(ctx,
+					   mask->match_buf,
+					   mask->match_sz,
+					   match_criteria_enable);
+	if (!mt) {
+		mlx5hws_err(ctx, "BWC: failed creating match template\n");
+		return false;
+	}
+
+	ret = mlx5hws_definer_calc_layout(ctx, mt, &match_layout);
+	if (ret) {
+		/* The only case that we're interested in is E2BIG,
+		 * which means that the match parameters need to be
+		 * split into complex martcher.
+		 * For all other cases (good or bad) - just return true
+		 * and let the usual match creation path handle it,
+		 * both for good and bad flows.
+		 */
+		if (ret == E2BIG) {
+			is_complex = true;
+			mlx5hws_dbg(ctx, "Matcher definer layout: need complex matcher\n");
+		} else {
+			mlx5hws_err(ctx, "Failed to calculate matcher definer layout\n");
+		}
+	}
+
+	mlx5hws_match_template_destroy(mt);
+
+	return is_complex;
+}
+
+int mlx5hws_bwc_matcher_create_complex(struct mlx5hws_bwc_matcher *bwc_matcher,
+				       struct mlx5hws_table *table,
+				       u32 priority,
+				       u8 match_criteria_enable,
+				       struct mlx5hws_match_parameters *mask)
+{
+	mlx5hws_err(table->ctx, "Complex matcher is not supported yet\n");
+	return -EOPNOTSUPP;
+}
+
+void
+mlx5hws_bwc_matcher_destroy_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	/* nothing to do here */
+}
+
+int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
+				    struct mlx5hws_match_parameters *params,
+				    u32 flow_source,
+				    struct mlx5hws_rule_action rule_actions[],
+				    u16 bwc_queue_idx)
+{
+	mlx5hws_err(bwc_rule->bwc_matcher->matcher->tbl->ctx,
+		    "Complex rule is not supported yet\n");
+	return -EOPNOTSUPP;
+}
+
+int mlx5hws_bwc_rule_destroy_complex(struct mlx5hws_bwc_rule *bwc_rule)
+{
+	return 0;
+}
+
+int mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
+{
+	mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
+		    "Moving complex rule is not supported yet\n");
+	return -EOPNOTSUPP;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.h
new file mode 100644
index 000000000000..068ee8118609
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_bwc_complex.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_BWC_COMPLEX_H_
+#define MLX5HWS_BWC_COMPLEX_H_
+
+bool mlx5hws_bwc_match_params_is_complex(struct mlx5hws_context *ctx,
+					 u8 match_criteria_enable,
+					 struct mlx5hws_match_parameters *mask);
+
+int mlx5hws_bwc_matcher_create_complex(struct mlx5hws_bwc_matcher *bwc_matcher,
+				       struct mlx5hws_table *table,
+				       u32 priority,
+				       u8 match_criteria_enable,
+				       struct mlx5hws_match_parameters *mask);
+
+void mlx5hws_bwc_matcher_destroy_complex(struct mlx5hws_bwc_matcher *bwc_matcher);
+
+int mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher);
+
+int mlx5hws_bwc_rule_create_complex(struct mlx5hws_bwc_rule *bwc_rule,
+				    struct mlx5hws_match_parameters *params,
+				    u32 flow_source,
+				    struct mlx5hws_rule_action rule_actions[],
+				    u16 bwc_queue_idx);
+
+int mlx5hws_bwc_rule_destroy_complex(struct mlx5hws_bwc_rule *bwc_rule);
+
+#endif /* MLX5HWS_BWC_COMPLEX_H_ */
-- 
cgit v1.3-3-g829e


From d4a605e968e7f0af58f228ab7bf96d9d7d4f0b69 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:40:54 +0300
Subject: net/mlx5: HWS, added debug dump and internal headers

Added debug dump of the existing HWS state,
and all the required internal definitions.

To dump the HWS state, cat the following debugfs node:

  cat /sys/kernel/debug/mlx5/<PCI>/steering/fdb/ctx_<ctx_id>

Reviewed-by: Hamdan Agbariya <hamdani@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_debug.c         | 480 +++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_debug.h         |  40 ++
 .../mlx5/core/steering/hws/mlx5hws_internal.h      |  59 +++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_prm.h  | 514 +++++++++++++++++++++
 4 files changed, 1093 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_prm.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.c
new file mode 100644
index 000000000000..2b8c5a4e1c4c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.c
@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/version.h>
+#include "mlx5hws_internal.h"
+
+static int
+hws_debug_dump_matcher_template_definer(struct seq_file *f,
+					void *parent_obj,
+					struct mlx5hws_definer *definer,
+					enum mlx5hws_debug_res_type type)
+{
+	int i;
+
+	if (!definer)
+		return 0;
+
+	seq_printf(f, "%d,0x%llx,0x%llx,%d,%d,",
+		   type,
+		   HWS_PTR_TO_ID(definer),
+		   HWS_PTR_TO_ID(parent_obj),
+		   definer->obj_id,
+		   definer->type);
+
+	for (i = 0; i < DW_SELECTORS; i++)
+		seq_printf(f, "0x%x%s", definer->dw_selector[i],
+			   (i == DW_SELECTORS - 1) ? "," : "-");
+
+	for (i = 0; i < BYTE_SELECTORS; i++)
+		seq_printf(f, "0x%x%s", definer->byte_selector[i],
+			   (i == BYTE_SELECTORS - 1) ? "," : "-");
+
+	for (i = 0; i < MLX5HWS_JUMBO_TAG_SZ; i++)
+		seq_printf(f, "%02x", definer->mask.jumbo[i]);
+
+	seq_puts(f, "\n");
+
+	return 0;
+}
+
+static int
+hws_debug_dump_matcher_match_template(struct seq_file *f, struct mlx5hws_matcher *matcher)
+{
+	enum mlx5hws_debug_res_type type;
+	int i, ret;
+
+	for (i = 0; i < matcher->num_of_mt; i++) {
+		struct mlx5hws_match_template *mt = &matcher->mt[i];
+
+		seq_printf(f, "%d,0x%llx,0x%llx,%d,%d,%d\n",
+			   MLX5HWS_DEBUG_RES_TYPE_MATCHER_MATCH_TEMPLATE,
+			   HWS_PTR_TO_ID(mt),
+			   HWS_PTR_TO_ID(matcher),
+			   mt->fc_sz,
+			   0, 0);
+
+		type = MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_MATCH_DEFINER;
+		ret = hws_debug_dump_matcher_template_definer(f, mt, mt->definer, type);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+hws_debug_dump_matcher_action_template(struct seq_file *f, struct mlx5hws_matcher *matcher)
+{
+	enum mlx5hws_action_type action_type;
+	int i, j;
+
+	for (i = 0; i < matcher->num_of_at; i++) {
+		struct mlx5hws_action_template *at = &matcher->at[i];
+
+		seq_printf(f, "%d,0x%llx,0x%llx,%d,%d,%d",
+			   MLX5HWS_DEBUG_RES_TYPE_MATCHER_ACTION_TEMPLATE,
+			   HWS_PTR_TO_ID(at),
+			   HWS_PTR_TO_ID(matcher),
+			   at->only_term,
+			   at->num_of_action_stes,
+			   at->num_actions);
+
+		for (j = 0; j < at->num_actions; j++) {
+			action_type = at->action_type_arr[j];
+			seq_printf(f, ",%s", mlx5hws_action_type_to_str(action_type));
+		}
+
+		seq_puts(f, "\n");
+	}
+
+	return 0;
+}
+
+static int
+hws_debug_dump_matcher_attr(struct seq_file *f, struct mlx5hws_matcher *matcher)
+{
+	struct mlx5hws_matcher_attr *attr = &matcher->attr;
+
+	seq_printf(f, "%d,0x%llx,%d,%d,%d,%d,%d,%d,%d,%d\n",
+		   MLX5HWS_DEBUG_RES_TYPE_MATCHER_ATTR,
+		   HWS_PTR_TO_ID(matcher),
+		   attr->priority,
+		   attr->mode,
+		   attr->table.sz_row_log,
+		   attr->table.sz_col_log,
+		   attr->optimize_using_rule_idx,
+		   attr->optimize_flow_src,
+		   attr->insert_mode,
+		   attr->distribute_mode);
+
+	return 0;
+}
+
+static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *matcher)
+{
+	enum mlx5hws_table_type tbl_type = matcher->tbl->type;
+	struct mlx5hws_cmd_ft_query_attr ft_attr = {0};
+	struct mlx5hws_pool_chunk *ste;
+	struct mlx5hws_pool *ste_pool;
+	u64 icm_addr_0 = 0;
+	u64 icm_addr_1 = 0;
+	u32 ste_0_id = -1;
+	u32 ste_1_id = -1;
+	int ret;
+
+	seq_printf(f, "%d,0x%llx,0x%llx,%d,%d,0x%llx",
+		   MLX5HWS_DEBUG_RES_TYPE_MATCHER,
+		   HWS_PTR_TO_ID(matcher),
+		   HWS_PTR_TO_ID(matcher->tbl),
+		   matcher->num_of_mt,
+		   matcher->end_ft_id,
+		   matcher->col_matcher ? HWS_PTR_TO_ID(matcher->col_matcher) : 0);
+
+	ste = &matcher->match_ste.ste;
+	ste_pool = matcher->match_ste.pool;
+	if (ste_pool) {
+		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
+			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+	}
+
+	seq_printf(f, ",%d,%d,%d,%d",
+		   matcher->match_ste.rtc_0_id,
+		   (int)ste_0_id,
+		   matcher->match_ste.rtc_1_id,
+		   (int)ste_1_id);
+
+	ste = &matcher->action_ste[0].ste;
+	ste_pool = matcher->action_ste[0].pool;
+	if (ste_pool) {
+		ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste);
+		if (tbl_type == MLX5HWS_TABLE_TYPE_FDB)
+			ste_1_id = mlx5hws_pool_chunk_get_base_mirror_id(ste_pool, ste);
+		else
+			ste_1_id = -1;
+	} else {
+		ste_0_id = -1;
+		ste_1_id = -1;
+	}
+
+	ft_attr.type = matcher->tbl->fw_ft_type;
+	ret = mlx5hws_cmd_flow_table_query(matcher->tbl->ctx->mdev,
+					   matcher->end_ft_id,
+					   &ft_attr,
+					   &icm_addr_0,
+					   &icm_addr_1);
+	if (ret)
+		return ret;
+
+	seq_printf(f, ",%d,%d,%d,%d,%d,0x%llx,0x%llx\n",
+		   matcher->action_ste[0].rtc_0_id,
+		   (int)ste_0_id,
+		   matcher->action_ste[0].rtc_1_id,
+		   (int)ste_1_id,
+		   0,
+		   mlx5hws_debug_icm_to_idx(icm_addr_0),
+		   mlx5hws_debug_icm_to_idx(icm_addr_1));
+
+	ret = hws_debug_dump_matcher_attr(f, matcher);
+	if (ret)
+		return ret;
+
+	ret = hws_debug_dump_matcher_match_template(f, matcher);
+	if (ret)
+		return ret;
+
+	ret = hws_debug_dump_matcher_action_template(f, matcher);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int hws_debug_dump_table(struct seq_file *f, struct mlx5hws_table *tbl)
+{
+	struct mlx5hws_cmd_ft_query_attr ft_attr = {0};
+	struct mlx5hws_matcher *matcher;
+	u64 local_icm_addr_0 = 0;
+	u64 local_icm_addr_1 = 0;
+	u64 icm_addr_0 = 0;
+	u64 icm_addr_1 = 0;
+	int ret;
+
+	seq_printf(f, "%d,0x%llx,0x%llx,%d,%d,%d,%d,%d",
+		   MLX5HWS_DEBUG_RES_TYPE_TABLE,
+		   HWS_PTR_TO_ID(tbl),
+		   HWS_PTR_TO_ID(tbl->ctx),
+		   tbl->ft_id,
+		   MLX5HWS_TABLE_TYPE_BASE + tbl->type,
+		   tbl->fw_ft_type,
+		   tbl->level,
+		   0);
+
+	ft_attr.type = tbl->fw_ft_type;
+	ret = mlx5hws_cmd_flow_table_query(tbl->ctx->mdev,
+					   tbl->ft_id,
+					   &ft_attr,
+					   &icm_addr_0,
+					   &icm_addr_1);
+	if (ret)
+		return ret;
+
+	seq_printf(f, ",0x%llx,0x%llx,0x%llx,0x%llx,0x%llx\n",
+		   mlx5hws_debug_icm_to_idx(icm_addr_0),
+		   mlx5hws_debug_icm_to_idx(icm_addr_1),
+		   mlx5hws_debug_icm_to_idx(local_icm_addr_0),
+		   mlx5hws_debug_icm_to_idx(local_icm_addr_1),
+		   HWS_PTR_TO_ID(tbl->default_miss.miss_tbl));
+
+	list_for_each_entry(matcher, &tbl->matchers_list, list_node) {
+		ret = hws_debug_dump_matcher(f, matcher);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+hws_debug_dump_context_send_engine(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_send_engine *send_queue;
+	struct mlx5hws_send_ring *send_ring;
+	struct mlx5hws_send_ring_cq *cq;
+	struct mlx5hws_send_ring_sq *sq;
+	int i;
+
+	for (i = 0; i < (int)ctx->queues; i++) {
+		send_queue = &ctx->send_queue[i];
+		seq_printf(f, "%d,0x%llx,%d,%d,%d,%d,%d,%d,%d,%d,%d\n",
+			   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_SEND_ENGINE,
+			   HWS_PTR_TO_ID(ctx),
+			   i,
+			   send_queue->used_entries,
+			   send_queue->num_entries,
+			   1, /* one send ring per queue */
+			   send_queue->num_entries,
+			   send_queue->err,
+			   send_queue->completed.ci,
+			   send_queue->completed.pi,
+			   send_queue->completed.mask);
+
+		send_ring = &send_queue->send_ring;
+		cq = &send_ring->send_cq;
+		sq = &send_ring->send_sq;
+
+		seq_printf(f, "%d,0x%llx,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d\n",
+			   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_SEND_RING,
+			   HWS_PTR_TO_ID(ctx),
+			   0, /* one send ring per send queue */
+			   i,
+			   cq->mcq.cqn,
+			   0,
+			   0,
+			   0,
+			   0,
+			   0,
+			   0,
+			   cq->mcq.cqe_sz,
+			   sq->sqn,
+			   0,
+			   0,
+			   0);
+	}
+
+	return 0;
+}
+
+static int hws_debug_dump_context_caps(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_cmd_query_caps *caps = ctx->caps;
+
+	seq_printf(f, "%d,0x%llx,%s,%d,%d,%d,%d,",
+		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_CAPS,
+		   HWS_PTR_TO_ID(ctx),
+		   caps->fw_ver,
+		   caps->wqe_based_update,
+		   caps->ste_format,
+		   caps->ste_alloc_log_max,
+		   caps->log_header_modify_argument_max_alloc);
+
+	seq_printf(f, "%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%s\n",
+		   caps->flex_protocols,
+		   caps->rtc_reparse_mode,
+		   caps->rtc_index_mode,
+		   caps->ste_alloc_log_gran,
+		   caps->stc_alloc_log_max,
+		   caps->stc_alloc_log_gran,
+		   caps->rtc_log_depth_max,
+		   caps->format_select_gtpu_dw_0,
+		   caps->format_select_gtpu_dw_1,
+		   caps->format_select_gtpu_dw_2,
+		   caps->format_select_gtpu_ext_dw_0,
+		   caps->nic_ft.max_level,
+		   caps->nic_ft.reparse,
+		   caps->fdb_ft.max_level,
+		   caps->fdb_ft.reparse,
+		   caps->log_header_modify_argument_granularity,
+		   caps->linear_match_definer,
+		   "regc_3");
+
+	return 0;
+}
+
+static int hws_debug_dump_context_attr(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	seq_printf(f, "%u,0x%llx,%d,%zu,%d,%s,%d,%d\n",
+		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_ATTR,
+		   HWS_PTR_TO_ID(ctx),
+		   ctx->pd_num,
+		   ctx->queues,
+		   ctx->send_queue->num_entries,
+		   "None", /* no shared gvmi */
+		   ctx->caps->vhca_id,
+		   0xffff); /* no shared gvmi */
+
+	return 0;
+}
+
+static int hws_debug_dump_context_info(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	struct mlx5_core_dev *dev = ctx->mdev;
+	int ret;
+
+	seq_printf(f, "%d,0x%llx,%d,%s,%s.KERNEL_%u_%u_%u\n",
+		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT,
+		   HWS_PTR_TO_ID(ctx),
+		   ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT,
+		   pci_name(dev->pdev),
+		   HWS_DEBUG_FORMAT_VERSION,
+		   LINUX_VERSION_MAJOR,
+		   LINUX_VERSION_PATCHLEVEL,
+		   LINUX_VERSION_SUBLEVEL);
+
+	ret = hws_debug_dump_context_attr(f, ctx);
+	if (ret)
+		return ret;
+
+	ret = hws_debug_dump_context_caps(f, ctx);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int hws_debug_dump_context_stc_resource(struct seq_file *f,
+					       struct mlx5hws_context *ctx,
+					       u32 tbl_type,
+					       struct mlx5hws_pool_resource *resource)
+{
+	seq_printf(f, "%d,0x%llx,%u,%u\n",
+		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_STC,
+		   HWS_PTR_TO_ID(ctx),
+		   tbl_type,
+		   resource->base_id);
+
+	return 0;
+}
+
+static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_pool *stc_pool;
+	u32 table_type;
+	int ret;
+	int i;
+
+	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
+		stc_pool = ctx->stc_pool[i];
+		table_type = MLX5HWS_TABLE_TYPE_BASE + i;
+
+		if (!stc_pool)
+			continue;
+
+		if (stc_pool->resource[0]) {
+			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
+								  stc_pool->resource[0]);
+			if (ret)
+				return ret;
+		}
+
+		if (i == MLX5HWS_TABLE_TYPE_FDB && stc_pool->mirror_resource[0]) {
+			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
+								  stc_pool->mirror_resource[0]);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int hws_debug_dump_context(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_table *tbl;
+	int ret;
+
+	ret = hws_debug_dump_context_info(f, ctx);
+	if (ret)
+		return ret;
+
+	ret = hws_debug_dump_context_send_engine(f, ctx);
+	if (ret)
+		return ret;
+
+	ret = hws_debug_dump_context_stc(f, ctx);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(tbl, &ctx->tbl_list, tbl_list_node) {
+		ret = hws_debug_dump_table(f, tbl);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int
+hws_debug_dump(struct seq_file *f, struct mlx5hws_context *ctx)
+{
+	int ret;
+
+	if (!f || !ctx)
+		return -EINVAL;
+
+	mutex_lock(&ctx->ctrl_lock);
+	ret = hws_debug_dump_context(f, ctx);
+	mutex_unlock(&ctx->ctrl_lock);
+
+	return ret;
+}
+
+static int hws_dump_show(struct seq_file *file, void *priv)
+{
+	return hws_debug_dump(file, file->private);
+}
+DEFINE_SHOW_ATTRIBUTE(hws_dump);
+
+void mlx5hws_debug_init_dump(struct mlx5hws_context *ctx)
+{
+	struct mlx5_core_dev *dev = ctx->mdev;
+	char file_name[128];
+
+	ctx->debug_info.steering_debugfs =
+		debugfs_create_dir("steering", mlx5_debugfs_get_dev_root(dev));
+	ctx->debug_info.fdb_debugfs =
+		debugfs_create_dir("fdb", ctx->debug_info.steering_debugfs);
+
+	sprintf(file_name, "ctx_%p", ctx);
+	debugfs_create_file(file_name, 0444, ctx->debug_info.fdb_debugfs,
+			    ctx, &hws_dump_fops);
+}
+
+void mlx5hws_debug_uninit_dump(struct mlx5hws_context *ctx)
+{
+	debugfs_remove_recursive(ctx->debug_info.steering_debugfs);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.h
new file mode 100644
index 000000000000..b93a536035d9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_debug.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_DEBUG_H_
+#define MLX5HWS_DEBUG_H_
+
+#define HWS_DEBUG_FORMAT_VERSION "1.0"
+
+#define HWS_PTR_TO_ID(p) ((u64)(uintptr_t)(p) & 0xFFFFFFFFULL)
+
+enum mlx5hws_debug_res_type {
+	MLX5HWS_DEBUG_RES_TYPE_CONTEXT = 4000,
+	MLX5HWS_DEBUG_RES_TYPE_CONTEXT_ATTR = 4001,
+	MLX5HWS_DEBUG_RES_TYPE_CONTEXT_CAPS = 4002,
+	MLX5HWS_DEBUG_RES_TYPE_CONTEXT_SEND_ENGINE = 4003,
+	MLX5HWS_DEBUG_RES_TYPE_CONTEXT_SEND_RING = 4004,
+	MLX5HWS_DEBUG_RES_TYPE_CONTEXT_STC = 4005,
+
+	MLX5HWS_DEBUG_RES_TYPE_TABLE = 4100,
+
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER = 4200,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_ATTR = 4201,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_MATCH_TEMPLATE = 4202,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_MATCH_DEFINER = 4203,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_ACTION_TEMPLATE = 4204,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_HASH_DEFINER = 4205,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_RANGE_DEFINER = 4206,
+	MLX5HWS_DEBUG_RES_TYPE_MATCHER_TEMPLATE_COMPARE_MATCH_DEFINER = 4207,
+};
+
+static inline u64
+mlx5hws_debug_icm_to_idx(u64 icm_addr)
+{
+	return (icm_addr >> 6) & 0xffffffff;
+}
+
+void mlx5hws_debug_init_dump(struct mlx5hws_context *ctx);
+void mlx5hws_debug_uninit_dump(struct mlx5hws_context *ctx);
+
+#endif /* MLX5HWS_DEBUG_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h
new file mode 100644
index 000000000000..458bc31be6ac
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_INTERNAL_H_
+#define MLX5HWS_INTERNAL_H_
+
+#include <linux/mlx5/transobj.h>
+
+#include "../dr_types.h"
+
+#include "mlx5hws_prm.h"
+
+#include "mlx5hws.h"
+
+#include "mlx5hws_pool.h"
+#include "mlx5hws_vport.h"
+#include "mlx5hws_context.h"
+#include "mlx5hws_table.h"
+#include "mlx5hws_send.h"
+#include "mlx5hws_rule.h"
+#include "mlx5hws_cmd.h"
+#include "mlx5hws_action.h"
+#include "mlx5hws_definer.h"
+#include "mlx5hws_matcher.h"
+#include "mlx5hws_debug.h"
+#include "mlx5hws_pat_arg.h"
+#include "mlx5hws_bwc.h"
+#include "mlx5hws_bwc_complex.h"
+
+#define W_SIZE		2
+#define DW_SIZE		4
+#define BITS_IN_BYTE	8
+#define BITS_IN_DW	(BITS_IN_BYTE * DW_SIZE)
+
+#define IS_BIT_SET(_value, _bit) ((_value) & (1ULL << (_bit)))
+
+#define mlx5hws_err(ctx, arg...) mlx5_core_err((ctx)->mdev, ##arg)
+#define mlx5hws_info(ctx, arg...) mlx5_core_info((ctx)->mdev, ##arg)
+#define mlx5hws_dbg(ctx, arg...) mlx5_core_dbg((ctx)->mdev, ##arg)
+
+#define MLX5HWS_TABLE_TYPE_BASE 2
+#define MLX5HWS_ACTION_STE_IDX_ANY 0
+
+static inline bool is_mem_zero(const u8 *mem, size_t size)
+{
+	if (unlikely(!size)) {
+		pr_warn("HWS: invalid buffer of size 0 in %s\n", __func__);
+		return true;
+	}
+
+	return (*mem == 0) && memcmp(mem, mem + 1, size - 1) == 0;
+}
+
+static inline unsigned long align(unsigned long val, unsigned long align)
+{
+	return (val + align - 1) & ~(align - 1);
+}
+
+#endif /* MLX5HWS_INTERNAL_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_prm.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_prm.h
new file mode 100644
index 000000000000..de92cecbeb92
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_prm.h
@@ -0,0 +1,514 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5_PRM_H_
+#define MLX5_PRM_H_
+
+#define MLX5_MAX_ACTIONS_DATA_IN_HEADER_MODIFY 512
+
+/* Action type of header modification. */
+enum {
+	MLX5_MODIFICATION_TYPE_SET = 0x1,
+	MLX5_MODIFICATION_TYPE_ADD = 0x2,
+	MLX5_MODIFICATION_TYPE_COPY = 0x3,
+	MLX5_MODIFICATION_TYPE_INSERT = 0x4,
+	MLX5_MODIFICATION_TYPE_REMOVE = 0x5,
+	MLX5_MODIFICATION_TYPE_NOP = 0x6,
+	MLX5_MODIFICATION_TYPE_REMOVE_WORDS = 0x7,
+	MLX5_MODIFICATION_TYPE_ADD_FIELD = 0x8,
+	MLX5_MODIFICATION_TYPE_MAX,
+};
+
+/* The field of packet to be modified. */
+enum mlx5_modification_field {
+	MLX5_MODI_OUT_NONE = -1,
+	MLX5_MODI_OUT_SMAC_47_16 = 1,
+	MLX5_MODI_OUT_SMAC_15_0,
+	MLX5_MODI_OUT_ETHERTYPE,
+	MLX5_MODI_OUT_DMAC_47_16,
+	MLX5_MODI_OUT_DMAC_15_0,
+	MLX5_MODI_OUT_IP_DSCP,
+	MLX5_MODI_OUT_TCP_FLAGS,
+	MLX5_MODI_OUT_TCP_SPORT,
+	MLX5_MODI_OUT_TCP_DPORT,
+	MLX5_MODI_OUT_IPV4_TTL,
+	MLX5_MODI_OUT_UDP_SPORT,
+	MLX5_MODI_OUT_UDP_DPORT,
+	MLX5_MODI_OUT_SIPV6_127_96,
+	MLX5_MODI_OUT_SIPV6_95_64,
+	MLX5_MODI_OUT_SIPV6_63_32,
+	MLX5_MODI_OUT_SIPV6_31_0,
+	MLX5_MODI_OUT_DIPV6_127_96,
+	MLX5_MODI_OUT_DIPV6_95_64,
+	MLX5_MODI_OUT_DIPV6_63_32,
+	MLX5_MODI_OUT_DIPV6_31_0,
+	MLX5_MODI_OUT_SIPV4,
+	MLX5_MODI_OUT_DIPV4,
+	MLX5_MODI_OUT_FIRST_VID,
+	MLX5_MODI_IN_SMAC_47_16 = 0x31,
+	MLX5_MODI_IN_SMAC_15_0,
+	MLX5_MODI_IN_ETHERTYPE,
+	MLX5_MODI_IN_DMAC_47_16,
+	MLX5_MODI_IN_DMAC_15_0,
+	MLX5_MODI_IN_IP_DSCP,
+	MLX5_MODI_IN_TCP_FLAGS,
+	MLX5_MODI_IN_TCP_SPORT,
+	MLX5_MODI_IN_TCP_DPORT,
+	MLX5_MODI_IN_IPV4_TTL,
+	MLX5_MODI_IN_UDP_SPORT,
+	MLX5_MODI_IN_UDP_DPORT,
+	MLX5_MODI_IN_SIPV6_127_96,
+	MLX5_MODI_IN_SIPV6_95_64,
+	MLX5_MODI_IN_SIPV6_63_32,
+	MLX5_MODI_IN_SIPV6_31_0,
+	MLX5_MODI_IN_DIPV6_127_96,
+	MLX5_MODI_IN_DIPV6_95_64,
+	MLX5_MODI_IN_DIPV6_63_32,
+	MLX5_MODI_IN_DIPV6_31_0,
+	MLX5_MODI_IN_SIPV4,
+	MLX5_MODI_IN_DIPV4,
+	MLX5_MODI_OUT_IPV6_HOPLIMIT,
+	MLX5_MODI_IN_IPV6_HOPLIMIT,
+	MLX5_MODI_META_DATA_REG_A,
+	MLX5_MODI_META_DATA_REG_B = 0x50,
+	MLX5_MODI_META_REG_C_0,
+	MLX5_MODI_META_REG_C_1,
+	MLX5_MODI_META_REG_C_2,
+	MLX5_MODI_META_REG_C_3,
+	MLX5_MODI_META_REG_C_4,
+	MLX5_MODI_META_REG_C_5,
+	MLX5_MODI_META_REG_C_6,
+	MLX5_MODI_META_REG_C_7,
+	MLX5_MODI_OUT_TCP_SEQ_NUM,
+	MLX5_MODI_IN_TCP_SEQ_NUM,
+	MLX5_MODI_OUT_TCP_ACK_NUM,
+	MLX5_MODI_IN_TCP_ACK_NUM = 0x5C,
+	MLX5_MODI_GTP_TEID = 0x6E,
+	MLX5_MODI_OUT_IP_ECN = 0x73,
+	MLX5_MODI_TUNNEL_HDR_DW_1 = 0x75,
+	MLX5_MODI_GTPU_FIRST_EXT_DW_0 = 0x76,
+	MLX5_MODI_HASH_RESULT = 0x81,
+	MLX5_MODI_IN_MPLS_LABEL_0 = 0x8a,
+	MLX5_MODI_IN_MPLS_LABEL_1,
+	MLX5_MODI_IN_MPLS_LABEL_2,
+	MLX5_MODI_IN_MPLS_LABEL_3,
+	MLX5_MODI_IN_MPLS_LABEL_4,
+	MLX5_MODI_OUT_IP_PROTOCOL = 0x4A,
+	MLX5_MODI_OUT_IPV6_NEXT_HDR = 0x4A,
+	MLX5_MODI_META_REG_C_8 = 0x8F,
+	MLX5_MODI_META_REG_C_9 = 0x90,
+	MLX5_MODI_META_REG_C_10 = 0x91,
+	MLX5_MODI_META_REG_C_11 = 0x92,
+	MLX5_MODI_META_REG_C_12 = 0x93,
+	MLX5_MODI_META_REG_C_13 = 0x94,
+	MLX5_MODI_META_REG_C_14 = 0x95,
+	MLX5_MODI_META_REG_C_15 = 0x96,
+	MLX5_MODI_OUT_IPV4_TOTAL_LEN = 0x11D,
+	MLX5_MODI_OUT_IPV6_PAYLOAD_LEN = 0x11E,
+	MLX5_MODI_OUT_IPV4_IHL = 0x11F,
+	MLX5_MODI_OUT_TCP_DATA_OFFSET = 0x120,
+	MLX5_MODI_OUT_ESP_SPI = 0x5E,
+	MLX5_MODI_OUT_ESP_SEQ_NUM = 0x82,
+	MLX5_MODI_OUT_IPSEC_NEXT_HDR = 0x126,
+	MLX5_MODI_INVALID = INT_MAX,
+};
+
+enum {
+	MLX5_GET_HCA_CAP_OP_MOD_NIC_FLOW_TABLE = 0x7 << 1,
+	MLX5_GET_HCA_CAP_OP_MOD_ESW_FLOW_TABLE = 0x8 << 1,
+	MLX5_SET_HCA_CAP_OP_MOD_ESW = 0x9 << 1,
+	MLX5_GET_HCA_CAP_OP_MOD_WQE_BASED_FLOW_TABLE = 0x1B << 1,
+	MLX5_GET_HCA_CAP_OP_MOD_GENERAL_DEVICE_2 = 0x20 << 1,
+};
+
+enum mlx5_ifc_rtc_update_mode {
+	MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH = 0x0,
+	MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET = 0x1,
+};
+
+enum mlx5_ifc_rtc_access_mode {
+	MLX5_IFC_RTC_STE_ACCESS_MODE_BY_HASH = 0x0,
+	MLX5_IFC_RTC_STE_ACCESS_MODE_LINEAR = 0x1,
+};
+
+enum mlx5_ifc_rtc_ste_format {
+	MLX5_IFC_RTC_STE_FORMAT_8DW = 0x4,
+	MLX5_IFC_RTC_STE_FORMAT_11DW = 0x5,
+	MLX5_IFC_RTC_STE_FORMAT_RANGE = 0x7,
+};
+
+enum mlx5_ifc_rtc_reparse_mode {
+	MLX5_IFC_RTC_REPARSE_NEVER = 0x0,
+	MLX5_IFC_RTC_REPARSE_ALWAYS = 0x1,
+	MLX5_IFC_RTC_REPARSE_BY_STC = 0x2,
+};
+
+#define MLX5_IFC_RTC_LINEAR_LOOKUP_TBL_LOG_MAX 16
+
+struct mlx5_ifc_rtc_bits {
+	u8 modify_field_select[0x40];
+	u8 reserved_at_40[0x40];
+	u8 update_index_mode[0x2];
+	u8 reparse_mode[0x2];
+	u8 num_match_ste[0x4];
+	u8 pd[0x18];
+	u8 reserved_at_a0[0x9];
+	u8 access_index_mode[0x3];
+	u8 num_hash_definer[0x4];
+	u8 update_method[0x1];
+	u8 reserved_at_b1[0x2];
+	u8 log_depth[0x5];
+	u8 log_hash_size[0x8];
+	u8 ste_format_0[0x8];
+	u8 table_type[0x8];
+	u8 ste_format_1[0x8];
+	u8 reserved_at_d8[0x8];
+	u8 match_definer_0[0x20];
+	u8 stc_id[0x20];
+	u8 ste_table_base_id[0x20];
+	u8 ste_table_offset[0x20];
+	u8 reserved_at_160[0x8];
+	u8 miss_flow_table_id[0x18];
+	u8 match_definer_1[0x20];
+	u8 reserved_at_1a0[0x260];
+};
+
+enum mlx5_ifc_stc_action_type {
+	MLX5_IFC_STC_ACTION_TYPE_NOP = 0x00,
+	MLX5_IFC_STC_ACTION_TYPE_COPY = 0x05,
+	MLX5_IFC_STC_ACTION_TYPE_SET = 0x06,
+	MLX5_IFC_STC_ACTION_TYPE_ADD = 0x07,
+	MLX5_IFC_STC_ACTION_TYPE_REMOVE_WORDS = 0x08,
+	MLX5_IFC_STC_ACTION_TYPE_HEADER_REMOVE = 0x09,
+	MLX5_IFC_STC_ACTION_TYPE_HEADER_INSERT = 0x0b,
+	MLX5_IFC_STC_ACTION_TYPE_TAG = 0x0c,
+	MLX5_IFC_STC_ACTION_TYPE_ACC_MODIFY_LIST = 0x0e,
+	MLX5_IFC_STC_ACTION_TYPE_CRYPTO_IPSEC_ENCRYPTION = 0x10,
+	MLX5_IFC_STC_ACTION_TYPE_CRYPTO_IPSEC_DECRYPTION = 0x11,
+	MLX5_IFC_STC_ACTION_TYPE_ASO = 0x12,
+	MLX5_IFC_STC_ACTION_TYPE_TRAILER = 0x13,
+	MLX5_IFC_STC_ACTION_TYPE_COUNTER = 0x14,
+	MLX5_IFC_STC_ACTION_TYPE_ADD_FIELD = 0x1b,
+	MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_STE_TABLE = 0x80,
+	MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_TIR = 0x81,
+	MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT = 0x82,
+	MLX5_IFC_STC_ACTION_TYPE_DROP = 0x83,
+	MLX5_IFC_STC_ACTION_TYPE_ALLOW = 0x84,
+	MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_VPORT = 0x85,
+	MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_UPLINK = 0x86,
+};
+
+enum mlx5_ifc_stc_reparse_mode {
+	MLX5_IFC_STC_REPARSE_IGNORE = 0x0,
+	MLX5_IFC_STC_REPARSE_NEVER = 0x1,
+	MLX5_IFC_STC_REPARSE_ALWAYS = 0x2,
+};
+
+struct mlx5_ifc_stc_ste_param_ste_table_bits {
+	u8 ste_obj_id[0x20];
+	u8 match_definer_id[0x20];
+	u8 reserved_at_40[0x3];
+	u8 log_hash_size[0x5];
+	u8 reserved_at_48[0x38];
+};
+
+struct mlx5_ifc_stc_ste_param_tir_bits {
+	u8 reserved_at_0[0x8];
+	u8 tirn[0x18];
+	u8 reserved_at_20[0x60];
+};
+
+struct mlx5_ifc_stc_ste_param_table_bits {
+	u8 reserved_at_0[0x8];
+	u8 table_id[0x18];
+	u8 reserved_at_20[0x60];
+};
+
+struct mlx5_ifc_stc_ste_param_flow_counter_bits {
+	u8 flow_counter_id[0x20];
+};
+
+enum {
+	MLX5_ASO_CT_NUM_PER_OBJ = 1,
+	MLX5_ASO_METER_NUM_PER_OBJ = 2,
+	MLX5_ASO_IPSEC_NUM_PER_OBJ = 1,
+	MLX5_ASO_FIRST_HIT_NUM_PER_OBJ = 512,
+};
+
+struct mlx5_ifc_stc_ste_param_execute_aso_bits {
+	u8 aso_object_id[0x20];
+	u8 return_reg_id[0x4];
+	u8 aso_type[0x4];
+	u8 reserved_at_28[0x18];
+};
+
+struct mlx5_ifc_stc_ste_param_ipsec_encrypt_bits {
+	u8 ipsec_object_id[0x20];
+};
+
+struct mlx5_ifc_stc_ste_param_ipsec_decrypt_bits {
+	u8 ipsec_object_id[0x20];
+};
+
+struct mlx5_ifc_stc_ste_param_trailer_bits {
+	u8 reserved_at_0[0x8];
+	u8 command[0x4];
+	u8 reserved_at_c[0x2];
+	u8 type[0x2];
+	u8 reserved_at_10[0xa];
+	u8 length[0x6];
+};
+
+struct mlx5_ifc_stc_ste_param_header_modify_list_bits {
+	u8 header_modify_pattern_id[0x20];
+	u8 header_modify_argument_id[0x20];
+};
+
+enum mlx5_ifc_header_anchors {
+	MLX5_HEADER_ANCHOR_PACKET_START = 0x0,
+	MLX5_HEADER_ANCHOR_MAC = 0x1,
+	MLX5_HEADER_ANCHOR_FIRST_VLAN_START = 0x2,
+	MLX5_HEADER_ANCHOR_IPV6_IPV4 = 0x07,
+	MLX5_HEADER_ANCHOR_ESP = 0x08,
+	MLX5_HEADER_ANCHOR_TCP_UDP = 0x09,
+	MLX5_HEADER_ANCHOR_TUNNEL_HEADER = 0x0a,
+	MLX5_HEADER_ANCHOR_INNER_MAC = 0x13,
+	MLX5_HEADER_ANCHOR_INNER_IPV6_IPV4 = 0x19,
+	MLX5_HEADER_ANCHOR_INNER_TCP_UDP = 0x1a,
+	MLX5_HEADER_ANCHOR_L4_PAYLOAD = 0x1b,
+	MLX5_HEADER_ANCHOR_INNER_L4_PAYLOAD = 0x1c
+};
+
+struct mlx5_ifc_stc_ste_param_remove_bits {
+	u8 action_type[0x4];
+	u8 decap[0x1];
+	u8 reserved_at_5[0x5];
+	u8 remove_start_anchor[0x6];
+	u8 reserved_at_10[0x2];
+	u8 remove_end_anchor[0x6];
+	u8 reserved_at_18[0x8];
+};
+
+struct mlx5_ifc_stc_ste_param_remove_words_bits {
+	u8 action_type[0x4];
+	u8 reserved_at_4[0x6];
+	u8 remove_start_anchor[0x6];
+	u8 reserved_at_10[0x1];
+	u8 remove_offset[0x7];
+	u8 reserved_at_18[0x2];
+	u8 remove_size[0x6];
+};
+
+struct mlx5_ifc_stc_ste_param_insert_bits {
+	u8 action_type[0x4];
+	u8 encap[0x1];
+	u8 inline_data[0x1];
+	u8 reserved_at_6[0x4];
+	u8 insert_anchor[0x6];
+	u8 reserved_at_10[0x1];
+	u8 insert_offset[0x7];
+	u8 reserved_at_18[0x1];
+	u8 insert_size[0x7];
+	u8 insert_argument[0x20];
+};
+
+struct mlx5_ifc_stc_ste_param_vport_bits {
+	u8 eswitch_owner_vhca_id[0x10];
+	u8 vport_number[0x10];
+	u8 eswitch_owner_vhca_id_valid[0x1];
+	u8 reserved_at_21[0x5f];
+};
+
+union mlx5_ifc_stc_param_bits {
+	struct mlx5_ifc_stc_ste_param_ste_table_bits ste_table;
+	struct mlx5_ifc_stc_ste_param_tir_bits tir;
+	struct mlx5_ifc_stc_ste_param_table_bits table;
+	struct mlx5_ifc_stc_ste_param_flow_counter_bits counter;
+	struct mlx5_ifc_stc_ste_param_header_modify_list_bits modify_header;
+	struct mlx5_ifc_stc_ste_param_execute_aso_bits aso;
+	struct mlx5_ifc_stc_ste_param_remove_bits remove_header;
+	struct mlx5_ifc_stc_ste_param_insert_bits insert_header;
+	struct mlx5_ifc_set_action_in_bits add;
+	struct mlx5_ifc_set_action_in_bits set;
+	struct mlx5_ifc_copy_action_in_bits copy;
+	struct mlx5_ifc_stc_ste_param_vport_bits vport;
+	struct mlx5_ifc_stc_ste_param_ipsec_encrypt_bits ipsec_encrypt;
+	struct mlx5_ifc_stc_ste_param_ipsec_decrypt_bits ipsec_decrypt;
+	struct mlx5_ifc_stc_ste_param_trailer_bits trailer;
+	u8 reserved_at_0[0x80];
+};
+
+enum {
+	MLX5_IFC_MODIFY_STC_FIELD_SELECT_NEW_STC = BIT(0),
+};
+
+struct mlx5_ifc_stc_bits {
+	u8 modify_field_select[0x40];
+	u8 reserved_at_40[0x46];
+	u8 reparse_mode[0x2];
+	u8 table_type[0x8];
+	u8 ste_action_offset[0x8];
+	u8 action_type[0x8];
+	u8 reserved_at_a0[0x60];
+	union mlx5_ifc_stc_param_bits stc_param;
+	u8 reserved_at_180[0x280];
+};
+
+struct mlx5_ifc_ste_bits {
+	u8 modify_field_select[0x40];
+	u8 reserved_at_40[0x48];
+	u8 table_type[0x8];
+	u8 reserved_at_90[0x370];
+};
+
+struct mlx5_ifc_definer_bits {
+	u8 modify_field_select[0x40];
+	u8 reserved_at_40[0x50];
+	u8 format_id[0x10];
+	u8 reserved_at_60[0x60];
+	u8 format_select_dw3[0x8];
+	u8 format_select_dw2[0x8];
+	u8 format_select_dw1[0x8];
+	u8 format_select_dw0[0x8];
+	u8 format_select_dw7[0x8];
+	u8 format_select_dw6[0x8];
+	u8 format_select_dw5[0x8];
+	u8 format_select_dw4[0x8];
+	u8 reserved_at_100[0x18];
+	u8 format_select_dw8[0x8];
+	u8 reserved_at_120[0x20];
+	u8 format_select_byte3[0x8];
+	u8 format_select_byte2[0x8];
+	u8 format_select_byte1[0x8];
+	u8 format_select_byte0[0x8];
+	u8 format_select_byte7[0x8];
+	u8 format_select_byte6[0x8];
+	u8 format_select_byte5[0x8];
+	u8 format_select_byte4[0x8];
+	u8 reserved_at_180[0x40];
+	u8 ctrl[0xa0];
+	u8 match_mask[0x160];
+};
+
+struct mlx5_ifc_arg_bits {
+	u8 rsvd0[0x88];
+	u8 access_pd[0x18];
+};
+
+struct mlx5_ifc_header_modify_pattern_in_bits {
+	u8 modify_field_select[0x40];
+
+	u8 reserved_at_40[0x40];
+
+	u8 pattern_length[0x8];
+	u8 reserved_at_88[0x18];
+
+	u8 reserved_at_a0[0x60];
+
+	u8 pattern_data[MLX5_MAX_ACTIONS_DATA_IN_HEADER_MODIFY * 8];
+};
+
+struct mlx5_ifc_create_rtc_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_rtc_bits rtc;
+};
+
+struct mlx5_ifc_create_stc_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_stc_bits stc;
+};
+
+struct mlx5_ifc_create_ste_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_ste_bits ste;
+};
+
+struct mlx5_ifc_create_definer_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_definer_bits definer;
+};
+
+struct mlx5_ifc_create_arg_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_arg_bits arg;
+};
+
+struct mlx5_ifc_create_header_modify_pattern_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_header_modify_pattern_in_bits pattern;
+};
+
+struct mlx5_ifc_generate_wqe_in_bits {
+	u8 opcode[0x10];
+	u8 uid[0x10];
+	u8 reserved_at_20[0x10];
+	u8 op_mode[0x10];
+	u8 reserved_at_40[0x40];
+	u8 reserved_at_80[0x8];
+	u8 pdn[0x18];
+	u8 reserved_at_a0[0x160];
+	u8 wqe_ctrl[0x80];
+	u8 wqe_gta_ctrl[0x180];
+	u8 wqe_gta_data_0[0x200];
+	u8 wqe_gta_data_1[0x200];
+};
+
+struct mlx5_ifc_generate_wqe_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+	u8 syndrome[0x20];
+	u8 reserved_at_40[0x1c0];
+	u8 cqe_data[0x200];
+};
+
+enum mlx5_access_aso_opc_mod {
+	ASO_OPC_MOD_IPSEC = 0x0,
+	ASO_OPC_MOD_CONNECTION_TRACKING = 0x1,
+	ASO_OPC_MOD_POLICER = 0x2,
+	ASO_OPC_MOD_RACE_AVOIDANCE = 0x3,
+	ASO_OPC_MOD_FLOW_HIT = 0x4,
+};
+
+enum {
+	MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION = BIT(0),
+	MLX5_IFC_MODIFY_FLOW_TABLE_RTC_ID = BIT(1),
+};
+
+enum {
+	MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_DEFAULT = 0,
+	MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL = 1,
+};
+
+struct mlx5_ifc_alloc_packet_reformat_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+
+	u8 syndrome[0x20];
+
+	u8 packet_reformat_id[0x20];
+
+	u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_dealloc_packet_reformat_in_bits {
+	u8 opcode[0x10];
+	u8 reserved_at_10[0x10];
+
+	u8 reserved_at_20[0x10];
+	u8 op_mod[0x10];
+
+	u8 packet_reformat_id[0x20];
+
+	u8 reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_dealloc_packet_reformat_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+
+	u8 syndrome[0x20];
+
+	u8 reserved_at_40[0x40];
+};
+
+#endif /* MLX5_PRM_H_ */
-- 
cgit v1.3-3-g829e


From 2ca62599aa0bbc0e61595531614e0989ba6b3194 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:35:50 +0300
Subject: net/mlx5: HWS, added send engine and context handling

Added implementation of send engine and handling of HWS context.

Reviewed-by: Itamar Gozlan <igozlan@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../mlx5/core/steering/hws/mlx5hws_context.c       |  260 +++++
 .../mlx5/core/steering/hws/mlx5hws_context.h       |   64 ++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_send.c | 1209 ++++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/mlx5hws_send.h |  270 +++++
 4 files changed, 1803 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.c
new file mode 100644
index 000000000000..00e4fdf4a558
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA CORPORATION. All rights reserved. */
+
+#include "mlx5hws_internal.h"
+
+bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx)
+{
+	return IS_BIT_SET(ctx->caps->rtc_reparse_mode, MLX5_IFC_RTC_REPARSE_BY_STC);
+}
+
+u8 mlx5hws_context_get_reparse_mode(struct mlx5hws_context *ctx)
+{
+	/* Prefer to use dynamic reparse, reparse only specific actions */
+	if (mlx5hws_context_cap_dynamic_reparse(ctx))
+		return MLX5_IFC_RTC_REPARSE_NEVER;
+
+	/* Otherwise use less efficient static */
+	return MLX5_IFC_RTC_REPARSE_ALWAYS;
+}
+
+static int hws_context_pools_init(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_pool_attr pool_attr = {0};
+	u8 max_log_sz;
+	int ret;
+	int i;
+
+	ret = mlx5hws_pat_init_pattern_cache(&ctx->pattern_cache);
+	if (ret)
+		return ret;
+
+	ret = mlx5hws_definer_init_cache(&ctx->definer_cache);
+	if (ret)
+		goto uninit_pat_cache;
+
+	/* Create an STC pool per FT type */
+	pool_attr.pool_type = MLX5HWS_POOL_TYPE_STC;
+	pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STC_POOL;
+	max_log_sz = min(MLX5HWS_POOL_STC_LOG_SZ, ctx->caps->stc_alloc_log_max);
+	pool_attr.alloc_log_sz = max(max_log_sz, ctx->caps->stc_alloc_log_gran);
+
+	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
+		pool_attr.table_type = i;
+		ctx->stc_pool[i] = mlx5hws_pool_create(ctx, &pool_attr);
+		if (!ctx->stc_pool[i]) {
+			mlx5hws_err(ctx, "Failed to allocate STC pool [%d]", i);
+			ret = -ENOMEM;
+			goto free_stc_pools;
+		}
+	}
+
+	return 0;
+
+free_stc_pools:
+	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++)
+		if (ctx->stc_pool[i])
+			mlx5hws_pool_destroy(ctx->stc_pool[i]);
+
+	mlx5hws_definer_uninit_cache(ctx->definer_cache);
+uninit_pat_cache:
+	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
+	return ret;
+}
+
+static void hws_context_pools_uninit(struct mlx5hws_context *ctx)
+{
+	int i;
+
+	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
+		if (ctx->stc_pool[i])
+			mlx5hws_pool_destroy(ctx->stc_pool[i]);
+	}
+
+	mlx5hws_definer_uninit_cache(ctx->definer_cache);
+	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
+}
+
+static int hws_context_init_pd(struct mlx5hws_context *ctx)
+{
+	int ret = 0;
+
+	ret = mlx5_core_alloc_pd(ctx->mdev, &ctx->pd_num);
+	if (ret) {
+		mlx5hws_err(ctx, "Failed to allocate PD\n");
+		return ret;
+	}
+
+	ctx->flags |= MLX5HWS_CONTEXT_FLAG_PRIVATE_PD;
+
+	return 0;
+}
+
+static int hws_context_uninit_pd(struct mlx5hws_context *ctx)
+{
+	if (ctx->flags & MLX5HWS_CONTEXT_FLAG_PRIVATE_PD)
+		mlx5_core_dealloc_pd(ctx->mdev, ctx->pd_num);
+
+	return 0;
+}
+
+static void hws_context_check_hws_supp(struct mlx5hws_context *ctx)
+{
+	struct mlx5hws_cmd_query_caps *caps = ctx->caps;
+
+	/* HWS not supported on device / FW */
+	if (!caps->wqe_based_update) {
+		mlx5hws_err(ctx, "Required HWS WQE based insertion cap not supported\n");
+		return;
+	}
+
+	if (!caps->eswitch_manager) {
+		mlx5hws_err(ctx, "HWS is not supported for non eswitch manager port\n");
+		return;
+	}
+
+	/* Current solution requires all rules to set reparse bit */
+	if ((!caps->nic_ft.reparse ||
+	     (!caps->fdb_ft.reparse && caps->eswitch_manager)) ||
+	    !IS_BIT_SET(caps->rtc_reparse_mode, MLX5_IFC_RTC_REPARSE_ALWAYS)) {
+		mlx5hws_err(ctx, "Required HWS reparse cap not supported\n");
+		return;
+	}
+
+	/* FW/HW must support 8DW STE */
+	if (!IS_BIT_SET(caps->ste_format, MLX5_IFC_RTC_STE_FORMAT_8DW)) {
+		mlx5hws_err(ctx, "Required HWS STE format not supported\n");
+		return;
+	}
+
+	/* Adding rules by hash and by offset are requirements */
+	if (!IS_BIT_SET(caps->rtc_index_mode, MLX5_IFC_RTC_STE_UPDATE_MODE_BY_HASH) ||
+	    !IS_BIT_SET(caps->rtc_index_mode, MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET)) {
+		mlx5hws_err(ctx, "Required HWS RTC update mode not supported\n");
+		return;
+	}
+
+	/* Support for SELECT definer ID is required */
+	if (!IS_BIT_SET(caps->definer_format_sup, MLX5_IFC_DEFINER_FORMAT_ID_SELECT)) {
+		mlx5hws_err(ctx, "Required HWS Dynamic definer not supported\n");
+		return;
+	}
+
+	ctx->flags |= MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT;
+}
+
+static int hws_context_init_hws(struct mlx5hws_context *ctx,
+				struct mlx5hws_context_attr *attr)
+{
+	int ret;
+
+	hws_context_check_hws_supp(ctx);
+
+	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT))
+		return 0;
+
+	ret = hws_context_init_pd(ctx);
+	if (ret)
+		return ret;
+
+	ret = hws_context_pools_init(ctx);
+	if (ret)
+		goto uninit_pd;
+
+	if (attr->bwc)
+		ctx->flags |= MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
+
+	ret = mlx5hws_send_queues_open(ctx, attr->queues, attr->queue_size);
+	if (ret)
+		goto pools_uninit;
+
+	INIT_LIST_HEAD(&ctx->tbl_list);
+
+	return 0;
+
+pools_uninit:
+	hws_context_pools_uninit(ctx);
+uninit_pd:
+	hws_context_uninit_pd(ctx);
+	return ret;
+}
+
+static void hws_context_uninit_hws(struct mlx5hws_context *ctx)
+{
+	if (!(ctx->flags & MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT))
+		return;
+
+	mlx5hws_send_queues_close(ctx);
+	hws_context_pools_uninit(ctx);
+	hws_context_uninit_pd(ctx);
+}
+
+struct mlx5hws_context *mlx5hws_context_open(struct mlx5_core_dev *mdev,
+					     struct mlx5hws_context_attr *attr)
+{
+	struct mlx5hws_context *ctx;
+	int ret;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return NULL;
+
+	ctx->mdev = mdev;
+
+	mutex_init(&ctx->ctrl_lock);
+	xa_init(&ctx->peer_ctx_xa);
+
+	ctx->caps = kzalloc(sizeof(*ctx->caps), GFP_KERNEL);
+	if (!ctx->caps)
+		goto free_ctx;
+
+	ret = mlx5hws_cmd_query_caps(mdev, ctx->caps);
+	if (ret)
+		goto free_caps;
+
+	ret = mlx5hws_vport_init_vports(ctx);
+	if (ret)
+		goto free_caps;
+
+	ret = hws_context_init_hws(ctx, attr);
+	if (ret)
+		goto uninit_vports;
+
+	mlx5hws_debug_init_dump(ctx);
+
+	return ctx;
+
+uninit_vports:
+	mlx5hws_vport_uninit_vports(ctx);
+free_caps:
+	kfree(ctx->caps);
+free_ctx:
+	xa_destroy(&ctx->peer_ctx_xa);
+	mutex_destroy(&ctx->ctrl_lock);
+	kfree(ctx);
+	return NULL;
+}
+
+int mlx5hws_context_close(struct mlx5hws_context *ctx)
+{
+	mlx5hws_debug_uninit_dump(ctx);
+	hws_context_uninit_hws(ctx);
+	mlx5hws_vport_uninit_vports(ctx);
+	kfree(ctx->caps);
+	xa_destroy(&ctx->peer_ctx_xa);
+	mutex_destroy(&ctx->ctrl_lock);
+	kfree(ctx);
+	return 0;
+}
+
+void mlx5hws_context_set_peer(struct mlx5hws_context *ctx,
+			      struct mlx5hws_context *peer_ctx,
+			      u16 peer_vhca_id)
+{
+	mutex_lock(&ctx->ctrl_lock);
+
+	if (xa_err(xa_store(&ctx->peer_ctx_xa, peer_vhca_id, peer_ctx, GFP_KERNEL)))
+		pr_warn("HWS: failed storing peer vhca ID in peer xarray\n");
+
+	mutex_unlock(&ctx->ctrl_lock);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.h
new file mode 100644
index 000000000000..e5a7ce604334
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_context.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_CONTEXT_H_
+#define MLX5HWS_CONTEXT_H_
+
+enum mlx5hws_context_flags {
+	MLX5HWS_CONTEXT_FLAG_HWS_SUPPORT = 1 << 0,
+	MLX5HWS_CONTEXT_FLAG_PRIVATE_PD = 1 << 1,
+	MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT = 1 << 2,
+};
+
+enum mlx5hws_context_shared_stc_type {
+	MLX5HWS_CONTEXT_SHARED_STC_DECAP_L3 = 0,
+	MLX5HWS_CONTEXT_SHARED_STC_DOUBLE_POP = 1,
+	MLX5HWS_CONTEXT_SHARED_STC_MAX = 2,
+};
+
+struct mlx5hws_context_common_res {
+	struct mlx5hws_action_default_stc *default_stc;
+	struct mlx5hws_action_shared_stc *shared_stc[MLX5HWS_CONTEXT_SHARED_STC_MAX];
+	struct mlx5hws_cmd_forward_tbl *default_miss;
+};
+
+struct mlx5hws_context_debug_info {
+	struct dentry *steering_debugfs;
+	struct dentry *fdb_debugfs;
+};
+
+struct mlx5hws_context_vports {
+	u16 esw_manager_gvmi;
+	u16 uplink_gvmi;
+	struct xarray vport_gvmi_xa;
+};
+
+struct mlx5hws_context {
+	struct mlx5_core_dev *mdev;
+	struct mlx5hws_cmd_query_caps *caps;
+	u32 pd_num;
+	struct mlx5hws_pool *stc_pool[MLX5HWS_TABLE_TYPE_MAX];
+	struct mlx5hws_context_common_res common_res[MLX5HWS_TABLE_TYPE_MAX];
+	struct mlx5hws_pattern_cache *pattern_cache;
+	struct mlx5hws_definer_cache *definer_cache;
+	struct mutex ctrl_lock; /* control lock to protect the whole context */
+	enum mlx5hws_context_flags flags;
+	struct mlx5hws_send_engine *send_queue;
+	size_t queues;
+	struct mutex *bwc_send_queue_locks; /* protect BWC queues */
+	struct list_head tbl_list;
+	struct mlx5hws_context_debug_info debug_info;
+	struct xarray peer_ctx_xa;
+	struct mlx5hws_context_vports vports;
+};
+
+static inline bool mlx5hws_context_bwc_supported(struct mlx5hws_context *ctx)
+{
+	return ctx->flags & MLX5HWS_CONTEXT_FLAG_BWC_SUPPORT;
+}
+
+bool mlx5hws_context_cap_dynamic_reparse(struct mlx5hws_context *ctx);
+
+u8 mlx5hws_context_get_reparse_mode(struct mlx5hws_context *ctx);
+
+#endif /* MLX5HWS_CONTEXT_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c
new file mode 100644
index 000000000000..fb97a15c041a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c
@@ -0,0 +1,1209 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#include "mlx5hws_internal.h"
+#include "lib/clock.h"
+
+enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 };
+
+struct mlx5hws_send_ring_dep_wqe *
+mlx5hws_send_add_new_dep_wqe(struct mlx5hws_send_engine *queue)
+{
+	struct mlx5hws_send_ring_sq *send_sq = &queue->send_ring.send_sq;
+	unsigned int idx = send_sq->head_dep_idx++ & (queue->num_entries - 1);
+
+	memset(&send_sq->dep_wqe[idx].wqe_data.tag, 0, MLX5HWS_MATCH_TAG_SZ);
+
+	return &send_sq->dep_wqe[idx];
+}
+
+void mlx5hws_send_abort_new_dep_wqe(struct mlx5hws_send_engine *queue)
+{
+	queue->send_ring.send_sq.head_dep_idx--;
+}
+
+void mlx5hws_send_all_dep_wqe(struct mlx5hws_send_engine *queue)
+{
+	struct mlx5hws_send_ring_sq *send_sq = &queue->send_ring.send_sq;
+	struct mlx5hws_send_ste_attr ste_attr = {0};
+	struct mlx5hws_send_ring_dep_wqe *dep_wqe;
+
+	ste_attr.send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	ste_attr.send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	ste_attr.send_attr.len = MLX5HWS_WQE_SZ_GTA_CTRL + MLX5HWS_WQE_SZ_GTA_DATA;
+	ste_attr.gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE;
+
+	/* Fence first from previous depend WQEs  */
+	ste_attr.send_attr.fence = 1;
+
+	while (send_sq->head_dep_idx != send_sq->tail_dep_idx) {
+		dep_wqe = &send_sq->dep_wqe[send_sq->tail_dep_idx++ & (queue->num_entries - 1)];
+
+		/* Notify HW on the last WQE */
+		ste_attr.send_attr.notify_hw = (send_sq->tail_dep_idx == send_sq->head_dep_idx);
+		ste_attr.send_attr.user_data = dep_wqe->user_data;
+		ste_attr.send_attr.rule = dep_wqe->rule;
+
+		ste_attr.rtc_0 = dep_wqe->rtc_0;
+		ste_attr.rtc_1 = dep_wqe->rtc_1;
+		ste_attr.retry_rtc_0 = dep_wqe->retry_rtc_0;
+		ste_attr.retry_rtc_1 = dep_wqe->retry_rtc_1;
+		ste_attr.used_id_rtc_0 = &dep_wqe->rule->rtc_0;
+		ste_attr.used_id_rtc_1 = &dep_wqe->rule->rtc_1;
+		ste_attr.wqe_ctrl = &dep_wqe->wqe_ctrl;
+		ste_attr.wqe_data = &dep_wqe->wqe_data;
+		ste_attr.direct_index = dep_wqe->direct_index;
+
+		mlx5hws_send_ste(queue, &ste_attr);
+
+		/* Fencing is done only on the first WQE */
+		ste_attr.send_attr.fence = 0;
+	}
+}
+
+struct mlx5hws_send_engine_post_ctrl
+mlx5hws_send_engine_post_start(struct mlx5hws_send_engine *queue)
+{
+	struct mlx5hws_send_engine_post_ctrl ctrl;
+
+	ctrl.queue = queue;
+	/* Currently only one send ring is supported */
+	ctrl.send_ring = &queue->send_ring;
+	ctrl.num_wqebbs = 0;
+
+	return ctrl;
+}
+
+void mlx5hws_send_engine_post_req_wqe(struct mlx5hws_send_engine_post_ctrl *ctrl,
+				      char **buf, size_t *len)
+{
+	struct mlx5hws_send_ring_sq *send_sq = &ctrl->send_ring->send_sq;
+	unsigned int idx;
+
+	idx = (send_sq->cur_post + ctrl->num_wqebbs) & send_sq->buf_mask;
+
+	/* Note that *buf is a single MLX5_SEND_WQE_BB. It cannot be used
+	 * as buffer of more than one WQE_BB, since the two MLX5_SEND_WQE_BB
+	 * can be on 2 different kernel memory pages.
+	 */
+	*buf = mlx5_wq_cyc_get_wqe(&send_sq->wq, idx);
+	*len = MLX5_SEND_WQE_BB;
+
+	if (!ctrl->num_wqebbs) {
+		*buf += sizeof(struct mlx5hws_wqe_ctrl_seg);
+		*len -= sizeof(struct mlx5hws_wqe_ctrl_seg);
+	}
+
+	ctrl->num_wqebbs++;
+}
+
+static void hws_send_engine_post_ring(struct mlx5hws_send_ring_sq *sq,
+				      struct mlx5hws_wqe_ctrl_seg *doorbell_cseg)
+{
+	/* ensure wqe is visible to device before updating doorbell record */
+	dma_wmb();
+
+	*sq->wq.db = cpu_to_be32(sq->cur_post);
+
+	/* ensure doorbell record is visible to device before ringing the
+	 * doorbell
+	 */
+	wmb();
+
+	mlx5_write64((__be32 *)doorbell_cseg, sq->uar_map);
+
+	/* Ensure doorbell is written on uar_page before poll_cq */
+	WRITE_ONCE(doorbell_cseg, NULL);
+}
+
+static void
+hws_send_wqe_set_tag(struct mlx5hws_wqe_gta_data_seg_ste *wqe_data,
+		     struct mlx5hws_rule_match_tag *tag,
+		     bool is_jumbo)
+{
+	if (is_jumbo) {
+		/* Clear previous possibly dirty control */
+		memset(wqe_data, 0, MLX5HWS_STE_CTRL_SZ);
+		memcpy(wqe_data->jumbo, tag->jumbo, MLX5HWS_JUMBO_TAG_SZ);
+	} else {
+		/* Clear previous possibly dirty control and actions */
+		memset(wqe_data, 0, MLX5HWS_STE_CTRL_SZ + MLX5HWS_ACTIONS_SZ);
+		memcpy(wqe_data->tag, tag->match, MLX5HWS_MATCH_TAG_SZ);
+	}
+}
+
+void mlx5hws_send_engine_post_end(struct mlx5hws_send_engine_post_ctrl *ctrl,
+				  struct mlx5hws_send_engine_post_attr *attr)
+{
+	struct mlx5hws_wqe_ctrl_seg *wqe_ctrl;
+	struct mlx5hws_send_ring_sq *sq;
+	unsigned int idx;
+	u32 flags = 0;
+
+	sq = &ctrl->send_ring->send_sq;
+	idx = sq->cur_post & sq->buf_mask;
+	sq->last_idx = idx;
+
+	wqe_ctrl = mlx5_wq_cyc_get_wqe(&sq->wq, idx);
+
+	wqe_ctrl->opmod_idx_opcode =
+		cpu_to_be32((attr->opmod << 24) |
+			    ((sq->cur_post & 0xffff) << 8) |
+			    attr->opcode);
+	wqe_ctrl->qpn_ds =
+		cpu_to_be32((attr->len + sizeof(struct mlx5hws_wqe_ctrl_seg)) / 16 |
+				 sq->sqn << 8);
+	wqe_ctrl->imm = cpu_to_be32(attr->id);
+
+	flags |= attr->notify_hw ? MLX5_WQE_CTRL_CQ_UPDATE : 0;
+	flags |= attr->fence ? MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE : 0;
+	wqe_ctrl->flags = cpu_to_be32(flags);
+
+	sq->wr_priv[idx].id = attr->id;
+	sq->wr_priv[idx].retry_id = attr->retry_id;
+
+	sq->wr_priv[idx].rule = attr->rule;
+	sq->wr_priv[idx].user_data = attr->user_data;
+	sq->wr_priv[idx].num_wqebbs = ctrl->num_wqebbs;
+
+	if (attr->rule) {
+		sq->wr_priv[idx].rule->pending_wqes++;
+		sq->wr_priv[idx].used_id = attr->used_id;
+	}
+
+	sq->cur_post += ctrl->num_wqebbs;
+
+	if (attr->notify_hw)
+		hws_send_engine_post_ring(sq, wqe_ctrl);
+}
+
+static void hws_send_wqe(struct mlx5hws_send_engine *queue,
+			 struct mlx5hws_send_engine_post_attr *send_attr,
+			 struct mlx5hws_wqe_gta_ctrl_seg *send_wqe_ctrl,
+			 void *send_wqe_data,
+			 void *send_wqe_tag,
+			 bool is_jumbo,
+			 u8 gta_opcode,
+			 u32 direct_index)
+{
+	struct mlx5hws_wqe_gta_data_seg_ste *wqe_data;
+	struct mlx5hws_wqe_gta_ctrl_seg *wqe_ctrl;
+	struct mlx5hws_send_engine_post_ctrl ctrl;
+	size_t wqe_len;
+
+	ctrl = mlx5hws_send_engine_post_start(queue);
+	mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
+	mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_data, &wqe_len);
+
+	wqe_ctrl->op_dirix = cpu_to_be32(gta_opcode << 28 | direct_index);
+	memcpy(wqe_ctrl->stc_ix, send_wqe_ctrl->stc_ix,
+	       sizeof(send_wqe_ctrl->stc_ix));
+
+	if (send_wqe_data)
+		memcpy(wqe_data, send_wqe_data, sizeof(*wqe_data));
+	else
+		hws_send_wqe_set_tag(wqe_data, send_wqe_tag, is_jumbo);
+
+	mlx5hws_send_engine_post_end(&ctrl, send_attr);
+}
+
+void mlx5hws_send_ste(struct mlx5hws_send_engine *queue,
+		      struct mlx5hws_send_ste_attr *ste_attr)
+{
+	struct mlx5hws_send_engine_post_attr *send_attr = &ste_attr->send_attr;
+	u8 notify_hw = send_attr->notify_hw;
+	u8 fence = send_attr->fence;
+
+	if (ste_attr->rtc_1) {
+		send_attr->id = ste_attr->rtc_1;
+		send_attr->used_id = ste_attr->used_id_rtc_1;
+		send_attr->retry_id = ste_attr->retry_rtc_1;
+		send_attr->fence = fence;
+		send_attr->notify_hw = notify_hw && !ste_attr->rtc_0;
+		hws_send_wqe(queue, send_attr,
+			     ste_attr->wqe_ctrl,
+			     ste_attr->wqe_data,
+			     ste_attr->wqe_tag,
+			     ste_attr->wqe_tag_is_jumbo,
+			     ste_attr->gta_opcode,
+			     ste_attr->direct_index);
+	}
+
+	if (ste_attr->rtc_0) {
+		send_attr->id = ste_attr->rtc_0;
+		send_attr->used_id = ste_attr->used_id_rtc_0;
+		send_attr->retry_id = ste_attr->retry_rtc_0;
+		send_attr->fence = fence && !ste_attr->rtc_1;
+		send_attr->notify_hw = notify_hw;
+		hws_send_wqe(queue, send_attr,
+			     ste_attr->wqe_ctrl,
+			     ste_attr->wqe_data,
+			     ste_attr->wqe_tag,
+			     ste_attr->wqe_tag_is_jumbo,
+			     ste_attr->gta_opcode,
+			     ste_attr->direct_index);
+	}
+
+	/* Restore to original requested values */
+	send_attr->notify_hw = notify_hw;
+	send_attr->fence = fence;
+}
+
+static void hws_send_engine_retry_post_send(struct mlx5hws_send_engine *queue,
+					    struct mlx5hws_send_ring_priv *priv,
+					    u16 wqe_cnt)
+{
+	struct mlx5hws_send_engine_post_attr send_attr = {0};
+	struct mlx5hws_wqe_gta_data_seg_ste *wqe_data;
+	struct mlx5hws_wqe_gta_ctrl_seg *wqe_ctrl;
+	struct mlx5hws_send_engine_post_ctrl ctrl;
+	struct mlx5hws_send_ring_sq *send_sq;
+	unsigned int idx;
+	size_t wqe_len;
+	char *p;
+
+	send_attr.rule = priv->rule;
+	send_attr.opcode = MLX5HWS_WQE_OPCODE_TBL_ACCESS;
+	send_attr.opmod = MLX5HWS_WQE_GTA_OPMOD_STE;
+	send_attr.len = MLX5_SEND_WQE_BB * 2 - sizeof(struct mlx5hws_wqe_ctrl_seg);
+	send_attr.notify_hw = 1;
+	send_attr.fence = 0;
+	send_attr.user_data = priv->user_data;
+	send_attr.id = priv->retry_id;
+	send_attr.used_id = priv->used_id;
+
+	ctrl = mlx5hws_send_engine_post_start(queue);
+	mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
+	mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_data, &wqe_len);
+
+	send_sq = &ctrl.send_ring->send_sq;
+	idx = wqe_cnt & send_sq->buf_mask;
+	p = mlx5_wq_cyc_get_wqe(&send_sq->wq, idx);
+
+	/* Copy old gta ctrl */
+	memcpy(wqe_ctrl, p + sizeof(struct mlx5hws_wqe_ctrl_seg),
+	       MLX5_SEND_WQE_BB - sizeof(struct mlx5hws_wqe_ctrl_seg));
+
+	idx = (wqe_cnt + 1) & send_sq->buf_mask;
+	p = mlx5_wq_cyc_get_wqe(&send_sq->wq, idx);
+
+	/* Copy old gta data */
+	memcpy(wqe_data, p, MLX5_SEND_WQE_BB);
+
+	mlx5hws_send_engine_post_end(&ctrl, &send_attr);
+}
+
+void mlx5hws_send_engine_flush_queue(struct mlx5hws_send_engine *queue)
+{
+	struct mlx5hws_send_ring_sq *sq = &queue->send_ring.send_sq;
+	struct mlx5hws_wqe_ctrl_seg *wqe_ctrl;
+
+	wqe_ctrl = mlx5_wq_cyc_get_wqe(&sq->wq, sq->last_idx);
+	wqe_ctrl->flags |= cpu_to_be32(MLX5_WQE_CTRL_CQ_UPDATE);
+
+	hws_send_engine_post_ring(sq, wqe_ctrl);
+}
+
+static void
+hws_send_engine_update_rule_resize(struct mlx5hws_send_engine *queue,
+				   struct mlx5hws_send_ring_priv *priv,
+				   enum mlx5hws_flow_op_status *status)
+{
+	switch (priv->rule->resize_info->state) {
+	case MLX5HWS_RULE_RESIZE_STATE_WRITING:
+		if (priv->rule->status == MLX5HWS_RULE_STATUS_FAILING) {
+			/* Backup original RTCs */
+			u32 orig_rtc_0 = priv->rule->resize_info->rtc_0;
+			u32 orig_rtc_1 = priv->rule->resize_info->rtc_1;
+
+			/* Delete partially failed move rule using resize_info */
+			priv->rule->resize_info->rtc_0 = priv->rule->rtc_0;
+			priv->rule->resize_info->rtc_1 = priv->rule->rtc_1;
+
+			/* Move rule to original RTC for future delete */
+			priv->rule->rtc_0 = orig_rtc_0;
+			priv->rule->rtc_1 = orig_rtc_1;
+		}
+		/* Clean leftovers */
+		mlx5hws_rule_move_hws_remove(priv->rule, queue, priv->user_data);
+		break;
+
+	case MLX5HWS_RULE_RESIZE_STATE_DELETING:
+		if (priv->rule->status == MLX5HWS_RULE_STATUS_FAILING) {
+			*status = MLX5HWS_FLOW_OP_ERROR;
+		} else {
+			*status = MLX5HWS_FLOW_OP_SUCCESS;
+			priv->rule->matcher = priv->rule->matcher->resize_dst;
+		}
+		priv->rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_IDLE;
+		priv->rule->status = MLX5HWS_RULE_STATUS_CREATED;
+		break;
+
+	default:
+		break;
+	}
+}
+
+static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue,
+					struct mlx5hws_send_ring_priv *priv,
+					u16 wqe_cnt,
+					enum mlx5hws_flow_op_status *status)
+{
+	priv->rule->pending_wqes--;
+
+	if (*status == MLX5HWS_FLOW_OP_ERROR) {
+		if (priv->retry_id) {
+			hws_send_engine_retry_post_send(queue, priv, wqe_cnt);
+			return;
+		}
+		/* Some part of the rule failed */
+		priv->rule->status = MLX5HWS_RULE_STATUS_FAILING;
+		*priv->used_id = 0;
+	} else {
+		*priv->used_id = priv->id;
+	}
+
+	/* Update rule status for the last completion */
+	if (!priv->rule->pending_wqes) {
+		if (unlikely(mlx5hws_rule_move_in_progress(priv->rule))) {
+			hws_send_engine_update_rule_resize(queue, priv, status);
+			return;
+		}
+
+		if (unlikely(priv->rule->status == MLX5HWS_RULE_STATUS_FAILING)) {
+			/* Rule completely failed and doesn't require cleanup */
+			if (!priv->rule->rtc_0 && !priv->rule->rtc_1)
+				priv->rule->status = MLX5HWS_RULE_STATUS_FAILED;
+
+			*status = MLX5HWS_FLOW_OP_ERROR;
+		} else {
+			/* Increase the status, this only works on good flow as the enum
+			 * is arrange it away creating -> created -> deleting -> deleted
+			 */
+			priv->rule->status++;
+			*status = MLX5HWS_FLOW_OP_SUCCESS;
+			/* Rule was deleted now we can safely release action STEs
+			 * and clear resize info
+			 */
+			if (priv->rule->status == MLX5HWS_RULE_STATUS_DELETED) {
+				mlx5hws_rule_free_action_ste(priv->rule);
+				mlx5hws_rule_clear_resize_info(priv->rule);
+			}
+		}
+	}
+}
+
+static void hws_send_engine_update(struct mlx5hws_send_engine *queue,
+				   struct mlx5_cqe64 *cqe,
+				   struct mlx5hws_send_ring_priv *priv,
+				   struct mlx5hws_flow_op_result res[],
+				   s64 *i,
+				   u32 res_nb,
+				   u16 wqe_cnt)
+{
+	enum mlx5hws_flow_op_status status;
+
+	if (!cqe || (likely(be32_to_cpu(cqe->byte_cnt) >> 31 == 0) &&
+		     likely(get_cqe_opcode(cqe) == MLX5_CQE_REQ))) {
+		status = MLX5HWS_FLOW_OP_SUCCESS;
+	} else {
+		status = MLX5HWS_FLOW_OP_ERROR;
+	}
+
+	if (priv->user_data) {
+		if (priv->rule) {
+			hws_send_engine_update_rule(queue, priv, wqe_cnt, &status);
+			/* Completion is provided on the last rule WQE */
+			if (priv->rule->pending_wqes)
+				return;
+		}
+
+		if (*i < res_nb) {
+			res[*i].user_data = priv->user_data;
+			res[*i].status = status;
+			(*i)++;
+			mlx5hws_send_engine_dec_rule(queue);
+		} else {
+			mlx5hws_send_engine_gen_comp(queue, priv->user_data, status);
+		}
+	}
+}
+
+static int mlx5hws_parse_cqe(struct mlx5hws_send_ring_cq *cq,
+			     struct mlx5_cqe64 *cqe64)
+{
+	if (unlikely(get_cqe_opcode(cqe64) != MLX5_CQE_REQ)) {
+		struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe64;
+
+		mlx5_core_err(cq->mdev, "Bad OP in HWS SQ CQE: 0x%x\n", get_cqe_opcode(cqe64));
+		mlx5_core_err(cq->mdev, "vendor_err_synd=%x\n", err_cqe->vendor_err_synd);
+		mlx5_core_err(cq->mdev, "syndrome=%x\n", err_cqe->syndrome);
+		print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET,
+			       16, 1, err_cqe,
+			       sizeof(*err_cqe), false);
+		return CQ_POLL_ERR;
+	}
+
+	return CQ_OK;
+}
+
+static int mlx5hws_cq_poll_one(struct mlx5hws_send_ring_cq *cq)
+{
+	struct mlx5_cqe64 *cqe64;
+	int err;
+
+	cqe64 = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe64) {
+		if (unlikely(cq->mdev->state ==
+			     MLX5_DEVICE_STATE_INTERNAL_ERROR)) {
+			mlx5_core_dbg_once(cq->mdev,
+					   "Polling CQ while device is shutting down\n");
+			return CQ_POLL_ERR;
+		}
+		return CQ_EMPTY;
+	}
+
+	mlx5_cqwq_pop(&cq->wq);
+	err = mlx5hws_parse_cqe(cq, cqe64);
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	return err;
+}
+
+static void hws_send_engine_poll_cq(struct mlx5hws_send_engine *queue,
+				    struct mlx5hws_flow_op_result res[],
+				    s64 *polled,
+				    u32 res_nb)
+{
+	struct mlx5hws_send_ring *send_ring = &queue->send_ring;
+	struct mlx5hws_send_ring_cq *cq = &send_ring->send_cq;
+	struct mlx5hws_send_ring_sq *sq = &send_ring->send_sq;
+	struct mlx5hws_send_ring_priv *priv;
+	struct mlx5_cqe64 *cqe;
+	u8 cqe_opcode;
+	u16 wqe_cnt;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
+		return;
+
+	cqe_opcode = get_cqe_opcode(cqe);
+	if (cqe_opcode == MLX5_CQE_INVALID)
+		return;
+
+	if (unlikely(cqe_opcode != MLX5_CQE_REQ))
+		queue->err = true;
+
+	wqe_cnt = be16_to_cpu(cqe->wqe_counter) & sq->buf_mask;
+
+	while (cq->poll_wqe != wqe_cnt) {
+		priv = &sq->wr_priv[cq->poll_wqe];
+		hws_send_engine_update(queue, NULL, priv, res, polled, res_nb, 0);
+		cq->poll_wqe = (cq->poll_wqe + priv->num_wqebbs) & sq->buf_mask;
+	}
+
+	priv = &sq->wr_priv[wqe_cnt];
+	cq->poll_wqe = (wqe_cnt + priv->num_wqebbs) & sq->buf_mask;
+	hws_send_engine_update(queue, cqe, priv, res, polled, res_nb, wqe_cnt);
+	mlx5hws_cq_poll_one(cq);
+}
+
+static void hws_send_engine_poll_list(struct mlx5hws_send_engine *queue,
+				      struct mlx5hws_flow_op_result res[],
+				      s64 *polled,
+				      u32 res_nb)
+{
+	struct mlx5hws_completed_poll *comp = &queue->completed;
+
+	while (comp->ci != comp->pi) {
+		if (*polled < res_nb) {
+			res[*polled].status =
+				comp->entries[comp->ci].status;
+			res[*polled].user_data =
+				comp->entries[comp->ci].user_data;
+			(*polled)++;
+			comp->ci = (comp->ci + 1) & comp->mask;
+			mlx5hws_send_engine_dec_rule(queue);
+		} else {
+			return;
+		}
+	}
+}
+
+static int hws_send_engine_poll(struct mlx5hws_send_engine *queue,
+				struct mlx5hws_flow_op_result res[],
+				u32 res_nb)
+{
+	s64 polled = 0;
+
+	hws_send_engine_poll_list(queue, res, &polled, res_nb);
+
+	if (polled >= res_nb)
+		return polled;
+
+	hws_send_engine_poll_cq(queue, res, &polled, res_nb);
+
+	return polled;
+}
+
+int mlx5hws_send_queue_poll(struct mlx5hws_context *ctx,
+			    u16 queue_id,
+			    struct mlx5hws_flow_op_result res[],
+			    u32 res_nb)
+{
+	return hws_send_engine_poll(&ctx->send_queue[queue_id], res, res_nb);
+}
+
+static int hws_send_ring_alloc_sq(struct mlx5_core_dev *mdev,
+				  int numa_node,
+				  struct mlx5hws_send_engine *queue,
+				  struct mlx5hws_send_ring_sq *sq,
+				  void *sqc_data)
+{
+	void *sqc_wq = MLX5_ADDR_OF(sqc, sqc_data, wq);
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct mlx5_wq_param param;
+	size_t buf_sz;
+	int err;
+
+	sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map;
+	sq->mdev = mdev;
+
+	param.db_numa_node = numa_node;
+	param.buf_numa_node = numa_node;
+	err = mlx5_wq_cyc_create(mdev, &param, sqc_wq, wq, &sq->wq_ctrl);
+	if (err)
+		return err;
+	wq->db = &wq->db[MLX5_SND_DBR];
+
+	buf_sz = queue->num_entries * MAX_WQES_PER_RULE;
+	sq->dep_wqe = kcalloc(queue->num_entries, sizeof(*sq->dep_wqe), GFP_KERNEL);
+	if (!sq->dep_wqe) {
+		err = -ENOMEM;
+		goto destroy_wq_cyc;
+	}
+
+	sq->wr_priv = kzalloc(sizeof(*sq->wr_priv) * buf_sz, GFP_KERNEL);
+	if (!sq->dep_wqe) {
+		err = -ENOMEM;
+		goto free_dep_wqe;
+	}
+
+	sq->buf_mask = (queue->num_entries * MAX_WQES_PER_RULE) - 1;
+
+	return 0;
+
+free_dep_wqe:
+	kfree(sq->dep_wqe);
+destroy_wq_cyc:
+	mlx5_wq_destroy(&sq->wq_ctrl);
+	return err;
+}
+
+static void hws_send_ring_free_sq(struct mlx5hws_send_ring_sq *sq)
+{
+	if (!sq)
+		return;
+	kfree(sq->wr_priv);
+	kfree(sq->dep_wqe);
+	mlx5_wq_destroy(&sq->wq_ctrl);
+}
+
+static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn,
+				   void *sqc_data,
+				   struct mlx5hws_send_engine *queue,
+				   struct mlx5hws_send_ring_sq *sq,
+				   struct mlx5hws_send_ring_cq *cq)
+{
+	void *in, *sqc, *wq;
+	int inlen, err;
+	u8 ts_format;
+
+	inlen = MLX5_ST_SZ_BYTES(create_sq_in) +
+		sizeof(u64) * sq->wq_ctrl.buf.npages;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	sqc = MLX5_ADDR_OF(create_sq_in, in, ctx);
+	wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+	memcpy(sqc, sqc_data, MLX5_ST_SZ_BYTES(sqc));
+	MLX5_SET(sqc, sqc, cqn, cq->mcq.cqn);
+
+	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
+	MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+
+	ts_format = mlx5_is_real_time_sq(mdev) ? MLX5_TIMESTAMP_FORMAT_REAL_TIME :
+						 MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
+	MLX5_SET(sqc, sqc, ts_format, ts_format);
+
+	MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
+	MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index);
+	MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET64(wq, wq, dbr_addr, sq->wq_ctrl.db.dma);
+
+	mlx5_fill_page_frag_array(&sq->wq_ctrl.buf,
+				  (__be64 *)MLX5_ADDR_OF(wq, wq, pas));
+
+	err = mlx5_core_create_sq(mdev, in, inlen, &sq->sqn);
+
+	kvfree(in);
+
+	return err;
+}
+
+static int hws_send_ring_set_sq_rdy(struct mlx5_core_dev *mdev, u32 sqn)
+{
+	void *in, *sqc;
+	int inlen, err;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_sq_in);
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_sq_in, in, sq_state, MLX5_SQC_STATE_RST);
+	sqc = MLX5_ADDR_OF(modify_sq_in, in, ctx);
+	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RDY);
+
+	err = mlx5_core_modify_sq(mdev, sqn, in);
+
+	kvfree(in);
+
+	return err;
+}
+
+static void hws_send_ring_close_sq(struct mlx5hws_send_ring_sq *sq)
+{
+	mlx5_core_destroy_sq(sq->mdev, sq->sqn);
+	mlx5_wq_destroy(&sq->wq_ctrl);
+	kfree(sq->wr_priv);
+	kfree(sq->dep_wqe);
+}
+
+static int hws_send_ring_create_sq_rdy(struct mlx5_core_dev *mdev, u32 pdn,
+				       void *sqc_data,
+				       struct mlx5hws_send_engine *queue,
+				       struct mlx5hws_send_ring_sq *sq,
+				       struct mlx5hws_send_ring_cq *cq)
+{
+	int err;
+
+	err = hws_send_ring_create_sq(mdev, pdn, sqc_data, queue, sq, cq);
+	if (err)
+		return err;
+
+	err = hws_send_ring_set_sq_rdy(mdev, sq->sqn);
+	if (err)
+		hws_send_ring_close_sq(sq);
+
+	return err;
+}
+
+static int hws_send_ring_open_sq(struct mlx5hws_context *ctx,
+				 int numa_node,
+				 struct mlx5hws_send_engine *queue,
+				 struct mlx5hws_send_ring_sq *sq,
+				 struct mlx5hws_send_ring_cq *cq)
+{
+	size_t buf_sz, sq_log_buf_sz;
+	void *sqc_data, *wq;
+	int err;
+
+	sqc_data = kvzalloc(MLX5_ST_SZ_BYTES(sqc), GFP_KERNEL);
+	if (!sqc_data)
+		return -ENOMEM;
+
+	buf_sz = queue->num_entries * MAX_WQES_PER_RULE;
+	sq_log_buf_sz = ilog2(roundup_pow_of_two(buf_sz));
+
+	wq = MLX5_ADDR_OF(sqc, sqc_data, wq);
+	MLX5_SET(wq, wq, log_wq_stride, ilog2(MLX5_SEND_WQE_BB));
+	MLX5_SET(wq, wq, pd, ctx->pd_num);
+	MLX5_SET(wq, wq, log_wq_sz, sq_log_buf_sz);
+
+	err = hws_send_ring_alloc_sq(ctx->mdev, numa_node, queue, sq, sqc_data);
+	if (err)
+		goto err_free_sqc;
+
+	err = hws_send_ring_create_sq_rdy(ctx->mdev, ctx->pd_num, sqc_data,
+					  queue, sq, cq);
+	if (err)
+		goto err_free_sq;
+
+	kvfree(sqc_data);
+
+	return 0;
+err_free_sq:
+	hws_send_ring_free_sq(sq);
+err_free_sqc:
+	kvfree(sqc_data);
+	return err;
+}
+
+static void hws_cq_complete(struct mlx5_core_cq *mcq,
+			    struct mlx5_eqe *eqe)
+{
+	pr_err("CQ completion CQ: #%u\n", mcq->cqn);
+}
+
+static int hws_send_ring_alloc_cq(struct mlx5_core_dev *mdev,
+				  int numa_node,
+				  struct mlx5hws_send_engine *queue,
+				  void *cqc_data,
+				  struct mlx5hws_send_ring_cq *cq)
+{
+	struct mlx5_core_cq *mcq = &cq->mcq;
+	struct mlx5_wq_param param;
+	struct mlx5_cqe64 *cqe;
+	int err;
+	u32 i;
+
+	param.buf_numa_node = numa_node;
+	param.db_numa_node = numa_node;
+
+	err = mlx5_cqwq_create(mdev, &param, cqc_data, &cq->wq, &cq->wq_ctrl);
+	if (err)
+		return err;
+
+	mcq->cqe_sz = 64;
+	mcq->set_ci_db = cq->wq_ctrl.db.db;
+	mcq->arm_db = cq->wq_ctrl.db.db + 1;
+	mcq->comp = hws_cq_complete;
+
+	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
+		cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
+		cqe->op_own = 0xf1;
+	}
+
+	cq->mdev = mdev;
+
+	return 0;
+}
+
+static int hws_send_ring_create_cq(struct mlx5_core_dev *mdev,
+				   struct mlx5hws_send_engine *queue,
+				   void *cqc_data,
+				   struct mlx5hws_send_ring_cq *cq)
+{
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
+	struct mlx5_core_cq *mcq = &cq->mcq;
+	void *in, *cqc;
+	int inlen, eqn;
+	int err;
+
+	err = mlx5_comp_eqn_get(mdev, 0, &eqn);
+	if (err)
+		return err;
+
+	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
+		sizeof(u64) * cq->wq_ctrl.buf.npages;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+	memcpy(cqc, cqc_data, MLX5_ST_SZ_BYTES(cqc));
+	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf,
+				  (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));
+
+	MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn);
+	MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index);
+	MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);
+
+	err = mlx5_core_create_cq(mdev, mcq, in, inlen, out, sizeof(out));
+
+	kvfree(in);
+
+	return err;
+}
+
+static int hws_send_ring_open_cq(struct mlx5_core_dev *mdev,
+				 struct mlx5hws_send_engine *queue,
+				 int numa_node,
+				 struct mlx5hws_send_ring_cq *cq)
+{
+	void *cqc_data;
+	int err;
+
+	cqc_data = kvzalloc(MLX5_ST_SZ_BYTES(cqc), GFP_KERNEL);
+	if (!cqc_data)
+		return -ENOMEM;
+
+	MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index);
+	MLX5_SET(cqc, cqc_data, cqe_sz, queue->num_entries);
+	MLX5_SET(cqc, cqc_data, log_cq_size, ilog2(queue->num_entries));
+
+	err = hws_send_ring_alloc_cq(mdev, numa_node, queue, cqc_data, cq);
+	if (err)
+		goto err_out;
+
+	err = hws_send_ring_create_cq(mdev, queue, cqc_data, cq);
+	if (err)
+		goto err_free_cq;
+
+	kvfree(cqc_data);
+
+	return 0;
+
+err_free_cq:
+	mlx5_wq_destroy(&cq->wq_ctrl);
+err_out:
+	kvfree(cqc_data);
+	return err;
+}
+
+static void hws_send_ring_close_cq(struct mlx5hws_send_ring_cq *cq)
+{
+	mlx5_core_destroy_cq(cq->mdev, &cq->mcq);
+	mlx5_wq_destroy(&cq->wq_ctrl);
+}
+
+static void hws_send_ring_close(struct mlx5hws_send_engine *queue)
+{
+	hws_send_ring_close_sq(&queue->send_ring.send_sq);
+	hws_send_ring_close_cq(&queue->send_ring.send_cq);
+}
+
+static int mlx5hws_send_ring_open(struct mlx5hws_context *ctx,
+				  struct mlx5hws_send_engine *queue)
+{
+	int numa_node = dev_to_node(mlx5_core_dma_dev(ctx->mdev));
+	struct mlx5hws_send_ring *ring = &queue->send_ring;
+	int err;
+
+	err = hws_send_ring_open_cq(ctx->mdev, queue, numa_node, &ring->send_cq);
+	if (err)
+		return err;
+
+	err = hws_send_ring_open_sq(ctx, numa_node, queue, &ring->send_sq,
+				    &ring->send_cq);
+	if (err)
+		goto close_cq;
+
+	return err;
+
+close_cq:
+	hws_send_ring_close_cq(&ring->send_cq);
+	return err;
+}
+
+void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue)
+{
+	hws_send_ring_close(queue);
+	kfree(queue->completed.entries);
+}
+
+int mlx5hws_send_queue_open(struct mlx5hws_context *ctx,
+			    struct mlx5hws_send_engine *queue,
+			    u16 queue_size)
+{
+	int err;
+
+	mutex_init(&queue->lock);
+
+	queue->num_entries = roundup_pow_of_two(queue_size);
+	queue->used_entries = 0;
+
+	queue->completed.entries = kcalloc(queue->num_entries,
+					   sizeof(queue->completed.entries[0]),
+					   GFP_KERNEL);
+	if (!queue->completed.entries)
+		return -ENOMEM;
+
+	queue->completed.pi = 0;
+	queue->completed.ci = 0;
+	queue->completed.mask = queue->num_entries - 1;
+	err = mlx5hws_send_ring_open(ctx, queue);
+	if (err)
+		goto free_completed_entries;
+
+	return 0;
+
+free_completed_entries:
+	kfree(queue->completed.entries);
+	return err;
+}
+
+static void __hws_send_queues_close(struct mlx5hws_context *ctx, u16 queues)
+{
+	while (queues--)
+		mlx5hws_send_queue_close(&ctx->send_queue[queues]);
+}
+
+static void hws_send_queues_bwc_locks_destroy(struct mlx5hws_context *ctx)
+{
+	int bwc_queues = ctx->queues - 1;
+	int i;
+
+	if (!mlx5hws_context_bwc_supported(ctx))
+		return;
+
+	for (i = 0; i < bwc_queues; i++)
+		mutex_destroy(&ctx->bwc_send_queue_locks[i]);
+	kfree(ctx->bwc_send_queue_locks);
+}
+
+void mlx5hws_send_queues_close(struct mlx5hws_context *ctx)
+{
+	hws_send_queues_bwc_locks_destroy(ctx);
+	__hws_send_queues_close(ctx, ctx->queues);
+	kfree(ctx->send_queue);
+}
+
+static int hws_bwc_send_queues_init(struct mlx5hws_context *ctx)
+{
+	/* Number of BWC queues is equal to number of the usual HWS queues */
+	int bwc_queues = ctx->queues - 1;
+	int i;
+
+	if (!mlx5hws_context_bwc_supported(ctx))
+		return 0;
+
+	ctx->queues += bwc_queues;
+
+	ctx->bwc_send_queue_locks = kcalloc(bwc_queues,
+					    sizeof(*ctx->bwc_send_queue_locks),
+					    GFP_KERNEL);
+
+	if (!ctx->bwc_send_queue_locks)
+		return -ENOMEM;
+
+	for (i = 0; i < bwc_queues; i++)
+		mutex_init(&ctx->bwc_send_queue_locks[i]);
+
+	return 0;
+}
+
+int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
+			     u16 queues,
+			     u16 queue_size)
+{
+	int err = 0;
+	u32 i;
+
+	/* Open one extra queue for control path */
+	ctx->queues = queues + 1;
+
+	/* open a separate set of queues and locks for bwc API */
+	err = hws_bwc_send_queues_init(ctx);
+	if (err)
+		return err;
+
+	ctx->send_queue = kcalloc(ctx->queues, sizeof(*ctx->send_queue), GFP_KERNEL);
+	if (!ctx->send_queue) {
+		err = -ENOMEM;
+		goto free_bwc_locks;
+	}
+
+	for (i = 0; i < ctx->queues; i++) {
+		err = mlx5hws_send_queue_open(ctx, &ctx->send_queue[i], queue_size);
+		if (err)
+			goto close_send_queues;
+	}
+
+	return 0;
+
+close_send_queues:
+	 __hws_send_queues_close(ctx, i);
+
+	kfree(ctx->send_queue);
+
+free_bwc_locks:
+	hws_send_queues_bwc_locks_destroy(ctx);
+
+	return err;
+}
+
+int mlx5hws_send_queue_action(struct mlx5hws_context *ctx,
+			      u16 queue_id,
+			      u32 actions)
+{
+	struct mlx5hws_send_ring_sq *send_sq;
+	struct mlx5hws_send_engine *queue;
+	bool wait_comp = false;
+	s64 polled = 0;
+
+	queue = &ctx->send_queue[queue_id];
+	send_sq = &queue->send_ring.send_sq;
+
+	switch (actions) {
+	case MLX5HWS_SEND_QUEUE_ACTION_DRAIN_SYNC:
+		wait_comp = true;
+		fallthrough;
+	case MLX5HWS_SEND_QUEUE_ACTION_DRAIN_ASYNC:
+		if (send_sq->head_dep_idx != send_sq->tail_dep_idx)
+			/* Send dependent WQEs to drain the queue */
+			mlx5hws_send_all_dep_wqe(queue);
+		else
+			/* Signal on the last posted WQE */
+			mlx5hws_send_engine_flush_queue(queue);
+
+		/* Poll queue until empty */
+		while (wait_comp && !mlx5hws_send_engine_empty(queue))
+			hws_send_engine_poll_cq(queue, NULL, &polled, 0);
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+hws_send_wqe_fw(struct mlx5_core_dev *mdev,
+		u32 pd_num,
+		struct mlx5hws_send_engine_post_attr *send_attr,
+		struct mlx5hws_wqe_gta_ctrl_seg *send_wqe_ctrl,
+		void *send_wqe_match_data,
+		void *send_wqe_match_tag,
+		void *send_wqe_range_data,
+		void *send_wqe_range_tag,
+		bool is_jumbo,
+		u8 gta_opcode)
+{
+	bool has_range = send_wqe_range_data || send_wqe_range_tag;
+	bool has_match = send_wqe_match_data || send_wqe_match_tag;
+	struct mlx5hws_wqe_gta_data_seg_ste gta_wqe_data0 = {0};
+	struct mlx5hws_wqe_gta_data_seg_ste gta_wqe_data1 = {0};
+	struct mlx5hws_wqe_gta_ctrl_seg gta_wqe_ctrl = {0};
+	struct mlx5hws_cmd_generate_wqe_attr attr = {0};
+	struct mlx5hws_wqe_ctrl_seg wqe_ctrl = {0};
+	struct mlx5_cqe64 cqe;
+	u32 flags = 0;
+	int ret;
+
+	/* Set WQE control */
+	wqe_ctrl.opmod_idx_opcode = cpu_to_be32((send_attr->opmod << 24) | send_attr->opcode);
+	wqe_ctrl.qpn_ds = cpu_to_be32((send_attr->len + sizeof(struct mlx5hws_wqe_ctrl_seg)) / 16);
+	flags |= send_attr->notify_hw ? MLX5_WQE_CTRL_CQ_UPDATE : 0;
+	wqe_ctrl.flags = cpu_to_be32(flags);
+	wqe_ctrl.imm = cpu_to_be32(send_attr->id);
+
+	/* Set GTA WQE CTRL */
+	memcpy(gta_wqe_ctrl.stc_ix, send_wqe_ctrl->stc_ix, sizeof(send_wqe_ctrl->stc_ix));
+	gta_wqe_ctrl.op_dirix = cpu_to_be32(gta_opcode << 28);
+
+	/* Set GTA match WQE DATA */
+	if (has_match) {
+		if (send_wqe_match_data)
+			memcpy(&gta_wqe_data0, send_wqe_match_data, sizeof(gta_wqe_data0));
+		else
+			hws_send_wqe_set_tag(&gta_wqe_data0, send_wqe_match_tag, is_jumbo);
+
+		gta_wqe_data0.rsvd1_definer = cpu_to_be32(send_attr->match_definer_id << 8);
+		attr.gta_data_0 = (u8 *)&gta_wqe_data0;
+	}
+
+	/* Set GTA range WQE DATA */
+	if (has_range) {
+		if (send_wqe_range_data)
+			memcpy(&gta_wqe_data1, send_wqe_range_data, sizeof(gta_wqe_data1));
+		else
+			hws_send_wqe_set_tag(&gta_wqe_data1, send_wqe_range_tag, false);
+
+		gta_wqe_data1.rsvd1_definer = cpu_to_be32(send_attr->range_definer_id << 8);
+		attr.gta_data_1 = (u8 *)&gta_wqe_data1;
+	}
+
+	attr.pdn = pd_num;
+	attr.wqe_ctrl = (u8 *)&wqe_ctrl;
+	attr.gta_ctrl = (u8 *)&gta_wqe_ctrl;
+
+send_wqe:
+	ret = mlx5hws_cmd_generate_wqe(mdev, &attr, &cqe);
+	if (ret) {
+		mlx5_core_err(mdev, "Failed to write WQE using command");
+		return ret;
+	}
+
+	if ((get_cqe_opcode(&cqe) == MLX5_CQE_REQ) &&
+	    (be32_to_cpu(cqe.byte_cnt) >> 31 == 0)) {
+		*send_attr->used_id = send_attr->id;
+		return 0;
+	}
+
+	/* Retry if rule failed */
+	if (send_attr->retry_id) {
+		wqe_ctrl.imm = cpu_to_be32(send_attr->retry_id);
+		send_attr->id = send_attr->retry_id;
+		send_attr->retry_id = 0;
+		goto send_wqe;
+	}
+
+	return -1;
+}
+
+void mlx5hws_send_stes_fw(struct mlx5hws_context *ctx,
+			  struct mlx5hws_send_engine *queue,
+			  struct mlx5hws_send_ste_attr *ste_attr)
+{
+	struct mlx5hws_send_engine_post_attr *send_attr = &ste_attr->send_attr;
+	struct mlx5hws_rule *rule = send_attr->rule;
+	struct mlx5_core_dev *mdev;
+	u16 queue_id;
+	u32 pdn;
+	int ret;
+
+	queue_id = queue - ctx->send_queue;
+	mdev = ctx->mdev;
+	pdn = ctx->pd_num;
+
+	/* Writing through FW can't HW fence, therefore we drain the queue */
+	if (send_attr->fence)
+		mlx5hws_send_queue_action(ctx,
+					  queue_id,
+					  MLX5HWS_SEND_QUEUE_ACTION_DRAIN_SYNC);
+
+	if (ste_attr->rtc_1) {
+		send_attr->id = ste_attr->rtc_1;
+		send_attr->used_id = ste_attr->used_id_rtc_1;
+		send_attr->retry_id = ste_attr->retry_rtc_1;
+		ret = hws_send_wqe_fw(mdev, pdn, send_attr,
+				      ste_attr->wqe_ctrl,
+				      ste_attr->wqe_data,
+				      ste_attr->wqe_tag,
+				      ste_attr->range_wqe_data,
+				      ste_attr->range_wqe_tag,
+				      ste_attr->wqe_tag_is_jumbo,
+				      ste_attr->gta_opcode);
+		if (ret)
+			goto fail_rule;
+	}
+
+	if (ste_attr->rtc_0) {
+		send_attr->id = ste_attr->rtc_0;
+		send_attr->used_id = ste_attr->used_id_rtc_0;
+		send_attr->retry_id = ste_attr->retry_rtc_0;
+		ret = hws_send_wqe_fw(mdev, pdn, send_attr,
+				      ste_attr->wqe_ctrl,
+				      ste_attr->wqe_data,
+				      ste_attr->wqe_tag,
+				      ste_attr->range_wqe_data,
+				      ste_attr->range_wqe_tag,
+				      ste_attr->wqe_tag_is_jumbo,
+				      ste_attr->gta_opcode);
+		if (ret)
+			goto fail_rule;
+	}
+
+	/* Increase the status, this only works on good flow as the enum
+	 * is arrange it away creating -> created -> deleting -> deleted
+	 */
+	if (likely(rule))
+		rule->status++;
+
+	mlx5hws_send_engine_gen_comp(queue, send_attr->user_data, MLX5HWS_FLOW_OP_SUCCESS);
+
+	return;
+
+fail_rule:
+	if (likely(rule))
+		rule->status = !rule->rtc_0 && !rule->rtc_1 ?
+			MLX5HWS_RULE_STATUS_FAILED : MLX5HWS_RULE_STATUS_FAILING;
+
+	mlx5hws_send_engine_gen_comp(queue, send_attr->user_data, MLX5HWS_FLOW_OP_ERROR);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.h
new file mode 100644
index 000000000000..b50825d6dc53
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.h
@@ -0,0 +1,270 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_SEND_H_
+#define MLX5HWS_SEND_H_
+
+/* As a single operation requires at least two WQEBBS.
+ * This means a maximum of 16 such operations per rule.
+ */
+#define MAX_WQES_PER_RULE 32
+
+enum mlx5hws_wqe_opcode {
+	MLX5HWS_WQE_OPCODE_TBL_ACCESS = 0x2c,
+};
+
+enum mlx5hws_wqe_opmod {
+	MLX5HWS_WQE_OPMOD_GTA_STE = 0,
+	MLX5HWS_WQE_OPMOD_GTA_MOD_ARG = 1,
+};
+
+enum mlx5hws_wqe_gta_opcode {
+	MLX5HWS_WQE_GTA_OP_ACTIVATE = 0,
+	MLX5HWS_WQE_GTA_OP_DEACTIVATE = 1,
+};
+
+enum mlx5hws_wqe_gta_opmod {
+	MLX5HWS_WQE_GTA_OPMOD_STE = 0,
+	MLX5HWS_WQE_GTA_OPMOD_MOD_ARG = 1,
+};
+
+enum mlx5hws_wqe_gta_sz {
+	MLX5HWS_WQE_SZ_GTA_CTRL = 48,
+	MLX5HWS_WQE_SZ_GTA_DATA = 64,
+};
+
+/* WQE Control segment. */
+struct mlx5hws_wqe_ctrl_seg {
+	__be32 opmod_idx_opcode;
+	__be32 qpn_ds;
+	__be32 flags;
+	__be32 imm;
+};
+
+struct mlx5hws_wqe_gta_ctrl_seg {
+	__be32 op_dirix;
+	__be32 stc_ix[5];
+	__be32 rsvd0[6];
+};
+
+struct mlx5hws_wqe_gta_data_seg_ste {
+	__be32 rsvd0_ctr_id;
+	__be32 rsvd1_definer;
+	__be32 rsvd2[3];
+	union {
+		struct {
+		__be32 action[3];
+		__be32 tag[8];
+		};
+		__be32 jumbo[11];
+	};
+};
+
+struct mlx5hws_wqe_gta_data_seg_arg {
+	__be32 action_args[8];
+};
+
+struct mlx5hws_wqe_gta {
+	struct mlx5hws_wqe_gta_ctrl_seg gta_ctrl;
+	union {
+		struct mlx5hws_wqe_gta_data_seg_ste seg_ste;
+		struct mlx5hws_wqe_gta_data_seg_arg seg_arg;
+	};
+};
+
+struct mlx5hws_send_ring_cq {
+	struct mlx5_core_dev *mdev;
+	struct mlx5_cqwq wq;
+	struct mlx5_wq_ctrl wq_ctrl;
+	struct mlx5_core_cq mcq;
+	u16 poll_wqe;
+};
+
+struct mlx5hws_send_ring_priv {
+	struct mlx5hws_rule *rule;
+	void *user_data;
+	u32 num_wqebbs;
+	u32 id;
+	u32 retry_id;
+	u32 *used_id;
+};
+
+struct mlx5hws_send_ring_dep_wqe {
+	struct mlx5hws_wqe_gta_ctrl_seg wqe_ctrl;
+	struct mlx5hws_wqe_gta_data_seg_ste wqe_data;
+	struct mlx5hws_rule *rule;
+	u32 rtc_0;
+	u32 rtc_1;
+	u32 retry_rtc_0;
+	u32 retry_rtc_1;
+	u32 direct_index;
+	void *user_data;
+};
+
+struct mlx5hws_send_ring_sq {
+	struct mlx5_core_dev *mdev;
+	u16 cur_post;
+	u16 buf_mask;
+	struct mlx5hws_send_ring_priv *wr_priv;
+	unsigned int last_idx;
+	struct mlx5hws_send_ring_dep_wqe *dep_wqe;
+	unsigned int head_dep_idx;
+	unsigned int tail_dep_idx;
+	u32 sqn;
+	struct mlx5_wq_cyc wq;
+	struct mlx5_wq_ctrl wq_ctrl;
+	void __iomem *uar_map;
+};
+
+struct mlx5hws_send_ring {
+	struct mlx5hws_send_ring_cq send_cq;
+	struct mlx5hws_send_ring_sq send_sq;
+};
+
+struct mlx5hws_completed_poll_entry {
+	void *user_data;
+	enum mlx5hws_flow_op_status status;
+};
+
+struct mlx5hws_completed_poll {
+	struct mlx5hws_completed_poll_entry *entries;
+	u16 ci;
+	u16 pi;
+	u16 mask;
+};
+
+struct mlx5hws_send_engine {
+	struct mlx5hws_send_ring send_ring;
+	struct mlx5_uars_page *uar; /* Uar is shared between rings of a queue */
+	struct mlx5hws_completed_poll completed;
+	u16 used_entries;
+	u16 num_entries;
+	bool err;
+	struct mutex lock; /* Protects the send engine */
+};
+
+struct mlx5hws_send_engine_post_ctrl {
+	struct mlx5hws_send_engine *queue;
+	struct mlx5hws_send_ring *send_ring;
+	size_t num_wqebbs;
+};
+
+struct mlx5hws_send_engine_post_attr {
+	u8 opcode;
+	u8 opmod;
+	u8 notify_hw;
+	u8 fence;
+	u8 match_definer_id;
+	u8 range_definer_id;
+	size_t len;
+	struct mlx5hws_rule *rule;
+	u32 id;
+	u32 retry_id;
+	u32 *used_id;
+	void *user_data;
+};
+
+struct mlx5hws_send_ste_attr {
+	u32 rtc_0;
+	u32 rtc_1;
+	u32 retry_rtc_0;
+	u32 retry_rtc_1;
+	u32 *used_id_rtc_0;
+	u32 *used_id_rtc_1;
+	bool wqe_tag_is_jumbo;
+	u8 gta_opcode;
+	u32 direct_index;
+	struct mlx5hws_send_engine_post_attr send_attr;
+	struct mlx5hws_rule_match_tag *wqe_tag;
+	struct mlx5hws_rule_match_tag *range_wqe_tag;
+	struct mlx5hws_wqe_gta_ctrl_seg *wqe_ctrl;
+	struct mlx5hws_wqe_gta_data_seg_ste *wqe_data;
+	struct mlx5hws_wqe_gta_data_seg_ste *range_wqe_data;
+};
+
+struct mlx5hws_send_ring_dep_wqe *
+mlx5hws_send_add_new_dep_wqe(struct mlx5hws_send_engine *queue);
+
+void mlx5hws_send_abort_new_dep_wqe(struct mlx5hws_send_engine *queue);
+
+void mlx5hws_send_all_dep_wqe(struct mlx5hws_send_engine *queue);
+
+void mlx5hws_send_queue_close(struct mlx5hws_send_engine *queue);
+
+int mlx5hws_send_queue_open(struct mlx5hws_context *ctx,
+			    struct mlx5hws_send_engine *queue,
+			    u16 queue_size);
+
+void mlx5hws_send_queues_close(struct mlx5hws_context *ctx);
+
+int mlx5hws_send_queues_open(struct mlx5hws_context *ctx,
+			     u16 queues,
+			     u16 queue_size);
+
+int mlx5hws_send_queue_action(struct mlx5hws_context *ctx,
+			      u16 queue_id,
+			      u32 actions);
+
+int mlx5hws_send_test(struct mlx5hws_context *ctx,
+		      u16 queues,
+		      u16 queue_size);
+
+struct mlx5hws_send_engine_post_ctrl
+mlx5hws_send_engine_post_start(struct mlx5hws_send_engine *queue);
+
+void mlx5hws_send_engine_post_req_wqe(struct mlx5hws_send_engine_post_ctrl *ctrl,
+				      char **buf, size_t *len);
+
+void mlx5hws_send_engine_post_end(struct mlx5hws_send_engine_post_ctrl *ctrl,
+				  struct mlx5hws_send_engine_post_attr *attr);
+
+void mlx5hws_send_ste(struct mlx5hws_send_engine *queue,
+		      struct mlx5hws_send_ste_attr *ste_attr);
+
+void mlx5hws_send_stes_fw(struct mlx5hws_context *ctx,
+			  struct mlx5hws_send_engine *queue,
+			  struct mlx5hws_send_ste_attr *ste_attr);
+
+void mlx5hws_send_engine_flush_queue(struct mlx5hws_send_engine *queue);
+
+static inline bool mlx5hws_send_engine_empty(struct mlx5hws_send_engine *queue)
+{
+	struct mlx5hws_send_ring_sq *send_sq = &queue->send_ring.send_sq;
+	struct mlx5hws_send_ring_cq *send_cq = &queue->send_ring.send_cq;
+
+	return ((send_sq->cur_post & send_sq->buf_mask) == send_cq->poll_wqe);
+}
+
+static inline bool mlx5hws_send_engine_full(struct mlx5hws_send_engine *queue)
+{
+	return queue->used_entries >= queue->num_entries;
+}
+
+static inline void mlx5hws_send_engine_inc_rule(struct mlx5hws_send_engine *queue)
+{
+	queue->used_entries++;
+}
+
+static inline void mlx5hws_send_engine_dec_rule(struct mlx5hws_send_engine *queue)
+{
+	queue->used_entries--;
+}
+
+static inline void mlx5hws_send_engine_gen_comp(struct mlx5hws_send_engine *queue,
+						void *user_data,
+						int comp_status)
+{
+	struct mlx5hws_completed_poll *comp = &queue->completed;
+
+	comp->entries[comp->pi].status = comp_status;
+	comp->entries[comp->pi].user_data = user_data;
+
+	comp->pi = (comp->pi + 1) & comp->mask;
+}
+
+static inline bool mlx5hws_send_engine_err(struct mlx5hws_send_engine *queue)
+{
+	return queue->err;
+}
+
+#endif /* MLX5HWS_SEND_H_ */
-- 
cgit v1.3-3-g829e


From 510f9f61a1121a296a45962760d5e2824277fa37 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Thu, 20 Jun 2024 02:46:40 +0300
Subject: net/mlx5: HWS, added API and enabled HWS support

Enabling HWS support in the mlx5 driver:
 - added HWS API header
 - added HWS files in the mlx5 driver makefile
 - added kconfig flag that enables HWS compilation

Reviewed-by: Erez Shitrit <erezsh@nvidia.com>
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../ethernet/mellanox/mlx5/kconfig.rst             |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |  10 +
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  21 +
 .../mellanox/mlx5/core/steering/hws/Makefile       |   2 +
 .../mellanox/mlx5/core/steering/hws/mlx5hws.h      | 954 +++++++++++++++++++++
 .../mlx5/core/steering/hws/mlx5hws_internal.h      |   8 +-
 6 files changed, 994 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/Makefile
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst
index 20d3b7e87049..34e911480108 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst
@@ -130,6 +130,9 @@ Enabling the driver and kconfig options
 
 |    Build support for software-managed steering in the NIC.
 
+**CONFIG_MLX5_HW_STEERING=(y/n)**
+
+|    Build support for hardware-managed steering in the NIC.
 
 **CONFIG_MLX5_TC_CT=(y/n)**
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 685335832a93..ea6070180c96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -172,6 +172,16 @@ config MLX5_SW_STEERING
 	help
 	Build support for software-managed steering in the NIC.
 
+config MLX5_HW_STEERING
+	bool "Mellanox Technologies hardware-managed steering"
+	depends on MLX5_CORE_EN && MLX5_ESWITCH
+	default y
+	help
+	Build support for Hardware-Managed Flow Steering (HMFS) in the NIC.
+	HMFS is a new approach to managing steering rules where STEs are
+	written to ICM by HW (as opposed to SW in software-managed steering),
+	which allows higher rate of rule insertion.
+
 config MLX5_SF
 	bool "Mellanox Technologies subfunction device support using auxiliary device"
 	depends on MLX5_CORE && MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 1289475e7be7..5912f7e614f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -119,6 +119,27 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
 					steering/dr_action.o steering/fs_dr.o \
 					steering/dr_definer.o steering/dr_ptrn.o \
 					steering/dr_arg.o steering/dr_dbg.o lib/smfs.o
+
+#
+# HW Steering
+#
+mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/mlx5hws_cmd.o \
+					steering/hws/mlx5hws_context.o \
+					steering/hws/mlx5hws_pat_arg.o \
+					steering/hws/mlx5hws_buddy.o \
+					steering/hws/mlx5hws_pool.o \
+					steering/hws/mlx5hws_table.o \
+					steering/hws/mlx5hws_action.o \
+					steering/hws/mlx5hws_rule.o \
+					steering/hws/mlx5hws_matcher.o \
+					steering/hws/mlx5hws_send.o \
+					steering/hws/mlx5hws_definer.o \
+					steering/hws/mlx5hws_bwc.o \
+					steering/hws/mlx5hws_debug.o \
+					steering/hws/mlx5hws_vport.o \
+					steering/hws/mlx5hws_bwc_complex.o
+
+
 #
 # SF device
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/Makefile
new file mode 100644
index 000000000000..c78512eed8d7
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+subdir-ccflags-y += -I$(src)/..
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
new file mode 100644
index 000000000000..9a85d4e12f77
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -0,0 +1,954 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+
+#ifndef MLX5HWS_H_
+#define MLX5HWS_H_
+
+struct mlx5hws_context;
+struct mlx5hws_table;
+struct mlx5hws_matcher;
+struct mlx5hws_rule;
+
+enum mlx5hws_table_type {
+	MLX5HWS_TABLE_TYPE_FDB,
+	MLX5HWS_TABLE_TYPE_MAX,
+};
+
+enum mlx5hws_matcher_resource_mode {
+	/* Allocate resources based on number of rules with minimal failure probability */
+	MLX5HWS_MATCHER_RESOURCE_MODE_RULE,
+	/* Allocate fixed size hash table based on given column and rows */
+	MLX5HWS_MATCHER_RESOURCE_MODE_HTABLE,
+};
+
+enum mlx5hws_action_type {
+	MLX5HWS_ACTION_TYP_LAST,
+	MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2,
+	MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2,
+	MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2,
+	MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3,
+	MLX5HWS_ACTION_TYP_DROP,
+	MLX5HWS_ACTION_TYP_MISS,
+	MLX5HWS_ACTION_TYP_TBL,
+	MLX5HWS_ACTION_TYP_CTR,
+	MLX5HWS_ACTION_TYP_TAG,
+	MLX5HWS_ACTION_TYP_MODIFY_HDR,
+	MLX5HWS_ACTION_TYP_VPORT,
+	MLX5HWS_ACTION_TYP_POP_VLAN,
+	MLX5HWS_ACTION_TYP_PUSH_VLAN,
+	MLX5HWS_ACTION_TYP_ASO_METER,
+	MLX5HWS_ACTION_TYP_INSERT_HEADER,
+	MLX5HWS_ACTION_TYP_REMOVE_HEADER,
+	MLX5HWS_ACTION_TYP_RANGE,
+	MLX5HWS_ACTION_TYP_SAMPLER,
+	MLX5HWS_ACTION_TYP_DEST_ARRAY,
+	MLX5HWS_ACTION_TYP_MAX,
+};
+
+enum mlx5hws_action_flags {
+	MLX5HWS_ACTION_FLAG_HWS_FDB = 1 << 0,
+	/* Shared action can be used over a few threads, since the
+	 * data is written only once at the creation of the action.
+	 */
+	MLX5HWS_ACTION_FLAG_SHARED = 1 << 1,
+};
+
+enum mlx5hws_action_aso_meter_color {
+	MLX5HWS_ACTION_ASO_METER_COLOR_RED = 0x0,
+	MLX5HWS_ACTION_ASO_METER_COLOR_YELLOW = 0x1,
+	MLX5HWS_ACTION_ASO_METER_COLOR_GREEN = 0x2,
+	MLX5HWS_ACTION_ASO_METER_COLOR_UNDEFINED = 0x3,
+};
+
+enum mlx5hws_send_queue_actions {
+	/* Start executing all pending queued rules */
+	MLX5HWS_SEND_QUEUE_ACTION_DRAIN_ASYNC = 1 << 0,
+	/* Start executing all pending queued rules wait till completion */
+	MLX5HWS_SEND_QUEUE_ACTION_DRAIN_SYNC = 1 << 1,
+};
+
+struct mlx5hws_context_attr {
+	u16 queues;
+	u16 queue_size;
+	bool bwc; /* add support for backward compatible API*/
+};
+
+struct mlx5hws_table_attr {
+	enum mlx5hws_table_type type;
+	u32 level;
+};
+
+enum mlx5hws_matcher_flow_src {
+	MLX5HWS_MATCHER_FLOW_SRC_ANY = 0x0,
+	MLX5HWS_MATCHER_FLOW_SRC_WIRE = 0x1,
+	MLX5HWS_MATCHER_FLOW_SRC_VPORT = 0x2,
+};
+
+enum mlx5hws_matcher_insert_mode {
+	MLX5HWS_MATCHER_INSERT_BY_HASH = 0x0,
+	MLX5HWS_MATCHER_INSERT_BY_INDEX = 0x1,
+};
+
+enum mlx5hws_matcher_distribute_mode {
+	MLX5HWS_MATCHER_DISTRIBUTE_BY_HASH = 0x0,
+	MLX5HWS_MATCHER_DISTRIBUTE_BY_LINEAR = 0x1,
+};
+
+struct mlx5hws_matcher_attr {
+	/* Processing priority inside table */
+	u32 priority;
+	/* Provide all rules with unique rule_idx in num_log range to reduce locking */
+	bool optimize_using_rule_idx;
+	/* Resource mode and corresponding size */
+	enum mlx5hws_matcher_resource_mode mode;
+	/* Optimize insertion in case packet origin is the same for all rules */
+	enum mlx5hws_matcher_flow_src optimize_flow_src;
+	/* Define the insertion and distribution modes for this matcher */
+	enum mlx5hws_matcher_insert_mode insert_mode;
+	enum mlx5hws_matcher_distribute_mode distribute_mode;
+	/* Define whether the created matcher supports resizing into a bigger matcher */
+	bool resizable;
+	union {
+		struct {
+			u8 sz_row_log;
+			u8 sz_col_log;
+		} table;
+
+		struct {
+			u8 num_log;
+		} rule;
+	};
+	/* Optional AT attach configuration - Max number of additional AT */
+	u8 max_num_of_at_attach;
+};
+
+struct mlx5hws_rule_attr {
+	void *user_data;
+	/* Valid if matcher optimize_using_rule_idx is set or
+	 * if matcher is configured to insert rules by index.
+	 */
+	u32 rule_idx;
+	u32 flow_source;
+	u16 queue_id;
+	u32 burst:1;
+};
+
+/* In actions that take offset, the offset is unique, pointing to a single
+ * resource and the user should not reuse the same index because data changing
+ * is not atomic.
+ */
+struct mlx5hws_rule_action {
+	struct mlx5hws_action *action;
+	union {
+		struct {
+			u32 value;
+		} tag;
+
+		struct {
+			u32 offset;
+		} counter;
+
+		struct {
+			u32 offset;
+			u8 *data;
+		} modify_header;
+
+		struct {
+			u32 offset;
+			u8 hdr_idx;
+			u8 *data;
+		} reformat;
+
+		struct {
+			__be32 vlan_hdr;
+		} push_vlan;
+
+		struct {
+			u32 offset;
+			enum mlx5hws_action_aso_meter_color init_color;
+		} aso_meter;
+	};
+};
+
+struct mlx5hws_action_reformat_header {
+	size_t sz;
+	void *data;
+};
+
+struct mlx5hws_action_insert_header {
+	struct mlx5hws_action_reformat_header hdr;
+	/* PRM start anchor to which header will be inserted */
+	u8 anchor;
+	/* Header insertion offset in bytes, from the start
+	 * anchor to the location where new header will be inserted.
+	 */
+	u8 offset;
+	/* Indicates this header insertion adds encapsulation header to the packet,
+	 * requiring device to update offloaded fields (for example IPv4 total length).
+	 */
+	bool encap;
+};
+
+struct mlx5hws_action_remove_header_attr {
+	/* PRM start anchor from which header will be removed */
+	u8 anchor;
+	/* Header remove offset in bytes, from the start
+	 * anchor to the location where remove header starts.
+	 */
+	u8 offset;
+	/* Indicates the removed header size in bytes */
+	size_t size;
+};
+
+struct mlx5hws_action_mh_pattern {
+	/* Byte size of modify actions provided by "data" */
+	size_t sz;
+	/* PRM format modify actions pattern */
+	__be64 *data;
+};
+
+struct mlx5hws_action_dest_attr {
+	/* Required destination action to forward the packet */
+	struct mlx5hws_action *dest;
+	/* Optional reformat action */
+	struct mlx5hws_action *reformat;
+};
+
+/* Check whether HWS is supported
+ *
+ * @param[in] mdev
+ *	The device to check.
+ * @return true if supported, false otherwise.
+ */
+static inline bool mlx5hws_is_supported(struct mlx5_core_dev *mdev)
+{
+	u8 ignore_flow_level_rtc_valid;
+	u8 wqe_based_flow_table_update;
+
+	wqe_based_flow_table_update =
+		MLX5_CAP_GEN(mdev, wqe_based_flow_table_update_cap);
+	ignore_flow_level_rtc_valid =
+		MLX5_CAP_FLOWTABLE(mdev,
+				   flow_table_properties_nic_receive.ignore_flow_level_rtc_valid);
+
+	return wqe_based_flow_table_update && ignore_flow_level_rtc_valid;
+}
+
+/* Open a context used for direct rule insertion using hardware steering.
+ * Each context can contain multiple tables of different types.
+ *
+ * @param[in] mdev
+ *	The device to be used for HWS.
+ * @param[in] attr
+ *	Attributes used for context open.
+ * @return pointer to mlx5hws_context on success NULL otherwise.
+ */
+struct mlx5hws_context *
+mlx5hws_context_open(struct mlx5_core_dev *mdev,
+		     struct mlx5hws_context_attr *attr);
+
+/* Close a context used for direct hardware steering.
+ *
+ * @param[in] ctx
+ *	mlx5hws context to close.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_context_close(struct mlx5hws_context *ctx);
+
+/* Set a peer context, each context can have multiple contexts as peers.
+ *
+ * @param[in] ctx
+ *	The context in which the peer_ctx will be peered to it.
+ * @param[in] peer_ctx
+ *	The peer context.
+ * @param[in] peer_vhca_id
+ *	The peer context vhca id.
+ */
+void mlx5hws_context_set_peer(struct mlx5hws_context *ctx,
+			      struct mlx5hws_context *peer_ctx,
+			      u16 peer_vhca_id);
+
+/* Create a new direct rule table. Each table can contain multiple matchers.
+ *
+ * @param[in] ctx
+ *	The context in which the new table will be opened.
+ * @param[in] attr
+ *	Attributes used for table creation.
+ * @return pointer to mlx5hws_table on success NULL otherwise.
+ */
+struct mlx5hws_table *
+mlx5hws_table_create(struct mlx5hws_context *ctx,
+		     struct mlx5hws_table_attr *attr);
+
+/* Destroy direct rule table.
+ *
+ * @param[in] tbl
+ *	Table to destroy.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_table_destroy(struct mlx5hws_table *tbl);
+
+/* Get ID of the flow table.
+ *
+ * @param[in] tbl
+ *	Table to get ID of.
+ * @return ID of the table.
+ */
+u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl);
+
+/* Set default miss table for mlx5hws_table by using another mlx5hws_table
+ * Traffic which all table matchers miss will be forwarded to miss table.
+ *
+ * @param[in] tbl
+ *	Source table
+ * @param[in] miss_tbl
+ *	Target (miss) table, or NULL to remove current miss table
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
+				   struct mlx5hws_table *miss_tbl);
+
+/* Create new match template based on items mask, the match template
+ * will be used for matcher creation.
+ *
+ * @param[in] ctx
+ *	The context in which the new template will be created.
+ * @param[in] match_param
+ *	Describe the mask based on PRM match parameters
+ * @param[in] match_param_sz
+ *	Size of match param buffer
+ * @param[in] match_criteria_enable
+ *	Bitmap for each sub-set in match_criteria buffer
+ * @return pointer to mlx5hws_match_template on success NULL otherwise
+ */
+struct mlx5hws_match_template *
+mlx5hws_match_template_create(struct mlx5hws_context *ctx,
+			      u32 *match_param,
+			      u32 match_param_sz,
+			      u8 match_criteria_enable);
+
+/* Destroy match template.
+ *
+ * @param[in] mt
+ *	Match template to destroy.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_match_template_destroy(struct mlx5hws_match_template *mt);
+
+/* Create new action template based on action_type array, the action template
+ * will be used for matcher creation.
+ *
+ * @param[in] action_type
+ *	An array of actions based on the order of actions which will be provided
+ *	with rule_actions to mlx5hws_rule_create. The last action is marked
+ *	using MLX5HWS_ACTION_TYP_LAST.
+ * @return pointer to mlx5hws_action_template on success NULL otherwise
+ */
+struct mlx5hws_action_template *
+mlx5hws_action_template_create(enum mlx5hws_action_type action_type[]);
+
+/* Destroy action template.
+ *
+ * @param[in] at
+ *	Action template to destroy.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_action_template_destroy(struct mlx5hws_action_template *at);
+
+/* Create a new direct rule matcher. Each matcher can contain multiple rules.
+ * Matchers on the table will be processed by priority. Matching fields and
+ * mask are described by the match template. In some cases multiple match
+ * templates can be used on the same matcher.
+ *
+ * @param[in] table
+ *	The table in which the new matcher will be opened.
+ * @param[in] mt
+ *	Array of match templates to be used on matcher.
+ * @param[in] num_of_mt
+ *	Number of match templates in mt array.
+ * @param[in] at
+ *	Array of action templates to be used on matcher.
+ * @param[in] num_of_at
+ *	Number of action templates in mt array.
+ * @param[in] attr
+ *	Attributes used for matcher creation.
+ * @return pointer to mlx5hws_matcher on success NULL otherwise.
+ */
+struct mlx5hws_matcher *
+mlx5hws_matcher_create(struct mlx5hws_table *table,
+		       struct mlx5hws_match_template *mt[],
+		       u8 num_of_mt,
+		       struct mlx5hws_action_template *at[],
+		       u8 num_of_at,
+		       struct mlx5hws_matcher_attr *attr);
+
+/* Destroy direct rule matcher.
+ *
+ * @param[in] matcher
+ *	Matcher to destroy.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_matcher_destroy(struct mlx5hws_matcher *matcher);
+
+/* Attach new action template to direct rule matcher.
+ *
+ * @param[in] matcher
+ *	Matcher to attach at to.
+ * @param[in] at
+ *	Action template to be attached to the matcher.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
+			      struct mlx5hws_action_template *at);
+
+/* Link two matchers and enable moving rules from src matcher to dst matcher.
+ * Both matchers must be in the same table type, must be created with 'resizable'
+ * property, and should have the same characteristics (e.g. same mt, same at).
+ *
+ * It is the user's responsibility to make sure that the dst matcher
+ * was allocated with the appropriate size.
+ *
+ * Once the function is completed, the user is:
+ *  - allowed to move rules from src into dst matcher
+ *  - no longer allowed to insert rules to the src matcher
+ *
+ * The user is always allowed to insert rules to the dst matcher and
+ * to delete rules from any matcher.
+ *
+ * @param[in] src_matcher
+ *	source matcher for moving rules from
+ * @param[in] dst_matcher
+ *	destination matcher for moving rules to
+ * @return zero on successful move, non zero otherwise.
+ */
+int mlx5hws_matcher_resize_set_target(struct mlx5hws_matcher *src_matcher,
+				      struct mlx5hws_matcher *dst_matcher);
+
+/* Enqueue moving rule operation: moving rule from src matcher to a dst matcher
+ *
+ * @param[in] src_matcher
+ *	matcher that the rule belongs to
+ * @param[in] rule
+ *	the rule to move
+ * @param[in] attr
+ *	rule attributes
+ * @return zero on success, non zero otherwise.
+ */
+int mlx5hws_matcher_resize_rule_move(struct mlx5hws_matcher *src_matcher,
+				     struct mlx5hws_rule *rule,
+				     struct mlx5hws_rule_attr *attr);
+
+/* Enqueue create rule operation.
+ *
+ * @param[in] matcher
+ *	The matcher in which the new rule will be created.
+ * @param[in] mt_idx
+ *	Match template index to create the match with.
+ * @param[in] match_param
+ *	The match parameter PRM buffer used for the value matching.
+ * @param[in] rule_actions
+ *	Rule action to be executed on match.
+ * @param[in] at_idx
+ *	Action template index to apply the actions with.
+ * @param[in] num_of_actions
+ *	Number of rule actions.
+ * @param[in] attr
+ *	Rule creation attributes.
+ * @param[in, out] rule_handle
+ *	A valid rule handle. The handle doesn't require any initialization.
+ * @return zero on successful enqueue non zero otherwise.
+ */
+int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
+			u8 mt_idx,
+			u32 *match_param,
+			u8 at_idx,
+			struct mlx5hws_rule_action rule_actions[],
+			struct mlx5hws_rule_attr *attr,
+			struct mlx5hws_rule *rule_handle);
+
+/* Enqueue destroy rule operation.
+ *
+ * @param[in] rule
+ *	The rule destruction to enqueue.
+ * @param[in] attr
+ *	Rule destruction attributes.
+ * @return zero on successful enqueue non zero otherwise.
+ */
+int mlx5hws_rule_destroy(struct mlx5hws_rule *rule,
+			 struct mlx5hws_rule_attr *attr);
+
+/* Enqueue update actions on an existing rule.
+ *
+ * @param[in, out] rule_handle
+ *	A valid rule handle to update.
+ * @param[in] at_idx
+ *	Action template index to update the actions with.
+ *  @param[in] rule_actions
+ *	Rule action to be executed on match.
+ * @param[in] attr
+ *	Rule update attributes.
+ * @return zero on successful enqueue non zero otherwise.
+ */
+int mlx5hws_rule_action_update(struct mlx5hws_rule *rule,
+			       u8 at_idx,
+			       struct mlx5hws_rule_action rule_actions[],
+			       struct mlx5hws_rule_attr *attr);
+
+/* Get action type.
+ *
+ * @param[in] action
+ *	The action to get the type of.
+ * @return action type.
+ */
+enum mlx5hws_action_type
+mlx5hws_action_get_type(struct mlx5hws_action *action);
+
+/* Create direct rule drop action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_dest_drop(struct mlx5hws_context *ctx,
+				u32 flags);
+
+/* Create direct rule default miss action.
+ * Defaults are RX: Drop TX: Wire.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_default_miss(struct mlx5hws_context *ctx,
+				   u32 flags);
+
+/* Create direct rule goto table action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] tbl
+ *	Destination table.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_dest_table(struct mlx5hws_context *ctx,
+				 struct mlx5hws_table *tbl,
+				 u32 flags);
+
+/* Create direct rule goto table number action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] tbl_num
+ *	Destination table number.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_dest_table_num(struct mlx5hws_context *ctx,
+				     u32 table_num, u32 flags);
+
+/* Create direct rule range match action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] field
+ *	Field to comapare the value.
+ * @param[in] hit_ft
+ *	Flow table to go to on hit.
+ * @param[in] miss_ft
+ *	Flow table to go to on miss.
+ * @param[in] min
+ *	Minimal value of the field to be considered as hit.
+ * @param[in] max
+ *	Maximal value of the field to be considered as hit.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
+				       u32 field,
+				       struct mlx5_flow_table *hit_ft,
+				       struct mlx5_flow_table *miss_ft,
+				       u32 min, u32 max, u32 flags);
+
+/* Create direct rule flow sampler action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] sampler_id
+ *	Flow sampler object ID.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx,
+				   u32 sampler_id, u32 flags);
+
+/* Create direct rule goto vport action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] vport_num
+ *	Destination vport number.
+ * @param[in] vhca_id_valid
+ *	Tells if the vhca_id parameter is valid.
+ * @param[in] vhca_id
+ *	VHCA ID of the destination vport.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_dest_vport(struct mlx5hws_context *ctx,
+				 u16 vport_num,
+				 bool vhca_id_valid,
+				 u16 vhca_id,
+				 u32 flags);
+
+/* Create direct rule TAG action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_tag(struct mlx5hws_context *ctx,
+			  u32 flags);
+
+/* Create direct rule counter action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] obj_id
+ *	Direct rule counter object ID.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_counter(struct mlx5hws_context *ctx,
+			      u32 obj_id,
+			      u32 flags);
+
+/* Create direct rule reformat action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] reformat_type
+ *	Type of reformat prefixed with MLX5HWS_ACTION_TYP_REFORMAT.
+ * @param[in] num_of_hdrs
+ *	Number of provided headers in "hdrs" array.
+ * @param[in] hdrs
+ *	Headers array containing header information.
+ * @param[in] log_bulk_size
+ *	Number of unique values used with this reformat.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_reformat(struct mlx5hws_context *ctx,
+			       enum mlx5hws_action_type reformat_type,
+			       u8 num_of_hdrs,
+			       struct mlx5hws_action_reformat_header *hdrs,
+			       u32 log_bulk_size,
+			       u32 flags);
+
+/* Create direct rule modify header action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] num_of_patterns
+ *	Number of provided patterns in "patterns" array.
+ * @param[in] patterns
+ *	Patterns array containing pattern information.
+ * @param[in] log_bulk_size
+ *	Number of unique values used with this pattern.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_modify_header(struct mlx5hws_context *ctx,
+				    u8 num_of_patterns,
+				    struct mlx5hws_action_mh_pattern *patterns,
+				    u32 log_bulk_size,
+				    u32 flags);
+
+/* Create direct rule ASO flow meter action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] obj_id
+ *	ASO object ID.
+ * @param[in] return_reg_c
+ *	Copy the ASO object value into this reg_c, after a packet hits a rule with this ASO object.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_aso_meter(struct mlx5hws_context *ctx,
+				u32 obj_id,
+				u8 return_reg_c,
+				u32 flags);
+
+/* Create direct rule pop vlan action.
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_pop_vlan(struct mlx5hws_context *ctx, u32 flags);
+
+/* Create direct rule push vlan action.
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_push_vlan(struct mlx5hws_context *ctx, u32 flags);
+
+/* Create a dest array action, this action can duplicate packets and forward to
+ * multiple destinations in the destination list.
+ * @param[in] ctx
+ *     The context in which the new action will be created.
+ * @param[in] num_dest
+ *     The number of dests attributes.
+ * @param[in] dests
+ *     The destination array. Each contains a destination action and can have
+ *     additional actions.
+ * @param[in] ignore_flow_level
+ *     Boolean that says whether to turn on 'ignore_flow_level' for this dest.
+ * @param[in] flow_source
+ *     Source port of the traffic for this actions.
+ * @param[in] flags
+ *     Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
+				 size_t num_dest,
+				 struct mlx5hws_action_dest_attr *dests,
+				 bool ignore_flow_level,
+				 u32 flow_source,
+				 u32 flags);
+
+/* Create insert header action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] num_of_hdrs
+ *	Number of provided headers in "hdrs" array.
+ * @param[in] hdrs
+ *	Headers array containing header information.
+ * @param[in] log_bulk_size
+ *	Number of unique values used with this insert header.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_insert_header(struct mlx5hws_context *ctx,
+				    u8 num_of_hdrs,
+				    struct mlx5hws_action_insert_header *hdrs,
+				    u32 log_bulk_size,
+				    u32 flags);
+
+/* Create remove header action.
+ *
+ * @param[in] ctx
+ *	The context in which the new action will be created.
+ * @param[in] attr
+ *	attributes: specifies the remove header type, PRM start anchor and
+ *	the PRM end anchor or the PRM start anchor and remove size in bytes.
+ * @param[in] flags
+ *	Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_remove_header(struct mlx5hws_context *ctx,
+				    struct mlx5hws_action_remove_header_attr *attr,
+				    u32 flags);
+
+/* Create direct rule LAST action.
+ *
+ * @param[in] ctx
+ *     The context in which the new action will be created.
+ * @param[in] flags
+ *     Action creation flags. (enum mlx5hws_action_flags)
+ * @return pointer to mlx5hws_action on success NULL otherwise.
+ */
+struct mlx5hws_action *
+mlx5hws_action_create_last(struct mlx5hws_context *ctx, u32 flags);
+
+/* Destroy direct rule action.
+ *
+ * @param[in] action
+ *	The action to destroy.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_action_destroy(struct mlx5hws_action *action);
+
+enum mlx5hws_flow_op_status {
+	MLX5HWS_FLOW_OP_SUCCESS,
+	MLX5HWS_FLOW_OP_ERROR,
+};
+
+struct mlx5hws_flow_op_result {
+	enum mlx5hws_flow_op_status status;
+	void *user_data;
+};
+
+/* Poll queue for rule creation and deletions completions.
+ *
+ * @param[in] ctx
+ *	The context to which the queue belong to.
+ * @param[in] queue_id
+ *	The id of the queue to poll.
+ * @param[in, out] res
+ *	Completion array.
+ * @param[in] res_nb
+ *	Maximum number of results to return.
+ * @return negative number on failure, the number of completions otherwise.
+ */
+int mlx5hws_send_queue_poll(struct mlx5hws_context *ctx,
+			    u16 queue_id,
+			    struct mlx5hws_flow_op_result res[],
+			    u32 res_nb);
+
+/* Perform an action on the queue
+ *
+ * @param[in] ctx
+ *	The context to which the queue belong to.
+ * @param[in] queue_id
+ *	The id of the queue to perform the action on.
+ * @param[in] actions
+ *	Actions to perform on the queue. (enum mlx5hws_send_queue_actions)
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_send_queue_action(struct mlx5hws_context *ctx,
+			      u16 queue_id,
+			      u32 actions);
+
+/* Dump HWS info
+ *
+ * @param[in] ctx
+ *	The context which to dump the info from.
+ * @return zero on success non zero otherwise.
+ */
+int mlx5hws_debug_dump(struct mlx5hws_context *ctx);
+
+struct mlx5hws_bwc_matcher;
+struct mlx5hws_bwc_rule;
+
+struct mlx5hws_match_parameters {
+	size_t match_sz;
+	u32 *match_buf; /* Device spec format */
+};
+
+/* Create a new BWC direct rule matcher.
+ * This function does the following:
+ *   - creates match template based on flow items
+ *   - creates an empty action template
+ *   - creates a usual mlx5hws_matcher with these mt and at, setting
+ *     its size to minimal
+ * Notes:
+ *   - table->ctx must have BWC support
+ *   - complex rules are not supported
+ *
+ * @param[in] table
+ *	The table in which the new matcher will be opened
+ * @param[in] priority
+ *	Priority for this BWC matcher
+ * @param[in] match_criteria_enable
+ *	Bitmask that defines matching criteria
+ * @param[in] mask
+ *	Match parameters
+ * @return pointer to mlx5hws_bwc_matcher on success or NULL otherwise.
+ */
+struct mlx5hws_bwc_matcher *
+mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
+			   u32 priority,
+			   u8 match_criteria_enable,
+			   struct mlx5hws_match_parameters *mask);
+
+/* Destroy BWC direct rule matcher.
+ *
+ * @param[in] bwc_matcher
+ *	Matcher to destroy
+ * @return zero on success, non zero otherwise
+ */
+int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher);
+
+/* Create a new BWC rule.
+ * Unlike the usual rule creation function, this one is blocking: when the
+ * function returns, the rule is written to its place (no need to poll).
+ * This function does the following:
+ *   - finds matching action template based on the provided rule_actions, or
+ *     creates new action template if matching action template doesn't exist
+ *   - updates corresponding BWC matcher stats
+ *   - if needed, the function performs rehash:
+ *       - creates a new matcher based on mt, at, new_sz
+ *       - moves all the existing matcher rules to the new matcher
+ *       - removes the old matcher
+ *   - inserts new rule
+ *   - polls till completion is received
+ * Notes:
+ *   - matcher->tbl->ctx must have BWC support
+ *   - separate BWC ctx queues are used
+ *
+ * @param[in] bwc_matcher
+ *	The BWC matcher in which the new rule will be created.
+ * @param[in] params
+ *	Match perameters
+ * @param[in] flow_source
+ *	Flow source for this rule
+ * @param[in] rule_actions
+ *	Rule action to be executed on match
+ * @return valid BWC rule handle on success, NULL otherwise
+ */
+struct mlx5hws_bwc_rule *
+mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
+			struct mlx5hws_match_parameters *params,
+			u32 flow_source,
+			struct mlx5hws_rule_action rule_actions[]);
+
+/* Destroy BWC direct rule.
+ *
+ * @param[in] bwc_rule
+ *	Rule to destroy
+ * @return zero on success, non zero otherwise
+ */
+int mlx5hws_bwc_rule_destroy(struct mlx5hws_bwc_rule *bwc_rule);
+
+/* Update actions on an existing BWC rule.
+ *
+ * @param[in] bwc_rule
+ *	Rule to update
+ * @param[in] rule_actions
+ *	Rule action to update with
+ * @return zero on successful update, non zero otherwise.
+ */
+int mlx5hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
+				   struct mlx5hws_rule_action rule_actions[]);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h
index 458bc31be6ac..5643be1cd5bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_internal.h
@@ -5,13 +5,13 @@
 #define MLX5HWS_INTERNAL_H_
 
 #include <linux/mlx5/transobj.h>
-
-#include "../dr_types.h"
+#include <linux/mlx5/vport.h>
+#include "fs_core.h"
+#include "wq.h"
+#include "lib/mlx5.h"
 
 #include "mlx5hws_prm.h"
-
 #include "mlx5hws.h"
-
 #include "mlx5hws_pool.h"
 #include "mlx5hws_vport.h"
 #include "mlx5hws_context.h"
-- 
cgit v1.3-3-g829e


From 080d72f471c86f8906845bc822051f5790d0a90d Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Wed, 4 Sep 2024 17:47:43 +0200
Subject: libeth: add Tx buffer completion helpers

Software-side Tx buffers for storing DMA, frame size, skb pointers etc.
are pretty much generic and every driver defines them the same way. The
same can be said for software Tx completions -- same napi_consume_skb()s
and all that...
Add a couple simple wrappers for doing that to stop repeating the old
tale at least within the Intel code. Drivers are free to use 'priv'
member at the end of the structure.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/net/libeth/tx.h    | 129 +++++++++++++++++++++++++++++++++++++++++++++
 include/net/libeth/types.h |  25 +++++++++
 2 files changed, 154 insertions(+)
 create mode 100644 include/net/libeth/tx.h
 create mode 100644 include/net/libeth/types.h

diff --git a/include/net/libeth/tx.h b/include/net/libeth/tx.h
new file mode 100644
index 000000000000..35614f9523f6
--- /dev/null
+++ b/include/net/libeth/tx.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBETH_TX_H
+#define __LIBETH_TX_H
+
+#include <linux/skbuff.h>
+
+#include <net/libeth/types.h>
+
+/* Tx buffer completion */
+
+/**
+ * enum libeth_sqe_type - type of &libeth_sqe to act on Tx completion
+ * @LIBETH_SQE_EMPTY: unused/empty, no action required
+ * @LIBETH_SQE_CTX: context descriptor with empty SQE, no action required
+ * @LIBETH_SQE_SLAB: kmalloc-allocated buffer, unmap and kfree()
+ * @LIBETH_SQE_FRAG: mapped skb frag, only unmap DMA
+ * @LIBETH_SQE_SKB: &sk_buff, unmap and napi_consume_skb(), update stats
+ */
+enum libeth_sqe_type {
+	LIBETH_SQE_EMPTY		= 0U,
+	LIBETH_SQE_CTX,
+	LIBETH_SQE_SLAB,
+	LIBETH_SQE_FRAG,
+	LIBETH_SQE_SKB,
+};
+
+/**
+ * struct libeth_sqe - represents a Send Queue Element / Tx buffer
+ * @type: type of the buffer, see the enum above
+ * @rs_idx: index of the last buffer from the batch this one was sent in
+ * @raw: slab buffer to free via kfree()
+ * @skb: &sk_buff to consume
+ * @dma: DMA address to unmap
+ * @len: length of the mapped region to unmap
+ * @nr_frags: number of frags in the frame this buffer belongs to
+ * @packets: number of physical packets sent for this frame
+ * @bytes: number of physical bytes sent for this frame
+ * @priv: driver-private scratchpad
+ */
+struct libeth_sqe {
+	enum libeth_sqe_type		type:32;
+	u32				rs_idx;
+
+	union {
+		void				*raw;
+		struct sk_buff			*skb;
+	};
+
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+
+	u32				nr_frags;
+	u32				packets;
+	u32				bytes;
+
+	unsigned long			priv;
+} __aligned_largest;
+
+/**
+ * LIBETH_SQE_CHECK_PRIV - check the driver's private SQE data
+ * @p: type or name of the object the driver wants to fit into &libeth_sqe
+ *
+ * Make sure the driver's private data fits into libeth_sqe::priv. To be used
+ * right after its declaration.
+ */
+#define LIBETH_SQE_CHECK_PRIV(p)					  \
+	static_assert(sizeof(p) <= sizeof_field(struct libeth_sqe, priv))
+
+/**
+ * struct libeth_cq_pp - completion queue poll params
+ * @dev: &device to perform DMA unmapping
+ * @ss: onstack NAPI stats to fill
+ * @napi: whether it's called from the NAPI context
+ *
+ * libeth uses this structure to access objects needed for performing full
+ * Tx complete operation without passing lots of arguments and change the
+ * prototypes each time a new one is added.
+ */
+struct libeth_cq_pp {
+	struct device			*dev;
+	struct libeth_sq_napi_stats	*ss;
+
+	bool				napi;
+};
+
+/**
+ * libeth_tx_complete - perform Tx completion for one SQE
+ * @sqe: SQE to complete
+ * @cp: poll params
+ *
+ * Do Tx complete for all the types of buffers, incl. freeing, unmapping,
+ * updating the stats etc.
+ */
+static inline void libeth_tx_complete(struct libeth_sqe *sqe,
+				      const struct libeth_cq_pp *cp)
+{
+	switch (sqe->type) {
+	case LIBETH_SQE_EMPTY:
+		return;
+	case LIBETH_SQE_SKB:
+	case LIBETH_SQE_FRAG:
+	case LIBETH_SQE_SLAB:
+		dma_unmap_page(cp->dev, dma_unmap_addr(sqe, dma),
+			       dma_unmap_len(sqe, len), DMA_TO_DEVICE);
+		break;
+	default:
+		break;
+	}
+
+	switch (sqe->type) {
+	case LIBETH_SQE_SKB:
+		cp->ss->packets += sqe->packets;
+		cp->ss->bytes += sqe->bytes;
+
+		napi_consume_skb(sqe->skb, cp->napi);
+		break;
+	case LIBETH_SQE_SLAB:
+		kfree(sqe->raw);
+		break;
+	default:
+		break;
+	}
+
+	sqe->type = LIBETH_SQE_EMPTY;
+}
+
+#endif /* __LIBETH_TX_H */
diff --git a/include/net/libeth/types.h b/include/net/libeth/types.h
new file mode 100644
index 000000000000..603825e45133
--- /dev/null
+++ b/include/net/libeth/types.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBETH_TYPES_H
+#define __LIBETH_TYPES_H
+
+#include <linux/types.h>
+
+/**
+ * struct libeth_sq_napi_stats - "hot" counters to update in Tx completion loop
+ * @packets: completed frames counter
+ * @bytes: sum of bytes of completed frames above
+ * @raw: alias to access all the fields as an array
+ */
+struct libeth_sq_napi_stats {
+	union {
+		struct {
+							u32 packets;
+							u32 bytes;
+		};
+		DECLARE_FLEX_ARRAY(u32, raw);
+	};
+};
+
+#endif /* __LIBETH_TYPES_H */
-- 
cgit v1.3-3-g829e


From d9028db618a63e4bbe63eb56c0b0db2b4cb924bc Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Wed, 4 Sep 2024 17:47:44 +0200
Subject: idpf: convert to libeth Tx buffer completion

&idpf_tx_buffer is almost identical to the previous generations, as well
as the way it's handled. Moreover, relying on dma_unmap_addr() and
!!buf->skb instead of explicit defining of buffer's type was never good.
Use the newly added libeth helpers to do it properly and reduce the
copy-paste around the Tx code.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/idpf/idpf_singleq_txrx.c    |  82 +++------
 drivers/net/ethernet/intel/idpf/idpf_txrx.c        | 205 ++++++++-------------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h        |  50 +----
 3 files changed, 105 insertions(+), 232 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index fe64febf7436..98f26a4b835f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include <net/libeth/rx.h>
+#include <net/libeth/tx.h>
 
 #include "idpf.h"
 
@@ -224,6 +225,7 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
 		dma_unmap_addr_set(tx_buf, dma, dma);
+		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* align size to end of page */
 		max_data += -dma & (IDPF_TX_MAX_READ_REQ_SIZE - 1);
@@ -245,6 +247,8 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 				i = 0;
 			}
 
+			tx_q->tx_buf[i].type = LIBETH_SQE_EMPTY;
+
 			dma += max_data;
 			size -= max_data;
 
@@ -282,13 +286,13 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 	tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets,
 						  size, td_tag);
 
-	IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i);
+	first->type = LIBETH_SQE_SKB;
+	first->rs_idx = i;
 
-	/* set next_to_watch value indicating a packet is present */
-	first->next_to_watch = tx_desc;
+	IDPF_SINGLEQ_BUMP_RING_IDX(tx_q, i);
 
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
-	netdev_tx_sent_queue(nq, first->bytecount);
+	netdev_tx_sent_queue(nq, first->bytes);
 
 	idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
 }
@@ -306,8 +310,7 @@ idpf_tx_singleq_get_ctx_desc(struct idpf_tx_queue *txq)
 	struct idpf_base_tx_ctx_desc *ctx_desc;
 	int ntu = txq->next_to_use;
 
-	memset(&txq->tx_buf[ntu], 0, sizeof(struct idpf_tx_buf));
-	txq->tx_buf[ntu].ctx_entry = true;
+	txq->tx_buf[ntu].type = LIBETH_SQE_CTX;
 
 	ctx_desc = &txq->base_ctx[ntu];
 
@@ -396,11 +399,11 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 	first->skb = skb;
 
 	if (tso) {
-		first->gso_segs = offload.tso_segs;
-		first->bytecount = skb->len + ((first->gso_segs - 1) * offload.tso_hdr_len);
+		first->packets = offload.tso_segs;
+		first->bytes = skb->len + ((first->packets - 1) * offload.tso_hdr_len);
 	} else {
-		first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
-		first->gso_segs = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
+		first->packets = 1;
 	}
 	idpf_tx_singleq_map(tx_q, first, &offload);
 
@@ -420,10 +423,15 @@ out_drop:
 static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 				  int *cleaned)
 {
-	unsigned int total_bytes = 0, total_pkts = 0;
+	struct libeth_sq_napi_stats ss = { };
 	struct idpf_base_tx_desc *tx_desc;
 	u32 budget = tx_q->clean_budget;
 	s16 ntc = tx_q->next_to_clean;
+	struct libeth_cq_pp cp = {
+		.dev	= tx_q->dev,
+		.ss	= &ss,
+		.napi	= napi_budget,
+	};
 	struct idpf_netdev_priv *np;
 	struct idpf_tx_buf *tx_buf;
 	struct netdev_queue *nq;
@@ -441,47 +449,23 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 		 * such. We can skip this descriptor since there is no buffer
 		 * to clean.
 		 */
-		if (tx_buf->ctx_entry) {
-			/* Clear this flag here to avoid stale flag values when
-			 * this buffer is used for actual data in the future.
-			 * There are cases where the tx_buf struct / the flags
-			 * field will not be cleared before being reused.
-			 */
-			tx_buf->ctx_entry = false;
+		if (unlikely(tx_buf->type <= LIBETH_SQE_CTX)) {
+			tx_buf->type = LIBETH_SQE_EMPTY;
 			goto fetch_next_txq_desc;
 		}
 
-		/* if next_to_watch is not set then no work pending */
-		eop_desc = (struct idpf_base_tx_desc *)tx_buf->next_to_watch;
-		if (!eop_desc)
-			break;
-
-		/* prevent any other reads prior to eop_desc */
+		/* prevent any other reads prior to type */
 		smp_rmb();
 
+		eop_desc = &tx_q->base_tx[tx_buf->rs_idx];
+
 		/* if the descriptor isn't done, no work yet to do */
 		if (!(eop_desc->qw1 &
 		      cpu_to_le64(IDPF_TX_DESC_DTYPE_DESC_DONE)))
 			break;
 
-		/* clear next_to_watch to prevent false hangs */
-		tx_buf->next_to_watch = NULL;
-
 		/* update the statistics for this packet */
-		total_bytes += tx_buf->bytecount;
-		total_pkts += tx_buf->gso_segs;
-
-		napi_consume_skb(tx_buf->skb, napi_budget);
-
-		/* unmap skb header data */
-		dma_unmap_single(tx_q->dev,
-				 dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len),
-				 DMA_TO_DEVICE);
-
-		/* clear tx_buf data */
-		tx_buf->skb = NULL;
-		dma_unmap_len_set(tx_buf, len, 0);
+		libeth_tx_complete(tx_buf, &cp);
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
@@ -495,13 +479,7 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 			}
 
 			/* unmap any remaining paged data */
-			if (dma_unmap_len(tx_buf, len)) {
-				dma_unmap_page(tx_q->dev,
-					       dma_unmap_addr(tx_buf, dma),
-					       dma_unmap_len(tx_buf, len),
-					       DMA_TO_DEVICE);
-				dma_unmap_len_set(tx_buf, len, 0);
-			}
+			libeth_tx_complete(tx_buf, &cp);
 		}
 
 		/* update budget only if we did something */
@@ -521,11 +499,11 @@ fetch_next_txq_desc:
 	ntc += tx_q->desc_count;
 	tx_q->next_to_clean = ntc;
 
-	*cleaned += total_pkts;
+	*cleaned += ss.packets;
 
 	u64_stats_update_begin(&tx_q->stats_sync);
-	u64_stats_add(&tx_q->q_stats.packets, total_pkts);
-	u64_stats_add(&tx_q->q_stats.bytes, total_bytes);
+	u64_stats_add(&tx_q->q_stats.packets, ss.packets);
+	u64_stats_add(&tx_q->q_stats.bytes, ss.bytes);
 	u64_stats_update_end(&tx_q->stats_sync);
 
 	np = netdev_priv(tx_q->netdev);
@@ -533,7 +511,7 @@ fetch_next_txq_desc:
 
 	dont_wake = np->state != __IDPF_VPORT_UP ||
 		    !netif_carrier_ok(tx_q->netdev);
-	__netif_txq_completed_wake(nq, total_pkts, total_bytes,
+	__netif_txq_completed_wake(nq, ss.packets, ss.bytes,
 				   IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH,
 				   dont_wake);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 585c3dadd9bf..76479c4f3fec 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2,10 +2,19 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include <net/libeth/rx.h>
+#include <net/libeth/tx.h>
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
 
+struct idpf_tx_stash {
+	struct hlist_node hlist;
+	struct libeth_sqe buf;
+};
+
+#define idpf_tx_buf_compl_tag(buf)	(*(int *)&(buf)->priv)
+LIBETH_SQE_CHECK_PRIV(int);
+
 static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
 			       unsigned int count);
 
@@ -60,41 +69,18 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	}
 }
 
-/**
- * idpf_tx_buf_rel - Release a Tx buffer
- * @tx_q: the queue that owns the buffer
- * @tx_buf: the buffer to free
- */
-static void idpf_tx_buf_rel(struct idpf_tx_queue *tx_q,
-			    struct idpf_tx_buf *tx_buf)
-{
-	if (tx_buf->skb) {
-		if (dma_unmap_len(tx_buf, len))
-			dma_unmap_single(tx_q->dev,
-					 dma_unmap_addr(tx_buf, dma),
-					 dma_unmap_len(tx_buf, len),
-					 DMA_TO_DEVICE);
-		dev_kfree_skb_any(tx_buf->skb);
-	} else if (dma_unmap_len(tx_buf, len)) {
-		dma_unmap_page(tx_q->dev,
-			       dma_unmap_addr(tx_buf, dma),
-			       dma_unmap_len(tx_buf, len),
-			       DMA_TO_DEVICE);
-	}
-
-	tx_buf->next_to_watch = NULL;
-	tx_buf->skb = NULL;
-	tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
-	dma_unmap_len_set(tx_buf, len, 0);
-}
-
 /**
  * idpf_tx_buf_rel_all - Free any empty Tx buffers
  * @txq: queue to be cleaned
  */
 static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 {
+	struct libeth_sq_napi_stats ss = { };
 	struct idpf_buf_lifo *buf_stack;
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
 	u16 i;
 
 	/* Buffers already cleared, nothing to do */
@@ -103,7 +89,7 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 
 	/* Free all the Tx buffer sk_buffs */
 	for (i = 0; i < txq->desc_count; i++)
-		idpf_tx_buf_rel(txq, &txq->tx_buf[i]);
+		libeth_tx_complete(&txq->tx_buf[i], &cp);
 
 	kfree(txq->tx_buf);
 	txq->tx_buf = NULL;
@@ -203,10 +189,6 @@ static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
 	if (!tx_q->tx_buf)
 		return -ENOMEM;
 
-	/* Initialize tx_bufs with invalid completion tags */
-	for (i = 0; i < tx_q->desc_count; i++)
-		tx_q->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
-
 	if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
 		return 0;
 
@@ -1655,37 +1637,6 @@ static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
 	wake_up(&vport->sw_marker_wq);
 }
 
-/**
- * idpf_tx_splitq_clean_hdr - Clean TX buffer resources for header portion of
- * packet
- * @tx_q: tx queue to clean buffer from
- * @tx_buf: buffer to be cleaned
- * @cleaned: pointer to stats struct to track cleaned packets/bytes
- * @napi_budget: Used to determine if we are in netpoll
- */
-static void idpf_tx_splitq_clean_hdr(struct idpf_tx_queue *tx_q,
-				     struct idpf_tx_buf *tx_buf,
-				     struct idpf_cleaned_stats *cleaned,
-				     int napi_budget)
-{
-	napi_consume_skb(tx_buf->skb, napi_budget);
-
-	if (dma_unmap_len(tx_buf, len)) {
-		dma_unmap_single(tx_q->dev,
-				 dma_unmap_addr(tx_buf, dma),
-				 dma_unmap_len(tx_buf, len),
-				 DMA_TO_DEVICE);
-
-		dma_unmap_len_set(tx_buf, len, 0);
-	}
-
-	/* clear tx_buf data */
-	tx_buf->skb = NULL;
-
-	cleaned->bytes += tx_buf->bytecount;
-	cleaned->packets += tx_buf->gso_segs;
-}
-
 /**
  * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
  * out of order completions
@@ -1696,28 +1647,25 @@ static void idpf_tx_splitq_clean_hdr(struct idpf_tx_queue *tx_q,
  */
 static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
 				       u16 compl_tag,
-				       struct idpf_cleaned_stats *cleaned,
+				       struct libeth_sq_napi_stats *cleaned,
 				       int budget)
 {
 	struct idpf_tx_stash *stash;
 	struct hlist_node *tmp_buf;
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= cleaned,
+		.napi	= budget,
+	};
 
 	/* Buffer completion */
 	hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
 				    hlist, compl_tag) {
-		if (unlikely(stash->buf.compl_tag != (int)compl_tag))
+		if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) !=
+			     (int)compl_tag))
 			continue;
 
-		if (stash->buf.skb) {
-			idpf_tx_splitq_clean_hdr(txq, &stash->buf, cleaned,
-						 budget);
-		} else if (dma_unmap_len(&stash->buf, len)) {
-			dma_unmap_page(txq->dev,
-				       dma_unmap_addr(&stash->buf, dma),
-				       dma_unmap_len(&stash->buf, len),
-				       DMA_TO_DEVICE);
-			dma_unmap_len_set(&stash->buf, len, 0);
-		}
+		libeth_tx_complete(&stash->buf, &cp);
 
 		/* Push shadow buf back onto stack */
 		idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
@@ -1737,8 +1685,7 @@ static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
 {
 	struct idpf_tx_stash *stash;
 
-	if (unlikely(!dma_unmap_addr(tx_buf, dma) &&
-		     !dma_unmap_len(tx_buf, len)))
+	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX))
 		return 0;
 
 	stash = idpf_buf_lifo_pop(&txq->stash->buf_stack);
@@ -1751,20 +1698,18 @@ static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
 
 	/* Store buffer params in shadow buffer */
 	stash->buf.skb = tx_buf->skb;
-	stash->buf.bytecount = tx_buf->bytecount;
-	stash->buf.gso_segs = tx_buf->gso_segs;
+	stash->buf.bytes = tx_buf->bytes;
+	stash->buf.packets = tx_buf->packets;
+	stash->buf.type = tx_buf->type;
 	dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma));
 	dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len));
-	stash->buf.compl_tag = tx_buf->compl_tag;
+	idpf_tx_buf_compl_tag(&stash->buf) = idpf_tx_buf_compl_tag(tx_buf);
 
 	/* Add buffer to buf_hash table to be freed later */
 	hash_add(txq->stash->sched_buf_hash, &stash->hlist,
-		 stash->buf.compl_tag);
-
-	memset(tx_buf, 0, sizeof(struct idpf_tx_buf));
+		 idpf_tx_buf_compl_tag(&stash->buf));
 
-	/* Reinitialize buf_id portion of tag */
-	tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
+	tx_buf->type = LIBETH_SQE_EMPTY;
 
 	return 0;
 }
@@ -1800,12 +1745,17 @@ do {								\
  */
 static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				 int napi_budget,
-				 struct idpf_cleaned_stats *cleaned,
+				 struct libeth_sq_napi_stats *cleaned,
 				 bool descs_only)
 {
 	union idpf_tx_flex_desc *next_pending_desc = NULL;
 	union idpf_tx_flex_desc *tx_desc;
 	s16 ntc = tx_q->next_to_clean;
+	struct libeth_cq_pp cp = {
+		.dev	= tx_q->dev,
+		.ss	= cleaned,
+		.napi	= napi_budget,
+	};
 	struct idpf_tx_buf *tx_buf;
 
 	tx_desc = &tx_q->flex_tx[ntc];
@@ -1821,13 +1771,10 @@ static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 		 * invalid completion tag since no buffer was used.  We can
 		 * skip this descriptor since there is no buffer to clean.
 		 */
-		if (unlikely(tx_buf->compl_tag == IDPF_SPLITQ_TX_INVAL_COMPL_TAG))
+		if (tx_buf->type <= LIBETH_SQE_CTX)
 			goto fetch_next_txq_desc;
 
-		eop_desc = (union idpf_tx_flex_desc *)tx_buf->next_to_watch;
-
-		/* clear next_to_watch to prevent false hangs */
-		tx_buf->next_to_watch = NULL;
+		eop_desc = &tx_q->flex_tx[tx_buf->rs_idx];
 
 		if (descs_only) {
 			if (idpf_stash_flow_sch_buffers(tx_q, tx_buf))
@@ -1844,8 +1791,7 @@ static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				}
 			}
 		} else {
-			idpf_tx_splitq_clean_hdr(tx_q, tx_buf, cleaned,
-						 napi_budget);
+			libeth_tx_complete(tx_buf, &cp);
 
 			/* unmap remaining buffers */
 			while (tx_desc != eop_desc) {
@@ -1853,13 +1799,7 @@ static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 							      tx_desc, tx_buf);
 
 				/* unmap any remaining paged data */
-				if (dma_unmap_len(tx_buf, len)) {
-					dma_unmap_page(tx_q->dev,
-						       dma_unmap_addr(tx_buf, dma),
-						       dma_unmap_len(tx_buf, len),
-						       DMA_TO_DEVICE);
-					dma_unmap_len_set(tx_buf, len, 0);
-				}
+				libeth_tx_complete(tx_buf, &cp);
 			}
 		}
 
@@ -1895,30 +1835,26 @@ do {							\
  * this completion tag.
  */
 static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
-				   struct idpf_cleaned_stats *cleaned,
+				   struct libeth_sq_napi_stats *cleaned,
 				   int budget)
 {
 	u16 idx = compl_tag & txq->compl_tag_bufid_m;
 	struct idpf_tx_buf *tx_buf = NULL;
 	u16 ntc = txq->next_to_clean;
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= cleaned,
+		.napi	= budget,
+	};
 	u16 num_descs_cleaned = 0;
 	u16 orig_idx = idx;
 
 	tx_buf = &txq->tx_buf[idx];
+	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX))
+		return false;
 
-	while (tx_buf->compl_tag == (int)compl_tag) {
-		if (tx_buf->skb) {
-			idpf_tx_splitq_clean_hdr(txq, tx_buf, cleaned, budget);
-		} else if (dma_unmap_len(tx_buf, len)) {
-			dma_unmap_page(txq->dev,
-				       dma_unmap_addr(tx_buf, dma),
-				       dma_unmap_len(tx_buf, len),
-				       DMA_TO_DEVICE);
-			dma_unmap_len_set(tx_buf, len, 0);
-		}
-
-		memset(tx_buf, 0, sizeof(struct idpf_tx_buf));
-		tx_buf->compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
+	while (idpf_tx_buf_compl_tag(tx_buf) == (int)compl_tag) {
+		libeth_tx_complete(tx_buf, &cp);
 
 		num_descs_cleaned++;
 		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
@@ -1965,7 +1901,7 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
  */
 static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 					 struct idpf_splitq_tx_compl_desc *desc,
-					 struct idpf_cleaned_stats *cleaned,
+					 struct libeth_sq_napi_stats *cleaned,
 					 int budget)
 {
 	u16 compl_tag;
@@ -2008,7 +1944,7 @@ static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
 	ntc -= complq->desc_count;
 
 	do {
-		struct idpf_cleaned_stats cleaned_stats = { };
+		struct libeth_sq_napi_stats cleaned_stats = { };
 		struct idpf_tx_queue *tx_q;
 		int rel_tx_qid;
 		u16 hw_head;
@@ -2307,6 +2243,12 @@ unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
 			   struct idpf_tx_buf *first, u16 idx)
 {
+	struct libeth_sq_napi_stats ss = { };
+	struct libeth_cq_pp cp = {
+		.dev	= txq->dev,
+		.ss	= &ss,
+	};
+
 	u64_stats_update_begin(&txq->stats_sync);
 	u64_stats_inc(&txq->q_stats.dma_map_errs);
 	u64_stats_update_end(&txq->stats_sync);
@@ -2316,7 +2258,7 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
 		struct idpf_tx_buf *tx_buf;
 
 		tx_buf = &txq->tx_buf[idx];
-		idpf_tx_buf_rel(txq, tx_buf);
+		libeth_tx_complete(tx_buf, &cp);
 		if (tx_buf == first)
 			break;
 		if (idx == 0)
@@ -2405,7 +2347,8 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 		if (dma_mapping_error(tx_q->dev, dma))
 			return idpf_tx_dma_map_error(tx_q, skb, first, i);
 
-		tx_buf->compl_tag = params->compl_tag;
+		idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
+		tx_buf->type = LIBETH_SQE_FRAG;
 
 		/* record length, and DMA address */
 		dma_unmap_len_set(tx_buf, len, size);
@@ -2479,8 +2422,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			 * simply pass over these holes and finish cleaning the
 			 * rest of the packet.
 			 */
-			memset(&tx_q->tx_buf[i], 0, sizeof(struct idpf_tx_buf));
-			tx_q->tx_buf[i].compl_tag = params->compl_tag;
+			tx_q->tx_buf[i].type = LIBETH_SQE_EMPTY;
 
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
@@ -2525,19 +2467,19 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	/* record SW timestamp if HW timestamp is not available */
 	skb_tx_timestamp(skb);
 
+	first->type = LIBETH_SQE_SKB;
+
 	/* write last descriptor with RS and EOP bits */
+	first->rs_idx = i;
 	td_cmd |= params->eop_cmd;
 	idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
 	i = idpf_tx_splitq_bump_ntu(tx_q, i);
 
-	/* set next_to_watch value indicating a packet is present */
-	first->next_to_watch = tx_desc;
-
 	tx_q->txq_grp->num_completions_pending++;
 
 	/* record bytecount for BQL */
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
-	netdev_tx_sent_queue(nq, first->bytecount);
+	netdev_tx_sent_queue(nq, first->bytes);
 
 	idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
 }
@@ -2737,8 +2679,7 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 	struct idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
-	memset(&txq->tx_buf[i], 0, sizeof(struct idpf_tx_buf));
-	txq->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
+	txq->tx_buf[i].type = LIBETH_SQE_CTX;
 
 	/* grab the next descriptor */
 	desc = &txq->flex_ctx[i];
@@ -2822,12 +2763,12 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 	first->skb = skb;
 
 	if (tso) {
-		first->gso_segs = tx_params.offload.tso_segs;
-		first->bytecount = skb->len +
-			((first->gso_segs - 1) * tx_params.offload.tso_hdr_len);
+		first->packets = tx_params.offload.tso_segs;
+		first->bytes = skb->len +
+			((first->packets - 1) * tx_params.offload.tso_hdr_len);
 	} else {
-		first->gso_segs = 1;
-		first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
+		first->packets = 1;
+		first->bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 	}
 
 	if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 6215dbee5546..1b20cd96c613 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -131,7 +131,6 @@ do {								\
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
 #define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
-#define IDPF_SPLITQ_TX_INVAL_COMPL_TAG	-1
 /* Adjust the generation for the completion tag and wrap if necessary */
 #define IDPF_TX_ADJ_COMPL_TAG_GEN(txq) \
 	((++(txq)->compl_tag_cur_gen) >= (txq)->compl_tag_gen_max ? \
@@ -149,47 +148,7 @@ union idpf_tx_flex_desc {
 	struct idpf_flex_tx_sched_desc flow; /* flow based scheduling */
 };
 
-/**
- * struct idpf_tx_buf
- * @next_to_watch: Next descriptor to clean
- * @skb: Pointer to the skb
- * @dma: DMA address
- * @len: DMA length
- * @bytecount: Number of bytes
- * @gso_segs: Number of GSO segments
- * @compl_tag: Splitq only, unique identifier for a buffer. Used to compare
- *	       with completion tag returned in buffer completion event.
- *	       Because the completion tag is expected to be the same in all
- *	       data descriptors for a given packet, and a single packet can
- *	       span multiple buffers, we need this field to track all
- *	       buffers associated with this completion tag independently of
- *	       the buf_id. The tag consists of a N bit buf_id and M upper
- *	       order "generation bits". See compl_tag_bufid_m and
- *	       compl_tag_gen_s in struct idpf_queue. We'll use a value of -1
- *	       to indicate the tag is not valid.
- * @ctx_entry: Singleq only. Used to indicate the corresponding entry
- *	       in the descriptor ring was used for a context descriptor and
- *	       this buffer entry should be skipped.
- */
-struct idpf_tx_buf {
-	void *next_to_watch;
-	struct sk_buff *skb;
-	DEFINE_DMA_UNMAP_ADDR(dma);
-	DEFINE_DMA_UNMAP_LEN(len);
-	unsigned int bytecount;
-	unsigned short gso_segs;
-
-	union {
-		int compl_tag;
-
-		bool ctx_entry;
-	};
-};
-
-struct idpf_tx_stash {
-	struct hlist_node hlist;
-	struct idpf_tx_buf buf;
-};
+#define idpf_tx_buf libeth_sqe
 
 /**
  * struct idpf_buf_lifo - LIFO for managing OOO completions
@@ -496,11 +455,6 @@ struct idpf_tx_queue_stats {
 	u64_stats_t dma_map_errs;
 };
 
-struct idpf_cleaned_stats {
-	u32 packets;
-	u32 bytes;
-};
-
 #define IDPF_ITR_DYNAMIC	1
 #define IDPF_ITR_MAX		0x1FE0
 #define IDPF_ITR_20K		0x0032
@@ -688,7 +642,7 @@ struct idpf_tx_queue {
 
 		void *desc_ring;
 	};
-	struct idpf_tx_buf *tx_buf;
+	struct libeth_sqe *tx_buf;
 	struct idpf_txq_group *txq_grp;
 	struct device *dev;
 	void __iomem *tail;
-- 
cgit v1.3-3-g829e


From 3dc95a3edd0a86b4a59670b3fafcc64c7d83e2e7 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Wed, 4 Sep 2024 17:47:45 +0200
Subject: netdevice: add netdev_tx_reset_subqueue() shorthand

Add a shorthand similar to other net*_subqueue() helpers for resetting
the queue by its index w/o obtaining &netdev_tx_queue beforehand
manually.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/linux/netdevice.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b47c00657bd0..44d1dbb54ffe 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3568,6 +3568,17 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
 #endif
 }
 
+/**
+ * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue
+ * @dev: network device
+ * @qid: stack index of the queue to reset
+ */
+static inline void netdev_tx_reset_subqueue(const struct net_device *dev,
+					    u32 qid)
+{
+	netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid));
+}
+
 /**
  * 	netdev_reset_queue - reset the packets and bytes count of a network device
  * 	@dev_queue: network device
@@ -3577,7 +3588,7 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
  */
 static inline void netdev_reset_queue(struct net_device *dev_queue)
 {
-	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
+	netdev_tx_reset_subqueue(dev_queue, 0);
 }
 
 /**
-- 
cgit v1.3-3-g829e


From 24eb35b15152ed6a2473019413b86b8f1c9714be Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Wed, 4 Sep 2024 17:47:46 +0200
Subject: idpf: refactor Tx completion routines

Add a mechanism to guard against stashing partial packets into the hash
table to make the driver more robust, with more efficient decision
making when cleaning.

Don't stash partial packets. This can happen when an RE (Report Event)
completion is received in flow scheduling mode, or when an out of order
RS (Report Status) completion is received. The first buffer with the skb
is stashed, but some or all of its frags are not because the stack is
out of reserve buffers. This leaves the ring in a weird state since
the frags are still on the ring.

Use the field libeth_sqe::nr_frags to track the number of
fragments/tx_bufs representing the packet. The clean routines check to
make sure there are enough reserve buffers on the stack before stashing
any part of the packet. If there are not, next_to_clean is left pointing
to the first buffer of the packet that failed to be stashed. This leaves
the whole packet on the ring, and the next time around, cleaning will
start from this packet.

An RS completion is still expected for this packet in either case. So
instead of being cleaned from the hash table, it will be cleaned from
the ring directly. This should all still be fine since the DESC_UNUSED
and BUFS_UNUSED will reflect the state of the ring. If we ever fall
below the thresholds, the TxQ will still be stopped, giving the
completion queue time to catch up. This may lead to stopping the queue
more frequently, but it guarantees the Tx ring will always be in a good
state.

Also, always use the idpf_tx_splitq_clean function to clean descriptors,
i.e. use it from clean_buf_ring as well. This way we avoid duplicating
the logic and make sure we're using the same reserve buffers guard rail.

This does require a switch from the s16 next_to_clean overflow
descriptor ring wrap calculation to u16 and the normal ring size check.

Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/idpf/idpf_singleq_txrx.c    |  24 +--
 drivers/net/ethernet/intel/idpf/idpf_txrx.c        | 168 +++++++++++++--------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h        |   6 +-
 3 files changed, 122 insertions(+), 76 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 98f26a4b835f..947d3ff9677c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -239,15 +239,16 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 								  offsets,
 								  max_data,
 								  td_tag);
-			tx_desc++;
-			i++;
-
-			if (i == tx_q->desc_count) {
+			if (unlikely(++i == tx_q->desc_count)) {
+				tx_buf = &tx_q->tx_buf[0];
 				tx_desc = &tx_q->base_tx[0];
 				i = 0;
+			} else {
+				tx_buf++;
+				tx_desc++;
 			}
 
-			tx_q->tx_buf[i].type = LIBETH_SQE_EMPTY;
+			tx_buf->type = LIBETH_SQE_EMPTY;
 
 			dma += max_data;
 			size -= max_data;
@@ -261,12 +262,14 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 
 		tx_desc->qw1 = idpf_tx_singleq_build_ctob(td_cmd, offsets,
 							  size, td_tag);
-		tx_desc++;
-		i++;
 
-		if (i == tx_q->desc_count) {
+		if (unlikely(++i == tx_q->desc_count)) {
+			tx_buf = &tx_q->tx_buf[0];
 			tx_desc = &tx_q->base_tx[0];
 			i = 0;
+		} else {
+			tx_buf++;
+			tx_desc++;
 		}
 
 		size = skb_frag_size(frag);
@@ -274,8 +277,6 @@ static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
 
 		dma = skb_frag_dma_map(tx_q->dev, frag, 0, size,
 				       DMA_TO_DEVICE);
-
-		tx_buf = &tx_q->tx_buf[i];
 	}
 
 	skb_tx_timestamp(first->skb);
@@ -454,6 +455,9 @@ static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
 			goto fetch_next_txq_desc;
 		}
 
+		if (unlikely(tx_buf->type != LIBETH_SQE_SKB))
+			break;
+
 		/* prevent any other reads prior to type */
 		smp_rmb();
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 76479c4f3fec..9844d01eaedb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -12,8 +12,8 @@ struct idpf_tx_stash {
 	struct libeth_sqe buf;
 };
 
-#define idpf_tx_buf_compl_tag(buf)	(*(int *)&(buf)->priv)
-LIBETH_SQE_CHECK_PRIV(int);
+#define idpf_tx_buf_compl_tag(buf)	(*(u32 *)&(buf)->priv)
+LIBETH_SQE_CHECK_PRIV(u32);
 
 static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
 			       unsigned int count);
@@ -77,11 +77,13 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 {
 	struct libeth_sq_napi_stats ss = { };
 	struct idpf_buf_lifo *buf_stack;
+	struct idpf_tx_stash *stash;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= &ss,
 	};
-	u16 i;
+	struct hlist_node *tmp;
+	u32 i, tag;
 
 	/* Buffers already cleared, nothing to do */
 	if (!txq->tx_buf)
@@ -101,6 +103,20 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 	if (!buf_stack->bufs)
 		return;
 
+	/*
+	 * If a Tx timeout occurred, there are potentially still bufs in the
+	 * hash table, free them here.
+	 */
+	hash_for_each_safe(txq->stash->sched_buf_hash, tag, tmp, stash,
+			   hlist) {
+		if (!stash)
+			continue;
+
+		libeth_tx_complete(&stash->buf, &cp);
+		hash_del(&stash->hlist);
+		idpf_buf_lifo_push(buf_stack, stash);
+	}
+
 	for (i = 0; i < buf_stack->size; i++)
 		kfree(buf_stack->bufs[i]);
 
@@ -117,6 +133,7 @@ static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
 static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
 {
 	idpf_tx_buf_rel_all(txq);
+	netdev_tx_reset_subqueue(txq->netdev, txq->idx);
 
 	if (!txq->desc_ring)
 		return;
@@ -1661,16 +1678,14 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
 	/* Buffer completion */
 	hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
 				    hlist, compl_tag) {
-		if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) !=
-			     (int)compl_tag))
+		if (unlikely(idpf_tx_buf_compl_tag(&stash->buf) != compl_tag))
 			continue;
 
+		hash_del(&stash->hlist);
 		libeth_tx_complete(&stash->buf, &cp);
 
 		/* Push shadow buf back onto stack */
 		idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
-
-		hash_del(&stash->hlist);
 	}
 }
 
@@ -1701,6 +1716,7 @@ static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
 	stash->buf.bytes = tx_buf->bytes;
 	stash->buf.packets = tx_buf->packets;
 	stash->buf.type = tx_buf->type;
+	stash->buf.nr_frags = tx_buf->nr_frags;
 	dma_unmap_addr_set(&stash->buf, dma, dma_unmap_addr(tx_buf, dma));
 	dma_unmap_len_set(&stash->buf, len, dma_unmap_len(tx_buf, len));
 	idpf_tx_buf_compl_tag(&stash->buf) = idpf_tx_buf_compl_tag(tx_buf);
@@ -1716,9 +1732,8 @@ static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
 
 #define idpf_tx_splitq_clean_bump_ntc(txq, ntc, desc, buf)	\
 do {								\
-	(ntc)++;						\
-	if (unlikely(!(ntc))) {					\
-		ntc -= (txq)->desc_count;			\
+	if (unlikely(++(ntc) == (txq)->desc_count)) {		\
+		ntc = 0;					\
 		buf = (txq)->tx_buf;				\
 		desc = &(txq)->flex_tx[0];			\
 	} else {						\
@@ -1742,59 +1757,66 @@ do {								\
  * Separate packet completion events will be reported on the completion queue,
  * and the buffers will be cleaned separately. The stats are not updated from
  * this function when using flow-based scheduling.
+ *
+ * Furthermore, in flow scheduling mode, check to make sure there are enough
+ * reserve buffers to stash the packet. If there are not, return early, which
+ * will leave next_to_clean pointing to the packet that failed to be stashed.
+ *
+ * Return: false in the scenario above, true otherwise.
  */
-static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
+static bool idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
 				 int napi_budget,
 				 struct libeth_sq_napi_stats *cleaned,
 				 bool descs_only)
 {
 	union idpf_tx_flex_desc *next_pending_desc = NULL;
 	union idpf_tx_flex_desc *tx_desc;
-	s16 ntc = tx_q->next_to_clean;
+	u32 ntc = tx_q->next_to_clean;
 	struct libeth_cq_pp cp = {
 		.dev	= tx_q->dev,
 		.ss	= cleaned,
 		.napi	= napi_budget,
 	};
 	struct idpf_tx_buf *tx_buf;
+	bool clean_complete = true;
 
 	tx_desc = &tx_q->flex_tx[ntc];
 	next_pending_desc = &tx_q->flex_tx[end];
 	tx_buf = &tx_q->tx_buf[ntc];
-	ntc -= tx_q->desc_count;
 
 	while (tx_desc != next_pending_desc) {
-		union idpf_tx_flex_desc *eop_desc;
+		u32 eop_idx;
 
 		/* If this entry in the ring was used as a context descriptor,
-		 * it's corresponding entry in the buffer ring will have an
-		 * invalid completion tag since no buffer was used.  We can
-		 * skip this descriptor since there is no buffer to clean.
+		 * it's corresponding entry in the buffer ring is reserved. We
+		 * can skip this descriptor since there is no buffer to clean.
 		 */
 		if (tx_buf->type <= LIBETH_SQE_CTX)
 			goto fetch_next_txq_desc;
 
-		eop_desc = &tx_q->flex_tx[tx_buf->rs_idx];
+		if (unlikely(tx_buf->type != LIBETH_SQE_SKB))
+			break;
+
+		eop_idx = tx_buf->rs_idx;
 
 		if (descs_only) {
-			if (idpf_stash_flow_sch_buffers(tx_q, tx_buf))
+			if (IDPF_TX_BUF_RSV_UNUSED(tx_q) < tx_buf->nr_frags) {
+				clean_complete = false;
 				goto tx_splitq_clean_out;
+			}
+
+			idpf_stash_flow_sch_buffers(tx_q, tx_buf);
 
-			while (tx_desc != eop_desc) {
+			while (ntc != eop_idx) {
 				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
 							      tx_desc, tx_buf);
-
-				if (dma_unmap_len(tx_buf, len)) {
-					if (idpf_stash_flow_sch_buffers(tx_q,
-									tx_buf))
-						goto tx_splitq_clean_out;
-				}
+				idpf_stash_flow_sch_buffers(tx_q, tx_buf);
 			}
 		} else {
 			libeth_tx_complete(tx_buf, &cp);
 
 			/* unmap remaining buffers */
-			while (tx_desc != eop_desc) {
+			while (ntc != eop_idx) {
 				idpf_tx_splitq_clean_bump_ntc(tx_q, ntc,
 							      tx_desc, tx_buf);
 
@@ -1808,8 +1830,9 @@ fetch_next_txq_desc:
 	}
 
 tx_splitq_clean_out:
-	ntc += tx_q->desc_count;
 	tx_q->next_to_clean = ntc;
+
+	return clean_complete;
 }
 
 #define idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, buf)	\
@@ -1840,48 +1863,63 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
 {
 	u16 idx = compl_tag & txq->compl_tag_bufid_m;
 	struct idpf_tx_buf *tx_buf = NULL;
-	u16 ntc = txq->next_to_clean;
 	struct libeth_cq_pp cp = {
 		.dev	= txq->dev,
 		.ss	= cleaned,
 		.napi	= budget,
 	};
-	u16 num_descs_cleaned = 0;
-	u16 orig_idx = idx;
+	u16 ntc, orig_idx = idx;
 
 	tx_buf = &txq->tx_buf[idx];
-	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX))
+
+	if (unlikely(tx_buf->type <= LIBETH_SQE_CTX ||
+		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
 		return false;
 
-	while (idpf_tx_buf_compl_tag(tx_buf) == (int)compl_tag) {
+	if (tx_buf->type == LIBETH_SQE_SKB)
 		libeth_tx_complete(tx_buf, &cp);
 
-		num_descs_cleaned++;
+	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
+
+	while (idpf_tx_buf_compl_tag(tx_buf) == compl_tag) {
+		libeth_tx_complete(tx_buf, &cp);
 		idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
 	}
 
-	/* If we didn't clean anything on the ring for this completion, there's
-	 * nothing more to do.
-	 */
-	if (unlikely(!num_descs_cleaned))
-		return false;
-
-	/* Otherwise, if we did clean a packet on the ring directly, it's safe
-	 * to assume that the descriptors starting from the original
-	 * next_to_clean up until the previously cleaned packet can be reused.
-	 * Therefore, we will go back in the ring and stash any buffers still
-	 * in the ring into the hash table to be cleaned later.
+	/*
+	 * It's possible the packet we just cleaned was an out of order
+	 * completion, which means we can stash the buffers starting from
+	 * the original next_to_clean and reuse the descriptors. We need
+	 * to compare the descriptor ring next_to_clean packet's "first" buffer
+	 * to the "first" buffer of the packet we just cleaned to determine if
+	 * this is the case. Howevever, next_to_clean can point to either a
+	 * reserved buffer that corresponds to a context descriptor used for the
+	 * next_to_clean packet (TSO packet) or the "first" buffer (single
+	 * packet). The orig_idx from the packet we just cleaned will always
+	 * point to the "first" buffer. If next_to_clean points to a reserved
+	 * buffer, let's bump ntc once and start the comparison from there.
 	 */
+	ntc = txq->next_to_clean;
 	tx_buf = &txq->tx_buf[ntc];
-	while (tx_buf != &txq->tx_buf[orig_idx]) {
-		idpf_stash_flow_sch_buffers(txq, tx_buf);
+
+	if (tx_buf->type == LIBETH_SQE_CTX)
 		idpf_tx_clean_buf_ring_bump_ntc(txq, ntc, tx_buf);
-	}
 
-	/* Finally, update next_to_clean to reflect the work that was just done
-	 * on the ring, if any. If the packet was only cleaned from the hash
-	 * table, the ring will not be impacted, therefore we should not touch
-	 * next_to_clean. The updated idx is used here
+	/*
+	 * If ntc still points to a different "first" buffer, clean the
+	 * descriptor ring and stash all of the buffers for later cleaning. If
+	 * we cannot stash all of the buffers, next_to_clean will point to the
+	 * "first" buffer of the packet that could not be stashed and cleaning
+	 * will start there next time.
+	 */
+	if (unlikely(tx_buf != &txq->tx_buf[orig_idx] &&
+		     !idpf_tx_splitq_clean(txq, orig_idx, budget, cleaned,
+					   true)))
+		return true;
+
+	/*
+	 * Otherwise, update next_to_clean to reflect the cleaning that was
+	 * done above.
 	 */
 	txq->next_to_clean = idx;
 
@@ -1909,7 +1947,8 @@ static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
 	if (!idpf_queue_has(FLOW_SCH_EN, txq)) {
 		u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head);
 
-		return idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+		idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+		return;
 	}
 
 	compl_tag = le16_to_cpu(desc->q_head_compl_tag.compl_tag);
@@ -2337,6 +2376,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 	dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE);
 
 	tx_buf = first;
+	first->nr_frags = 0;
 
 	params->compl_tag =
 		(tx_q->compl_tag_cur_gen << tx_q->compl_tag_gen_s) | i;
@@ -2347,6 +2387,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 		if (dma_mapping_error(tx_q->dev, dma))
 			return idpf_tx_dma_map_error(tx_q, skb, first, i);
 
+		first->nr_frags++;
 		idpf_tx_buf_compl_tag(tx_buf) = params->compl_tag;
 		tx_buf->type = LIBETH_SQE_FRAG;
 
@@ -2402,14 +2443,15 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			idpf_tx_splitq_build_desc(tx_desc, params, td_cmd,
 						  max_data);
 
-			tx_desc++;
-			i++;
-
-			if (i == tx_q->desc_count) {
+			if (unlikely(++i == tx_q->desc_count)) {
+				tx_buf = tx_q->tx_buf;
 				tx_desc = &tx_q->flex_tx[0];
 				i = 0;
 				tx_q->compl_tag_cur_gen =
 					IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
+			} else {
+				tx_buf++;
+				tx_desc++;
 			}
 
 			/* Since this packet has a buffer that is going to span
@@ -2422,7 +2464,7 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			 * simply pass over these holes and finish cleaning the
 			 * rest of the packet.
 			 */
-			tx_q->tx_buf[i].type = LIBETH_SQE_EMPTY;
+			tx_buf->type = LIBETH_SQE_EMPTY;
 
 			/* Adjust the DMA offset and the remaining size of the
 			 * fragment.  On the first iteration of this loop,
@@ -2446,13 +2488,15 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 			break;
 
 		idpf_tx_splitq_build_desc(tx_desc, params, td_cmd, size);
-		tx_desc++;
-		i++;
 
-		if (i == tx_q->desc_count) {
+		if (unlikely(++i == tx_q->desc_count)) {
+			tx_buf = tx_q->tx_buf;
 			tx_desc = &tx_q->flex_tx[0];
 			i = 0;
 			tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
+		} else {
+			tx_buf++;
+			tx_desc++;
 		}
 
 		size = skb_frag_size(frag);
@@ -2460,8 +2504,6 @@ static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
 
 		dma = skb_frag_dma_map(tx_q->dev, frag, 0, size,
 				       DMA_TO_DEVICE);
-
-		tx_buf = &tx_q->tx_buf[i];
 	}
 
 	/* record SW timestamp if HW timestamp is not available */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 1b20cd96c613..3a2a92e79e60 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -127,7 +127,7 @@ do {								\
  */
 #define IDPF_TX_COMPLQ_PENDING(txq)	\
 	(((txq)->num_completions_pending >= (txq)->complq->num_completions ? \
-	0 : U64_MAX) + \
+	0 : U32_MAX) + \
 	(txq)->num_completions_pending - (txq)->complq->num_completions)
 
 #define IDPF_TX_SPLITQ_COMPL_TAG_WIDTH	16
@@ -785,7 +785,7 @@ struct idpf_compl_queue {
 	u32 next_to_use;
 	u32 next_to_clean;
 
-	u32 num_completions;
+	aligned_u64 num_completions;
 	__cacheline_group_end_aligned(read_write);
 
 	__cacheline_group_begin_aligned(cold);
@@ -917,7 +917,7 @@ struct idpf_txq_group {
 
 	struct idpf_compl_queue *complq;
 
-	u32 num_completions_pending;
+	aligned_u64 num_completions_pending;
 };
 
 static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector)
-- 
cgit v1.3-3-g829e


From e4b398dd82f5d5867bc5f442c43abc8fba30ed2c Mon Sep 17 00:00:00 2001
From: Michal Kubiak <michal.kubiak@intel.com>
Date: Wed, 4 Sep 2024 17:47:47 +0200
Subject: idpf: fix netdev Tx queue stop/wake

netif_txq_maybe_stop() returns -1, 0, or 1, while
idpf_tx_maybe_stop_common() says it returns 0 or -EBUSY. As a result,
there sometimes are Tx queue timeout warnings despite that the queue
is empty or there is at least enough space to restart it.
Make idpf_tx_maybe_stop_common() inline and returning true or false,
handling the return of netif_txq_maybe_stop() properly. Use a correct
goto in idpf_tx_maybe_stop_splitq() to avoid stopping the queue or
incrementing the stops counter twice.

Fixes: 6818c4d5b3c2 ("idpf: add splitq start_xmit")
Fixes: a5ab9ee0df0b ("idpf: add singleq start_xmit and napi poll")
Cc: stable@vger.kernel.org # 6.7+
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/idpf/idpf_singleq_txrx.c    |  4 +++
 drivers/net/ethernet/intel/idpf/idpf_txrx.c        | 35 ++++++----------------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h        |  9 +++++-
 3 files changed, 21 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 947d3ff9677c..5ba360abbe66 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -375,6 +375,10 @@ netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 				      IDPF_TX_DESCS_FOR_CTX)) {
 		idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
 
+		u64_stats_update_begin(&tx_q->stats_sync);
+		u64_stats_inc(&tx_q->q_stats.q_busy);
+		u64_stats_update_end(&tx_q->stats_sync);
+
 		return NETDEV_TX_BUSY;
 	}
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 9844d01eaedb..5d74f324bcd4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2132,29 +2132,6 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
 
-/**
- * idpf_tx_maybe_stop_common - 1st level check for common Tx stop conditions
- * @tx_q: the queue to be checked
- * @size: number of descriptors we want to assure is available
- *
- * Returns 0 if stop is not needed
- */
-int idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q, unsigned int size)
-{
-	struct netdev_queue *nq;
-
-	if (likely(IDPF_DESC_UNUSED(tx_q) >= size))
-		return 0;
-
-	u64_stats_update_begin(&tx_q->stats_sync);
-	u64_stats_inc(&tx_q->q_stats.q_busy);
-	u64_stats_update_end(&tx_q->stats_sync);
-
-	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
-
-	return netif_txq_maybe_stop(nq, IDPF_DESC_UNUSED(tx_q), size, size);
-}
-
 /**
  * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
  * @tx_q: the queue to be checked
@@ -2166,7 +2143,7 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
 				     unsigned int descs_needed)
 {
 	if (idpf_tx_maybe_stop_common(tx_q, descs_needed))
-		goto splitq_stop;
+		goto out;
 
 	/* If there are too many outstanding completions expected on the
 	 * completion queue, stop the TX queue to give the device some time to
@@ -2185,10 +2162,12 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
 	return 0;
 
 splitq_stop:
+	netif_stop_subqueue(tx_q->netdev, tx_q->idx);
+
+out:
 	u64_stats_update_begin(&tx_q->stats_sync);
 	u64_stats_inc(&tx_q->q_stats.q_busy);
 	u64_stats_update_end(&tx_q->stats_sync);
-	netif_stop_subqueue(tx_q->netdev, tx_q->idx);
 
 	return -EBUSY;
 }
@@ -2211,7 +2190,11 @@ void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
 	nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
 	tx_q->next_to_use = val;
 
-	idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED);
+	if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) {
+		u64_stats_update_begin(&tx_q->stats_sync);
+		u64_stats_inc(&tx_q->q_stats.q_busy);
+		u64_stats_update_end(&tx_q->stats_sync);
+	}
 
 	/* Force memory writes to complete before letting h/w
 	 * know there are new descriptors to fetch.  (Only
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 3a2a92e79e60..33305de06975 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -1018,7 +1018,6 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
 			   struct idpf_tx_buf *first, u16 ring_idx);
 unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
 					 struct sk_buff *skb);
-int idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q, unsigned int size);
 void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);
 netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
 				  struct idpf_tx_queue *tx_q);
@@ -1027,4 +1026,12 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq,
 				      u16 cleaned_count);
 int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off);
 
+static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q,
+					     u32 needed)
+{
+	return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
+					  IDPF_DESC_UNUSED(tx_q),
+					  needed, needed);
+}
+
 #endif /* !_IDPF_TXRX_H_ */
-- 
cgit v1.3-3-g829e


From 9c4a27da0ecc4080dfcd63903dd94f01ba1399dd Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Wed, 4 Sep 2024 17:47:48 +0200
Subject: idpf: enable WB_ON_ITR

Tell hardware to write back completed descriptors even when interrupts
are disabled. Otherwise, descriptors might not be written back until
the hardware can flush a full cacheline of descriptors. This can cause
unnecessary delays when traffic is light (or even trigger Tx queue
timeout).

The example scenario to reproduce the Tx timeout if the fix is not
applied:
  - configure at least 2 Tx queues to be assigned to the same q_vector,
  - generate a huge Tx traffic on the first Tx queue
  - try to send a few packets using the second Tx queue.
In such a case Tx timeout will appear on the second Tx queue because no
completion descriptors are written back for that queue while interrupts
are disabled due to NAPI polling.

Fixes: c2d548cad150 ("idpf: add TX splitq napi poll support")
Fixes: a5ab9ee0df0b ("idpf: add singleq start_xmit and napi poll")
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Co-developed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Michal Kubiak <michal.kubiak@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_dev.c         |  2 ++
 .../net/ethernet/intel/idpf/idpf_singleq_txrx.c    |  6 ++++-
 drivers/net/ethernet/intel/idpf/idpf_txrx.c        |  7 +++++-
 drivers/net/ethernet/intel/idpf/idpf_txrx.h        | 27 +++++++++++++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_vf_dev.c      |  2 ++
 5 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index 3df9935685e9..6c913a703df6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -97,8 +97,10 @@ static int idpf_intr_reg_init(struct idpf_vport *vport)
 		intr->dyn_ctl = idpf_get_reg_addr(adapter,
 						  reg_vals[vec_id].dyn_ctl_reg);
 		intr->dyn_ctl_intena_m = PF_GLINT_DYN_CTL_INTENA_M;
+		intr->dyn_ctl_intena_msk_m = PF_GLINT_DYN_CTL_INTENA_MSK_M;
 		intr->dyn_ctl_itridx_s = PF_GLINT_DYN_CTL_ITR_INDX_S;
 		intr->dyn_ctl_intrvl_s = PF_GLINT_DYN_CTL_INTERVAL_S;
+		intr->dyn_ctl_wb_on_itr_m = PF_GLINT_DYN_CTL_WB_ON_ITR_M;
 
 		spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing,
 					       IDPF_PF_ITR_IDX_SPACING);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index 5ba360abbe66..dfd7cf1d9aa0 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -1120,8 +1120,10 @@ int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget)
 						    &work_done);
 
 	/* If work not completed, return budget and polling will return */
-	if (!clean_complete)
+	if (!clean_complete) {
+		idpf_vport_intr_set_wb_on_itr(q_vector);
 		return budget;
+	}
 
 	work_done = min_t(int, work_done, budget - 1);
 
@@ -1130,6 +1132,8 @@ int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget)
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
 		idpf_vport_intr_update_itr_ena_irq(q_vector);
+	else
+		idpf_vport_intr_set_wb_on_itr(q_vector);
 
 	return work_done;
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 5d74f324bcd4..d4e6f0e10487 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3715,6 +3715,7 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector)
 	/* net_dim() updates ITR out-of-band using a work item */
 	idpf_net_dim(q_vector);
 
+	q_vector->wb_on_itr = false;
 	intval = idpf_vport_intr_buildreg_itr(q_vector,
 					      IDPF_NO_ITR_UPDATE_IDX, 0);
 
@@ -4017,8 +4018,10 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 	clean_complete &= idpf_tx_splitq_clean_all(q_vector, budget, &work_done);
 
 	/* If work not completed, return budget and polling will return */
-	if (!clean_complete)
+	if (!clean_complete) {
+		idpf_vport_intr_set_wb_on_itr(q_vector);
 		return budget;
+	}
 
 	work_done = min_t(int, work_done, budget - 1);
 
@@ -4027,6 +4030,8 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
 	 */
 	if (likely(napi_complete_done(napi, work_done)))
 		idpf_vport_intr_update_itr_ena_irq(q_vector);
+	else
+		idpf_vport_intr_set_wb_on_itr(q_vector);
 
 	/* Switch to poll mode in the tear-down path after sending disable
 	 * queues virtchnl message, as the interrupts will be disabled after
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 33305de06975..f0537826f840 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -349,9 +349,11 @@ struct idpf_vec_regs {
  * struct idpf_intr_reg
  * @dyn_ctl: Dynamic control interrupt register
  * @dyn_ctl_intena_m: Mask for dyn_ctl interrupt enable
+ * @dyn_ctl_intena_msk_m: Mask for dyn_ctl interrupt enable mask
  * @dyn_ctl_itridx_s: Register bit offset for ITR index
  * @dyn_ctl_itridx_m: Mask for ITR index
  * @dyn_ctl_intrvl_s: Register bit offset for ITR interval
+ * @dyn_ctl_wb_on_itr_m: Mask for WB on ITR feature
  * @rx_itr: RX ITR register
  * @tx_itr: TX ITR register
  * @icr_ena: Interrupt cause register offset
@@ -360,9 +362,11 @@ struct idpf_vec_regs {
 struct idpf_intr_reg {
 	void __iomem *dyn_ctl;
 	u32 dyn_ctl_intena_m;
+	u32 dyn_ctl_intena_msk_m;
 	u32 dyn_ctl_itridx_s;
 	u32 dyn_ctl_itridx_m;
 	u32 dyn_ctl_intrvl_s;
+	u32 dyn_ctl_wb_on_itr_m;
 	void __iomem *rx_itr;
 	void __iomem *tx_itr;
 	void __iomem *icr_ena;
@@ -383,6 +387,7 @@ struct idpf_intr_reg {
  * @intr_reg: See struct idpf_intr_reg
  * @napi: napi handler
  * @total_events: Number of interrupts processed
+ * @wb_on_itr: whether WB on ITR is enabled
  * @tx_dim: Data for TX net_dim algorithm
  * @tx_itr_value: TX interrupt throttling rate
  * @tx_intr_mode: Dynamic ITR or not
@@ -413,6 +418,7 @@ struct idpf_q_vector {
 	__cacheline_group_begin_aligned(read_write);
 	struct napi_struct napi;
 	u16 total_events;
+	bool wb_on_itr;
 
 	struct dim tx_dim;
 	u16 tx_itr_value;
@@ -431,7 +437,7 @@ struct idpf_q_vector {
 	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
-libeth_cacheline_set_assert(struct idpf_q_vector, 104,
+libeth_cacheline_set_assert(struct idpf_q_vector, 112,
 			    424 + 2 * sizeof(struct dim),
 			    8 + sizeof(cpumask_var_t));
 
@@ -987,6 +993,25 @@ static inline void idpf_tx_splitq_build_desc(union idpf_tx_flex_desc *desc,
 		idpf_tx_splitq_build_flow_desc(desc, params, td_cmd, size);
 }
 
+/**
+ * idpf_vport_intr_set_wb_on_itr - enable descriptor writeback on disabled interrupts
+ * @q_vector: pointer to queue vector struct
+ */
+static inline void idpf_vport_intr_set_wb_on_itr(struct idpf_q_vector *q_vector)
+{
+	struct idpf_intr_reg *reg;
+
+	if (q_vector->wb_on_itr)
+		return;
+
+	q_vector->wb_on_itr = true;
+	reg = &q_vector->intr_reg;
+
+	writel(reg->dyn_ctl_wb_on_itr_m | reg->dyn_ctl_intena_msk_m |
+	       (IDPF_NO_ITR_UPDATE_IDX << reg->dyn_ctl_itridx_s),
+	       reg->dyn_ctl);
+}
+
 int idpf_vport_singleq_napi_poll(struct napi_struct *napi, int budget);
 void idpf_vport_init_num_qs(struct idpf_vport *vport,
 			    struct virtchnl2_create_vport *vport_msg);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
index 629cb5cb7c9f..99b8dbaf4225 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
@@ -97,7 +97,9 @@ static int idpf_vf_intr_reg_init(struct idpf_vport *vport)
 		intr->dyn_ctl = idpf_get_reg_addr(adapter,
 						  reg_vals[vec_id].dyn_ctl_reg);
 		intr->dyn_ctl_intena_m = VF_INT_DYN_CTLN_INTENA_M;
+		intr->dyn_ctl_intena_msk_m = VF_INT_DYN_CTLN_INTENA_MSK_M;
 		intr->dyn_ctl_itridx_s = VF_INT_DYN_CTLN_ITR_INDX_S;
+		intr->dyn_ctl_wb_on_itr_m = VF_INT_DYN_CTLN_WB_ON_ITR_M;
 
 		spacing = IDPF_ITR_IDX_SPACING(reg_vals[vec_id].itrn_index_spacing,
 					       IDPF_VF_ITR_IDX_SPACING);
-- 
cgit v1.3-3-g829e


From a7e387375f22a4fd46c8ffcfa395a0ca8c186f9e Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Fri, 6 Sep 2024 00:00:35 +0800
Subject: selftests: return failure when timestamps can't be reported

When I was trying to modify the tx timestamping feature, I found that
running "./txtimestamp -4 -C -L 127.0.0.1" didn't reflect the error:
I succeeded to generate timestamp stored in the skb but later failed
to report it to the userspace (which means failed to put css into cmsg).
It can happen when someone writes buggy codes in __sock_recv_timestamp(),
for example.

After adding the check so that running ./txtimestamp will reflect the
result correctly like this if there is a bug in the reporting phase:
protocol:     TCP
payload:      10
server port:  9000

family:       INET
test SND
    USR: 1725458477 s 667997 us (seq=0, len=0)
Failed to report timestamps
    USR: 1725458477 s 718128 us (seq=0, len=0)
Failed to report timestamps
    USR: 1725458477 s 768273 us (seq=0, len=0)
Failed to report timestamps
    USR: 1725458477 s 818416 us (seq=0, len=0)
Failed to report timestamps
...

In the future, it will help us detect whether the new coming patch has
bugs or not.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240905160035.62407-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/txtimestamp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c
index ec60a16c9307..d626f22f9550 100644
--- a/tools/testing/selftests/net/txtimestamp.c
+++ b/tools/testing/selftests/net/txtimestamp.c
@@ -356,8 +356,12 @@ static void __recv_errmsg_cmsg(struct msghdr *msg, int payload_len)
 		}
 	}
 
-	if (batch > 1)
+	if (batch > 1) {
 		fprintf(stderr, "batched %d timestamps\n", batch);
+	} else if (!batch) {
+		fprintf(stderr, "Failed to report timestamps\n");
+		test_failed = true;
+	}
 }
 
 static int recv_errmsg(int fd)
-- 
cgit v1.3-3-g829e


From f58817c852e9c9eb8116c24d8271a35159636605 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 6 Sep 2024 20:46:07 +0200
Subject: selftests: mptcp: lib: add time per subtests in TAP output

It adds 'time=<N>ms' in the diagnostic data of the TAP output, e.g.

  ok 1 - pm_netlink: defaults addr list # time=9ms

This addition is useful to quickly identify which subtests are taking a
longer time than the others, or more than expected.

Note that there are no specific formats to follow to show this time
according to the TAP 13 [1], TAP 14 [2] and KTAP [3] specifications.
Let's then define this one here.

Link: https://testanything.org/tap-version-13-specification.html [1]
Link: https://testanything.org/tap-version-14-specification.html [2]
Link: https://docs.kernel.org/dev-tools/ktap.html [3]
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240906-net-next-mptcp-ksft-subtest-time-v2-1-31d5ee4f3bdf@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_lib.sh | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index 4578a331041e..975d4d4c862a 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -29,6 +29,7 @@ declare -rx MPTCP_LIB_AF_INET6=10
 MPTCP_LIB_SUBTESTS=()
 MPTCP_LIB_SUBTESTS_DUPLICATED=0
 MPTCP_LIB_SUBTEST_FLAKY=0
+MPTCP_LIB_SUBTESTS_LAST_TS_MS=
 MPTCP_LIB_TEST_COUNTER=0
 MPTCP_LIB_TEST_FORMAT="%02u %-50s"
 MPTCP_LIB_IP_MPTCP=0
@@ -205,6 +206,11 @@ mptcp_lib_kversion_ge() {
 	mptcp_lib_fail_if_expected_feature "kernel version ${1} lower than ${v}"
 }
 
+mptcp_lib_subtests_last_ts_reset() {
+	MPTCP_LIB_SUBTESTS_LAST_TS_MS="$(date +%s%3N)"
+}
+mptcp_lib_subtests_last_ts_reset
+
 __mptcp_lib_result_check_duplicated() {
 	local subtest
 
@@ -219,13 +225,22 @@ __mptcp_lib_result_check_duplicated() {
 
 __mptcp_lib_result_add() {
 	local result="${1}"
+	local time="time="
+	local ts_prev_ms
 	shift
 
 	local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1))
 
 	__mptcp_lib_result_check_duplicated "${*}"
 
-	MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*}")
+	# not to add two '#'
+	[[ "${*}" != *"#"* ]] && time="# ${time}"
+
+	ts_prev_ms="${MPTCP_LIB_SUBTESTS_LAST_TS_MS}"
+	mptcp_lib_subtests_last_ts_reset
+	time+="$((MPTCP_LIB_SUBTESTS_LAST_TS_MS - ts_prev_ms))ms"
+
+	MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*} ${time}")
 }
 
 # $1: test name
-- 
cgit v1.3-3-g829e


From 1a38cee4bbd0adeb62e11aab429678b1fb4a12ae Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 6 Sep 2024 20:46:08 +0200
Subject: selftests: mptcp: connect: remote time in TAP output

It is now added by the MPTCP lib automatically, see the parent commit.

The time in the TAP output might be slightly different from the one
displayed before, but that's OK.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240906-net-next-mptcp-ksft-subtest-time-v2-2-31d5ee4f3bdf@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index b77fb7065bfb..f61e2f5870ea 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -431,7 +431,6 @@ do_transfer()
 
 	local duration
 	duration=$((stop-start))
-	result_msg+=" # time=${duration}ms"
 	printf "(duration %05sms) " "${duration}"
 	if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then
 		mptcp_lib_pr_fail "client exit code $retc, server $rets"
-- 
cgit v1.3-3-g829e


From d4e192728efc532bc9a93e664f81fac602786450 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 6 Sep 2024 20:46:09 +0200
Subject: selftests: mptcp: reset the last TS before the first test

Just to slightly improve the precision of the duration of the first
test.

In mptcp_join.sh, the last append_prev_results is now done as soon as
the last test is over: this will add the last result in the list, and
get a more precise time for this last test.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240906-net-next-mptcp-ksft-subtest-time-v2-3-31d5ee4f3bdf@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 2 ++
 tools/testing/selftests/net/mptcp/mptcp_join.sh    | 3 ++-
 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh | 1 +
 tools/testing/selftests/net/mptcp/pm_netlink.sh    | 2 ++
 tools/testing/selftests/net/mptcp/simult_flows.sh  | 1 +
 tools/testing/selftests/net/mptcp/userspace_pm.sh  | 1 +
 6 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index f61e2f5870ea..49d90c4dbc01 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -847,6 +847,8 @@ stop_if_error()
 make_file "$cin" "client"
 make_file "$sin" "server"
 
+mptcp_lib_subtests_last_ts_reset
+
 check_mptcp_disabled
 
 stop_if_error "The kernel configuration is not valid for MPTCP"
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 43f8a9bd84c4..3564cd06643c 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3959,9 +3959,11 @@ if [ ${#tests[@]} -eq 0 ]; then
 	tests=("${all_tests_names[@]}")
 fi
 
+mptcp_lib_subtests_last_ts_reset
 for subtests in "${tests[@]}"; do
 	"${subtests}"
 done
+append_prev_results
 
 if [ ${ret} -ne 0 ]; then
 	echo
@@ -3972,7 +3974,6 @@ if [ ${ret} -ne 0 ]; then
 	echo
 fi
 
-append_prev_results
 mptcp_lib_result_print_all_tap
 
 exit $ret
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 68899a303a1a..5e8d5b83e2d0 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -349,6 +349,7 @@ init
 make_file "$cin" "client" 1
 make_file "$sin" "server" 1
 trap cleanup EXIT
+mptcp_lib_subtests_last_ts_reset
 
 run_tests $ns1 $ns2 10.0.1.1
 run_tests $ns1 $ns2 dead:beef:1::1
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 2757378b1b13..2e6648a2b2c0 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -137,6 +137,8 @@ check()
 	fi
 }
 
+mptcp_lib_subtests_last_ts_reset
+
 check "show_endpoints" "" "defaults addr list"
 
 default_limits="$(get_limits)"
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index f74e1c3c126d..8fa77c8e9b65 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -286,6 +286,7 @@ while getopts "bcdhi" option;do
 done
 
 setup
+mptcp_lib_subtests_last_ts_reset
 run_test 10 10 0 0 "balanced bwidth"
 run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 9cb05978269d..3651f73451cf 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -150,6 +150,7 @@ mptcp_lib_events "${ns2}" "${client_evts}" client_evts_pid
 server_evts=$(mktemp)
 mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid
 sleep 0.5
+mptcp_lib_subtests_last_ts_reset
 
 print_title "Init"
 print_test "Created network namespaces ns1, ns2"
-- 
cgit v1.3-3-g829e


From a5b6be42aac0fd3b94adaeec3cda4d847b304fd8 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 6 Sep 2024 20:46:10 +0200
Subject: selftests: mptcp: diag: remove trailing whitespace

It doesn't need to be there, and it can cause some issues with TAP
parsers expecting only one space around the directive delimiter (#).

Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240906-net-next-mptcp-ksft-subtest-time-v2-4-31d5ee4f3bdf@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/diag.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 776d43a6922d..2bd0c1eb70c5 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -284,7 +284,7 @@ echo "b" | \
 			./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \
 				127.0.0.1 >/dev/null &
 wait_connected $ns 10000
-chk_msk_nr 2 "after MPC handshake "
+chk_msk_nr 2 "after MPC handshake"
 chk_last_time_info 10000
 chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
-- 
cgit v1.3-3-g829e


From a92d1db0c989d4244d3a671d78f291606ed4ce35 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 6 Sep 2024 20:46:11 +0200
Subject: selftests: mptcp: connect: remove duplicated spaces in TAP output

It is nice to have a visual alignment in the test output to present the
different results, but it makes less sense in the TAP output that is
there for computers.

It sounds then better to remove the duplicated whitespaces in the TAP
output, also because it can cause some issues with TAP parsers expecting
only one space around the directive delimiter (#).

While at it, change the variable name (result_msg) to something more
explicit.

Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240906-net-next-mptcp-ksft-subtest-time-v2-5-31d5ee4f3bdf@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.sh | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
index 49d90c4dbc01..57325d57e4c6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh
@@ -345,9 +345,11 @@ do_transfer()
 
 	local addr_port
 	addr_port=$(printf "%s:%d" ${connect_addr} ${port})
-	local result_msg
-	result_msg="$(printf "%.3s %-5s -> %.3s (%-20s) %-5s" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto})"
-	mptcp_lib_print_title "${result_msg}"
+	local pretty_title
+	pretty_title="$(printf "%.3s %-5s -> %.3s (%-20s) %-5s" ${connector_ns} ${cl_proto} ${listener_ns} ${addr_port} ${srv_proto})"
+	mptcp_lib_print_title "${pretty_title}"
+
+	local tap_title="${connector_ns:0:3} ${cl_proto} -> ${listener_ns:0:3} (${addr_port}) ${srv_proto}"
 
 	if $capture; then
 		local capuser
@@ -443,7 +445,7 @@ do_transfer()
 
 		echo
 		cat "$capout"
-		mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}"
+		mptcp_lib_result_fail "${TEST_GROUP}: ${tap_title}"
 		return 1
 	fi
 
@@ -543,12 +545,12 @@ do_transfer()
 
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then
 		mptcp_lib_pr_ok "${extra:1}"
-		mptcp_lib_result_pass "${TEST_GROUP}: ${result_msg}"
+		mptcp_lib_result_pass "${TEST_GROUP}: ${tap_title}"
 	else
 		if [ -n "${extra}" ]; then
 			mptcp_lib_print_warn "${extra:1}"
 		fi
-		mptcp_lib_result_fail "${TEST_GROUP}: ${result_msg}"
+		mptcp_lib_result_fail "${TEST_GROUP}: ${tap_title}"
 	fi
 
 	cat "$capout"
-- 
cgit v1.3-3-g829e


From 17245a195df4c86b1fd38718d8cdc532c040c08e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 6 Sep 2024 09:10:59 -0700
Subject: net: remove dev_pick_tx_cpu_id()

dev_pick_tx_cpu_id() has been introduced with two users by
commit a4ea8a3dacc3 ("net: Add generic ndo_select_queue functions").
The use in AF_PACKET has been removed in 2019 by
commit b71b5837f871 ("packet: rework packet_pick_tx_queue() to use common code selection")
The other user was a Netlogic XLP driver, removed in 2021 by
commit 47ac6f567c28 ("staging: Remove Netlogic XLP network driver").

It's relatively unlikely that any modern driver will need an
.ndo_select_queue implementation which picks purely based on CPU ID
and skips XPS, delete dev_pick_tx_cpu_id()

Found by code inspection.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240906161059.715546-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 2 --
 net/core/dev.c            | 7 -------
 2 files changed, 9 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b47c00657bd0..2e40a137dc12 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3085,8 +3085,6 @@ void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
-u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev);
 
 int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
diff --git a/net/core/dev.c b/net/core/dev.c
index 22c3f14d9287..8f4dead64284 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4247,13 +4247,6 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(dev_pick_tx_zero);
 
-u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev)
-{
-	return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
-}
-EXPORT_SYMBOL(dev_pick_tx_cpu_id);
-
 u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev)
 {
-- 
cgit v1.3-3-g829e


From 579770dd89855915096db8364261543c37ed34ef Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 5 Sep 2024 12:32:37 -0700
Subject: af_unix: Remove single nest in manage_oob().

This is a prep for the later fix.

No functional change intended.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240905193240.17565-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 45 +++++++++++++++++++++++----------------------
 1 file changed, 23 insertions(+), 22 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index a1894019ebd5..03820454bc72 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2654,11 +2654,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 				  int flags, int copied)
 {
+	struct sk_buff *unlinked_skb = NULL;
 	struct unix_sock *u = unix_sk(sk);
 
 	if (!unix_skb_len(skb)) {
-		struct sk_buff *unlinked_skb = NULL;
-
 		spin_lock(&sk->sk_receive_queue.lock);
 
 		if (copied && (!u->oob_skb || skb == u->oob_skb)) {
@@ -2674,31 +2673,33 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		spin_unlock(&sk->sk_receive_queue.lock);
 
 		consume_skb(unlinked_skb);
-	} else {
-		struct sk_buff *unlinked_skb = NULL;
+		return skb;
+	}
 
-		spin_lock(&sk->sk_receive_queue.lock);
+	spin_lock(&sk->sk_receive_queue.lock);
 
-		if (skb == u->oob_skb) {
-			if (copied) {
-				skb = NULL;
-			} else if (!(flags & MSG_PEEK)) {
-				WRITE_ONCE(u->oob_skb, NULL);
-
-				if (!sock_flag(sk, SOCK_URGINLINE)) {
-					__skb_unlink(skb, &sk->sk_receive_queue);
-					unlinked_skb = skb;
-					skb = skb_peek(&sk->sk_receive_queue);
-				}
-			} else if (!sock_flag(sk, SOCK_URGINLINE)) {
-				skb = skb_peek_next(skb, &sk->sk_receive_queue);
-			}
-		}
+	if (skb != u->oob_skb)
+		goto unlock;
 
-		spin_unlock(&sk->sk_receive_queue.lock);
+	if (copied) {
+		skb = NULL;
+	} else if (!(flags & MSG_PEEK)) {
+		WRITE_ONCE(u->oob_skb, NULL);
 
-		kfree_skb(unlinked_skb);
+		if (!sock_flag(sk, SOCK_URGINLINE)) {
+			__skb_unlink(skb, &sk->sk_receive_queue);
+			unlinked_skb = skb;
+			skb = skb_peek(&sk->sk_receive_queue);
+		}
+	} else if (!sock_flag(sk, SOCK_URGINLINE)) {
+		skb = skb_peek_next(skb, &sk->sk_receive_queue);
 	}
+
+unlock:
+	spin_unlock(&sk->sk_receive_queue.lock);
+
+	kfree_skb(unlinked_skb);
+
 	return skb;
 }
 #endif
-- 
cgit v1.3-3-g829e


From beb2c5f19b6ab033b187e770a659c730c3bd05ca Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 5 Sep 2024 12:32:38 -0700
Subject: af_unix: Rename unlinked_skb in manage_oob().

When OOB skb has been already consumed, manage_oob() returns the next
skb if exists.  In such a case, we need to fall back to the else branch
below.

Then, we need to keep two skbs and free them later with consume_skb()
and kfree_skb().

Let's rename unlinked_skb accordingly.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240905193240.17565-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 03820454bc72..91d7877a1079 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2654,7 +2654,7 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 				  int flags, int copied)
 {
-	struct sk_buff *unlinked_skb = NULL;
+	struct sk_buff *read_skb = NULL, *unread_skb = NULL;
 	struct unix_sock *u = unix_sk(sk);
 
 	if (!unix_skb_len(skb)) {
@@ -2665,14 +2665,14 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		} else if (flags & MSG_PEEK) {
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
 		} else {
-			unlinked_skb = skb;
+			read_skb = skb;
 			skb = skb_peek_next(skb, &sk->sk_receive_queue);
-			__skb_unlink(unlinked_skb, &sk->sk_receive_queue);
+			__skb_unlink(read_skb, &sk->sk_receive_queue);
 		}
 
 		spin_unlock(&sk->sk_receive_queue.lock);
 
-		consume_skb(unlinked_skb);
+		consume_skb(read_skb);
 		return skb;
 	}
 
@@ -2688,7 +2688,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 
 		if (!sock_flag(sk, SOCK_URGINLINE)) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
-			unlinked_skb = skb;
+			unread_skb = skb;
 			skb = skb_peek(&sk->sk_receive_queue);
 		}
 	} else if (!sock_flag(sk, SOCK_URGINLINE)) {
@@ -2698,7 +2698,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 unlock:
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	kfree_skb(unlinked_skb);
+	kfree_skb(unread_skb);
 
 	return skb;
 }
-- 
cgit v1.3-3-g829e


From a0264a9f51fe0d196f22efd7538eb749e3448c2d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 5 Sep 2024 12:32:39 -0700
Subject: af_unix: Move spin_lock() in manage_oob().

When OOB skb has been already consumed, manage_oob() returns the next
skb if exists.  In such a case, we need to fall back to the else branch
below.

Then, we want to keep holding spin_lock(&sk->sk_receive_queue.lock).

Let's move it out of if-else branch and add lightweight check before
spin_lock() for major use cases without OOB skb.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240905193240.17565-4-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 91d7877a1079..159d78fc3d14 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2657,9 +2657,12 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 	struct sk_buff *read_skb = NULL, *unread_skb = NULL;
 	struct unix_sock *u = unix_sk(sk);
 
-	if (!unix_skb_len(skb)) {
-		spin_lock(&sk->sk_receive_queue.lock);
+	if (likely(unix_skb_len(skb) && skb != READ_ONCE(u->oob_skb)))
+		return skb;
 
+	spin_lock(&sk->sk_receive_queue.lock);
+
+	if (!unix_skb_len(skb)) {
 		if (copied && (!u->oob_skb || skb == u->oob_skb)) {
 			skb = NULL;
 		} else if (flags & MSG_PEEK) {
@@ -2670,14 +2673,9 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 			__skb_unlink(read_skb, &sk->sk_receive_queue);
 		}
 
-		spin_unlock(&sk->sk_receive_queue.lock);
-
-		consume_skb(read_skb);
-		return skb;
+		goto unlock;
 	}
 
-	spin_lock(&sk->sk_receive_queue.lock);
-
 	if (skb != u->oob_skb)
 		goto unlock;
 
@@ -2698,6 +2696,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 unlock:
 	spin_unlock(&sk->sk_receive_queue.lock);
 
+	consume_skb(read_skb);
 	kfree_skb(unread_skb);
 
 	return skb;
-- 
cgit v1.3-3-g829e


From 5aa57d9f2d5311f19434d95b2a81610aa263e23b Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 5 Sep 2024 12:32:40 -0700
Subject: af_unix: Don't return OOB skb in manage_oob().

syzbot reported use-after-free in unix_stream_recv_urg(). [0]

The scenario is

  1. send(MSG_OOB)
  2. recv(MSG_OOB)
     -> The consumed OOB remains in recv queue
  3. send(MSG_OOB)
  4. recv()
     -> manage_oob() returns the next skb of the consumed OOB
     -> This is also OOB, but unix_sk(sk)->oob_skb is not cleared
  5. recv(MSG_OOB)
     -> unix_sk(sk)->oob_skb is used but already freed

The recent commit 8594d9b85c07 ("af_unix: Don't call skb_get() for OOB
skb.") uncovered the issue.

If the OOB skb is consumed and the next skb is peeked in manage_oob(),
we still need to check if the skb is OOB.

Let's do so by falling back to the following checks in manage_oob()
and add the test case in selftest.

Note that we need to add a similar check for SIOCATMARK.

[0]:
BUG: KASAN: slab-use-after-free in unix_stream_read_actor+0xa6/0xb0 net/unix/af_unix.c:2959
Read of size 4 at addr ffff8880326abcc4 by task syz-executor178/5235

CPU: 0 UID: 0 PID: 5235 Comm: syz-executor178 Not tainted 6.11.0-rc5-syzkaller-00742-gfbdaffe41adc #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:93 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119
 print_address_description mm/kasan/report.c:377 [inline]
 print_report+0x169/0x550 mm/kasan/report.c:488
 kasan_report+0x143/0x180 mm/kasan/report.c:601
 unix_stream_read_actor+0xa6/0xb0 net/unix/af_unix.c:2959
 unix_stream_recv_urg+0x1df/0x320 net/unix/af_unix.c:2640
 unix_stream_read_generic+0x2456/0x2520 net/unix/af_unix.c:2778
 unix_stream_recvmsg+0x22b/0x2c0 net/unix/af_unix.c:2996
 sock_recvmsg_nosec net/socket.c:1046 [inline]
 sock_recvmsg+0x22f/0x280 net/socket.c:1068
 ____sys_recvmsg+0x1db/0x470 net/socket.c:2816
 ___sys_recvmsg net/socket.c:2858 [inline]
 __sys_recvmsg+0x2f0/0x3e0 net/socket.c:2888
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f5360d6b4e9
Code: 48 83 c4 28 c3 e8 37 17 00 00 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fff29b3a458 EFLAGS: 00000246 ORIG_RAX: 000000000000002f
RAX: ffffffffffffffda RBX: 00007fff29b3a638 RCX: 00007f5360d6b4e9
RDX: 0000000000002001 RSI: 0000000020000640 RDI: 0000000000000003
RBP: 00007f5360dde610 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001
R13: 00007fff29b3a628 R14: 0000000000000001 R15: 0000000000000001
 </TASK>

Allocated by task 5235:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 unpoison_slab_object mm/kasan/common.c:312 [inline]
 __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:338
 kasan_slab_alloc include/linux/kasan.h:201 [inline]
 slab_post_alloc_hook mm/slub.c:3988 [inline]
 slab_alloc_node mm/slub.c:4037 [inline]
 kmem_cache_alloc_node_noprof+0x16b/0x320 mm/slub.c:4080
 __alloc_skb+0x1c3/0x440 net/core/skbuff.c:667
 alloc_skb include/linux/skbuff.h:1320 [inline]
 alloc_skb_with_frags+0xc3/0x770 net/core/skbuff.c:6528
 sock_alloc_send_pskb+0x91a/0xa60 net/core/sock.c:2815
 sock_alloc_send_skb include/net/sock.h:1778 [inline]
 queue_oob+0x108/0x680 net/unix/af_unix.c:2198
 unix_stream_sendmsg+0xd24/0xf80 net/unix/af_unix.c:2351
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg+0x221/0x270 net/socket.c:745
 ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597
 ___sys_sendmsg net/socket.c:2651 [inline]
 __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2680
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 5235:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579
 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240
 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
 kasan_slab_free include/linux/kasan.h:184 [inline]
 slab_free_hook mm/slub.c:2252 [inline]
 slab_free mm/slub.c:4473 [inline]
 kmem_cache_free+0x145/0x350 mm/slub.c:4548
 unix_stream_read_generic+0x1ef6/0x2520 net/unix/af_unix.c:2917
 unix_stream_recvmsg+0x22b/0x2c0 net/unix/af_unix.c:2996
 sock_recvmsg_nosec net/socket.c:1046 [inline]
 sock_recvmsg+0x22f/0x280 net/socket.c:1068
 __sys_recvfrom+0x256/0x3e0 net/socket.c:2255
 __do_sys_recvfrom net/socket.c:2273 [inline]
 __se_sys_recvfrom net/socket.c:2269 [inline]
 __x64_sys_recvfrom+0xde/0x100 net/socket.c:2269
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The buggy address belongs to the object at ffff8880326abc80
 which belongs to the cache skbuff_head_cache of size 240
The buggy address is located 68 bytes inside of
 freed 240-byte region [ffff8880326abc80, ffff8880326abd70)

The buggy address belongs to the physical page:
page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x326ab
ksm flags: 0xfff00000000000(node=0|zone=1|lastcpupid=0x7ff)
page_type: 0xfdffffff(slab)
raw: 00fff00000000000 ffff88801eaee780 ffffea0000b7dc80 dead000000000003
raw: 0000000000000000 00000000800c000c 00000001fdffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 0, migratetype Unmovable, gfp_mask 0x52cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP), pid 4686, tgid 4686 (udevadm), ts 32357469485, free_ts 28829011109
 set_page_owner include/linux/page_owner.h:32 [inline]
 post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1493
 prep_new_page mm/page_alloc.c:1501 [inline]
 get_page_from_freelist+0x2e4c/0x2f10 mm/page_alloc.c:3439
 __alloc_pages_noprof+0x256/0x6c0 mm/page_alloc.c:4695
 __alloc_pages_node_noprof include/linux/gfp.h:269 [inline]
 alloc_pages_node_noprof include/linux/gfp.h:296 [inline]
 alloc_slab_page+0x5f/0x120 mm/slub.c:2321
 allocate_slab+0x5a/0x2f0 mm/slub.c:2484
 new_slab mm/slub.c:2537 [inline]
 ___slab_alloc+0xcd1/0x14b0 mm/slub.c:3723
 __slab_alloc+0x58/0xa0 mm/slub.c:3813
 __slab_alloc_node mm/slub.c:3866 [inline]
 slab_alloc_node mm/slub.c:4025 [inline]
 kmem_cache_alloc_node_noprof+0x1fe/0x320 mm/slub.c:4080
 __alloc_skb+0x1c3/0x440 net/core/skbuff.c:667
 alloc_skb include/linux/skbuff.h:1320 [inline]
 alloc_uevent_skb+0x74/0x230 lib/kobject_uevent.c:289
 uevent_net_broadcast_untagged lib/kobject_uevent.c:326 [inline]
 kobject_uevent_net_broadcast+0x2fd/0x580 lib/kobject_uevent.c:410
 kobject_uevent_env+0x57d/0x8e0 lib/kobject_uevent.c:608
 kobject_synth_uevent+0x4ef/0xae0 lib/kobject_uevent.c:207
 uevent_store+0x4b/0x70 drivers/base/bus.c:633
 kernfs_fop_write_iter+0x3a1/0x500 fs/kernfs/file.c:334
 new_sync_write fs/read_write.c:497 [inline]
 vfs_write+0xa72/0xc90 fs/read_write.c:590
page last free pid 1 tgid 1 stack trace:
 reset_page_owner include/linux/page_owner.h:25 [inline]
 free_pages_prepare mm/page_alloc.c:1094 [inline]
 free_unref_page+0xd22/0xea0 mm/page_alloc.c:2612
 kasan_depopulate_vmalloc_pte+0x74/0x90 mm/kasan/shadow.c:408
 apply_to_pte_range mm/memory.c:2797 [inline]
 apply_to_pmd_range mm/memory.c:2841 [inline]
 apply_to_pud_range mm/memory.c:2877 [inline]
 apply_to_p4d_range mm/memory.c:2913 [inline]
 __apply_to_page_range+0x8a8/0xe50 mm/memory.c:2947
 kasan_release_vmalloc+0x9a/0xb0 mm/kasan/shadow.c:525
 purge_vmap_node+0x3e3/0x770 mm/vmalloc.c:2208
 __purge_vmap_area_lazy+0x708/0xae0 mm/vmalloc.c:2290
 _vm_unmap_aliases+0x79d/0x840 mm/vmalloc.c:2885
 change_page_attr_set_clr+0x2fe/0xdb0 arch/x86/mm/pat/set_memory.c:1881
 change_page_attr_set arch/x86/mm/pat/set_memory.c:1922 [inline]
 set_memory_nx+0xf2/0x130 arch/x86/mm/pat/set_memory.c:2110
 free_init_pages arch/x86/mm/init.c:924 [inline]
 free_kernel_image_pages arch/x86/mm/init.c:943 [inline]
 free_initmem+0x79/0x110 arch/x86/mm/init.c:970
 kernel_init+0x31/0x2b0 init/main.c:1476
 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

Memory state around the buggy address:
 ffff8880326abb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff8880326abc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc
>ffff8880326abc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                           ^
 ffff8880326abd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc
 ffff8880326abd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb

Fixes: 93c99f21db36 ("af_unix: Don't stop recv(MSG_DONTWAIT) if consumed OOB skb is at the head.")
Reported-by: syzbot+8811381d455e3e9ec788@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=8811381d455e3e9ec788
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240905193240.17565-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c                            |  9 +++++++--
 tools/testing/selftests/net/af_unix/msg_oob.c | 23 +++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 159d78fc3d14..001ccc55ef0f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2673,7 +2673,8 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 			__skb_unlink(read_skb, &sk->sk_receive_queue);
 		}
 
-		goto unlock;
+		if (!skb)
+			goto unlock;
 	}
 
 	if (skb != u->oob_skb)
@@ -3175,9 +3176,13 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			skb = skb_peek(&sk->sk_receive_queue);
 			if (skb) {
 				struct sk_buff *oob_skb = READ_ONCE(u->oob_skb);
+				struct sk_buff *next_skb;
+
+				next_skb = skb_peek_next(skb, &sk->sk_receive_queue);
 
 				if (skb == oob_skb ||
-				    (!oob_skb && !unix_skb_len(skb)))
+				    (!unix_skb_len(skb) &&
+				     (!oob_skb || next_skb == oob_skb)))
 					answ = 1;
 			}
 
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 535eb2c3d7d1..3ed3882a93b8 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -525,6 +525,29 @@ TEST_F(msg_oob, ex_oob_drop_2)
 	}
 }
 
+TEST_F(msg_oob, ex_oob_oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("", -EAGAIN, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("", -EINVAL, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(false);
+}
+
 TEST_F(msg_oob, ex_oob_ahead_break)
 {
 	sendpair("hello", 5, MSG_OOB);
-- 
cgit v1.3-3-g829e


From 969431d2b0df7e926169b211164f534be5098f8e Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 5 Sep 2024 12:49:32 -0700
Subject: net: ag71xx: add COMPILE_TEST to test compilation

While this driver is meant for MIPS only, it can be compiled on x86 just
fine. Remove pointless parentheses while at it.

Enables CI building of this driver.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240905194938.8453-2-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/atheros/Kconfig b/drivers/net/ethernet/atheros/Kconfig
index 482c58c4c584..bec5cdf8d1da 100644
--- a/drivers/net/ethernet/atheros/Kconfig
+++ b/drivers/net/ethernet/atheros/Kconfig
@@ -6,7 +6,7 @@
 config NET_VENDOR_ATHEROS
 	bool "Atheros devices"
 	default y
-	depends on (PCI || ATH79)
+	depends on PCI || ATH79 || COMPILE_TEST
 	help
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 
@@ -19,7 +19,7 @@ if NET_VENDOR_ATHEROS
 
 config AG71XX
 	tristate "Atheros AR7XXX/AR9XXX built-in ethernet mac support"
-	depends on ATH79
+	depends on ATH79 || COMPILE_TEST
 	select PHYLINK
 	imply NET_SELFTESTS
 	help
-- 
cgit v1.3-3-g829e


From 7c3736a12938112a4d1c007156272b7036ce4981 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 5 Sep 2024 12:49:33 -0700
Subject: net: ag71xx: add MODULE_DESCRIPTION

Now that COMPILE_TEST is enabled, it gets flagged when building with
allmodconfig W=1 builds. Text taken from the beginning of the file.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240905194938.8453-3-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index db2a8ade6205..e7da70f14f06 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -2033,4 +2033,5 @@ static struct platform_driver ag71xx_driver = {
 };
 
 module_platform_driver(ag71xx_driver);
+MODULE_DESCRIPTION("Atheros AR71xx built-in ethernet mac driver");
 MODULE_LICENSE("GPL v2");
-- 
cgit v1.3-3-g829e


From 28540850577b269a881f5f7b579ba93ea670abb5 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 5 Sep 2024 12:49:34 -0700
Subject: net: ag71xx: update FIFO bits and descriptions

Taken from QCA SDK. No functional difference as same bits get applied.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240905194938.8453-4-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 48 +++++++++++++++++------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index e7da70f14f06..74e01ce6161f 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -149,11 +149,11 @@
 #define FIFO_CFG4_MC		BIT(8)	/* Multicast Packet */
 #define FIFO_CFG4_BC		BIT(9)	/* Broadcast Packet */
 #define FIFO_CFG4_DR		BIT(10)	/* Dribble */
-#define FIFO_CFG4_LE		BIT(11)	/* Long Event */
-#define FIFO_CFG4_CF		BIT(12)	/* Control Frame */
-#define FIFO_CFG4_PF		BIT(13)	/* Pause Frame */
-#define FIFO_CFG4_UO		BIT(14)	/* Unsupported Opcode */
-#define FIFO_CFG4_VT		BIT(15)	/* VLAN tag detected */
+#define FIFO_CFG4_CF		BIT(11)	/* Control Frame */
+#define FIFO_CFG4_PF		BIT(12)	/* Pause Frame */
+#define FIFO_CFG4_UO		BIT(13)	/* Unsupported Opcode */
+#define FIFO_CFG4_VT		BIT(14)	/* VLAN tag detected */
+#define FIFO_CFG4_LE		BIT(15)	/* Long Event */
 #define FIFO_CFG4_FT		BIT(16)	/* Frame Truncated */
 #define FIFO_CFG4_UC		BIT(17)	/* Unicast Packet */
 #define FIFO_CFG4_INIT	(FIFO_CFG4_DE | FIFO_CFG4_DV | FIFO_CFG4_FC | \
@@ -168,28 +168,28 @@
 #define FIFO_CFG5_DV		BIT(1)	/* RX_DV Event */
 #define FIFO_CFG5_FC		BIT(2)	/* False Carrier */
 #define FIFO_CFG5_CE		BIT(3)	/* Code Error */
-#define FIFO_CFG5_LM		BIT(4)	/* Length Mismatch */
-#define FIFO_CFG5_LO		BIT(5)	/* Length Out of Range */
-#define FIFO_CFG5_OK		BIT(6)	/* Packet is OK */
-#define FIFO_CFG5_MC		BIT(7)	/* Multicast Packet */
-#define FIFO_CFG5_BC		BIT(8)	/* Broadcast Packet */
-#define FIFO_CFG5_DR		BIT(9)	/* Dribble */
-#define FIFO_CFG5_CF		BIT(10)	/* Control Frame */
-#define FIFO_CFG5_PF		BIT(11)	/* Pause Frame */
-#define FIFO_CFG5_UO		BIT(12)	/* Unsupported Opcode */
-#define FIFO_CFG5_VT		BIT(13)	/* VLAN tag detected */
-#define FIFO_CFG5_LE		BIT(14)	/* Long Event */
-#define FIFO_CFG5_FT		BIT(15)	/* Frame Truncated */
-#define FIFO_CFG5_16		BIT(16)	/* unknown */
-#define FIFO_CFG5_17		BIT(17)	/* unknown */
+#define FIFO_CFG5_CR		BIT(4)  /* CRC error */
+#define FIFO_CFG5_LM		BIT(5)	/* Length Mismatch */
+#define FIFO_CFG5_LO		BIT(6)	/* Length Out of Range */
+#define FIFO_CFG5_OK		BIT(7)	/* Packet is OK */
+#define FIFO_CFG5_MC		BIT(8)	/* Multicast Packet */
+#define FIFO_CFG5_BC		BIT(9)	/* Broadcast Packet */
+#define FIFO_CFG5_DR		BIT(10)	/* Dribble */
+#define FIFO_CFG5_CF		BIT(11)	/* Control Frame */
+#define FIFO_CFG5_PF		BIT(12)	/* Pause Frame */
+#define FIFO_CFG5_UO		BIT(13)	/* Unsupported Opcode */
+#define FIFO_CFG5_VT		BIT(14)	/* VLAN tag detected */
+#define FIFO_CFG5_LE		BIT(15)	/* Long Event */
+#define FIFO_CFG5_FT		BIT(16)	/* Frame Truncated */
+#define FIFO_CFG5_UC		BIT(17)	/* Unicast Packet */
 #define FIFO_CFG5_SF		BIT(18)	/* Short Frame */
 #define FIFO_CFG5_BM		BIT(19)	/* Byte Mode */
 #define FIFO_CFG5_INIT	(FIFO_CFG5_DE | FIFO_CFG5_DV | FIFO_CFG5_FC | \
-			 FIFO_CFG5_CE | FIFO_CFG5_LO | FIFO_CFG5_OK | \
-			 FIFO_CFG5_MC | FIFO_CFG5_BC | FIFO_CFG5_DR | \
-			 FIFO_CFG5_CF | FIFO_CFG5_PF | FIFO_CFG5_VT | \
-			 FIFO_CFG5_LE | FIFO_CFG5_FT | FIFO_CFG5_16 | \
-			 FIFO_CFG5_17 | FIFO_CFG5_SF)
+			 FIFO_CFG5_CE | FIFO_CFG5_LM | FIFO_CFG5_LO | \
+			 FIFO_CFG5_OK | FIFO_CFG5_MC | FIFO_CFG5_BC | \
+			 FIFO_CFG5_DR | FIFO_CFG5_CF | FIFO_CFG5_UO | \
+			 FIFO_CFG5_VT | FIFO_CFG5_LE | FIFO_CFG5_FT | \
+			 FIFO_CFG5_UC | FIFO_CFG5_SF)
 
 #define AG71XX_REG_TX_CTRL	0x0180
 #define TX_CTRL_TXE		BIT(0)	/* Tx Enable */
-- 
cgit v1.3-3-g829e


From 441a2798623cc3eefd936b33a9cf8d1973b6688b Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 5 Sep 2024 12:49:35 -0700
Subject: net: ag71xx: use ethtool_puts

Allows simplifying get_strings and avoids manual pointer manipulation.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240905194938.8453-5-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 74e01ce6161f..35db6912e845 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -509,8 +509,7 @@ static void ag71xx_ethtool_get_strings(struct net_device *netdev, u32 sset,
 	switch (sset) {
 	case ETH_SS_STATS:
 		for (i = 0; i < ARRAY_SIZE(ag71xx_statistics); i++)
-			memcpy(data + i * ETH_GSTRING_LEN,
-			       ag71xx_statistics[i].name, ETH_GSTRING_LEN);
+			ethtool_puts(&data, ag71xx_statistics[i].name);
 		break;
 	case ETH_SS_TEST:
 		net_selftest_get_strings(data);
-- 
cgit v1.3-3-g829e


From bfff5d8e211189396c8f9841d0b027f13452b162 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 5 Sep 2024 12:49:36 -0700
Subject: net: ag71xx: get reset control using devm api

Currently, the of variant is missing reset_control_put in error paths.
The devm variant does not require it.

Allows removing mdio_reset from the struct as it is not used outside the
function.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240905194938.8453-6-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 35db6912e845..a32a72fa4179 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -379,7 +379,6 @@ struct ag71xx {
 	u32 fifodata[3];
 	int mac_idx;
 
-	struct reset_control *mdio_reset;
 	struct clk *clk_mdio;
 };
 
@@ -689,6 +688,7 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 {
 	struct device *dev = &ag->pdev->dev;
 	struct net_device *ndev = ag->ndev;
+	struct reset_control *mdio_reset;
 	static struct mii_bus *mii_bus;
 	struct device_node *np, *mnp;
 	int err;
@@ -705,10 +705,10 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	if (!mii_bus)
 		return -ENOMEM;
 
-	ag->mdio_reset = of_reset_control_get_exclusive(np, "mdio");
-	if (IS_ERR(ag->mdio_reset)) {
+	mdio_reset = devm_reset_control_get_exclusive(dev, "mdio");
+	if (IS_ERR(mdio_reset)) {
 		netif_err(ag, probe, ndev, "Failed to get reset mdio.\n");
-		return PTR_ERR(ag->mdio_reset);
+		return PTR_ERR(mdio_reset);
 	}
 
 	mii_bus->name = "ag71xx_mdio";
@@ -719,10 +719,10 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	mii_bus->parent = dev;
 	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "%s.%d", np->name, ag->mac_idx);
 
-	if (!IS_ERR(ag->mdio_reset)) {
-		reset_control_assert(ag->mdio_reset);
+	if (!IS_ERR(mdio_reset)) {
+		reset_control_assert(mdio_reset);
 		msleep(100);
-		reset_control_deassert(ag->mdio_reset);
+		reset_control_deassert(mdio_reset);
 		msleep(200);
 	}
 
-- 
cgit v1.3-3-g829e


From 40f111cc6e1b35562e815170d8f7efb49bf0fb21 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Thu, 5 Sep 2024 12:49:37 -0700
Subject: net: ag71xx: remove always true branch

The opposite of this condition is checked above and if true, function
returns. Which means this can never be false.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20240905194938.8453-7-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index a32a72fa4179..e28a4b018b11 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -719,12 +719,10 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	mii_bus->parent = dev;
 	snprintf(mii_bus->id, MII_BUS_ID_SIZE, "%s.%d", np->name, ag->mac_idx);
 
-	if (!IS_ERR(mdio_reset)) {
-		reset_control_assert(mdio_reset);
-		msleep(100);
-		reset_control_deassert(mdio_reset);
-		msleep(200);
-	}
+	reset_control_assert(mdio_reset);
+	msleep(100);
+	reset_control_deassert(mdio_reset);
+	msleep(200);
 
 	mnp = of_get_child_by_name(np, "mdio");
 	err = devm_of_mdiobus_register(dev, mii_bus, mnp);
-- 
cgit v1.3-3-g829e


From 8410adf2e38ad32f20edf6d90e049a8203f51d9e Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 5 Sep 2024 12:49:38 -0700
Subject: net: ag71xx: disable napi interrupts during probe

ag71xx_probe is registering ag71xx_interrupt as handler for gmac0/gmac1
interrupts. The handler is trying to use napi_schedule to handle the
processing of packets. But the netif_napi_add for this device is
called a lot later in ag71xx_probe.

It can therefore happen that a still running gmac0/gmac1 is triggering the
interrupt handler with a bit from AG71XX_INT_POLL set in
AG71XX_REG_INT_STATUS. The handler will then call napi_schedule and the
napi code will crash the system because the ag->napi is not yet
initialized.

The gmcc0/gmac1 must be brought in a state in which it doesn't signal a
AG71XX_INT_POLL related status bits as interrupt before registering the
interrupt handler. ag71xx_hw_start will take care of re-initializing the
AG71XX_REG_INT_ENABLE.

This will become relevant when dual GMAC devices get added here.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240905194938.8453-8-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index e28a4b018b11..96a6189cc31e 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1850,6 +1850,12 @@ static int ag71xx_probe(struct platform_device *pdev)
 	if (!ag->mac_base)
 		return -ENOMEM;
 
+	/* ensure that HW is in manual polling mode before interrupts are
+	 * activated. Otherwise ag71xx_interrupt might call napi_schedule
+	 * before it is initialized by netif_napi_add.
+	 */
+	ag71xx_int_disable(ag, AG71XX_INT_POLL);
+
 	ndev->irq = platform_get_irq(pdev, 0);
 	err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt,
 			       0x0, dev_name(&pdev->dev), ndev);
-- 
cgit v1.3-3-g829e


From dbd61921a6adbd231d8ca91537f1e7b62e9fea61 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 5 Sep 2024 19:15:51 -0400
Subject: selftests: support interpreted scripts with ksft_runner.sh

Support testcases that are themselves not executable, but need an
interpreter to run them.

If a test file is not executable, but an executable file
ksft_runner.sh exists in the TARGET dir, kselftest will run

    ./ksft_runner.sh ./$BASENAME_TEST

Packetdrill may add hundreds of packetdrill scripts for testing. These
scripts must be passed to the packetdrill process.

Have kselftest run each test directly, as it already solves common
runner requirements like parallel execution and isolation (netns).
A previous RFC added a wrapper in between, which would have to
reimplement such functionality.

Link: https://lore.kernel.org/netdev/66d4d97a4cac_3df182941a@willemb.c.googlers.com.notmuch/T/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240905231653.2427327-2-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/kselftest/runner.sh | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 74954f6a8f94..2c3c58e65a41 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -111,8 +111,11 @@ run_one()
 			stdbuf="/usr/bin/stdbuf --output=L "
 		fi
 		eval kselftest_cmd_args="\$${kselftest_cmd_args_ref:-}"
-		cmd="$stdbuf ./$BASENAME_TEST $kselftest_cmd_args"
-		if [ ! -x "$TEST" ]; then
+		if [ -x "$TEST" ]; then
+			cmd="$stdbuf ./$BASENAME_TEST $kselftest_cmd_args"
+		elif [ -x "./ksft_runner.sh" ]; then
+			cmd="$stdbuf ./ksft_runner.sh ./$BASENAME_TEST"
+		else
 			echo "# Warning: file $TEST is not executable"
 
 			if [ $(head -n 1 "$TEST" | cut -c -2) = "#!" ]
-- 
cgit v1.3-3-g829e


From 8a405552fd3b1eefe186e724343e88790f6be832 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 5 Sep 2024 19:15:52 -0400
Subject: selftests/net: integrate packetdrill with ksft

Lay the groundwork to import into kselftests the over 150 packetdrill
TCP/IP conformance tests on github.com/google/packetdrill.

Florian recently added support for packetdrill tests in nf_conntrack,
in commit a8a388c2aae49 ("selftests: netfilter: add packetdrill based
conntrack tests").

This patch takes a slightly different approach. It relies on
ksft_runner.sh to run every *.pkt file in the directory.

Any future imports of packetdrill tests should require no additional
coding. Just add the *.pkt files.

Initially import only two features/directories from github. One with a
single script, and one with two. This was the only reason to pick
tcp/inq and tcp/md5.

The path replaces the directory hierarchy in github with a flat space
of files: $(subst /,_,$(wildcard tcp/**/*.pkt)). This is the most
straightforward option to integrate with kselftests. The Linked thread
reviewed two ways to maintain the hierarchy: TEST_PROGS_RECURSE and
PRESERVE_TEST_DIRS. But both introduce significant changes to
kselftest infra and with that risk to existing tests.

Implementation notes:
- restore alphabetical order when adding the new directory to
  tools/testing/selftests/Makefile
- imported *.pkt files and support verbatim from the github project,
  except for
    - update `source ./defaults.sh` path (to adjust for flat dir)
    - add SPDX headers
    - remove one author statement
    - Acknowledgment: drop an e (checkpatch)

Tested:
	make -C tools/testing/selftests \
	  TARGETS=net/packetdrill \
	  run_tests

	make -C tools/testing/selftests \
	  TARGETS=net/packetdrill \
	  install INSTALL_PATH=$KSFT_INSTALL_PATH

	# in virtme-ng
	./run_kselftest.sh -c net/packetdrill
	./run_kselftest.sh -t net/packetdrill:tcp_inq_client.pkt

Link: https://lore.kernel.org/netdev/20240827193417.2792223-1-willemdebruijn.kernel@gmail.com/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240905231653.2427327-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/Makefile                   |  5 +-
 tools/testing/selftests/net/packetdrill/Makefile   |  9 ++++
 tools/testing/selftests/net/packetdrill/config     |  5 ++
 .../testing/selftests/net/packetdrill/defaults.sh  | 63 ++++++++++++++++++++++
 .../selftests/net/packetdrill/ksft_runner.sh       | 41 ++++++++++++++
 .../selftests/net/packetdrill/tcp_inq_client.pkt   | 51 ++++++++++++++++++
 .../selftests/net/packetdrill/tcp_inq_server.pkt   | 51 ++++++++++++++++++
 .../packetdrill/tcp_md5_md5-only-on-client-ack.pkt | 28 ++++++++++
 8 files changed, 251 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/net/packetdrill/Makefile
 create mode 100644 tools/testing/selftests/net/packetdrill/config
 create mode 100755 tools/testing/selftests/net/packetdrill/defaults.sh
 create mode 100755 tools/testing/selftests/net/packetdrill/ksft_runner.sh
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_md5_md5-only-on-client-ack.pkt

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index a5f1c0c27dff..3b7df5477317 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -65,10 +65,11 @@ TARGETS += net/af_unix
 TARGETS += net/forwarding
 TARGETS += net/hsr
 TARGETS += net/mptcp
-TARGETS += net/openvswitch
-TARGETS += net/tcp_ao
 TARGETS += net/netfilter
+TARGETS += net/openvswitch
+TARGETS += net/packetdrill
 TARGETS += net/rds
+TARGETS += net/tcp_ao
 TARGETS += nsfs
 TARGETS += perf_events
 TARGETS += pidfd
diff --git a/tools/testing/selftests/net/packetdrill/Makefile b/tools/testing/selftests/net/packetdrill/Makefile
new file mode 100644
index 000000000000..870f7258dc8d
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+TEST_INCLUDES := ksft_runner.sh \
+		 defaults.sh \
+		 ../../kselftest/ktap_helpers.sh
+
+TEST_PROGS := $(wildcard *.pkt)
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/packetdrill/config b/tools/testing/selftests/net/packetdrill/config
new file mode 100644
index 000000000000..0d402830f18d
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/config
@@ -0,0 +1,5 @@
+CONFIG_IPV6=y
+CONFIG_NET_SCH_FIFO=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_TUN=y
diff --git a/tools/testing/selftests/net/packetdrill/defaults.sh b/tools/testing/selftests/net/packetdrill/defaults.sh
new file mode 100755
index 000000000000..1095a7b22f44
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/defaults.sh
@@ -0,0 +1,63 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Set standard production config values that relate to TCP behavior.
+
+# Flush old cached data (fastopen cookies).
+ip tcp_metrics flush all > /dev/null 2>&1
+
+# TCP min, default, and max receive and send buffer sizes.
+sysctl -q net.ipv4.tcp_rmem="4096 540000 $((15*1024*1024))"
+sysctl -q net.ipv4.tcp_wmem="4096 $((256*1024)) 4194304"
+
+# TCP timestamps.
+sysctl -q net.ipv4.tcp_timestamps=1
+
+# TCP SYN(ACK) retry thresholds
+sysctl -q net.ipv4.tcp_syn_retries=5
+sysctl -q net.ipv4.tcp_synack_retries=5
+
+# TCP Forward RTO-Recovery, RFC 5682.
+sysctl -q net.ipv4.tcp_frto=2
+
+# TCP Selective Acknowledgements (SACK)
+sysctl -q net.ipv4.tcp_sack=1
+
+# TCP Duplicate Selective Acknowledgements (DSACK)
+sysctl -q net.ipv4.tcp_dsack=1
+
+# TCP FACK (Forward Acknowldgement)
+sysctl -q net.ipv4.tcp_fack=0
+
+# TCP reordering degree ("dupthresh" threshold for entering Fast Recovery).
+sysctl -q net.ipv4.tcp_reordering=3
+
+# TCP congestion control.
+sysctl -q net.ipv4.tcp_congestion_control=cubic
+
+# TCP slow start after idle.
+sysctl -q net.ipv4.tcp_slow_start_after_idle=0
+
+# TCP RACK and TLP.
+sysctl -q net.ipv4.tcp_early_retrans=4 net.ipv4.tcp_recovery=1
+
+# TCP method for deciding when to defer sending to accumulate big TSO packets.
+sysctl -q net.ipv4.tcp_tso_win_divisor=3
+
+# TCP Explicit Congestion Notification (ECN)
+sysctl -q net.ipv4.tcp_ecn=0
+
+sysctl -q net.ipv4.tcp_pacing_ss_ratio=200
+sysctl -q net.ipv4.tcp_pacing_ca_ratio=120
+sysctl -q net.ipv4.tcp_notsent_lowat=4294967295 > /dev/null 2>&1
+
+sysctl -q net.ipv4.tcp_fastopen=0x70403
+sysctl -q net.ipv4.tcp_fastopen_key=a1a1a1a1-b2b2b2b2-c3c3c3c3-d4d4d4d4
+
+sysctl -q net.ipv4.tcp_syncookies=1
+
+# Override the default qdisc on the tun device.
+# Many tests fail with timing errors if the default
+# is FQ and that paces their flows.
+tc qdisc add dev tun0 root pfifo
+
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
new file mode 100755
index 000000000000..2f62caccbbbc
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -0,0 +1,41 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source "$(dirname $(realpath $0))/../../kselftest/ktap_helpers.sh"
+
+readonly ipv4_args=('--ip_version=ipv4 '
+		    '--local_ip=192.168.0.1 '
+		    '--gateway_ip=192.168.0.1 '
+		    '--netmask_ip=255.255.0.0 '
+		    '--remote_ip=192.0.2.1 '
+		    '-D CMSG_LEVEL_IP=SOL_IP '
+		    '-D CMSG_TYPE_RECVERR=IP_RECVERR ')
+
+readonly ipv6_args=('--ip_version=ipv6 '
+		    '--mtu=1520 '
+		    '--local_ip=fd3d:0a0b:17d6::1 '
+		    '--gateway_ip=fd3d:0a0b:17d6:8888::1 '
+		    '--remote_ip=fd3d:fa7b:d17d::1 '
+		    '-D CMSG_LEVEL_IP=SOL_IPV6 '
+		    '-D CMSG_TYPE_RECVERR=IPV6_RECVERR ')
+
+if [ $# -ne 1 ]; then
+	ktap_exit_fail_msg "usage: $0 <script>"
+	exit "$KSFT_FAIL"
+fi
+script="$1"
+
+if [ -z "$(which packetdrill)" ]; then
+	ktap_skip_all "packetdrill not found in PATH"
+	exit "$KSFT_SKIP"
+fi
+
+ktap_print_header
+ktap_set_plan 2
+
+packetdrill ${ipv4_args[@]} $(basename $script) > /dev/null \
+	&& ktap_test_pass "ipv4" || ktap_test_fail "ipv4"
+packetdrill ${ipv6_args[@]} $(basename $script) > /dev/null \
+	&& ktap_test_pass "ipv6" || ktap_test_fail "ipv6"
+
+ktap_finished
diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt
new file mode 100644
index 000000000000..df49c67645ac
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_inq_client.pkt
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP_INQ and TCP_CM_INQ on the client side.
+`./defaults.sh
+`
+
+// Create a socket and set it to non-blocking.
+    0	socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0	fcntl(3, F_GETFL) = 0x2 (flags O_RDWR)
+   +0	fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+
+// Connect to the server and enable TCP_INQ.
+   +0	connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+   +0	setsockopt(3, SOL_TCP, TCP_INQ, [1], 4) = 0
+
+   +0	> S 0:0(0) <mss 1460,sackOK,TS val 100 ecr 0,nop,wscale 8>
+ +.01	< S. 0:0(0) ack 1 win 5792 <mss 1460,sackOK,TS val 700 ecr 100,nop,wscale 7>
+   +0	> . 1:1(0) ack 1 <nop,nop,TS val 200 ecr 700>
+
+// Now we have 10K of data ready on the socket.
+   +0	< . 1:10001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 10001 <nop,nop,TS val 200 ecr 700>
+
+// We read 1K and we should have 9K ready to read.
+   +0	recvmsg(3, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 1000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=9000}]}, 0) = 1000
+// We read 9K and we should have no further data ready to read.
+   +0	recvmsg(3, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 9000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=0}]}, 0) = 9000
+
+// Server sends more data and closes the connections.
+   +0	< F. 10001:20001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 20002 <nop,nop,TS val 200 ecr 700>
+
+// We read 10K and we should have one "fake" byte because the connection is
+// closed.
+   +0	recvmsg(3, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 10000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=1}]}, 0) = 10000
+// Now, receive EOF.
+   +0	read(3, ..., 2000) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt
new file mode 100644
index 000000000000..04a5e2590c62
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_inq_server.pkt
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test TCP_INQ and TCP_CM_INQ on the server side.
+`./defaults.sh
+`
+
+// Initialize connection
+    0	socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0	setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0	bind(3, ..., ...) = 0
+   +0	listen(3, 1) = 0
+
+   +0	< S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+   +0	> S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+ +.01	< . 1:1(0) ack 1 win 514
+
+// Accept the connection and enable TCP_INQ.
+   +0	accept(3, ..., ...) = 4
+   +0	setsockopt(4, SOL_TCP, TCP_INQ, [1], 4) = 0
+
+// Now we have 10K of data ready on the socket.
+   +0	< . 1:10001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 10001
+
+// We read 2K and we should have 8K ready to read.
+   +0	recvmsg(4, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 2000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=8000}]}, 0) = 2000
+// We read 8K and we should have no further data ready to read.
+   +0	recvmsg(4, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 8000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=0}]}, 0) = 8000
+// Client sends more data and closes the connections.
+   +0	< F. 10001:20001(10000) ack 1 win 514
+   +0	> . 1:1(0) ack 20002
+
+// We read 10K and we should have one "fake" byte because the connection is
+// closed.
+   +0	recvmsg(4, {msg_name(...)=...,
+		    msg_iov(1)=[{..., 10000}],
+		    msg_flags=0,
+		    msg_control=[{cmsg_level=SOL_TCP,
+				  cmsg_type=TCP_CM_INQ,
+				  cmsg_data=1}]}, 0) = 10000
+// Now, receive error.
+   +0	read(3, ..., 2000) = -1 ENOTCONN (Transport endpoint is not connected)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_md5_md5-only-on-client-ack.pkt b/tools/testing/selftests/net/packetdrill/tcp_md5_md5-only-on-client-ack.pkt
new file mode 100644
index 000000000000..25dfef95d3f8
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_md5_md5-only-on-client-ack.pkt
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test what happens when client does not provide MD5 on SYN,
+// but then does on the ACK that completes the three-way handshake.
+
+`./defaults.sh`
+
+// Establish a connection.
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 10>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+// Ooh, weird: client provides MD5 option on the ACK:
+ +.01 < . 1:1(0) ack 1 win 514 <md5 000102030405060708090a0b0c0d0e0f,nop,nop>
+ +.01 < . 1:1(0) ack 1 win 514 <md5 000102030405060708090a0b0c0d0e0f,nop,nop>
+
+// The TCP listener refcount should be 2, but on buggy kernels it can be 0:
+   +0 `grep " 0A " /proc/net/tcp /proc/net/tcp6 | grep ":1F90"`
+
+// Now here comes the legit ACK:
+ +.01 < . 1:1(0) ack 1 win 514
+
+// Make sure the connection is OK:
+   +0 accept(3, ..., ...) = 4
+
+ +.01 write(4, ..., 1000) = 1000
-- 
cgit v1.3-3-g829e


From 5aa3b55bb312c389bc7bf9d8c220d7cc5cab04a3 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Fri, 6 Sep 2024 08:36:09 +0100
Subject: net: ibm: emac: Use __iomem annotation for emac_[xg]aht_base

dev->emacp contains an __iomem pointer and values derived
from it are used as __iomem pointers. So use this annotation
in the return type for helpers that derive pointers from dev->emacp.

Flagged by Sparse as:

.../core.c:444:36: warning: incorrect type in argument 1 (different address spaces)
.../core.c:444:36:    expected unsigned int volatile [noderef] [usertype] __iomem *addr
.../core.c:444:36:    got unsigned int [usertype] *
.../core.c: note: in included file:
.../core.h:416:25: warning: cast removes address space '__iomem' of expression

Compile tested only.
No functional change intended.

Signed-off-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240906-emac-iomem-v1-1-207cc4f3fed0@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 2 +-
 drivers/net/ethernet/ibm/emac/core.h | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index a19d098f2e2b..6ace55837172 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -418,8 +418,8 @@ do_retry:
 
 static void emac_hash_mc(struct emac_instance *dev)
 {
+	u32 __iomem *gaht_base = emac_gaht_base(dev);
 	const int regs = EMAC_XAHT_REGS(dev);
-	u32 *gaht_base = emac_gaht_base(dev);
 	u32 gaht_temp[EMAC_XAHT_MAX_REGS];
 	struct netdev_hw_addr *ha;
 	int i;
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 295516b07662..d8664bd65e1f 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -400,7 +400,7 @@ static inline int emac_has_feature(struct emac_instance *dev,
 	((u32)(1 << (EMAC_XAHT_WIDTH(dev) - 1)) >>	\
 	 ((slot) & (u32)(EMAC_XAHT_WIDTH(dev) - 1)))
 
-static inline u32 *emac_xaht_base(struct emac_instance *dev)
+static inline u32 __iomem *emac_xaht_base(struct emac_instance *dev)
 {
 	struct emac_regs __iomem *p = dev->emacp;
 	int offset;
@@ -413,10 +413,10 @@ static inline u32 *emac_xaht_base(struct emac_instance *dev)
 	else
 		offset = offsetof(struct emac_regs, u0.emac4.iaht1);
 
-	return (u32 *)((ptrdiff_t)p + offset);
+	return (u32 __iomem *)((__force ptrdiff_t)p + offset);
 }
 
-static inline u32 *emac_gaht_base(struct emac_instance *dev)
+static inline u32 __iomem *emac_gaht_base(struct emac_instance *dev)
 {
 	/* GAHT registers always come after an identical number of
 	 * IAHT registers.
-- 
cgit v1.3-3-g829e


From 9e70eb4a9a8e61105932def55f4667d9a0055381 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Fri, 6 Sep 2024 15:06:49 +0530
Subject: net: ti: icssg-prueth: Make pa_stats optional

pa_stats is optional in dt bindings, make it optional in driver as well.
Currently if pa_stats syscon regmap is not found driver returns -ENODEV.
Fix this by not returning an error in case pa_stats is not found and
continue generating ethtool stats without pa_stats.

Fixes: 550ee90ac61c ("net: ti: icssg-prueth: Add support for PA Stats")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240906093649.870883-1-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_ethtool.c | 17 ++++++++++++-----
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  |  2 +-
 drivers/net/ethernet/ti/icssg/icssg_stats.c   | 21 +++++++++++++--------
 3 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
index 73b6cef10401..b715af21d23a 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c
@@ -68,9 +68,13 @@ static int emac_nway_reset(struct net_device *ndev)
 
 static int emac_get_sset_count(struct net_device *ndev, int stringset)
 {
+	struct prueth_emac *emac = netdev_priv(ndev);
 	switch (stringset) {
 	case ETH_SS_STATS:
-		return ICSSG_NUM_ETHTOOL_STATS;
+		if (emac->prueth->pa_stats)
+			return ICSSG_NUM_ETHTOOL_STATS;
+		else
+			return ICSSG_NUM_ETHTOOL_STATS - ICSSG_NUM_PA_STATS;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -78,6 +82,7 @@ static int emac_get_sset_count(struct net_device *ndev, int stringset)
 
 static void emac_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 {
+	struct prueth_emac *emac = netdev_priv(ndev);
 	u8 *p = data;
 	int i;
 
@@ -86,8 +91,9 @@ static void emac_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 		for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++)
 			if (!icssg_all_miig_stats[i].standard_stats)
 				ethtool_puts(&p, icssg_all_miig_stats[i].name);
-		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++)
-			ethtool_puts(&p, icssg_all_pa_stats[i].name);
+		if (emac->prueth->pa_stats)
+			for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++)
+				ethtool_puts(&p, icssg_all_pa_stats[i].name);
 		break;
 	default:
 		break;
@@ -106,8 +112,9 @@ static void emac_get_ethtool_stats(struct net_device *ndev,
 		if (!icssg_all_miig_stats[i].standard_stats)
 			*(data++) = emac->stats[i];
 
-	for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++)
-		*(data++) = emac->pa_stats[i];
+	if (emac->prueth->pa_stats)
+		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++)
+			*(data++) = emac->pa_stats[i];
 }
 
 static int emac_get_ts_info(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index becdda143c19..6644203d6bb7 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1185,7 +1185,7 @@ static int prueth_probe(struct platform_device *pdev)
 	prueth->pa_stats = syscon_regmap_lookup_by_phandle(np, "ti,pa-stats");
 	if (IS_ERR(prueth->pa_stats)) {
 		dev_err(dev, "couldn't get ti,pa-stats syscon regmap\n");
-		return -ENODEV;
+		prueth->pa_stats = NULL;
 	}
 
 	if (eth0_node) {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 06a15c0b2acc..8800bd3a8d07 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -42,11 +42,14 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 			emac->stats[i] -= tx_pkt_cnt * 8;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
-		reg = ICSSG_FW_STATS_BASE + icssg_all_pa_stats[i].offset *
-		      PRUETH_NUM_MACS + slice * sizeof(u32);
-		regmap_read(prueth->pa_stats, reg, &val);
-		emac->pa_stats[i] += val;
+	if (prueth->pa_stats) {
+		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
+			reg = ICSSG_FW_STATS_BASE +
+			      icssg_all_pa_stats[i].offset *
+			      PRUETH_NUM_MACS + slice * sizeof(u32);
+			regmap_read(prueth->pa_stats, reg, &val);
+			emac->pa_stats[i] += val;
+		}
 	}
 }
 
@@ -70,9 +73,11 @@ int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name)
 			return emac->stats[icssg_all_miig_stats[i].offset / sizeof(u32)];
 	}
 
-	for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
-		if (!strcmp(icssg_all_pa_stats[i].name, stat_name))
-			return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)];
+	if (emac->prueth->pa_stats) {
+		for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) {
+			if (!strcmp(icssg_all_pa_stats[i].name, stat_name))
+				return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)];
+		}
 	}
 
 	netdev_err(emac->ndev, "Invalid stats %s\n", stat_name);
-- 
cgit v1.3-3-g829e


From 3fc85527b08c71eea2bca140e8fd939859a1cdfc Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:17 +0300
Subject: bnxt_en: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://patch.msgid.link/20240906144632.404651-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 7392a716f28d..094e0b5c8521 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -5043,11 +5043,8 @@ static int bnxt_get_ts_info(struct net_device *dev,
 	struct bnxt_ptp_cfg *ptp;
 
 	ptp = bp->ptp_cfg;
-	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 
-	info->phc_index = -1;
 	if (!ptp)
 		return 0;
 
-- 
cgit v1.3-3-g829e


From 0644646d91b2111bad2b776261e6213468b1eb39 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:18 +0300
Subject: tg3: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Link: https://patch.msgid.link/20240906144632.404651-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/tg3.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 0ec5f01551f9..378815917741 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6145,9 +6145,7 @@ static int tg3_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info
 {
 	struct tg3 *tp = netdev_priv(dev);
 
-	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	if (tg3_flag(tp, PTP_CAPABLE)) {
 		info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
@@ -6157,8 +6155,6 @@ static int tg3_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info
 
 	if (tp->ptp_clock)
 		info->phc_index = ptp_clock_index(tp->ptp_clock);
-	else
-		info->phc_index = -1;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
 
-- 
cgit v1.3-3-g829e


From 1db368a040662cff2f7df84e683b8352ba7de4a0 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:19 +0300
Subject: bonding: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-4-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 47ab4ccd6fc1..b560644ee1b1 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -5886,9 +5886,6 @@ static int bond_ethtool_get_ts_info(struct net_device *bond_dev,
 	if (real_dev) {
 		ret = ethtool_get_ts_info_by_layer(real_dev, info);
 	} else {
-		info->phc_index = -1;
-		info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-					SOF_TIMESTAMPING_SOFTWARE;
 		/* Check if all slaves support software tx timestamping */
 		rcu_read_lock();
 		bond_for_each_slave_rcu(bond, slave, iter) {
-- 
cgit v1.3-3-g829e


From 18eb4d0440d8a104e8a10e032b62c3a2217b1e3a Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:20 +0300
Subject: amd-xgbe: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://patch.msgid.link/20240906144632.404651-5-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
index 21407a26f806..5fc94c2f638e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c
@@ -582,16 +582,12 @@ static int xgbe_get_ts_info(struct net_device *netdev,
 	struct xgbe_prv_data *pdata = netdev_priv(netdev);
 
 	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				   SOF_TIMESTAMPING_RX_SOFTWARE |
-				   SOF_TIMESTAMPING_SOFTWARE |
 				   SOF_TIMESTAMPING_TX_HARDWARE |
 				   SOF_TIMESTAMPING_RX_HARDWARE |
 				   SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (pdata->ptp_clock)
 		ts_info->phc_index = ptp_clock_index(pdata->ptp_clock);
-	else
-		ts_info->phc_index = -1;
 
 	ts_info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
 	ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
-- 
cgit v1.3-3-g829e


From a8fe0c07f56c1bd5e8d06fbbde2235ab56266575 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:21 +0300
Subject: net: macb: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Link: https://patch.msgid.link/20240906144632.404651-6-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 8e1e4b2b2386..f06babec04a0 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3410,8 +3410,6 @@ static int gem_get_ts_info(struct net_device *dev,
 
 	info->so_timestamping =
 		SOF_TIMESTAMPING_TX_SOFTWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
@@ -3423,7 +3421,8 @@ static int gem_get_ts_info(struct net_device *dev,
 		(1 << HWTSTAMP_FILTER_NONE) |
 		(1 << HWTSTAMP_FILTER_ALL);
 
-	info->phc_index = bp->ptp_clock ? ptp_clock_index(bp->ptp_clock) : -1;
+	if (bp->ptp_clock)
+		info->phc_index = ptp_clock_index(bp->ptp_clock);
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 441d0a79c950fc01f96f1060cde0bb8258d5f9f1 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:22 +0300
Subject: liquidio: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-7-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 5835965dbc32..c849e2c871a9 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -2496,37 +2496,31 @@ ret_intrmod:
 	return ret;
 }
 
+#ifdef PTP_HARDWARE_TIMESTAMPING
 static int lio_get_ts_info(struct net_device *netdev,
 			   struct kernel_ethtool_ts_info *info)
 {
 	struct lio *lio = GET_LIO(netdev);
 
 	info->so_timestamping =
-#ifdef PTP_HARDWARE_TIMESTAMPING
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE |
-		SOF_TIMESTAMPING_TX_SOFTWARE |
-#endif
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE;
+		SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	if (lio->ptp_clock)
 		info->phc_index = ptp_clock_index(lio->ptp_clock);
-	else
-		info->phc_index = -1;
 
-#ifdef PTP_HARDWARE_TIMESTAMPING
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
 			   (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
 			   (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
-#endif
 
 	return 0;
 }
+#endif
 
 /* Return register dump len. */
 static int lio_get_regs_len(struct net_device *dev)
@@ -3146,7 +3140,9 @@ static const struct ethtool_ops lio_ethtool_ops = {
 	.set_coalesce		= lio_set_intr_coalesce,
 	.get_priv_flags		= lio_get_priv_flags,
 	.set_priv_flags		= lio_set_priv_flags,
+#ifdef PTP_HARDWARE_TIMESTAMPING
 	.get_ts_info		= lio_get_ts_info,
+#endif
 };
 
 static const struct ethtool_ops lio_vf_ethtool_ops = {
@@ -3169,7 +3165,9 @@ static const struct ethtool_ops lio_vf_ethtool_ops = {
 	.set_coalesce		= lio_set_intr_coalesce,
 	.get_priv_flags		= lio_get_priv_flags,
 	.set_priv_flags		= lio_set_priv_flags,
+#ifdef PTP_HARDWARE_TIMESTAMPING
 	.get_ts_info		= lio_get_ts_info,
+#endif
 };
 
 void liquidio_set_ethtool_ops(struct net_device *netdev)
-- 
cgit v1.3-3-g829e


From fedc2e795fd59f0cb7339dc8b5c7642da419ab87 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:23 +0300
Subject: net: thunderx: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-8-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 6a04d2530176..d0ff0c170b1a 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -844,8 +844,6 @@ static int nicvf_get_ts_info(struct net_device *netdev,
 		return ethtool_op_get_ts_info(netdev, info);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From e4e0145ac5ac75472693bc33c72af79f3d786805 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:24 +0300
Subject: enic: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-9-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic_ethtool.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index f2f1055880b2..31685ee304c6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -601,9 +601,7 @@ static int enic_set_rxfh(struct net_device *netdev,
 static int enic_get_ts_info(struct net_device *netdev,
 			    struct kernel_ethtool_ts_info *info)
 {
-	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE;
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 6cba6812a335e9b00fad0b5ce14688d3b6d7be8f Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:25 +0300
Subject: net/funeth: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-10-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/fungible/funeth/funeth_ethtool.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
index 7f081e6e8c87..ba83dbf4ed22 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_ethtool.c
@@ -1042,12 +1042,9 @@ static int fun_set_rxfh(struct net_device *netdev,
 static int fun_get_ts_info(struct net_device *netdev,
 			   struct kernel_ethtool_ts_info *info)
 {
-	info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_HARDWARE |
+	info->so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
-	info->phc_index = -1;
 	info->tx_types = BIT(HWTSTAMP_TX_OFF);
 	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
 	return 0;
-- 
cgit v1.3-3-g829e


From 0de3c713e9b8b1085a1454122268f16aeeb3ee9b Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:26 +0300
Subject: net: mscc: ocelot: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-11-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mscc/ocelot_ptp.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c
index b3c28260adf8..e172638b0601 100644
--- a/drivers/net/ethernet/mscc/ocelot_ptp.c
+++ b/drivers/net/ethernet/mscc/ocelot_ptp.c
@@ -582,17 +582,13 @@ EXPORT_SYMBOL(ocelot_hwstamp_set);
 int ocelot_get_ts_info(struct ocelot *ocelot, int port,
 		       struct kernel_ethtool_ts_info *info)
 {
-	info->phc_index = ocelot->ptp_clock ?
-			  ptp_clock_index(ocelot->ptp_clock) : -1;
-	if (info->phc_index == -1) {
-		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-					 SOF_TIMESTAMPING_RX_SOFTWARE |
-					 SOF_TIMESTAMPING_SOFTWARE;
+	if (ocelot->ptp_clock) {
+		info->phc_index = ptp_clock_index(ocelot->ptp_clock);
+	} else {
+		info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE;
 		return 0;
 	}
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
-				 SOF_TIMESTAMPING_RX_SOFTWARE |
-				 SOF_TIMESTAMPING_SOFTWARE |
 				 SOF_TIMESTAMPING_TX_HARDWARE |
 				 SOF_TIMESTAMPING_RX_HARDWARE |
 				 SOF_TIMESTAMPING_RAW_HARDWARE;
-- 
cgit v1.3-3-g829e


From 36d84998da9f4056bcb671316b3eaa1117e90140 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:27 +0300
Subject: qede: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-12-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qede/qede_ptp.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 63e3dac4d5f7..9d6399a5c780 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -326,25 +326,18 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct kernel_ethtool_ts_info *i
 	struct qede_ptp *ptp = edev->ptp;
 
 	if (!ptp) {
-		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-					SOF_TIMESTAMPING_RX_SOFTWARE |
-					SOF_TIMESTAMPING_SOFTWARE;
-		info->phc_index = -1;
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
 
 		return 0;
 	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
-				SOF_TIMESTAMPING_RX_SOFTWARE |
-				SOF_TIMESTAMPING_SOFTWARE |
 				SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	if (ptp->clock)
 		info->phc_index = ptp_clock_index(ptp->clock);
-	else
-		info->phc_index = -1;
 
 	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
 			   BIT(HWTSTAMP_FILTER_PTP_V1_L4_EVENT) |
-- 
cgit v1.3-3-g829e


From 9d02e6c9513932befd0a02b9673e0576f7b82658 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:28 +0300
Subject: sfc: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://patch.msgid.link/20240906144632.404651-13-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/ethtool.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 848b1923133a..bb1930818beb 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -230,11 +230,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 {
 	struct efx_nic *efx = efx_netdev_priv(net_dev);
 
-	/* Software capabilities */
-	ts_info->so_timestamping = (SOF_TIMESTAMPING_RX_SOFTWARE |
-				    SOF_TIMESTAMPING_SOFTWARE);
-	ts_info->phc_index = -1;
-
 	efx_ptp_get_ts_info(efx, ts_info);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 4c00bb4c519b243c5f7231d153ff43edb4b14ba9 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:29 +0300
Subject: sfc/siena: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://patch.msgid.link/20240906144632.404651-14-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/siena/ethtool.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/sfc/siena/ethtool.c b/drivers/net/ethernet/sfc/siena/ethtool.c
index 88ddc226b012..c5ad84db9613 100644
--- a/drivers/net/ethernet/sfc/siena/ethtool.c
+++ b/drivers/net/ethernet/sfc/siena/ethtool.c
@@ -230,11 +230,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev,
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
-	/* Software capabilities */
-	ts_info->so_timestamping = (SOF_TIMESTAMPING_RX_SOFTWARE |
-				    SOF_TIMESTAMPING_SOFTWARE);
-	ts_info->phc_index = -1;
-
 	efx_siena_ptp_get_ts_info(efx, ts_info);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 9364fa7fcf127514e2b740bc606f719ae5bc5961 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:30 +0300
Subject: net: stmmac: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-15-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 220c582904f4..a45af300bad8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -1200,13 +1200,13 @@ static int stmmac_get_ts_info(struct net_device *dev,
 
 		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
 					SOF_TIMESTAMPING_TX_HARDWARE |
-					SOF_TIMESTAMPING_RX_SOFTWARE |
 					SOF_TIMESTAMPING_RX_HARDWARE |
-					SOF_TIMESTAMPING_SOFTWARE |
 					SOF_TIMESTAMPING_RAW_HARDWARE;
 
 		if (priv->ptp_clock)
 			info->phc_index = ptp_clock_index(priv->ptp_clock);
+		else
+			info->phc_index = 0;
 
 		info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON);
 
-- 
cgit v1.3-3-g829e


From d25e9e178c2ad94be03900e5559e82aabde198a0 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:31 +0300
Subject: ixp4xx_eth: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://patch.msgid.link/20240906144632.404651-16-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xscale/ixp4xx_eth.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 56df37f8d50a..aef316278eb4 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -1026,9 +1026,7 @@ static int ixp4xx_get_ts_info(struct net_device *dev,
 
 	if (info->phc_index < 0) {
 		info->so_timestamping =
-			SOF_TIMESTAMPING_TX_SOFTWARE |
-			SOF_TIMESTAMPING_RX_SOFTWARE |
-			SOF_TIMESTAMPING_SOFTWARE;
+			SOF_TIMESTAMPING_TX_SOFTWARE;
 		return 0;
 	}
 	info->so_timestamping =
-- 
cgit v1.3-3-g829e


From f8e82440d95940627672100ebf08b76a9702feae Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Fri, 6 Sep 2024 17:46:32 +0300
Subject: ptp: ptp_ines: Remove setting of RX software timestamp

The responsibility for reporting of RX software timestamp has moved to
the core layer (see __ethtool_get_ts_info()), remove usage from the
device drivers.

Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20240906144632.404651-17-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_ines.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c
index e6f7d2bf8dde..14a23d3a27f2 100644
--- a/drivers/ptp/ptp_ines.c
+++ b/drivers/ptp/ptp_ines.c
@@ -562,12 +562,8 @@ static int ines_ts_info(struct mii_timestamper *mii_ts,
 		SOF_TIMESTAMPING_TX_HARDWARE |
 		SOF_TIMESTAMPING_TX_SOFTWARE |
 		SOF_TIMESTAMPING_RX_HARDWARE |
-		SOF_TIMESTAMPING_RX_SOFTWARE |
-		SOF_TIMESTAMPING_SOFTWARE |
 		SOF_TIMESTAMPING_RAW_HARDWARE;
 
-	info->phc_index = -1;
-
 	info->tx_types =
 		(1 << HWTSTAMP_TX_OFF) |
 		(1 << HWTSTAMP_TX_ON) |
-- 
cgit v1.3-3-g829e


From 4a0ec34870a2d278373897cf182cbe662d559eb2 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 6 Sep 2024 16:26:17 -0700
Subject: ionic: debug line for Tx completion errors

Here's a little debugging aid in case the device starts throwing
Tx completion errors.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-2-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index fc79baad4561..ccdc0eefabe4 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -648,7 +648,14 @@ static void ionic_rx_clean(struct ionic_queue *q,
 
 	stats = q_to_rx_stats(q);
 
-	if (comp->status) {
+	if (unlikely(comp->status)) {
+		/* Most likely status==2 and the pkt received was bigger
+		 * than the buffer available: comp->len will show the
+		 * pkt size received that didn't fit the advertised desc.len
+		 */
+		dev_dbg(q->dev, "q%d drop comp->status %d comp->len %d desc->len %d\n",
+			q->index, comp->status, comp->len, q->rxq[q->head_idx].len);
+
 		stats->dropped++;
 		return;
 	}
-- 
cgit v1.3-3-g829e


From 7639a6e058155614d638072de6be2fba485813d6 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 6 Sep 2024 16:26:18 -0700
Subject: ionic: rename ionic_xdp_rx_put_bufs

We aren't "putting" buf, we're just unlinking them from our tracking in
order to let the XDP_TX and XDP_REDIRECT tx clean paths take care of the
pages when they are done with them.  This rename clears up the intent.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-3-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index ccdc0eefabe4..d62b2b60b133 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -481,9 +481,9 @@ int ionic_xdp_xmit(struct net_device *netdev, int n,
 	return nxmit;
 }
 
-static void ionic_xdp_rx_put_bufs(struct ionic_queue *q,
-				  struct ionic_buf_info *buf_info,
-				  int nbufs)
+static void ionic_xdp_rx_unlink_bufs(struct ionic_queue *q,
+				     struct ionic_buf_info *buf_info,
+				     int nbufs)
 {
 	int i;
 
@@ -600,7 +600,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 			netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err);
 			goto out_xdp_abort;
 		}
-		ionic_xdp_rx_put_bufs(rxq, buf_info, nbufs);
+		ionic_xdp_rx_unlink_bufs(rxq, buf_info, nbufs);
 		stats->xdp_tx++;
 
 		/* the Tx completion will free the buffers */
@@ -612,7 +612,7 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 			netdev_dbg(netdev, "xdp_do_redirect err %d\n", err);
 			goto out_xdp_abort;
 		}
-		ionic_xdp_rx_put_bufs(rxq, buf_info, nbufs);
+		ionic_xdp_rx_unlink_bufs(rxq, buf_info, nbufs);
 		rxq->xdp_flush = true;
 		stats->xdp_redirect++;
 		break;
-- 
cgit v1.3-3-g829e


From 7b4ec51f165f37b0102f98df1b0c13b64b5178e8 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 6 Sep 2024 16:26:19 -0700
Subject: ionic: use per-queue xdp_prog

We originally were using a per-interface xdp_prog variable to track
a loaded XDP program since we knew there would never be support for a
per-queue XDP program.  With that, we only built the per queue rxq_info
struct when an XDP program was loaded and removed it on XDP program unload,
and used the pointer as an indicator in the Rx hotpath to know to how build
the buffers.  However, that's really not the model generally used, and
makes a conversion to page_pool Rx buffer cacheing a little problematic.

This patch converts the driver to use the more common approach of using
a per-queue xdp_prog pointer to work out buffer allocations and need
for bpf_prog_run_xdp().  We jostle a couple of fields in the queue struct
in order to keep the new xdp_prog pointer in a warm cacheline.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-4-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_dev.h  |  7 +++--
 drivers/net/ethernet/pensando/ionic/ionic_lif.c  | 37 ++++++++++++------------
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 21 +++++++-------
 3 files changed, 34 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index f2f07bf88545..3ae6b34cc85f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -238,9 +238,8 @@ struct ionic_queue {
 	unsigned int index;
 	unsigned int num_descs;
 	unsigned int max_sg_elems;
+
 	u64 features;
-	unsigned int type;
-	unsigned int hw_index;
 	unsigned int hw_type;
 	bool xdp_flush;
 	union {
@@ -261,7 +260,11 @@ struct ionic_queue {
 		struct ionic_rxq_sg_desc *rxq_sgl;
 	};
 	struct xdp_rxq_info *xdp_rxq_info;
+	struct bpf_prog *xdp_prog;
 	struct ionic_queue *partner;
+
+	unsigned int type;
+	unsigned int hw_index;
 	dma_addr_t base_pa;
 	dma_addr_t cmb_base_pa;
 	dma_addr_t sg_base_pa;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 86774d9922d8..68b540d26702 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -46,7 +46,7 @@ static int ionic_start_queues(struct ionic_lif *lif);
 static void ionic_stop_queues(struct ionic_lif *lif);
 static void ionic_lif_queue_identify(struct ionic_lif *lif);
 
-static int ionic_xdp_queues_config(struct ionic_lif *lif);
+static int ionic_xdp_rxqs_update(struct ionic_lif *lif);
 static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q);
 
 static void ionic_dim_work(struct work_struct *work)
@@ -2143,7 +2143,7 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 	int derr = 0;
 	int i, err;
 
-	err = ionic_xdp_queues_config(lif);
+	err = ionic_xdp_rxqs_update(lif);
 	if (err)
 		return err;
 
@@ -2192,7 +2192,7 @@ err_out:
 		derr = ionic_qcq_disable(lif, lif->rxqcqs[i], derr);
 	}
 
-	ionic_xdp_queues_config(lif);
+	ionic_xdp_rxqs_update(lif);
 
 	return err;
 }
@@ -2698,35 +2698,35 @@ err_out:
 	return err;
 }
 
-static int ionic_xdp_queues_config(struct ionic_lif *lif)
+static int ionic_xdp_rxqs_update(struct ionic_lif *lif)
 {
+	struct bpf_prog *xdp_prog;
 	unsigned int i;
 	int err;
 
 	if (!lif->rxqcqs)
 		return 0;
 
-	/* There's no need to rework memory if not going to/from NULL program.
-	 * If there is no lif->xdp_prog, there should also be no q.xdp_rxq_info
-	 * This way we don't need to keep an *xdp_prog in every queue struct.
-	 */
-	if (!lif->xdp_prog == !lif->rxqcqs[0]->q.xdp_rxq_info)
-		return 0;
-
+	xdp_prog = READ_ONCE(lif->xdp_prog);
 	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) {
 		struct ionic_queue *q = &lif->rxqcqs[i]->q;
 
-		if (q->xdp_rxq_info) {
+		if (q->xdp_prog) {
 			ionic_xdp_unregister_rxq_info(q);
-			continue;
+			q->xdp_prog = NULL;
 		}
 
-		err = ionic_xdp_register_rxq_info(q, lif->rxqcqs[i]->napi.napi_id);
-		if (err) {
-			dev_err(lif->ionic->dev, "failed to register RX queue %d info for XDP, err %d\n",
-				i, err);
-			goto err_out;
+		if (xdp_prog) {
+			unsigned int napi_id = lif->rxqcqs[i]->napi.napi_id;
+
+			err = ionic_xdp_register_rxq_info(q, napi_id);
+			if (err) {
+				dev_err(lif->ionic->dev, "failed to register RX queue %d info for XDP, err %d\n",
+					i, err);
+				goto err_out;
+			}
 		}
+		q->xdp_prog = xdp_prog;
 	}
 
 	return 0;
@@ -2878,6 +2878,7 @@ static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b)
 	swap(a->q.base,       b->q.base);
 	swap(a->q.base_pa,    b->q.base_pa);
 	swap(a->q.info,       b->q.info);
+	swap(a->q.xdp_prog,   b->q.xdp_prog);
 	swap(a->q.xdp_rxq_info, b->q.xdp_rxq_info);
 	swap(a->q.partner,    b->q.partner);
 	swap(a->q_base,       b->q_base);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index d62b2b60b133..858ab4fd9218 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -190,7 +190,7 @@ static bool ionic_rx_buf_recycle(struct ionic_queue *q,
 	if (page_to_nid(buf_info->page) != numa_mem_id())
 		return false;
 
-	size = ALIGN(len, q->xdp_rxq_info ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ);
+	size = ALIGN(len, q->xdp_prog ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ);
 	buf_info->page_offset += size;
 	if (buf_info->page_offset >= IONIC_PAGE_SIZE)
 		return false;
@@ -639,8 +639,7 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_qcq *qcq = q_to_qcq(q);
 	struct ionic_rx_stats *stats;
-	struct bpf_prog *xdp_prog;
-	unsigned int headroom;
+	unsigned int headroom = 0;
 	struct sk_buff *skb;
 	bool synced = false;
 	bool use_copybreak;
@@ -664,14 +663,13 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	stats->pkts++;
 	stats->bytes += len;
 
-	xdp_prog = READ_ONCE(q->lif->xdp_prog);
-	if (xdp_prog) {
-		if (ionic_run_xdp(stats, netdev, xdp_prog, q, desc_info->bufs, len))
+	if (q->xdp_prog) {
+		if (ionic_run_xdp(stats, netdev, q->xdp_prog, q, desc_info->bufs, len))
 			return;
 		synced = true;
+		headroom = XDP_PACKET_HEADROOM;
 	}
 
-	headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0;
 	use_copybreak = len <= q->lif->rx_copybreak;
 	if (use_copybreak)
 		skb = ionic_rx_copybreak(netdev, q, desc_info,
@@ -814,7 +812,7 @@ void ionic_rx_fill(struct ionic_queue *q)
 	len = netdev->mtu + VLAN_ETH_HLEN;
 
 	for (i = n_fill; i; i--) {
-		unsigned int headroom;
+		unsigned int headroom = 0;
 		unsigned int buf_len;
 
 		nfrags = 0;
@@ -835,11 +833,12 @@ void ionic_rx_fill(struct ionic_queue *q)
 		 * XDP uses space in the first buffer, so account for
 		 * head room, tail room, and ip header in the first frag size.
 		 */
-		headroom = q->xdp_rxq_info ? XDP_PACKET_HEADROOM : 0;
-		if (q->xdp_rxq_info)
+		if (q->xdp_prog) {
 			buf_len = IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN;
-		else
+			headroom = XDP_PACKET_HEADROOM;
+		} else {
 			buf_len = ionic_rx_buf_size(buf_info);
+		}
 		frag_len = min_t(u16, len, buf_len);
 
 		desc->addr = cpu_to_le64(ionic_rx_buf_pa(buf_info) + headroom);
-- 
cgit v1.3-3-g829e


From 668e423920de1b64f7c1b60fa323c50e8d10719e Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 6 Sep 2024 16:26:20 -0700
Subject: ionic: always use rxq_info

Instead of setting up and tearing down the rxq_info only when the XDP
program is loaded or unloaded, we will build the rxq_info whether or not
XDP is in use.  This is the more common use pattern and better supports
future conversion to page_pool.  Since the rxq_info wants the napi_id
we re-order things slightly to tie this into the queue init and deinit
functions where we do the add and delete of napi.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-5-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 51 ++++++++-----------------
 1 file changed, 15 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 68b540d26702..6da6774d4d30 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -46,8 +46,9 @@ static int ionic_start_queues(struct ionic_lif *lif);
 static void ionic_stop_queues(struct ionic_lif *lif);
 static void ionic_lif_queue_identify(struct ionic_lif *lif);
 
-static int ionic_xdp_rxqs_update(struct ionic_lif *lif);
-static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q);
+static void ionic_xdp_rxqs_prog_update(struct ionic_lif *lif);
+static void ionic_unregister_rxq_info(struct ionic_queue *q);
+static int ionic_register_rxq_info(struct ionic_queue *q, unsigned int napi_id);
 
 static void ionic_dim_work(struct work_struct *work)
 {
@@ -380,6 +381,7 @@ static void ionic_lif_qcq_deinit(struct ionic_lif *lif, struct ionic_qcq *qcq)
 	if (!(qcq->flags & IONIC_QCQ_F_INITED))
 		return;
 
+	ionic_unregister_rxq_info(&qcq->q);
 	if (qcq->flags & IONIC_QCQ_F_INTR) {
 		ionic_intr_mask(idev->intr_ctrl, qcq->intr.index,
 				IONIC_INTR_MASK_SET);
@@ -437,9 +439,7 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq)
 		qcq->sg_base_pa = 0;
 	}
 
-	ionic_xdp_unregister_rxq_info(&qcq->q);
 	ionic_qcq_intr_free(lif, qcq);
-
 	vfree(qcq->q.info);
 	qcq->q.info = NULL;
 }
@@ -925,6 +925,11 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq)
 		netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi);
 	else
 		netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi);
+	err = ionic_register_rxq_info(q, qcq->napi.napi_id);
+	if (err) {
+		netif_napi_del(&qcq->napi);
+		return err;
+	}
 
 	qcq->flags |= IONIC_QCQ_F_INITED;
 
@@ -2143,9 +2148,7 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 	int derr = 0;
 	int i, err;
 
-	err = ionic_xdp_rxqs_update(lif);
-	if (err)
-		return err;
+	ionic_xdp_rxqs_prog_update(lif);
 
 	for (i = 0; i < lif->nxqs; i++) {
 		if (!(lif->rxqcqs[i] && lif->txqcqs[i])) {
@@ -2192,7 +2195,7 @@ err_out:
 		derr = ionic_qcq_disable(lif, lif->rxqcqs[i], derr);
 	}
 
-	ionic_xdp_rxqs_update(lif);
+	ionic_xdp_rxqs_prog_update(lif);
 
 	return err;
 }
@@ -2651,7 +2654,7 @@ static void ionic_vf_attr_replay(struct ionic_lif *lif)
 	ionic_vf_start(ionic);
 }
 
-static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q)
+static void ionic_unregister_rxq_info(struct ionic_queue *q)
 {
 	struct xdp_rxq_info *xi;
 
@@ -2665,7 +2668,7 @@ static void ionic_xdp_unregister_rxq_info(struct ionic_queue *q)
 	kfree(xi);
 }
 
-static int ionic_xdp_register_rxq_info(struct ionic_queue *q, unsigned int napi_id)
+static int ionic_register_rxq_info(struct ionic_queue *q, unsigned int napi_id)
 {
 	struct xdp_rxq_info *rxq_info;
 	int err;
@@ -2698,44 +2701,20 @@ err_out:
 	return err;
 }
 
-static int ionic_xdp_rxqs_update(struct ionic_lif *lif)
+static void ionic_xdp_rxqs_prog_update(struct ionic_lif *lif)
 {
 	struct bpf_prog *xdp_prog;
 	unsigned int i;
-	int err;
 
 	if (!lif->rxqcqs)
-		return 0;
+		return;
 
 	xdp_prog = READ_ONCE(lif->xdp_prog);
 	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) {
 		struct ionic_queue *q = &lif->rxqcqs[i]->q;
 
-		if (q->xdp_prog) {
-			ionic_xdp_unregister_rxq_info(q);
-			q->xdp_prog = NULL;
-		}
-
-		if (xdp_prog) {
-			unsigned int napi_id = lif->rxqcqs[i]->napi.napi_id;
-
-			err = ionic_xdp_register_rxq_info(q, napi_id);
-			if (err) {
-				dev_err(lif->ionic->dev, "failed to register RX queue %d info for XDP, err %d\n",
-					i, err);
-				goto err_out;
-			}
-		}
 		q->xdp_prog = xdp_prog;
 	}
-
-	return 0;
-
-err_out:
-	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++)
-		ionic_xdp_unregister_rxq_info(&lif->rxqcqs[i]->q);
-
-	return err;
 }
 
 static int ionic_xdp_config(struct net_device *netdev, struct netdev_bpf *bpf)
-- 
cgit v1.3-3-g829e


From a7f3f635f07afc73711c66c023c1046bd2187d72 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Fri, 6 Sep 2024 16:26:21 -0700
Subject: ionic: Fully reconfigure queues when going to/from a NULL XDP program

Currently when going to/from a NULL XDP program the driver uses
ionic_stop_queues_reconfig() and then ionic_start_queues_reconfig() in
order to re-register the xdp_rxq_info and re-init the queues. This is
fine until page_pool(s) are used in an upcoming patch.

In preparation for adding page_pool support make sure to completely
rebuild the queues when going to/from a NULL XDP program. Without this
change the call to mem_allocator_disconnect() never happens when going
to a NULL XDP program, which eventually results in
xdp_rxq_info_reg_mem_model() failing with -ENOSPC due to the mem_id_pool
ida having no remaining space.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-6-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 11 ++++++++---
 drivers/net/ethernet/pensando/ionic/ionic_lif.h |  2 ++
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 6da6774d4d30..54e5519d1110 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -2745,10 +2745,13 @@ static int ionic_xdp_config(struct net_device *netdev, struct netdev_bpf *bpf)
 	if (!netif_running(netdev)) {
 		old_prog = xchg(&lif->xdp_prog, bpf->prog);
 	} else {
+		struct ionic_queue_params qparams;
+
+		ionic_init_queue_params(lif, &qparams);
+		qparams.xdp_prog = bpf->prog;
 		mutex_lock(&lif->queue_lock);
-		ionic_stop_queues_reconfig(lif);
+		ionic_reconfigure_queues(lif, &qparams);
 		old_prog = xchg(&lif->xdp_prog, bpf->prog);
-		ionic_start_queues_reconfig(lif);
 		mutex_unlock(&lif->queue_lock);
 	}
 
@@ -2908,7 +2911,8 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 	}
 	if (qparam->nxqs != lif->nxqs ||
 	    qparam->nrxq_descs != lif->nrxq_descs ||
-	    qparam->rxq_features != lif->rxq_features) {
+	    qparam->rxq_features != lif->rxq_features ||
+	    qparam->xdp_prog != lif->xdp_prog) {
 		rx_qcqs = devm_kcalloc(lif->ionic->dev, lif->ionic->nrxqs_per_lif,
 				       sizeof(struct ionic_qcq *), GFP_KERNEL);
 		if (!rx_qcqs) {
@@ -2984,6 +2988,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 				goto err_out;
 
 			rx_qcqs[i]->q.features = qparam->rxq_features;
+			rx_qcqs[i]->q.xdp_prog = qparam->xdp_prog;
 		}
 	}
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 3e1005293c4a..e01756fb7fdd 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -268,6 +268,7 @@ struct ionic_queue_params {
 	unsigned int ntxq_descs;
 	unsigned int nrxq_descs;
 	u64 rxq_features;
+	struct bpf_prog *xdp_prog;
 	bool intr_split;
 	bool cmb_tx;
 	bool cmb_rx;
@@ -280,6 +281,7 @@ static inline void ionic_init_queue_params(struct ionic_lif *lif,
 	qparam->ntxq_descs = lif->ntxq_descs;
 	qparam->nrxq_descs = lif->nrxq_descs;
 	qparam->rxq_features = lif->rxq_features;
+	qparam->xdp_prog = lif->xdp_prog;
 	qparam->intr_split = test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state);
 	qparam->cmb_tx = test_bit(IONIC_LIF_F_CMB_TX_RINGS, lif->state);
 	qparam->cmb_rx = test_bit(IONIC_LIF_F_CMB_RX_RINGS, lif->state);
-- 
cgit v1.3-3-g829e


From ac8813c0ab7d2816946379bff2677a5f725e37bf Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 6 Sep 2024 16:26:22 -0700
Subject: ionic: convert Rx queue buffers to use page_pool

Our home-grown buffer management needs to go away and we need
to be playing nicely with the page_pool infrastructure.  This
converts the Rx traffic queues to use page_pool.

Also, since ionic_rx_buf_size() was removed, redefine
IONIC_PAGE_SIZE to account for IONIC_MAX_BUF_LEN being the
largest allowed buffer to prevent overflowing u16 variables,
which could happen when PAGE_SIZE is defined as >= 64KB.

include/linux/minmax.h:93:37: warning: conversion from 'long unsigned int' to 'u16' {aka 'short unsigned int'} changes value from '65536' to '0' [-Woverflow]

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-7-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/Kconfig            |   1 +
 drivers/net/ethernet/pensando/ionic/ionic_dev.h  |  16 +-
 drivers/net/ethernet/pensando/ionic/ionic_lif.c  |  80 ++++--
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 344 +++++++++++------------
 4 files changed, 233 insertions(+), 208 deletions(-)

diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig
index 3f7519e435b8..01fe76786f77 100644
--- a/drivers/net/ethernet/pensando/Kconfig
+++ b/drivers/net/ethernet/pensando/Kconfig
@@ -23,6 +23,7 @@ config IONIC
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select NET_DEVLINK
 	select DIMLIB
+	select PAGE_POOL
 	help
 	  This enables the support for the Pensando family of Ethernet
 	  adapters.  More specific information on this driver can be
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
index 3ae6b34cc85f..c8c710cfe70c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@@ -181,10 +181,7 @@ struct ionic_queue;
 struct ionic_qcq;
 
 #define IONIC_MAX_BUF_LEN			((u16)-1)
-#define IONIC_PAGE_SIZE				PAGE_SIZE
-#define IONIC_PAGE_SPLIT_SZ			(PAGE_SIZE / 2)
-#define IONIC_PAGE_GFP_MASK			(GFP_ATOMIC | __GFP_NOWARN |\
-						 __GFP_COMP | __GFP_MEMALLOC)
+#define IONIC_PAGE_SIZE				MIN(PAGE_SIZE, IONIC_MAX_BUF_LEN)
 
 #define IONIC_XDP_MAX_LINEAR_MTU	(IONIC_PAGE_SIZE -	\
 					 (VLAN_ETH_HLEN +	\
@@ -248,11 +245,6 @@ struct ionic_queue {
 		struct ionic_rxq_desc *rxq;
 		struct ionic_admin_cmd *adminq;
 	};
-	union {
-		void __iomem *cmb_base;
-		struct ionic_txq_desc __iomem *cmb_txq;
-		struct ionic_rxq_desc __iomem *cmb_rxq;
-	};
 	union {
 		void *sg_base;
 		struct ionic_txq_sg_desc *txq_sgl;
@@ -261,8 +253,14 @@ struct ionic_queue {
 	};
 	struct xdp_rxq_info *xdp_rxq_info;
 	struct bpf_prog *xdp_prog;
+	struct page_pool *page_pool;
 	struct ionic_queue *partner;
 
+	union {
+		void __iomem *cmb_base;
+		struct ionic_txq_desc __iomem *cmb_txq;
+		struct ionic_rxq_desc __iomem *cmb_rxq;
+	};
 	unsigned int type;
 	unsigned int hw_index;
 	dma_addr_t base_pa;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 54e5519d1110..a9d66d79bbf1 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -13,6 +13,7 @@
 #include <linux/cpumask.h>
 #include <linux/crash_dump.h>
 #include <linux/vmalloc.h>
+#include <net/page_pool/helpers.h>
 
 #include "ionic.h"
 #include "ionic_bus.h"
@@ -439,6 +440,9 @@ static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq)
 		qcq->sg_base_pa = 0;
 	}
 
+	page_pool_destroy(qcq->q.page_pool);
+	qcq->q.page_pool = NULL;
+
 	ionic_qcq_intr_free(lif, qcq);
 	vfree(qcq->q.info);
 	qcq->q.info = NULL;
@@ -553,7 +557,8 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type,
 			   unsigned int cq_desc_size,
 			   unsigned int sg_desc_size,
 			   unsigned int desc_info_size,
-			   unsigned int pid, struct ionic_qcq **qcq)
+			   unsigned int pid, struct bpf_prog *xdp_prog,
+			   struct ionic_qcq **qcq)
 {
 	struct ionic_dev *idev = &lif->ionic->idev;
 	struct device *dev = lif->ionic->dev;
@@ -579,6 +584,31 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type,
 		goto err_out_free_qcq;
 	}
 
+	if (type == IONIC_QTYPE_RXQ) {
+		struct page_pool_params pp_params = {
+			.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+			.order = 0,
+			.pool_size = num_descs,
+			.nid = NUMA_NO_NODE,
+			.dev = lif->ionic->dev,
+			.napi = &new->napi,
+			.dma_dir = DMA_FROM_DEVICE,
+			.max_len = PAGE_SIZE,
+			.netdev = lif->netdev,
+		};
+
+		if (xdp_prog)
+			pp_params.dma_dir = DMA_BIDIRECTIONAL;
+
+		new->q.page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(new->q.page_pool)) {
+			netdev_err(lif->netdev, "Cannot create page_pool\n");
+			err = PTR_ERR(new->q.page_pool);
+			new->q.page_pool = NULL;
+			goto err_out_free_q_info;
+		}
+	}
+
 	new->q.type = type;
 	new->q.max_sg_elems = lif->qtype_info[type].max_sg_elems;
 
@@ -586,12 +616,12 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type,
 			   desc_size, sg_desc_size, pid);
 	if (err) {
 		netdev_err(lif->netdev, "Cannot initialize queue\n");
-		goto err_out_free_q_info;
+		goto err_out_free_page_pool;
 	}
 
 	err = ionic_alloc_qcq_interrupt(lif, new);
 	if (err)
-		goto err_out_free_q_info;
+		goto err_out_free_page_pool;
 
 	err = ionic_cq_init(lif, &new->cq, &new->intr, num_descs, cq_desc_size);
 	if (err) {
@@ -712,6 +742,8 @@ err_out_free_irq:
 		devm_free_irq(dev, new->intr.vector, &new->napi);
 		ionic_intr_free(lif->ionic, new->intr.index);
 	}
+err_out_free_page_pool:
+	page_pool_destroy(new->q.page_pool);
 err_out_free_q_info:
 	vfree(new->q.info);
 err_out_free_qcq:
@@ -734,7 +766,7 @@ static int ionic_qcqs_alloc(struct ionic_lif *lif)
 			      sizeof(struct ionic_admin_comp),
 			      0,
 			      sizeof(struct ionic_admin_desc_info),
-			      lif->kern_pid, &lif->adminqcq);
+			      lif->kern_pid, NULL, &lif->adminqcq);
 	if (err)
 		return err;
 	ionic_debugfs_add_qcq(lif, lif->adminqcq);
@@ -747,7 +779,7 @@ static int ionic_qcqs_alloc(struct ionic_lif *lif)
 				      sizeof(union ionic_notifyq_comp),
 				      0,
 				      sizeof(struct ionic_admin_desc_info),
-				      lif->kern_pid, &lif->notifyqcq);
+				      lif->kern_pid, NULL, &lif->notifyqcq);
 		if (err)
 			goto err_out;
 		ionic_debugfs_add_qcq(lif, lif->notifyqcq);
@@ -965,7 +997,7 @@ int ionic_lif_create_hwstamp_txq(struct ionic_lif *lif)
 	err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, txq_i, "hwstamp_tx", flags,
 			      num_desc, desc_sz, comp_sz, sg_desc_sz,
 			      sizeof(struct ionic_tx_desc_info),
-			      lif->kern_pid, &txq);
+			      lif->kern_pid, NULL, &txq);
 	if (err)
 		goto err_qcq_alloc;
 
@@ -1025,7 +1057,7 @@ int ionic_lif_create_hwstamp_rxq(struct ionic_lif *lif)
 	err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, rxq_i, "hwstamp_rx", flags,
 			      num_desc, desc_sz, comp_sz, sg_desc_sz,
 			      sizeof(struct ionic_rx_desc_info),
-			      lif->kern_pid, &rxq);
+			      lif->kern_pid, NULL, &rxq);
 	if (err)
 		goto err_qcq_alloc;
 
@@ -2051,7 +2083,7 @@ static int ionic_txrx_alloc(struct ionic_lif *lif)
 		err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags,
 				      num_desc, desc_sz, comp_sz, sg_desc_sz,
 				      sizeof(struct ionic_tx_desc_info),
-				      lif->kern_pid, &lif->txqcqs[i]);
+				      lif->kern_pid, NULL, &lif->txqcqs[i]);
 		if (err)
 			goto err_out;
 
@@ -2083,7 +2115,8 @@ static int ionic_txrx_alloc(struct ionic_lif *lif)
 		err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags,
 				      num_desc, desc_sz, comp_sz, sg_desc_sz,
 				      sizeof(struct ionic_rx_desc_info),
-				      lif->kern_pid, &lif->rxqcqs[i]);
+				      lif->kern_pid, lif->xdp_prog,
+				      &lif->rxqcqs[i]);
 		if (err)
 			goto err_out;
 
@@ -2679,15 +2712,15 @@ static int ionic_register_rxq_info(struct ionic_queue *q, unsigned int napi_id)
 
 	err = xdp_rxq_info_reg(rxq_info, q->lif->netdev, q->index, napi_id);
 	if (err) {
-		dev_err(q->dev, "Queue %d xdp_rxq_info_reg failed, err %d\n",
-			q->index, err);
+		netdev_err(q->lif->netdev, "q%d xdp_rxq_info_reg failed, err %d\n",
+			   q->index, err);
 		goto err_out;
 	}
 
-	err = xdp_rxq_info_reg_mem_model(rxq_info, MEM_TYPE_PAGE_ORDER0, NULL);
+	err = xdp_rxq_info_reg_mem_model(rxq_info, MEM_TYPE_PAGE_POOL, q->page_pool);
 	if (err) {
-		dev_err(q->dev, "Queue %d xdp_rxq_info_reg_mem_model failed, err %d\n",
-			q->index, err);
+		netdev_err(q->lif->netdev, "q%d xdp_rxq_info_reg_mem_model failed, err %d\n",
+			   q->index, err);
 		xdp_rxq_info_unreg(rxq_info);
 		goto err_out;
 	}
@@ -2853,7 +2886,16 @@ err_out:
 
 static void ionic_swap_queues(struct ionic_qcq *a, struct ionic_qcq *b)
 {
-	/* only swapping the queues, not the napi, flags, or other stuff */
+	/* only swapping the queues and napi, not flags or other stuff */
+	swap(a->napi,         b->napi);
+
+	if (a->q.type == IONIC_QTYPE_RXQ) {
+		swap(a->q.page_pool, b->q.page_pool);
+		a->q.page_pool->p.napi = &a->napi;
+		if (b->q.page_pool)  /* is NULL when increasing queue count */
+			b->q.page_pool->p.napi = &b->napi;
+	}
+
 	swap(a->q.features,   b->q.features);
 	swap(a->q.num_descs,  b->q.num_descs);
 	swap(a->q.desc_size,  b->q.desc_size);
@@ -2943,7 +2985,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 				err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags,
 						      4, desc_sz, comp_sz, sg_desc_sz,
 						      sizeof(struct ionic_tx_desc_info),
-						      lif->kern_pid, &lif->txqcqs[i]);
+						      lif->kern_pid, NULL, &lif->txqcqs[i]);
 				if (err)
 					goto err_out;
 			}
@@ -2952,7 +2994,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 			err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags,
 					      num_desc, desc_sz, comp_sz, sg_desc_sz,
 					      sizeof(struct ionic_tx_desc_info),
-					      lif->kern_pid, &tx_qcqs[i]);
+					      lif->kern_pid, NULL, &tx_qcqs[i]);
 			if (err)
 				goto err_out;
 		}
@@ -2974,7 +3016,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 				err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags,
 						      4, desc_sz, comp_sz, sg_desc_sz,
 						      sizeof(struct ionic_rx_desc_info),
-						      lif->kern_pid, &lif->rxqcqs[i]);
+						      lif->kern_pid, NULL, &lif->rxqcqs[i]);
 				if (err)
 					goto err_out;
 			}
@@ -2983,7 +3025,7 @@ int ionic_reconfigure_queues(struct ionic_lif *lif,
 			err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags,
 					      num_desc, desc_sz, comp_sz, sg_desc_sz,
 					      sizeof(struct ionic_rx_desc_info),
-					      lif->kern_pid, &rx_qcqs[i]);
+					      lif->kern_pid, qparam->xdp_prog, &rx_qcqs[i]);
 			if (err)
 				goto err_out;
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 858ab4fd9218..35e3751dd5a7 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -6,6 +6,7 @@
 #include <linux/if_vlan.h>
 #include <net/ip6_checksum.h>
 #include <net/netdev_queues.h>
+#include <net/page_pool/helpers.h>
 
 #include "ionic.h"
 #include "ionic_lif.h"
@@ -118,108 +119,57 @@ static void *ionic_rx_buf_va(struct ionic_buf_info *buf_info)
 
 static dma_addr_t ionic_rx_buf_pa(struct ionic_buf_info *buf_info)
 {
-	return buf_info->dma_addr + buf_info->page_offset;
+	return page_pool_get_dma_addr(buf_info->page) + buf_info->page_offset;
 }
 
-static unsigned int ionic_rx_buf_size(struct ionic_buf_info *buf_info)
+static void __ionic_rx_put_buf(struct ionic_queue *q,
+			       struct ionic_buf_info *buf_info,
+			       bool recycle_direct)
 {
-	return min_t(u32, IONIC_MAX_BUF_LEN, IONIC_PAGE_SIZE - buf_info->page_offset);
-}
-
-static int ionic_rx_page_alloc(struct ionic_queue *q,
-			       struct ionic_buf_info *buf_info)
-{
-	struct device *dev = q->dev;
-	dma_addr_t dma_addr;
-	struct page *page;
-
-	page = alloc_pages(IONIC_PAGE_GFP_MASK, 0);
-	if (unlikely(!page)) {
-		net_err_ratelimited("%s: %s page alloc failed\n",
-				    dev_name(dev), q->name);
-		q_to_rx_stats(q)->alloc_err++;
-		return -ENOMEM;
-	}
-
-	dma_addr = dma_map_page(dev, page, 0,
-				IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(dev, dma_addr))) {
-		__free_pages(page, 0);
-		net_err_ratelimited("%s: %s dma map failed\n",
-				    dev_name(dev), q->name);
-		q_to_rx_stats(q)->dma_map_err++;
-		return -EIO;
-	}
-
-	buf_info->dma_addr = dma_addr;
-	buf_info->page = page;
-	buf_info->page_offset = 0;
-
-	return 0;
-}
-
-static void ionic_rx_page_free(struct ionic_queue *q,
-			       struct ionic_buf_info *buf_info)
-{
-	struct device *dev = q->dev;
-
-	if (unlikely(!buf_info)) {
-		net_err_ratelimited("%s: %s invalid buf_info in free\n",
-				    dev_name(dev), q->name);
-		return;
-	}
-
 	if (!buf_info->page)
 		return;
 
-	dma_unmap_page(dev, buf_info->dma_addr, IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
-	__free_pages(buf_info->page, 0);
+	page_pool_put_full_page(q->page_pool, buf_info->page, recycle_direct);
 	buf_info->page = NULL;
+	buf_info->len = 0;
+	buf_info->page_offset = 0;
 }
 
-static bool ionic_rx_buf_recycle(struct ionic_queue *q,
-				 struct ionic_buf_info *buf_info, u32 len)
-{
-	u32 size;
-
-	/* don't re-use pages allocated in low-mem condition */
-	if (page_is_pfmemalloc(buf_info->page))
-		return false;
-
-	/* don't re-use buffers from non-local numa nodes */
-	if (page_to_nid(buf_info->page) != numa_mem_id())
-		return false;
-
-	size = ALIGN(len, q->xdp_prog ? IONIC_PAGE_SIZE : IONIC_PAGE_SPLIT_SZ);
-	buf_info->page_offset += size;
-	if (buf_info->page_offset >= IONIC_PAGE_SIZE)
-		return false;
 
-	get_page(buf_info->page);
+static void ionic_rx_put_buf(struct ionic_queue *q,
+			     struct ionic_buf_info *buf_info)
+{
+	__ionic_rx_put_buf(q, buf_info, false);
+}
 
-	return true;
+static void ionic_rx_put_buf_direct(struct ionic_queue *q,
+				    struct ionic_buf_info *buf_info)
+{
+	__ionic_rx_put_buf(q, buf_info, true);
 }
 
 static void ionic_rx_add_skb_frag(struct ionic_queue *q,
 				  struct sk_buff *skb,
 				  struct ionic_buf_info *buf_info,
-				  u32 off, u32 len,
+				  u32 headroom, u32 len,
 				  bool synced)
 {
 	if (!synced)
-		dma_sync_single_range_for_cpu(q->dev, ionic_rx_buf_pa(buf_info),
-					      off, len, DMA_FROM_DEVICE);
+		page_pool_dma_sync_for_cpu(q->page_pool,
+					   buf_info->page,
+					   buf_info->page_offset + headroom,
+					   len);
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
-			buf_info->page, buf_info->page_offset + off,
-			len,
-			IONIC_PAGE_SIZE);
+			buf_info->page, buf_info->page_offset + headroom,
+			len, buf_info->len);
 
-	if (!ionic_rx_buf_recycle(q, buf_info, len)) {
-		dma_unmap_page(q->dev, buf_info->dma_addr,
-			       IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
-		buf_info->page = NULL;
-	}
+	/* napi_gro_frags() will release/recycle the
+	 * page_pool buffers from the frags list
+	 */
+	buf_info->page = NULL;
+	buf_info->len = 0;
+	buf_info->page_offset = 0;
 }
 
 static struct sk_buff *ionic_rx_build_skb(struct ionic_queue *q,
@@ -244,12 +194,13 @@ static struct sk_buff *ionic_rx_build_skb(struct ionic_queue *q,
 		q_to_rx_stats(q)->alloc_err++;
 		return NULL;
 	}
+	skb_mark_for_recycle(skb);
 
 	if (headroom)
 		frag_len = min_t(u16, len,
 				 IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN);
 	else
-		frag_len = min_t(u16, len, ionic_rx_buf_size(buf_info));
+		frag_len = min_t(u16, len, IONIC_PAGE_SIZE);
 
 	if (unlikely(!buf_info->page))
 		goto err_bad_buf_page;
@@ -260,7 +211,7 @@ static struct sk_buff *ionic_rx_build_skb(struct ionic_queue *q,
 	for (i = 0; i < num_sg_elems; i++, buf_info++) {
 		if (unlikely(!buf_info->page))
 			goto err_bad_buf_page;
-		frag_len = min_t(u16, len, ionic_rx_buf_size(buf_info));
+		frag_len = min_t(u16, len, buf_info->len);
 		ionic_rx_add_skb_frag(q, skb, buf_info, 0, frag_len, synced);
 		len -= frag_len;
 	}
@@ -277,11 +228,13 @@ static struct sk_buff *ionic_rx_copybreak(struct net_device *netdev,
 					  struct ionic_rx_desc_info *desc_info,
 					  unsigned int headroom,
 					  unsigned int len,
+					  unsigned int num_sg_elems,
 					  bool synced)
 {
 	struct ionic_buf_info *buf_info;
 	struct device *dev = q->dev;
 	struct sk_buff *skb;
+	int i;
 
 	buf_info = &desc_info->bufs[0];
 
@@ -292,54 +245,52 @@ static struct sk_buff *ionic_rx_copybreak(struct net_device *netdev,
 		q_to_rx_stats(q)->alloc_err++;
 		return NULL;
 	}
-
-	if (unlikely(!buf_info->page)) {
-		dev_kfree_skb(skb);
-		return NULL;
-	}
+	skb_mark_for_recycle(skb);
 
 	if (!synced)
-		dma_sync_single_range_for_cpu(dev, ionic_rx_buf_pa(buf_info),
-					      headroom, len, DMA_FROM_DEVICE);
+		page_pool_dma_sync_for_cpu(q->page_pool,
+					   buf_info->page,
+					   buf_info->page_offset + headroom,
+					   len);
+
 	skb_copy_to_linear_data(skb, ionic_rx_buf_va(buf_info) + headroom, len);
-	dma_sync_single_range_for_device(dev, ionic_rx_buf_pa(buf_info),
-					 headroom, len, DMA_FROM_DEVICE);
 
 	skb_put(skb, len);
 	skb->protocol = eth_type_trans(skb, netdev);
 
+	/* recycle the Rx buffer now that we're done with it */
+	ionic_rx_put_buf_direct(q, buf_info);
+	buf_info++;
+	for (i = 0; i < num_sg_elems; i++, buf_info++)
+		ionic_rx_put_buf_direct(q, buf_info);
+
 	return skb;
 }
 
 static void ionic_xdp_tx_desc_clean(struct ionic_queue *q,
-				    struct ionic_tx_desc_info *desc_info)
+				    struct ionic_tx_desc_info *desc_info,
+				    bool in_napi)
 {
-	unsigned int nbufs = desc_info->nbufs;
-	struct ionic_buf_info *buf_info;
-	struct device *dev = q->dev;
-	int i;
+	struct xdp_frame_bulk bq;
 
-	if (!nbufs)
+	if (!desc_info->nbufs)
 		return;
 
-	buf_info = desc_info->bufs;
-	dma_unmap_single(dev, buf_info->dma_addr,
-			 buf_info->len, DMA_TO_DEVICE);
-	if (desc_info->act == XDP_TX)
-		__free_pages(buf_info->page, 0);
-	buf_info->page = NULL;
+	xdp_frame_bulk_init(&bq);
+	rcu_read_lock(); /* need for xdp_return_frame_bulk */
 
-	buf_info++;
-	for (i = 1; i < nbufs + 1 && buf_info->page; i++, buf_info++) {
-		dma_unmap_page(dev, buf_info->dma_addr,
-			       buf_info->len, DMA_TO_DEVICE);
-		if (desc_info->act == XDP_TX)
-			__free_pages(buf_info->page, 0);
-		buf_info->page = NULL;
+	if (desc_info->act == XDP_TX) {
+		if (likely(in_napi))
+			xdp_return_frame_rx_napi(desc_info->xdpf);
+		else
+			xdp_return_frame(desc_info->xdpf);
+	} else if (desc_info->act == XDP_REDIRECT) {
+		ionic_tx_desc_unmap_bufs(q, desc_info);
+		xdp_return_frame_bulk(desc_info->xdpf, &bq);
 	}
 
-	if (desc_info->act == XDP_REDIRECT)
-		xdp_return_frame(desc_info->xdpf);
+	xdp_flush_frame_bulk(&bq);
+	rcu_read_unlock();
 
 	desc_info->nbufs = 0;
 	desc_info->xdpf = NULL;
@@ -363,9 +314,17 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 	buf_info = desc_info->bufs;
 	stats = q_to_tx_stats(q);
 
-	dma_addr = ionic_tx_map_single(q, frame->data, len);
-	if (!dma_addr)
-		return -EIO;
+	if (act == XDP_TX) {
+		dma_addr = page_pool_get_dma_addr(page) +
+			   off + XDP_PACKET_HEADROOM;
+		dma_sync_single_for_device(q->dev, dma_addr,
+					   len, DMA_TO_DEVICE);
+	} else /* XDP_REDIRECT */ {
+		dma_addr = ionic_tx_map_single(q, frame->data, len);
+		if (!dma_addr)
+			return -EIO;
+	}
+
 	buf_info->dma_addr = dma_addr;
 	buf_info->len = len;
 	buf_info->page = page;
@@ -387,10 +346,21 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 		frag = sinfo->frags;
 		elem = ionic_tx_sg_elems(q);
 		for (i = 0; i < sinfo->nr_frags; i++, frag++, bi++) {
-			dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag));
-			if (!dma_addr) {
-				ionic_tx_desc_unmap_bufs(q, desc_info);
-				return -EIO;
+			if (act == XDP_TX) {
+				struct page *pg = skb_frag_page(frag);
+
+				dma_addr = page_pool_get_dma_addr(pg) +
+					   skb_frag_off(frag);
+				dma_sync_single_for_device(q->dev, dma_addr,
+							   skb_frag_size(frag),
+							   DMA_TO_DEVICE);
+			} else {
+				dma_addr = ionic_tx_map_frag(q, frag, 0,
+							     skb_frag_size(frag));
+				if (dma_mapping_error(q->dev, dma_addr)) {
+					ionic_tx_desc_unmap_bufs(q, desc_info);
+					return -EIO;
+				}
 			}
 			bi->dma_addr = dma_addr;
 			bi->len = skb_frag_size(frag);
@@ -488,8 +458,6 @@ static void ionic_xdp_rx_unlink_bufs(struct ionic_queue *q,
 	int i;
 
 	for (i = 0; i < nbufs; i++) {
-		dma_unmap_page(q->dev, buf_info->dma_addr,
-			       IONIC_PAGE_SIZE, DMA_FROM_DEVICE);
 		buf_info->page = NULL;
 		buf_info++;
 	}
@@ -516,11 +484,9 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 	frag_len = min_t(u16, len, IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN);
 	xdp_prepare_buff(&xdp_buf, ionic_rx_buf_va(buf_info),
 			 XDP_PACKET_HEADROOM, frag_len, false);
-
-	dma_sync_single_range_for_cpu(rxq->dev, ionic_rx_buf_pa(buf_info),
-				      XDP_PACKET_HEADROOM, frag_len,
-				      DMA_FROM_DEVICE);
-
+	page_pool_dma_sync_for_cpu(rxq->page_pool, buf_info->page,
+				   buf_info->page_offset + XDP_PACKET_HEADROOM,
+				   frag_len);
 	prefetchw(&xdp_buf.data_hard_start);
 
 	/*  We limit MTU size to one buffer if !xdp_has_frags, so
@@ -542,15 +508,16 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 		do {
 			if (unlikely(sinfo->nr_frags >= MAX_SKB_FRAGS)) {
 				err = -ENOSPC;
-				goto out_xdp_abort;
+				break;
 			}
 
 			frag = &sinfo->frags[sinfo->nr_frags];
 			sinfo->nr_frags++;
 			bi++;
-			frag_len = min_t(u16, remain_len, ionic_rx_buf_size(bi));
-			dma_sync_single_range_for_cpu(rxq->dev, ionic_rx_buf_pa(bi),
-						      0, frag_len, DMA_FROM_DEVICE);
+			frag_len = min_t(u16, remain_len, bi->len);
+			page_pool_dma_sync_for_cpu(rxq->page_pool, bi->page,
+						   buf_info->page_offset,
+						   frag_len);
 			skb_frag_fill_page_desc(frag, bi->page, 0, frag_len);
 			sinfo->xdp_frags_size += frag_len;
 			remain_len -= frag_len;
@@ -569,14 +536,16 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 		return false;  /* false = we didn't consume the packet */
 
 	case XDP_DROP:
-		ionic_rx_page_free(rxq, buf_info);
+		ionic_rx_put_buf_direct(rxq, buf_info);
 		stats->xdp_drop++;
 		break;
 
 	case XDP_TX:
 		xdpf = xdp_convert_buff_to_frame(&xdp_buf);
-		if (!xdpf)
-			goto out_xdp_abort;
+		if (!xdpf) {
+			err = -ENOSPC;
+			break;
+		}
 
 		txq = rxq->partner;
 		nq = netdev_get_tx_queue(netdev, txq->index);
@@ -588,7 +557,8 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 					  ionic_q_space_avail(txq),
 					  1, 1)) {
 			__netif_tx_unlock(nq);
-			goto out_xdp_abort;
+			err = -EIO;
+			break;
 		}
 
 		err = ionic_xdp_post_frame(txq, xdpf, XDP_TX,
@@ -598,19 +568,17 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 		__netif_tx_unlock(nq);
 		if (unlikely(err)) {
 			netdev_dbg(netdev, "tx ionic_xdp_post_frame err %d\n", err);
-			goto out_xdp_abort;
+			break;
 		}
 		ionic_xdp_rx_unlink_bufs(rxq, buf_info, nbufs);
 		stats->xdp_tx++;
-
-		/* the Tx completion will free the buffers */
 		break;
 
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(netdev, &xdp_buf, xdp_prog);
 		if (unlikely(err)) {
 			netdev_dbg(netdev, "xdp_do_redirect err %d\n", err);
-			goto out_xdp_abort;
+			break;
 		}
 		ionic_xdp_rx_unlink_bufs(rxq, buf_info, nbufs);
 		rxq->xdp_flush = true;
@@ -619,15 +587,15 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 
 	case XDP_ABORTED:
 	default:
-		goto out_xdp_abort;
+		err = -EIO;
+		break;
 	}
 
-	return true;
-
-out_xdp_abort:
-	trace_xdp_exception(netdev, xdp_prog, xdp_action);
-	ionic_rx_page_free(rxq, buf_info);
-	stats->xdp_aborted++;
+	if (err) {
+		ionic_rx_put_buf_direct(rxq, buf_info);
+		trace_xdp_exception(netdev, xdp_prog, xdp_action);
+		stats->xdp_aborted++;
+	}
 
 	return true;
 }
@@ -673,7 +641,8 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	use_copybreak = len <= q->lif->rx_copybreak;
 	if (use_copybreak)
 		skb = ionic_rx_copybreak(netdev, q, desc_info,
-					 headroom, len, synced);
+					 headroom, len,
+					 comp->num_sg_elems, synced);
 	else
 		skb = ionic_rx_build_skb(q, desc_info, headroom, len,
 					 comp->num_sg_elems, synced);
@@ -794,6 +763,9 @@ void ionic_rx_fill(struct ionic_queue *q)
 	struct ionic_buf_info *buf_info;
 	unsigned int fill_threshold;
 	struct ionic_rxq_desc *desc;
+	unsigned int first_frag_len;
+	unsigned int first_buf_len;
+	unsigned int headroom = 0;
 	unsigned int remain_len;
 	unsigned int frag_len;
 	unsigned int nfrags;
@@ -811,35 +783,42 @@ void ionic_rx_fill(struct ionic_queue *q)
 
 	len = netdev->mtu + VLAN_ETH_HLEN;
 
-	for (i = n_fill; i; i--) {
-		unsigned int headroom = 0;
-		unsigned int buf_len;
+	if (q->xdp_prog) {
+		/* Always alloc the full size buffer, but only need
+		 * the actual frag_len in the descriptor
+		 * XDP uses space in the first buffer, so account for
+		 * head room, tail room, and ip header in the first frag size.
+		 */
+		headroom = XDP_PACKET_HEADROOM;
+		first_buf_len = IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN + headroom;
+		first_frag_len = min_t(u16, len + headroom, first_buf_len);
+	} else {
+		/* Use MTU size if smaller than max buffer size */
+		first_frag_len = min_t(u16, len, IONIC_PAGE_SIZE);
+		first_buf_len = first_frag_len;
+	}
 
+	for (i = n_fill; i; i--) {
+		/* fill main descriptor - buf[0] */
 		nfrags = 0;
 		remain_len = len;
 		desc = &q->rxq[q->head_idx];
 		desc_info = &q->rx_info[q->head_idx];
 		buf_info = &desc_info->bufs[0];
 
-		if (!buf_info->page) { /* alloc a new buffer? */
-			if (unlikely(ionic_rx_page_alloc(q, buf_info))) {
-				desc->addr = 0;
-				desc->len = 0;
-				return;
-			}
-		}
-
-		/* fill main descriptor - buf[0]
-		 * XDP uses space in the first buffer, so account for
-		 * head room, tail room, and ip header in the first frag size.
-		 */
-		if (q->xdp_prog) {
-			buf_len = IONIC_XDP_MAX_LINEAR_MTU + VLAN_ETH_HLEN;
-			headroom = XDP_PACKET_HEADROOM;
-		} else {
-			buf_len = ionic_rx_buf_size(buf_info);
+		buf_info->len = first_buf_len;
+		frag_len = first_frag_len - headroom;
+
+		/* get a new buffer if we can't reuse one */
+		if (!buf_info->page)
+			buf_info->page = page_pool_alloc(q->page_pool,
+							 &buf_info->page_offset,
+							 &buf_info->len,
+							 GFP_ATOMIC);
+		if (unlikely(!buf_info->page)) {
+			buf_info->len = 0;
+			return;
 		}
-		frag_len = min_t(u16, len, buf_len);
 
 		desc->addr = cpu_to_le64(ionic_rx_buf_pa(buf_info) + headroom);
 		desc->len = cpu_to_le16(frag_len);
@@ -850,16 +829,26 @@ void ionic_rx_fill(struct ionic_queue *q)
 		/* fill sg descriptors - buf[1..n] */
 		sg_elem = q->rxq_sgl[q->head_idx].elems;
 		for (j = 0; remain_len > 0 && j < q->max_sg_elems; j++, sg_elem++) {
-			if (!buf_info->page) { /* alloc a new sg buffer? */
-				if (unlikely(ionic_rx_page_alloc(q, buf_info))) {
-					sg_elem->addr = 0;
-					sg_elem->len = 0;
+			frag_len = min_t(u16, remain_len, IONIC_PAGE_SIZE);
+
+			/* Recycle any leftover buffers that are too small to reuse */
+			if (unlikely(buf_info->page && buf_info->len < frag_len))
+				ionic_rx_put_buf_direct(q, buf_info);
+
+			/* Get new buffer if needed */
+			if (!buf_info->page) {
+				buf_info->len = frag_len;
+				buf_info->page = page_pool_alloc(q->page_pool,
+								 &buf_info->page_offset,
+								 &buf_info->len,
+								 GFP_ATOMIC);
+				if (unlikely(!buf_info->page)) {
+					buf_info->len = 0;
 					return;
 				}
 			}
 
 			sg_elem->addr = cpu_to_le64(ionic_rx_buf_pa(buf_info));
-			frag_len = min_t(u16, remain_len, ionic_rx_buf_size(buf_info));
 			sg_elem->len = cpu_to_le16(frag_len);
 			remain_len -= frag_len;
 			buf_info++;
@@ -889,17 +878,12 @@ void ionic_rx_fill(struct ionic_queue *q)
 void ionic_rx_empty(struct ionic_queue *q)
 {
 	struct ionic_rx_desc_info *desc_info;
-	struct ionic_buf_info *buf_info;
 	unsigned int i, j;
 
 	for (i = 0; i < q->num_descs; i++) {
 		desc_info = &q->rx_info[i];
-		for (j = 0; j < ARRAY_SIZE(desc_info->bufs); j++) {
-			buf_info = &desc_info->bufs[j];
-			if (buf_info->page)
-				ionic_rx_page_free(q, buf_info);
-		}
-
+		for (j = 0; j < ARRAY_SIZE(desc_info->bufs); j++)
+			ionic_rx_put_buf(q, &desc_info->bufs[j]);
 		desc_info->nbufs = 0;
 	}
 
@@ -1172,7 +1156,7 @@ static void ionic_tx_clean(struct ionic_queue *q,
 	struct sk_buff *skb;
 
 	if (desc_info->xdpf) {
-		ionic_xdp_tx_desc_clean(q->partner, desc_info);
+		ionic_xdp_tx_desc_clean(q->partner, desc_info, in_napi);
 		stats->clean++;
 
 		if (unlikely(__netif_subqueue_stopped(q->lif->netdev, q->index)))
-- 
cgit v1.3-3-g829e


From 3c0bf13f5d5fcd6722e83a7203bf3dbb3ef73b6f Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Fri, 6 Sep 2024 16:26:23 -0700
Subject: ionic: Allow XDP program to be hot swapped

Using examples of other driver(s), add the ability to hot-swap an XDP
program without having to reconfigure the queues. To prevent the
q->xdp_prog to be read/written more than once use READ_ONCE() and
WRITE_ONCE() on the q->xdp_prog.

The q->xdp_prog was being checked in multiple different for loops in the
hot path. The change to allow xdp_prog hot swapping created the
possibility for many READ_ONCE(q->xdp_prog) calls during a single napi
callback. Refactor the Rx napi handling to allow a previous
READ_ONCE(q->xdp_prog) (or NULL for hwstamp_rxq) to be passed into the
relevant functions.

Also, move other Rx related hotpath handling into the newly created
ionic_rx_cq_service() function to reduce the scope of the xdp_prog
local variable and put all Rx handling in one function similar to Tx.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20240906232623.39651-8-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c  | 12 +++--
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 58 +++++++++++++++++-------
 drivers/net/ethernet/pensando/ionic/ionic_txrx.h |  4 +-
 3 files changed, 52 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index a9d66d79bbf1..40496587b2b3 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1074,7 +1074,7 @@ int ionic_lif_create_hwstamp_rxq(struct ionic_lif *lif)
 			goto err_qcq_init;
 
 		if (test_bit(IONIC_LIF_F_UP, lif->state)) {
-			ionic_rx_fill(&rxq->q);
+			ionic_rx_fill(&rxq->q, NULL);
 			err = ionic_qcq_enable(rxq);
 			if (err)
 				goto err_qcq_enable;
@@ -2190,7 +2190,8 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 			goto err_out;
 		}
 
-		ionic_rx_fill(&lif->rxqcqs[i]->q);
+		ionic_rx_fill(&lif->rxqcqs[i]->q,
+			      READ_ONCE(lif->rxqcqs[i]->q.xdp_prog));
 		err = ionic_qcq_enable(lif->rxqcqs[i]);
 		if (err)
 			goto err_out;
@@ -2203,7 +2204,7 @@ static int ionic_txrx_enable(struct ionic_lif *lif)
 	}
 
 	if (lif->hwstamp_rxq) {
-		ionic_rx_fill(&lif->hwstamp_rxq->q);
+		ionic_rx_fill(&lif->hwstamp_rxq->q, NULL);
 		err = ionic_qcq_enable(lif->hwstamp_rxq);
 		if (err)
 			goto err_out_hwstamp_rx;
@@ -2746,7 +2747,7 @@ static void ionic_xdp_rxqs_prog_update(struct ionic_lif *lif)
 	for (i = 0; i < lif->ionic->nrxqs_per_lif && lif->rxqcqs[i]; i++) {
 		struct ionic_queue *q = &lif->rxqcqs[i]->q;
 
-		q->xdp_prog = xdp_prog;
+		WRITE_ONCE(q->xdp_prog, xdp_prog);
 	}
 }
 
@@ -2777,6 +2778,9 @@ static int ionic_xdp_config(struct net_device *netdev, struct netdev_bpf *bpf)
 
 	if (!netif_running(netdev)) {
 		old_prog = xchg(&lif->xdp_prog, bpf->prog);
+	} else if (lif->xdp_prog && bpf->prog) {
+		old_prog = xchg(&lif->xdp_prog, bpf->prog);
+		ionic_xdp_rxqs_prog_update(lif);
 	} else {
 		struct ionic_queue_params qparams;
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 35e3751dd5a7..0eeda7e502db 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -602,7 +602,8 @@ static bool ionic_run_xdp(struct ionic_rx_stats *stats,
 
 static void ionic_rx_clean(struct ionic_queue *q,
 			   struct ionic_rx_desc_info *desc_info,
-			   struct ionic_rxq_comp *comp)
+			   struct ionic_rxq_comp *comp,
+			   struct bpf_prog *xdp_prog)
 {
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_qcq *qcq = q_to_qcq(q);
@@ -631,8 +632,8 @@ static void ionic_rx_clean(struct ionic_queue *q,
 	stats->pkts++;
 	stats->bytes += len;
 
-	if (q->xdp_prog) {
-		if (ionic_run_xdp(stats, netdev, q->xdp_prog, q, desc_info->bufs, len))
+	if (xdp_prog) {
+		if (ionic_run_xdp(stats, netdev, xdp_prog, q, desc_info->bufs, len))
 			return;
 		synced = true;
 		headroom = XDP_PACKET_HEADROOM;
@@ -718,7 +719,7 @@ static void ionic_rx_clean(struct ionic_queue *q,
 		napi_gro_frags(&qcq->napi);
 }
 
-bool ionic_rx_service(struct ionic_cq *cq)
+static bool __ionic_rx_service(struct ionic_cq *cq, struct bpf_prog *xdp_prog)
 {
 	struct ionic_rx_desc_info *desc_info;
 	struct ionic_queue *q = cq->bound_q;
@@ -740,11 +741,16 @@ bool ionic_rx_service(struct ionic_cq *cq)
 	q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);
 
 	/* clean the related q entry, only one per qc completion */
-	ionic_rx_clean(q, desc_info, comp);
+	ionic_rx_clean(q, desc_info, comp, xdp_prog);
 
 	return true;
 }
 
+bool ionic_rx_service(struct ionic_cq *cq)
+{
+	return __ionic_rx_service(cq, NULL);
+}
+
 static inline void ionic_write_cmb_desc(struct ionic_queue *q,
 					void *desc)
 {
@@ -755,7 +761,7 @@ static inline void ionic_write_cmb_desc(struct ionic_queue *q,
 		memcpy_toio(&q->cmb_txq[q->head_idx], desc, sizeof(q->cmb_txq[0]));
 }
 
-void ionic_rx_fill(struct ionic_queue *q)
+void ionic_rx_fill(struct ionic_queue *q, struct bpf_prog *xdp_prog)
 {
 	struct net_device *netdev = q->lif->netdev;
 	struct ionic_rx_desc_info *desc_info;
@@ -783,7 +789,7 @@ void ionic_rx_fill(struct ionic_queue *q)
 
 	len = netdev->mtu + VLAN_ETH_HLEN;
 
-	if (q->xdp_prog) {
+	if (xdp_prog) {
 		/* Always alloc the full size buffer, but only need
 		 * the actual frag_len in the descriptor
 		 * XDP uses space in the first buffer, so account for
@@ -964,6 +970,32 @@ static void ionic_xdp_do_flush(struct ionic_cq *cq)
 	}
 }
 
+static unsigned int ionic_rx_cq_service(struct ionic_cq *cq,
+					unsigned int work_to_do)
+{
+	struct ionic_queue *q = cq->bound_q;
+	unsigned int work_done = 0;
+	struct bpf_prog *xdp_prog;
+
+	if (work_to_do == 0)
+		return 0;
+
+	xdp_prog = READ_ONCE(q->xdp_prog);
+	while (__ionic_rx_service(cq, xdp_prog)) {
+		if (cq->tail_idx == cq->num_descs - 1)
+			cq->done_color = !cq->done_color;
+
+		cq->tail_idx = (cq->tail_idx + 1) & (cq->num_descs - 1);
+
+		if (++work_done >= work_to_do)
+			break;
+	}
+	ionic_rx_fill(q, xdp_prog);
+	ionic_xdp_do_flush(cq);
+
+	return work_done;
+}
+
 int ionic_rx_napi(struct napi_struct *napi, int budget)
 {
 	struct ionic_qcq *qcq = napi_to_qcq(napi);
@@ -974,12 +1006,8 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
 	if (unlikely(!budget))
 		return budget;
 
-	work_done = ionic_cq_service(cq, budget,
-				     ionic_rx_service, NULL, NULL);
+	work_done = ionic_rx_cq_service(cq, budget);
 
-	ionic_rx_fill(cq->bound_q);
-
-	ionic_xdp_do_flush(cq);
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
 		ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR);
 		flags |= IONIC_INTR_CRED_UNMASK;
@@ -1020,12 +1048,8 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
 	if (unlikely(!budget))
 		return budget;
 
-	rx_work_done = ionic_cq_service(rxcq, budget,
-					ionic_rx_service, NULL, NULL);
-
-	ionic_rx_fill(rxcq->bound_q);
+	rx_work_done = ionic_rx_cq_service(rxcq, budget);
 
-	ionic_xdp_do_flush(rxcq);
 	if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
 		ionic_dim_update(rxqcq, 0);
 		flags |= IONIC_INTR_CRED_UNMASK;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h
index 9e73e324e7a1..b2b9a2dc9eb8 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h
@@ -4,9 +4,11 @@
 #ifndef _IONIC_TXRX_H_
 #define _IONIC_TXRX_H_
 
+struct bpf_prog;
+
 void ionic_tx_flush(struct ionic_cq *cq);
 
-void ionic_rx_fill(struct ionic_queue *q);
+void ionic_rx_fill(struct ionic_queue *q, struct bpf_prog *xdp_prog);
 void ionic_rx_empty(struct ionic_queue *q);
 void ionic_tx_empty(struct ionic_queue *q);
 int ionic_rx_napi(struct napi_struct *napi, int budget);
-- 
cgit v1.3-3-g829e


From 63acda75801fa2f8ff10c4748cc8c420d34f6ea3 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:29 +0200
Subject: net: lan966x: select FDMA library

Select the newly introduced FDMA library.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/microchip/lan966x/Kconfig b/drivers/net/ethernet/microchip/lan966x/Kconfig
index f9ebffc04eb8..f663b6e12466 100644
--- a/drivers/net/ethernet/microchip/lan966x/Kconfig
+++ b/drivers/net/ethernet/microchip/lan966x/Kconfig
@@ -8,6 +8,7 @@ config LAN966X_SWITCH
 	select PHYLINK
 	select PAGE_POOL
 	select VCAP
+	select FDMA
 	help
 	  This driver supports the Lan966x network switch device.
 
-- 
cgit v1.3-3-g829e


From 1dfe4ca8cb4af9d648b0f04e4449728e94eb516e Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:30 +0200
Subject: net: lan966x: use FDMA library symbols

Include and use the new FDMA header, which now provides the required
masks and bit offsets for operating on the DCB's and DB's.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/Makefile       |  1 +
 drivers/net/ethernet/microchip/lan966x/lan966x_main.h | 10 +---------
 2 files changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile
index 3b6ac331691d..4cdbe263502c 100644
--- a/drivers/net/ethernet/microchip/lan966x/Makefile
+++ b/drivers/net/ethernet/microchip/lan966x/Makefile
@@ -20,3 +20,4 @@ lan966x-switch-$(CONFIG_DEBUG_FS) += lan966x_vcap_debugfs.o
 
 # Provide include files
 ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap
+ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/fdma
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index f8bebbcf77b2..4d2aa775fbfd 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -16,6 +16,7 @@
 #include <net/switchdev.h>
 #include <net/xdp.h>
 
+#include <fdma_api.h>
 #include <vcap_api.h>
 #include <vcap_api_client.h>
 
@@ -76,15 +77,6 @@
 
 #define FDMA_RX_DCB_MAX_DBS		1
 #define FDMA_TX_DCB_MAX_DBS		1
-#define FDMA_DCB_INFO_DATAL(x)		((x) & GENMASK(15, 0))
-
-#define FDMA_DCB_STATUS_BLOCKL(x)	((x) & GENMASK(15, 0))
-#define FDMA_DCB_STATUS_SOF		BIT(16)
-#define FDMA_DCB_STATUS_EOF		BIT(17)
-#define FDMA_DCB_STATUS_INTR		BIT(18)
-#define FDMA_DCB_STATUS_DONE		BIT(19)
-#define FDMA_DCB_STATUS_BLOCKO(x)	(((x) << 20) & GENMASK(31, 20))
-#define FDMA_DCB_INVALID_DATA		0x1
 
 #define FDMA_XTR_CHANNEL		6
 #define FDMA_INJ_CHANNEL		0
-- 
cgit v1.3-3-g829e


From 8274d40eafa37b570ad7be8b7fe5fe507509c153 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:31 +0200
Subject: net: lan966x: replace a few variables with new equivalent ones

Replace the old rx and tx variables: channel_id, FDMA_DCB_MAX,
FDMA_RX_DCB_MAX_DBS, FDMA_TX_DCB_MAX_DBS, dcb_index and db_index with
the equivalents from the FDMA rx and tx structs. These variables are not
entangled in any buffer allocation and can therefore be replaced in
advance.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 131 ++++++++++++---------
 .../net/ethernet/microchip/lan966x/lan966x_main.h  |  19 +--
 2 files changed, 81 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 3960534ac2ad..b64f04ff99a8 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -27,10 +27,11 @@ static struct page *lan966x_fdma_rx_alloc_page(struct lan966x_rx *rx,
 
 static void lan966x_fdma_rx_free_pages(struct lan966x_rx *rx)
 {
+	struct fdma *fdma = &rx->fdma;
 	int i, j;
 
-	for (i = 0; i < FDMA_DCB_MAX; ++i) {
-		for (j = 0; j < FDMA_RX_DCB_MAX_DBS; ++j)
+	for (i = 0; i < fdma->n_dcbs; ++i) {
+		for (j = 0; j < fdma->n_dbs; ++j)
 			page_pool_put_full_page(rx->page_pool,
 						rx->page[i][j], false);
 	}
@@ -38,9 +39,10 @@ static void lan966x_fdma_rx_free_pages(struct lan966x_rx *rx)
 
 static void lan966x_fdma_rx_free_page(struct lan966x_rx *rx)
 {
+	struct fdma *fdma = &rx->fdma;
 	struct page *page;
 
-	page = rx->page[rx->dcb_index][rx->db_index];
+	page = rx->page[fdma->dcb_index][fdma->db_index];
 	if (unlikely(!page))
 		return;
 
@@ -51,10 +53,11 @@ static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx,
 				    struct lan966x_rx_dcb *dcb,
 				    u64 nextptr)
 {
+	struct fdma *fdma = &rx->fdma;
 	struct lan966x_db *db;
 	int i;
 
-	for (i = 0; i < FDMA_RX_DCB_MAX_DBS; ++i) {
+	for (i = 0; i < fdma->n_dbs; ++i) {
 		db = &dcb->db[i];
 		db->status = FDMA_DCB_STATUS_INTR;
 	}
@@ -72,7 +75,7 @@ static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx)
 	struct page_pool_params pp_params = {
 		.order = rx->page_order,
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
-		.pool_size = FDMA_DCB_MAX,
+		.pool_size = rx->fdma.n_dcbs,
 		.nid = NUMA_NO_NODE,
 		.dev = lan966x->dev,
 		.dma_dir = DMA_FROM_DEVICE,
@@ -104,6 +107,7 @@ static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx)
 static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
+	struct fdma *fdma = &rx->fdma;
 	struct lan966x_rx_dcb *dcb;
 	struct lan966x_db *db;
 	struct page *page;
@@ -114,7 +118,7 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 		return PTR_ERR(rx->page_pool);
 
 	/* calculate how many pages are needed to allocate the dcbs */
-	size = sizeof(struct lan966x_rx_dcb) * FDMA_DCB_MAX;
+	size = sizeof(struct lan966x_rx_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 
 	rx->dcbs = dma_alloc_coherent(lan966x->dev, size, &rx->dma, GFP_KERNEL);
@@ -122,16 +126,16 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 		return -ENOMEM;
 
 	rx->last_entry = rx->dcbs;
-	rx->db_index = 0;
-	rx->dcb_index = 0;
+	fdma->db_index = 0;
+	fdma->dcb_index = 0;
 
 	/* Now for each dcb allocate the dbs */
-	for (i = 0; i < FDMA_DCB_MAX; ++i) {
+	for (i = 0; i < fdma->n_dcbs; ++i) {
 		dcb = &rx->dcbs[i];
 		dcb->info = 0;
 
 		/* For each db allocate a page and map it to the DB dataptr. */
-		for (j = 0; j < FDMA_RX_DCB_MAX_DBS; ++j) {
+		for (j = 0; j < fdma->n_dbs; ++j) {
 			db = &dcb->db[j];
 			page = lan966x_fdma_rx_alloc_page(rx, db);
 			if (!page)
@@ -149,17 +153,20 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 
 static void lan966x_fdma_rx_advance_dcb(struct lan966x_rx *rx)
 {
-	rx->dcb_index++;
-	rx->dcb_index &= FDMA_DCB_MAX - 1;
+	struct fdma *fdma = &rx->fdma;
+
+	fdma->dcb_index++;
+	fdma->dcb_index &= fdma->n_dcbs - 1;
 }
 
 static void lan966x_fdma_rx_free(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
+	struct fdma *fdma = &rx->fdma;
 	u32 size;
 
 	/* Now it is possible to do the cleanup of dcb */
-	size = sizeof(struct lan966x_tx_dcb) * FDMA_DCB_MAX;
+	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	dma_free_coherent(lan966x->dev, size, rx->dcbs, rx->dma);
 }
@@ -167,21 +174,22 @@ static void lan966x_fdma_rx_free(struct lan966x_rx *rx)
 static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
+	struct fdma *fdma = &rx->fdma;
 	u32 mask;
 
 	/* When activating a channel, first is required to write the first DCB
 	 * address and then to activate it
 	 */
 	lan_wr(lower_32_bits((u64)rx->dma), lan966x,
-	       FDMA_DCB_LLP(rx->channel_id));
+	       FDMA_DCB_LLP(fdma->channel_id));
 	lan_wr(upper_32_bits((u64)rx->dma), lan966x,
-	       FDMA_DCB_LLP1(rx->channel_id));
+	       FDMA_DCB_LLP1(fdma->channel_id));
 
-	lan_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(FDMA_RX_DCB_MAX_DBS) |
+	lan_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
 	       FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(1) |
 	       FDMA_CH_CFG_CH_INJ_PORT_SET(0) |
 	       FDMA_CH_CFG_CH_MEM_SET(1),
-	       lan966x, FDMA_CH_CFG(rx->channel_id));
+	       lan966x, FDMA_CH_CFG(fdma->channel_id));
 
 	/* Start fdma */
 	lan_rmw(FDMA_PORT_CTRL_XTR_STOP_SET(0),
@@ -191,13 +199,13 @@ static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
 	/* Enable interrupts */
 	mask = lan_rd(lan966x, FDMA_INTR_DB_ENA);
 	mask = FDMA_INTR_DB_ENA_INTR_DB_ENA_GET(mask);
-	mask |= BIT(rx->channel_id);
+	mask |= BIT(fdma->channel_id);
 	lan_rmw(FDMA_INTR_DB_ENA_INTR_DB_ENA_SET(mask),
 		FDMA_INTR_DB_ENA_INTR_DB_ENA,
 		lan966x, FDMA_INTR_DB_ENA);
 
 	/* Activate the channel */
-	lan_rmw(FDMA_CH_ACTIVATE_CH_ACTIVATE_SET(BIT(rx->channel_id)),
+	lan_rmw(FDMA_CH_ACTIVATE_CH_ACTIVATE_SET(BIT(fdma->channel_id)),
 		FDMA_CH_ACTIVATE_CH_ACTIVATE,
 		lan966x, FDMA_CH_ACTIVATE);
 }
@@ -205,18 +213,19 @@ static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
 static void lan966x_fdma_rx_disable(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
+	struct fdma *fdma = &rx->fdma;
 	u32 val;
 
 	/* Disable the channel */
-	lan_rmw(FDMA_CH_DISABLE_CH_DISABLE_SET(BIT(rx->channel_id)),
+	lan_rmw(FDMA_CH_DISABLE_CH_DISABLE_SET(BIT(fdma->channel_id)),
 		FDMA_CH_DISABLE_CH_DISABLE,
 		lan966x, FDMA_CH_DISABLE);
 
 	readx_poll_timeout_atomic(lan966x_fdma_channel_active, lan966x,
-				  val, !(val & BIT(rx->channel_id)),
+				  val, !(val & BIT(fdma->channel_id)),
 				  READL_SLEEP_US, READL_TIMEOUT_US);
 
-	lan_rmw(FDMA_CH_DB_DISCARD_DB_DISCARD_SET(BIT(rx->channel_id)),
+	lan_rmw(FDMA_CH_DB_DISCARD_DB_DISCARD_SET(BIT(fdma->channel_id)),
 		FDMA_CH_DB_DISCARD_DB_DISCARD,
 		lan966x, FDMA_CH_DB_DISCARD);
 }
@@ -225,7 +234,7 @@ static void lan966x_fdma_rx_reload(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
 
-	lan_rmw(FDMA_CH_RELOAD_CH_RELOAD_SET(BIT(rx->channel_id)),
+	lan_rmw(FDMA_CH_RELOAD_CH_RELOAD_SET(BIT(rx->fdma.channel_id)),
 		FDMA_CH_RELOAD_CH_RELOAD,
 		lan966x, FDMA_CH_RELOAD);
 }
@@ -240,28 +249,29 @@ static void lan966x_fdma_tx_add_dcb(struct lan966x_tx *tx,
 static int lan966x_fdma_tx_alloc(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
+	struct fdma *fdma = &tx->fdma;
 	struct lan966x_tx_dcb *dcb;
 	struct lan966x_db *db;
 	int size;
 	int i, j;
 
-	tx->dcbs_buf = kcalloc(FDMA_DCB_MAX, sizeof(struct lan966x_tx_dcb_buf),
+	tx->dcbs_buf = kcalloc(fdma->n_dcbs, sizeof(struct lan966x_tx_dcb_buf),
 			       GFP_KERNEL);
 	if (!tx->dcbs_buf)
 		return -ENOMEM;
 
 	/* calculate how many pages are needed to allocate the dcbs */
-	size = sizeof(struct lan966x_tx_dcb) * FDMA_DCB_MAX;
+	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	tx->dcbs = dma_alloc_coherent(lan966x->dev, size, &tx->dma, GFP_KERNEL);
 	if (!tx->dcbs)
 		goto out;
 
 	/* Now for each dcb allocate the db */
-	for (i = 0; i < FDMA_DCB_MAX; ++i) {
+	for (i = 0; i < fdma->n_dcbs; ++i) {
 		dcb = &tx->dcbs[i];
 
-		for (j = 0; j < FDMA_TX_DCB_MAX_DBS; ++j) {
+		for (j = 0; j < fdma->n_dbs; ++j) {
 			db = &dcb->db[j];
 			db->dataptr = 0;
 			db->status = 0;
@@ -280,11 +290,12 @@ out:
 static void lan966x_fdma_tx_free(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
+	struct fdma *fdma = &tx->fdma;
 	int size;
 
 	kfree(tx->dcbs_buf);
 
-	size = sizeof(struct lan966x_tx_dcb) * FDMA_DCB_MAX;
+	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	dma_free_coherent(lan966x->dev, size, tx->dcbs, tx->dma);
 }
@@ -292,21 +303,22 @@ static void lan966x_fdma_tx_free(struct lan966x_tx *tx)
 static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
+	struct fdma *fdma = &tx->fdma;
 	u32 mask;
 
 	/* When activating a channel, first is required to write the first DCB
 	 * address and then to activate it
 	 */
 	lan_wr(lower_32_bits((u64)tx->dma), lan966x,
-	       FDMA_DCB_LLP(tx->channel_id));
+	       FDMA_DCB_LLP(fdma->channel_id));
 	lan_wr(upper_32_bits((u64)tx->dma), lan966x,
-	       FDMA_DCB_LLP1(tx->channel_id));
+	       FDMA_DCB_LLP1(fdma->channel_id));
 
-	lan_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(FDMA_TX_DCB_MAX_DBS) |
+	lan_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
 	       FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(1) |
 	       FDMA_CH_CFG_CH_INJ_PORT_SET(0) |
 	       FDMA_CH_CFG_CH_MEM_SET(1),
-	       lan966x, FDMA_CH_CFG(tx->channel_id));
+	       lan966x, FDMA_CH_CFG(fdma->channel_id));
 
 	/* Start fdma */
 	lan_rmw(FDMA_PORT_CTRL_INJ_STOP_SET(0),
@@ -316,13 +328,13 @@ static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
 	/* Enable interrupts */
 	mask = lan_rd(lan966x, FDMA_INTR_DB_ENA);
 	mask = FDMA_INTR_DB_ENA_INTR_DB_ENA_GET(mask);
-	mask |= BIT(tx->channel_id);
+	mask |= BIT(fdma->channel_id);
 	lan_rmw(FDMA_INTR_DB_ENA_INTR_DB_ENA_SET(mask),
 		FDMA_INTR_DB_ENA_INTR_DB_ENA,
 		lan966x, FDMA_INTR_DB_ENA);
 
 	/* Activate the channel */
-	lan_rmw(FDMA_CH_ACTIVATE_CH_ACTIVATE_SET(BIT(tx->channel_id)),
+	lan_rmw(FDMA_CH_ACTIVATE_CH_ACTIVATE_SET(BIT(fdma->channel_id)),
 		FDMA_CH_ACTIVATE_CH_ACTIVATE,
 		lan966x, FDMA_CH_ACTIVATE);
 }
@@ -330,18 +342,19 @@ static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
 static void lan966x_fdma_tx_disable(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
+	struct fdma *fdma = &tx->fdma;
 	u32 val;
 
 	/* Disable the channel */
-	lan_rmw(FDMA_CH_DISABLE_CH_DISABLE_SET(BIT(tx->channel_id)),
+	lan_rmw(FDMA_CH_DISABLE_CH_DISABLE_SET(BIT(fdma->channel_id)),
 		FDMA_CH_DISABLE_CH_DISABLE,
 		lan966x, FDMA_CH_DISABLE);
 
 	readx_poll_timeout_atomic(lan966x_fdma_channel_active, lan966x,
-				  val, !(val & BIT(tx->channel_id)),
+				  val, !(val & BIT(fdma->channel_id)),
 				  READL_SLEEP_US, READL_TIMEOUT_US);
 
-	lan_rmw(FDMA_CH_DB_DISCARD_DB_DISCARD_SET(BIT(tx->channel_id)),
+	lan_rmw(FDMA_CH_DB_DISCARD_DB_DISCARD_SET(BIT(fdma->channel_id)),
 		FDMA_CH_DB_DISCARD_DB_DISCARD,
 		lan966x, FDMA_CH_DB_DISCARD);
 
@@ -354,7 +367,7 @@ static void lan966x_fdma_tx_reload(struct lan966x_tx *tx)
 	struct lan966x *lan966x = tx->lan966x;
 
 	/* Write the registers to reload the channel */
-	lan_rmw(FDMA_CH_RELOAD_CH_RELOAD_SET(BIT(tx->channel_id)),
+	lan_rmw(FDMA_CH_RELOAD_CH_RELOAD_SET(BIT(tx->fdma.channel_id)),
 		FDMA_CH_RELOAD_CH_RELOAD,
 		lan966x, FDMA_CH_RELOAD);
 }
@@ -402,7 +415,7 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 	xdp_frame_bulk_init(&bq);
 
 	spin_lock_irqsave(&lan966x->tx_lock, flags);
-	for (i = 0; i < FDMA_DCB_MAX; ++i) {
+	for (i = 0; i < tx->fdma.n_dcbs; ++i) {
 		dcb_buf = &tx->dcbs_buf[i];
 
 		if (!dcb_buf->used)
@@ -451,10 +464,11 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 
 static bool lan966x_fdma_rx_more_frames(struct lan966x_rx *rx)
 {
+	struct fdma *fdma = &rx->fdma;
 	struct lan966x_db *db;
 
 	/* Check if there is any data */
-	db = &rx->dcbs[rx->dcb_index].db[rx->db_index];
+	db = &rx->dcbs[fdma->dcb_index].db[fdma->db_index];
 	if (unlikely(!(db->status & FDMA_DCB_STATUS_DONE)))
 		return false;
 
@@ -464,12 +478,13 @@ static bool lan966x_fdma_rx_more_frames(struct lan966x_rx *rx)
 static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port)
 {
 	struct lan966x *lan966x = rx->lan966x;
+	struct fdma *fdma = &rx->fdma;
 	struct lan966x_port *port;
 	struct lan966x_db *db;
 	struct page *page;
 
-	db = &rx->dcbs[rx->dcb_index].db[rx->db_index];
-	page = rx->page[rx->dcb_index][rx->db_index];
+	db = &rx->dcbs[fdma->dcb_index].db[fdma->db_index];
+	page = rx->page[fdma->dcb_index][fdma->db_index];
 	if (unlikely(!page))
 		return FDMA_ERROR;
 
@@ -494,14 +509,15 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx,
 						 u64 src_port)
 {
 	struct lan966x *lan966x = rx->lan966x;
+	struct fdma *fdma = &rx->fdma;
 	struct lan966x_db *db;
 	struct sk_buff *skb;
 	struct page *page;
 	u64 timestamp;
 
 	/* Get the received frame and unmap it */
-	db = &rx->dcbs[rx->dcb_index].db[rx->db_index];
-	page = rx->page[rx->dcb_index][rx->db_index];
+	db = &rx->dcbs[fdma->dcb_index].db[fdma->db_index];
+	page = rx->page[fdma->dcb_index][fdma->db_index];
 
 	skb = build_skb(page_address(page), PAGE_SIZE << rx->page_order);
 	if (unlikely(!skb))
@@ -546,16 +562,18 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 {
 	struct lan966x *lan966x = container_of(napi, struct lan966x, napi);
 	struct lan966x_rx *rx = &lan966x->rx;
-	int dcb_reload = rx->dcb_index;
 	struct lan966x_rx_dcb *old_dcb;
+	struct fdma *fdma = &rx->fdma;
+	int dcb_reload, counter = 0;
 	struct lan966x_db *db;
 	bool redirect = false;
 	struct sk_buff *skb;
 	struct page *page;
-	int counter = 0;
 	u64 src_port;
 	u64 nextptr;
 
+	dcb_reload = fdma->dcb_index;
+
 	lan966x_fdma_tx_clear_buf(lan966x, weight);
 
 	/* Get all received skb */
@@ -594,16 +612,16 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 
 allocate_new:
 	/* Allocate new pages and map them */
-	while (dcb_reload != rx->dcb_index) {
-		db = &rx->dcbs[dcb_reload].db[rx->db_index];
+	while (dcb_reload != fdma->dcb_index) {
+		db = &rx->dcbs[dcb_reload].db[fdma->db_index];
 		page = lan966x_fdma_rx_alloc_page(rx, db);
 		if (unlikely(!page))
 			break;
-		rx->page[dcb_reload][rx->db_index] = page;
+		rx->page[dcb_reload][fdma->db_index] = page;
 
 		old_dcb = &rx->dcbs[dcb_reload];
 		dcb_reload++;
-		dcb_reload &= FDMA_DCB_MAX - 1;
+		dcb_reload &= fdma->n_dcbs - 1;
 
 		nextptr = rx->dma + ((unsigned long)old_dcb -
 				     (unsigned long)rx->dcbs);
@@ -650,9 +668,10 @@ irqreturn_t lan966x_fdma_irq_handler(int irq, void *args)
 static int lan966x_fdma_get_next_dcb(struct lan966x_tx *tx)
 {
 	struct lan966x_tx_dcb_buf *dcb_buf;
+	struct fdma *fdma = &tx->fdma;
 	int i;
 
-	for (i = 0; i < FDMA_DCB_MAX; ++i) {
+	for (i = 0; i < fdma->n_dcbs; ++i) {
 		dcb_buf = &tx->dcbs_buf[i];
 		if (!dcb_buf->used && i != tx->last_in_use)
 			return i;
@@ -931,7 +950,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 		goto restore;
 	lan966x_fdma_rx_start(&lan966x->rx);
 
-	size = sizeof(struct lan966x_rx_dcb) * FDMA_DCB_MAX;
+	size = sizeof(struct lan966x_rx_dcb) * lan966x->rx.fdma.n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma);
 
@@ -1034,10 +1053,14 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 		return 0;
 
 	lan966x->rx.lan966x = lan966x;
-	lan966x->rx.channel_id = FDMA_XTR_CHANNEL;
+	lan966x->rx.fdma.channel_id = FDMA_XTR_CHANNEL;
+	lan966x->rx.fdma.n_dcbs = FDMA_DCB_MAX;
+	lan966x->rx.fdma.n_dbs = FDMA_RX_DCB_MAX_DBS;
 	lan966x->rx.max_mtu = lan966x_fdma_get_max_frame(lan966x);
 	lan966x->tx.lan966x = lan966x;
-	lan966x->tx.channel_id = FDMA_INJ_CHANNEL;
+	lan966x->tx.fdma.channel_id = FDMA_INJ_CHANNEL;
+	lan966x->tx.fdma.n_dcbs = FDMA_DCB_MAX;
+	lan966x->tx.fdma.n_dbs = FDMA_TX_DCB_MAX_DBS;
 	lan966x->tx.last_in_use = -1;
 
 	err = lan966x_fdma_rx_alloc(&lan966x->rx);
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 4d2aa775fbfd..fb9d8e00fe69 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -211,6 +211,8 @@ struct lan966x_tx_dcb {
 struct lan966x_rx {
 	struct lan966x *lan966x;
 
+	struct fdma fdma;
+
 	/* Pointer to the array of hardware dcbs. */
 	struct lan966x_rx_dcb *dcbs;
 
@@ -220,17 +222,6 @@ struct lan966x_rx {
 	/* For each DB, there is a page */
 	struct page *page[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
 
-	/* Represents the db_index, it can have a value between 0 and
-	 * FDMA_RX_DCB_MAX_DBS, once it reaches the value of FDMA_RX_DCB_MAX_DBS
-	 * it means that the DCB can be reused.
-	 */
-	int db_index;
-
-	/* Represents the index in the dcbs. It has a value between 0 and
-	 * FDMA_DCB_MAX
-	 */
-	int dcb_index;
-
 	/* Represents the dma address to the dcbs array */
 	dma_addr_t dma;
 
@@ -244,8 +235,6 @@ struct lan966x_rx {
 	 */
 	u32 max_mtu;
 
-	u8 channel_id;
-
 	struct page_pool *page_pool;
 };
 
@@ -267,6 +256,8 @@ struct lan966x_tx_dcb_buf {
 struct lan966x_tx {
 	struct lan966x *lan966x;
 
+	struct fdma fdma;
+
 	/* Pointer to the dcb list */
 	struct lan966x_tx_dcb *dcbs;
 	u16 last_in_use;
@@ -277,8 +268,6 @@ struct lan966x_tx {
 	/* Array of dcbs that are given to the HW */
 	struct lan966x_tx_dcb_buf *dcbs_buf;
 
-	u8 channel_id;
-
 	bool activated;
 };
 
-- 
cgit v1.3-3-g829e


From 01a70754327bd628610587b6b7ae5efe2a5e7d1c Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:32 +0200
Subject: net: lan966x: use the FDMA library for allocation of rx buffers

Use the two functions: fdma_alloc_phys() and fdma_dcb_init() for rx
buffer allocation and use the new buffers throughout.

In order to replace the old buffers with the new ones, we have to do the
following refactoring:

    - use fdma_alloc_phys() and fdma_dcb_init()

    - replace the variables: rx->dma, rx->dcbs and rx->last_entry
      with the equivalents from the FDMA struct.

    - make use of fdma->db_size for rx buffer size.

    - add lan966x_fdma_rx_dataptr_cb callback for obtaining the dataptr.

    - Initialize FDMA struct values.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 116 ++++++++++-----------
 .../net/ethernet/microchip/lan966x/lan966x_main.h  |  15 ---
 2 files changed, 55 insertions(+), 76 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index b64f04ff99a8..99d09c97737e 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -6,13 +6,30 @@
 
 #include "lan966x_main.h"
 
+static int lan966x_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+				      u64 *dataptr)
+{
+	struct lan966x *lan966x = (struct lan966x *)fdma->priv;
+	struct lan966x_rx *rx = &lan966x->rx;
+	struct page *page;
+
+	page = page_pool_dev_alloc_pages(rx->page_pool);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	rx->page[dcb][db] = page;
+	*dataptr = page_pool_get_dma_addr(page) + XDP_PACKET_HEADROOM;
+
+	return 0;
+}
+
 static int lan966x_fdma_channel_active(struct lan966x *lan966x)
 {
 	return lan_rd(lan966x, FDMA_CH_ACTIVE);
 }
 
 static struct page *lan966x_fdma_rx_alloc_page(struct lan966x_rx *rx,
-					       struct lan966x_db *db)
+					       struct fdma_db *db)
 {
 	struct page *page;
 
@@ -50,11 +67,11 @@ static void lan966x_fdma_rx_free_page(struct lan966x_rx *rx)
 }
 
 static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx,
-				    struct lan966x_rx_dcb *dcb,
+				    struct fdma_dcb *dcb,
 				    u64 nextptr)
 {
 	struct fdma *fdma = &rx->fdma;
-	struct lan966x_db *db;
+	struct fdma_db *db;
 	int i;
 
 	for (i = 0; i < fdma->n_dbs; ++i) {
@@ -65,8 +82,8 @@ static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx,
 	dcb->nextptr = FDMA_DCB_INVALID_DATA;
 	dcb->info = FDMA_DCB_INFO_DATAL(PAGE_SIZE << rx->page_order);
 
-	rx->last_entry->nextptr = nextptr;
-	rx->last_entry = dcb;
+	fdma->last_dcb->nextptr = nextptr;
+	fdma->last_dcb = dcb;
 }
 
 static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx)
@@ -108,45 +125,17 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
 	struct fdma *fdma = &rx->fdma;
-	struct lan966x_rx_dcb *dcb;
-	struct lan966x_db *db;
-	struct page *page;
-	int i, j;
-	int size;
+	int err;
 
 	if (lan966x_fdma_rx_alloc_page_pool(rx))
 		return PTR_ERR(rx->page_pool);
 
-	/* calculate how many pages are needed to allocate the dcbs */
-	size = sizeof(struct lan966x_rx_dcb) * fdma->n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-
-	rx->dcbs = dma_alloc_coherent(lan966x->dev, size, &rx->dma, GFP_KERNEL);
-	if (!rx->dcbs)
-		return -ENOMEM;
-
-	rx->last_entry = rx->dcbs;
-	fdma->db_index = 0;
-	fdma->dcb_index = 0;
-
-	/* Now for each dcb allocate the dbs */
-	for (i = 0; i < fdma->n_dcbs; ++i) {
-		dcb = &rx->dcbs[i];
-		dcb->info = 0;
-
-		/* For each db allocate a page and map it to the DB dataptr. */
-		for (j = 0; j < fdma->n_dbs; ++j) {
-			db = &dcb->db[j];
-			page = lan966x_fdma_rx_alloc_page(rx, db);
-			if (!page)
-				return -ENOMEM;
-
-			db->status = 0;
-			rx->page[i][j] = page;
-		}
+	err = fdma_alloc_coherent(lan966x->dev, fdma);
+	if (err)
+		return err;
 
-		lan966x_fdma_rx_add_dcb(rx, dcb, rx->dma + sizeof(*dcb) * i);
-	}
+	fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size),
+		       FDMA_DCB_STATUS_INTR);
 
 	return 0;
 }
@@ -168,7 +157,7 @@ static void lan966x_fdma_rx_free(struct lan966x_rx *rx)
 	/* Now it is possible to do the cleanup of dcb */
 	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
-	dma_free_coherent(lan966x->dev, size, rx->dcbs, rx->dma);
+	dma_free_coherent(lan966x->dev, size, fdma->dcbs, fdma->dma);
 }
 
 static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
@@ -180,9 +169,9 @@ static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
 	/* When activating a channel, first is required to write the first DCB
 	 * address and then to activate it
 	 */
-	lan_wr(lower_32_bits((u64)rx->dma), lan966x,
+	lan_wr(lower_32_bits((u64)fdma->dma), lan966x,
 	       FDMA_DCB_LLP(fdma->channel_id));
-	lan_wr(upper_32_bits((u64)rx->dma), lan966x,
+	lan_wr(upper_32_bits((u64)fdma->dma), lan966x,
 	       FDMA_DCB_LLP1(fdma->channel_id));
 
 	lan_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
@@ -297,7 +286,7 @@ static void lan966x_fdma_tx_free(struct lan966x_tx *tx)
 
 	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
-	dma_free_coherent(lan966x->dev, size, tx->dcbs, tx->dma);
+	dma_free_coherent(lan966x->dev, size, fdma->dcbs, fdma->dma);
 }
 
 static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
@@ -465,10 +454,10 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 static bool lan966x_fdma_rx_more_frames(struct lan966x_rx *rx)
 {
 	struct fdma *fdma = &rx->fdma;
-	struct lan966x_db *db;
+	struct fdma_db *db;
 
 	/* Check if there is any data */
-	db = &rx->dcbs[fdma->dcb_index].db[fdma->db_index];
+	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
 	if (unlikely(!(db->status & FDMA_DCB_STATUS_DONE)))
 		return false;
 
@@ -480,10 +469,10 @@ static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port)
 	struct lan966x *lan966x = rx->lan966x;
 	struct fdma *fdma = &rx->fdma;
 	struct lan966x_port *port;
-	struct lan966x_db *db;
+	struct fdma_db *db;
 	struct page *page;
 
-	db = &rx->dcbs[fdma->dcb_index].db[fdma->db_index];
+	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
 	page = rx->page[fdma->dcb_index][fdma->db_index];
 	if (unlikely(!page))
 		return FDMA_ERROR;
@@ -510,16 +499,16 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx,
 {
 	struct lan966x *lan966x = rx->lan966x;
 	struct fdma *fdma = &rx->fdma;
-	struct lan966x_db *db;
 	struct sk_buff *skb;
+	struct fdma_db *db;
 	struct page *page;
 	u64 timestamp;
 
 	/* Get the received frame and unmap it */
-	db = &rx->dcbs[fdma->dcb_index].db[fdma->db_index];
+	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
 	page = rx->page[fdma->dcb_index][fdma->db_index];
 
-	skb = build_skb(page_address(page), PAGE_SIZE << rx->page_order);
+	skb = build_skb(page_address(page), fdma->db_size);
 	if (unlikely(!skb))
 		goto free_page;
 
@@ -562,12 +551,12 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 {
 	struct lan966x *lan966x = container_of(napi, struct lan966x, napi);
 	struct lan966x_rx *rx = &lan966x->rx;
-	struct lan966x_rx_dcb *old_dcb;
 	struct fdma *fdma = &rx->fdma;
 	int dcb_reload, counter = 0;
-	struct lan966x_db *db;
+	struct fdma_dcb *old_dcb;
 	bool redirect = false;
 	struct sk_buff *skb;
+	struct fdma_db *db;
 	struct page *page;
 	u64 src_port;
 	u64 nextptr;
@@ -613,18 +602,18 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 allocate_new:
 	/* Allocate new pages and map them */
 	while (dcb_reload != fdma->dcb_index) {
-		db = &rx->dcbs[dcb_reload].db[fdma->db_index];
+		db = &fdma->dcbs[dcb_reload].db[fdma->db_index];
 		page = lan966x_fdma_rx_alloc_page(rx, db);
 		if (unlikely(!page))
 			break;
 		rx->page[dcb_reload][fdma->db_index] = page;
 
-		old_dcb = &rx->dcbs[dcb_reload];
+		old_dcb = &fdma->dcbs[dcb_reload];
 		dcb_reload++;
 		dcb_reload &= fdma->n_dcbs - 1;
 
-		nextptr = rx->dma + ((unsigned long)old_dcb -
-				     (unsigned long)rx->dcbs);
+		nextptr = fdma->dma + ((unsigned long)old_dcb -
+				     (unsigned long)fdma->dcbs);
 		lan966x_fdma_rx_add_dcb(rx, old_dcb, nextptr);
 		lan966x_fdma_rx_reload(rx);
 	}
@@ -933,8 +922,8 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 	int err;
 
 	/* Store these for later to free them */
-	rx_dma = lan966x->rx.dma;
-	rx_dcbs = lan966x->rx.dcbs;
+	rx_dma = lan966x->rx.fdma.dma;
+	rx_dcbs = lan966x->rx.fdma.dcbs;
 	page_pool = lan966x->rx.page_pool;
 
 	napi_synchronize(&lan966x->napi);
@@ -950,7 +939,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 		goto restore;
 	lan966x_fdma_rx_start(&lan966x->rx);
 
-	size = sizeof(struct lan966x_rx_dcb) * lan966x->rx.fdma.n_dcbs;
+	size = sizeof(struct fdma_dcb) * lan966x->rx.fdma.n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma);
 
@@ -962,8 +951,8 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 	return err;
 restore:
 	lan966x->rx.page_pool = page_pool;
-	lan966x->rx.dma = rx_dma;
-	lan966x->rx.dcbs = rx_dcbs;
+	lan966x->rx.fdma.dma = rx_dma;
+	lan966x->rx.fdma.dcbs = rx_dcbs;
 	lan966x_fdma_rx_start(&lan966x->rx);
 
 	return err;
@@ -1056,6 +1045,11 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 	lan966x->rx.fdma.channel_id = FDMA_XTR_CHANNEL;
 	lan966x->rx.fdma.n_dcbs = FDMA_DCB_MAX;
 	lan966x->rx.fdma.n_dbs = FDMA_RX_DCB_MAX_DBS;
+	lan966x->rx.fdma.priv = lan966x;
+	lan966x->rx.fdma.size = fdma_get_size(&lan966x->rx.fdma);
+	lan966x->rx.fdma.db_size = PAGE_SIZE << lan966x->rx.page_order;
+	lan966x->rx.fdma.ops.nextptr_cb = &fdma_nextptr_cb;
+	lan966x->rx.fdma.ops.dataptr_cb = &lan966x_fdma_rx_dataptr_cb;
 	lan966x->rx.max_mtu = lan966x_fdma_get_max_frame(lan966x);
 	lan966x->tx.lan966x = lan966x;
 	lan966x->tx.fdma.channel_id = FDMA_INJ_CHANNEL;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index fb9d8e00fe69..8edb5ea484ee 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -196,12 +196,6 @@ struct lan966x_db {
 	u64 status;
 };
 
-struct lan966x_rx_dcb {
-	u64 nextptr;
-	u64 info;
-	struct lan966x_db db[FDMA_RX_DCB_MAX_DBS];
-};
-
 struct lan966x_tx_dcb {
 	u64 nextptr;
 	u64 info;
@@ -213,18 +207,9 @@ struct lan966x_rx {
 
 	struct fdma fdma;
 
-	/* Pointer to the array of hardware dcbs. */
-	struct lan966x_rx_dcb *dcbs;
-
-	/* Pointer to the last address in the dcbs. */
-	struct lan966x_rx_dcb *last_entry;
-
 	/* For each DB, there is a page */
 	struct page *page[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS];
 
-	/* Represents the dma address to the dcbs array */
-	dma_addr_t dma;
-
 	/* Represents the page order that is used to allocate the pages for the
 	 * RX buffers. This value is calculated based on max MTU of the devices.
 	 */
-- 
cgit v1.3-3-g829e


From 2b5a09e67b72146161df176ba73ddb4d6607f3a0 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:33 +0200
Subject: net: lan966x: use FDMA library for adding DCB's in the rx path

Use the fdma_dcb_add() function to add DCB's in the rx path. This gets
rid of the open-coding of nextptr and dataptr handling and the functions
for adding DCB's.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 54 ++--------------------
 1 file changed, 5 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 99d09c97737e..b85b15ca2052 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -28,20 +28,6 @@ static int lan966x_fdma_channel_active(struct lan966x *lan966x)
 	return lan_rd(lan966x, FDMA_CH_ACTIVE);
 }
 
-static struct page *lan966x_fdma_rx_alloc_page(struct lan966x_rx *rx,
-					       struct fdma_db *db)
-{
-	struct page *page;
-
-	page = page_pool_dev_alloc_pages(rx->page_pool);
-	if (unlikely(!page))
-		return NULL;
-
-	db->dataptr = page_pool_get_dma_addr(page) + XDP_PACKET_HEADROOM;
-
-	return page;
-}
-
 static void lan966x_fdma_rx_free_pages(struct lan966x_rx *rx)
 {
 	struct fdma *fdma = &rx->fdma;
@@ -66,26 +52,6 @@ static void lan966x_fdma_rx_free_page(struct lan966x_rx *rx)
 	page_pool_recycle_direct(rx->page_pool, page);
 }
 
-static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx,
-				    struct fdma_dcb *dcb,
-				    u64 nextptr)
-{
-	struct fdma *fdma = &rx->fdma;
-	struct fdma_db *db;
-	int i;
-
-	for (i = 0; i < fdma->n_dbs; ++i) {
-		db = &dcb->db[i];
-		db->status = FDMA_DCB_STATUS_INTR;
-	}
-
-	dcb->nextptr = FDMA_DCB_INVALID_DATA;
-	dcb->info = FDMA_DCB_INFO_DATAL(PAGE_SIZE << rx->page_order);
-
-	fdma->last_dcb->nextptr = nextptr;
-	fdma->last_dcb = dcb;
-}
-
 static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
@@ -551,15 +517,11 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 {
 	struct lan966x *lan966x = container_of(napi, struct lan966x, napi);
 	struct lan966x_rx *rx = &lan966x->rx;
+	int old_dcb, dcb_reload, counter = 0;
 	struct fdma *fdma = &rx->fdma;
-	int dcb_reload, counter = 0;
-	struct fdma_dcb *old_dcb;
 	bool redirect = false;
 	struct sk_buff *skb;
-	struct fdma_db *db;
-	struct page *page;
 	u64 src_port;
-	u64 nextptr;
 
 	dcb_reload = fdma->dcb_index;
 
@@ -602,19 +564,13 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 allocate_new:
 	/* Allocate new pages and map them */
 	while (dcb_reload != fdma->dcb_index) {
-		db = &fdma->dcbs[dcb_reload].db[fdma->db_index];
-		page = lan966x_fdma_rx_alloc_page(rx, db);
-		if (unlikely(!page))
-			break;
-		rx->page[dcb_reload][fdma->db_index] = page;
-
-		old_dcb = &fdma->dcbs[dcb_reload];
+		old_dcb = dcb_reload;
 		dcb_reload++;
 		dcb_reload &= fdma->n_dcbs - 1;
 
-		nextptr = fdma->dma + ((unsigned long)old_dcb -
-				     (unsigned long)fdma->dcbs);
-		lan966x_fdma_rx_add_dcb(rx, old_dcb, nextptr);
+		fdma_dcb_add(fdma, old_dcb, FDMA_DCB_INFO_DATAL(fdma->db_size),
+			     FDMA_DCB_STATUS_INTR);
+
 		lan966x_fdma_rx_reload(rx);
 	}
 
-- 
cgit v1.3-3-g829e


From f51293b3ea89b3028745d8f0c9206df4bdc16905 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:34 +0200
Subject: net: lan966x: use library helper for freeing rx buffers

The library has the helper fdma_free_phys() for freeing physical FDMA
memory. Use it in the exit path.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index b85b15ca2052..627806a10674 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -114,18 +114,6 @@ static void lan966x_fdma_rx_advance_dcb(struct lan966x_rx *rx)
 	fdma->dcb_index &= fdma->n_dcbs - 1;
 }
 
-static void lan966x_fdma_rx_free(struct lan966x_rx *rx)
-{
-	struct lan966x *lan966x = rx->lan966x;
-	struct fdma *fdma = &rx->fdma;
-	u32 size;
-
-	/* Now it is possible to do the cleanup of dcb */
-	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-	dma_free_coherent(lan966x->dev, size, fdma->dcbs, fdma->dma);
-}
-
 static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
@@ -1019,7 +1007,7 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 
 	err = lan966x_fdma_tx_alloc(&lan966x->tx);
 	if (err) {
-		lan966x_fdma_rx_free(&lan966x->rx);
+		fdma_free_coherent(lan966x->dev, &lan966x->rx.fdma);
 		return err;
 	}
 
@@ -1040,7 +1028,7 @@ void lan966x_fdma_deinit(struct lan966x *lan966x)
 	napi_disable(&lan966x->napi);
 
 	lan966x_fdma_rx_free_pages(&lan966x->rx);
-	lan966x_fdma_rx_free(&lan966x->rx);
+	fdma_free_coherent(lan966x->dev, &lan966x->rx.fdma);
 	page_pool_destroy(lan966x->rx.page_pool);
 	lan966x_fdma_tx_free(&lan966x->tx);
 }
-- 
cgit v1.3-3-g829e


From df2ddc1458c39eacb8678333bea668a76de540de Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:35 +0200
Subject: net: lan966x: use the FDMA library for allocation of tx buffers

Use the two functions: fdma_alloc_phys() and fdma_dcb_init() for rx
buffer allocation and use the new buffers throughout.

In order to replace the old buffers with the new ones, we have to do the
following refactoring:

    - use fdma_alloc_phys() and fdma_dcb_init()

    - replace the variables: tx->dma, tx->dcbs and tx->curr_entry
      with the equivalents from the FDMA struct.

    - add lan966x_fdma_tx_dataptr_cb callback for obtaining the dataptr.

    - Initialize FDMA struct values.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 75 ++++++++++------------
 .../net/ethernet/microchip/lan966x/lan966x_main.h  | 16 -----
 2 files changed, 34 insertions(+), 57 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 627806a10674..3afc6c4c68a4 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -23,6 +23,16 @@ static int lan966x_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db,
 	return 0;
 }
 
+static int lan966x_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+				      u64 *dataptr)
+{
+	struct lan966x *lan966x = (struct lan966x *)fdma->priv;
+
+	*dataptr = lan966x->tx.dcbs_buf[dcb].dma_addr;
+
+	return 0;
+}
+
 static int lan966x_fdma_channel_active(struct lan966x *lan966x)
 {
 	return lan_rd(lan966x, FDMA_CH_ACTIVE);
@@ -182,46 +192,22 @@ static void lan966x_fdma_rx_reload(struct lan966x_rx *rx)
 		lan966x, FDMA_CH_RELOAD);
 }
 
-static void lan966x_fdma_tx_add_dcb(struct lan966x_tx *tx,
-				    struct lan966x_tx_dcb *dcb)
-{
-	dcb->nextptr = FDMA_DCB_INVALID_DATA;
-	dcb->info = 0;
-}
-
 static int lan966x_fdma_tx_alloc(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
 	struct fdma *fdma = &tx->fdma;
-	struct lan966x_tx_dcb *dcb;
-	struct lan966x_db *db;
-	int size;
-	int i, j;
+	int err;
 
 	tx->dcbs_buf = kcalloc(fdma->n_dcbs, sizeof(struct lan966x_tx_dcb_buf),
 			       GFP_KERNEL);
 	if (!tx->dcbs_buf)
 		return -ENOMEM;
 
-	/* calculate how many pages are needed to allocate the dcbs */
-	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-	tx->dcbs = dma_alloc_coherent(lan966x->dev, size, &tx->dma, GFP_KERNEL);
-	if (!tx->dcbs)
+	err = fdma_alloc_coherent(lan966x->dev, fdma);
+	if (err)
 		goto out;
 
-	/* Now for each dcb allocate the db */
-	for (i = 0; i < fdma->n_dcbs; ++i) {
-		dcb = &tx->dcbs[i];
-
-		for (j = 0; j < fdma->n_dbs; ++j) {
-			db = &dcb->db[j];
-			db->dataptr = 0;
-			db->status = 0;
-		}
-
-		lan966x_fdma_tx_add_dcb(tx, dcb);
-	}
+	fdma_dcbs_init(fdma, 0, 0);
 
 	return 0;
 
@@ -238,7 +224,7 @@ static void lan966x_fdma_tx_free(struct lan966x_tx *tx)
 
 	kfree(tx->dcbs_buf);
 
-	size = sizeof(struct lan966x_tx_dcb) * fdma->n_dcbs;
+	size = sizeof(struct fdma_dcb) * fdma->n_dcbs;
 	size = ALIGN(size, PAGE_SIZE);
 	dma_free_coherent(lan966x->dev, size, fdma->dcbs, fdma->dma);
 }
@@ -252,9 +238,9 @@ static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
 	/* When activating a channel, first is required to write the first DCB
 	 * address and then to activate it
 	 */
-	lan_wr(lower_32_bits((u64)tx->dma), lan966x,
+	lan_wr(lower_32_bits((u64)fdma->dma), lan966x,
 	       FDMA_DCB_LLP(fdma->channel_id));
-	lan_wr(upper_32_bits((u64)tx->dma), lan966x,
+	lan_wr(upper_32_bits((u64)fdma->dma), lan966x,
 	       FDMA_DCB_LLP1(fdma->channel_id));
 
 	lan_wr(FDMA_CH_CFG_CH_DCB_DB_CNT_SET(fdma->n_dbs) |
@@ -349,22 +335,23 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 	struct lan966x_tx *tx = &lan966x->tx;
 	struct lan966x_rx *rx = &lan966x->rx;
 	struct lan966x_tx_dcb_buf *dcb_buf;
+	struct fdma *fdma = &tx->fdma;
 	struct xdp_frame_bulk bq;
-	struct lan966x_db *db;
 	unsigned long flags;
 	bool clear = false;
+	struct fdma_db *db;
 	int i;
 
 	xdp_frame_bulk_init(&bq);
 
 	spin_lock_irqsave(&lan966x->tx_lock, flags);
-	for (i = 0; i < tx->fdma.n_dcbs; ++i) {
+	for (i = 0; i < fdma->n_dcbs; ++i) {
 		dcb_buf = &tx->dcbs_buf[i];
 
 		if (!dcb_buf->used)
 			continue;
 
-		db = &tx->dcbs[i].db[0];
+		db = &fdma->dcbs[i].db[0];
 		if (!(db->status & FDMA_DCB_STATUS_DONE))
 			continue;
 
@@ -617,10 +604,10 @@ static void lan966x_fdma_tx_setup_dcb(struct lan966x_tx *tx,
 				      int next_to_use, int len,
 				      dma_addr_t dma_addr)
 {
-	struct lan966x_tx_dcb *next_dcb;
-	struct lan966x_db *next_db;
+	struct fdma_dcb *next_dcb;
+	struct fdma_db *next_db;
 
-	next_dcb = &tx->dcbs[next_to_use];
+	next_dcb = &tx->fdma.dcbs[next_to_use];
 	next_dcb->nextptr = FDMA_DCB_INVALID_DATA;
 
 	next_db = &next_dcb->db[0];
@@ -635,13 +622,14 @@ static void lan966x_fdma_tx_setup_dcb(struct lan966x_tx *tx,
 static void lan966x_fdma_tx_start(struct lan966x_tx *tx, int next_to_use)
 {
 	struct lan966x *lan966x = tx->lan966x;
-	struct lan966x_tx_dcb *dcb;
+	struct fdma *fdma = &tx->fdma;
+	struct fdma_dcb *dcb;
 
 	if (likely(lan966x->tx.activated)) {
 		/* Connect current dcb to the next db */
-		dcb = &tx->dcbs[tx->last_in_use];
-		dcb->nextptr = tx->dma + (next_to_use *
-					  sizeof(struct lan966x_tx_dcb));
+		dcb = &fdma->dcbs[tx->last_in_use];
+		dcb->nextptr = fdma->dma + (next_to_use *
+					  sizeof(struct fdma_dcb));
 
 		lan966x_fdma_tx_reload(tx);
 	} else {
@@ -999,6 +987,11 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 	lan966x->tx.fdma.channel_id = FDMA_INJ_CHANNEL;
 	lan966x->tx.fdma.n_dcbs = FDMA_DCB_MAX;
 	lan966x->tx.fdma.n_dbs = FDMA_TX_DCB_MAX_DBS;
+	lan966x->tx.fdma.priv = lan966x;
+	lan966x->tx.fdma.size = fdma_get_size(&lan966x->tx.fdma);
+	lan966x->tx.fdma.db_size = PAGE_SIZE << lan966x->rx.page_order;
+	lan966x->tx.fdma.ops.nextptr_cb = &fdma_nextptr_cb;
+	lan966x->tx.fdma.ops.dataptr_cb = &lan966x_fdma_tx_dataptr_cb;
 	lan966x->tx.last_in_use = -1;
 
 	err = lan966x_fdma_rx_alloc(&lan966x->rx);
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 8edb5ea484ee..99efc596c9e6 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -191,17 +191,6 @@ enum vcap_is1_port_sel_rt {
 
 struct lan966x_port;
 
-struct lan966x_db {
-	u64 dataptr;
-	u64 status;
-};
-
-struct lan966x_tx_dcb {
-	u64 nextptr;
-	u64 info;
-	struct lan966x_db db[FDMA_TX_DCB_MAX_DBS];
-};
-
 struct lan966x_rx {
 	struct lan966x *lan966x;
 
@@ -243,13 +232,8 @@ struct lan966x_tx {
 
 	struct fdma fdma;
 
-	/* Pointer to the dcb list */
-	struct lan966x_tx_dcb *dcbs;
 	u16 last_in_use;
 
-	/* Represents the DMA address to the first entry of the dcb entries. */
-	dma_addr_t dma;
-
 	/* Array of dcbs that are given to the HW */
 	struct lan966x_tx_dcb_buf *dcbs_buf;
 
-- 
cgit v1.3-3-g829e


From 29cc3a66a81ddaa237a3fe3c14cf0fc582db25bf Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:36 +0200
Subject: net: lan966x: use FDMA library for adding DCB's in the tx path

Use the fdma_dcb_add() function to add DCB's in the tx path. This gets
rid of the open-coding of nextptr and dataptr handling and leaves it to
the library.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 62 +++++++++++-----------
 1 file changed, 30 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 3afc6c4c68a4..1beafadce87a 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -33,6 +33,16 @@ static int lan966x_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db,
 	return 0;
 }
 
+static int lan966x_fdma_xdp_tx_dataptr_cb(struct fdma *fdma, int dcb, int db,
+					  u64 *dataptr)
+{
+	struct lan966x *lan966x = (struct lan966x *)fdma->priv;
+
+	*dataptr = lan966x->tx.dcbs_buf[dcb].dma_addr + XDP_PACKET_HEADROOM;
+
+	return 0;
+}
+
 static int lan966x_fdma_channel_active(struct lan966x *lan966x)
 {
 	return lan_rd(lan966x, FDMA_CH_ACTIVE);
@@ -600,25 +610,6 @@ static int lan966x_fdma_get_next_dcb(struct lan966x_tx *tx)
 	return -1;
 }
 
-static void lan966x_fdma_tx_setup_dcb(struct lan966x_tx *tx,
-				      int next_to_use, int len,
-				      dma_addr_t dma_addr)
-{
-	struct fdma_dcb *next_dcb;
-	struct fdma_db *next_db;
-
-	next_dcb = &tx->fdma.dcbs[next_to_use];
-	next_dcb->nextptr = FDMA_DCB_INVALID_DATA;
-
-	next_db = &next_dcb->db[0];
-	next_db->dataptr = dma_addr;
-	next_db->status = FDMA_DCB_STATUS_SOF |
-			  FDMA_DCB_STATUS_EOF |
-			  FDMA_DCB_STATUS_INTR |
-			  FDMA_DCB_STATUS_BLOCKO(0) |
-			  FDMA_DCB_STATUS_BLOCKL(len);
-}
-
 static void lan966x_fdma_tx_start(struct lan966x_tx *tx, int next_to_use)
 {
 	struct lan966x *lan966x = tx->lan966x;
@@ -692,11 +683,6 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 
 		next_dcb_buf->data.xdpf = xdpf;
 		next_dcb_buf->len = xdpf->len + IFH_LEN_BYTES;
-
-		/* Setup next dcb */
-		lan966x_fdma_tx_setup_dcb(tx, next_to_use,
-					  xdpf->len + IFH_LEN_BYTES,
-					  dma_addr);
 	} else {
 		page = ptr;
 
@@ -713,11 +699,6 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 
 		next_dcb_buf->data.page = page;
 		next_dcb_buf->len = len + IFH_LEN_BYTES;
-
-		/* Setup next dcb */
-		lan966x_fdma_tx_setup_dcb(tx, next_to_use,
-					  len + IFH_LEN_BYTES,
-					  dma_addr + XDP_PACKET_HEADROOM);
 	}
 
 	/* Fill up the buffer */
@@ -728,6 +709,17 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 	next_dcb_buf->ptp = false;
 	next_dcb_buf->dev = port->dev;
 
+	__fdma_dcb_add(&tx->fdma,
+		       next_to_use,
+		       0,
+		       FDMA_DCB_STATUS_INTR |
+		       FDMA_DCB_STATUS_SOF |
+		       FDMA_DCB_STATUS_EOF |
+		       FDMA_DCB_STATUS_BLOCKO(0) |
+		       FDMA_DCB_STATUS_BLOCKL(next_dcb_buf->len),
+		       &fdma_nextptr_cb,
+		       &lan966x_fdma_xdp_tx_dataptr_cb);
+
 	/* Start the transmission */
 	lan966x_fdma_tx_start(tx, next_to_use);
 
@@ -787,9 +779,6 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev)
 		goto release;
 	}
 
-	/* Setup next dcb */
-	lan966x_fdma_tx_setup_dcb(tx, next_to_use, skb->len, dma_addr);
-
 	/* Fill up the buffer */
 	next_dcb_buf = &tx->dcbs_buf[next_to_use];
 	next_dcb_buf->use_skb = true;
@@ -801,6 +790,15 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev)
 	next_dcb_buf->ptp = false;
 	next_dcb_buf->dev = dev;
 
+	fdma_dcb_add(&tx->fdma,
+		     next_to_use,
+		     0,
+		     FDMA_DCB_STATUS_INTR |
+		     FDMA_DCB_STATUS_SOF |
+		     FDMA_DCB_STATUS_EOF |
+		     FDMA_DCB_STATUS_BLOCKO(0) |
+		     FDMA_DCB_STATUS_BLOCKL(skb->len));
+
 	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
 	    LAN966X_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP)
 		next_dcb_buf->ptp = true;
-- 
cgit v1.3-3-g829e


From 8cdd0bd02283036130396d70183c15a97f3be6b7 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:37 +0200
Subject: net: lan966x: use library helper for freeing tx buffers

The library has the helper fdma_free_phys() for freeing physical FDMA
memory. Use it in the exit path.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 1beafadce87a..6f7e3c27c1a7 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -229,14 +229,9 @@ out:
 static void lan966x_fdma_tx_free(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
-	struct fdma *fdma = &tx->fdma;
-	int size;
 
 	kfree(tx->dcbs_buf);
-
-	size = sizeof(struct fdma_dcb) * fdma->n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-	dma_free_coherent(lan966x->dev, size, fdma->dcbs, fdma->dma);
+	fdma_free_coherent(lan966x->dev, &tx->fdma);
 }
 
 static void lan966x_fdma_tx_activate(struct lan966x_tx *tx)
-- 
cgit v1.3-3-g829e


From c06fef96c7d599ac6d1cdfd42ffee8c8d59729fe Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:38 +0200
Subject: net: lan966x: ditch tx->last_in_use variable

This variable is used in the tx path to determine the last used DCB. The
library has the variable last_dcb for the exact same purpose. Ditch the
last_in_use variable throughout.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c    | 20 ++++----------------
 .../net/ethernet/microchip/lan966x/lan966x_main.h    |  2 --
 2 files changed, 4 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 6f7e3c27c1a7..b5a97c5a2e1b 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -293,7 +293,6 @@ static void lan966x_fdma_tx_disable(struct lan966x_tx *tx)
 		lan966x, FDMA_CH_DB_DISCARD);
 
 	tx->activated = false;
-	tx->last_in_use = -1;
 }
 
 static void lan966x_fdma_tx_reload(struct lan966x_tx *tx)
@@ -598,34 +597,24 @@ static int lan966x_fdma_get_next_dcb(struct lan966x_tx *tx)
 
 	for (i = 0; i < fdma->n_dcbs; ++i) {
 		dcb_buf = &tx->dcbs_buf[i];
-		if (!dcb_buf->used && i != tx->last_in_use)
+		if (!dcb_buf->used && &fdma->dcbs[i] != fdma->last_dcb)
 			return i;
 	}
 
 	return -1;
 }
 
-static void lan966x_fdma_tx_start(struct lan966x_tx *tx, int next_to_use)
+static void lan966x_fdma_tx_start(struct lan966x_tx *tx)
 {
 	struct lan966x *lan966x = tx->lan966x;
-	struct fdma *fdma = &tx->fdma;
-	struct fdma_dcb *dcb;
 
 	if (likely(lan966x->tx.activated)) {
-		/* Connect current dcb to the next db */
-		dcb = &fdma->dcbs[tx->last_in_use];
-		dcb->nextptr = fdma->dma + (next_to_use *
-					  sizeof(struct fdma_dcb));
-
 		lan966x_fdma_tx_reload(tx);
 	} else {
 		/* Because it is first time, then just activate */
 		lan966x->tx.activated = true;
 		lan966x_fdma_tx_activate(tx);
 	}
-
-	/* Move to next dcb because this last in use */
-	tx->last_in_use = next_to_use;
 }
 
 int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
@@ -716,7 +705,7 @@ int lan966x_fdma_xmit_xdpf(struct lan966x_port *port, void *ptr, u32 len)
 		       &lan966x_fdma_xdp_tx_dataptr_cb);
 
 	/* Start the transmission */
-	lan966x_fdma_tx_start(tx, next_to_use);
+	lan966x_fdma_tx_start(tx);
 
 out:
 	spin_unlock(&lan966x->tx_lock);
@@ -799,7 +788,7 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev)
 		next_dcb_buf->ptp = true;
 
 	/* Start the transmission */
-	lan966x_fdma_tx_start(tx, next_to_use);
+	lan966x_fdma_tx_start(tx);
 
 	return NETDEV_TX_OK;
 
@@ -985,7 +974,6 @@ int lan966x_fdma_init(struct lan966x *lan966x)
 	lan966x->tx.fdma.db_size = PAGE_SIZE << lan966x->rx.page_order;
 	lan966x->tx.fdma.ops.nextptr_cb = &fdma_nextptr_cb;
 	lan966x->tx.fdma.ops.dataptr_cb = &lan966x_fdma_tx_dataptr_cb;
-	lan966x->tx.last_in_use = -1;
 
 	err = lan966x_fdma_rx_alloc(&lan966x->rx);
 	if (err)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 99efc596c9e6..25cb2f61986f 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -232,8 +232,6 @@ struct lan966x_tx {
 
 	struct fdma fdma;
 
-	u16 last_in_use;
-
 	/* Array of dcbs that are given to the HW */
 	struct lan966x_tx_dcb_buf *dcbs_buf;
 
-- 
cgit v1.3-3-g829e


From 9fbc5719f6aa2afbb5445e2b59fe577b4cb9d87c Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:39 +0200
Subject: net: lan966x: use a few FDMA helpers throughout

The library provides helpers for a number of DCB and DB operations. Use
these throughout the code and remove the old ones.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/microchip/lan966x/lan966x_fdma.c  | 42 ++++++----------------
 1 file changed, 11 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index b5a97c5a2e1b..4c8f83e4c5de 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -126,14 +126,6 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx)
 	return 0;
 }
 
-static void lan966x_fdma_rx_advance_dcb(struct lan966x_rx *rx)
-{
-	struct fdma *fdma = &rx->fdma;
-
-	fdma->dcb_index++;
-	fdma->dcb_index &= fdma->n_dcbs - 1;
-}
-
 static void lan966x_fdma_rx_start(struct lan966x_rx *rx)
 {
 	struct lan966x *lan966x = rx->lan966x;
@@ -355,8 +347,8 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 		if (!dcb_buf->used)
 			continue;
 
-		db = &fdma->dcbs[i].db[0];
-		if (!(db->status & FDMA_DCB_STATUS_DONE))
+		db = fdma_db_get(fdma, i, 0);
+		if (!fdma_db_is_done(db))
 			continue;
 
 		dcb_buf->dev->stats.tx_packets++;
@@ -396,19 +388,6 @@ static void lan966x_fdma_tx_clear_buf(struct lan966x *lan966x, int weight)
 	spin_unlock_irqrestore(&lan966x->tx_lock, flags);
 }
 
-static bool lan966x_fdma_rx_more_frames(struct lan966x_rx *rx)
-{
-	struct fdma *fdma = &rx->fdma;
-	struct fdma_db *db;
-
-	/* Check if there is any data */
-	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
-	if (unlikely(!(db->status & FDMA_DCB_STATUS_DONE)))
-		return false;
-
-	return true;
-}
-
 static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port)
 {
 	struct lan966x *lan966x = rx->lan966x;
@@ -417,7 +396,7 @@ static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port)
 	struct fdma_db *db;
 	struct page *page;
 
-	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
+	db = fdma_db_next_get(fdma);
 	page = rx->page[fdma->dcb_index][fdma->db_index];
 	if (unlikely(!page))
 		return FDMA_ERROR;
@@ -450,7 +429,7 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx,
 	u64 timestamp;
 
 	/* Get the received frame and unmap it */
-	db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index];
+	db = fdma_db_next_get(fdma);
 	page = rx->page[fdma->dcb_index][fdma->db_index];
 
 	skb = build_skb(page_address(page), fdma->db_size);
@@ -508,7 +487,7 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 
 	/* Get all received skb */
 	while (counter < weight) {
-		if (!lan966x_fdma_rx_more_frames(rx))
+		if (!fdma_has_frames(fdma))
 			break;
 
 		counter++;
@@ -518,22 +497,22 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight)
 			break;
 		case FDMA_ERROR:
 			lan966x_fdma_rx_free_page(rx);
-			lan966x_fdma_rx_advance_dcb(rx);
+			fdma_dcb_advance(fdma);
 			goto allocate_new;
 		case FDMA_REDIRECT:
 			redirect = true;
 			fallthrough;
 		case FDMA_TX:
-			lan966x_fdma_rx_advance_dcb(rx);
+			fdma_dcb_advance(fdma);
 			continue;
 		case FDMA_DROP:
 			lan966x_fdma_rx_free_page(rx);
-			lan966x_fdma_rx_advance_dcb(rx);
+			fdma_dcb_advance(fdma);
 			continue;
 		}
 
 		skb = lan966x_fdma_rx_get_frame(rx, src_port);
-		lan966x_fdma_rx_advance_dcb(rx);
+		fdma_dcb_advance(fdma);
 		if (!skb)
 			goto allocate_new;
 
@@ -597,7 +576,8 @@ static int lan966x_fdma_get_next_dcb(struct lan966x_tx *tx)
 
 	for (i = 0; i < fdma->n_dcbs; ++i) {
 		dcb_buf = &tx->dcbs_buf[i];
-		if (!dcb_buf->used && &fdma->dcbs[i] != fdma->last_dcb)
+		if (!dcb_buf->used &&
+		    !fdma_is_last(&tx->fdma, &tx->fdma.dcbs[i]))
 			return i;
 	}
 
-- 
cgit v1.3-3-g829e


From 89ba464fcf548d64bc7215dfe769f791330ae8b6 Mon Sep 17 00:00:00 2001
From: Daniel Machon <daniel.machon@microchip.com>
Date: Thu, 5 Sep 2024 10:06:40 +0200
Subject: net: lan966x: refactor buffer reload function

Now that we store everything in the fdma structs, refactor
lan966x_fdma_reload() to store and restore the entire struct.

Signed-off-by: Daniel Machon <daniel.machon@microchip.com>
Reviewed-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 4c8f83e4c5de..502670718104 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -810,14 +810,11 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x)
 static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 {
 	struct page_pool *page_pool;
-	dma_addr_t rx_dma;
-	void *rx_dcbs;
-	u32 size;
+	struct fdma fdma_rx_old;
 	int err;
 
 	/* Store these for later to free them */
-	rx_dma = lan966x->rx.fdma.dma;
-	rx_dcbs = lan966x->rx.fdma.dcbs;
+	memcpy(&fdma_rx_old, &lan966x->rx.fdma, sizeof(struct fdma));
 	page_pool = lan966x->rx.page_pool;
 
 	napi_synchronize(&lan966x->napi);
@@ -833,9 +830,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 		goto restore;
 	lan966x_fdma_rx_start(&lan966x->rx);
 
-	size = sizeof(struct fdma_dcb) * lan966x->rx.fdma.n_dcbs;
-	size = ALIGN(size, PAGE_SIZE);
-	dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma);
+	fdma_free_coherent(lan966x->dev, &fdma_rx_old);
 
 	page_pool_destroy(page_pool);
 
@@ -845,8 +840,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
 	return err;
 restore:
 	lan966x->rx.page_pool = page_pool;
-	lan966x->rx.fdma.dma = rx_dma;
-	lan966x->rx.fdma.dcbs = rx_dcbs;
+	memcpy(&lan966x->rx.fdma, &fdma_rx_old, sizeof(struct fdma));
 	lan966x_fdma_rx_start(&lan966x->rx);
 
 	return err;
-- 
cgit v1.3-3-g829e


From 0246388b9b7963babbdc0960d1f5bef676611346 Mon Sep 17 00:00:00 2001
From: Lee Trager <lee@trager.us>
Date: Thu, 5 Sep 2024 16:37:51 -0700
Subject: eth: fbnic: Add devlink firmware version info

This adds support to show firmware version information for both stored and
running firmware versions. The version and commit is displayed separately
to aid monitoring tools which only care about the version.

Example output:
  # devlink dev info
  pci/0000:01:00.0:
    driver fbnic
    serial_number 88-25-08-ff-ff-01-50-92
    versions:
        running:
          fw 24.07.15-017
          fw.commit h999784ae9df0
          fw.bootloader 24.07.10-000
          fw.bootloader.commit hfef3ac835ce7
        stored:
          fw 24.07.24-002
          fw.commit hc9d14a68b3f2
          fw.bootloader 24.07.22-000
          fw.bootloader.commit h922f8493eb96
          fw.undi 01.00.03-000

Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240905233820.1713043-1-lee@trager.us
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../networking/device_drivers/ethernet/index.rst   |  1 +
 .../device_drivers/ethernet/meta/fbnic.rst         | 29 +++++++++
 MAINTAINERS                                        |  1 +
 drivers/net/ethernet/meta/fbnic/fbnic_devlink.c    | 75 ++++++++++++++++++++++
 4 files changed, 106 insertions(+)
 create mode 100644 Documentation/networking/device_drivers/ethernet/meta/fbnic.rst

diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst
index 6932d8c043c2..6fc1961492b7 100644
--- a/Documentation/networking/device_drivers/ethernet/index.rst
+++ b/Documentation/networking/device_drivers/ethernet/index.rst
@@ -44,6 +44,7 @@ Contents:
    marvell/octeon_ep
    marvell/octeon_ep_vf
    mellanox/mlx5/index
+   meta/fbnic
    microsoft/netvsc
    neterion/s2io
    netronome/nfp
diff --git a/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst b/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst
new file mode 100644
index 000000000000..32ff114f5c26
--- /dev/null
+++ b/Documentation/networking/device_drivers/ethernet/meta/fbnic.rst
@@ -0,0 +1,29 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+=====================================
+Meta Platforms Host Network Interface
+=====================================
+
+Firmware Versions
+-----------------
+
+fbnic has three components stored on the flash which are provided in one PLDM
+image:
+
+1. fw - The control firmware used to view and modify firmware settings, request
+   firmware actions, and retrieve firmware counters outside of the data path.
+   This is the firmware which fbnic_fw.c interacts with.
+2. bootloader - The firmware which validate firmware security and control basic
+   operations including loading and updating the firmware. This is also known
+   as the cmrt firmware.
+3. undi - This is the UEFI driver which is based on the Linux driver.
+
+fbnic stores two copies of these three components on flash. This allows fbnic
+to fall back to an older version of firmware automatically in case firmware
+fails to boot. Version information for both is provided as running and stored.
+The undi is only provided in stored as it is not actively running once the Linux
+driver takes over.
+
+devlink dev info provides version information for all three components. In
+addition to the version the hg commit hash of the build is included as a
+separate entry.
diff --git a/MAINTAINERS b/MAINTAINERS
index ca1469d52076..4053168fdc12 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14833,6 +14833,7 @@ M:	Alexander Duyck <alexanderduyck@fb.com>
 M:	Jakub Kicinski <kuba@kernel.org>
 R:	kernel-team@meta.com
 S:	Supported
+F:	Documentation/networking/device_drivers/ethernet/meta/
 F:	drivers/net/ethernet/meta/
 
 METHODE UDPU SUPPORT
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
index e87049dfd223..ef05ae8f5039 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c
@@ -10,6 +10,56 @@
 
 #define FBNIC_SN_STR_LEN	24
 
+static int fbnic_version_running_put(struct devlink_info_req *req,
+				     struct fbnic_fw_ver *fw_ver,
+				     char *ver_name)
+{
+	char running_ver[FBNIC_FW_VER_MAX_SIZE];
+	int err;
+
+	fbnic_mk_fw_ver_str(fw_ver->version, running_ver);
+	err = devlink_info_version_running_put(req, ver_name, running_ver);
+	if (err)
+		return err;
+
+	if (strlen(fw_ver->commit) > 0) {
+		char commit_name[FBNIC_SN_STR_LEN];
+
+		snprintf(commit_name, FBNIC_SN_STR_LEN, "%s.commit", ver_name);
+		err = devlink_info_version_running_put(req, commit_name,
+						       fw_ver->commit);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int fbnic_version_stored_put(struct devlink_info_req *req,
+				    struct fbnic_fw_ver *fw_ver,
+				    char *ver_name)
+{
+	char stored_ver[FBNIC_FW_VER_MAX_SIZE];
+	int err;
+
+	fbnic_mk_fw_ver_str(fw_ver->version, stored_ver);
+	err = devlink_info_version_stored_put(req, ver_name, stored_ver);
+	if (err)
+		return err;
+
+	if (strlen(fw_ver->commit) > 0) {
+		char commit_name[FBNIC_SN_STR_LEN];
+
+		snprintf(commit_name, FBNIC_SN_STR_LEN, "%s.commit", ver_name);
+		err = devlink_info_version_stored_put(req, commit_name,
+						      fw_ver->commit);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int fbnic_devlink_info_get(struct devlink *devlink,
 				  struct devlink_info_req *req,
 				  struct netlink_ext_ack *extack)
@@ -17,6 +67,31 @@ static int fbnic_devlink_info_get(struct devlink *devlink,
 	struct fbnic_dev *fbd = devlink_priv(devlink);
 	int err;
 
+	err = fbnic_version_running_put(req, &fbd->fw_cap.running.mgmt,
+					DEVLINK_INFO_VERSION_GENERIC_FW);
+	if (err)
+		return err;
+
+	err = fbnic_version_running_put(req, &fbd->fw_cap.running.bootloader,
+					DEVLINK_INFO_VERSION_GENERIC_FW_BOOTLOADER);
+	if (err)
+		return err;
+
+	err = fbnic_version_stored_put(req, &fbd->fw_cap.stored.mgmt,
+				       DEVLINK_INFO_VERSION_GENERIC_FW);
+	if (err)
+		return err;
+
+	err = fbnic_version_stored_put(req, &fbd->fw_cap.stored.bootloader,
+				       DEVLINK_INFO_VERSION_GENERIC_FW_BOOTLOADER);
+	if (err)
+		return err;
+
+	err = fbnic_version_stored_put(req, &fbd->fw_cap.stored.undi,
+				       DEVLINK_INFO_VERSION_GENERIC_FW_UNDI);
+	if (err)
+		return err;
+
 	if (fbd->dsn) {
 		unsigned char serial[FBNIC_SN_STR_LEN];
 		u8 dsn[8];
-- 
cgit v1.3-3-g829e


From f8406a2fd279d05eb4a76c9b77cb740b6f350549 Mon Sep 17 00:00:00 2001
From: "D. Wythe" <alibuda@linux.alibaba.com>
Date: Fri, 6 Sep 2024 10:35:35 +0800
Subject: net/smc: add sysctl for smc_limit_hs

In commit 48b6190a0042 ("net/smc: Limit SMC visits when handshake workqueue congested"),
we introduce a mechanism to put constraint on SMC connections visit
according to the pressure of SMC handshake process.

At that time, we believed that controlling the feature through netlink
was sufficient. However, most people have realized now that netlink is
not convenient in container scenarios, and sysctl is a more suitable
approach.

In addition, since commit 462791bbfa35 ("net/smc: add sysctl interface for SMC")
had introcuded smc_sysctl_net_init(), it is reasonable for us to
initialize limit_smc_hs in it instead of initializing it in
smc_pnet_net_int().

Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
Reviewed-by: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Jan Karcher <jaka@linux.ibm.com>
Link: https://patch.msgid.link/1725590135-5631-1-git-send-email-alibuda@linux.alibaba.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/smc/smc_pnet.c   |  3 ---
 net/smc/smc_sysctl.c | 11 +++++++++++
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 2adb92b8c469..1dd362326c0a 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -887,9 +887,6 @@ int smc_pnet_net_init(struct net *net)
 
 	smc_pnet_create_pnetids_list(net);
 
-	/* disable handshake limitation by default */
-	net->smc.limit_smc_hs = 0;
-
 	return 0;
 }
 
diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c
index 13f2bc092db1..2fab6456f765 100644
--- a/net/smc/smc_sysctl.c
+++ b/net/smc/smc_sysctl.c
@@ -90,6 +90,15 @@ static struct ctl_table smc_table[] = {
 		.extra1		= &conns_per_lgr_min,
 		.extra2		= &conns_per_lgr_max,
 	},
+	{
+		.procname	= "limit_smc_hs",
+		.data		= &init_net.smc.limit_smc_hs,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
 };
 
 int __net_init smc_sysctl_net_init(struct net *net)
@@ -121,6 +130,8 @@ int __net_init smc_sysctl_net_init(struct net *net)
 	WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init);
 	net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER;
 	net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER;
+	/* disable handshake limitation by default */
+	net->smc.limit_smc_hs = 0;
 
 	return 0;
 
-- 
cgit v1.3-3-g829e


From 525034e2e2ee60d31519af0919e374b0032a70de Mon Sep 17 00:00:00 2001
From: Alexander Dahl <ada@thorsis.com>
Date: Fri, 6 Sep 2024 08:22:56 +0200
Subject: net: mdiobus: Debug print fwnode handle instead of raw pointer

Was slightly misleading before, because printed is pointer to fwnode,
not to phy device, as placement in message suggested.  Include header
for dev_dbg() declaration while at it.

Output before:

    [  +0.001247] mdio_bus f802c000.ethernet-ffffffff: registered phy 2612f00a fwnode at address 3

Output after:

    [  +0.001229] mdio_bus f802c000.ethernet-ffffffff: registered phy fwnode /ahb/apb/ethernet@f802c000/ethernet-phy@3 at address 3

Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Alexander Dahl <ada@thorsis.com>
Link: https://patch.msgid.link/20240906062256.11289-1-ada@thorsis.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mdio/fwnode_mdio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c
index fd02f5cbc853..b156493d7084 100644
--- a/drivers/net/mdio/fwnode_mdio.c
+++ b/drivers/net/mdio/fwnode_mdio.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/dev_printk.h>
 #include <linux/fwnode_mdio.h>
 #include <linux/of.h>
 #include <linux/phy.h>
@@ -104,7 +105,7 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio,
 		return rc;
 	}
 
-	dev_dbg(&mdio->dev, "registered phy %p fwnode at address %i\n",
+	dev_dbg(&mdio->dev, "registered phy fwnode %pfw at address %i\n",
 		child, addr);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 29aeb4e8918e6aeeaf0bb7a03b000a73596d54a3 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Fri, 26 Jul 2024 16:13:24 +0530
Subject: Bluetooth: Add a helper function to extract iso header

Add a helper function hci_iso_hdr() to extract iso header from skb.

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index d1d073089f38..bab1e3d7452a 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -2901,6 +2901,11 @@ static inline struct hci_sco_hdr *hci_sco_hdr(const struct sk_buff *skb)
 	return (struct hci_sco_hdr *) skb->data;
 }
 
+static inline struct hci_iso_hdr *hci_iso_hdr(const struct sk_buff *skb)
+{
+	return (struct hci_iso_hdr *)skb->data;
+}
+
 /* Command opcode pack/unpack */
 #define hci_opcode_pack(ogf, ocf)	((__u16) ((ocf & 0x03ff)|(ogf << 10)))
 #define hci_opcode_ogf(op)		(op >> 10)
-- 
cgit v1.3-3-g829e


From 861da2c11c64abe706a8d39645bbcd3141c2efb5 Mon Sep 17 00:00:00 2001
From: Kiran <kiran.k@intel.com>
Date: Fri, 26 Jul 2024 16:13:26 +0530
Subject: Bluetooth: btintel_pcie: Add support for ISO data

Add support for handling ISO RX and TX packets.

Signed-off-by: Kiran <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 1c7631f22c52..d255bdf777b4 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -46,6 +46,7 @@ MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
 #define BTINTEL_PCIE_HCI_ACL_PKT	0x00000002
 #define BTINTEL_PCIE_HCI_SCO_PKT	0x00000003
 #define BTINTEL_PCIE_HCI_EVT_PKT	0x00000004
+#define BTINTEL_PCIE_HCI_ISO_PKT	0x00000005
 
 static inline void ipc_print_ia_ring(struct hci_dev *hdev, struct ia *ia,
 				     u16 queue_num)
@@ -423,6 +424,18 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 			goto exit_error;
 		}
 		break;
+
+	case BTINTEL_PCIE_HCI_ISO_PKT:
+		if (skb->len >= HCI_ISO_HDR_SIZE) {
+			plen = HCI_ISO_HDR_SIZE + __le16_to_cpu(hci_iso_hdr(skb)->dlen);
+			pkt_type = HCI_ISODATA_PKT;
+		} else {
+			bt_dev_err(hdev, "ISO packet is too short");
+			ret = -EILSEQ;
+			goto exit_error;
+		}
+		break;
+
 	default:
 		bt_dev_err(hdev, "Invalid packet type received: 0x%4.4x",
 			   pcie_pkt_type);
@@ -1082,6 +1095,9 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev,
 		type = BTINTEL_PCIE_HCI_SCO_PKT;
 		hdev->stat.sco_tx++;
 		break;
+	case HCI_ISODATA_PKT:
+		type = BTINTEL_PCIE_HCI_ISO_PKT;
+		break;
 	default:
 		bt_dev_err(hdev, "Unknown HCI packet type");
 		return -EILSEQ;
-- 
cgit v1.3-3-g829e


From f9685f315fd6a84d86c8a53eb5d8e17652858d53 Mon Sep 17 00:00:00 2001
From: Alexander Hall <bearodark@gmail.com>
Date: Tue, 30 Jul 2024 15:08:25 -0700
Subject: Bluetooth: btusb: Add MediaTek MT7925-B22M support ID 0x13d3:0x3604

This patch fixes bluetooth support on the MediaTek MT7925 WiFi 7 +
BT 5.3 M.2 chipset that I purchased from aliexpress (and which
arrived today). The PCB states that it is an MT7925B22M.

Device from /sys/kernel/debug/usb/devices:

T:  Bus=03 Lev=02 Prnt=03 Port=02 Cnt=01 Dev#=  4 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=13d3 ProdID=3604 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:  If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=(none)
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

High fidelity images I took of the chip itself for future reference:
https://archive.org/details/MediaTek-MT7925B22M/

Webpage the chip was purchased from, note it is different from the
images taken:
https://web.archive.org/web/20240620021119/https://www.aliexpress.
us/item/3256806821207897.html

Signed-off-by: Alexander Hall <bearodark@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 51d9d4532dda..d3514def9828 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -696,6 +696,9 @@ static const struct usb_device_id quirks_table[] = {
 	{ USB_DEVICE(0x13d3, 0x3603), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH |
 						     BTUSB_VALID_LE_STATES },
+	{ USB_DEVICE(0x13d3, 0x3604), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH |
+						     BTUSB_VALID_LE_STATES },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
-- 
cgit v1.3-3-g829e


From e5e465a1ae62d146f9652756289aae9b6453dc90 Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Fri, 9 Aug 2024 13:42:24 +0800
Subject: dt-bindings: net: bluetooth: Add support for Amlogic Bluetooth

Add binding document for Amlogic Bluetooth chipsets attached over UART.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../bindings/net/bluetooth/amlogic,w155s2-bt.yaml  | 63 ++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/bluetooth/amlogic,w155s2-bt.yaml

diff --git a/Documentation/devicetree/bindings/net/bluetooth/amlogic,w155s2-bt.yaml b/Documentation/devicetree/bindings/net/bluetooth/amlogic,w155s2-bt.yaml
new file mode 100644
index 000000000000..6fd7557039d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/bluetooth/amlogic,w155s2-bt.yaml
@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright (C) 2024 Amlogic, Inc. All rights reserved
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/bluetooth/amlogic,w155s2-bt.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Amlogic Bluetooth chips
+
+description:
+  The W155S2 is an Amlogic Bluetooth and Wi-Fi combo chip. It works on
+  the standard H4 protocol via a 4-wire UART interface, with baud rates
+  up to 4 Mbps.
+
+maintainers:
+  - Yang Li <yang.li@amlogic.com>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - amlogic,w265s1-bt
+              - amlogic,w265p1-bt
+          - const: amlogic,w155s2-bt
+      - enum:
+          - amlogic,w155s2-bt
+          - amlogic,w265s2-bt
+
+  clocks:
+    maxItems: 1
+    description: clock provided to the controller (32.768KHz)
+
+  enable-gpios:
+    maxItems: 1
+
+  vddio-supply:
+    description: VDD_IO supply regulator handle
+
+  firmware-name:
+    maxItems: 1
+    description: specify the path of firmware bin to load
+
+required:
+  - compatible
+  - clocks
+  - enable-gpios
+  - vddio-supply
+  - firmware-name
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    bluetooth {
+        compatible = "amlogic,w155s2-bt";
+        clocks = <&extclk>;
+        enable-gpios = <&gpio 17 GPIO_ACTIVE_HIGH>;
+        vddio-supply = <&wcn_3v3>;
+        firmware-name = "amlogic/aml_w155s2_bt_uart.bin";
+    };
+
-- 
cgit v1.3-3-g829e


From 37bac77e4649e8158698a60addc22ec4faf5649a Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Fri, 9 Aug 2024 13:42:25 +0800
Subject: Bluetooth: hci_uart: Add support for Amlogic HCI UART

Add a new HCI protocol HCI_UART_AML for the Amlogic Bluetooth
controller. It works on the standard H4 protocol via a 4-wire UART
interface, with baud rates up to 4 Mbps.

The controller supports two types of commands: the TCI commands and the
vendor command. The former is for initial setup including setting baud
rates, downloading fw, starting chip and etc, while the latter is for
dumping firmware versions and setting public address after firmware
updates and normal startup.

It was verified on board of T602 (S905X4 + W265S2).

dmesg:
..
[    5.313450] Bluetooth: HCI UART protocol AML registered
[    6.506052] Bluetooth: hci0: fw_version: date = 42.28, number = 0xb2fd
...

Co-developed-by: Ye He <ye.he@amlogic.com>
Signed-off-by: Ye He <ye.he@amlogic.com>
Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/Kconfig     |  12 +
 drivers/bluetooth/Makefile    |   1 +
 drivers/bluetooth/hci_aml.c   | 755 ++++++++++++++++++++++++++++++++++++++++++
 drivers/bluetooth/hci_ldisc.c |   8 +-
 drivers/bluetooth/hci_uart.h  |   8 +-
 5 files changed, 781 insertions(+), 3 deletions(-)
 create mode 100644 drivers/bluetooth/hci_aml.c

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 769fa288179d..18767b54df35 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -274,6 +274,18 @@ config BT_HCIUART_MRVL
 
 	  Say Y here to compile support for HCI MRVL protocol.
 
+config BT_HCIUART_AML
+	bool "Amlogic protocol support"
+	depends on BT_HCIUART
+	depends on BT_HCIUART_SERDEV
+	select BT_HCIUART_H4
+	select FW_LOADER
+	help
+	  The Amlogic protocol support enables Bluetooth HCI over serial
+	  port interface for Amlogic Bluetooth controllers.
+
+	  Say Y here to compile support for HCI AML protocol.
+
 config BT_HCIBCM203X
 	tristate "HCI BCM203x USB driver"
 	depends on USB
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index 0730d6684d1a..81856512ddd0 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -51,4 +51,5 @@ hci_uart-$(CONFIG_BT_HCIUART_BCM)	+= hci_bcm.o
 hci_uart-$(CONFIG_BT_HCIUART_QCA)	+= hci_qca.o
 hci_uart-$(CONFIG_BT_HCIUART_AG6XX)	+= hci_ag6xx.o
 hci_uart-$(CONFIG_BT_HCIUART_MRVL)	+= hci_mrvl.o
+hci_uart-$(CONFIG_BT_HCIUART_AML)	+= hci_aml.o
 hci_uart-objs				:= $(hci_uart-y)
diff --git a/drivers/bluetooth/hci_aml.c b/drivers/bluetooth/hci_aml.c
new file mode 100644
index 000000000000..dc9541e76d81
--- /dev/null
+++ b/drivers/bluetooth/hci_aml.c
@@ -0,0 +1,755 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR MIT)
+/*
+ * Copyright (C) 2024 Amlogic, Inc. All rights reserved
+ */
+
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/property.h>
+#include <linux/of.h>
+#include <linux/serdev.h>
+#include <linux/clk.h>
+#include <linux/firmware.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci.h>
+
+#include "hci_uart.h"
+
+#define AML_EVT_HEAD_SIZE		4
+#define AML_BDADDR_DEFAULT (&(bdaddr_t) {{ 0x00, 0xff, 0x00, 0x22, 0x2d, 0xae }})
+
+#define AML_FIRMWARE_OPERATION_SIZE		(248)
+#define AML_FIRMWARE_MAX_SIZE			(512 * 1024)
+
+/* TCI command */
+#define AML_TCI_CMD_READ			0xFEF0
+#define AML_TCI_CMD_WRITE			0xFEF1
+#define AML_TCI_CMD_UPDATE_BAUDRATE		0xFEF2
+#define AML_TCI_CMD_HARDWARE_RESET		0xFEF2
+#define AML_TCI_CMD_DOWNLOAD_BT_FW		0xFEF3
+
+/* Vendor command */
+#define AML_BT_HCI_VENDOR_CMD			0xFC1A
+
+/* TCI operation parameter in controller chip */
+#define AML_OP_UART_MODE			0x00A30128
+#define AML_OP_EVT_ENABLE			0x00A70014
+#define AML_OP_MEM_HARD_TRANS_EN		0x00A7000C
+#define AML_OP_RF_CFG				0x00F03040
+#define AML_OP_RAM_POWER_CTR			0x00F03050
+#define AML_OP_HARDWARE_RST			0x00F03058
+#define AML_OP_ICCM_RAM_BASE			0x00000000
+#define AML_OP_DCCM_RAM_BASE			0x00D00000
+
+/* UART configuration */
+#define AML_UART_XMIT_EN			BIT(12)
+#define AML_UART_RECV_EN			BIT(13)
+#define AML_UART_TIMEOUT_INT_EN			BIT(14)
+#define AML_UART_CLK_SOURCE			40000000
+
+/* Controller event */
+#define AML_EVT_EN				BIT(24)
+
+/* RAM power control */
+#define AML_RAM_POWER_ON			(0)
+#define AML_RAM_POWER_OFF			(1)
+
+/* RF configuration */
+#define AML_RF_ANT_SINGLE			BIT(28)
+#define AML_RF_ANT_DOUBLE			BIT(29)
+
+/* Memory transaction */
+#define AML_MM_CTR_HARD_TRAS_EN			BIT(27)
+
+/* Controller reset */
+#define AML_CTR_CPU_RESET			BIT(8)
+#define AML_CTR_MAC_RESET			BIT(9)
+#define AML_CTR_PHY_RESET			BIT(10)
+
+enum {
+	FW_ICCM,
+	FW_DCCM
+};
+
+struct aml_fw_len {
+	u32 iccm_len;
+	u32 dccm_len;
+};
+
+struct aml_tci_rsp {
+	u8 num_cmd_packet;
+	u16 opcode;
+	u8 status;
+} __packed;
+
+struct aml_device_data {
+	int iccm_offset;
+	int dccm_offset;
+	bool is_coex;
+};
+
+struct aml_serdev {
+	struct hci_uart serdev_hu;
+	struct device *dev;
+	struct gpio_desc *bt_en_gpio;
+	struct regulator *bt_supply;
+	struct clk *lpo_clk;
+	const struct aml_device_data *aml_dev_data;
+	const char *firmware_name;
+};
+
+struct aml_data {
+	struct sk_buff *rx_skb;
+	struct sk_buff_head txq;
+};
+
+static const struct h4_recv_pkt aml_recv_pkts[] = {
+	{ H4_RECV_ACL, .recv = hci_recv_frame },
+	{ H4_RECV_SCO, .recv = hci_recv_frame },
+	{ H4_RECV_EVENT, .recv = hci_recv_frame },
+	{ H4_RECV_ISO, .recv = hci_recv_frame },
+};
+
+/* The TCI command is a private command, which is for setting baud rate,
+ * downloading firmware, initiating RAM.
+ *
+ * op_code |      op_len           | op_addr | parameter   |
+ * --------|-----------------------|---------|-------------|
+ *   2B    | 1B len(addr+param)    |    4B   |  len(param) |
+ */
+static int aml_send_tci_cmd(struct hci_dev *hdev, u16 op_code, u32 op_addr,
+			    u32 *param, u32 param_len)
+{
+	struct aml_tci_rsp *rsp = NULL;
+	struct sk_buff *skb = NULL;
+	size_t buf_len = 0;
+	u8 *buf = NULL;
+	int err = 0;
+
+	buf_len = sizeof(op_addr) + param_len;
+	buf = kmalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, &op_addr, sizeof(op_addr));
+	if (param && param_len > 0)
+		memcpy(buf + sizeof(op_addr), param, param_len);
+
+	skb = __hci_cmd_sync_ev(hdev, op_code, buf_len, buf,
+				HCI_EV_CMD_COMPLETE, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		bt_dev_err(hdev, "Failed to send TCI cmd (error: %d)", err);
+		goto exit;
+	}
+
+	rsp = skb_pull_data(skb, sizeof(struct aml_tci_rsp));
+	if (!rsp)
+		goto skb_free;
+
+	if (rsp->opcode != op_code || rsp->status != 0x00) {
+		bt_dev_err(hdev, "send TCI cmd (0x%04X), response (0x%04X):(%d)",
+		       op_code, rsp->opcode, rsp->status);
+		err = -EINVAL;
+		goto skb_free;
+	}
+
+skb_free:
+	kfree_skb(skb);
+
+exit:
+	kfree(buf);
+	return err;
+}
+
+static int aml_update_chip_baudrate(struct hci_dev *hdev, u32 baud)
+{
+	u32 value;
+
+	value = ((AML_UART_CLK_SOURCE / baud) - 1) & 0x0FFF;
+	value |= AML_UART_XMIT_EN | AML_UART_RECV_EN | AML_UART_TIMEOUT_INT_EN;
+
+	return aml_send_tci_cmd(hdev, AML_TCI_CMD_UPDATE_BAUDRATE,
+				  AML_OP_UART_MODE, &value, sizeof(value));
+}
+
+static int aml_start_chip(struct hci_dev *hdev)
+{
+	u32 value = 0;
+	int ret;
+
+	value = AML_MM_CTR_HARD_TRAS_EN;
+	ret = aml_send_tci_cmd(hdev, AML_TCI_CMD_WRITE,
+			       AML_OP_MEM_HARD_TRANS_EN,
+			       &value, sizeof(value));
+	if (ret)
+		return ret;
+
+	/* controller hardware reset */
+	value = AML_CTR_CPU_RESET | AML_CTR_MAC_RESET | AML_CTR_PHY_RESET;
+	ret = aml_send_tci_cmd(hdev, AML_TCI_CMD_HARDWARE_RESET,
+			       AML_OP_HARDWARE_RST,
+			       &value, sizeof(value));
+	return ret;
+}
+
+static int aml_send_firmware_segment(struct hci_dev *hdev,
+				     u8 fw_type,
+				     u8 *seg,
+				     u32 seg_size,
+				     u32 offset)
+{
+	u32 op_addr = 0;
+
+	if (fw_type == FW_ICCM)
+		op_addr = AML_OP_ICCM_RAM_BASE  + offset;
+	else if (fw_type == FW_DCCM)
+		op_addr = AML_OP_DCCM_RAM_BASE + offset;
+
+	return aml_send_tci_cmd(hdev, AML_TCI_CMD_DOWNLOAD_BT_FW,
+			     op_addr, (u32 *)seg, seg_size);
+}
+
+static int aml_send_firmware(struct hci_dev *hdev, u8 fw_type,
+			     u8 *fw, u32 fw_size, u32 offset)
+{
+	u32 seg_size = 0;
+	u32 seg_off = 0;
+
+	if (fw_size > AML_FIRMWARE_MAX_SIZE) {
+		bt_dev_err(hdev,
+			"Firmware size %d kB is larger than the maximum of 512 kB. Aborting.",
+			fw_size);
+		return -EINVAL;
+	}
+	while (fw_size > 0) {
+		seg_size = (fw_size > AML_FIRMWARE_OPERATION_SIZE) ?
+			   AML_FIRMWARE_OPERATION_SIZE : fw_size;
+		if (aml_send_firmware_segment(hdev, fw_type, (fw + seg_off),
+					      seg_size, offset)) {
+			bt_dev_err(hdev, "Failed send firmware, type: %d, offset: 0x%x",
+			       fw_type, offset);
+			return -EINVAL;
+		}
+		seg_off += seg_size;
+		fw_size -= seg_size;
+		offset += seg_size;
+	}
+	return 0;
+}
+
+static int aml_download_firmware(struct hci_dev *hdev, const char *fw_name)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct aml_serdev *amldev = serdev_device_get_drvdata(hu->serdev);
+	const struct firmware *firmware = NULL;
+	struct aml_fw_len *fw_len = NULL;
+	u8 *iccm_start = NULL, *dccm_start = NULL;
+	u32 iccm_len, dccm_len;
+	u32 value = 0;
+	int ret = 0;
+
+	/* Enable firmware download event */
+	value = AML_EVT_EN;
+	ret = aml_send_tci_cmd(hdev, AML_TCI_CMD_WRITE,
+			       AML_OP_EVT_ENABLE,
+			       &value, sizeof(value));
+	if (ret)
+		goto exit;
+
+	/* RAM power on */
+	value = AML_RAM_POWER_ON;
+	ret = aml_send_tci_cmd(hdev, AML_TCI_CMD_WRITE,
+			       AML_OP_RAM_POWER_CTR,
+			       &value, sizeof(value));
+	if (ret)
+		goto exit;
+
+	/* Check RAM power status */
+	ret = aml_send_tci_cmd(hdev, AML_TCI_CMD_READ,
+			       AML_OP_RAM_POWER_CTR, NULL, 0);
+	if (ret)
+		goto exit;
+
+	ret = request_firmware(&firmware, fw_name, &hdev->dev);
+	if (ret < 0) {
+		bt_dev_err(hdev, "Failed to load <%s>:(%d)", fw_name, ret);
+		goto exit;
+	}
+
+	fw_len = (struct aml_fw_len *)firmware->data;
+
+	/* Download ICCM */
+	iccm_start = (u8 *)(firmware->data) + sizeof(struct aml_fw_len)
+			+ amldev->aml_dev_data->iccm_offset;
+	iccm_len = fw_len->iccm_len - amldev->aml_dev_data->iccm_offset;
+	ret = aml_send_firmware(hdev, FW_ICCM, iccm_start, iccm_len,
+				amldev->aml_dev_data->iccm_offset);
+	if (ret) {
+		bt_dev_err(hdev, "Failed to send FW_ICCM (%d)", ret);
+		goto exit;
+	}
+
+	/* Download DCCM */
+	dccm_start = (u8 *)(firmware->data) + sizeof(struct aml_fw_len) + fw_len->iccm_len;
+	dccm_len = fw_len->dccm_len;
+	ret = aml_send_firmware(hdev, FW_DCCM, dccm_start, dccm_len,
+				amldev->aml_dev_data->dccm_offset);
+	if (ret) {
+		bt_dev_err(hdev, "Failed to send FW_DCCM (%d)", ret);
+		goto exit;
+	}
+
+	/* Disable firmware download event */
+	value = 0;
+	ret = aml_send_tci_cmd(hdev, AML_TCI_CMD_WRITE,
+			       AML_OP_EVT_ENABLE,
+			       &value, sizeof(value));
+	if (ret)
+		goto exit;
+
+exit:
+	if (firmware)
+		release_firmware(firmware);
+	return ret;
+}
+
+static int aml_send_reset(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = __hci_cmd_sync_ev(hdev, HCI_OP_RESET, 0, NULL,
+				HCI_EV_CMD_COMPLETE, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		bt_dev_err(hdev, "Failed to send hci reset cmd (%d)", err);
+		return err;
+	}
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int aml_dump_fw_version(struct hci_dev *hdev)
+{
+	struct aml_tci_rsp *rsp = NULL;
+	struct sk_buff *skb;
+	u8 value[6] = {0};
+	u8 *fw_ver = NULL;
+	int err = 0;
+
+	skb = __hci_cmd_sync_ev(hdev, AML_BT_HCI_VENDOR_CMD, sizeof(value), value,
+				HCI_EV_CMD_COMPLETE, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		bt_dev_err(hdev, "Failed to get fw version (error: %d)", err);
+		return err;
+	}
+
+	rsp = skb_pull_data(skb, sizeof(struct aml_tci_rsp));
+	if (!rsp)
+		goto exit;
+
+	if (rsp->opcode != AML_BT_HCI_VENDOR_CMD || rsp->status != 0x00) {
+		bt_dev_err(hdev, "dump version, error response (0x%04X):(%d)",
+		       rsp->opcode, rsp->status);
+		err = -EINVAL;
+		goto exit;
+	}
+
+	fw_ver = (u8 *)rsp + AML_EVT_HEAD_SIZE;
+	bt_dev_info(hdev, "fw_version: date = %02x.%02x, number = 0x%02x%02x",
+		*(fw_ver + 1), *fw_ver, *(fw_ver + 3), *(fw_ver + 2));
+
+exit:
+	kfree_skb(skb);
+	return err;
+}
+
+static int aml_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	struct aml_tci_rsp *rsp = NULL;
+	struct sk_buff *skb;
+	int err = 0;
+
+	bt_dev_info(hdev, "set bdaddr (%pM)", bdaddr);
+	skb = __hci_cmd_sync_ev(hdev, AML_BT_HCI_VENDOR_CMD,
+				sizeof(bdaddr_t), bdaddr,
+				HCI_EV_CMD_COMPLETE, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		bt_dev_err(hdev, "Failed to set bdaddr (error: %d)", err);
+		return err;
+	}
+
+	rsp = skb_pull_data(skb, sizeof(struct aml_tci_rsp));
+	if (!rsp)
+		goto exit;
+
+	if (rsp->opcode != AML_BT_HCI_VENDOR_CMD || rsp->status != 0x00) {
+		bt_dev_err(hdev, "error response (0x%x):(%d)", rsp->opcode, rsp->status);
+		err = -EINVAL;
+		goto exit;
+	}
+
+exit:
+	kfree_skb(skb);
+	return err;
+}
+
+static int aml_check_bdaddr(struct hci_dev *hdev)
+{
+	struct hci_rp_read_bd_addr *paddr;
+	struct sk_buff *skb;
+	int err;
+
+	if (bacmp(&hdev->public_addr, BDADDR_ANY))
+		return 0;
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_READ_BD_ADDR, 0, NULL,
+			     HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		bt_dev_err(hdev, "Failed to read bdaddr (error: %d)", err);
+		return err;
+	}
+
+	paddr = skb_pull_data(skb, sizeof(struct hci_rp_read_bd_addr));
+	if (!paddr)
+		goto exit;
+
+	if (!bacmp(&paddr->bdaddr, AML_BDADDR_DEFAULT)) {
+		bt_dev_info(hdev, "amlbt using default bdaddr (%pM)", &paddr->bdaddr);
+		set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks);
+	}
+
+exit:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int aml_config_rf(struct hci_dev *hdev, bool is_coex)
+{
+	u32 value = AML_RF_ANT_DOUBLE;
+
+	/* Use a single antenna when co-existing with wifi */
+	if (is_coex)
+		value = AML_RF_ANT_SINGLE;
+
+	return aml_send_tci_cmd(hdev, AML_TCI_CMD_WRITE,
+				AML_OP_RF_CFG,
+				&value, sizeof(value));
+}
+
+static int aml_parse_dt(struct aml_serdev *amldev)
+{
+	struct device *pdev = amldev->dev;
+
+	amldev->bt_en_gpio = devm_gpiod_get(pdev, "enable",
+					GPIOD_OUT_LOW);
+	if (IS_ERR(amldev->bt_en_gpio)) {
+		dev_err(pdev, "Failed to acquire enable gpios");
+		return PTR_ERR(amldev->bt_en_gpio);
+	}
+
+	if (device_property_read_string(pdev, "firmware-name",
+					&amldev->firmware_name)) {
+		dev_err(pdev, "Failed to acquire firmware path");
+		return -ENODEV;
+	}
+
+	amldev->bt_supply = devm_regulator_get(pdev, "vddio");
+	if (IS_ERR(amldev->bt_supply)) {
+		dev_err(pdev, "Failed to acquire regulator");
+		return PTR_ERR(amldev->bt_supply);
+	}
+
+	amldev->lpo_clk = devm_clk_get(pdev, NULL);
+	if (IS_ERR(amldev->lpo_clk)) {
+		dev_err(pdev, "Failed to acquire clock source");
+		return PTR_ERR(amldev->lpo_clk);
+	}
+
+	return 0;
+}
+
+static int aml_power_on(struct aml_serdev *amldev)
+{
+	int err;
+
+	err = regulator_enable(amldev->bt_supply);
+	if (err) {
+		dev_err(amldev->dev, "Failed to enable regulator: (%d)", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(amldev->lpo_clk);
+	if (err) {
+		dev_err(amldev->dev, "Failed to enable lpo clock: (%d)", err);
+		return err;
+	}
+
+	gpiod_set_value_cansleep(amldev->bt_en_gpio, 1);
+
+	/* Wait 20ms for bluetooth controller power on */
+	msleep(20);
+	return 0;
+}
+
+static int aml_power_off(struct aml_serdev *amldev)
+{
+	gpiod_set_value_cansleep(amldev->bt_en_gpio, 0);
+
+	clk_disable_unprepare(amldev->lpo_clk);
+
+	regulator_disable(amldev->bt_supply);
+
+	return 0;
+}
+
+static int aml_set_baudrate(struct hci_uart *hu, unsigned int speed)
+{
+	/* update controller baudrate */
+	if (aml_update_chip_baudrate(hu->hdev, speed) != 0) {
+		bt_dev_err(hu->hdev, "Failed to update baud rate");
+		return -EINVAL;
+	}
+
+	/* update local baudrate */
+	serdev_device_set_baudrate(hu->serdev, speed);
+
+	return 0;
+}
+
+/* Initialize protocol */
+static int aml_open(struct hci_uart *hu)
+{
+	struct aml_serdev *amldev = serdev_device_get_drvdata(hu->serdev);
+	struct aml_data *aml_data;
+	int err;
+
+	err = aml_parse_dt(amldev);
+	if (err)
+		return err;
+
+	if (!hci_uart_has_flow_control(hu)) {
+		bt_dev_err(hu->hdev, "no flow control");
+		return -EOPNOTSUPP;
+	}
+
+	aml_data = kzalloc(sizeof(*aml_data), GFP_KERNEL);
+	if (!aml_data)
+		return -ENOMEM;
+
+	skb_queue_head_init(&aml_data->txq);
+
+	hu->priv = aml_data;
+
+	return 0;
+}
+
+static int aml_close(struct hci_uart *hu)
+{
+	struct aml_serdev *amldev = serdev_device_get_drvdata(hu->serdev);
+	struct aml_data *aml_data = hu->priv;
+
+	skb_queue_purge(&aml_data->txq);
+	kfree_skb(aml_data->rx_skb);
+	kfree(aml_data);
+
+	hu->priv = NULL;
+
+	return aml_power_off(amldev);
+}
+
+static int aml_flush(struct hci_uart *hu)
+{
+	struct aml_data *aml_data = hu->priv;
+
+	skb_queue_purge(&aml_data->txq);
+
+	return 0;
+}
+
+static int aml_setup(struct hci_uart *hu)
+{
+	struct aml_serdev *amldev = serdev_device_get_drvdata(hu->serdev);
+	struct hci_dev *hdev = amldev->serdev_hu.hdev;
+	int err;
+
+	/* Setup bdaddr */
+	hdev->set_bdaddr = aml_set_bdaddr;
+
+	err = aml_power_on(amldev);
+	if (err)
+		return err;
+
+	err = aml_set_baudrate(hu, amldev->serdev_hu.proto->oper_speed);
+	if (err)
+		return err;
+
+	err = aml_download_firmware(hdev, amldev->firmware_name);
+	if (err)
+		return err;
+
+	err = aml_config_rf(hdev, amldev->aml_dev_data->is_coex);
+	if (err)
+		return err;
+
+	err = aml_start_chip(hdev);
+	if (err)
+		return err;
+
+	/* Wait 60ms for controller startup */
+	msleep(60);
+
+	err = aml_dump_fw_version(hdev);
+	if (err)
+		return err;
+
+	err = aml_send_reset(hdev);
+	if (err)
+		return err;
+
+	err = aml_check_bdaddr(hdev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int aml_enqueue(struct hci_uart *hu, struct sk_buff *skb)
+{
+	struct aml_data *aml_data = hu->priv;
+
+	skb_queue_tail(&aml_data->txq, skb);
+
+	return 0;
+}
+
+static struct sk_buff *aml_dequeue(struct hci_uart *hu)
+{
+	struct aml_data *aml_data = hu->priv;
+	struct sk_buff *skb;
+
+	skb = skb_dequeue(&aml_data->txq);
+
+	/* Prepend skb with frame type */
+	if (skb)
+		memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1);
+
+	return skb;
+}
+
+static int aml_recv(struct hci_uart *hu, const void *data, int count)
+{
+	struct aml_data *aml_data = hu->priv;
+	int err;
+
+	aml_data->rx_skb = h4_recv_buf(hu->hdev, aml_data->rx_skb, data, count,
+				       aml_recv_pkts,
+				       ARRAY_SIZE(aml_recv_pkts));
+	if (IS_ERR(aml_data->rx_skb)) {
+		err = PTR_ERR(aml_data->rx_skb);
+		bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err);
+		aml_data->rx_skb = NULL;
+		return err;
+	}
+
+	return count;
+}
+
+static const struct hci_uart_proto aml_hci_proto = {
+	.id		= HCI_UART_AML,
+	.name		= "AML",
+	.init_speed	= 115200,
+	.oper_speed	= 4000000,
+	.open		= aml_open,
+	.close		= aml_close,
+	.setup		= aml_setup,
+	.flush		= aml_flush,
+	.recv		= aml_recv,
+	.enqueue	= aml_enqueue,
+	.dequeue	= aml_dequeue,
+};
+
+static void aml_device_driver_shutdown(struct device *dev)
+{
+	struct aml_serdev *amldev = dev_get_drvdata(dev);
+
+	aml_power_off(amldev);
+}
+
+static int aml_serdev_probe(struct serdev_device *serdev)
+{
+	struct aml_serdev *amldev;
+	int err;
+
+	amldev = devm_kzalloc(&serdev->dev, sizeof(*amldev), GFP_KERNEL);
+	if (!amldev)
+		return -ENOMEM;
+
+	amldev->serdev_hu.serdev = serdev;
+	amldev->dev = &serdev->dev;
+	serdev_device_set_drvdata(serdev, amldev);
+
+	err = hci_uart_register_device(&amldev->serdev_hu, &aml_hci_proto);
+	if (err)
+		return dev_err_probe(amldev->dev, err,
+			      "Failed to register hci uart device");
+
+	amldev->aml_dev_data = device_get_match_data(&serdev->dev);
+
+	return 0;
+}
+
+static void aml_serdev_remove(struct serdev_device *serdev)
+{
+	struct aml_serdev *amldev = serdev_device_get_drvdata(serdev);
+
+	hci_uart_unregister_device(&amldev->serdev_hu);
+}
+
+static const struct aml_device_data data_w155s2 = {
+	.iccm_offset = 256 * 1024,
+};
+
+static const struct aml_device_data data_w265s2 = {
+	.iccm_offset = 384 * 1024,
+};
+
+static const struct of_device_id aml_bluetooth_of_match[] = {
+	{ .compatible = "amlogic,w155s2-bt", .data = &data_w155s2 },
+	{ .compatible = "amlogic,w265s2-bt", .data = &data_w265s2 },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, aml_bluetooth_of_match);
+
+static struct serdev_device_driver aml_serdev_driver = {
+	.probe = aml_serdev_probe,
+	.remove = aml_serdev_remove,
+	.driver = {
+		.name = "hci_uart_aml",
+		.of_match_table = aml_bluetooth_of_match,
+		.shutdown = aml_device_driver_shutdown,
+	},
+};
+
+int __init aml_init(void)
+{
+	serdev_device_driver_register(&aml_serdev_driver);
+
+	return hci_uart_register_proto(&aml_hci_proto);
+}
+
+int __exit aml_deinit(void)
+{
+	serdev_device_driver_unregister(&aml_serdev_driver);
+
+	return hci_uart_unregister_proto(&aml_hci_proto);
+}
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index 30192bb08354..d307c41a5470 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -870,7 +870,9 @@ static int __init hci_uart_init(void)
 #ifdef CONFIG_BT_HCIUART_MRVL
 	mrvl_init();
 #endif
-
+#ifdef CONFIG_BT_HCIUART_AML
+	aml_init();
+#endif
 	return 0;
 }
 
@@ -906,7 +908,9 @@ static void __exit hci_uart_exit(void)
 #ifdef CONFIG_BT_HCIUART_MRVL
 	mrvl_deinit();
 #endif
-
+#ifdef CONFIG_BT_HCIUART_AML
+	aml_deinit();
+#endif
 	tty_unregister_ldisc(&hci_uart_ldisc);
 }
 
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index 00bf7ae82c5b..fbf3079b92a5 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -20,7 +20,7 @@
 #define HCIUARTGETFLAGS		_IOR('U', 204, int)
 
 /* UART protocols */
-#define HCI_UART_MAX_PROTO	12
+#define HCI_UART_MAX_PROTO	13
 
 #define HCI_UART_H4	0
 #define HCI_UART_BCSP	1
@@ -34,6 +34,7 @@
 #define HCI_UART_AG6XX	9
 #define HCI_UART_NOKIA	10
 #define HCI_UART_MRVL	11
+#define HCI_UART_AML	12
 
 #define HCI_UART_RAW_DEVICE	0
 #define HCI_UART_RESET_ON_INIT	1
@@ -209,3 +210,8 @@ int ag6xx_deinit(void);
 int mrvl_init(void);
 int mrvl_deinit(void);
 #endif
+
+#ifdef CONFIG_BT_HCIUART_AML
+int aml_init(void);
+int aml_deinit(void);
+#endif
-- 
cgit v1.3-3-g829e


From 7494ef879636e9fabaf5a1a7fdfee81b3c6b206b Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Fri, 9 Aug 2024 13:42:26 +0800
Subject: MAINTAINERS: Add an entry for Amlogic HCI UART (M: Yang Li)

Add Amlogic Bluetooth entry to MAINTAINERS to clarify the maintainers

Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4053168fdc12..87f9ff0d1649 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1153,6 +1153,13 @@ S:	Supported
 F:	arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi
 F:	drivers/net/ethernet/amd/xgbe/
 
+AMLOGIC BLUETOOTH DRIVER
+M:	Yang Li <yang.li@amlogic.com>
+L:	linux-bluetooth@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/bluetooth/amlogic,w155s2-bt.yaml
+F:	drivers/bluetooth/hci_aml.c
+
 AMLOGIC DDR PMU DRIVER
 M:	Jiucheng Xu <jiucheng.xu@amlogic.com>
 L:	linux-amlogic@lists.infradead.org
-- 
cgit v1.3-3-g829e


From 0fec656d08aa59ad3ea1bba148a4f7e5618fd4d3 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 12 Aug 2024 11:01:15 -0400
Subject: Bluetooth: btusb: Invert LE State flag to set invalid rather then
 valid

This inverts the LE State flag so by default we assume the controllers
would report valid states rather than invalid so it is inline with the
respective quirk (HCI_QUIRK_BROKEN_LE_STATES).

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 226 ++++++++++++++++------------------------------
 1 file changed, 76 insertions(+), 150 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index d3514def9828..42c867b2e42c 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -59,7 +59,7 @@ static struct usb_driver btusb_driver;
 #define BTUSB_CW6622			BIT(19)
 #define BTUSB_MEDIATEK			BIT(20)
 #define BTUSB_WIDEBAND_SPEECH		BIT(21)
-#define BTUSB_VALID_LE_STATES		BIT(22)
+#define BTUSB_INVALID_LE_STATES		BIT(22)
 #define BTUSB_QCA_WCN6855		BIT(23)
 #define BTUSB_INTEL_BROKEN_SHUTDOWN_LED	BIT(24)
 #define BTUSB_INTEL_BROKEN_INITIAL_NCMD BIT(25)
@@ -298,115 +298,79 @@ static const struct usb_device_id quirks_table[] = {
 
 	/* QCA WCN6855 chipset */
 	{ USB_DEVICE(0x0cf3, 0xe600), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0cc), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0d6), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0e3), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9309), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9409), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0d0), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9108), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9109), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9208), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9209), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9308), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9408), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9508), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9509), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9608), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9609), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x10ab, 0x9f09), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3022), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0c7), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0c9), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0ca), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0cb), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0ce), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0de), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0df), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0e1), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0ea), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0ec), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3023), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3024), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3a22), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3a24), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3a26), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3a27), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* QCA WCN785x chipset */
 	{ USB_DEVICE(0x0cf3, 0xe700), .driver_info = BTUSB_QCA_WCN6855 |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Broadcom BCM2035 */
 	{ USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 },
@@ -571,134 +535,96 @@ static const struct usb_device_id quirks_table[] = {
 	/* MediaTek Bluetooth devices */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0e8d, 0xe0, 0x01, 0x01),
 	  .driver_info = BTUSB_MEDIATEK |
-			 BTUSB_WIDEBAND_SPEECH |
-			 BTUSB_VALID_LE_STATES },
+			 BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional MediaTek MT7615E Bluetooth devices */
 	{ USB_DEVICE(0x13d3, 0x3560), .driver_info = BTUSB_MEDIATEK},
 
 	/* Additional MediaTek MT7663 Bluetooth devices */
 	{ USB_DEVICE(0x043e, 0x310c), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3801), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional MediaTek MT7668 Bluetooth devices */
 	{ USB_DEVICE(0x043e, 0x3109), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional MediaTek MT7921 Bluetooth devices */
 	{ USB_DEVICE(0x0489, 0xe0c8), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0cd), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0e0), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f2), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3802), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0e8d, 0x0608), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3563), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3564), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3567), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3578), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3583), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3606), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* MediaTek MT7922 Bluetooth devices */
 	{ USB_DEVICE(0x13d3, 0x3585), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* MediaTek MT7922A Bluetooth devices */
 	{ USB_DEVICE(0x0489, 0xe0d8), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0d9), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0e2), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0e4), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f1), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f2), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f5), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f6), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe102), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x38e4), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3568), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3605), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3607), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3614), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3615), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x35f5, 0x7922), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional MediaTek MT7925 Bluetooth devices */
 	{ USB_DEVICE(0x0489, 0xe113), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3602), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3603), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3604), .driver_info = BTUSB_MEDIATEK |
-						     BTUSB_WIDEBAND_SPEECH |
-						     BTUSB_VALID_LE_STATES },
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
@@ -3959,7 +3885,7 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info & BTUSB_WIDEBAND_SPEECH)
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
-	if (!(id->driver_info & BTUSB_VALID_LE_STATES))
+	if (id->driver_info & BTUSB_INVALID_LE_STATES)
 		set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
 
 	if (id->driver_info & BTUSB_DIGIANSWER) {
-- 
cgit v1.3-3-g829e


From bdf9557f70e7512bb2f754abf90d9e9958745316 Mon Sep 17 00:00:00 2001
From: Hilda Wu <hildawu@realtek.com>
Date: Fri, 16 Aug 2024 16:58:22 +0800
Subject: Bluetooth: btusb: Add Realtek RTL8852C support ID 0x0489:0xe122

Add the support ID (0x0489, 0xe122) to usb_device_id table for
Realtek RTL8852C.

The device info from /sys/kernel/debug/usb/devices as below.

T:  Bus=03 Lev=01 Prnt=01 Port=02 Cnt=01 Dev#=  2 Spd=12   MxCh= 0
D:  Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e122 Rev= 0.00
S:  Manufacturer=Realtek
S:  Product=Bluetooth Radio
S:  SerialNumber=00e04c000001
C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=1ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms

Signed-off-by: Hilda Wu <hildawu@realtek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 42c867b2e42c..bb698ca98283 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -504,6 +504,8 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3592), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe122), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Realtek 8852BE Bluetooth devices */
 	{ USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK |
-- 
cgit v1.3-3-g829e


From 61b27cdf025bf47d3caf0f1ceab078b48774ba13 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Fri, 16 Aug 2024 16:43:08 +0530
Subject: Bluetooth: hci_h4: Add support for ISO packets in h4_recv.h

This adds ISO packet support in h4_recv.h, which was created before ISO
packet handling was added to hci_h4.c and hci_uart.c

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/h4_recv.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/bluetooth/h4_recv.h b/drivers/bluetooth/h4_recv.h
index 4f2c89742245..647d37ca4cdd 100644
--- a/drivers/bluetooth/h4_recv.h
+++ b/drivers/bluetooth/h4_recv.h
@@ -38,6 +38,13 @@ struct h4_recv_pkt {
 	.lsize = 1, \
 	.maxlen = HCI_MAX_EVENT_SIZE
 
+#define H4_RECV_ISO \
+	.type = HCI_ISODATA_PKT, \
+	.hlen = HCI_ISO_HDR_SIZE, \
+	.loff = 2, \
+	.lsize = 2, \
+	.maxlen = HCI_MAX_FRAME_SIZE
+
 static inline struct sk_buff *h4_recv_buf(struct hci_dev *hdev,
 					  struct sk_buff *skb,
 					  const unsigned char *buffer,
-- 
cgit v1.3-3-g829e


From 33b25739acb9bc4b1edfd39d25487d2520c7986b Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Fri, 16 Aug 2024 16:43:09 +0530
Subject: Bluetooth: btnxpuart: Add support for ISO packets

This enables btnxpuart driver to handle ISO RX packet when DUT is
configured as audio sink.

Tested IW612 on iMX8MMini platform and BlueZ-5.77 as follows:
1) Configured DUT with bap_bcast_sink role in pipewire configuration file.
2) Started pipewire and DUT is able to sync with Broadcast source through
pipewire.
3) ISO data RX is seen in btmon.
4) Audio/Music is heard on audio jack.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Tested-by: Sarveshwar Bajaj <sarveshwar.bajaj@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index ad1ec6f3685a..7c2030cec10e 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1412,6 +1412,7 @@ static const struct h4_recv_pkt nxp_recv_pkts[] = {
 	{ H4_RECV_ACL,          .recv = hci_recv_frame },
 	{ H4_RECV_SCO,          .recv = hci_recv_frame },
 	{ H4_RECV_EVENT,        .recv = hci_recv_frame },
+	{ H4_RECV_ISO,		.recv = hci_recv_frame },
 	{ NXP_RECV_CHIP_VER_V1, .recv = nxp_recv_chip_ver_v1 },
 	{ NXP_RECV_FW_REQ_V1,   .recv = nxp_recv_fw_req_v1 },
 	{ NXP_RECV_CHIP_VER_V3, .recv = nxp_recv_chip_ver_v3 },
-- 
cgit v1.3-3-g829e


From 5f4f954bba12af7ca1e0e7c1352b73aefdce1d81 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 19 Aug 2024 09:48:01 +0200
Subject: dt-bindings: bluetooth: bring the HW description closer to reality
 for wcn6855

Describe the inputs from the PMU that the Bluetooth module on wcn6855
consumes and drop the ones from the host. This breaks the current
contract but the only two users of wcn6855 upstream - sc8280xp based
boards - will be updated in DTS patches sent separately while the
hci_qca driver will remain backwards compatible with older DT sources.

Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml  | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
index 68c5ed111417..64a5c5004862 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
@@ -172,14 +172,14 @@ allOf:
               - qcom,wcn6855-bt
     then:
       required:
-        - enable-gpios
-        - swctrl-gpios
-        - vddio-supply
-        - vddbtcxmx-supply
         - vddrfacmn-supply
+        - vddaon-supply
+        - vddwlcx-supply
+        - vddwlmx-supply
+        - vddbtcmx-supply
         - vddrfa0p8-supply
         - vddrfa1p2-supply
-        - vddrfa1p7-supply
+        - vddrfa1p8-supply
   - if:
       properties:
         compatible:
-- 
cgit v1.3-3-g829e


From 2fcb7936cef3a045ced9d5b8cdb644bced9f99b5 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 19 Aug 2024 21:52:11 +0800
Subject: Bluetooth: L2CAP: Remove unused declarations

Commit e7b02296fb40 ("Bluetooth: Remove BT_HS") removed the implementations
but leave declarations.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 5cfdc813491a..313d0b972e06 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -968,10 +968,6 @@ void l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func,
 		     void *data);
 void l2cap_chan_del(struct l2cap_chan *chan, int err);
 void l2cap_send_conn_req(struct l2cap_chan *chan);
-void l2cap_move_start(struct l2cap_chan *chan);
-void l2cap_logical_cfm(struct l2cap_chan *chan, struct hci_chan *hchan,
-		       u8 status);
-void __l2cap_physical_cfm(struct l2cap_chan *chan, int result);
 
 struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn);
 void l2cap_conn_put(struct l2cap_conn *conn);
-- 
cgit v1.3-3-g829e


From fe4408da5bfd495e0eeea684932a267254f76f11 Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sat, 10 Aug 2024 22:14:15 +0800
Subject: Bluetooth: hci_conn: Remove redundant memset after kzalloc

Since kzalloc already zeroes the allocated memory, the subsequent
memset call is unnecessary. This patch removes the redundant memset to
clean up the code and enhance efficiency.

Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_conn.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index c82502e213a8..323d397b0e92 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -778,7 +778,6 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c
 	if (!d)
 		return -ENOMEM;
 
-	memset(d, 0, sizeof(*d));
 	d->big = big;
 	d->sync_handle = conn->sync_handle;
 
-- 
cgit v1.3-3-g829e


From 0519376db710783ebc97f1c72a09424af0bc920a Mon Sep 17 00:00:00 2001
From: Frédéric Danis <frederic.danis@collabora.com>
Date: Tue, 20 Aug 2024 16:17:16 +0200
Subject: Bluetooth: hci_ldisc: Use speed set by btattach as oper_speed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting a BCM UART controller not defined as a platform device or
a serdev with "btattach -B /dev/ttyS1 -P bcm -S 3000000" works fine
but the serial port remains at the init_speed, i.e. 115200.

The oper_speed is only set if a device is declared in ACPI, device
tree or as a platform device.

This commit copies the serial port speed fixed by hciattach to the
oper_speed on line discipline opening.

Signed-off-by: Frédéric Danis <frederic.danis@collabora.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_ldisc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index d307c41a5470..395d66e32a2e 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -507,6 +507,9 @@ static int hci_uart_tty_open(struct tty_struct *tty)
 	hu->alignment = 1;
 	hu->padding = 0;
 
+	/* Use serial port speed as oper_speed */
+	hu->oper_speed = tty->termios.c_ospeed;
+
 	INIT_WORK(&hu->init_ready, hci_uart_init_work);
 	INIT_WORK(&hu->write_work, hci_uart_write_work);
 
-- 
cgit v1.3-3-g829e


From a30ce2992075b9bd8824a5f1025383e8d9bc05bc Mon Sep 17 00:00:00 2001
From: Max Chou <max.chou@realtek.com>
Date: Tue, 20 Aug 2024 14:28:29 +0800
Subject: Bluetooth: btrtl: Add the support for RTL8922A

Add the support for RTL8922A BT controller on USB interface.
The necessary firmware will be submitted to linux-firmware project.

The device info from /sys/kernel/debug/usb/devices as below.

T:  Bus=01 Lev=02 Prnt=02 Port=02 Cnt=01 Dev#=  3 Spd=12   MxCh= 0
D:  Ver= 1.00 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0bda ProdID=8922 Rev= 0.00
S:  Manufacturer=Realtek
S:  Product=Bluetooth Radio
S:  SerialNumber=00E04C885A01
C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=1ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms

Signed-off-by: Max Chou <max.chou@realtek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c | 16 ++++++++++++++++
 drivers/bluetooth/btusb.c | 11 +++++++++++
 2 files changed, 27 insertions(+)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index fd7991ea7672..d95a1cfa35ed 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -30,6 +30,7 @@
 #define RTL_ROM_LMP_8822B	0x8822
 #define RTL_ROM_LMP_8852A	0x8852
 #define RTL_ROM_LMP_8851B	0x8851
+#define RTL_ROM_LMP_8922A	0x8922
 #define RTL_CONFIG_MAGIC	0x8723ab55
 
 #define RTL_VSC_OP_COREDUMP	0xfcff
@@ -69,6 +70,7 @@ enum btrtl_chip_id {
 	CHIP_ID_8852B = 20,
 	CHIP_ID_8852C = 25,
 	CHIP_ID_8851B = 36,
+	CHIP_ID_8922A = 44,
 	CHIP_ID_8852BT = 47,
 };
 
@@ -309,6 +311,15 @@ static const struct id_table ic_id_table[] = {
 	  .cfg_name = "rtl_bt/rtl8851bu_config",
 	  .hw_info  = "rtl8851bu" },
 
+	/* 8922A */
+	{ IC_INFO(RTL_ROM_LMP_8922A, 0xa, 0xc, HCI_USB),
+	  .config_needed = false,
+	  .has_rom_version = true,
+	  .has_msft_ext = true,
+	  .fw_name  = "rtl_bt/rtl8922au_fw",
+	  .cfg_name = "rtl_bt/rtl8922au_config",
+	  .hw_info  = "rtl8922au" },
+
 	/* 8852BT/8852BE-VT */
 	{ IC_INFO(RTL_ROM_LMP_8852A, 0x87, 0xc, HCI_USB),
 	  .config_needed = false,
@@ -655,6 +666,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 		{ RTL_ROM_LMP_8852A, 20 },	/* 8852B */
 		{ RTL_ROM_LMP_8852A, 25 },	/* 8852C */
 		{ RTL_ROM_LMP_8851B, 36 },	/* 8851B */
+		{ RTL_ROM_LMP_8922A, 44 },	/* 8922A */
 		{ RTL_ROM_LMP_8852A, 47 },	/* 8852BT */
 	};
 
@@ -1255,6 +1267,7 @@ int btrtl_download_firmware(struct hci_dev *hdev,
 	case RTL_ROM_LMP_8852A:
 	case RTL_ROM_LMP_8703B:
 	case RTL_ROM_LMP_8851B:
+	case RTL_ROM_LMP_8922A:
 		err = btrtl_setup_rtl8723b(hdev, btrtl_dev);
 		break;
 	default:
@@ -1286,6 +1299,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
 	case CHIP_ID_8852B:
 	case CHIP_ID_8852C:
 	case CHIP_ID_8851B:
+	case CHIP_ID_8922A:
 	case CHIP_ID_8852BT:
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
@@ -1528,3 +1542,5 @@ MODULE_FIRMWARE("rtl_bt/rtl8852btu_config.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852cu_fw_v2.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8852cu_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8922au_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8922au_config.bin");
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index bb698ca98283..3e06cae2841e 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -530,6 +530,17 @@ static const struct usb_device_id quirks_table[] = {
 	/* Realtek 8852BT/8852BE-VT Bluetooth devices */
 	{ USB_DEVICE(0x0bda, 0x8520), .driver_info = BTUSB_REALTEK |
 						     BTUSB_WIDEBAND_SPEECH },
+
+	/* Realtek 8922AE Bluetooth devices */
+	{ USB_DEVICE(0x0bda, 0x8922), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3617), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3616), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe130), .driver_info = BTUSB_REALTEK |
+						     BTUSB_WIDEBAND_SPEECH },
+
 	/* Realtek Bluetooth devices */
 	{ USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01),
 	  .driver_info = BTUSB_REALTEK },
-- 
cgit v1.3-3-g829e


From cb45396f96f9671f7a18df481702e19998eb0f4b Mon Sep 17 00:00:00 2001
From: Pavel Nikulin <pavel@noa-labs.com>
Date: Wed, 21 Aug 2024 15:08:56 +0400
Subject: Bluetooth: btusb: Add Mediatek MT7925 support ID 0x13d3:0x3608

Add the support ID (0x13d3, 0x3608) to usb_device_id table for
Realtek MT7925B14L found on AW-EM637 WiFi+BT modules in 2024 Asus laptops.

The device info from /sys/kernel/debug/usb/devices as below.

T:  Bus=03 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  2 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=13d3 ProdID=3608 Rev= 1.00
S:  Manufacturer=MediaTek Inc.
S:  Product=Wireless_Device
S:  SerialNumber=000000000
C:* #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=100mA
A:  FirstIf#= 0 IfCount= 3 Cls=e0(wlcon) Sub=01 Prot=01
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=125us
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:  If#= 2 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=8a(I) Atr=03(Int.) MxPS=  64 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS=  64 Ivl=125us
I:* If#= 2 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=8a(I) Atr=03(Int.) MxPS= 512 Ivl=125us
E:  Ad=0a(O) Atr=03(Int.) MxPS= 512 Ivl=125us

Signed-off-by: Pavel Nikulin <pavel@noa-labs.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 3e06cae2841e..36a869a57910 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -638,6 +638,8 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3604), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3608), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Additional Realtek 8723AE Bluetooth devices */
 	{ USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK },
-- 
cgit v1.3-3-g829e


From 52bc7d66659faac6e5a47e3ab38d8c8f590e94e5 Mon Sep 17 00:00:00 2001
From: Li Zetao <lizetao1@huawei.com>
Date: Wed, 21 Aug 2024 09:24:03 +0800
Subject: Bluetooth: btrtl: Use kvmemdup to simplify the code

Use kvmemdup instead of kvmalloc() + memcpy() to simplify the code.

No functional change intended.

Signed-off-by: Li Zetao <lizetao1@huawei.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index d95a1cfa35ed..4c0f551a9975 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -890,10 +890,8 @@ static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff)
 	if (ret < 0)
 		return ret;
 	ret = fw->size;
-	*buff = kvmalloc(fw->size, GFP_KERNEL);
-	if (*buff)
-		memcpy(*buff, fw->data, ret);
-	else
+	*buff = kvmemdup(fw->data, fw->size, GFP_KERNEL);
+	if (!*buff)
 		ret = -ENOMEM;
 
 	release_firmware(fw);
-- 
cgit v1.3-3-g829e


From 97c7ed86322440131f834d34c6670d1d472901dd Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 27 Aug 2024 12:52:48 +0200
Subject: Bluetooth: Use led_set_brightness() in LED trigger activate()
 callback

A LED trigger's activate() callback gets called when the LED trigger
gets activated for a specific LED, so that the trigger code can ensure
the LED state matches the current state of the trigger condition
(LED_FULL when HCI_UP is set in this case).

led_trigger_event() is intended for trigger condition state changes and
iterates over _all_ LEDs which are controlled by this trigger changing
the brightness of each of them.

In the activate() case only the brightness of the LED which is being
activated needs to change and that LED is passed as an argument to
activate(), switch to led_set_brightness() to only change the brightness
of the LED being activated.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/leds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c
index f46847632ffa..6e349704efe4 100644
--- a/net/bluetooth/leds.c
+++ b/net/bluetooth/leds.c
@@ -48,7 +48,7 @@ static int power_activate(struct led_classdev *led_cdev)
 	htrig = to_hci_basic_led_trigger(led_cdev->trigger);
 	powered = test_bit(HCI_UP, &htrig->hdev->flags);
 
-	led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF);
+	led_set_brightness(led_cdev, powered ? LED_FULL : LED_OFF);
 
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 9a0570948c5def5c59e588dc0e009ed850a1f5a1 Mon Sep 17 00:00:00 2001
From: Hilda Wu <hildawu@realtek.com>
Date: Thu, 29 Aug 2024 16:40:05 +0800
Subject: Bluetooth: btrtl: Set msft ext address filter quirk for RTL8852B

For tracking multiple devices concurrently with a condition.
The patch enables the HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER quirk
on RTL8852B controller.

The quirk setting is based on commit 9e14606d8f38 ("Bluetooth: msft:
Extended monitor tracking by address filter")

With this setting, when a pattern monitor detects a device, this
feature issues an address monitor for tracking that device. Let the
original pattern monitor keep monitor new devices.

Signed-off-by: Hilda Wu <hildawu@realtek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btrtl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 4c0f551a9975..2d95b3ea046d 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1308,6 +1308,7 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
 			btrealtek_set_flag(hdev, REALTEK_ALT6_CONTINUOUS_TX_CHIP);
 
 		if (btrtl_dev->project_id == CHIP_ID_8852A ||
+		    btrtl_dev->project_id == CHIP_ID_8852B ||
 		    btrtl_dev->project_id == CHIP_ID_8852C)
 			set_bit(HCI_QUIRK_USE_MSFT_EXT_ADDRESS_FILTER, &hdev->quirks);
 
-- 
cgit v1.3-3-g829e


From d47da6bd4cfa982fe903f33423b9e2ec541e9496 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 30 Aug 2024 17:29:27 -0400
Subject: Bluetooth: hci_core: Fix sending MGMT_EV_CONNECT_FAILED

If HCI_CONN_MGMT_CONNECTED has been set then the event shall be
HCI_CONN_MGMT_DISCONNECTED.

Fixes: b644ba336997 ("Bluetooth: Update device_connected and device_found events to latest API")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  4 ++--
 net/bluetooth/hci_conn.c         |  6 ++----
 net/bluetooth/mgmt.c             | 13 +++++++++----
 3 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 1a32e602630e..88265d37aa72 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -2257,8 +2257,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			      bool mgmt_connected);
 void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 			    u8 link_type, u8 addr_type, u8 status);
-void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			 u8 addr_type, u8 status);
+void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn,
+			 u8 status);
 void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
 void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
 				  u8 status);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 323d397b0e92..d083117ee36c 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -106,8 +106,7 @@ void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status)
 	 * where a timeout + cancel does indicate an actual failure.
 	 */
 	if (status && status != HCI_ERROR_UNKNOWN_CONN_ID)
-		mgmt_connect_failed(hdev, &conn->dst, conn->type,
-				    conn->dst_type, status);
+		mgmt_connect_failed(hdev, conn, status);
 
 	/* The connection attempt was doing scan for new RPA, and is
 	 * in scan phase. If params are not associated with any other
@@ -1249,8 +1248,7 @@ void hci_conn_failed(struct hci_conn *conn, u8 status)
 		hci_le_conn_failed(conn, status);
 		break;
 	case ACL_LINK:
-		mgmt_connect_failed(hdev, &conn->dst, conn->type,
-				    conn->dst_type, status);
+		mgmt_connect_failed(hdev, conn, status);
 		break;
 	}
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 279902e8bd8a..e4f564d6f6fb 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -9779,13 +9779,18 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	mgmt_pending_remove(cmd);
 }
 
-void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
-			 u8 addr_type, u8 status)
+void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, u8 status)
 {
 	struct mgmt_ev_connect_failed ev;
 
-	bacpy(&ev.addr.bdaddr, bdaddr);
-	ev.addr.type = link_to_bdaddr(link_type, addr_type);
+	if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) {
+		mgmt_device_disconnected(hdev, &conn->dst, conn->type,
+					 conn->dst_type, status, true);
+		return;
+	}
+
+	bacpy(&ev.addr.bdaddr, &conn->dst);
+	ev.addr.type = link_to_bdaddr(conn->type, conn->dst_type);
 	ev.status = mgmt_status(status);
 
 	mgmt_event(MGMT_EV_CONNECT_FAILED, hdev, &ev, sizeof(ev), NULL);
-- 
cgit v1.3-3-g829e


From a1f1c24368ec9b1d2bbc77075d2ba340ea9d0a83 Mon Sep 17 00:00:00 2001
From: Justin Stitt <justinstitt@google.com>
Date: Thu, 5 Sep 2024 15:54:40 -0700
Subject: Bluetooth: replace deprecated strncpy with strscpy_pad

strncpy() is deprecated for use on NUL-terminated destination strings [0]
and as such we should prefer more robust and less ambiguous string interfaces.

The CAPI (part II) [1] states that the manufacturer id should be a
"zero-terminated ASCII string" and should "always [be] zero-terminated."

Much the same for the serial number: "The serial number, a seven-digit
number coded as a zero-terminated ASCII string".

Along with this, its clear the original author intended for these
buffers to be NUL-padded as well. To meet the specification as well as
properly NUL-pad, use strscpy_pad().

In doing this, an opportunity to simplify this code is also present.
Remove the min_t() and combine the length check into the main if.

Link: https://www.kernel.org/doc/html/latest/process/deprecated.html#strncpy-on-nul-terminated-strings [0]
Link: https://capi.org/downloads.html [1]
Link: https://manpages.debian.org/testing/linux-manual-4.8/strscpy.9.en.html
Link: https://github.com/KSPP/linux/issues/90
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Justin Stitt <justinstitt@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/cmtp/capi.c | 32 ++++++++------------------------
 1 file changed, 8 insertions(+), 24 deletions(-)

diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c
index f3bedc3b613a..884703fda979 100644
--- a/net/bluetooth/cmtp/capi.c
+++ b/net/bluetooth/cmtp/capi.c
@@ -248,18 +248,10 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s
 			break;
 
 		case CAPI_FUNCTION_GET_MANUFACTURER:
-			if (skb->len < CAPI_MSG_BASELEN + 15)
-				break;
-
-			if (!info && ctrl) {
-				int len = min_t(uint, CAPI_MANUFACTURER_LEN,
-						skb->data[CAPI_MSG_BASELEN + 14]);
-
-				memset(ctrl->manu, 0, CAPI_MANUFACTURER_LEN);
-				strncpy(ctrl->manu,
-					skb->data + CAPI_MSG_BASELEN + 15, len);
-			}
-
+			if (!info && ctrl && skb->len > CAPI_MSG_BASELEN + 14)
+				strscpy_pad(ctrl->manu,
+					    skb->data + CAPI_MSG_BASELEN + 15,
+					    skb->data[CAPI_MSG_BASELEN + 14]);
 			break;
 
 		case CAPI_FUNCTION_GET_VERSION:
@@ -276,18 +268,10 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s
 			break;
 
 		case CAPI_FUNCTION_GET_SERIAL_NUMBER:
-			if (skb->len < CAPI_MSG_BASELEN + 17)
-				break;
-
-			if (!info && ctrl) {
-				int len = min_t(uint, CAPI_SERIAL_LEN,
-						skb->data[CAPI_MSG_BASELEN + 16]);
-
-				memset(ctrl->serial, 0, CAPI_SERIAL_LEN);
-				strncpy(ctrl->serial,
-					skb->data + CAPI_MSG_BASELEN + 17, len);
-			}
-
+			if (!info && ctrl && skb->len > CAPI_MSG_BASELEN + 16)
+				strscpy_pad(ctrl->serial,
+					    skb->data + CAPI_MSG_BASELEN + 17,
+					    skb->data[CAPI_MSG_BASELEN + 16]);
 			break;
 		}
 
-- 
cgit v1.3-3-g829e


From 0023d340ba86cfe50b935829a73adea57ec2c629 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 10 Sep 2024 10:22:36 -0400
Subject: Bluetooth: CMTP: Mark BT_CMTP as DEPRECATED

This marks BT_CMTP as DEPRECATED in preparation to get it removed.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/cmtp/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/cmtp/Kconfig b/net/bluetooth/cmtp/Kconfig
index c8337786da6b..34e923466236 100644
--- a/net/bluetooth/cmtp/Kconfig
+++ b/net/bluetooth/cmtp/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config BT_CMTP
-	tristate "CMTP protocol support"
-	depends on BT_BREDR && ISDN_CAPI
+	tristate "CMTP protocol support (DEPRECATED)"
+	depends on BT_BREDR && ISDN_CAPI && DEPRECATED
 	help
 	  CMTP (CAPI Message Transport Protocol) is a transport layer
 	  for CAPI messages.  CMTP is required for the Bluetooth Common
-- 
cgit v1.3-3-g829e


From cfbfeee61582e638770a1a10deef866c9adb38f5 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 16 Aug 2023 12:05:00 -0700
Subject: Bluetooth: hci_sync: Ignore errors from HCI_OP_REMOTE_NAME_REQ_CANCEL

This ignores errors from HCI_OP_REMOTE_NAME_REQ_CANCEL since it
shouldn't interfere with the stopping of discovery and in certain
conditions it seems to be failing.

Link: https://github.com/bluez/bluez/issues/575
Fixes: d0b137062b2d ("Bluetooth: hci_sync: Rework init stages")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 5533e6f561b3..40ccdef168d7 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5380,7 +5380,10 @@ int hci_stop_discovery_sync(struct hci_dev *hdev)
 		if (!e)
 			return 0;
 
-		return hci_remote_name_cancel_sync(hdev, &e->data.bdaddr);
+		/* Ignore cancel errors since it should interfere with stopping
+		 * of the discovery.
+		 */
+		hci_remote_name_cancel_sync(hdev, &e->data.bdaddr);
 	}
 
 	return 0;
-- 
cgit v1.3-3-g829e


From 070a5e6295e88a2b75cbfef04ff8b4ec05775e6d Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:06 +0800
Subject: net: stmmac: move stmmac_fpe_cfg to stmmac_priv data

By moving the fpe_cfg field to the stmmac_priv data, stmmac_fpe_cfg
becomes platform-data eventually, instead of a run-time config.

Suggested-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Reviewed-by: Serge Semin <fancer.lancer@gmail.com>
Link: https://patch.msgid.link/d9b3d7ecb308c5e39778a4c8ae9df288a2754379.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.h        |  2 ++
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      | 30 ++++++++++++++++++++++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 20 +++++++--------
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c   | 16 +++---------
 include/linux/stmmac.h                            | 28 ---------------------
 5 files changed, 44 insertions(+), 52 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 7e90f34b8c88..68574798c03f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -28,6 +28,8 @@
 struct stmmac_extra_stats;
 struct stmmac_priv;
 struct stmmac_safety_stats;
+struct stmmac_fpe_cfg;
+enum stmmac_mpacket_type;
 struct dma_desc;
 struct dma_extended_desc;
 struct dma_edesc;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index b23b920eedb1..458d6b16ce21 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -146,6 +146,33 @@ struct stmmac_channel {
 	u32 index;
 };
 
+/* FPE link state */
+enum stmmac_fpe_state {
+	FPE_STATE_OFF = 0,
+	FPE_STATE_CAPABLE = 1,
+	FPE_STATE_ENTERING_ON = 2,
+	FPE_STATE_ON = 3,
+};
+
+/* FPE link-partner hand-shaking mPacket type */
+enum stmmac_mpacket_type {
+	MPACKET_VERIFY = 0,
+	MPACKET_RESPONSE = 1,
+};
+
+enum stmmac_fpe_task_state_t {
+	__FPE_REMOVING,
+	__FPE_TASK_SCHED,
+};
+
+struct stmmac_fpe_cfg {
+	bool enable;				/* FPE enable */
+	bool hs_enable;				/* FPE handshake enable */
+	enum stmmac_fpe_state lp_fpe_state;	/* Link Partner FPE state */
+	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
+	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
+};
+
 struct stmmac_tc_entry {
 	bool in_use;
 	bool in_hw;
@@ -339,11 +366,12 @@ struct stmmac_priv {
 	struct workqueue_struct *wq;
 	struct work_struct service_task;
 
-	/* Workqueue for handling FPE hand-shaking */
+	/* Frame Preemption feature (FPE) */
 	unsigned long fpe_task_state;
 	struct workqueue_struct *fpe_wq;
 	struct work_struct fpe_task;
 	char wq_name[IFNAMSIZ + 4];
+	struct stmmac_fpe_cfg fpe_cfg;
 
 	/* TC Handling */
 	unsigned int tc_entries_max;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d9fca8d1227c..529fe31f8b04 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -968,7 +968,7 @@ static void stmmac_mac_config(struct phylink_config *config, unsigned int mode,
 
 static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
 {
-	struct stmmac_fpe_cfg *fpe_cfg = priv->plat->fpe_cfg;
+	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
 	enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state;
 	enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state;
 	bool *hs_enable = &fpe_cfg->hs_enable;
@@ -3536,7 +3536,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	if (priv->dma_cap.fpesel) {
 		stmmac_fpe_start_wq(priv);
 
-		if (priv->plat->fpe_cfg->enable)
+		if (priv->fpe_cfg.enable)
 			stmmac_fpe_handshake(priv, true);
 	}
 
@@ -5982,7 +5982,7 @@ static int stmmac_set_features(struct net_device *netdev,
 
 static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 {
-	struct stmmac_fpe_cfg *fpe_cfg = priv->plat->fpe_cfg;
+	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
 	enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state;
 	enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state;
 	bool *hs_enable = &fpe_cfg->hs_enable;
@@ -7381,7 +7381,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 {
 	struct stmmac_priv *priv = container_of(work, struct stmmac_priv,
 						fpe_task);
-	struct stmmac_fpe_cfg *fpe_cfg = priv->plat->fpe_cfg;
+	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
 	enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state;
 	enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state;
 	bool *hs_enable = &fpe_cfg->hs_enable;
@@ -7427,17 +7427,17 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 
 void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable)
 {
-	if (priv->plat->fpe_cfg->hs_enable != enable) {
+	if (priv->fpe_cfg.hs_enable != enable) {
 		if (enable) {
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
-						priv->plat->fpe_cfg,
+						&priv->fpe_cfg,
 						MPACKET_VERIFY);
 		} else {
-			priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF;
-			priv->plat->fpe_cfg->lp_fpe_state = FPE_STATE_OFF;
+			priv->fpe_cfg.lo_fpe_state = FPE_STATE_OFF;
+			priv->fpe_cfg.lp_fpe_state = FPE_STATE_OFF;
 		}
 
-		priv->plat->fpe_cfg->hs_enable = enable;
+		priv->fpe_cfg.hs_enable = enable;
 	}
 }
 
@@ -7898,7 +7898,7 @@ int stmmac_suspend(struct device *dev)
 	if (priv->dma_cap.fpesel) {
 		/* Disable FPE */
 		stmmac_fpe_configure(priv, priv->ioaddr,
-				     priv->plat->fpe_cfg,
+				     &priv->fpe_cfg,
 				     priv->plat->tx_queues_to_use,
 				     priv->plat->rx_queues_to_use, false);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 996f2bcd07a2..9cc41ed01882 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -282,16 +282,6 @@ static int tc_init(struct stmmac_priv *priv)
 	if (ret)
 		return -ENOMEM;
 
-	if (!priv->plat->fpe_cfg) {
-		priv->plat->fpe_cfg = devm_kzalloc(priv->device,
-						   sizeof(*priv->plat->fpe_cfg),
-						   GFP_KERNEL);
-		if (!priv->plat->fpe_cfg)
-			return -ENOMEM;
-	} else {
-		memset(priv->plat->fpe_cfg, 0, sizeof(*priv->plat->fpe_cfg));
-	}
-
 	/* Fail silently as we can still use remaining features, e.g. CBS */
 	if (!dma_cap->frpsel)
 		return 0;
@@ -1076,7 +1066,7 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 	/* Actual FPE register configuration will be done after FPE handshake
 	 * is success.
 	 */
-	priv->plat->fpe_cfg->enable = fpe;
+	priv->fpe_cfg.enable = fpe;
 
 	ret = stmmac_est_configure(priv, priv, priv->est,
 				   priv->plat->clk_ptp_rate);
@@ -1109,9 +1099,9 @@ disable:
 		mutex_unlock(&priv->est_lock);
 	}
 
-	priv->plat->fpe_cfg->enable = false;
+	priv->fpe_cfg.enable = false;
 	stmmac_fpe_configure(priv, priv->ioaddr,
-			     priv->plat->fpe_cfg,
+			     &priv->fpe_cfg,
 			     priv->plat->tx_queues_to_use,
 			     priv->plat->rx_queues_to_use,
 			     false);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 338991c08f00..d79ff252cfdc 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -138,33 +138,6 @@ struct stmmac_txq_cfg {
 	int tbs_en;
 };
 
-/* FPE link state */
-enum stmmac_fpe_state {
-	FPE_STATE_OFF = 0,
-	FPE_STATE_CAPABLE = 1,
-	FPE_STATE_ENTERING_ON = 2,
-	FPE_STATE_ON = 3,
-};
-
-/* FPE link-partner hand-shaking mPacket type */
-enum stmmac_mpacket_type {
-	MPACKET_VERIFY = 0,
-	MPACKET_RESPONSE = 1,
-};
-
-enum stmmac_fpe_task_state_t {
-	__FPE_REMOVING,
-	__FPE_TASK_SCHED,
-};
-
-struct stmmac_fpe_cfg {
-	bool enable;				/* FPE enable */
-	bool hs_enable;				/* FPE handshake enable */
-	enum stmmac_fpe_state lp_fpe_state;	/* Link Partner FPE state */
-	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
-	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
-};
-
 struct stmmac_safety_feature_cfg {
 	u32 tsoee;
 	u32 mrxpee;
@@ -232,7 +205,6 @@ struct plat_stmmacenet_data {
 	struct fwnode_handle *port_node;
 	struct device_node *mdio_node;
 	struct stmmac_dma_cfg *dma_cfg;
-	struct stmmac_fpe_cfg *fpe_cfg;
 	struct stmmac_safety_feature_cfg *safety_feat_cfg;
 	int clk_csr;
 	int has_gmac;
-- 
cgit v1.3-3-g829e


From 59dd7fc932e54083b0e7d3e1f4ddf6ba3a158b0e Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:07 +0800
Subject: net: stmmac: drop stmmac_fpe_handshake

ethtool --set-mm can trigger FPE verification process by calling
stmmac_fpe_send_mpacket, stmmac_fpe_handshake should be gone.

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/42018b1a15eb3ced567fd6a73798c7cd4e08799a.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      |  1 -
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 23 +----------------------
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c   |  8 --------
 3 files changed, 1 insertion(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 458d6b16ce21..3ad182ef8e97 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -425,7 +425,6 @@ bool stmmac_eee_init(struct stmmac_priv *priv);
 int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt);
 int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size);
 int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled);
-void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable);
 
 static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv)
 {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 529fe31f8b04..3072ad33b105 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3533,13 +3533,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 
 	stmmac_set_hw_vlan_mode(priv, priv->hw);
 
-	if (priv->dma_cap.fpesel) {
+	if (priv->dma_cap.fpesel)
 		stmmac_fpe_start_wq(priv);
 
-		if (priv->fpe_cfg.enable)
-			stmmac_fpe_handshake(priv, true);
-	}
-
 	return 0;
 }
 
@@ -7425,22 +7421,6 @@ static void stmmac_fpe_lp_task(struct work_struct *work)
 	clear_bit(__FPE_TASK_SCHED, &priv->fpe_task_state);
 }
 
-void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable)
-{
-	if (priv->fpe_cfg.hs_enable != enable) {
-		if (enable) {
-			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
-						&priv->fpe_cfg,
-						MPACKET_VERIFY);
-		} else {
-			priv->fpe_cfg.lo_fpe_state = FPE_STATE_OFF;
-			priv->fpe_cfg.lp_fpe_state = FPE_STATE_OFF;
-		}
-
-		priv->fpe_cfg.hs_enable = enable;
-	}
-}
-
 static int stmmac_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
 {
 	const struct stmmac_xdp_buff *ctx = (void *)_ctx;
@@ -7902,7 +7882,6 @@ int stmmac_suspend(struct device *dev)
 				     priv->plat->tx_queues_to_use,
 				     priv->plat->rx_queues_to_use, false);
 
-		stmmac_fpe_handshake(priv, false);
 		stmmac_fpe_stop_wq(priv);
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 9cc41ed01882..b0cc45331ff7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1078,11 +1078,6 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 
 	netdev_info(priv->dev, "configured EST\n");
 
-	if (fpe) {
-		stmmac_fpe_handshake(priv, true);
-		netdev_info(priv->dev, "start FPE handshake\n");
-	}
-
 	return 0;
 
 disable:
@@ -1107,9 +1102,6 @@ disable:
 			     false);
 	netdev_info(priv->dev, "disabled FPE\n");
 
-	stmmac_fpe_handshake(priv, false);
-	netdev_info(priv->dev, "stop FPE handshake\n");
-
 	return ret;
 }
 
-- 
cgit v1.3-3-g829e


From 8d43e99a5a03ae8307b2d588ec080308f35ebc9e Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:08 +0800
Subject: net: stmmac: refactor FPE verification process

Drop driver defined stmmac_fpe_state, and switch to common
ethtool_mm_verify_status for local TX verification status.

Local side and remote side verification processes are completely
independent. There is no reason at all to keep a local state and
a remote state.

Add a spinlock to avoid races among ISR, timer, link update
and register configuration.

This patch is based on Vladimir Oltean's proposal.

Vladimir Oltean says:

  ====================
  In the INITIAL state, the timer sends MPACKET_VERIFY. Eventually the
  stmmac_fpe_event_status() IRQ fires and advances the state to VERIFYING,
  then rearms the timer after verify_time ms. If a subsequent IRQ comes in
  and modifies the state to SUCCEEDED after getting MPACKET_RESPONSE, the
  timer sees this. It must enable the EFPE bit now. Otherwise, it
  decrements the verify_limit counter and tries again. Eventually it
  moves the status to FAILED, from which the IRQ cannot move it anywhere
  else, except for another stmmac_fpe_apply() call.
  ====================

Co-developed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/151f86c8428eba967039718c6bf90a7d841e703b.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c  |   4 -
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c       |  19 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac5.h       |   2 +-
 .../net/ethernet/stmicro/stmmac/dwxgmac2_core.c    |   9 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |   2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac.h       |  36 ++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  | 256 ++++++++++-----------
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c    |   8 +-
 8 files changed, 166 insertions(+), 170 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 31c387cc5f26..7947b1212a2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -58,10 +58,6 @@ static void dwmac4_core_init(struct mac_device_info *hw,
 	if (hw->pcs)
 		value |= GMAC_PCS_IRQ_DEFAULT;
 
-	/* Enable FPE interrupt */
-	if ((GMAC_HW_FEAT_FPESEL & readl(ioaddr + GMAC_HW_FEATURE3)) >> 26)
-		value |= GMAC_INT_FPE_EN;
-
 	writel(value, ioaddr + GMAC_INT_EN);
 
 	if (GMAC_INT_DEFAULT_ENABLE & GMAC_INT_TSIE)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index e02cebc3f1b7..850cfc4df6eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -575,11 +575,11 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index,
 
 void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
 			  u32 num_txq, u32 num_rxq,
-			  bool enable)
+			  bool tx_enable, bool pmac_enable)
 {
 	u32 value;
 
-	if (enable) {
+	if (tx_enable) {
 		cfg->fpe_csr = EFPE;
 		value = readl(ioaddr + GMAC_RXQ_CTRL1);
 		value &= ~GMAC_RXQCTRL_FPRQ;
@@ -589,6 +589,21 @@ void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
 		cfg->fpe_csr = 0;
 	}
 	writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS);
+
+	value = readl(ioaddr + GMAC_INT_EN);
+
+	if (pmac_enable) {
+		if (!(value & GMAC_INT_FPE_EN)) {
+			/* Dummy read to clear any pending masked interrupts */
+			readl(ioaddr + MAC_FPE_CTRL_STS);
+
+			value |= GMAC_INT_FPE_EN;
+		}
+	} else {
+		value &= ~GMAC_INT_FPE_EN;
+	}
+
+	writel(value, ioaddr + GMAC_INT_EN);
 }
 
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index bf33a51d229e..c3031c1357d0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -104,7 +104,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index,
 			   u32 sub_second_inc, u32 systime_flags);
 void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
 			  u32 num_txq, u32 num_rxq,
-			  bool enable);
+			  bool tx_enable, bool pmac_enable);
 void dwmac5_fpe_send_mpacket(void __iomem *ioaddr,
 			     struct stmmac_fpe_cfg *cfg,
 			     enum stmmac_mpacket_type type);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index cbf2dd976ab1..f519d43738b0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -1504,13 +1504,14 @@ static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en,
 	writel(value, ioaddr + XGMAC_RX_CONFIG);
 }
 
-static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
-				   u32 num_txq,
-				   u32 num_rxq, bool enable)
+static void dwxgmac3_fpe_configure(void __iomem *ioaddr,
+				   struct stmmac_fpe_cfg *cfg,
+				   u32 num_txq, u32 num_rxq,
+				   bool tx_enable, bool pmac_enable)
 {
 	u32 value;
 
-	if (!enable) {
+	if (!tx_enable) {
 		value = readl(ioaddr + XGMAC_FPE_CTRL_STS);
 
 		value &= ~XGMAC_EFPE;
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 68574798c03f..4942fc398ea6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -421,7 +421,7 @@ struct stmmac_ops {
 	void (*set_arp_offload)(struct mac_device_info *hw, bool en, u32 addr);
 	void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
 			      u32 num_txq, u32 num_rxq,
-			      bool enable);
+			      bool tx_enable, bool pmac_enable);
 	void (*fpe_send_mpacket)(void __iomem *ioaddr,
 				 struct stmmac_fpe_cfg *cfg,
 				 enum stmmac_mpacket_type type);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 3ad182ef8e97..ea135203ff2e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -146,31 +146,30 @@ struct stmmac_channel {
 	u32 index;
 };
 
-/* FPE link state */
-enum stmmac_fpe_state {
-	FPE_STATE_OFF = 0,
-	FPE_STATE_CAPABLE = 1,
-	FPE_STATE_ENTERING_ON = 2,
-	FPE_STATE_ON = 3,
-};
-
 /* FPE link-partner hand-shaking mPacket type */
 enum stmmac_mpacket_type {
 	MPACKET_VERIFY = 0,
 	MPACKET_RESPONSE = 1,
 };
 
-enum stmmac_fpe_task_state_t {
-	__FPE_REMOVING,
-	__FPE_TASK_SCHED,
-};
+#define STMMAC_FPE_MM_MAX_VERIFY_RETRIES	3
+#define STMMAC_FPE_MM_MAX_VERIFY_TIME_MS	128
 
 struct stmmac_fpe_cfg {
-	bool enable;				/* FPE enable */
-	bool hs_enable;				/* FPE handshake enable */
-	enum stmmac_fpe_state lp_fpe_state;	/* Link Partner FPE state */
-	enum stmmac_fpe_state lo_fpe_state;	/* Local station FPE state */
+	/* Serialize access to MAC Merge state between ethtool requests
+	 * and link state updates.
+	 */
+	spinlock_t lock;
+
 	u32 fpe_csr;				/* MAC_FPE_CTRL_STS reg cache */
+
+	enum ethtool_mm_verify_status status;
+	struct timer_list verify_timer;
+	bool verify_enabled;
+	int verify_retries;
+	bool pmac_enabled;
+	u32 verify_time;
+	bool tx_enabled;
 };
 
 struct stmmac_tc_entry {
@@ -367,10 +366,6 @@ struct stmmac_priv {
 	struct work_struct service_task;
 
 	/* Frame Preemption feature (FPE) */
-	unsigned long fpe_task_state;
-	struct workqueue_struct *fpe_wq;
-	struct work_struct fpe_task;
-	char wq_name[IFNAMSIZ + 4];
 	struct stmmac_fpe_cfg fpe_cfg;
 
 	/* TC Handling */
@@ -425,6 +420,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv);
 int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt);
 int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size);
 int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled);
+void stmmac_fpe_apply(struct stmmac_priv *priv);
 
 static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv)
 {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3072ad33b105..5a38bdb3f535 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -969,17 +969,30 @@ static void stmmac_mac_config(struct phylink_config *config, unsigned int mode,
 static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up)
 {
 	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state;
-	enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state;
-	bool *hs_enable = &fpe_cfg->hs_enable;
+	unsigned long flags;
 
-	if (is_up && *hs_enable) {
-		stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg,
-					MPACKET_VERIFY);
+	timer_shutdown_sync(&fpe_cfg->verify_timer);
+
+	spin_lock_irqsave(&fpe_cfg->lock, flags);
+
+	if (is_up && fpe_cfg->pmac_enabled) {
+		/* VERIFY process requires pmac enabled when NIC comes up */
+		stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg,
+				     priv->plat->tx_queues_to_use,
+				     priv->plat->rx_queues_to_use,
+				     false, true);
+
+		/* New link => maybe new partner => new verification process */
+		stmmac_fpe_apply(priv);
 	} else {
-		*lo_state = FPE_STATE_OFF;
-		*lp_state = FPE_STATE_OFF;
+		/* No link => turn off EFPE */
+		stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg,
+				     priv->plat->tx_queues_to_use,
+				     priv->plat->rx_queues_to_use,
+				     false, false);
 	}
+
+	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
 }
 
 static void stmmac_mac_link_down(struct phylink_config *config,
@@ -3358,27 +3371,6 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv)
 	}
 }
 
-static int stmmac_fpe_start_wq(struct stmmac_priv *priv)
-{
-	char *name;
-
-	clear_bit(__FPE_TASK_SCHED, &priv->fpe_task_state);
-	clear_bit(__FPE_REMOVING,  &priv->fpe_task_state);
-
-	name = priv->wq_name;
-	sprintf(name, "%s-fpe", priv->dev->name);
-
-	priv->fpe_wq = create_singlethread_workqueue(name);
-	if (!priv->fpe_wq) {
-		netdev_err(priv->dev, "%s: Failed to create workqueue\n", name);
-
-		return -ENOMEM;
-	}
-	netdev_info(priv->dev, "FPE workqueue start");
-
-	return 0;
-}
-
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
@@ -3533,9 +3525,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 
 	stmmac_set_hw_vlan_mode(priv, priv->hw);
 
-	if (priv->dma_cap.fpesel)
-		stmmac_fpe_start_wq(priv);
-
 	return 0;
 }
 
@@ -4032,18 +4021,6 @@ static int stmmac_open(struct net_device *dev)
 	return ret;
 }
 
-static void stmmac_fpe_stop_wq(struct stmmac_priv *priv)
-{
-	set_bit(__FPE_REMOVING, &priv->fpe_task_state);
-
-	if (priv->fpe_wq) {
-		destroy_workqueue(priv->fpe_wq);
-		priv->fpe_wq = NULL;
-	}
-
-	netdev_info(priv->dev, "FPE workqueue stop");
-}
-
 /**
  *  stmmac_release - close entry point of the driver
  *  @dev : device pointer.
@@ -4091,10 +4068,10 @@ static int stmmac_release(struct net_device *dev)
 
 	stmmac_release_ptp(priv);
 
-	pm_runtime_put(priv->device);
-
 	if (priv->dma_cap.fpesel)
-		stmmac_fpe_stop_wq(priv);
+		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
+
+	pm_runtime_put(priv->device);
 
 	return 0;
 }
@@ -5979,44 +5956,30 @@ static int stmmac_set_features(struct net_device *netdev,
 static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status)
 {
 	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state;
-	enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state;
-	bool *hs_enable = &fpe_cfg->hs_enable;
 
-	if (status == FPE_EVENT_UNKNOWN || !*hs_enable)
-		return;
+	/* This is interrupt context, just spin_lock() */
+	spin_lock(&fpe_cfg->lock);
 
-	/* If LP has sent verify mPacket, LP is FPE capable */
-	if ((status & FPE_EVENT_RVER) == FPE_EVENT_RVER) {
-		if (*lp_state < FPE_STATE_CAPABLE)
-			*lp_state = FPE_STATE_CAPABLE;
+	if (!fpe_cfg->pmac_enabled || status == FPE_EVENT_UNKNOWN)
+		goto unlock_out;
 
-		/* If user has requested FPE enable, quickly response */
-		if (*hs_enable)
-			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
-						fpe_cfg,
-						MPACKET_RESPONSE);
-	}
-
-	/* If Local has sent verify mPacket, Local is FPE capable */
-	if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER) {
-		if (*lo_state < FPE_STATE_CAPABLE)
-			*lo_state = FPE_STATE_CAPABLE;
-	}
+	/* LP has sent verify mPacket */
+	if ((status & FPE_EVENT_RVER) == FPE_EVENT_RVER)
+		stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg,
+					MPACKET_RESPONSE);
 
-	/* If LP has sent response mPacket, LP is entering FPE ON */
-	if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP)
-		*lp_state = FPE_STATE_ENTERING_ON;
+	/* Local has sent verify mPacket */
+	if ((status & FPE_EVENT_TVER) == FPE_EVENT_TVER &&
+	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED)
+		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING;
 
-	/* If Local has sent response mPacket, Local is entering FPE ON */
-	if ((status & FPE_EVENT_TRSP) == FPE_EVENT_TRSP)
-		*lo_state = FPE_STATE_ENTERING_ON;
+	/* LP has sent response mPacket */
+	if ((status & FPE_EVENT_RRSP) == FPE_EVENT_RRSP &&
+	    fpe_cfg->status == ETHTOOL_MM_VERIFY_STATUS_VERIFYING)
+		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED;
 
-	if (!test_bit(__FPE_REMOVING, &priv->fpe_task_state) &&
-	    !test_and_set_bit(__FPE_TASK_SCHED, &priv->fpe_task_state) &&
-	    priv->fpe_wq) {
-		queue_work(priv->fpe_wq, &priv->fpe_task);
-	}
+unlock_out:
+	spin_unlock(&fpe_cfg->lock);
 }
 
 static void stmmac_common_interrupt(struct stmmac_priv *priv)
@@ -7372,53 +7335,88 @@ int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size)
 	return ret;
 }
 
-#define SEND_VERIFY_MPAKCET_FMT "Send Verify mPacket lo_state=%d lp_state=%d\n"
-static void stmmac_fpe_lp_task(struct work_struct *work)
+/**
+ * stmmac_fpe_verify_timer - Timer for MAC Merge verification
+ * @t:  timer_list struct containing private info
+ *
+ * Verify the MAC Merge capability in the local TX direction, by
+ * transmitting Verify mPackets up to 3 times. Wait until link
+ * partner responds with a Response mPacket, otherwise fail.
+ */
+static void stmmac_fpe_verify_timer(struct timer_list *t)
 {
-	struct stmmac_priv *priv = container_of(work, struct stmmac_priv,
-						fpe_task);
-	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
-	enum stmmac_fpe_state *lo_state = &fpe_cfg->lo_fpe_state;
-	enum stmmac_fpe_state *lp_state = &fpe_cfg->lp_fpe_state;
-	bool *hs_enable = &fpe_cfg->hs_enable;
-	bool *enable = &fpe_cfg->enable;
-	int retries = 20;
-
-	while (retries-- > 0) {
-		/* Bail out immediately if FPE handshake is OFF */
-		if (*lo_state == FPE_STATE_OFF || !*hs_enable)
-			break;
-
-		if (*lo_state == FPE_STATE_ENTERING_ON &&
-		    *lp_state == FPE_STATE_ENTERING_ON) {
-			stmmac_fpe_configure(priv, priv->ioaddr,
-					     fpe_cfg,
-					     priv->plat->tx_queues_to_use,
-					     priv->plat->rx_queues_to_use,
-					     *enable);
-
-			netdev_info(priv->dev, "configured FPE\n");
+	struct stmmac_fpe_cfg *fpe_cfg = from_timer(fpe_cfg, t, verify_timer);
+	struct stmmac_priv *priv = container_of(fpe_cfg, struct stmmac_priv,
+						fpe_cfg);
+	unsigned long flags;
+	bool rearm = false;
 
-			*lo_state = FPE_STATE_ON;
-			*lp_state = FPE_STATE_ON;
-			netdev_info(priv->dev, "!!! BOTH FPE stations ON\n");
-			break;
-		}
+	spin_lock_irqsave(&fpe_cfg->lock, flags);
 
-		if ((*lo_state == FPE_STATE_CAPABLE ||
-		     *lo_state == FPE_STATE_ENTERING_ON) &&
-		     *lp_state != FPE_STATE_ON) {
-			netdev_info(priv->dev, SEND_VERIFY_MPAKCET_FMT,
-				    *lo_state, *lp_state);
+	switch (fpe_cfg->status) {
+	case ETHTOOL_MM_VERIFY_STATUS_INITIAL:
+	case ETHTOOL_MM_VERIFY_STATUS_VERIFYING:
+		if (fpe_cfg->verify_retries != 0) {
 			stmmac_fpe_send_mpacket(priv, priv->ioaddr,
-						fpe_cfg,
-						MPACKET_VERIFY);
+						fpe_cfg, MPACKET_VERIFY);
+			rearm = true;
+		} else {
+			fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_FAILED;
 		}
-		/* Sleep then retry */
-		msleep(500);
+
+		fpe_cfg->verify_retries--;
+		break;
+
+	case ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED:
+		stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg,
+				     priv->plat->tx_queues_to_use,
+				     priv->plat->rx_queues_to_use,
+				     true, true);
+		break;
+
+	default:
+		break;
 	}
 
-	clear_bit(__FPE_TASK_SCHED, &priv->fpe_task_state);
+	if (rearm) {
+		mod_timer(&fpe_cfg->verify_timer,
+			  jiffies + msecs_to_jiffies(fpe_cfg->verify_time));
+	}
+
+	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
+}
+
+static void stmmac_fpe_verify_timer_arm(struct stmmac_fpe_cfg *fpe_cfg)
+{
+	if (fpe_cfg->pmac_enabled && fpe_cfg->tx_enabled &&
+	    fpe_cfg->verify_enabled &&
+	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_FAILED &&
+	    fpe_cfg->status != ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED) {
+		timer_setup(&fpe_cfg->verify_timer, stmmac_fpe_verify_timer, 0);
+		mod_timer(&fpe_cfg->verify_timer, jiffies);
+	}
+}
+
+void stmmac_fpe_apply(struct stmmac_priv *priv)
+{
+	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
+
+	/* If verification is disabled, configure FPE right away.
+	 * Otherwise let the timer code do it.
+	 */
+	if (!fpe_cfg->verify_enabled) {
+		stmmac_fpe_configure(priv, priv->ioaddr, fpe_cfg,
+				     priv->plat->tx_queues_to_use,
+				     priv->plat->rx_queues_to_use,
+				     fpe_cfg->tx_enabled,
+				     fpe_cfg->pmac_enabled);
+	} else {
+		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_INITIAL;
+		fpe_cfg->verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES;
+
+		if (netif_running(priv->dev))
+			stmmac_fpe_verify_timer_arm(fpe_cfg);
+	}
 }
 
 static int stmmac_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
@@ -7535,9 +7533,6 @@ int stmmac_dvr_probe(struct device *device,
 
 	INIT_WORK(&priv->service_task, stmmac_service_task);
 
-	/* Initialize Link Partner FPE workqueue */
-	INIT_WORK(&priv->fpe_task, stmmac_fpe_lp_task);
-
 	/* Override with kernel parameters if supplied XXX CRS XXX
 	 * this needs to have multiple instances
 	 */
@@ -7702,6 +7697,12 @@ int stmmac_dvr_probe(struct device *device,
 
 	mutex_init(&priv->lock);
 
+	priv->fpe_cfg.verify_retries = STMMAC_FPE_MM_MAX_VERIFY_RETRIES;
+	priv->fpe_cfg.verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS;
+	priv->fpe_cfg.status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
+	timer_setup(&priv->fpe_cfg.verify_timer, stmmac_fpe_verify_timer, 0);
+	spin_lock_init(&priv->fpe_cfg.lock);
+
 	/* If a specific clk_csr value is passed from the platform
 	 * this means that the CSR Clock Range selection cannot be
 	 * changed at run-time and it is fixed. Viceversa the driver'll try to
@@ -7875,15 +7876,8 @@ int stmmac_suspend(struct device *dev)
 	}
 	rtnl_unlock();
 
-	if (priv->dma_cap.fpesel) {
-		/* Disable FPE */
-		stmmac_fpe_configure(priv, priv->ioaddr,
-				     &priv->fpe_cfg,
-				     priv->plat->tx_queues_to_use,
-				     priv->plat->rx_queues_to_use, false);
-
-		stmmac_fpe_stop_wq(priv);
-	}
+	if (priv->dma_cap.fpesel)
+		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
 
 	priv->speed = SPEED_UNKNOWN;
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index b0cc45331ff7..a58282d6458c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1063,11 +1063,6 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	/* Actual FPE register configuration will be done after FPE handshake
-	 * is success.
-	 */
-	priv->fpe_cfg.enable = fpe;
-
 	ret = stmmac_est_configure(priv, priv, priv->est,
 				   priv->plat->clk_ptp_rate);
 	mutex_unlock(&priv->est_lock);
@@ -1094,12 +1089,11 @@ disable:
 		mutex_unlock(&priv->est_lock);
 	}
 
-	priv->fpe_cfg.enable = false;
 	stmmac_fpe_configure(priv, priv->ioaddr,
 			     &priv->fpe_cfg,
 			     priv->plat->tx_queues_to_use,
 			     priv->plat->rx_queues_to_use,
-			     false);
+			     false, false);
 	netdev_info(priv->dev, "disabled FPE\n");
 
 	return ret;
-- 
cgit v1.3-3-g829e


From 0f156aceeef7bb1789d25cf7e82e561679398d38 Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:09 +0800
Subject: net: stmmac: configure FPE via ethtool-mm

Implement ethtool --show-mm and --set-mm callbacks.

NIC up/down, link up/down, suspend/resume, kselftest-ethtool_mm,
all tested okay.

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/06ed409314fe0ee37b78b800922f2c0cce762532.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c  |  4 +
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c       | 14 ++++
 drivers/net/ethernet/stmicro/stmmac/dwmac5.h       |  6 ++
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |  6 ++
 .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c   | 96 ++++++++++++++++++++++
 5 files changed, 126 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 7947b1212a2d..679efcc631f1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -1264,6 +1264,8 @@ const struct stmmac_ops dwmac410_ops = {
 	.fpe_configure = dwmac5_fpe_configure,
 	.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
 	.fpe_irq_status = dwmac5_fpe_irq_status,
+	.fpe_get_add_frag_size = dwmac5_fpe_get_add_frag_size,
+	.fpe_set_add_frag_size = dwmac5_fpe_set_add_frag_size,
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
@@ -1316,6 +1318,8 @@ const struct stmmac_ops dwmac510_ops = {
 	.fpe_configure = dwmac5_fpe_configure,
 	.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
 	.fpe_irq_status = dwmac5_fpe_irq_status,
+	.fpe_get_add_frag_size = dwmac5_fpe_get_add_frag_size,
+	.fpe_set_add_frag_size = dwmac5_fpe_set_add_frag_size,
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index 850cfc4df6eb..db7bbc50cfae 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -653,3 +653,17 @@ void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg,
 
 	writel(value, ioaddr + MAC_FPE_CTRL_STS);
 }
+
+int dwmac5_fpe_get_add_frag_size(const void __iomem *ioaddr)
+{
+	return FIELD_GET(DWMAC5_ADD_FRAG_SZ, readl(ioaddr + MTL_FPE_CTRL_STS));
+}
+
+void dwmac5_fpe_set_add_frag_size(void __iomem *ioaddr, u32 add_frag_size)
+{
+	u32 value;
+
+	value = readl(ioaddr + MTL_FPE_CTRL_STS);
+	writel(u32_replace_bits(value, add_frag_size, DWMAC5_ADD_FRAG_SZ),
+	       ioaddr + MTL_FPE_CTRL_STS);
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index c3031c1357d0..58704c15f320 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -39,6 +39,10 @@
 #define MAC_PPSx_INTERVAL(x)		(0x00000b88 + ((x) * 0x10))
 #define MAC_PPSx_WIDTH(x)		(0x00000b8c + ((x) * 0x10))
 
+#define MTL_FPE_CTRL_STS		0x00000c90
+/* Additional Fragment Size of preempted frames */
+#define DWMAC5_ADD_FRAG_SZ		GENMASK(1, 0)
+
 #define MTL_RXP_CONTROL_STATUS		0x00000ca0
 #define RXPI				BIT(31)
 #define NPE				GENMASK(23, 16)
@@ -109,5 +113,7 @@ void dwmac5_fpe_send_mpacket(void __iomem *ioaddr,
 			     struct stmmac_fpe_cfg *cfg,
 			     enum stmmac_mpacket_type type);
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev);
+int dwmac5_fpe_get_add_frag_size(const void __iomem *ioaddr);
+void dwmac5_fpe_set_add_frag_size(void __iomem *ioaddr, u32 add_frag_size);
 
 #endif /* __DWMAC5_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 4942fc398ea6..f080e271f7af 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -426,6 +426,8 @@ struct stmmac_ops {
 				 struct stmmac_fpe_cfg *cfg,
 				 enum stmmac_mpacket_type type);
 	int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev);
+	int (*fpe_get_add_frag_size)(const void __iomem *ioaddr);
+	void (*fpe_set_add_frag_size)(void __iomem *ioaddr, u32 add_frag_size);
 };
 
 #define stmmac_core_init(__priv, __args...) \
@@ -530,6 +532,10 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, fpe_send_mpacket, __args)
 #define stmmac_fpe_irq_status(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, fpe_irq_status, __args)
+#define stmmac_fpe_get_add_frag_size(__priv, __args...) \
+	stmmac_do_callback(__priv, mac, fpe_get_add_frag_size, __args)
+#define stmmac_fpe_set_add_frag_size(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mac, fpe_set_add_frag_size, __args)
 
 /* PTP and HW Timer helpers */
 struct stmmac_hwtimestamp {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index a45af300bad8..2a37592a6281 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -19,6 +19,7 @@
 #include "stmmac.h"
 #include "dwmac_dma.h"
 #include "dwxgmac2.h"
+#include "dwmac5.h"
 
 #define REG_SPACE_SIZE	0x1060
 #define GMAC4_REG_SPACE_SIZE	0x116C
@@ -1263,6 +1264,98 @@ static int stmmac_set_tunable(struct net_device *dev,
 	return ret;
 }
 
+static int stmmac_get_mm(struct net_device *ndev,
+			 struct ethtool_mm_state *state)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned long flags;
+	u32 frag_size;
+
+	if (!priv->dma_cap.fpesel)
+		return -EOPNOTSUPP;
+
+	spin_lock_irqsave(&priv->fpe_cfg.lock, flags);
+
+	state->max_verify_time = STMMAC_FPE_MM_MAX_VERIFY_TIME_MS;
+	state->verify_enabled = priv->fpe_cfg.verify_enabled;
+	state->pmac_enabled = priv->fpe_cfg.pmac_enabled;
+	state->verify_time = priv->fpe_cfg.verify_time;
+	state->tx_enabled = priv->fpe_cfg.tx_enabled;
+	state->verify_status = priv->fpe_cfg.status;
+	state->rx_min_frag_size = ETH_ZLEN;
+
+	/* FPE active if common tx_enabled and
+	 * (verification success or disabled(forced))
+	 */
+	if (state->tx_enabled &&
+	    (state->verify_status == ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED ||
+	     state->verify_status == ETHTOOL_MM_VERIFY_STATUS_DISABLED))
+		state->tx_active = true;
+	else
+		state->tx_active = false;
+
+	frag_size = stmmac_fpe_get_add_frag_size(priv, priv->ioaddr);
+	state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(frag_size);
+
+	spin_unlock_irqrestore(&priv->fpe_cfg.lock, flags);
+
+	return 0;
+}
+
+static int stmmac_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg,
+			 struct netlink_ext_ack *extack)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct stmmac_fpe_cfg *fpe_cfg = &priv->fpe_cfg;
+	unsigned long flags;
+	u32 frag_size;
+	int err;
+
+	err = ethtool_mm_frag_size_min_to_add(cfg->tx_min_frag_size,
+					      &frag_size, extack);
+	if (err)
+		return err;
+
+	/* Wait for the verification that's currently in progress to finish */
+	timer_shutdown_sync(&fpe_cfg->verify_timer);
+
+	spin_lock_irqsave(&fpe_cfg->lock, flags);
+
+	fpe_cfg->verify_enabled = cfg->verify_enabled;
+	fpe_cfg->pmac_enabled = cfg->pmac_enabled;
+	fpe_cfg->verify_time = cfg->verify_time;
+	fpe_cfg->tx_enabled = cfg->tx_enabled;
+
+	if (!cfg->verify_enabled)
+		fpe_cfg->status = ETHTOOL_MM_VERIFY_STATUS_DISABLED;
+
+	stmmac_fpe_set_add_frag_size(priv, priv->ioaddr, frag_size);
+	stmmac_fpe_apply(priv);
+
+	spin_unlock_irqrestore(&fpe_cfg->lock, flags);
+
+	return 0;
+}
+
+static void stmmac_get_mm_stats(struct net_device *ndev,
+				struct ethtool_mm_stats *s)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct stmmac_counters *mmc = &priv->mmc;
+
+	if (!priv->dma_cap.rmon)
+		return;
+
+	stmmac_mmc_read(priv, priv->mmcaddr, mmc);
+
+	s->MACMergeFrameAssErrorCount = mmc->mmc_rx_packet_assembly_err_cntr;
+	s->MACMergeFrameAssOkCount = mmc->mmc_rx_packet_assembly_ok_cntr;
+	s->MACMergeFrameSmdErrorCount = mmc->mmc_rx_packet_smd_err_cntr;
+	s->MACMergeFragCountRx = mmc->mmc_rx_fpe_fragment_cntr;
+	s->MACMergeFragCountTx = mmc->mmc_tx_fpe_fragment_cntr;
+	s->MACMergeHoldCount = mmc->mmc_tx_hold_req_cntr;
+}
+
 static const struct ethtool_ops stmmac_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES,
@@ -1301,6 +1394,9 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
 	.set_tunable = stmmac_set_tunable,
 	.get_link_ksettings = stmmac_ethtool_get_link_ksettings,
 	.set_link_ksettings = stmmac_ethtool_set_link_ksettings,
+	.get_mm = stmmac_get_mm,
+	.set_mm = stmmac_set_mm,
+	.get_mm_stats = stmmac_get_mm_stats,
 };
 
 void stmmac_set_ethtool_ops(struct net_device *netdev)
-- 
cgit v1.3-3-g829e


From 195e4f409a40f269bacc9a165f6ab77918b5422c Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:10 +0800
Subject: net: stmmac: support fp parameter of tc-mqprio

tc-mqprio can select whether traffic classes are express or preemptible.

After some traffic tests, MAC merge layer statistics are all good.

Local device:
ethtool --include-statistics --json --show-mm eth1
[ {
        "ifname": "eth1",
        "pmac-enabled": true,
        "tx-enabled": true,
        "tx-active": true,
        "tx-min-frag-size": 60,
        "rx-min-frag-size": 60,
        "verify-enabled": true,
        "verify-time": 100,
        "max-verify-time": 128,
        "verify-status": "SUCCEEDED",
        "statistics": {
            "MACMergeFrameAssErrorCount": 0,
            "MACMergeFrameSmdErrorCount": 0,
            "MACMergeFrameAssOkCount": 0,
            "MACMergeFragCountRx": 0,
            "MACMergeFragCountTx": 35105,
            "MACMergeHoldCount": 0
        }
    } ]

Remote device:
ethtool --include-statistics --json --show-mm end1
[ {
        "ifname": "end1",
        "pmac-enabled": true,
        "tx-enabled": true,
        "tx-active": true,
        "tx-min-frag-size": 60,
        "rx-min-frag-size": 60,
        "verify-enabled": true,
        "verify-time": 100,
        "max-verify-time": 128,
        "verify-status": "SUCCEEDED",
        "statistics": {
            "MACMergeFrameAssErrorCount": 0,
            "MACMergeFrameSmdErrorCount": 0,
            "MACMergeFrameAssOkCount": 35105,
            "MACMergeFragCountRx": 35105,
            "MACMergeFragCountTx": 0,
            "MACMergeHoldCount": 0
        }
    } ]

Tested on DWMAC CORE 5.10a

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/592965ea93ed8240f0a1b8f6f8ebb8914f69419b.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c |  2 +
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c      | 55 +++++++++++++
 drivers/net/ethernet/stmicro/stmmac/dwmac5.h      |  4 +
 drivers/net/ethernet/stmicro/stmmac/hwif.c        |  6 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h        | 12 +++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |  2 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c   | 94 +++++++++++++++++++++++
 7 files changed, 172 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 679efcc631f1..a1858f083eef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -1266,6 +1266,7 @@ const struct stmmac_ops dwmac410_ops = {
 	.fpe_irq_status = dwmac5_fpe_irq_status,
 	.fpe_get_add_frag_size = dwmac5_fpe_get_add_frag_size,
 	.fpe_set_add_frag_size = dwmac5_fpe_set_add_frag_size,
+	.fpe_map_preemption_class = dwmac5_fpe_map_preemption_class,
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
@@ -1320,6 +1321,7 @@ const struct stmmac_ops dwmac510_ops = {
 	.fpe_irq_status = dwmac5_fpe_irq_status,
 	.fpe_get_add_frag_size = dwmac5_fpe_get_add_frag_size,
 	.fpe_set_add_frag_size = dwmac5_fpe_set_add_frag_size,
+	.fpe_map_preemption_class = dwmac5_fpe_map_preemption_class,
 	.add_hw_vlan_rx_fltr = dwmac4_add_hw_vlan_rx_fltr,
 	.del_hw_vlan_rx_fltr = dwmac4_del_hw_vlan_rx_fltr,
 	.restore_hw_vlan_rx_fltr = dwmac4_restore_hw_vlan_rx_fltr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index db7bbc50cfae..ab96fc055f48 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -667,3 +667,58 @@ void dwmac5_fpe_set_add_frag_size(void __iomem *ioaddr, u32 add_frag_size)
 	writel(u32_replace_bits(value, add_frag_size, DWMAC5_ADD_FRAG_SZ),
 	       ioaddr + MTL_FPE_CTRL_STS);
 }
+
+#define ALG_ERR_MSG "TX algorithm SP is not suitable for one-to-many mapping"
+#define WEIGHT_ERR_MSG "TXQ weight %u differs across other TXQs in TC: [%u]"
+
+int dwmac5_fpe_map_preemption_class(struct net_device *ndev,
+				    struct netlink_ext_ack *extack, u32 pclass)
+{
+	u32 val, offset, count, queue_weight, preemptible_txqs = 0;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	u32 num_tc = ndev->num_tc;
+
+	if (!pclass)
+		goto update_mapping;
+
+	/* DWMAC CORE4+ can not program TC:TXQ mapping to hardware.
+	 *
+	 * Synopsys Databook:
+	 * "The number of Tx DMA channels is equal to the number of Tx queues,
+	 * and is direct one-to-one mapping."
+	 */
+	for (u32 tc = 0; tc < num_tc; tc++) {
+		count = ndev->tc_to_txq[tc].count;
+		offset = ndev->tc_to_txq[tc].offset;
+
+		if (pclass & BIT(tc))
+			preemptible_txqs |= GENMASK(offset + count - 1, offset);
+
+		/* This is 1:1 mapping, go to next TC */
+		if (count == 1)
+			continue;
+
+		if (priv->plat->tx_sched_algorithm == MTL_TX_ALGORITHM_SP) {
+			NL_SET_ERR_MSG_MOD(extack, ALG_ERR_MSG);
+			return -EINVAL;
+		}
+
+		queue_weight = priv->plat->tx_queues_cfg[offset].weight;
+
+		for (u32 i = 1; i < count; i++) {
+			if (priv->plat->tx_queues_cfg[offset + i].weight !=
+			    queue_weight) {
+				NL_SET_ERR_MSG_FMT_MOD(extack, WEIGHT_ERR_MSG,
+						       queue_weight, tc);
+				return -EINVAL;
+			}
+		}
+	}
+
+update_mapping:
+	val = readl(priv->ioaddr + MTL_FPE_CTRL_STS);
+	writel(u32_replace_bits(val, preemptible_txqs, DWMAC5_PREEMPTION_CLASS),
+	       priv->ioaddr + MTL_FPE_CTRL_STS);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
index 58704c15f320..6c6eb6790e83 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h
@@ -40,6 +40,8 @@
 #define MAC_PPSx_WIDTH(x)		(0x00000b8c + ((x) * 0x10))
 
 #define MTL_FPE_CTRL_STS		0x00000c90
+/* Preemption Classification */
+#define DWMAC5_PREEMPTION_CLASS		GENMASK(15, 8)
 /* Additional Fragment Size of preempted frames */
 #define DWMAC5_ADD_FRAG_SZ		GENMASK(1, 0)
 
@@ -115,5 +117,7 @@ void dwmac5_fpe_send_mpacket(void __iomem *ioaddr,
 int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev);
 int dwmac5_fpe_get_add_frag_size(const void __iomem *ioaddr);
 void dwmac5_fpe_set_add_frag_size(void __iomem *ioaddr, u32 add_frag_size);
+int dwmac5_fpe_map_preemption_class(struct net_device *ndev,
+				    struct netlink_ext_ack *extack, u32 pclass);
 
 #endif /* __DWMAC5_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 29367105df54..88cce28b2f98 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -171,7 +171,7 @@ static const struct stmmac_hwif_entry {
 		.mac = &dwmac4_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
-		.tc = &dwmac510_tc_ops,
+		.tc = &dwmac4_tc_ops,
 		.mmc = &dwmac_mmc_ops,
 		.est = &dwmac510_est_ops,
 		.setup = dwmac4_setup,
@@ -252,7 +252,7 @@ static const struct stmmac_hwif_entry {
 		.mac = &dwxgmac210_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
-		.tc = &dwmac510_tc_ops,
+		.tc = &dwxgmac_tc_ops,
 		.mmc = &dwxgmac_mmc_ops,
 		.est = &dwmac510_est_ops,
 		.setup = dwxgmac2_setup,
@@ -273,7 +273,7 @@ static const struct stmmac_hwif_entry {
 		.mac = &dwxlgmac2_ops,
 		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
-		.tc = &dwmac510_tc_ops,
+		.tc = &dwxgmac_tc_ops,
 		.mmc = &dwxgmac_mmc_ops,
 		.est = &dwmac510_est_ops,
 		.setup = dwxlgmac2_setup,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index f080e271f7af..d5a9f01ecac5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -7,6 +7,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/stmmac.h>
+#include <net/pkt_cls.h>
 
 #define stmmac_do_void_callback(__priv, __module, __cname,  __arg0, __args...) \
 ({ \
@@ -428,6 +429,9 @@ struct stmmac_ops {
 	int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev);
 	int (*fpe_get_add_frag_size)(const void __iomem *ioaddr);
 	void (*fpe_set_add_frag_size)(void __iomem *ioaddr, u32 add_frag_size);
+	int (*fpe_map_preemption_class)(struct net_device *ndev,
+					struct netlink_ext_ack *extack,
+					u32 pclass);
 };
 
 #define stmmac_core_init(__priv, __args...) \
@@ -536,6 +540,8 @@ struct stmmac_ops {
 	stmmac_do_callback(__priv, mac, fpe_get_add_frag_size, __args)
 #define stmmac_fpe_set_add_frag_size(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, fpe_set_add_frag_size, __args)
+#define stmmac_fpe_map_preemption_class(__priv, __args...) \
+	stmmac_do_void_callback(__priv, mac, fpe_map_preemption_class, __args)
 
 /* PTP and HW Timer helpers */
 struct stmmac_hwtimestamp {
@@ -623,6 +629,8 @@ struct stmmac_tc_ops {
 			 struct tc_etf_qopt_offload *qopt);
 	int (*query_caps)(struct stmmac_priv *priv,
 			  struct tc_query_caps_base *base);
+	int (*setup_mqprio)(struct stmmac_priv *priv,
+			    struct tc_mqprio_qopt_offload *qopt);
 };
 
 #define stmmac_tc_init(__priv, __args...) \
@@ -639,6 +647,8 @@ struct stmmac_tc_ops {
 	stmmac_do_callback(__priv, tc, setup_etf, __args)
 #define stmmac_tc_query_caps(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, query_caps, __args)
+#define stmmac_tc_setup_mqprio(__priv, __args...) \
+	stmmac_do_callback(__priv, tc, setup_mqprio, __args)
 
 struct stmmac_counters;
 
@@ -682,7 +692,9 @@ extern const struct stmmac_dma_ops dwmac4_dma_ops;
 extern const struct stmmac_ops dwmac410_ops;
 extern const struct stmmac_dma_ops dwmac410_dma_ops;
 extern const struct stmmac_ops dwmac510_ops;
+extern const struct stmmac_tc_ops dwmac4_tc_ops;
 extern const struct stmmac_tc_ops dwmac510_tc_ops;
+extern const struct stmmac_tc_ops dwxgmac_tc_ops;
 extern const struct stmmac_ops dwxgmac210_ops;
 extern const struct stmmac_ops dwxlgmac2_ops;
 extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5a38bdb3f535..d3895d7eecfc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -6216,6 +6216,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	switch (type) {
 	case TC_QUERY_CAPS:
 		return stmmac_tc_query_caps(priv, priv, type_data);
+	case TC_SETUP_QDISC_MQPRIO:
+		return stmmac_tc_setup_mqprio(priv, priv, type_data);
 	case TC_SETUP_BLOCK:
 		return flow_block_cb_setup_simple(type_data,
 						  &stmmac_block_cb_list,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index a58282d6458c..cfdb9ab1fa2a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1174,6 +1174,13 @@ static int tc_query_caps(struct stmmac_priv *priv,
 			 struct tc_query_caps_base *base)
 {
 	switch (base->type) {
+	case TC_SETUP_QDISC_MQPRIO: {
+		struct tc_mqprio_caps *caps = base->caps;
+
+		caps->validate_queue_counts = true;
+
+		return 0;
+	}
 	case TC_SETUP_QDISC_TAPRIO: {
 		struct tc_taprio_caps *caps = base->caps;
 
@@ -1190,6 +1197,81 @@ static int tc_query_caps(struct stmmac_priv *priv,
 	}
 }
 
+static void stmmac_reset_tc_mqprio(struct net_device *ndev,
+				   struct netlink_ext_ack *extack)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	netdev_reset_tc(ndev);
+	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
+	stmmac_fpe_map_preemption_class(priv, ndev, extack, 0);
+}
+
+static int tc_setup_dwmac510_mqprio(struct stmmac_priv *priv,
+				    struct tc_mqprio_qopt_offload *mqprio)
+{
+	struct netlink_ext_ack *extack = mqprio->extack;
+	struct tc_mqprio_qopt *qopt = &mqprio->qopt;
+	u32 offset, count, num_stack_tx_queues = 0;
+	struct net_device *ndev = priv->dev;
+	u32 num_tc = qopt->num_tc;
+	int err;
+
+	if (!num_tc) {
+		stmmac_reset_tc_mqprio(ndev, extack);
+		return 0;
+	}
+
+	err = netdev_set_num_tc(ndev, num_tc);
+	if (err)
+		return err;
+
+	for (u32 tc = 0; tc < num_tc; tc++) {
+		offset = qopt->offset[tc];
+		count = qopt->count[tc];
+		num_stack_tx_queues += count;
+
+		err = netdev_set_tc_queue(ndev, tc, count, offset);
+		if (err)
+			goto err_reset_tc;
+	}
+
+	err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues);
+	if (err)
+		goto err_reset_tc;
+
+	err = stmmac_fpe_map_preemption_class(priv, ndev, extack,
+					      mqprio->preemptible_tcs);
+	if (err)
+		goto err_reset_tc;
+
+	return 0;
+
+err_reset_tc:
+	stmmac_reset_tc_mqprio(ndev, extack);
+
+	return err;
+}
+
+static int tc_setup_mqprio_unimplemented(struct stmmac_priv *priv,
+					 struct tc_mqprio_qopt_offload *mqprio)
+{
+	NL_SET_ERR_MSG_MOD(mqprio->extack,
+			   "mqprio HW offload is not implemented for this MAC");
+	return -EOPNOTSUPP;
+}
+
+const struct stmmac_tc_ops dwmac4_tc_ops = {
+	.init = tc_init,
+	.setup_cls_u32 = tc_setup_cls_u32,
+	.setup_cbs = tc_setup_cbs,
+	.setup_cls = tc_setup_cls,
+	.setup_taprio = tc_setup_taprio,
+	.setup_etf = tc_setup_etf,
+	.query_caps = tc_query_caps,
+	.setup_mqprio = tc_setup_mqprio_unimplemented,
+};
+
 const struct stmmac_tc_ops dwmac510_tc_ops = {
 	.init = tc_init,
 	.setup_cls_u32 = tc_setup_cls_u32,
@@ -1198,4 +1280,16 @@ const struct stmmac_tc_ops dwmac510_tc_ops = {
 	.setup_taprio = tc_setup_taprio,
 	.setup_etf = tc_setup_etf,
 	.query_caps = tc_query_caps,
+	.setup_mqprio = tc_setup_dwmac510_mqprio,
+};
+
+const struct stmmac_tc_ops dwxgmac_tc_ops = {
+	.init = tc_init,
+	.setup_cls_u32 = tc_setup_cls_u32,
+	.setup_cbs = tc_setup_cbs,
+	.setup_cls = tc_setup_cls,
+	.setup_taprio = tc_setup_taprio,
+	.setup_etf = tc_setup_etf,
+	.query_caps = tc_query_caps,
+	.setup_mqprio = tc_setup_mqprio_unimplemented,
 };
-- 
cgit v1.3-3-g829e


From 15d8a407a54708cacefd5e36c069e7ba36a36050 Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:11 +0800
Subject: net: stmmac: support fp parameter of tc-taprio

tc-taprio can select whether traffic classes are express or preemptible.

0) tc qdisc add dev eth1 parent root handle 100 taprio \
        num_tc 4 \
        map 0 1 2 3 2 2 2 2 2 2 2 2 2 2 2 3 \
        queues 1@0 1@1 1@2 1@3 \
        base-time 1000000000 \
        sched-entry S 03 10000000 \
        sched-entry S 0e 10000000 \
        flags 0x2 fp P E E E

1) After some traffic tests, MAC merge layer statistics are all good.

Local device:
[ {
        "ifname": "eth1",
        "pmac-enabled": true,
        "tx-enabled": true,
        "tx-active": true,
        "tx-min-frag-size": 60,
        "rx-min-frag-size": 60,
        "verify-enabled": true,
        "verify-time": 100,
        "max-verify-time": 128,
        "verify-status": "SUCCEEDED",
        "statistics": {
            "MACMergeFrameAssErrorCount": 0,
            "MACMergeFrameSmdErrorCount": 0,
            "MACMergeFrameAssOkCount": 0,
            "MACMergeFragCountRx": 0,
            "MACMergeFragCountTx": 17837,
            "MACMergeHoldCount": 18639
        }
    } ]

Remote device:
[ {
        "ifname": "end1",
        "pmac-enabled": true,
        "tx-enabled": true,
        "tx-active": true,
        "tx-min-frag-size": 60,
        "rx-min-frag-size": 60,
        "verify-enabled": true,
        "verify-time": 100,
        "max-verify-time": 128,
        "verify-status": "SUCCEEDED",
        "statistics": {
            "MACMergeFrameAssErrorCount": 0,
            "MACMergeFrameSmdErrorCount": 0,
            "MACMergeFrameAssOkCount": 17189,
            "MACMergeFragCountRx": 17837,
            "MACMergeFragCountTx": 0,
            "MACMergeHoldCount": 0
        }
    } ]

Tested on DWMAC CORE 5.10a

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/0d21ae356fb3cab77337527e87d46748a4852055.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 39 ++++++++++++++-----------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index cfdb9ab1fa2a..05ffff00a524 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -931,9 +931,9 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 			       struct tc_taprio_qopt_offload *qopt)
 {
 	u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
+	struct netlink_ext_ack *extack = qopt->mqprio.extack;
 	struct timespec64 time, current_time, qopt_time;
 	ktime_t current_time_ns;
-	bool fpe = false;
 	int i, ret = 0;
 	u64 ctr;
 
@@ -1018,16 +1018,12 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 
 		switch (qopt->entries[i].command) {
 		case TC_TAPRIO_CMD_SET_GATES:
-			if (fpe)
-				return -EINVAL;
 			break;
 		case TC_TAPRIO_CMD_SET_AND_HOLD:
 			gates |= BIT(0);
-			fpe = true;
 			break;
 		case TC_TAPRIO_CMD_SET_AND_RELEASE:
 			gates &= ~BIT(0);
-			fpe = true;
 			break;
 		default:
 			return -EOPNOTSUPP;
@@ -1058,11 +1054,6 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 
 	tc_taprio_map_maxsdu_txq(priv, qopt);
 
-	if (fpe && !priv->dma_cap.fpesel) {
-		mutex_unlock(&priv->est_lock);
-		return -EOPNOTSUPP;
-	}
-
 	ret = stmmac_est_configure(priv, priv, priv->est,
 				   priv->plat->clk_ptp_rate);
 	mutex_unlock(&priv->est_lock);
@@ -1071,6 +1062,11 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 		goto disable;
 	}
 
+	ret = stmmac_fpe_map_preemption_class(priv, priv->dev, extack,
+					      qopt->mqprio.preemptible_tcs);
+	if (ret)
+		goto disable;
+
 	netdev_info(priv->dev, "configured EST\n");
 
 	return 0;
@@ -1089,11 +1085,8 @@ disable:
 		mutex_unlock(&priv->est_lock);
 	}
 
-	stmmac_fpe_configure(priv, priv->ioaddr,
-			     &priv->fpe_cfg,
-			     priv->plat->tx_queues_to_use,
-			     priv->plat->rx_queues_to_use,
-			     false, false);
+	stmmac_fpe_map_preemption_class(priv, priv->dev, extack, 0);
+
 	netdev_info(priv->dev, "disabled FPE\n");
 
 	return ret;
@@ -1150,6 +1143,18 @@ static int tc_setup_taprio(struct stmmac_priv *priv,
 	return err;
 }
 
+static int tc_setup_taprio_without_fpe(struct stmmac_priv *priv,
+				       struct tc_taprio_qopt_offload *qopt)
+{
+	if (!qopt->mqprio.preemptible_tcs)
+		return tc_setup_taprio(priv, qopt);
+
+	NL_SET_ERR_MSG_MOD(qopt->mqprio.extack,
+			   "taprio with FPE is not implemented for this MAC");
+
+	return -EOPNOTSUPP;
+}
+
 static int tc_setup_etf(struct stmmac_priv *priv,
 			struct tc_etf_qopt_offload *qopt)
 {
@@ -1266,7 +1271,7 @@ const struct stmmac_tc_ops dwmac4_tc_ops = {
 	.setup_cls_u32 = tc_setup_cls_u32,
 	.setup_cbs = tc_setup_cbs,
 	.setup_cls = tc_setup_cls,
-	.setup_taprio = tc_setup_taprio,
+	.setup_taprio = tc_setup_taprio_without_fpe,
 	.setup_etf = tc_setup_etf,
 	.query_caps = tc_query_caps,
 	.setup_mqprio = tc_setup_mqprio_unimplemented,
@@ -1288,7 +1293,7 @@ const struct stmmac_tc_ops dwxgmac_tc_ops = {
 	.setup_cls_u32 = tc_setup_cls_u32,
 	.setup_cbs = tc_setup_cbs,
 	.setup_cls = tc_setup_cls,
-	.setup_taprio = tc_setup_taprio,
+	.setup_taprio = tc_setup_taprio_without_fpe,
 	.setup_etf = tc_setup_etf,
 	.query_caps = tc_query_caps,
 	.setup_mqprio = tc_setup_mqprio_unimplemented,
-- 
cgit v1.3-3-g829e


From 22a805d880c2f2aaf37e0ed6a48aaecae98a0fe6 Mon Sep 17 00:00:00 2001
From: Furong Xu <0x1207@gmail.com>
Date: Fri, 6 Sep 2024 22:30:12 +0800
Subject: net: stmmac: silence FPE kernel logs

ethtool --show-mm can get real-time state of FPE.
fpe_irq_status logs should keep quiet.

tc-taprio can always query driver state, delete unbalanced logs.

Signed-off-by: Furong Xu <0x1207@gmail.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/39943d7967f291674a97ef0572878aca273087e9.1725631883.git.0x1207@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c    | 8 ++++----
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 4 ----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index ab96fc055f48..08add508db84 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -620,22 +620,22 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev)
 
 	if (value & TRSP) {
 		status |= FPE_EVENT_TRSP;
-		netdev_info(dev, "FPE: Respond mPacket is transmitted\n");
+		netdev_dbg(dev, "FPE: Respond mPacket is transmitted\n");
 	}
 
 	if (value & TVER) {
 		status |= FPE_EVENT_TVER;
-		netdev_info(dev, "FPE: Verify mPacket is transmitted\n");
+		netdev_dbg(dev, "FPE: Verify mPacket is transmitted\n");
 	}
 
 	if (value & RRSP) {
 		status |= FPE_EVENT_RRSP;
-		netdev_info(dev, "FPE: Respond mPacket is received\n");
+		netdev_dbg(dev, "FPE: Respond mPacket is received\n");
 	}
 
 	if (value & RVER) {
 		status |= FPE_EVENT_RVER;
-		netdev_info(dev, "FPE: Verify mPacket is received\n");
+		netdev_dbg(dev, "FPE: Verify mPacket is received\n");
 	}
 
 	return status;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 05ffff00a524..832998bc020b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -1067,8 +1067,6 @@ static int tc_taprio_configure(struct stmmac_priv *priv,
 	if (ret)
 		goto disable;
 
-	netdev_info(priv->dev, "configured EST\n");
-
 	return 0;
 
 disable:
@@ -1087,8 +1085,6 @@ disable:
 
 	stmmac_fpe_map_preemption_class(priv, priv->dev, extack, 0);
 
-	netdev_info(priv->dev, "disabled FPE\n");
-
 	return ret;
 }
 
-- 
cgit v1.3-3-g829e


From e503f82e304b039332226008addac9d13ac68cb9 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Sun, 8 Sep 2024 20:41:41 +0800
Subject: net-timestamp: correct the use of SOF_TIMESTAMPING_RAW_HARDWARE

SOF_TIMESTAMPING_RAW_HARDWARE is a report flag which passes the
timestamps generated by either SOF_TIMESTAMPING_TX_HARDWARE or
SOF_TIMESTAMPING_RX_HARDWARE to the userspace all the time.

So let us revise the doc here.

Link: https://lore.kernel.org/all/66d8c21d3042a_163d93294cb@willemb.c.googlers.com.notmuch/
Suggested-by: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Link: https://patch.msgid.link/20240908124141.39628-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/timestamping.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index 5e93cd71f99f..9c7773271393 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -158,7 +158,8 @@ SOF_TIMESTAMPING_SYS_HARDWARE:
 
 SOF_TIMESTAMPING_RAW_HARDWARE:
   Report hardware timestamps as generated by
-  SOF_TIMESTAMPING_TX_HARDWARE when available.
+  SOF_TIMESTAMPING_TX_HARDWARE or SOF_TIMESTAMPING_RX_HARDWARE
+  when available.
 
 
 1.3.3 Timestamp Options
-- 
cgit v1.3-3-g829e


From be8e9eb3750639aa5cffb3f764ca080caed41bd0 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Mon, 9 Sep 2024 09:56:11 +0800
Subject: net-timestamp: introduce SOF_TIMESTAMPING_OPT_RX_FILTER flag

introduce a new flag SOF_TIMESTAMPING_OPT_RX_FILTER in the receive
path. User can set it with SOF_TIMESTAMPING_SOFTWARE to filter
out rx software timestamp report, especially after a process turns on
netstamp_needed_key which can time stamp every incoming skb.

Previously, we found out if an application starts first which turns on
netstamp_needed_key, then another one only passing SOF_TIMESTAMPING_SOFTWARE
could also get rx timestamp. Now we handle this case by introducing this
new flag without breaking users.

Quoting Willem to explain why we need the flag:
"why a process would want to request software timestamp reporting, but
not receive software timestamp generation. The only use I see is when
the application does request
SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_TX_SOFTWARE."

Similarly, this new flag could also be used for hardware case where we
can set it with SOF_TIMESTAMPING_RAW_HARDWARE, then we won't receive
hardware receive timestamp.

Another thing about errqueue in this patch I have a few words to say:
In this case, we need to handle the egress path carefully, or else
reporting the tx timestamp will fail. Egress path and ingress path will
finally call sock_recv_timestamp(). We have to distinguish them.
Errqueue is a good indicator to reflect the flow direction.

Suggested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240909015612.3856-2-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/timestamping.rst | 17 +++++++++++++++++
 include/uapi/linux/net_tstamp.h           |  3 ++-
 net/ethtool/common.c                      |  1 +
 net/ipv4/tcp.c                            |  9 +++++++--
 net/socket.c                              | 10 ++++++++--
 5 files changed, 35 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index 9c7773271393..8199e6917671 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -267,6 +267,23 @@ SOF_TIMESTAMPING_OPT_TX_SWHW:
   two separate messages will be looped to the socket's error queue,
   each containing just one timestamp.
 
+SOF_TIMESTAMPING_OPT_RX_FILTER:
+  Filter out spurious receive timestamps: report a receive timestamp
+  only if the matching timestamp generation flag is enabled.
+
+  Receive timestamps are generated early in the ingress path, before a
+  packet's destination socket is known. If any socket enables receive
+  timestamps, packets for all socket will receive timestamped packets.
+  Including those that request timestamp reporting with
+  SOF_TIMESTAMPING_SOFTWARE and/or SOF_TIMESTAMPING_RAW_HARDWARE, but
+  do not request receive timestamp generation. This can happen when
+  requesting transmit timestamps only.
+
+  Receiving spurious timestamps is generally benign. A process can
+  ignore the unexpected non-zero value. But it makes behavior subtly
+  dependent on other sockets. This flag isolates the socket for more
+  deterministic behavior.
+
 New applications are encouraged to pass SOF_TIMESTAMPING_OPT_ID to
 disambiguate timestamps and SOF_TIMESTAMPING_OPT_TSONLY to operate
 regardless of the setting of sysctl net.core.tstamp_allow_data.
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index a2c66b3d7f0f..858339d1c1c4 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -32,8 +32,9 @@ enum {
 	SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14),
 	SOF_TIMESTAMPING_BIND_PHC = (1 << 15),
 	SOF_TIMESTAMPING_OPT_ID_TCP = (1 << 16),
+	SOF_TIMESTAMPING_OPT_RX_FILTER = (1 << 17),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID_TCP,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_RX_FILTER,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 781834ef57c3..6c245e59bbc1 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -427,6 +427,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = {
 	[const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)]  = "option-tx-swhw",
 	[const_ilog2(SOF_TIMESTAMPING_BIND_PHC)]     = "bind-phc",
 	[const_ilog2(SOF_TIMESTAMPING_OPT_ID_TCP)]   = "option-id-tcp",
+	[const_ilog2(SOF_TIMESTAMPING_OPT_RX_FILTER)] = "option-rx-filter",
 };
 static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8a5680b4e786..e359a9161445 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2235,6 +2235,7 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
 			struct scm_timestamping_internal *tss)
 {
 	int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
+	u32 tsflags = READ_ONCE(sk->sk_tsflags);
 	bool has_timestamping = false;
 
 	if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
@@ -2274,14 +2275,18 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
 			}
 		}
 
-		if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE)
+		if (tsflags & SOF_TIMESTAMPING_SOFTWARE &&
+		    (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE ||
+		     !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER)))
 			has_timestamping = true;
 		else
 			tss->ts[0] = (struct timespec64) {0};
 	}
 
 	if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
-		if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE)
+		if (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE &&
+		    (tsflags & SOF_TIMESTAMPING_RX_HARDWARE ||
+		     !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER)))
 			has_timestamping = true;
 		else
 			tss->ts[2] = (struct timespec64) {0};
diff --git a/net/socket.c b/net/socket.c
index 0a2bd22ec105..8d8b84fa404a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -946,11 +946,17 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 
 	memset(&tss, 0, sizeof(tss));
 	tsflags = READ_ONCE(sk->sk_tsflags);
-	if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
+	if ((tsflags & SOF_TIMESTAMPING_SOFTWARE &&
+	     (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE ||
+	      skb_is_err_queue(skb) ||
+	      !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) &&
 	    ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0))
 		empty = 0;
 	if (shhwtstamps &&
-	    (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
+	    (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE &&
+	     (tsflags & SOF_TIMESTAMPING_RX_HARDWARE ||
+	      skb_is_err_queue(skb) ||
+	      !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) &&
 	    !skb_is_swtx_tstamp(skb, false_tstamp)) {
 		if_index = 0;
 		if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV)
-- 
cgit v1.3-3-g829e


From fffe8efd689f29553f59dc6b3ce2867307ad37a2 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Mon, 9 Sep 2024 09:56:12 +0800
Subject: net-timestamp: add selftests for SOF_TIMESTAMPING_OPT_RX_FILTER

Test a few possible cases where we use SOF_TIMESTAMPING_OPT_RX_FILTER
with software or hardware report/generation flag.

Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240909015612.3856-3-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/rxtimestamp.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c
index 9eb42570294d..16ac4df55fdb 100644
--- a/tools/testing/selftests/net/rxtimestamp.c
+++ b/tools/testing/selftests/net/rxtimestamp.c
@@ -57,6 +57,8 @@ static struct sof_flag sof_flags[] = {
 	SOF_FLAG(SOF_TIMESTAMPING_SOFTWARE),
 	SOF_FLAG(SOF_TIMESTAMPING_RX_SOFTWARE),
 	SOF_FLAG(SOF_TIMESTAMPING_RX_HARDWARE),
+	SOF_FLAG(SOF_TIMESTAMPING_OPT_RX_FILTER),
+	SOF_FLAG(SOF_TIMESTAMPING_RAW_HARDWARE),
 };
 
 static struct socket_type socket_types[] = {
@@ -97,6 +99,22 @@ static struct test_case test_cases[] = {
 			| SOF_TIMESTAMPING_RX_HARDWARE },
 		{}
 	},
+	{
+		{ .so_timestamping = SOF_TIMESTAMPING_RAW_HARDWARE
+			| SOF_TIMESTAMPING_OPT_RX_FILTER },
+		{}
+	},
+	{
+		{ .so_timestamping = SOF_TIMESTAMPING_SOFTWARE
+			| SOF_TIMESTAMPING_OPT_RX_FILTER },
+		{}
+	},
+	{
+		{ .so_timestamping = SOF_TIMESTAMPING_SOFTWARE
+			| SOF_TIMESTAMPING_RX_SOFTWARE
+			| SOF_TIMESTAMPING_OPT_RX_FILTER },
+		{ .swtstamp = true }
+	},
 	{
 		{ .so_timestamping = SOF_TIMESTAMPING_SOFTWARE
 			| SOF_TIMESTAMPING_RX_SOFTWARE },
-- 
cgit v1.3-3-g829e


From 3f464b193d40e49299dcd087b10cc3b77cbbea68 Mon Sep 17 00:00:00 2001
From: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Date: Mon, 9 Sep 2024 15:42:59 +0200
Subject: net: dsa: microchip: update tag_ksz masks for KSZ9477 family

Remove magic number 7 by introducing a GENMASK macro instead.
Remove magic number 0x80 by using the BIT macro instead.

Signed-off-by: Pieter Van Trappen <pieter.van.trappen@cern.ch>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20240909134301.75448-1-vtpieter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/tag_ksz.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 1f46de394f2e..281bbac5539d 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -178,8 +178,9 @@ MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME);
 
 #define KSZ9477_INGRESS_TAG_LEN		2
 #define KSZ9477_PTP_TAG_LEN		4
-#define KSZ9477_PTP_TAG_INDICATION	0x80
+#define KSZ9477_PTP_TAG_INDICATION	BIT(7)
 
+#define KSZ9477_TAIL_TAG_EG_PORT_M	GENMASK(2, 0)
 #define KSZ9477_TAIL_TAG_PRIO		GENMASK(8, 7)
 #define KSZ9477_TAIL_TAG_OVERRIDE	BIT(9)
 #define KSZ9477_TAIL_TAG_LOOKUP		BIT(10)
@@ -312,7 +313,7 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev)
 {
 	/* Tag decoding */
 	u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN;
-	unsigned int port = tag[0] & 7;
+	unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M;
 	unsigned int len = KSZ_EGRESS_TAG_LEN;
 
 	/* Extra 4-bytes PTP timestamp */
-- 
cgit v1.3-3-g829e


From c48994baefdc1e092d1ebd979ae573e73fcfb9c5 Mon Sep 17 00:00:00 2001
From: Dave Taht <dave.taht@gmail.com>
Date: Mon, 9 Sep 2024 11:16:28 +0200
Subject: sch_cake: constify inverse square root cache
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sch_cake uses a cache of the first 16 values of the inverse square root
calculation for the Cobalt AQM to save some cycles on the fast path.
This cache is populated when the qdisc is first loaded, but there's
really no reason why it can't just be pre-populated. So change it to be
pre-populated with constants, which also makes it possible to constify
it.

This gives a modest space saving for the module (not counting debug data):
.text:  -224 bytes
.rodata: +80 bytes
.bss:    -64 bytes
Total:  -192 bytes

Signed-off-by: Dave Taht <dave.taht@gmail.com>
[ fixed up comment, rewrote commit message ]
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20240909091630.22177-1-toke@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_cake.c | 53 ++++++++++++++++++----------------------------------
 1 file changed, 18 insertions(+), 35 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index d2f49db70523..f2f9b75008bb 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -361,8 +361,24 @@ static const u8 besteffort[] = {
 static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7};
 static const u8 bulk_order[] = {1, 0, 2, 3};
 
+/* There is a big difference in timing between the accurate values placed in the
+ * cache and the approximations given by a single Newton step for small count
+ * values, particularly when stepping from count 1 to 2 or vice versa. Hence,
+ * these values are calculated using eight Newton steps, using the
+ * implementation below. Above 16, a single Newton step gives sufficient
+ * accuracy in either direction, given the precision stored.
+ *
+ * The magnitude of the error when stepping up to count 2 is such as to give the
+ * value that *should* have been produced at count 4.
+ */
+
 #define REC_INV_SQRT_CACHE (16)
-static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0};
+static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = {
+		~0,         ~0, 3037000500, 2479700525,
+	2147483647, 1920767767, 1753413056, 1623345051,
+	1518500250, 1431655765, 1358187914, 1294981364,
+	1239850263, 1191209601, 1147878294, 1108955788
+};
 
 /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
  * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
@@ -388,47 +404,14 @@ static void cobalt_newton_step(struct cobalt_vars *vars)
 static void cobalt_invsqrt(struct cobalt_vars *vars)
 {
 	if (vars->count < REC_INV_SQRT_CACHE)
-		vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count];
+		vars->rec_inv_sqrt = inv_sqrt_cache[vars->count];
 	else
 		cobalt_newton_step(vars);
 }
 
-/* There is a big difference in timing between the accurate values placed in
- * the cache and the approximations given by a single Newton step for small
- * count values, particularly when stepping from count 1 to 2 or vice versa.
- * Above 16, a single Newton step gives sufficient accuracy in either
- * direction, given the precision stored.
- *
- * The magnitude of the error when stepping up to count 2 is such as to give
- * the value that *should* have been produced at count 4.
- */
-
-static void cobalt_cache_init(void)
-{
-	struct cobalt_vars v;
-
-	memset(&v, 0, sizeof(v));
-	v.rec_inv_sqrt = ~0U;
-	cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt;
-
-	for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) {
-		cobalt_newton_step(&v);
-		cobalt_newton_step(&v);
-		cobalt_newton_step(&v);
-		cobalt_newton_step(&v);
-
-		cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt;
-	}
-}
-
 static void cobalt_vars_init(struct cobalt_vars *vars)
 {
 	memset(vars, 0, sizeof(*vars));
-
-	if (!cobalt_rec_inv_sqrt_cache[0]) {
-		cobalt_cache_init();
-		cobalt_rec_inv_sqrt_cache[0] = ~0;
-	}
 }
 
 /* CoDel control_law is t + interval/sqrt(count)
-- 
cgit v1.3-3-g829e


From 8df9439389a44fb2cc4ef695e08d6a8870b1616c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 9 Sep 2024 15:00:21 +0100
Subject: r8169: Fix spelling mistake: "tx_underun" -> "tx_underrun"

There is a spelling mistake in the struct field tx_underun, rename
it to tx_underrun.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/20240909140021.64884-1-colin.i.king@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 3cb1c4f5c91a..45ac8befba29 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -578,7 +578,7 @@ struct rtl8169_counters {
 	__le64	rx_broadcast;
 	__le32	rx_multicast;
 	__le16	tx_aborted;
-	__le16	tx_underun;
+	__le16	tx_underrun;
 };
 
 struct rtl8169_tc_offsets {
@@ -1843,7 +1843,7 @@ static void rtl8169_get_ethtool_stats(struct net_device *dev,
 	data[9] = le64_to_cpu(counters->rx_broadcast);
 	data[10] = le32_to_cpu(counters->rx_multicast);
 	data[11] = le16_to_cpu(counters->tx_aborted);
-	data[12] = le16_to_cpu(counters->tx_underun);
+	data[12] = le16_to_cpu(counters->tx_underrun);
 }
 
 static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data)
-- 
cgit v1.3-3-g829e


From d59239f8a4000e080e5fc606d6e709fad4028fb7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 9 Sep 2024 14:46:12 +0100
Subject: rtase: Fix spelling mistake: "tx_underun" -> "tx_underrun"

There is a spelling mistake in the struct field tx_underun, rename
it to tx_underrun.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240909134612.63912-1-colin.i.king@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 7882f2c0e1a4..869183e1565e 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -98,7 +98,7 @@ struct rtase_counters {
 	__le64 rx_broadcast;
 	__le32 rx_multicast;
 	__le16 tx_aborted;
-	__le16 tx_underun;
+	__le16 tx_underrun;
 } __packed;
 
 static void rtase_w8(const struct rtase_private *tp, u16 reg, u8 val8)
@@ -1619,8 +1619,8 @@ static void rtase_dump_state(const struct net_device *dev)
 		   le32_to_cpu(counters->rx_multicast));
 	netdev_err(dev, "tx_aborted %d\n",
 		   le16_to_cpu(counters->tx_aborted));
-	netdev_err(dev, "tx_underun %d\n",
-		   le16_to_cpu(counters->tx_underun));
+	netdev_err(dev, "tx_underrun %d\n",
+		   le16_to_cpu(counters->tx_underrun));
 }
 
 static void rtase_tx_timeout(struct net_device *dev, unsigned int txqueue)
-- 
cgit v1.3-3-g829e


From b1e455cd864c9a29a84673255715154374c76ab6 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 9 Sep 2024 12:10:13 -0400
Subject: net: xilinx: axienet: Remove unused checksum variables

These variables are set but never used. Remove them.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Radhey Shyam Pandey <radhey.shyam.pandey@amd.com>
Link: https://patch.msgid.link/20240909161016.1149119-2-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h      |  5 -----
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 12 ------------
 2 files changed, 17 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 43d81b40f761..d64b8abcf018 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -529,8 +529,6 @@ struct skbuf_dma_descriptor {
  *		  supported, the maximum frame size would be 9k. Else it is
  *		  1522 bytes (assuming support for basic VLAN)
  * @rxmem:	Stores rx memory size for jumbo frame handling.
- * @csum_offload_on_tx_path:	Stores the checksum selection on TX side.
- * @csum_offload_on_rx_path:	Stores the checksum selection on RX side.
  * @coalesce_count_rx:	Store the irq coalesce on RX side.
  * @coalesce_usec_rx:	IRQ coalesce delay for RX
  * @coalesce_count_tx:	Store the irq coalesce on TX side.
@@ -609,9 +607,6 @@ struct axienet_local {
 	u32 max_frm_size;
 	u32 rxmem;
 
-	int csum_offload_on_tx_path;
-	int csum_offload_on_rx_path;
-
 	u32 coalesce_count_rx;
 	u32 coalesce_usec_rx;
 	u32 coalesce_count_tx;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 374dff70ef0d..90ccb0acb14a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2639,38 +2639,26 @@ static int axienet_probe(struct platform_device *pdev)
 	if (!ret) {
 		switch (value) {
 		case 1:
-			lp->csum_offload_on_tx_path =
-				XAE_FEATURE_PARTIAL_TX_CSUM;
 			lp->features |= XAE_FEATURE_PARTIAL_TX_CSUM;
 			/* Can checksum TCP/UDP over IPv4. */
 			ndev->features |= NETIF_F_IP_CSUM;
 			break;
 		case 2:
-			lp->csum_offload_on_tx_path =
-				XAE_FEATURE_FULL_TX_CSUM;
 			lp->features |= XAE_FEATURE_FULL_TX_CSUM;
 			/* Can checksum TCP/UDP over IPv4. */
 			ndev->features |= NETIF_F_IP_CSUM;
 			break;
-		default:
-			lp->csum_offload_on_tx_path = XAE_NO_CSUM_OFFLOAD;
 		}
 	}
 	ret = of_property_read_u32(pdev->dev.of_node, "xlnx,rxcsum", &value);
 	if (!ret) {
 		switch (value) {
 		case 1:
-			lp->csum_offload_on_rx_path =
-				XAE_FEATURE_PARTIAL_RX_CSUM;
 			lp->features |= XAE_FEATURE_PARTIAL_RX_CSUM;
 			break;
 		case 2:
-			lp->csum_offload_on_rx_path =
-				XAE_FEATURE_FULL_RX_CSUM;
 			lp->features |= XAE_FEATURE_FULL_RX_CSUM;
 			break;
-		default:
-			lp->csum_offload_on_rx_path = XAE_NO_CSUM_OFFLOAD;
 		}
 	}
 	/* For supporting jumbo frames, the Axi Ethernet hardware must have
-- 
cgit v1.3-3-g829e


From dd28f4c0e81f42ba998462db0d117d93af5b7cb8 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 9 Sep 2024 12:10:14 -0400
Subject: net: xilinx: axienet: Enable NETIF_F_HW_CSUM for partial tx
 checksumming

Partial tx chechsumming is completely generic and does not depend on the
L3/L4 protocol. Signal this to the net subsystem by enabling the
more-generic offload feature (instead of restricting ourselves to
TCP/UDP over IPv4 checksumming only like is necessary with full
checksumming).

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240909161016.1149119-3-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 90ccb0acb14a..37f19101fcf4 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2640,8 +2640,8 @@ static int axienet_probe(struct platform_device *pdev)
 		switch (value) {
 		case 1:
 			lp->features |= XAE_FEATURE_PARTIAL_TX_CSUM;
-			/* Can checksum TCP/UDP over IPv4. */
-			ndev->features |= NETIF_F_IP_CSUM;
+			/* Can checksum any contiguous range */
+			ndev->features |= NETIF_F_HW_CSUM;
 			break;
 		case 2:
 			lp->features |= XAE_FEATURE_FULL_TX_CSUM;
-- 
cgit v1.3-3-g829e


From 06c069ff2f7013f85bd071e8bfccc4808ac59da4 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 9 Sep 2024 12:10:15 -0400
Subject: net: xilinx: axienet: Set RXCSUM in features

When it is supported by hardware, we enable receive checksum offload
unconditionally. Update features to reflect this.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20240909161016.1149119-4-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 37f19101fcf4..86f17c44ae90 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -2655,9 +2655,11 @@ static int axienet_probe(struct platform_device *pdev)
 		switch (value) {
 		case 1:
 			lp->features |= XAE_FEATURE_PARTIAL_RX_CSUM;
+			ndev->features |= NETIF_F_RXCSUM;
 			break;
 		case 2:
 			lp->features |= XAE_FEATURE_FULL_RX_CSUM;
+			ndev->features |= NETIF_F_RXCSUM;
 			break;
 		}
 	}
-- 
cgit v1.3-3-g829e


From 736f0c7a8ec2d1d39aed0b3fb67127a37eb5311b Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 9 Sep 2024 12:10:16 -0400
Subject: net: xilinx: axienet: Relax partial rx checksum checks

The partial rx checksum feature computes a checksum over the entire
packet, regardless of the L3 protocol. Remove the check for IPv4.
Additionally, testing with csum.py (from kselftests) shows no anomalies
with 64-byte packets, so we can remove that check as well.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240909161016.1149119-5-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 86f17c44ae90..ea7d7c03f48e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1188,9 +1188,7 @@ static int axienet_rx_poll(struct napi_struct *napi, int budget)
 				    csumstatus == XAE_IP_UDP_CSUM_VALIDATED) {
 					skb->ip_summed = CHECKSUM_UNNECESSARY;
 				}
-			} else if ((lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) != 0 &&
-				   skb->protocol == htons(ETH_P_IP) &&
-				   skb->len > 64) {
+			} else if (lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) {
 				skb->csum = be32_to_cpu(cur_p->app3 & 0xFFFF);
 				skb->ip_summed = CHECKSUM_COMPLETE;
 			}
-- 
cgit v1.3-3-g829e


From 955f5b1508629c27682c9e5f6bad47769908b47f Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Mon, 9 Sep 2024 12:23:42 -0500
Subject: net: amlogic,meson-dwmac: Fix "amlogic,tx-delay-ns" schema

The "amlogic,tx-delay-ns" property schema has unnecessary type reference
as it's a standard unit suffix, and the constraints are in freeform
text rather than schema.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Link: https://patch.msgid.link/20240909172342.487675-2-robh@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/net/amlogic,meson-dwmac.yaml          | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
index ee7a65b528cd..d1e2bca3c503 100644
--- a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
@@ -58,18 +58,18 @@ allOf:
             - const: timing-adjustment
 
         amlogic,tx-delay-ns:
-          $ref: /schemas/types.yaml#/definitions/uint32
+          enum: [0, 2, 4, 6]
+          default: 2
           description:
-            The internal RGMII TX clock delay (provided by this driver) in
-            nanoseconds. Allowed values are 0ns, 2ns, 4ns, 6ns.
-            When phy-mode is set to "rgmii" then the TX delay should be
-            explicitly configured. When not configured a fallback of 2ns is
-            used. When the phy-mode is set to either "rgmii-id" or "rgmii-txid"
-            the TX clock delay is already provided by the PHY. In that case
-            this property should be set to 0ns (which disables the TX clock
-            delay in the MAC to prevent the clock from going off because both
-            PHY and MAC are adding a delay).
-            Any configuration is ignored when the phy-mode is set to "rmii".
+            The internal RGMII TX clock delay (provided by this driver)
+            in nanoseconds. When phy-mode is set to "rgmii" then the TX
+            delay should be explicitly configured. When the phy-mode is
+            set to either "rgmii-id" or "rgmii-txid" the TX clock delay
+            is already provided by the PHY. In that case this property
+            should be set to 0ns (which disables the TX clock delay in
+            the MAC to prevent the clock from going off because both
+            PHY and MAC are adding a delay). Any configuration is
+            ignored when the phy-mode is set to "rmii".
 
         amlogic,rx-delay-ns:
           deprecated: true
-- 
cgit v1.3-3-g829e


From f775cb1bbfd50cbbdafd4b18c1650eb5477ba769 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 9 Sep 2024 13:27:35 -0700
Subject: bnxt_en: Increase the number of MSIX vectors for RoCE device

If RocE is supported on the device, set the number of RoCE MSIX vectors
to the number of online CPUs + 1 and capped at these maximums:

VF: 2
NPAR: 5
PF: 64

For the PF, the maximum is now increased from the previous value
of 9 to get better performance for kernel applications.

Remove the unnecessary check for BNXT_FLAG_ROCE_CAP.
bnxt_set_dflt_ulp_msix() will only be called if the flag is set.

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240909202737.93852-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 14 ++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h |  6 ++++--
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index b9e7d3e7b15d..fdd6356f21ef 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -176,11 +176,17 @@ EXPORT_SYMBOL(bnxt_unregister_dev);
 
 static int bnxt_set_dflt_ulp_msix(struct bnxt *bp)
 {
-	u32 roce_msix = BNXT_VF(bp) ?
-			BNXT_MAX_VF_ROCE_MSIX : BNXT_MAX_ROCE_MSIX;
+	int roce_msix = BNXT_MAX_ROCE_MSIX;
 
-	return ((bp->flags & BNXT_FLAG_ROCE_CAP) ?
-		min_t(u32, roce_msix, num_online_cpus()) : 0);
+	if (BNXT_VF(bp))
+		roce_msix = BNXT_MAX_ROCE_MSIX_VF;
+	else if (bp->port_partition_type)
+		roce_msix = BNXT_MAX_ROCE_MSIX_NPAR_PF;
+
+	/* NQ MSIX vectors should match the number of CPUs plus 1 more for
+	 * the CREQ MSIX, up to the default.
+	 */
+	return min_t(int, roce_msix, num_online_cpus() + 1);
 }
 
 int bnxt_send_msg(struct bnxt_en_dev *edev,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index 4eafe6ec0abf..4f4914f5c84c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -15,8 +15,10 @@
 
 #define BNXT_MIN_ROCE_CP_RINGS	2
 #define BNXT_MIN_ROCE_STAT_CTXS	1
-#define BNXT_MAX_ROCE_MSIX	9
-#define BNXT_MAX_VF_ROCE_MSIX	2
+
+#define BNXT_MAX_ROCE_MSIX_VF		2
+#define BNXT_MAX_ROCE_MSIX_NPAR_PF	5
+#define BNXT_MAX_ROCE_MSIX		64
 
 struct hwrm_async_event_cmpl;
 struct bnxt;
-- 
cgit v1.3-3-g829e


From 2d51eb0bd81cfbafc762592ede9e9234063cc853 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 9 Sep 2024 13:27:36 -0700
Subject: bnxt_en: Add MSIX check in bnxt_check_rings()

bnxt_check_rings() is called to ensure that we have the hardware ring
resources before committing to reinitialize with the new number of
rings.  MSIX vectors are never checked at this point, because up
until recently we must first disable MSIX before we can allocate the
new set of MSIX vectors.

Now that we support dynamic MSIX allocation, check to make sure we
can dynamically allocate the new MSIX vectors as the last step in
bnxt_check_rings() if dynamic MSIX is supported.

For example, the IOMMU group may limit the number of MSIX vectors
for the device.  With this patch, the ring change will fail more
gracefully when there is not enough MSIX vectors.

It is also better to move bnxt_check_rings() to be called as the last
step when changing ethtool rings.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240909202737.93852-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 19 ++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 11 ++++++-----
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c9248ed9330c..6e422e24750a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13803,6 +13803,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	int max_rx, max_tx, max_cp, tx_sets = 1, tx_cp;
 	struct bnxt_hw_rings hwr = {0};
 	int rx_rings = rx;
+	int rc;
 
 	if (tcs)
 		tx_sets = tcs;
@@ -13835,7 +13836,23 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	}
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		hwr.cp_p5 = hwr.tx + rx;
-	return bnxt_hwrm_check_rings(bp, &hwr);
+	rc = bnxt_hwrm_check_rings(bp, &hwr);
+	if (!rc && pci_msix_can_alloc_dyn(bp->pdev)) {
+		if (!bnxt_ulp_registered(bp->edev)) {
+			hwr.cp += bnxt_get_ulp_msix_num(bp);
+			hwr.cp = min_t(int, hwr.cp, bnxt_get_max_func_irqs(bp));
+		}
+		if (hwr.cp > bp->total_irqs) {
+			int total_msix = bnxt_change_msix(bp, hwr.cp);
+
+			if (total_msix < hwr.cp) {
+				netdev_warn(bp->dev, "Unable to allocate %d MSIX vectors, maximum available %d\n",
+					    hwr.cp, total_msix);
+				rc = -ENOSPC;
+			}
+		}
+	}
+	return rc;
 }
 
 static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 094e0b5c8521..f71cc8188b4e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -955,11 +955,6 @@ static int bnxt_set_channels(struct net_device *dev,
 		}
 		tx_xdp = req_rx_rings;
 	}
-	rc = bnxt_check_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, tx_xdp);
-	if (rc) {
-		netdev_warn(dev, "Unable to allocate the requested rings\n");
-		return rc;
-	}
 
 	if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) !=
 	    bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) &&
@@ -968,6 +963,12 @@ static int bnxt_set_channels(struct net_device *dev,
 		return -EINVAL;
 	}
 
+	rc = bnxt_check_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, tx_xdp);
+	if (rc) {
+		netdev_warn(dev, "Unable to allocate the requested rings\n");
+		return rc;
+	}
+
 	if (netif_running(dev)) {
 		if (BNXT_PF(bp)) {
 			/* TODO CHIMP_FW: Send message to all VF's
-- 
cgit v1.3-3-g829e


From f77cdee5db06c6e4c30573889964c4cf1e3042a3 Mon Sep 17 00:00:00 2001
From: Edwin Peer <edwin.peer@broadcom.com>
Date: Mon, 9 Sep 2024 13:27:37 -0700
Subject: bnxt_en: resize bnxt_irq name field to fit format string

The name field of struct bnxt_irq is written using snprintf in
bnxt_setup_msix(). Make the field large enough to fit the maximal
formatted string to prevent truncation.  Truncated IRQ names are
less meaningful to the user.  For example, "enp4s0f0np0-TxRx-0"
gets truncated to "enp4s0f0np0-TxRx-" with the existing code.

Make sure we have space for the extra characters added to the IRQ
names:

  - the characters introduced by the static format string: hyphens
  - the maximal static substituted ring type string: "TxRx"
  - the maximum length of an integer formatted as a string, even
    though reasonable ring numbers would never be as long as this.

Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240909202737.93852-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3b805ed433ed..69231e85140b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1217,12 +1217,15 @@ struct bnxt_napi {
 	bool			in_reset;
 };
 
+/* "TxRx", 2 hypens, plus maximum integer */
+#define BNXT_IRQ_NAME_EXTRA	17
+
 struct bnxt_irq {
 	irq_handler_t	handler;
 	unsigned int	vector;
 	u8		requested:1;
 	u8		have_cpumask:1;
-	char		name[IFNAMSIZ + 2];
+	char		name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
 	cpumask_var_t	cpu_mask;
 };
 
-- 
cgit v1.3-3-g829e


From 221013afb459e5deb8bd08e29b37050af5586d1c Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Date: Mon, 9 Sep 2024 09:27:41 +0200
Subject: can: Switch back to struct platform_driver::remove()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit 0edb555a65d1 ("platform: Make platform_driver::remove()
return void") .remove() is (again) the right callback to implement for
platform drivers.

Convert all can drivers to use .remove(), with the eventual goal to drop
struct platform_driver::remove_new(). As .remove() and .remove_new() have
the same prototypes, conversion is done by just changing the structure
member name in the driver initializer.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://patch.msgid.link/20240909072742.381003-2-u.kleine-koenig@baylibre.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/at91_can.c                   | 2 +-
 drivers/net/can/bxcan.c                      | 2 +-
 drivers/net/can/c_can/c_can_platform.c       | 2 +-
 drivers/net/can/cc770/cc770_isa.c            | 2 +-
 drivers/net/can/cc770/cc770_platform.c       | 2 +-
 drivers/net/can/ctucanfd/ctucanfd_platform.c | 2 +-
 drivers/net/can/flexcan/flexcan-core.c       | 2 +-
 drivers/net/can/grcan.c                      | 2 +-
 drivers/net/can/ifi_canfd/ifi_canfd.c        | 2 +-
 drivers/net/can/janz-ican3.c                 | 2 +-
 drivers/net/can/m_can/m_can_platform.c       | 2 +-
 drivers/net/can/mscan/mpc5xxx_can.c          | 2 +-
 drivers/net/can/rcar/rcar_can.c              | 2 +-
 drivers/net/can/rcar/rcar_canfd.c            | 2 +-
 drivers/net/can/sja1000/sja1000_isa.c        | 2 +-
 drivers/net/can/sja1000/sja1000_platform.c   | 2 +-
 drivers/net/can/softing/softing_main.c       | 2 +-
 drivers/net/can/sun4i_can.c                  | 2 +-
 drivers/net/can/ti_hecc.c                    | 2 +-
 drivers/net/can/xilinx_can.c                 | 2 +-
 20 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 11f434d708b3..191707d7e3da 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -1191,7 +1191,7 @@ MODULE_DEVICE_TABLE(platform, at91_can_id_table);
 
 static struct platform_driver at91_can_driver = {
 	.probe = at91_can_probe,
-	.remove_new = at91_can_remove,
+	.remove = at91_can_remove,
 	.driver = {
 		.name = KBUILD_MODNAME,
 		.of_match_table = of_match_ptr(at91_can_dt_ids),
diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c
index 49cf9682b925..bfc60eb33dc3 100644
--- a/drivers/net/can/bxcan.c
+++ b/drivers/net/can/bxcan.c
@@ -1092,7 +1092,7 @@ static struct platform_driver bxcan_driver = {
 		.of_match_table = bxcan_of_match,
 	},
 	.probe = bxcan_probe,
-	.remove_new = bxcan_remove,
+	.remove = bxcan_remove,
 };
 
 module_platform_driver(bxcan_driver);
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index e2ec69aa46e5..6cba9717a6d8 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -476,7 +476,7 @@ static struct platform_driver c_can_plat_driver = {
 		.of_match_table = c_can_of_table,
 	},
 	.probe = c_can_plat_probe,
-	.remove_new = c_can_plat_remove,
+	.remove = c_can_plat_remove,
 	.suspend = c_can_suspend,
 	.resume = c_can_resume,
 	.id_table = c_can_id_table,
diff --git a/drivers/net/can/cc770/cc770_isa.c b/drivers/net/can/cc770/cc770_isa.c
index 22009440a983..d06762817153 100644
--- a/drivers/net/can/cc770/cc770_isa.c
+++ b/drivers/net/can/cc770/cc770_isa.c
@@ -307,7 +307,7 @@ static void cc770_isa_remove(struct platform_device *pdev)
 
 static struct platform_driver cc770_isa_driver = {
 	.probe = cc770_isa_probe,
-	.remove_new = cc770_isa_remove,
+	.remove = cc770_isa_remove,
 	.driver = {
 		.name = KBUILD_MODNAME,
 	},
diff --git a/drivers/net/can/cc770/cc770_platform.c b/drivers/net/can/cc770/cc770_platform.c
index f2424fe58612..b6c4f02ffb97 100644
--- a/drivers/net/can/cc770/cc770_platform.c
+++ b/drivers/net/can/cc770/cc770_platform.c
@@ -247,7 +247,7 @@ static struct platform_driver cc770_platform_driver = {
 		.of_match_table = cc770_platform_table,
 	},
 	.probe = cc770_platform_probe,
-	.remove_new = cc770_platform_remove,
+	.remove = cc770_platform_remove,
 };
 
 module_platform_driver(cc770_platform_driver);
diff --git a/drivers/net/can/ctucanfd/ctucanfd_platform.c b/drivers/net/can/ctucanfd/ctucanfd_platform.c
index 55bb10b157b4..70e2577c8541 100644
--- a/drivers/net/can/ctucanfd/ctucanfd_platform.c
+++ b/drivers/net/can/ctucanfd/ctucanfd_platform.c
@@ -111,7 +111,7 @@ MODULE_DEVICE_TABLE(of, ctucan_of_match);
 
 static struct platform_driver ctucanfd_driver = {
 	.probe	= ctucan_platform_probe,
-	.remove_new = ctucan_platform_remove,
+	.remove = ctucan_platform_remove,
 	.driver	= {
 		.name = DRV_NAME,
 		.pm = &ctucan_platform_pm_ops,
diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index d11411029330..ac1a860986df 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -2385,7 +2385,7 @@ static struct platform_driver flexcan_driver = {
 		.of_match_table = flexcan_of_match,
 	},
 	.probe = flexcan_probe,
-	.remove_new = flexcan_remove,
+	.remove = flexcan_remove,
 	.id_table = flexcan_id_table,
 };
 
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index 6d3ba71a6a73..cdf0ec9fa7f3 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1725,7 +1725,7 @@ static struct platform_driver grcan_driver = {
 		.of_match_table = grcan_match,
 	},
 	.probe = grcan_probe,
-	.remove_new = grcan_remove,
+	.remove = grcan_remove,
 };
 
 module_platform_driver(grcan_driver);
diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c
index 72307297d75e..d32b10900d2f 100644
--- a/drivers/net/can/ifi_canfd/ifi_canfd.c
+++ b/drivers/net/can/ifi_canfd/ifi_canfd.c
@@ -1033,7 +1033,7 @@ static struct platform_driver ifi_canfd_plat_driver = {
 		.of_match_table	= ifi_canfd_of_table,
 	},
 	.probe	= ifi_canfd_plat_probe,
-	.remove_new = ifi_canfd_plat_remove,
+	.remove = ifi_canfd_plat_remove,
 };
 
 module_platform_driver(ifi_canfd_plat_driver);
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index d048ea565b89..60c7b83b4539 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -2049,7 +2049,7 @@ static struct platform_driver ican3_driver = {
 		.name	= DRV_NAME,
 	},
 	.probe		= ican3_probe,
-	.remove_new	= ican3_remove,
+	.remove		= ican3_remove,
 };
 
 module_platform_driver(ican3_driver);
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index 983ab80260dd..b832566efda0 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -231,7 +231,7 @@ static struct platform_driver m_can_plat_driver = {
 		.pm     = &m_can_pmops,
 	},
 	.probe = m_can_plat_probe,
-	.remove_new = m_can_plat_remove,
+	.remove = m_can_plat_remove,
 };
 
 module_platform_driver(m_can_plat_driver);
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index 5b3d69c3b6b6..0080c39ee182 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -435,7 +435,7 @@ static struct platform_driver mpc5xxx_can_driver = {
 		.of_match_table = mpc5xxx_can_table,
 	},
 	.probe = mpc5xxx_can_probe,
-	.remove_new = mpc5xxx_can_remove,
+	.remove = mpc5xxx_can_remove,
 #ifdef CONFIG_PM
 	.suspend = mpc5xxx_can_suspend,
 	.resume = mpc5xxx_can_resume,
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index f5aa5dbacaf2..2b7dd359f27b 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -907,7 +907,7 @@ static struct platform_driver rcar_can_driver = {
 		.pm = &rcar_can_pm_ops,
 	},
 	.probe = rcar_can_probe,
-	.remove_new = rcar_can_remove,
+	.remove = rcar_can_remove,
 };
 
 module_platform_driver(rcar_can_driver);
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index c919668bbe7a..df1a5d0b37b2 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -2118,7 +2118,7 @@ static struct platform_driver rcar_canfd_driver = {
 		.pm = &rcar_canfd_pm_ops,
 	},
 	.probe = rcar_canfd_probe,
-	.remove_new = rcar_canfd_remove,
+	.remove = rcar_canfd_remove,
 };
 
 module_platform_driver(rcar_canfd_driver);
diff --git a/drivers/net/can/sja1000/sja1000_isa.c b/drivers/net/can/sja1000/sja1000_isa.c
index fca5a9a1d857..2d1f715459d7 100644
--- a/drivers/net/can/sja1000/sja1000_isa.c
+++ b/drivers/net/can/sja1000/sja1000_isa.c
@@ -245,7 +245,7 @@ static void sja1000_isa_remove(struct platform_device *pdev)
 
 static struct platform_driver sja1000_isa_driver = {
 	.probe = sja1000_isa_probe,
-	.remove_new = sja1000_isa_remove,
+	.remove = sja1000_isa_remove,
 	.driver = {
 		.name = DRV_NAME,
 	},
diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c
index 33f0e46ab1c2..c42ebe9da55a 100644
--- a/drivers/net/can/sja1000/sja1000_platform.c
+++ b/drivers/net/can/sja1000/sja1000_platform.c
@@ -329,7 +329,7 @@ static void sp_remove(struct platform_device *pdev)
 
 static struct platform_driver sp_driver = {
 	.probe = sp_probe,
-	.remove_new = sp_remove,
+	.remove = sp_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = sp_of_table,
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index bd25137062c5..278ee8722770 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -854,7 +854,7 @@ static struct platform_driver softing_driver = {
 		.name = KBUILD_MODNAME,
 	},
 	.probe = softing_pdev_probe,
-	.remove_new = softing_pdev_remove,
+	.remove = softing_pdev_remove,
 };
 
 module_platform_driver(softing_driver);
diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index ab8d01784686..360158c295d3 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -914,7 +914,7 @@ static struct platform_driver sun4i_can_driver = {
 		.of_match_table = sun4ican_of_match,
 	},
 	.probe = sun4ican_probe,
-	.remove_new = sun4ican_remove,
+	.remove = sun4ican_remove,
 };
 
 module_platform_driver(sun4i_can_driver);
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 5aab440074c6..644e8b8eb91e 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -1025,7 +1025,7 @@ static struct platform_driver ti_hecc_driver = {
 		.of_match_table = ti_hecc_dt_ids,
 	},
 	.probe = ti_hecc_probe,
-	.remove_new = ti_hecc_remove,
+	.remove = ti_hecc_remove,
 	.suspend = ti_hecc_suspend,
 	.resume = ti_hecc_resume,
 };
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index d944911d7f05..436c0e4b0344 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -2103,7 +2103,7 @@ static void xcan_remove(struct platform_device *pdev)
 
 static struct platform_driver xcan_driver = {
 	.probe = xcan_probe,
-	.remove_new = xcan_remove,
+	.remove = xcan_remove,
 	.driver	= {
 		.name = DRIVER_NAME,
 		.pm = &xcan_dev_pm_ops,
-- 
cgit v1.3-3-g829e


From fe1456451a111203860e124cda8396f8f2c9c16c Mon Sep 17 00:00:00 2001
From: Stefan Mätje <stefan.maetje@esd.eu>
Date: Tue, 10 Sep 2024 19:02:36 +0200
Subject: can: usb: Kconfig: Fix list of devices for esd_usb driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The CAN-USB/3-FD was missing on the list of supported devices.

Signed-off-by: Stefan Mätje <stefan.maetje@esd.eu>
Link: https://patch.msgid.link/20240910170236.2287637-1-stefan.maetje@esd.eu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 3e1fba12c0c3..9dae0c71a2e1 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -17,11 +17,12 @@ config CAN_EMS_USB
 config CAN_ESD_USB
 	tristate "esd electronics gmbh CAN/USB interfaces"
 	help
-	  This driver adds supports for several CAN/USB interfaces
+	  This driver adds support for several CAN/USB interfaces
 	  from esd electronics gmbh (https://www.esd.eu).
 
 	  The drivers supports the following devices:
 	    - esd CAN-USB/2
+	    - esd CAN-USB/3-FD
 	    - esd CAN-USB/Micro
 
 	  To compile this driver as a module, choose M here: the module
-- 
cgit v1.3-3-g829e


From 709cbd5bb49b54c3d73c1a89b8ebce09c10ed2ed Mon Sep 17 00:00:00 2001
From: Jake Hamby <Jake.Hamby@Teledyne.com>
Date: Fri, 6 Sep 2024 23:19:51 +0000
Subject: can: m_can: m_can_chip_config(): mask timestamp wraparound IRQ

On the Microchip SAMA7G54 MPU the IR_TSW (timestamp wraparound) fires
at about 1 Hz, but the driver doesn't care about it. Add it to the
list of interrupts to disable in m_can_chip_config to reduce unneeded
wakeups.

Link: https://patch.msgid.link/DM8PR14MB5221D9DD3A7F2130EF161AF7EF9E2@DM8PR14MB5221.namprd14.prod.outlook.com
Signed-off-by: Jake Hamby <Jake.Hamby@Teledyne.com>
Link: https://patch.msgid.link/20240911-can-m_can-mask-timestamp-wraparound-irq-v1-1-0155b70dc827@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 012c3d22b01d..a7b3bc439ae5 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1434,7 +1434,8 @@ static int m_can_chip_config(struct net_device *dev)
 
 	/* Disable unused interrupts */
 	interrupts &= ~(IR_ARA | IR_ELO | IR_DRX | IR_TEFF | IR_TFE | IR_TCF |
-			IR_HPM | IR_RF1F | IR_RF1W | IR_RF1N | IR_RF0F);
+			IR_HPM | IR_RF1F | IR_RF1W | IR_RF1N | IR_RF0F |
+			IR_TSW);
 
 	err = m_can_config_enable(cdev);
 	if (err)
-- 
cgit v1.3-3-g829e


From cd0983c7f8809d685bc57eda1f11cc1cdb67b9ac Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Sep 2024 11:21:04 +0000
Subject: can: rockchip_canfd: rkcanfd_timestamp_init(): rework delay
 calculation

Rework the delay calculation to only require a single 64-bit division.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
[mkl: port to on-top of existing 32-bit division fix]
Link: https://patch.msgid.link/20240911-can-rockchip_canfd-fixes-v1-1-5ce385b5ab10@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-timestamp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
index fb1a8f4e6217..43d4b5721812 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -71,8 +71,8 @@ void rkcanfd_timestamp_init(struct rkcanfd_priv *priv)
 
 	max_cycles = div_u64(ULLONG_MAX, cc->mult);
 	max_cycles = min(max_cycles, cc->mask);
-	work_delay_ns = div_u64(clocksource_cyc2ns(max_cycles, cc->mult, cc->shift), 3);
-	priv->work_delay_jiffies = nsecs_to_jiffies(work_delay_ns);
+	work_delay_ns = clocksource_cyc2ns(max_cycles, cc->mult, cc->shift);
+	priv->work_delay_jiffies = div_u64(work_delay_ns, 3u * NSEC_PER_SEC / HZ);
 	INIT_DELAYED_WORK(&priv->timestamp, rkcanfd_timestamp_work);
 
 	netdev_dbg(priv->ndev, "clock=%lu.%02luMHz bitrate=%lu.%02luMBit/s div=%u rate=%lu.%02luMHz mult=%u shift=%u delay=%lus\n",
-- 
cgit v1.3-3-g829e


From a63e10462af67257b99b5330b32d1a47583803e2 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 11 Sep 2024 10:09:48 +0200
Subject: can: rockchip_canfd: rkcanfd_handle_error_int_reg_ec(): fix decoding
 of error code register

Probably due to a copy/paste error rkcanfd_handle_error_int_reg_ec()
checks twice if the RKCANFD_REG_ERROR_CODE_TX_ACK_EOF bit is set in
reg_ec.

Keep the correct check for RKCANFD_REG_ERROR_CODE_TX_ACK_EOF and
remove the superfluous one.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://patch.msgid.link/9a46d10d-e4e3-40a5-8fb6-f4637959f124@stanley.mountain
Fixes: ff60bfbaf67f ("can: rockchip_canfd: add driver for Rockchip CAN-FD controller")
Link: https://patch.msgid.link/20240911-can-rockchip_canfd-fixes-v1-2-5ce385b5ab10@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 6883153e8fc1..df18c85fc078 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -491,11 +491,9 @@ rkcanfd_handle_error_int_reg_ec(struct rkcanfd_priv *priv, struct can_frame *cf,
 		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_CRC)
 			cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
 		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_ACK_EOF)
-			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
+			cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
 		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_ACK)
 			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
-		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_ACK_EOF)
-			cf->data[3] = CAN_ERR_PROT_LOC_ACK_DEL;
 		/* RKCANFD_REG_ERROR_CODE_TX_ERROR */
 		else if (reg_ec & RKCANFD_REG_ERROR_CODE_TX_OVERLOAD)
 			cf->data[2] |= CAN_ERR_PROT_OVERLOAD;
-- 
cgit v1.3-3-g829e


From 4b3fc475c61fa8733a9acc9d743f6cc9ca4915f5 Mon Sep 17 00:00:00 2001
From: Russell King <linux@armlinux.org.uk>
Date: Fri, 6 Sep 2024 16:05:07 +0530
Subject: net: phylink: Add phylink_set_fixed_link() to configure fixed link
 state in phylink

The function allows for the configuration of a fixed link state for a given
phylink instance. This addition is particularly useful for network devices that
operate with a fixed link configuration, where the link parameters do not change
dynamically. By using `phylink_set_fixed_link()`, drivers can easily set up
the fixed link state during initialization or configuration changes.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <linux@armlinux.org.uk>
Signed-off-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/phylink.h   |  2 ++
 2 files changed, 44 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index ab4e9fc03017..4309317de3d1 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1635,6 +1635,48 @@ static int phylink_register_sfp(struct phylink *pl,
 	return ret;
 }
 
+/**
+ * phylink_set_fixed_link() - set the fixed link
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ * @state: a pointer to a struct phylink_link_state.
+ *
+ * This function is used when the link parameters are known and do not change,
+ * making it suitable for certain types of network connections.
+ *
+ * Returns: zero on success or negative error code.
+ */
+int phylink_set_fixed_link(struct phylink *pl,
+			   const struct phylink_link_state *state)
+{
+	const struct phy_setting *s;
+	unsigned long *adv;
+
+	if (pl->cfg_link_an_mode != MLO_AN_PHY || !state ||
+	    !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state))
+		return -EINVAL;
+
+	s = phy_lookup_setting(state->speed, state->duplex,
+			       pl->supported, true);
+	if (!s)
+		return -EINVAL;
+
+	adv = pl->link_config.advertising;
+	linkmode_zero(adv);
+	linkmode_set_bit(s->bit, adv);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, adv);
+
+	pl->link_config.speed = state->speed;
+	pl->link_config.duplex = state->duplex;
+	pl->link_config.link = 1;
+	pl->link_config.an_complete = 1;
+
+	pl->cfg_link_an_mode = MLO_AN_FIXED;
+	pl->cur_link_an_mode = pl->cfg_link_an_mode;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(phylink_set_fixed_link);
+
 /**
  * phylink_create() - create a phylink instance
  * @config: a pointer to the target &struct phylink_config
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 2381e07429a2..5c01048860c4 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -598,6 +598,8 @@ int phylink_fwnode_phy_connect(struct phylink *pl,
 			       const struct fwnode_handle *fwnode,
 			       u32 flags);
 void phylink_disconnect_phy(struct phylink *);
+int phylink_set_fixed_link(struct phylink *,
+			   const struct phylink_link_state *);
 
 void phylink_mac_change(struct phylink *, bool up);
 void phylink_pcs_change(struct phylink_pcs *, bool up);
-- 
cgit v1.3-3-g829e


From ef0250456cc33f741d5cfd3dcc2d044ab7882758 Mon Sep 17 00:00:00 2001
From: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Date: Fri, 6 Sep 2024 16:05:08 +0530
Subject: net: lan743x: Create separate PCS power reset function

Create separate PCS power reset function from lan743x_sgmii_config () to use
as subroutine.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 55 ++++++++++++++-------------
 1 file changed, 29 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index e418539565b1..ce1e104adc20 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1147,12 +1147,39 @@ static int lan743x_pcs_seq_state(struct lan743x_adapter *adapter, u8 state)
 	return 0;
 }
 
+static int lan743x_pcs_power_reset(struct lan743x_adapter *adapter)
+{
+	int mii_ctl;
+	int ret;
+
+	/* SGMII/1000/2500BASE-X PCS power down */
+	mii_ctl = lan743x_sgmii_read(adapter, MDIO_MMD_VEND2, MII_BMCR);
+	if (mii_ctl < 0)
+		return mii_ctl;
+
+	mii_ctl |= BMCR_PDOWN;
+	ret = lan743x_sgmii_write(adapter, MDIO_MMD_VEND2, MII_BMCR, mii_ctl);
+	if (ret < 0)
+		return ret;
+
+	ret = lan743x_pcs_seq_state(adapter, PCS_POWER_STATE_DOWN);
+	if (ret < 0)
+		return ret;
+
+	/* SGMII/1000/2500BASE-X PCS power up */
+	mii_ctl &= ~BMCR_PDOWN;
+	ret = lan743x_sgmii_write(adapter, MDIO_MMD_VEND2, MII_BMCR, mii_ctl);
+	if (ret < 0)
+		return ret;
+
+	return lan743x_pcs_seq_state(adapter, PCS_POWER_STATE_UP);
+}
+
 static int lan743x_sgmii_config(struct lan743x_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct phy_device *phydev = netdev->phydev;
 	enum lan743x_sgmii_lsd lsd = POWER_DOWN;
-	int mii_ctl;
 	bool status;
 	int ret;
 
@@ -1209,31 +1236,7 @@ static int lan743x_sgmii_config(struct lan743x_adapter *adapter)
 		netif_dbg(adapter, drv, adapter->netdev,
 			  "SGMII 1G mode enable\n");
 
-	/* SGMII/1000/2500BASE-X PCS power down */
-	mii_ctl = lan743x_sgmii_read(adapter, MDIO_MMD_VEND2, MII_BMCR);
-	if (mii_ctl < 0)
-		return mii_ctl;
-
-	mii_ctl |= BMCR_PDOWN;
-	ret = lan743x_sgmii_write(adapter, MDIO_MMD_VEND2, MII_BMCR, mii_ctl);
-	if (ret < 0)
-		return ret;
-
-	ret = lan743x_pcs_seq_state(adapter, PCS_POWER_STATE_DOWN);
-	if (ret < 0)
-		return ret;
-
-	/* SGMII/1000/2500BASE-X PCS power up */
-	mii_ctl &= ~BMCR_PDOWN;
-	ret = lan743x_sgmii_write(adapter, MDIO_MMD_VEND2, MII_BMCR, mii_ctl);
-	if (ret < 0)
-		return ret;
-
-	ret = lan743x_pcs_seq_state(adapter, PCS_POWER_STATE_UP);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return lan743x_pcs_power_reset(adapter);
 }
 
 static void lan743x_mac_set_address(struct lan743x_adapter *adapter,
-- 
cgit v1.3-3-g829e


From 92b740a43fea39949242a736d70cc6f483ffed04 Mon Sep 17 00:00:00 2001
From: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Date: Fri, 6 Sep 2024 16:05:09 +0530
Subject: net: lan743x: Create separate Link Speed Duplex state function

Create separate Link Speed Duplex (LSD) update state function from
lan743x_sgmii_config () to use as subroutine.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 75 ++++++++++++++++-----------
 1 file changed, 45 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index ce1e104adc20..b4a4c2840a83 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -992,6 +992,42 @@ static int lan743x_sgmii_write(struct lan743x_adapter *adapter,
 	return ret;
 }
 
+static int lan743x_get_lsd(int speed, int duplex, u8 mss)
+{
+	int lsd;
+
+	switch (speed) {
+	case SPEED_2500:
+		if (mss == MASTER_SLAVE_STATE_SLAVE)
+			lsd = LINK_2500_SLAVE;
+		else
+			lsd = LINK_2500_MASTER;
+		break;
+	case SPEED_1000:
+		if (mss == MASTER_SLAVE_STATE_SLAVE)
+			lsd = LINK_1000_SLAVE;
+		else
+			lsd = LINK_1000_MASTER;
+		break;
+	case SPEED_100:
+		if (duplex == DUPLEX_FULL)
+			lsd = LINK_100FD;
+		else
+			lsd = LINK_100HD;
+		break;
+	case SPEED_10:
+		if (duplex == DUPLEX_FULL)
+			lsd = LINK_10FD;
+		else
+			lsd = LINK_10HD;
+		break;
+	default:
+		lsd = -EINVAL;
+	}
+
+	return lsd;
+}
+
 static int lan743x_sgmii_mpll_set(struct lan743x_adapter *adapter,
 				  u16 baud)
 {
@@ -1179,42 +1215,21 @@ static int lan743x_sgmii_config(struct lan743x_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct phy_device *phydev = netdev->phydev;
-	enum lan743x_sgmii_lsd lsd = POWER_DOWN;
 	bool status;
 	int ret;
 
-	switch (phydev->speed) {
-	case SPEED_2500:
-		if (phydev->master_slave_state == MASTER_SLAVE_STATE_MASTER)
-			lsd = LINK_2500_MASTER;
-		else
-			lsd = LINK_2500_SLAVE;
-		break;
-	case SPEED_1000:
-		if (phydev->master_slave_state == MASTER_SLAVE_STATE_MASTER)
-			lsd = LINK_1000_MASTER;
-		else
-			lsd = LINK_1000_SLAVE;
-		break;
-	case SPEED_100:
-		if (phydev->duplex)
-			lsd = LINK_100FD;
-		else
-			lsd = LINK_100HD;
-		break;
-	case SPEED_10:
-		if (phydev->duplex)
-			lsd = LINK_10FD;
-		else
-			lsd = LINK_10HD;
-		break;
-	default:
+	ret = lan743x_get_lsd(phydev->speed, phydev->duplex,
+			      phydev->master_slave_state);
+	if (ret < 0) {
 		netif_err(adapter, drv, adapter->netdev,
-			  "Invalid speed %d\n", phydev->speed);
-		return -EINVAL;
+			  "error %d link-speed-duplex(LSD) invalid\n", ret);
+		return ret;
 	}
 
-	adapter->sgmii_lsd = lsd;
+	adapter->sgmii_lsd = ret;
+	netif_dbg(adapter, drv, adapter->netdev,
+		  "Link Speed Duplex (lsd) : 0x%X\n", adapter->sgmii_lsd);
+
 	ret = lan743x_sgmii_aneg_update(adapter);
 	if (ret < 0) {
 		netif_err(adapter, drv, adapter->netdev,
-- 
cgit v1.3-3-g829e


From a5f199a8d8a03512199a9e7cdd4d8ea06c943295 Mon Sep 17 00:00:00 2001
From: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Date: Fri, 6 Sep 2024 16:05:10 +0530
Subject: net: lan743x: Migrate phylib to phylink

Migrate phy support from phylib to phylink.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/Kconfig        |   5 +-
 drivers/net/ethernet/microchip/lan743x_main.c | 566 ++++++++++++++++----------
 drivers/net/ethernet/microchip/lan743x_main.h |   3 +
 3 files changed, 349 insertions(+), 225 deletions(-)

diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index ce2435987fb6..2e3eb37a45cd 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -46,12 +46,13 @@ config LAN743X
 	tristate "LAN743x support"
 	depends on PCI
 	depends on PTP_1588_CLOCK_OPTIONAL
-	select PHYLIB
 	select FIXED_PHY
 	select CRC16
 	select CRC32
+	select PHYLINK
 	help
-	  Support for the Microchip LAN743x PCI Express Gigabit Ethernet chip
+	  Support for the Microchip LAN743x and PCI11x1x families of PCI
+	  Express Ethernet devices
 
 	  To compile this driver as a module, choose M here. The module will be
 	  called lan743x.
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index b4a4c2840a83..2767bfa4bdec 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -15,6 +15,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/iopoll.h>
 #include <linux/crc16.h>
+#include <linux/phylink.h>
 #include "lan743x_main.h"
 #include "lan743x_ethtool.h"
 
@@ -1077,26 +1078,7 @@ static int lan743x_sgmii_2_5G_mode_set(struct lan743x_adapter *adapter,
 					      VR_MII_BAUD_RATE_1P25GBPS);
 }
 
-static int lan743x_is_sgmii_2_5G_mode(struct lan743x_adapter *adapter,
-				      bool *status)
-{
-	int ret;
-
-	ret = lan743x_sgmii_read(adapter, MDIO_MMD_VEND2,
-				 VR_MII_GEN2_4_MPLL_CTRL1);
-	if (ret < 0)
-		return ret;
-
-	if (ret == VR_MII_MPLL_MULTIPLIER_125 ||
-	    ret == VR_MII_MPLL_MULTIPLIER_50)
-		*status = true;
-	else
-		*status = false;
-
-	return 0;
-}
-
-static int lan743x_sgmii_aneg_update(struct lan743x_adapter *adapter)
+static int lan743x_serdes_clock_and_aneg_update(struct lan743x_adapter *adapter)
 {
 	enum lan743x_sgmii_lsd lsd = adapter->sgmii_lsd;
 	int mii_ctrl;
@@ -1211,49 +1193,6 @@ static int lan743x_pcs_power_reset(struct lan743x_adapter *adapter)
 	return lan743x_pcs_seq_state(adapter, PCS_POWER_STATE_UP);
 }
 
-static int lan743x_sgmii_config(struct lan743x_adapter *adapter)
-{
-	struct net_device *netdev = adapter->netdev;
-	struct phy_device *phydev = netdev->phydev;
-	bool status;
-	int ret;
-
-	ret = lan743x_get_lsd(phydev->speed, phydev->duplex,
-			      phydev->master_slave_state);
-	if (ret < 0) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "error %d link-speed-duplex(LSD) invalid\n", ret);
-		return ret;
-	}
-
-	adapter->sgmii_lsd = ret;
-	netif_dbg(adapter, drv, adapter->netdev,
-		  "Link Speed Duplex (lsd) : 0x%X\n", adapter->sgmii_lsd);
-
-	ret = lan743x_sgmii_aneg_update(adapter);
-	if (ret < 0) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "error %d SGMII cfg failed\n", ret);
-		return ret;
-	}
-
-	ret = lan743x_is_sgmii_2_5G_mode(adapter, &status);
-	if (ret < 0) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "error %d SGMII get mode failed\n", ret);
-		return ret;
-	}
-
-	if (status)
-		netif_dbg(adapter, drv, adapter->netdev,
-			  "SGMII 2.5G mode enable\n");
-	else
-		netif_dbg(adapter, drv, adapter->netdev,
-			  "SGMII 1G mode enable\n");
-
-	return lan743x_pcs_power_reset(adapter);
-}
-
 static void lan743x_mac_set_address(struct lan743x_adapter *adapter,
 				    u8 *addr)
 {
@@ -1407,103 +1346,11 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter)
 				  50000, 1000000);
 }
 
-static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter,
-					   u16 local_adv, u16 remote_adv)
-{
-	struct lan743x_phy *phy = &adapter->phy;
-	u8 cap;
-
-	if (phy->fc_autoneg)
-		cap = mii_resolve_flowctrl_fdx(local_adv, remote_adv);
-	else
-		cap = phy->fc_request_control;
-
-	lan743x_mac_flow_ctrl_set_enables(adapter,
-					  cap & FLOW_CTRL_TX,
-					  cap & FLOW_CTRL_RX);
-}
-
 static int lan743x_phy_init(struct lan743x_adapter *adapter)
 {
 	return lan743x_phy_reset(adapter);
 }
 
-static void lan743x_phy_link_status_change(struct net_device *netdev)
-{
-	struct lan743x_adapter *adapter = netdev_priv(netdev);
-	struct phy_device *phydev = netdev->phydev;
-	u32 data;
-
-	phy_print_status(phydev);
-	if (phydev->state == PHY_RUNNING) {
-		int remote_advertisement = 0;
-		int local_advertisement = 0;
-
-		data = lan743x_csr_read(adapter, MAC_CR);
-
-		/* set duplex mode */
-		if (phydev->duplex)
-			data |= MAC_CR_DPX_;
-		else
-			data &= ~MAC_CR_DPX_;
-
-		/* set bus speed */
-		switch (phydev->speed) {
-		case SPEED_10:
-			data &= ~MAC_CR_CFG_H_;
-			data &= ~MAC_CR_CFG_L_;
-		break;
-		case SPEED_100:
-			data &= ~MAC_CR_CFG_H_;
-			data |= MAC_CR_CFG_L_;
-		break;
-		case SPEED_1000:
-			data |= MAC_CR_CFG_H_;
-			data &= ~MAC_CR_CFG_L_;
-		break;
-		case SPEED_2500:
-			data |= MAC_CR_CFG_H_;
-			data |= MAC_CR_CFG_L_;
-		break;
-		}
-		lan743x_csr_write(adapter, MAC_CR, data);
-
-		local_advertisement =
-			linkmode_adv_to_mii_adv_t(phydev->advertising);
-		remote_advertisement =
-			linkmode_adv_to_mii_adv_t(phydev->lp_advertising);
-
-		lan743x_phy_update_flowcontrol(adapter, local_advertisement,
-					       remote_advertisement);
-		lan743x_ptp_update_latency(adapter, phydev->speed);
-		if (phydev->interface == PHY_INTERFACE_MODE_SGMII ||
-		    phydev->interface == PHY_INTERFACE_MODE_1000BASEX ||
-		    phydev->interface == PHY_INTERFACE_MODE_2500BASEX)
-			lan743x_sgmii_config(adapter);
-
-		data = lan743x_csr_read(adapter, MAC_CR);
-		if (phydev->enable_tx_lpi)
-			data |=  MAC_CR_EEE_EN_;
-		else
-			data &= ~MAC_CR_EEE_EN_;
-		lan743x_csr_write(adapter, MAC_CR, data);
-	}
-}
-
-static void lan743x_phy_close(struct lan743x_adapter *adapter)
-{
-	struct net_device *netdev = adapter->netdev;
-	struct phy_device *phydev = netdev->phydev;
-
-	phy_stop(netdev->phydev);
-	phy_disconnect(netdev->phydev);
-
-	/* using phydev here as phy_disconnect NULLs netdev->phydev */
-	if (phy_is_pseudo_fixed_link(phydev))
-		fixed_phy_unregister(phydev);
-
-}
-
 static void lan743x_phy_interface_select(struct lan743x_adapter *adapter)
 {
 	u32 id_rev;
@@ -1520,65 +1367,9 @@ static void lan743x_phy_interface_select(struct lan743x_adapter *adapter)
 		adapter->phy_interface = PHY_INTERFACE_MODE_MII;
 	else
 		adapter->phy_interface = PHY_INTERFACE_MODE_RGMII;
-}
-
-static int lan743x_phy_open(struct lan743x_adapter *adapter)
-{
-	struct net_device *netdev = adapter->netdev;
-	struct lan743x_phy *phy = &adapter->phy;
-	struct fixed_phy_status fphy_status = {
-		.link = 1,
-		.speed = SPEED_1000,
-		.duplex = DUPLEX_FULL,
-	};
-	struct phy_device *phydev;
-	int ret = -EIO;
-
-	/* try devicetree phy, or fixed link */
-	phydev = of_phy_get_and_connect(netdev, adapter->pdev->dev.of_node,
-					lan743x_phy_link_status_change);
 
-	if (!phydev) {
-		/* try internal phy */
-		phydev = phy_find_first(adapter->mdiobus);
-		if (!phydev)	{
-			if ((adapter->csr.id_rev & ID_REV_ID_MASK_) ==
-					ID_REV_ID_LAN7431_) {
-				phydev = fixed_phy_register(PHY_POLL,
-							    &fphy_status, NULL);
-				if (IS_ERR(phydev)) {
-					netdev_err(netdev, "No PHY/fixed_PHY found\n");
-					return PTR_ERR(phydev);
-				}
-			} else {
-				goto return_error;
-				}
-		}
-
-		lan743x_phy_interface_select(adapter);
-
-		ret = phy_connect_direct(netdev, phydev,
-					 lan743x_phy_link_status_change,
-					 adapter->phy_interface);
-		if (ret)
-			goto return_error;
-	}
-
-	/* MAC doesn't support 1000T Half */
-	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
-	/* support both flow controls */
-	phy_support_asym_pause(phydev);
-	phy->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX);
-	phy->fc_autoneg = phydev->autoneg;
-
-	phy_start(phydev);
-	phy_start_aneg(phydev);
-	phy_attached_info(phydev);
-	return 0;
-
-return_error:
-	return ret;
+	netif_dbg(adapter, drv, adapter->netdev,
+		  "selected phy interface: 0x%X\n", adapter->phy_interface);
 }
 
 static void lan743x_rfe_open(struct lan743x_adapter *adapter)
@@ -3079,6 +2870,317 @@ return_error:
 	return ret;
 }
 
+static int lan743x_phylink_sgmii_config(struct lan743x_adapter *adapter)
+{
+	u32 sgmii_ctl;
+	int ret;
+
+	ret = lan743x_get_lsd(SPEED_1000, DUPLEX_FULL,
+			      MASTER_SLAVE_STATE_MASTER);
+	if (ret < 0) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "error %d link-speed-duplex(LSD) invalid\n", ret);
+		return ret;
+	}
+
+	adapter->sgmii_lsd = ret;
+	netif_dbg(adapter, drv, adapter->netdev,
+		  "Link Speed Duplex (lsd) : 0x%X\n", adapter->sgmii_lsd);
+
+	/* LINK_STATUS_SOURCE from the External PHY via SGMII */
+	sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+	sgmii_ctl &= ~SGMII_CTL_LINK_STATUS_SOURCE_;
+	lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
+
+	ret = lan743x_serdes_clock_and_aneg_update(adapter);
+	if (ret < 0) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "error %d sgmii aneg update failed\n", ret);
+		return ret;
+	}
+
+	return lan743x_pcs_power_reset(adapter);
+}
+
+static int lan743x_phylink_1000basex_config(struct lan743x_adapter *adapter)
+{
+	u32 sgmii_ctl;
+	int ret;
+
+	ret = lan743x_get_lsd(SPEED_1000, DUPLEX_FULL,
+			      MASTER_SLAVE_STATE_MASTER);
+	if (ret < 0) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "error %d link-speed-duplex(LSD) invalid\n", ret);
+		return ret;
+	}
+
+	adapter->sgmii_lsd = ret;
+	netif_dbg(adapter, drv, adapter->netdev,
+		  "Link Speed Duplex (lsd) : 0x%X\n", adapter->sgmii_lsd);
+
+	/* LINK_STATUS_SOURCE from 1000BASE-X PCS link status */
+	sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+	sgmii_ctl |= SGMII_CTL_LINK_STATUS_SOURCE_;
+	lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
+
+	ret = lan743x_serdes_clock_and_aneg_update(adapter);
+	if (ret < 0) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "error %d 1000basex aneg update failed\n", ret);
+		return ret;
+	}
+
+	return lan743x_pcs_power_reset(adapter);
+}
+
+static int lan743x_phylink_2500basex_config(struct lan743x_adapter *adapter)
+{
+	u32 sgmii_ctl;
+	int ret;
+
+	ret = lan743x_get_lsd(SPEED_2500, DUPLEX_FULL,
+			      MASTER_SLAVE_STATE_MASTER);
+	if (ret < 0) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "error %d link-speed-duplex(LSD) invalid\n", ret);
+		return ret;
+	}
+
+	adapter->sgmii_lsd = ret;
+	netif_dbg(adapter, drv, adapter->netdev,
+		  "Link Speed Duplex (lsd) : 0x%X\n", adapter->sgmii_lsd);
+
+	/* LINK_STATUS_SOURCE from 2500BASE-X PCS link status */
+	sgmii_ctl = lan743x_csr_read(adapter, SGMII_CTL);
+	sgmii_ctl |= SGMII_CTL_LINK_STATUS_SOURCE_;
+	lan743x_csr_write(adapter, SGMII_CTL, sgmii_ctl);
+
+	ret = lan743x_serdes_clock_and_aneg_update(adapter);
+	if (ret < 0) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "error %d 2500basex aneg update failed\n", ret);
+		return ret;
+	}
+
+	return lan743x_pcs_power_reset(adapter);
+}
+
+static void lan743x_phylink_mac_config(struct phylink_config *config,
+				       unsigned int link_an_mode,
+				       const struct phylink_link_state *state)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret;
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_2500BASEX:
+		ret = lan743x_phylink_2500basex_config(adapter);
+		if (ret < 0)
+			netif_err(adapter, drv, adapter->netdev,
+				  "2500BASEX config failed. Error %d\n", ret);
+		else
+			netif_dbg(adapter, drv, adapter->netdev,
+				  "2500BASEX mode selected and configured\n");
+		break;
+	case PHY_INTERFACE_MODE_1000BASEX:
+		ret = lan743x_phylink_1000basex_config(adapter);
+		if (ret < 0)
+			netif_err(adapter, drv, adapter->netdev,
+				  "1000BASEX config failed. Error %d\n", ret);
+		else
+			netif_dbg(adapter, drv, adapter->netdev,
+				  "1000BASEX mode selected and configured\n");
+		break;
+	case PHY_INTERFACE_MODE_SGMII:
+		ret = lan743x_phylink_sgmii_config(adapter);
+		if (ret < 0)
+			netif_err(adapter, drv, adapter->netdev,
+				  "SGMII config failed. Error %d\n", ret);
+		else
+			netif_dbg(adapter, drv, adapter->netdev,
+				  "SGMII mode selected and configured\n");
+		break;
+	default:
+		netif_dbg(adapter, drv, adapter->netdev,
+			  "RGMII/GMII/MII(0x%X) mode enable\n",
+			  state->interface);
+		break;
+	}
+}
+
+static void lan743x_phylink_mac_link_down(struct phylink_config *config,
+					  unsigned int link_an_mode,
+					  phy_interface_t interface)
+{
+	netif_tx_stop_all_queues(to_net_dev(config->dev));
+}
+
+static void lan743x_phylink_mac_link_up(struct phylink_config *config,
+					struct phy_device *phydev,
+					unsigned int link_an_mode,
+					phy_interface_t interface,
+					int speed, int duplex,
+					bool tx_pause, bool rx_pause)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int mac_cr;
+	u8 cap;
+
+	mac_cr = lan743x_csr_read(adapter, MAC_CR);
+	/* Pre-initialize register bits.
+	 * Resulting value corresponds to SPEED_10
+	 */
+	mac_cr &= ~(MAC_CR_CFG_H_ | MAC_CR_CFG_L_);
+	if (speed == SPEED_2500)
+		mac_cr |= MAC_CR_CFG_H_ | MAC_CR_CFG_L_;
+	else if (speed == SPEED_1000)
+		mac_cr |= MAC_CR_CFG_H_;
+	else if (speed == SPEED_100)
+		mac_cr |= MAC_CR_CFG_L_;
+
+	lan743x_csr_write(adapter, MAC_CR, mac_cr);
+
+	lan743x_ptp_update_latency(adapter, speed);
+
+	/* Flow Control operation */
+	cap = 0;
+	if (tx_pause)
+		cap |= FLOW_CTRL_TX;
+	if (rx_pause)
+		cap |= FLOW_CTRL_RX;
+
+	lan743x_mac_flow_ctrl_set_enables(adapter,
+					  cap & FLOW_CTRL_TX,
+					  cap & FLOW_CTRL_RX);
+
+	netif_tx_wake_all_queues(netdev);
+}
+
+static const struct phylink_mac_ops lan743x_phylink_mac_ops = {
+	.mac_config = lan743x_phylink_mac_config,
+	.mac_link_down = lan743x_phylink_mac_link_down,
+	.mac_link_up = lan743x_phylink_mac_link_up,
+};
+
+static int lan743x_phylink_create(struct lan743x_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct phylink *pl;
+
+	adapter->phylink_config.dev = &netdev->dev;
+	adapter->phylink_config.type = PHYLINK_NETDEV;
+	adapter->phylink_config.mac_managed_pm = false;
+
+	adapter->phylink_config.mac_capabilities = MAC_ASYM_PAUSE |
+		MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD;
+
+	lan743x_phy_interface_select(adapter);
+
+	switch (adapter->phy_interface) {
+	case PHY_INTERFACE_MODE_SGMII:
+		__set_bit(PHY_INTERFACE_MODE_SGMII,
+			  adapter->phylink_config.supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_1000BASEX,
+			  adapter->phylink_config.supported_interfaces);
+		__set_bit(PHY_INTERFACE_MODE_2500BASEX,
+			  adapter->phylink_config.supported_interfaces);
+		adapter->phylink_config.mac_capabilities |= MAC_2500FD;
+		break;
+	case PHY_INTERFACE_MODE_GMII:
+		__set_bit(PHY_INTERFACE_MODE_GMII,
+			  adapter->phylink_config.supported_interfaces);
+		break;
+	case PHY_INTERFACE_MODE_MII:
+		__set_bit(PHY_INTERFACE_MODE_MII,
+			  adapter->phylink_config.supported_interfaces);
+		break;
+	default:
+		phy_interface_set_rgmii(adapter->phylink_config.supported_interfaces);
+	}
+
+	pl = phylink_create(&adapter->phylink_config, NULL,
+			    adapter->phy_interface, &lan743x_phylink_mac_ops);
+
+	if (IS_ERR(pl)) {
+		netdev_err(netdev, "Could not create phylink (%pe)\n", pl);
+		return PTR_ERR(pl);
+	}
+
+	adapter->phylink = pl;
+	netdev_dbg(netdev, "lan743x phylink created");
+
+	return 0;
+}
+
+static bool lan743x_phy_handle_exists(struct device_node *dn)
+{
+	dn = of_parse_phandle(dn, "phy-handle", 0);
+	of_node_put(dn);
+	return dn != NULL;
+}
+
+static int lan743x_phylink_connect(struct lan743x_adapter *adapter)
+{
+	struct device_node *dn = adapter->pdev->dev.of_node;
+	struct net_device *dev = adapter->netdev;
+	struct phy_device *phydev;
+	int ret;
+
+	if (dn)
+		ret = phylink_of_phy_connect(adapter->phylink, dn, 0);
+
+	if (!dn || (ret && !lan743x_phy_handle_exists(dn))) {
+		phydev = phy_find_first(adapter->mdiobus);
+		if (phydev) {
+			/* attach the mac to the phy */
+			ret = phylink_connect_phy(adapter->phylink, phydev);
+		} else if (((adapter->csr.id_rev & ID_REV_ID_MASK_) ==
+			      ID_REV_ID_LAN7431_) || adapter->is_pci11x1x) {
+			struct phylink_link_state state;
+			unsigned long caps;
+
+			caps = adapter->phylink_config.mac_capabilities;
+			if (caps & MAC_2500FD) {
+				state.speed = SPEED_2500;
+				state.duplex = DUPLEX_FULL;
+			} else if (caps & MAC_1000FD) {
+				state.speed = SPEED_1000;
+				state.duplex = DUPLEX_FULL;
+			} else {
+				state.speed = SPEED_UNKNOWN;
+				state.duplex = DUPLEX_UNKNOWN;
+			}
+
+			ret = phylink_set_fixed_link(adapter->phylink, &state);
+			if (ret) {
+				netdev_err(dev, "Could not set fixed link\n");
+				return ret;
+			}
+		} else {
+			netdev_err(dev, "no PHY found\n");
+			return -ENXIO;
+		}
+	}
+
+	if (ret) {
+		netdev_err(dev, "Could not attach PHY (%d)\n", ret);
+		return ret;
+	}
+
+	phylink_start(adapter->phylink);
+
+	return 0;
+}
+
+static void lan743x_phylink_disconnect(struct lan743x_adapter *adapter)
+{
+	phylink_stop(adapter->phylink);
+	phylink_disconnect_phy(adapter->phylink);
+}
+
 static int lan743x_netdev_close(struct net_device *netdev)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
@@ -3092,7 +3194,7 @@ static int lan743x_netdev_close(struct net_device *netdev)
 
 	lan743x_ptp_close(adapter);
 
-	lan743x_phy_close(adapter);
+	lan743x_phylink_disconnect(adapter);
 
 	lan743x_mac_close(adapter);
 
@@ -3115,13 +3217,13 @@ static int lan743x_netdev_open(struct net_device *netdev)
 	if (ret)
 		goto close_intr;
 
-	ret = lan743x_phy_open(adapter);
+	ret = lan743x_phylink_connect(adapter);
 	if (ret)
 		goto close_mac;
 
 	ret = lan743x_ptp_open(adapter);
 	if (ret)
-		goto close_phy;
+		goto close_mac;
 
 	lan743x_rfe_open(adapter);
 
@@ -3161,9 +3263,8 @@ close_rx:
 			lan743x_rx_close(&adapter->rx[index]);
 	}
 	lan743x_ptp_close(adapter);
-
-close_phy:
-	lan743x_phy_close(adapter);
+	if (adapter->phylink)
+		lan743x_phylink_disconnect(adapter);
 
 close_mac:
 	lan743x_mac_close(adapter);
@@ -3192,11 +3293,14 @@ static netdev_tx_t lan743x_netdev_xmit_frame(struct sk_buff *skb,
 static int lan743x_netdev_ioctl(struct net_device *netdev,
 				struct ifreq *ifr, int cmd)
 {
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
 	if (!netif_running(netdev))
 		return -EINVAL;
 	if (cmd == SIOCSHWTSTAMP)
 		return lan743x_ptp_ioctl(netdev, ifr, cmd);
-	return phy_mii_ioctl(netdev->phydev, ifr, cmd);
+
+	return phylink_mii_ioctl(adapter->phylink, ifr, cmd);
 }
 
 static void lan743x_netdev_set_multicast(struct net_device *netdev)
@@ -3301,10 +3405,17 @@ static void lan743x_mdiobus_cleanup(struct lan743x_adapter *adapter)
 	mdiobus_unregister(adapter->mdiobus);
 }
 
+static void lan743x_destroy_phylink(struct lan743x_adapter *adapter)
+{
+	phylink_destroy(adapter->phylink);
+	adapter->phylink = NULL;
+}
+
 static void lan743x_full_cleanup(struct lan743x_adapter *adapter)
 {
 	unregister_netdev(adapter->netdev);
 
+	lan743x_destroy_phylink(adapter);
 	lan743x_mdiobus_cleanup(adapter);
 	lan743x_hardware_cleanup(adapter);
 	lan743x_pci_cleanup(adapter);
@@ -3518,14 +3629,21 @@ static int lan743x_pcidev_probe(struct pci_dev *pdev,
 				    NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
 	adapter->netdev->hw_features = adapter->netdev->features;
 
-	/* carrier off reporting is important to ethtool even BEFORE open */
-	netif_carrier_off(netdev);
+	ret = lan743x_phylink_create(adapter);
+	if (ret < 0) {
+		netif_err(adapter, probe, netdev,
+			  "failed to setup phylink (%d)\n", ret);
+		goto cleanup_mdiobus;
+	}
 
 	ret = register_netdev(adapter->netdev);
 	if (ret < 0)
-		goto cleanup_mdiobus;
+		goto cleanup_phylink;
 	return 0;
 
+cleanup_phylink:
+	lan743x_destroy_phylink(adapter);
+
 cleanup_mdiobus:
 	lan743x_mdiobus_cleanup(adapter);
 
@@ -3781,6 +3899,7 @@ static int lan743x_pm_resume(struct device *dev)
 	       MAC_WK_SRC_WK_FR_SAVED_;
 	lan743x_csr_write(adapter, MAC_WK_SRC, data);
 
+	rtnl_lock();
 	/* open netdev when netdev is at running state while resume.
 	 * For instance, it is true when system wakesup after pm-suspend
 	 * However, it is false when system wakes up after suspend GUI menu
@@ -3789,6 +3908,7 @@ static int lan743x_pm_resume(struct device *dev)
 		lan743x_netdev_open(netdev);
 
 	netif_device_attach(netdev);
+	rtnl_unlock();
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 3b2585a384e2..7f73d66854be 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -5,6 +5,7 @@
 #define _LAN743X_H
 
 #include <linux/phy.h>
+#include <linux/phylink.h>
 #include "lan743x_ptp.h"
 
 #define DRIVER_AUTHOR   "Bryan Whitehead <Bryan.Whitehead@microchip.com>"
@@ -1083,6 +1084,8 @@ struct lan743x_adapter {
 	u32			flags;
 	u32			hw_cfg;
 	phy_interface_t		phy_interface;
+	struct phylink		*phylink;
+	struct phylink_config	phylink_config;
 };
 
 #define LAN743X_COMPONENT_FLAG_RX(channel)  BIT(20 + (channel))
-- 
cgit v1.3-3-g829e


From f95f28d794ed0b3c71103646ee29e0bcc947c83a Mon Sep 17 00:00:00 2001
From: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Date: Fri, 6 Sep 2024 16:05:11 +0530
Subject: net: lan743x: Add support to ethtool phylink get and set settings

Add support to ethtool phylink functions:
  - get/set settings like speed, duplex etc
  - get/set the wake-on-lan (WOL)
  - get/set the energy-efficient ethernet (EEE)
  - get/set the pause

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Raju Lakkaraju <Raju.Lakkaraju@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 123 ++++++++---------------
 drivers/net/ethernet/microchip/lan743x_main.c    |  22 ++++
 drivers/net/ethernet/microchip/lan743x_main.h    |   1 +
 3 files changed, 67 insertions(+), 79 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 0f1c0edec460..1a1cbd034eda 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -1054,61 +1054,55 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev,
 				   struct ethtool_keee *eee)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
-	struct phy_device *phydev = netdev->phydev;
-	u32 buf;
-	int ret;
-
-	if (!phydev)
-		return -EIO;
-	if (!phydev->drv) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "Missing PHY Driver\n");
-		return -EIO;
-	}
 
-	ret = phy_ethtool_get_eee(phydev, eee);
-	if (ret < 0)
-		return ret;
+	eee->tx_lpi_timer = lan743x_csr_read(adapter,
+					     MAC_EEE_TX_LPI_REQ_DLY_CNT);
 
-	buf = lan743x_csr_read(adapter, MAC_CR);
-	if (buf & MAC_CR_EEE_EN_) {
-		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
-		buf = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
-		eee->tx_lpi_timer = buf;
-	} else {
-		eee->tx_lpi_timer = 0;
-	}
-
-	return 0;
+	return phylink_ethtool_get_eee(adapter->phylink, eee);
 }
 
 static int lan743x_ethtool_set_eee(struct net_device *netdev,
 				   struct ethtool_keee *eee)
 {
-	struct lan743x_adapter *adapter;
-	struct phy_device *phydev;
-	u32 buf = 0;
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	u32 tx_lpi_timer;
 
-	if (!netdev)
-		return -EINVAL;
-	adapter = netdev_priv(netdev);
-	if (!adapter)
-		return -EINVAL;
-	phydev = netdev->phydev;
-	if (!phydev)
-		return -EIO;
-	if (!phydev->drv) {
-		netif_err(adapter, drv, adapter->netdev,
-			  "Missing PHY Driver\n");
-		return -EIO;
-	}
+	tx_lpi_timer = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
+	if (tx_lpi_timer != eee->tx_lpi_timer) {
+		u32 mac_cr = lan743x_csr_read(adapter, MAC_CR);
+
+		/* Software should only change this field when Energy Efficient
+		 * Ethernet Enable (EEEEN) is cleared.
+		 * This function will trigger an autonegotiation restart and
+		 * eee will be reenabled during link up if eee was negotiated.
+		 */
+		lan743x_mac_eee_enable(adapter, false);
+		lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT,
+				  eee->tx_lpi_timer);
 
-	if (eee->eee_enabled) {
-		buf = (u32)eee->tx_lpi_timer;
-		lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, buf);
+		if (mac_cr & MAC_CR_EEE_EN_)
+			lan743x_mac_eee_enable(adapter, true);
 	}
 
-	return phy_ethtool_set_eee(phydev, eee);
+	return phylink_ethtool_set_eee(adapter->phylink, eee);
+}
+
+static int
+lan743x_ethtool_set_link_ksettings(struct net_device *netdev,
+				   const struct ethtool_link_ksettings *cmd)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return phylink_ethtool_ksettings_set(adapter->phylink, cmd);
+}
+
+static int
+lan743x_ethtool_get_link_ksettings(struct net_device *netdev,
+				   struct ethtool_link_ksettings *cmd)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return phylink_ethtool_ksettings_get(adapter->phylink, cmd);
 }
 
 #ifdef CONFIG_PM
@@ -1120,8 +1114,7 @@ static void lan743x_ethtool_get_wol(struct net_device *netdev,
 	wol->supported = 0;
 	wol->wolopts = 0;
 
-	if (netdev->phydev)
-		phy_ethtool_get_wol(netdev->phydev, wol);
+	phylink_ethtool_get_wol(adapter->phylink, wol);
 
 	if (wol->supported != adapter->phy_wol_supported)
 		netif_warn(adapter, drv, adapter->netdev,
@@ -1162,7 +1155,7 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev,
 		    !(adapter->phy_wol_supported & WAKE_MAGICSECURE))
 			phy_wol.wolopts &= ~WAKE_MAGIC;
 
-		ret = phy_ethtool_set_wol(netdev->phydev, &phy_wol);
+		ret = phylink_ethtool_set_wol(adapter->phylink, wol);
 		if (ret && (ret != -EOPNOTSUPP))
 			return ret;
 
@@ -1351,44 +1344,16 @@ static void lan743x_get_pauseparam(struct net_device *dev,
 				   struct ethtool_pauseparam *pause)
 {
 	struct lan743x_adapter *adapter = netdev_priv(dev);
-	struct lan743x_phy *phy = &adapter->phy;
 
-	if (phy->fc_request_control & FLOW_CTRL_TX)
-		pause->tx_pause = 1;
-	if (phy->fc_request_control & FLOW_CTRL_RX)
-		pause->rx_pause = 1;
-	pause->autoneg = phy->fc_autoneg;
+	phylink_ethtool_get_pauseparam(adapter->phylink, pause);
 }
 
 static int lan743x_set_pauseparam(struct net_device *dev,
 				  struct ethtool_pauseparam *pause)
 {
 	struct lan743x_adapter *adapter = netdev_priv(dev);
-	struct phy_device *phydev = dev->phydev;
-	struct lan743x_phy *phy = &adapter->phy;
-
-	if (!phydev)
-		return -ENODEV;
-
-	if (!phy_validate_pause(phydev, pause))
-		return -EINVAL;
-
-	phy->fc_request_control = 0;
-	if (pause->rx_pause)
-		phy->fc_request_control |= FLOW_CTRL_RX;
 
-	if (pause->tx_pause)
-		phy->fc_request_control |= FLOW_CTRL_TX;
-
-	phy->fc_autoneg = pause->autoneg;
-
-	if (pause->autoneg == AUTONEG_DISABLE)
-		lan743x_mac_flow_ctrl_set_enables(adapter, pause->tx_pause,
-						  pause->rx_pause);
-	else
-		phy_set_asym_pause(phydev, pause->rx_pause,  pause->tx_pause);
-
-	return 0;
+	return phylink_ethtool_set_pauseparam(adapter->phylink, pause);
 }
 
 const struct ethtool_ops lan743x_ethtool_ops = {
@@ -1413,8 +1378,8 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_ts_info = lan743x_ethtool_get_ts_info,
 	.get_eee = lan743x_ethtool_get_eee,
 	.set_eee = lan743x_ethtool_set_eee,
-	.get_link_ksettings = phy_ethtool_get_link_ksettings,
-	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+	.get_link_ksettings = lan743x_ethtool_get_link_ksettings,
+	.set_link_ksettings = lan743x_ethtool_set_link_ksettings,
 	.get_regs_len = lan743x_get_regs_len,
 	.get_regs = lan743x_get_regs,
 	.get_pauseparam = lan743x_get_pauseparam,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 2767bfa4bdec..4dc5adcda6a3 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -2966,6 +2966,18 @@ static int lan743x_phylink_2500basex_config(struct lan743x_adapter *adapter)
 	return lan743x_pcs_power_reset(adapter);
 }
 
+void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable)
+{
+	u32 mac_cr;
+
+	mac_cr = lan743x_csr_read(adapter, MAC_CR);
+	if (enable)
+		mac_cr |= MAC_CR_EEE_EN_;
+	else
+		mac_cr &= ~MAC_CR_EEE_EN_;
+	lan743x_csr_write(adapter, MAC_CR, mac_cr);
+}
+
 static void lan743x_phylink_mac_config(struct phylink_config *config,
 				       unsigned int link_an_mode,
 				       const struct phylink_link_state *state)
@@ -3014,7 +3026,11 @@ static void lan743x_phylink_mac_link_down(struct phylink_config *config,
 					  unsigned int link_an_mode,
 					  phy_interface_t interface)
 {
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
 	netif_tx_stop_all_queues(to_net_dev(config->dev));
+	lan743x_mac_eee_enable(adapter, false);
 }
 
 static void lan743x_phylink_mac_link_up(struct phylink_config *config,
@@ -3056,6 +3072,9 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config,
 					  cap & FLOW_CTRL_TX,
 					  cap & FLOW_CTRL_RX);
 
+	if (phydev)
+		lan743x_mac_eee_enable(adapter, phydev->enable_tx_lpi);
+
 	netif_tx_wake_all_queues(netdev);
 }
 
@@ -3239,6 +3258,9 @@ static int lan743x_netdev_open(struct net_device *netdev)
 			goto close_tx;
 	}
 
+	if (netdev->phydev)
+		phy_support_eee(netdev->phydev);
+
 #ifdef CONFIG_PM
 	if (adapter->netdev->phydev) {
 		struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 7f73d66854be..8ef897c114d3 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -1206,5 +1206,6 @@ void lan743x_hs_syslock_release(struct lan743x_adapter *adapter);
 void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter,
 				       bool tx_enable, bool rx_enable);
 int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr);
+void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable);
 
 #endif /* _LAN743X_H */
-- 
cgit v1.3-3-g829e


From d41905b3bb890a32c87b65228b241daad8837fb0 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Tue, 10 Sep 2024 14:41:29 +0200
Subject: selftests/xsk: Read current MAX_SKB_FRAGS from sysctl knob

Currently, xskxceiver assumes that MAX_SKB_FRAGS value is always 17
which is not true - since the introduction of BIG TCP this can now take
any value between 17 to 45 via CONFIG_MAX_SKB_FRAGS.

Adjust the TOO_MANY_FRAGS test case to read the currently configured
MAX_SKB_FRAGS value by reading it from /proc/sys/net/core/max_skb_frags.
If running system does not provide that sysctl file then let us try
running the test with a default value.

Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Link: https://lore.kernel.org/bpf/20240910124129.289874-1-maciej.fijalkowski@intel.com
---
 tools/testing/selftests/bpf/xskxceiver.c | 43 ++++++++++++++++++++++++++++----
 tools/testing/selftests/bpf/xskxceiver.h |  1 -
 2 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 8144fd145237..1ee0ef114f9d 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -324,6 +324,25 @@ out:
 	return zc_avail;
 }
 
+#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags"
+static unsigned int get_max_skb_frags(void)
+{
+	unsigned int max_skb_frags = 0;
+	FILE *file;
+
+	file = fopen(MAX_SKB_FRAGS_PATH, "r");
+	if (!file) {
+		ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH);
+		return 0;
+	}
+
+	if (fscanf(file, "%u", &max_skb_frags) != 1)
+		ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH);
+
+	fclose(file);
+	return max_skb_frags;
+}
+
 static struct option long_options[] = {
 	{"interface", required_argument, 0, 'i'},
 	{"busy-poll", no_argument, 0, 'b'},
@@ -2244,13 +2263,24 @@ static int testapp_poll_rxq_tmout(struct test_spec *test)
 
 static int testapp_too_many_frags(struct test_spec *test)
 {
-	struct pkt pkts[2 * XSK_DESC__MAX_SKB_FRAGS + 2] = {};
+	struct pkt *pkts;
 	u32 max_frags, i;
+	int ret;
 
-	if (test->mode == TEST_MODE_ZC)
+	if (test->mode == TEST_MODE_ZC) {
 		max_frags = test->ifobj_tx->xdp_zc_max_segs;
-	else
-		max_frags = XSK_DESC__MAX_SKB_FRAGS;
+	} else {
+		max_frags = get_max_skb_frags();
+		if (!max_frags) {
+			ksft_print_msg("Couldn't retrieve MAX_SKB_FRAGS from system, using default (17) value\n");
+			max_frags = 17;
+		}
+		max_frags += 1;
+	}
+
+	pkts = calloc(2 * max_frags + 2, sizeof(struct pkt));
+	if (!pkts)
+		return TEST_FAILURE;
 
 	test->mtu = MAX_ETH_JUMBO_SIZE;
 
@@ -2280,7 +2310,10 @@ static int testapp_too_many_frags(struct test_spec *test)
 	pkts[2 * max_frags + 1].valid = true;
 
 	pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2);
-	return testapp_validate_traffic(test);
+	ret = testapp_validate_traffic(test);
+
+	free(pkts);
+	return ret;
 }
 
 static int xsk_load_xdp_programs(struct ifobject *ifobj)
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index 885c948c5d83..e46e823f6a1a 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -55,7 +55,6 @@
 #define XSK_UMEM__LARGE_FRAME_SIZE (3 * 1024)
 #define XSK_UMEM__MAX_FRAME_SIZE (4 * 1024)
 #define XSK_DESC__INVALID_OPTION (0xffff)
-#define XSK_DESC__MAX_SKB_FRAGS 18
 #define HUGEPAGE_SIZE (2 * 1024 * 1024)
 #define PKT_DUMP_NB_TO_PRINT 16
 #define RUN_ALL_TESTS UINT_MAX
-- 
cgit v1.3-3-g829e


From 23dc9867329c72b48e5039ac93fbf50d9099cdb3 Mon Sep 17 00:00:00 2001
From: Daniel Xu <dxu@dxuuu.xyz>
Date: Thu, 5 Sep 2024 19:22:44 -0600
Subject: bpf, cpumap: Move xdp:xdp_cpumap_kthread tracepoint before rcv

cpumap takes RX processing out of softirq and onto a separate kthread.
Since the kthread needs to be scheduled in order to run (versus softirq
which does not), we can theoretically experience extra latency if the
system is under load and the scheduler is being unfair to us.

Moving the tracepoint to before passing the skb list up the stack allows
users to more accurately measure enqueue/dequeue latency introduced by
cpumap via xdp:xdp_cpumap_enqueue and xdp:xdp_cpumap_kthread tracepoints.

f9419f7bd7a5 ("bpf: cpumap add tracepoints") which added the tracepoints
states that the intent behind them was for general observability and for
a feedback loop to see if the queues are being overwhelmed. This change
does not mess with either of those use cases but rather adds a third
one.

Signed-off-by: Daniel Xu <dxu@dxuuu.xyz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://lore.kernel.org/bpf/47615d5b5e302e4bd30220473779e98b492d47cd.1725585718.git.dxu@dxuuu.xyz
---
 kernel/bpf/cpumap.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index fbdf5a1aabfe..a2f46785ac3b 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -354,12 +354,14 @@ static int cpu_map_kthread_run(void *data)
 
 			list_add_tail(&skb->list, &list);
 		}
-		netif_receive_skb_list(&list);
 
-		/* Feedback loop via tracepoint */
+		/* Feedback loop via tracepoint.
+		 * NB: keep before recv to allow measuring enqueue/dequeue latency.
+		 */
 		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
 					 sched, &stats);
 
+		netif_receive_skb_list(&list);
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
 	__set_current_state(TASK_RUNNING);
-- 
cgit v1.3-3-g829e


From 8aeaed21befc90f27f4fca6dd190850d97d2e9e3 Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Wed, 11 Sep 2024 11:37:15 +0800
Subject: bpf: Support __nullable argument suffix for tp_btf

Pointers passed to tp_btf were trusted to be valid, but some tracepoints
do take NULL pointer as input, such as trace_tcp_send_reset(). Then the
invalid memory access cannot be detected by verifier.

This patch fix it by add a suffix "__nullable" to the unreliable
argument. The suffix is shown in btf, and PTR_MAYBE_NULL will be added
to nullable arguments. Then users must check the pointer before use it.

A problem here is that we use "btf_trace_##call" to search func_proto.
As it is a typedef, argument names as well as the suffix are not
recorded. To solve this, I use bpf_raw_event_map to find
"__bpf_trace##template" from "btf_trace_##call", and then we can see the
suffix.

Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240911033719.91468-2-lulie@linux.alibaba.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 kernel/bpf/btf.c      |  3 +++
 kernel/bpf/verifier.c | 36 ++++++++++++++++++++++++++++++++----
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 520f49f422fe..7e03a98ccb7c 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6523,6 +6523,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	if (prog_args_trusted(prog))
 		info->reg_type |= PTR_TRUSTED;
 
+	if (btf_param_match_suffix(btf, &args[arg], "__nullable"))
+		info->reg_type |= PTR_MAYBE_NULL;
+
 	if (tgt_prog) {
 		enum bpf_prog_type tgt_type;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d8520095ca03..39d5710c68ad 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -28,6 +28,8 @@
 #include <linux/cpumask.h>
 #include <linux/bpf_mem_alloc.h>
 #include <net/xdp.h>
+#include <linux/trace_events.h>
+#include <linux/kallsyms.h>
 
 #include "disasm.h"
 
@@ -21154,11 +21156,13 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 {
 	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
 	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
+	char trace_symbol[KSYM_SYMBOL_LEN];
 	const char prefix[] = "btf_trace_";
+	struct bpf_raw_event_map *btp;
 	int ret = 0, subprog = -1, i;
 	const struct btf_type *t;
 	bool conservative = true;
-	const char *tname;
+	const char *tname, *fname;
 	struct btf *btf;
 	long addr = 0;
 	struct module *mod = NULL;
@@ -21289,10 +21293,34 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
 			return -EINVAL;
 		}
 		tname += sizeof(prefix) - 1;
-		t = btf_type_by_id(btf, t->type);
-		if (!btf_type_is_ptr(t))
-			/* should never happen in valid vmlinux build */
+
+		/* The func_proto of "btf_trace_##tname" is generated from typedef without argument
+		 * names. Thus using bpf_raw_event_map to get argument names.
+		 */
+		btp = bpf_get_raw_tracepoint(tname);
+		if (!btp)
 			return -EINVAL;
+		fname = kallsyms_lookup((unsigned long)btp->bpf_func, NULL, NULL, NULL,
+					trace_symbol);
+		bpf_put_raw_tracepoint(btp);
+
+		if (fname)
+			ret = btf_find_by_name_kind(btf, fname, BTF_KIND_FUNC);
+
+		if (!fname || ret < 0) {
+			bpf_log(log, "Cannot find btf of tracepoint template, fall back to %s%s.\n",
+				prefix, tname);
+			t = btf_type_by_id(btf, t->type);
+			if (!btf_type_is_ptr(t))
+				/* should never happen in valid vmlinux build */
+				return -EINVAL;
+		} else {
+			t = btf_type_by_id(btf, ret);
+			if (!btf_type_is_func(t))
+				/* should never happen in valid vmlinux build */
+				return -EINVAL;
+		}
+
 		t = btf_type_by_id(btf, t->type);
 		if (!btf_type_is_func_proto(t))
 			/* should never happen in valid vmlinux build */
-- 
cgit v1.3-3-g829e


From 2060f07f861a237345922023e9347a204c0795af Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Wed, 11 Sep 2024 11:37:16 +0800
Subject: selftests/bpf: Add test for __nullable suffix in tp_btf

Add a tracepoint with __nullable suffix in bpf_testmod, and add cases
for it:

$ ./test_progs -t "tp_btf_nullable"
 #406/1   tp_btf_nullable/handle_tp_btf_nullable_bare1:OK
 #406/2   tp_btf_nullable/handle_tp_btf_nullable_bare2:OK
 #406     tp_btf_nullable:OK
 Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240911033719.91468-3-lulie@linux.alibaba.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 .../selftests/bpf/bpf_testmod/bpf_testmod-events.h |  6 ++++++
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        |  2 ++
 .../selftests/bpf/prog_tests/tp_btf_nullable.c     | 14 +++++++++++++
 .../selftests/bpf/progs/test_tp_btf_nullable.c     | 24 ++++++++++++++++++++++
 4 files changed, 46 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
index 11ee801e75e7..6c3b4d4f173a 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
@@ -34,6 +34,12 @@ DECLARE_TRACE(bpf_testmod_test_write_bare,
 	TP_ARGS(task, ctx)
 );
 
+/* Used in bpf_testmod_test_read() to test __nullable suffix */
+DECLARE_TRACE(bpf_testmod_test_nullable_bare,
+	TP_PROTO(struct bpf_testmod_test_read_ctx *ctx__nullable),
+	TP_ARGS(ctx__nullable)
+);
+
 #undef BPF_TESTMOD_DECLARE_TRACE
 #ifdef DECLARE_TRACE_WRITABLE
 #define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index fd28c1157bd3..a32771da4293 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -356,6 +356,8 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	if (bpf_testmod_loop_test(101) > 100)
 		trace_bpf_testmod_test_read(current, &ctx);
 
+	trace_bpf_testmod_test_nullable_bare(NULL);
+
 	/* Magic number to enable writable tp */
 	if (len == 64) {
 		struct bpf_testmod_test_writable_ctx writable = {
diff --git a/tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c b/tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c
new file mode 100644
index 000000000000..accc42e01f8a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_tp_btf_nullable.skel.h"
+
+void test_tp_btf_nullable(void)
+{
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	RUN_TESTS(test_tp_btf_nullable);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
new file mode 100644
index 000000000000..bba3e37f749b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../bpf_testmod/bpf_testmod.h"
+#include "bpf_misc.h"
+
+SEC("tp_btf/bpf_testmod_test_nullable_bare")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx)
+{
+	return nullable_ctx->len;
+}
+
+SEC("tp_btf/bpf_testmod_test_nullable_bare")
+int BPF_PROG(handle_tp_btf_nullable_bare2, struct bpf_testmod_test_read_ctx *nullable_ctx)
+{
+	if (nullable_ctx)
+		return nullable_ctx->len;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.3-3-g829e


From edd3f6f7588c713477e1299c38c84dcd91a7f148 Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Wed, 11 Sep 2024 11:37:17 +0800
Subject: tcp: Use skb__nullable in trace_tcp_send_reset

Replace skb with skb__nullable as the argument name. The suffix tells
bpf verifier through btf that the arg could be NULL and should be
checked in tp_btf prog.

For now, this is the only nullable argument in tcp tracepoints.

Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20240911033719.91468-4-lulie@linux.alibaba.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 include/trace/events/tcp.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 1c8bd8e186b8..a27c4b619dff 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -91,10 +91,10 @@ DEFINE_RST_REASON(FN, FN)
 TRACE_EVENT(tcp_send_reset,
 
 	TP_PROTO(const struct sock *sk,
-		 const struct sk_buff *skb,
+		 const struct sk_buff *skb__nullable,
 		 const enum sk_rst_reason reason),
 
-	TP_ARGS(sk, skb, reason),
+	TP_ARGS(sk, skb__nullable, reason),
 
 	TP_STRUCT__entry(
 		__field(const void *, skbaddr)
@@ -106,7 +106,7 @@ TRACE_EVENT(tcp_send_reset,
 	),
 
 	TP_fast_assign(
-		__entry->skbaddr = skb;
+		__entry->skbaddr = skb__nullable;
 		__entry->skaddr = sk;
 		/* Zero means unknown state. */
 		__entry->state = sk ? sk->sk_state : 0;
@@ -118,13 +118,13 @@ TRACE_EVENT(tcp_send_reset,
 			const struct inet_sock *inet = inet_sk(sk);
 
 			TP_STORE_ADDR_PORTS(__entry, inet, sk);
-		} else if (skb) {
-			const struct tcphdr *th = (const struct tcphdr *)skb->data;
+		} else if (skb__nullable) {
+			const struct tcphdr *th = (const struct tcphdr *)skb__nullable->data;
 			/*
 			 * We should reverse the 4-tuple of skb, so later
 			 * it can print the right flow direction of rst.
 			 */
-			TP_STORE_ADDR_PORTS_SKB(skb, th, entry->daddr, entry->saddr);
+			TP_STORE_ADDR_PORTS_SKB(skb__nullable, th, entry->daddr, entry->saddr);
 		}
 		__entry->reason = reason;
 	),
-- 
cgit v1.3-3-g829e


From ffc83860d8c09705d8e83474b8c6ec4d1d3dca41 Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Wed, 11 Sep 2024 11:37:18 +0800
Subject: bpf: Allow bpf_dynptr_from_skb() for tp_btf

Making tp_btf able to use bpf_dynptr_from_skb(), which is useful for skb
parsing, especially for non-linear paged skb data. This is achieved by
adding KF_TRUSTED_ARGS flag to bpf_dynptr_from_skb and registering it
for TRACING progs. With KF_TRUSTED_ARGS, args from fentry/fexit are
excluded, so that unsafe progs like fexit/__kfree_skb are not allowed.

We also need the skb dynptr to be read-only in tp_btf. Because
may_access_direct_pkt_data() returns false by default when checking
bpf_dynptr_from_skb, there is no need to add BPF_PROG_TYPE_TRACING to it
explicitly.

Suggested-by: Martin KaFai Lau <martin.lau@linux.dev>
Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20240911033719.91468-5-lulie@linux.alibaba.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 net/core/filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index f09d875cc053..c6012a3a14b2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -12063,7 +12063,7 @@ int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
 }
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_skb)
-BTF_ID_FLAGS(func, bpf_dynptr_from_skb)
+BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_kfunc_check_set_skb)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_xdp)
@@ -12112,6 +12112,7 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 					       &bpf_kfunc_set_sock_addr);
-- 
cgit v1.3-3-g829e


From 83dff601715bdc086dc1fc470ee3aaff42215e65 Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Wed, 11 Sep 2024 11:37:19 +0800
Subject: selftests/bpf: Expand skb dynptr selftests for tp_btf

Add 3 test cases for skb dynptr used in tp_btf:
- test_dynptr_skb_tp_btf: use skb dynptr in tp_btf and make sure it is
  read-only.
- skb_invalid_ctx_fentry/skb_invalid_ctx_fexit: bpf_dynptr_from_skb
  should fail in fentry/fexit.

In test_dynptr_skb_tp_btf, to trigger the tracepoint in kfree_skb,
test_pkt_access is used for its test_run, as in kfree_skb.c. Because the
test process is different from others, a new setup type is defined,
i.e., SETUP_SKB_PROG_TP.

The result is like:
$ ./test_progs -t 'dynptr/test_dynptr_skb_tp_btf'
  #84/14   dynptr/test_dynptr_skb_tp_btf:OK
  #84      dynptr:OK
  #127     kfunc_dynptr_param:OK
  Summary: 2/1 PASSED, 0 SKIPPED, 0 FAILED

$ ./test_progs -t 'dynptr/skb_invalid_ctx_f'
  #84/85   dynptr/skb_invalid_ctx_fentry:OK
  #84/86   dynptr/skb_invalid_ctx_fexit:OK
  #84      dynptr:OK
  #127     kfunc_dynptr_param:OK
  Summary: 2/2 PASSED, 0 SKIPPED, 0 FAILED

Also fix two coding style nits (change spaces to tabs).

Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Link: https://lore.kernel.org/r/20240911033719.91468-6-lulie@linux.alibaba.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/dynptr.c    | 37 ++++++++++++++++++++--
 tools/testing/selftests/bpf/progs/dynptr_fail.c    | 25 +++++++++++++++
 tools/testing/selftests/bpf/progs/dynptr_success.c | 23 ++++++++++++++
 3 files changed, 83 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index 7cfac53c0d58..b614a5272dfd 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -9,6 +9,7 @@
 enum test_setup_type {
 	SETUP_SYSCALL_SLEEP,
 	SETUP_SKB_PROG,
+	SETUP_SKB_PROG_TP,
 };
 
 static struct {
@@ -28,6 +29,7 @@ static struct {
 	{"test_dynptr_clone", SETUP_SKB_PROG},
 	{"test_dynptr_skb_no_buff", SETUP_SKB_PROG},
 	{"test_dynptr_skb_strcmp", SETUP_SKB_PROG},
+	{"test_dynptr_skb_tp_btf", SETUP_SKB_PROG_TP},
 };
 
 static void verify_success(const char *prog_name, enum test_setup_type setup_type)
@@ -35,7 +37,7 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 	struct dynptr_success *skel;
 	struct bpf_program *prog;
 	struct bpf_link *link;
-       int err;
+	int err;
 
 	skel = dynptr_success__open();
 	if (!ASSERT_OK_PTR(skel, "dynptr_success__open"))
@@ -47,7 +49,7 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
 		goto cleanup;
 
-       bpf_program__set_autoload(prog, true);
+	bpf_program__set_autoload(prog, true);
 
 	err = dynptr_success__load(skel);
 	if (!ASSERT_OK(err, "dynptr_success__load"))
@@ -87,6 +89,37 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ
 
 		break;
 	}
+	case SETUP_SKB_PROG_TP:
+	{
+		struct __sk_buff skb = {};
+		struct bpf_object *obj;
+		int aux_prog_fd;
+
+		/* Just use its test_run to trigger kfree_skb tracepoint */
+		err = bpf_prog_test_load("./test_pkt_access.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+					 &obj, &aux_prog_fd);
+		if (!ASSERT_OK(err, "prog_load sched cls"))
+			goto cleanup;
+
+		LIBBPF_OPTS(bpf_test_run_opts, topts,
+			    .data_in = &pkt_v4,
+			    .data_size_in = sizeof(pkt_v4),
+			    .ctx_in = &skb,
+			    .ctx_size_in = sizeof(skb),
+		);
+
+		link = bpf_program__attach(prog);
+		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+			goto cleanup;
+
+		err = bpf_prog_test_run_opts(aux_prog_fd, &topts);
+		bpf_link__destroy(link);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
 	}
 
 	ASSERT_EQ(skel->bss->err, 0, "err");
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index e35bc1eac52a..c3bc186af21e 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -6,6 +6,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include <linux/if_ether.h>
 #include "bpf_misc.h"
 #include "bpf_kfuncs.h"
@@ -1254,6 +1255,30 @@ int skb_invalid_ctx(void *ctx)
 	return 0;
 }
 
+SEC("fentry/skb_tx_error")
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(skb_invalid_ctx_fentry, void *skb)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	return 0;
+}
+
+SEC("fexit/skb_tx_error")
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(skb_invalid_ctx_fexit, void *skb)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	return 0;
+}
+
 /* Reject writes to dynptr slot for uninit arg */
 SEC("?raw_tp")
 __failure __msg("potential write to dynptr at off=-16")
diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c
index 5985920d162e..bfcc85686cf0 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_success.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_success.c
@@ -5,6 +5,7 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
 #include "bpf_kfuncs.h"
 #include "errno.h"
@@ -544,3 +545,25 @@ int test_dynptr_skb_strcmp(struct __sk_buff *skb)
 
 	return 1;
 }
+
+SEC("tp_btf/kfree_skb")
+int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location)
+{
+	__u8 write_data[2] = {1, 2};
+	struct bpf_dynptr ptr;
+	int ret;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* since tp_btf skbs are read only, writes should fail */
+	ret = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+	if (ret != -EINVAL) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}
-- 
cgit v1.3-3-g829e


From b1339be951ad31947ae19bc25cb08769bf255100 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 6 Sep 2024 15:44:49 +0000
Subject: sock_map: Add a cond_resched() in sock_hash_free()

Several syzbot soft lockup reports all have in common sock_hash_free()

If a map with a large number of buckets is destroyed, we need to yield
the cpu when needed.

Fixes: 75e68e5bf2c7 ("bpf, sockhash: Synchronize delete from bucket list on map free")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20240906154449.3742932-1-edumazet@google.com
---
 net/core/sock_map.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index d3dbb92153f2..724b6856fcc3 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1183,6 +1183,7 @@ static void sock_hash_free(struct bpf_map *map)
 			sock_put(elem->sk);
 			sock_hash_free_elem(htab, elem);
 		}
+		cond_resched();
 	}
 
 	/* wait for psock readers accessing its map link */
-- 
cgit v1.3-3-g829e


From 430d67bdcb04ee8502c2b10dcbaced4253649189 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 6 Sep 2024 15:25:31 +0200
Subject: net: hsr: Use the seqnr lock for frames received via interlink port.

syzbot reported that the seqnr_lock is not acquire for frames received
over the interlink port. In the interlink case a new seqnr is generated
and assigned to the frame.
Frames, which are received over the slave port have already a sequence
number assigned so the lock is not required.

Acquire the hsr_priv::seqnr_lock during in the invocation of
hsr_forward_skb() if a packet has been received from the interlink port.

Reported-by: syzbot+3d602af7549af539274e@syzkaller.appspotmail.com
Closes: https://groups.google.com/g/syzkaller-bugs/c/KppVvGviGg4/m/EItSdCZdBAAJ
Fixes: 5055cccfc2d1c ("net: hsr: Provide RedBox support (HSR-SAN)")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Lukasz Majewski <lukma@denx.de>
Tested-by: Lukasz Majewski <lukma@denx.de>
Link: https://patch.msgid.link/20240906132816.657485-2-bigeasy@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_slave.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
index af6cf64a00e0..464f683e016d 100644
--- a/net/hsr/hsr_slave.c
+++ b/net/hsr/hsr_slave.c
@@ -67,7 +67,16 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
 		skb_set_network_header(skb, ETH_HLEN + HSR_HLEN);
 	skb_reset_mac_len(skb);
 
-	hsr_forward_skb(skb, port);
+	/* Only the frames received over the interlink port will assign a
+	 * sequence number and require synchronisation vs other sender.
+	 */
+	if (port->type == HSR_PT_INTERLINK) {
+		spin_lock_bh(&hsr->seqnr_lock);
+		hsr_forward_skb(skb, port);
+		spin_unlock_bh(&hsr->seqnr_lock);
+	} else {
+		hsr_forward_skb(skb, port);
+	}
 
 finish_consume:
 	return RX_HANDLER_CONSUMED;
-- 
cgit v1.3-3-g829e


From 35e24f28c2e9b2c3b711200b07e4f9926f464c6b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 6 Sep 2024 15:25:32 +0200
Subject: net: hsr: Remove interlink_sequence_nr.

Remove interlink_sequence_nr which is unused.

[ bigeasy: split out from Eric's patch ].

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://patch.msgid.link/20240906132816.657485-3-bigeasy@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/hsr/hsr_device.c | 1 -
 net/hsr/hsr_main.h   | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index a06e790042e2..10393836992d 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -625,7 +625,6 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
 	/* Overflow soon to find bugs easier: */
 	hsr->sequence_nr = HSR_SEQNR_START;
 	hsr->sup_sequence_nr = HSR_SUP_SEQNR_START;
-	hsr->interlink_sequence_nr = HSR_SEQNR_START;
 
 	timer_setup(&hsr->announce_timer, hsr_announce, 0);
 	timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0);
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index ab1f8d35d9dc..fcfeb79bb040 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -203,7 +203,6 @@ struct hsr_priv {
 	struct timer_list	prune_proxy_timer;
 	int announce_count;
 	u16 sequence_nr;
-	u16 interlink_sequence_nr; /* Interlink port seq_nr */
 	u16 sup_sequence_nr;	/* For HSRv1 separate seq_nr for supervision */
 	enum hsr_version prot_version;	/* Indicate if HSRv0, HSRv1 or PRPv1 */
 	spinlock_t seqnr_lock;	/* locking for sequence_nr */
-- 
cgit v1.3-3-g829e


From 65b02260a0e0c7cbb2faafd6c84ad95f68a2acae Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 9 Sep 2024 22:09:21 +0200
Subject: mptcp: export mptcp_subflow_early_fallback()

This helper will be used outside protocol.h in the following commit.

While at it, also add a 'pr_fallback()' debug print, to help identifying
fallbacks.

Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240909-net-next-mptcp-fallback-x-mpc-v1-1-da7ebb4cd2a3@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 7 -------
 net/mptcp/protocol.h | 8 ++++++++
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 37ebcb7640eb..cbbcc46cfef0 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3717,13 +3717,6 @@ static int mptcp_ioctl(struct sock *sk, int cmd, int *karg)
 	return 0;
 }
 
-static void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
-					 struct mptcp_subflow_context *subflow)
-{
-	subflow->request_mptcp = 0;
-	__mptcp_do_fallback(msk);
-}
-
 static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct mptcp_subflow_context *subflow;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index bf03bff9ac44..302bd808b839 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1215,6 +1215,14 @@ static inline void mptcp_do_fallback(struct sock *ssk)
 
 #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a)
 
+static inline void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
+						struct mptcp_subflow_context *subflow)
+{
+	pr_fallback(msk);
+	subflow->request_mptcp = 0;
+	__mptcp_do_fallback(msk);
+}
+
 static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
 {
 	struct mptcp_ext *mpext;
-- 
cgit v1.3-3-g829e


From 6982826fe5e53ef115836de7dd397bd970030937 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 9 Sep 2024 22:09:22 +0200
Subject: mptcp: fallback to TCP after SYN+MPC drops

Some middleboxes might be nasty with MPTCP, and decide to drop packets
with MPTCP options, instead of just dropping the MPTCP options (or
letting them pass...).

In this case, it sounds better to fallback to "plain" TCP after 2
retransmissions, and try again.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/477
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240909-net-next-mptcp-fallback-x-mpc-v1-2-da7ebb4cd2a3@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/mptcp.h  |  4 ++++
 net/ipv4/tcp_timer.c |  1 +
 net/mptcp/ctrl.c     | 20 ++++++++++++++++++++
 net/mptcp/mib.c      |  1 +
 net/mptcp/mib.h      |  1 +
 5 files changed, 27 insertions(+)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 0bc4ab03f487..814b5f2e3ed5 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -223,6 +223,8 @@ static inline __be32 mptcp_reset_option(const struct sk_buff *skb)
 
 	return htonl(0u);
 }
+
+void mptcp_active_detect_blackhole(struct sock *sk, bool expired);
 #else
 
 static inline void mptcp_init(void)
@@ -307,6 +309,8 @@ static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct reques
 }
 
 static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }
+
+static inline void mptcp_active_detect_blackhole(struct sock *sk, bool expired) { }
 #endif /* CONFIG_MPTCP */
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 86169127e4d1..79064580c8c0 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -282,6 +282,7 @@ static int tcp_write_timeout(struct sock *sk)
 		expired = retransmits_timed_out(sk, retry_until,
 						READ_ONCE(icsk->icsk_user_timeout));
 	tcp_fastopen_active_detect_blackhole(sk, expired);
+	mptcp_active_detect_blackhole(sk, expired);
 
 	if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
 		tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 99382c317ebb..0b23e3c5e8ff 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -12,6 +12,7 @@
 #include <net/netns/generic.h>
 
 #include "protocol.h"
+#include "mib.h"
 
 #define MPTCP_SYSCTL_PATH "net/mptcp"
 
@@ -277,6 +278,25 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {}
 
 #endif /* CONFIG_SYSCTL */
 
+/* Check the number of retransmissions, and fallback to TCP if needed */
+void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
+{
+	struct mptcp_subflow_context *subflow;
+	u32 timeouts;
+
+	if (!sk_is_mptcp(ssk))
+		return;
+
+	timeouts = inet_csk(ssk)->icsk_retransmits;
+	subflow = mptcp_subflow_ctx(ssk);
+
+	if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT &&
+	    (timeouts == 2 || (timeouts < 2 && expired))) {
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP);
+		mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
+	}
+}
+
 static int __net_init mptcp_net_init(struct net *net)
 {
 	struct mptcp_pernet *pernet = mptcp_get_pernet(net);
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index ec0d461cb921..d70a3e2bfad6 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -15,6 +15,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPCapableACKRX", MPTCP_MIB_MPCAPABLEPASSIVEACK),
 	SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK),
 	SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK),
+	SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP),
 	SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT),
 	SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
 	SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index d68136f93dac..062775700b63 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -10,6 +10,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_MPCAPABLEPASSIVEACK,	/* Received third ACK with MP_CAPABLE */
 	MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK,/* Server-side fallback during 3-way handshake */
 	MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */
+	MPTCP_MIB_MPCAPABLEACTIVEDROP,	/* Client-side fallback due to a MPC drop */
 	MPTCP_MIB_TOKENFALLBACKINIT,	/* Could not init/allocate token */
 	MPTCP_MIB_RETRANSSEGS,		/* Segments retransmitted at the MPTCP-level */
 	MPTCP_MIB_JOINNOTOKEN,		/* Received MP_JOIN but the token was not found */
-- 
cgit v1.3-3-g829e


From 27069e7cb3d1cea9377069266acf19b9cc5ad0ae Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 9 Sep 2024 22:09:23 +0200
Subject: mptcp: disable active MPTCP in case of blackhole

An MPTCP firewall blackhole can be detected if the following SYN
retransmission after a fallback to "plain" TCP is accepted.

In case of blackhole, a similar technique to the one in place with TFO
is now used: MPTCP can be disabled for a certain period of time, 1h by
default. This time period will grow exponentially when more blackhole
issues get detected right after MPTCP is re-enabled and will reset to
the initial value when the blackhole issue goes away.

The blackhole period can be modified thanks to a new sysctl knob:
blackhole_timeout. Two new MIB counters help understanding what's
happening:

- 'Blackhole', incremented when a blackhole is detected.
- 'MPCapableSYNTXDisabled', incremented when an MPTCP connection
  directly falls back to TCP during the blackhole period.

Because the technique is inspired by the one used by TFO, an important
part of the new code is similar to what can find in tcp_fastopen.c, with
some adaptations to the MPTCP case.

Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/57
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240909-net-next-mptcp-fallback-x-mpc-v1-3-da7ebb4cd2a3@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/mptcp-sysctl.rst |  11 +++
 net/mptcp/ctrl.c                          | 121 +++++++++++++++++++++++++++++-
 net/mptcp/mib.c                           |   2 +
 net/mptcp/mib.h                           |   2 +
 net/mptcp/protocol.c                      |  11 ++-
 net/mptcp/protocol.h                      |   8 +-
 net/mptcp/subflow.c                       |   4 +
 7 files changed, 151 insertions(+), 8 deletions(-)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index fd514bba8c43..95598c21fc8e 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -34,6 +34,17 @@ available_schedulers - STRING
 	Shows the available schedulers choices that are registered. More packet
 	schedulers may be available, but not loaded.
 
+blackhole_timeout - INTEGER (seconds)
+	Initial time period in second to disable MPTCP on active MPTCP sockets
+	when a MPTCP firewall blackhole issue happens. This time period will
+	grow exponentially when more blackhole issues get detected right after
+	MPTCP is re-enabled and will reset to the initial value when the
+	blackhole issue goes away.
+
+	0 to disable the blackhole detection.
+
+	Default: 3600
+
 checksum_enabled - BOOLEAN
 	Control whether DSS checksum can be enabled.
 
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 0b23e3c5e8ff..38d8121331d4 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -28,8 +28,11 @@ struct mptcp_pernet {
 #endif
 
 	unsigned int add_addr_timeout;
+	unsigned int blackhole_timeout;
 	unsigned int close_timeout;
 	unsigned int stale_loss_cnt;
+	atomic_t active_disable_times;
+	unsigned long active_disable_stamp;
 	u8 mptcp_enabled;
 	u8 checksum_enabled;
 	u8 allow_join_initial_addr_port;
@@ -88,6 +91,8 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
 	pernet->add_addr_timeout = TCP_RTO_MAX;
+	pernet->blackhole_timeout = 3600;
+	atomic_set(&pernet->active_disable_times, 0);
 	pernet->close_timeout = TCP_TIMEWAIT_LEN;
 	pernet->checksum_enabled = 0;
 	pernet->allow_join_initial_addr_port = 1;
@@ -152,6 +157,20 @@ static int proc_available_schedulers(const struct ctl_table *ctl,
 	return ret;
 }
 
+static int proc_blackhole_detect_timeout(const struct ctl_table *table,
+					 int write, void *buffer, size_t *lenp,
+					 loff_t *ppos)
+{
+	struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns);
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		atomic_set(&pernet->active_disable_times, 0);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -218,6 +237,13 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.mode = 0644,
 		.proc_handler = proc_dointvec_jiffies,
 	},
+	{
+		.procname = "blackhole_timeout",
+		.maxlen = sizeof(unsigned int),
+		.mode = 0644,
+		.proc_handler = proc_blackhole_detect_timeout,
+		.extra1 = SYSCTL_ZERO,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -241,6 +267,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[6].data = &pernet->scheduler;
 	/* table[7] is for available_schedulers which is read-only info */
 	table[8].data = &pernet->close_timeout;
+	table[9].data = &pernet->blackhole_timeout;
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));
@@ -278,6 +305,88 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {}
 
 #endif /* CONFIG_SYSCTL */
 
+/* The following code block is to deal with middle box issues with MPTCP,
+ * similar to what is done with TFO.
+ * The proposed solution is to disable active MPTCP globally when SYN+MPC are
+ * dropped, while SYN without MPC aren't. In this case, active side MPTCP is
+ * disabled globally for 1hr at first. Then if it happens again, it is disabled
+ * for 2h, then 4h, 8h, ...
+ * The timeout is reset back to 1hr when a successful active MPTCP connection is
+ * fully established.
+ */
+
+/* Disable active MPTCP and record current jiffies and active_disable_times */
+void mptcp_active_disable(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+	struct mptcp_pernet *pernet;
+
+	pernet = mptcp_get_pernet(net);
+
+	if (!READ_ONCE(pernet->blackhole_timeout))
+		return;
+
+	/* Paired with READ_ONCE() in mptcp_active_should_disable() */
+	WRITE_ONCE(pernet->active_disable_stamp, jiffies);
+
+	/* Paired with smp_rmb() in mptcp_active_should_disable().
+	 * We want pernet->active_disable_stamp to be updated first.
+	 */
+	smp_mb__before_atomic();
+	atomic_inc(&pernet->active_disable_times);
+
+	MPTCP_INC_STATS(net, MPTCP_MIB_BLACKHOLE);
+}
+
+/* Calculate timeout for MPTCP active disable
+ * Return true if we are still in the active MPTCP disable period
+ * Return false if timeout already expired and we should use active MPTCP
+ */
+bool mptcp_active_should_disable(struct sock *ssk)
+{
+	struct net *net = sock_net(ssk);
+	unsigned int blackhole_timeout;
+	struct mptcp_pernet *pernet;
+	unsigned long timeout;
+	int disable_times;
+	int multiplier;
+
+	pernet = mptcp_get_pernet(net);
+	blackhole_timeout = READ_ONCE(pernet->blackhole_timeout);
+
+	if (!blackhole_timeout)
+		return false;
+
+	disable_times = atomic_read(&pernet->active_disable_times);
+	if (!disable_times)
+		return false;
+
+	/* Paired with smp_mb__before_atomic() in mptcp_active_disable() */
+	smp_rmb();
+
+	/* Limit timeout to max: 2^6 * initial timeout */
+	multiplier = 1 << min(disable_times - 1, 6);
+
+	/* Paired with the WRITE_ONCE() in mptcp_active_disable(). */
+	timeout = READ_ONCE(pernet->active_disable_stamp) +
+		  multiplier * blackhole_timeout * HZ;
+
+	return time_before(jiffies, timeout);
+}
+
+/* Enable active MPTCP and reset active_disable_times if needed */
+void mptcp_active_enable(struct sock *sk)
+{
+	struct mptcp_pernet *pernet = mptcp_get_pernet(sock_net(sk));
+
+	if (atomic_read(&pernet->active_disable_times)) {
+		struct dst_entry *dst = sk_dst_get(sk);
+
+		if (dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))
+			atomic_set(&pernet->active_disable_times, 0);
+	}
+}
+
 /* Check the number of retransmissions, and fallback to TCP if needed */
 void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
 {
@@ -290,10 +399,14 @@ void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
 	timeouts = inet_csk(ssk)->icsk_retransmits;
 	subflow = mptcp_subflow_ctx(ssk);
 
-	if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT &&
-	    (timeouts == 2 || (timeouts < 2 && expired))) {
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP);
-		mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
+	if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) {
+		if (timeouts == 2 || (timeouts < 2 && expired)) {
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP);
+			subflow->mpc_drop = 1;
+			mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
+		} else {
+			subflow->mpc_drop = 0;
+		}
 	}
 }
 
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index d70a3e2bfad6..38c2efc82b94 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -16,6 +16,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK),
 	SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK),
 	SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP),
+	SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED),
 	SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT),
 	SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
 	SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
@@ -74,6 +75,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE),
 	SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT),
 	SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB),
+	SNMP_MIB_ITEM("Blackhole", MPTCP_MIB_BLACKHOLE),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 062775700b63..c8ffe18a8722 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -11,6 +11,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK,/* Server-side fallback during 3-way handshake */
 	MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */
 	MPTCP_MIB_MPCAPABLEACTIVEDROP,	/* Client-side fallback due to a MPC drop */
+	MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */
 	MPTCP_MIB_TOKENFALLBACKINIT,	/* Could not init/allocate token */
 	MPTCP_MIB_RETRANSSEGS,		/* Segments retransmitted at the MPTCP-level */
 	MPTCP_MIB_JOINNOTOKEN,		/* Received MP_JOIN but the token was not found */
@@ -75,6 +76,7 @@ enum linux_mptcp_mib_field {
 					 */
 	MPTCP_MIB_RCVWNDCONFLICT,	/* Conflict with while updating msk rcv wnd */
 	MPTCP_MIB_CURRESTAB,		/* Current established MPTCP connections */
+	MPTCP_MIB_BLACKHOLE,		/* A blackhole has been detected */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index cbbcc46cfef0..c2317919fc14 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3737,9 +3737,14 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info))
 		mptcp_subflow_early_fallback(msk, subflow);
 #endif
-	if (subflow->request_mptcp && mptcp_token_new_connect(ssk)) {
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT);
-		mptcp_subflow_early_fallback(msk, subflow);
+	if (subflow->request_mptcp) {
+		if (mptcp_active_should_disable(sk)) {
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDISABLED);
+			mptcp_subflow_early_fallback(msk, subflow);
+		} else if (mptcp_token_new_connect(ssk) < 0) {
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT);
+			mptcp_subflow_early_fallback(msk, subflow);
+		}
 	}
 
 	WRITE_ONCE(msk->write_seq, subflow->idsn);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 302bd808b839..74417aae08d0 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -531,7 +531,8 @@ struct mptcp_subflow_context {
 		valid_csum_seen : 1,        /* at least one csum validated */
 		is_mptfo : 1,	    /* subflow is doing TFO */
 		close_event_done : 1,       /* has done the post-closed part */
-		__unused : 9;
+		mpc_drop : 1,	    /* the MPC option has been dropped in a rtx */
+		__unused : 8;
 	bool	data_avail;
 	bool	scheduled;
 	u32	remote_nonce;
@@ -697,6 +698,11 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net);
 unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
+
+void mptcp_active_disable(struct sock *sk);
+bool mptcp_active_should_disable(struct sock *ssk);
+void mptcp_active_enable(struct sock *sk);
+
 void mptcp_get_available_schedulers(char *buf, size_t maxlen);
 void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 				       struct mptcp_subflow_context *subflow,
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index b9b14e75e8c2..1040b3b9696b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -546,6 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->mp_capable = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
+		mptcp_active_enable(parent);
 		mptcp_propagate_state(parent, sk, subflow, &mp_opt);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
@@ -591,6 +592,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
 		}
 	} else if (mptcp_check_fallback(sk)) {
+		/* It looks like MPTCP is blocked, while TCP is not */
+		if (subflow->mpc_drop)
+			mptcp_active_disable(parent);
 fallback:
 		mptcp_propagate_state(parent, sk, subflow, NULL);
 	}
-- 
cgit v1.3-3-g829e


From af647fe240a9c9ea5f63bb9194b971049098955e Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Tue, 10 Sep 2024 13:06:35 +0100
Subject: qlcnic: make read-only const array key static

Don't populate the const read-only array key on the stack at
run time, instead make it static.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240910120635.115266-1-colin.i.king@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index bcef8ab715bf..d7cdea8f604d 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2042,12 +2042,14 @@ int qlcnic_83xx_config_hw_lro(struct qlcnic_adapter *adapter, int mode)
 
 int qlcnic_83xx_config_rss(struct qlcnic_adapter *adapter, int enable)
 {
-	int err;
-	u32 word;
 	struct qlcnic_cmd_args cmd;
-	const u64 key[] = { 0xbeac01fa6a42b73bULL, 0x8030f20c77cb2da3ULL,
-			    0xae7b30b4d0ca2bcbULL, 0x43a38fb04167253dULL,
-			    0x255b0ec26d5a56daULL };
+	static const u64 key[] = {
+		0xbeac01fa6a42b73bULL, 0x8030f20c77cb2da3ULL,
+		0xae7b30b4d0ca2bcbULL, 0x43a38fb04167253dULL,
+		0x255b0ec26d5a56daULL
+	};
+	u32 word;
+	int err;
 
 	err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIGURE_RSS);
 	if (err)
-- 
cgit v1.3-3-g829e


From cf06766f1525d35542cbb15fe6103caf44840376 Mon Sep 17 00:00:00 2001
From: Jonathan Cooper <jonathan.s.cooper@amd.com>
Date: Tue, 10 Sep 2024 16:30:13 +0100
Subject: sfc: Add X4 PF support

Add X4 series. Most functionality is the same as previous
EF10 nics but enough is different to warrant a new nic type struct
and revision; for example legacy interrupts and SRIOV are
not supported.

Most removed features will be re-added later as new implementations.

Signed-off-by: Jonathan Cooper <jonathan.s.cooper@amd.com>
Acked-by: Edward Cree <ecree.xilinx@gmail.com>
Acked-by: Martin Habets <habetsm.xilinx@gmail.com>
Link: https://patch.msgid.link/20240910153014.12803-1-jonathan.s.cooper@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/ef10.c       | 127 ++++++++++++++++++++++++++++++++++
 drivers/net/ethernet/sfc/efx.c        |   4 ++
 drivers/net/ethernet/sfc/nic.h        |   2 +
 drivers/net/ethernet/sfc/nic_common.h |   1 +
 4 files changed, 134 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 7d69302ffa0a..de131fc5fa0b 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4302,3 +4302,130 @@ const struct efx_nic_type efx_hunt_a0_nic_type = {
 	.sensor_event = efx_mcdi_sensor_event,
 	.rx_recycle_ring_size = efx_ef10_recycle_ring_size,
 };
+
+const struct efx_nic_type efx_x4_nic_type = {
+	.is_vf = false,
+	.mem_bar = efx_ef10_pf_mem_bar,
+	.mem_map_size = efx_ef10_mem_map_size,
+	.probe = efx_ef10_probe_pf,
+	.remove = efx_ef10_remove,
+	.dimension_resources = efx_ef10_dimension_resources,
+	.init = efx_ef10_init_nic,
+	.fini = efx_ef10_fini_nic,
+	.map_reset_reason = efx_ef10_map_reset_reason,
+	.map_reset_flags = efx_ef10_map_reset_flags,
+	.reset = efx_ef10_reset,
+	.probe_port = efx_mcdi_port_probe,
+	.remove_port = efx_mcdi_port_remove,
+	.fini_dmaq = efx_fini_dmaq,
+	.prepare_flr = efx_ef10_prepare_flr,
+	.finish_flr = efx_port_dummy_op_void,
+	.describe_stats = efx_ef10_describe_stats,
+	.update_stats = efx_ef10_update_stats_pf,
+	.start_stats = efx_mcdi_mac_start_stats,
+	.pull_stats = efx_mcdi_mac_pull_stats,
+	.stop_stats = efx_mcdi_mac_stop_stats,
+	.push_irq_moderation = efx_ef10_push_irq_moderation,
+	.reconfigure_mac = efx_ef10_mac_reconfigure,
+	.check_mac_fault = efx_mcdi_mac_check_fault,
+	.reconfigure_port = efx_mcdi_port_reconfigure,
+	.get_wol = efx_ef10_get_wol,
+	.set_wol = efx_ef10_set_wol,
+	.resume_wol = efx_port_dummy_op_void,
+	.get_fec_stats = efx_ef10_get_fec_stats,
+	.test_chip = efx_ef10_test_chip,
+	.test_nvram = efx_mcdi_nvram_test_all,
+	.mcdi_request = efx_ef10_mcdi_request,
+	.mcdi_poll_response = efx_ef10_mcdi_poll_response,
+	.mcdi_read_response = efx_ef10_mcdi_read_response,
+	.mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
+	.mcdi_reboot_detected = efx_ef10_mcdi_reboot_detected,
+	.irq_enable_master = efx_port_dummy_op_void,
+	.irq_test_generate = efx_ef10_irq_test_generate,
+	.irq_disable_non_ev = efx_port_dummy_op_void,
+	.irq_handle_msi = efx_ef10_msi_interrupt,
+	.tx_probe = efx_ef10_tx_probe,
+	.tx_init = efx_ef10_tx_init,
+	.tx_write = efx_ef10_tx_write,
+	.tx_limit_len = efx_ef10_tx_limit_len,
+	.tx_enqueue = __efx_enqueue_skb,
+	.rx_push_rss_config = efx_mcdi_pf_rx_push_rss_config,
+	.rx_pull_rss_config = efx_mcdi_rx_pull_rss_config,
+	.rx_push_rss_context_config = efx_mcdi_rx_push_rss_context_config,
+	.rx_pull_rss_context_config = efx_mcdi_rx_pull_rss_context_config,
+	.rx_restore_rss_contexts = efx_mcdi_rx_restore_rss_contexts,
+	.rx_probe = efx_mcdi_rx_probe,
+	.rx_init = efx_mcdi_rx_init,
+	.rx_remove = efx_mcdi_rx_remove,
+	.rx_write = efx_ef10_rx_write,
+	.rx_defer_refill = efx_ef10_rx_defer_refill,
+	.rx_packet = __efx_rx_packet,
+	.ev_probe = efx_mcdi_ev_probe,
+	.ev_init = efx_ef10_ev_init,
+	.ev_fini = efx_mcdi_ev_fini,
+	.ev_remove = efx_mcdi_ev_remove,
+	.ev_process = efx_ef10_ev_process,
+	.ev_read_ack = efx_ef10_ev_read_ack,
+	.ev_test_generate = efx_ef10_ev_test_generate,
+	.filter_table_probe = efx_ef10_filter_table_probe,
+	.filter_table_restore = efx_mcdi_filter_table_restore,
+	.filter_table_remove = efx_ef10_filter_table_remove,
+	.filter_insert = efx_mcdi_filter_insert,
+	.filter_remove_safe = efx_mcdi_filter_remove_safe,
+	.filter_get_safe = efx_mcdi_filter_get_safe,
+	.filter_clear_rx = efx_mcdi_filter_clear_rx,
+	.filter_count_rx_used = efx_mcdi_filter_count_rx_used,
+	.filter_get_rx_id_limit = efx_mcdi_filter_get_rx_id_limit,
+	.filter_get_rx_ids = efx_mcdi_filter_get_rx_ids,
+#ifdef CONFIG_RFS_ACCEL
+	.filter_rfs_expire_one = efx_mcdi_filter_rfs_expire_one,
+#endif
+#ifdef CONFIG_SFC_MTD
+	.mtd_probe = efx_ef10_mtd_probe,
+	.mtd_rename = efx_mcdi_mtd_rename,
+	.mtd_read = efx_mcdi_mtd_read,
+	.mtd_erase = efx_mcdi_mtd_erase,
+	.mtd_write = efx_mcdi_mtd_write,
+	.mtd_sync = efx_mcdi_mtd_sync,
+#endif
+	.ptp_write_host_time = efx_ef10_ptp_write_host_time,
+	.ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
+	.ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
+	.vlan_rx_add_vid = efx_ef10_vlan_rx_add_vid,
+	.vlan_rx_kill_vid = efx_ef10_vlan_rx_kill_vid,
+	.udp_tnl_push_ports = efx_ef10_udp_tnl_push_ports,
+	.udp_tnl_has_port = efx_ef10_udp_tnl_has_port,
+#ifdef CONFIG_SFC_SRIOV
+	/* currently set to the VF versions of these functions
+	 * because SRIOV will be reimplemented later.
+	 */
+	.vswitching_probe = efx_ef10_vswitching_probe_vf,
+	.vswitching_restore = efx_ef10_vswitching_restore_vf,
+	.vswitching_remove = efx_ef10_vswitching_remove_vf,
+#endif
+	.get_mac_address = efx_ef10_get_mac_address_pf,
+	.set_mac_address = efx_ef10_set_mac_address,
+	.tso_versions = efx_ef10_tso_versions,
+
+	.get_phys_port_id = efx_ef10_get_phys_port_id,
+	.revision = EFX_REV_X4,
+	.max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
+	.rx_prefix_size = ES_DZ_RX_PREFIX_SIZE,
+	.rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST,
+	.rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST,
+	.can_rx_scatter = true,
+	.always_rx_scatter = true,
+	.option_descriptors = true,
+	.min_interrupt_mode = EFX_INT_MODE_MSIX,
+	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
+	.offload_features = EF10_OFFLOAD_FEATURES,
+	.mcdi_max_ver = 2,
+	.max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS,
+	.hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
+			    1 << HWTSTAMP_FILTER_ALL,
+	.check_caps = ef10_check_caps,
+	.print_additional_fwver = efx_ef10_print_additional_fwver,
+	.sensor_event = efx_mcdi_sensor_event,
+	.rx_recycle_ring_size = efx_ef10_recycle_ring_size,
+};
+
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 6f1a01ded7d4..36b3b57e2055 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -821,6 +821,10 @@ static const struct pci_device_id efx_pci_table[] = {
 	 .driver_data = (unsigned long) &efx_hunt_a0_nic_type},
 	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x1b03),  /* SFC9250 VF */
 	 .driver_data = (unsigned long) &efx_hunt_a0_vf_nic_type},
+	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0c03),  /* X4 PF (FF/LL) */
+	 .driver_data = (unsigned long)&efx_x4_nic_type},
+	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x2c03),  /* X4 PF (FF only) */
+	 .driver_data = (unsigned long)&efx_x4_nic_type},
 	{0}			/* end of list */
 };
 
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 1db64fc6e909..9fa5c4c713ab 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -211,4 +211,6 @@ int efx_ef10_tx_tso_desc(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
 extern const struct efx_nic_type efx_hunt_a0_nic_type;
 extern const struct efx_nic_type efx_hunt_a0_vf_nic_type;
 
+extern const struct efx_nic_type efx_x4_nic_type;
+
 #endif /* EFX_NIC_H */
diff --git a/drivers/net/ethernet/sfc/nic_common.h b/drivers/net/ethernet/sfc/nic_common.h
index 466df5348b29..7ec4ac7b7ff5 100644
--- a/drivers/net/ethernet/sfc/nic_common.h
+++ b/drivers/net/ethernet/sfc/nic_common.h
@@ -21,6 +21,7 @@ enum {
 	 */
 	EFX_REV_HUNT_A0 = 4,
 	EFX_REV_EF100 = 5,
+	EFX_REV_X4 = 6,
 };
 
 static inline int efx_nic_rev(struct efx_nic *efx)
-- 
cgit v1.3-3-g829e


From b2d9544070d052804a12a7859aa212e952b96691 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 10 Sep 2024 15:09:13 -0700
Subject: net: gianfar: fix NVMEM mac address

If nvmem loads after the ethernet driver, mac address assignments will
not take effect. of_get_ethdev_address returns EPROBE_DEFER in such a
case so we need to handle that to avoid eth_hw_addr_random.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240910220913.14101-1-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/gianfar.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 2baef59f741d..ecb1703ea150 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -754,6 +754,8 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 		priv->device_flags |= FSL_GIANFAR_DEV_HAS_BUF_STASHING;
 
 	err = of_get_ethdev_address(np, dev);
+	if (err == -EPROBE_DEFER)
+		goto err_grp_init;
 	if (err) {
 		eth_hw_addr_random(dev);
 		dev_info(&ofdev->dev, "Using random MAC address: %pM\n", dev->dev_addr);
-- 
cgit v1.3-3-g829e


From fce1e9f86af13cbd6696ef0c8775990559108f45 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 10 Sep 2024 19:46:35 +0200
Subject: net: ethtool: phy: Check the req_info.pdn field for GET commands

When processing the netlink GET requests to get PHY info, the req_info.pdn
pointer is NULL when no PHY matches the requested parameters, such as when
the phy_index is invalid, or there's simply no PHY attached to the
interface.

Therefore, check the req_info.pdn pointer for NULL instead of
dereferencing it.

Suggested-by: Eric Dumazet <edumazet@google.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Closes: https://lore.kernel.org/netdev/CANn89iKRW0WpGAh1tKqY345D8WkYCPm3Y9ym--Si42JZrQAu1g@mail.gmail.com/T/#mfced87d607d18ea32b3b4934dfa18d7b36669285
Fixes: 17194be4c8e1 ("net: ethtool: Introduce a command to list PHYs on an interface")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240910174636.857352-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index 560dd039c662..4ef7c6e32d10 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -164,7 +164,7 @@ int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_unlock_rtnl;
 
 	/* No PHY, return early */
-	if (!req_info.pdn->phy)
+	if (!req_info.pdn)
 		goto err_unlock_rtnl;
 
 	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
-- 
cgit v1.3-3-g829e


From b2c8a506f6a70d60583aa2d8abfd4aca01b578fb Mon Sep 17 00:00:00 2001
From: Divya Koppera <divya.koppera@microchip.com>
Date: Mon, 9 Sep 2024 17:13:39 +0530
Subject: net: phy: microchip_t1: Cable Diagnostics for lan887x

Add support for cable diagnostics in lan887x PHY.
Using this we can diagnose connected/open/short wires and
also length where cable fault is occurred.

Signed-off-by: Divya Koppera <divya.koppera@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240909114339.3446-1-divya.koppera@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/microchip_t1.c | 413 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 413 insertions(+)

diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c
index 5732ad65e7f9..a5ef8fe50704 100644
--- a/drivers/net/phy/microchip_t1.c
+++ b/drivers/net/phy/microchip_t1.c
@@ -175,6 +175,9 @@
 #define LAN887X_LED_LINK_ACT_ANY_SPEED		0x0
 
 /* MX chip top registers */
+#define LAN887X_CHIP_HARD_RST			0xf03e
+#define LAN887X_CHIP_HARD_RST_RESET		BIT(0)
+
 #define LAN887X_CHIP_SOFT_RST			0xf03f
 #define LAN887X_CHIP_SOFT_RST_RESET		BIT(0)
 
@@ -188,9 +191,60 @@
 #define LAN887X_EFUSE_READ_DAT9_SGMII_DIS	BIT(9)
 #define LAN887X_EFUSE_READ_DAT9_MAC_MODE	GENMASK(1, 0)
 
+#define LAN887X_CALIB_CONFIG_100		0x437
+#define LAN887X_CALIB_CONFIG_100_CBL_DIAG_USE_LOCAL_SMPL	BIT(5)
+#define LAN887X_CALIB_CONFIG_100_CBL_DIAG_STB_SYNC_MODE		BIT(4)
+#define LAN887X_CALIB_CONFIG_100_CBL_DIAG_CLK_ALGN_MODE		BIT(3)
+#define LAN887X_CALIB_CONFIG_100_VAL \
+	(LAN887X_CALIB_CONFIG_100_CBL_DIAG_CLK_ALGN_MODE |\
+	LAN887X_CALIB_CONFIG_100_CBL_DIAG_STB_SYNC_MODE |\
+	LAN887X_CALIB_CONFIG_100_CBL_DIAG_USE_LOCAL_SMPL)
+
+#define LAN887X_MAX_PGA_GAIN_100		0x44f
+#define LAN887X_MIN_PGA_GAIN_100		0x450
+#define LAN887X_START_CBL_DIAG_100		0x45a
+#define LAN887X_CBL_DIAG_DONE			BIT(1)
+#define LAN887X_CBL_DIAG_START			BIT(0)
+#define LAN887X_CBL_DIAG_STOP			0x0
+
+#define LAN887X_CBL_DIAG_TDR_THRESH_100		0x45b
+#define LAN887X_CBL_DIAG_AGC_THRESH_100		0x45c
+#define LAN887X_CBL_DIAG_MIN_WAIT_CONFIG_100	0x45d
+#define LAN887X_CBL_DIAG_MAX_WAIT_CONFIG_100	0x45e
+#define LAN887X_CBL_DIAG_CYC_CONFIG_100		0x45f
+#define LAN887X_CBL_DIAG_TX_PULSE_CONFIG_100	0x460
+#define LAN887X_CBL_DIAG_MIN_PGA_GAIN_100	0x462
+#define LAN887X_CBL_DIAG_AGC_GAIN_100		0x497
+#define LAN887X_CBL_DIAG_POS_PEAK_VALUE_100	0x499
+#define LAN887X_CBL_DIAG_NEG_PEAK_VALUE_100	0x49a
+#define LAN887X_CBL_DIAG_POS_PEAK_TIME_100	0x49c
+#define LAN887X_CBL_DIAG_NEG_PEAK_TIME_100	0x49d
+
+#define MICROCHIP_CABLE_NOISE_MARGIN		20
+#define MICROCHIP_CABLE_TIME_MARGIN		89
+#define MICROCHIP_CABLE_MIN_TIME_DIFF		96
+#define MICROCHIP_CABLE_MAX_TIME_DIFF	\
+	(MICROCHIP_CABLE_MIN_TIME_DIFF + MICROCHIP_CABLE_TIME_MARGIN)
+
 #define DRIVER_AUTHOR	"Nisar Sayed <nisar.sayed@microchip.com>"
 #define DRIVER_DESC	"Microchip LAN87XX/LAN937x/LAN887x T1 PHY driver"
 
+/* TEST_MODE_NORMAL: Non-hybrid results to calculate cable status(open/short/ok)
+ * TEST_MODE_HYBRID: Hybrid results to calculate distance to fault
+ */
+enum cable_diag_mode {
+	TEST_MODE_NORMAL,
+	TEST_MODE_HYBRID
+};
+
+/* CD_TEST_INIT: Cable test is initated
+ * CD_TEST_DONE: Cable test is done
+ */
+enum cable_diag_state {
+	CD_TEST_INIT,
+	CD_TEST_DONE
+};
+
 struct access_ereg_val {
 	u8  mode;
 	u8  bank;
@@ -1420,6 +1474,362 @@ static void lan887x_get_strings(struct phy_device *phydev, u8 *data)
 		ethtool_puts(&data, lan887x_hw_stats[i].string);
 }
 
+static int lan887x_cd_reset(struct phy_device *phydev,
+			    enum cable_diag_state cd_done)
+{
+	u16 val;
+	int rc;
+
+	/* Chip hard-reset */
+	rc = phy_write_mmd(phydev, MDIO_MMD_VEND1, LAN887X_CHIP_HARD_RST,
+			   LAN887X_CHIP_HARD_RST_RESET);
+	if (rc < 0)
+		return rc;
+
+	/* Wait for reset to complete */
+	rc = phy_read_poll_timeout(phydev, MII_PHYSID2, val,
+				   ((val & GENMASK(15, 4)) ==
+				    (PHY_ID_LAN887X & GENMASK(15, 4))),
+				   5000, 50000, true);
+	if (rc < 0)
+		return rc;
+
+	if (cd_done == CD_TEST_DONE) {
+		/* Cable diagnostics complete. Restore PHY. */
+		rc = lan887x_phy_setup(phydev);
+		if (rc < 0)
+			return rc;
+
+		rc = lan887x_phy_init(phydev);
+		if (rc < 0)
+			return rc;
+
+		rc = lan887x_phy_reconfig(phydev);
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int lan887x_cable_test_prep(struct phy_device *phydev,
+				   enum cable_diag_mode mode)
+{
+	static const struct lan887x_regwr_map values[] = {
+		{MDIO_MMD_VEND1, LAN887X_MAX_PGA_GAIN_100, 0x1f},
+		{MDIO_MMD_VEND1, LAN887X_MIN_PGA_GAIN_100, 0x0},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_TDR_THRESH_100, 0x1},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_AGC_THRESH_100, 0x3c},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_MIN_WAIT_CONFIG_100, 0x0},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_MAX_WAIT_CONFIG_100, 0x46},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_CYC_CONFIG_100, 0x5a},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_TX_PULSE_CONFIG_100, 0x44d5},
+		{MDIO_MMD_VEND1, LAN887X_CBL_DIAG_MIN_PGA_GAIN_100, 0x0},
+
+	};
+	int rc;
+
+	rc = lan887x_cd_reset(phydev, CD_TEST_INIT);
+	if (rc < 0)
+		return rc;
+
+	/* Forcing DUT to master mode, as we don't care about
+	 * mode during diagnostics
+	 */
+	rc = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_PMD_BT1_CTRL,
+			   MDIO_PMA_PMD_BT1_CTRL_CFG_MST);
+	if (rc < 0)
+		return rc;
+
+	rc = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x80b0, 0x0038);
+	if (rc < 0)
+		return rc;
+
+	rc = phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+			    LAN887X_CALIB_CONFIG_100, 0,
+			    LAN887X_CALIB_CONFIG_100_VAL);
+	if (rc < 0)
+		return rc;
+
+	for (int i = 0; i < ARRAY_SIZE(values); i++) {
+		rc = phy_write_mmd(phydev, values[i].mmd, values[i].reg,
+				   values[i].val);
+		if (rc < 0)
+			return rc;
+
+		if (mode &&
+		    values[i].reg == LAN887X_CBL_DIAG_MAX_WAIT_CONFIG_100) {
+			rc = phy_write_mmd(phydev, values[i].mmd,
+					   values[i].reg, 0xa);
+			if (rc < 0)
+				return rc;
+		}
+	}
+
+	if (mode == TEST_MODE_HYBRID) {
+		rc = phy_modify_mmd(phydev, MDIO_MMD_PMAPMD,
+				    LAN887X_AFE_PORT_TESTBUS_CTRL4,
+				    BIT(0), BIT(0));
+		if (rc < 0)
+			return rc;
+	}
+
+	/* HW_INIT 100T1, Get DUT running in 100T1 mode */
+	rc = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26,
+			    LAN887X_REG_REG26_HW_INIT_SEQ_EN,
+			    LAN887X_REG_REG26_HW_INIT_SEQ_EN);
+	if (rc < 0)
+		return rc;
+
+	/* Cable diag requires hard reset and is sensitive regarding the delays.
+	 * Hard reset is expected into and out of cable diag.
+	 * Wait for 50ms
+	 */
+	msleep(50);
+
+	/* Start cable diag */
+	return phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			   LAN887X_START_CBL_DIAG_100,
+			   LAN887X_CBL_DIAG_START);
+}
+
+static int lan887x_cable_test_chk(struct phy_device *phydev,
+				  enum cable_diag_mode mode)
+{
+	int val;
+	int rc;
+
+	if (mode == TEST_MODE_HYBRID) {
+		/* Cable diag requires hard reset and is sensitive regarding the delays.
+		 * Hard reset is expected into and out of cable diag.
+		 * Wait for cable diag to complete.
+		 * Minimum wait time is 50ms if the condition is not a match.
+		 */
+		rc = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
+					       LAN887X_START_CBL_DIAG_100, val,
+					       ((val & LAN887X_CBL_DIAG_DONE) ==
+						LAN887X_CBL_DIAG_DONE),
+					       50000, 500000, false);
+		if (rc < 0)
+			return rc;
+	} else {
+		rc = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				  LAN887X_START_CBL_DIAG_100);
+		if (rc < 0)
+			return rc;
+
+		if ((rc & LAN887X_CBL_DIAG_DONE) != LAN887X_CBL_DIAG_DONE)
+			return -EAGAIN;
+	}
+
+	/* Stop cable diag */
+	return phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			     LAN887X_START_CBL_DIAG_100,
+			     LAN887X_CBL_DIAG_STOP);
+}
+
+static int lan887x_cable_test_start(struct phy_device *phydev)
+{
+	int rc, ret;
+
+	rc = lan887x_cable_test_prep(phydev, TEST_MODE_NORMAL);
+	if (rc < 0) {
+		ret = lan887x_cd_reset(phydev, CD_TEST_DONE);
+		if (ret < 0)
+			return ret;
+
+		return rc;
+	}
+
+	return 0;
+}
+
+static int lan887x_cable_test_report(struct phy_device *phydev)
+{
+	int pos_peak_cycle, pos_peak_cycle_hybrid, pos_peak_in_phases;
+	int pos_peak_time, pos_peak_time_hybrid, neg_peak_time;
+	int neg_peak_cycle, neg_peak_in_phases;
+	int pos_peak_in_phases_hybrid;
+	int gain_idx, gain_idx_hybrid;
+	int pos_peak_phase_hybrid;
+	int pos_peak, neg_peak;
+	int distance;
+	int detect;
+	int length;
+	int ret;
+	int rc;
+
+	/* Read non-hybrid results */
+	gain_idx = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				LAN887X_CBL_DIAG_AGC_GAIN_100);
+	if (gain_idx < 0) {
+		rc = gain_idx;
+		goto error;
+	}
+
+	pos_peak = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				LAN887X_CBL_DIAG_POS_PEAK_VALUE_100);
+	if (pos_peak < 0) {
+		rc = pos_peak;
+		goto error;
+	}
+
+	neg_peak = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				LAN887X_CBL_DIAG_NEG_PEAK_VALUE_100);
+	if (neg_peak < 0) {
+		rc = neg_peak;
+		goto error;
+	}
+
+	pos_peak_time = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     LAN887X_CBL_DIAG_POS_PEAK_TIME_100);
+	if (pos_peak_time < 0) {
+		rc = pos_peak_time;
+		goto error;
+	}
+
+	neg_peak_time = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     LAN887X_CBL_DIAG_NEG_PEAK_TIME_100);
+	if (neg_peak_time < 0) {
+		rc = neg_peak_time;
+		goto error;
+	}
+
+	/* Calculate non-hybrid values */
+	pos_peak_cycle = (pos_peak_time >> 7) & 0x7f;
+	pos_peak_in_phases = (pos_peak_cycle * 96) + (pos_peak_time & 0x7f);
+	neg_peak_cycle = (neg_peak_time >> 7) & 0x7f;
+	neg_peak_in_phases = (neg_peak_cycle * 96) + (neg_peak_time & 0x7f);
+
+	/* Deriving the status of cable */
+	if (pos_peak > MICROCHIP_CABLE_NOISE_MARGIN &&
+	    neg_peak > MICROCHIP_CABLE_NOISE_MARGIN && gain_idx >= 0) {
+		if (pos_peak_in_phases > neg_peak_in_phases &&
+		    ((pos_peak_in_phases - neg_peak_in_phases) >=
+		     MICROCHIP_CABLE_MIN_TIME_DIFF) &&
+		    ((pos_peak_in_phases - neg_peak_in_phases) <
+		     MICROCHIP_CABLE_MAX_TIME_DIFF) &&
+		    pos_peak_in_phases > 0) {
+			detect = LAN87XX_CABLE_TEST_SAME_SHORT;
+		} else if (neg_peak_in_phases > pos_peak_in_phases &&
+			   ((neg_peak_in_phases - pos_peak_in_phases) >=
+			    MICROCHIP_CABLE_MIN_TIME_DIFF) &&
+			   ((neg_peak_in_phases - pos_peak_in_phases) <
+			    MICROCHIP_CABLE_MAX_TIME_DIFF) &&
+			   neg_peak_in_phases > 0) {
+			detect = LAN87XX_CABLE_TEST_OPEN;
+		} else {
+			detect = LAN87XX_CABLE_TEST_OK;
+		}
+	} else {
+		detect = LAN87XX_CABLE_TEST_OK;
+	}
+
+	if (detect == LAN87XX_CABLE_TEST_OK) {
+		distance = 0;
+		goto get_len;
+	}
+
+	/* Re-initialize PHY and start cable diag test */
+	rc = lan887x_cable_test_prep(phydev, TEST_MODE_HYBRID);
+	if (rc < 0)
+		goto cd_stop;
+
+	/* Wait for cable diag test completion */
+	rc = lan887x_cable_test_chk(phydev, TEST_MODE_HYBRID);
+	if (rc < 0)
+		goto cd_stop;
+
+	/* Read hybrid results */
+	gain_idx_hybrid = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				       LAN887X_CBL_DIAG_AGC_GAIN_100);
+	if (gain_idx_hybrid < 0) {
+		rc = gain_idx_hybrid;
+		goto error;
+	}
+
+	pos_peak_time_hybrid = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+					    LAN887X_CBL_DIAG_POS_PEAK_TIME_100);
+	if (pos_peak_time_hybrid < 0) {
+		rc = pos_peak_time_hybrid;
+		goto error;
+	}
+
+	/* Calculate hybrid values to derive cable length to fault */
+	pos_peak_cycle_hybrid = (pos_peak_time_hybrid >> 7) & 0x7f;
+	pos_peak_phase_hybrid = pos_peak_time_hybrid & 0x7f;
+	pos_peak_in_phases_hybrid = pos_peak_cycle_hybrid * 96 +
+				    pos_peak_phase_hybrid;
+
+	/* Distance to fault calculation.
+	 * distance = (peak_in_phases - peak_in_phases_hybrid) *
+	 *             propagationconstant.
+	 * constant to convert number of phases to meters
+	 * propagationconstant = 0.015953
+	 *                       (0.6811 * 2.9979 * 156.2499 * 0.0001 * 0.5)
+	 * Applying constant 1.5953 as ethtool further devides by 100 to
+	 * convert to meters.
+	 */
+	if (detect == LAN87XX_CABLE_TEST_OPEN) {
+		distance = (((pos_peak_in_phases - pos_peak_in_phases_hybrid)
+			     * 15953) / 10000);
+	} else if (detect == LAN87XX_CABLE_TEST_SAME_SHORT) {
+		distance = (((neg_peak_in_phases - pos_peak_in_phases_hybrid)
+			     * 15953) / 10000);
+	} else {
+		distance = 0;
+	}
+
+get_len:
+	rc = lan887x_cd_reset(phydev, CD_TEST_DONE);
+	if (rc < 0)
+		return rc;
+
+	length = ((u32)distance & GENMASK(15, 0));
+	ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A,
+				lan87xx_cable_test_report_trans(detect));
+	ethnl_cable_test_fault_length(phydev, ETHTOOL_A_CABLE_PAIR_A, length);
+
+	return 0;
+
+cd_stop:
+	/* Stop cable diag */
+	ret = phy_write_mmd(phydev, MDIO_MMD_VEND1,
+			    LAN887X_START_CBL_DIAG_100,
+			    LAN887X_CBL_DIAG_STOP);
+	if (ret < 0)
+		return ret;
+
+error:
+	/* Cable diag test failed */
+	ret = lan887x_cd_reset(phydev, CD_TEST_DONE);
+	if (ret < 0)
+		return ret;
+
+	/* Return error in failure case */
+	return rc;
+}
+
+static int lan887x_cable_test_get_status(struct phy_device *phydev,
+					 bool *finished)
+{
+	int rc;
+
+	rc = lan887x_cable_test_chk(phydev, TEST_MODE_NORMAL);
+	if (rc < 0) {
+		/* Let PHY statemachine poll again */
+		if (rc == -EAGAIN)
+			return 0;
+		return rc;
+	}
+
+	/* Cable diag test complete */
+	*finished = true;
+
+	/* Retrieve test status and cable length to fault */
+	return lan887x_cable_test_report(phydev);
+}
+
 static struct phy_driver microchip_t1_phy_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX),
@@ -1458,6 +1868,7 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_LAN887X),
 		.name		= "Microchip LAN887x T1 PHY",
+		.flags          = PHY_POLL_CABLE_TEST,
 		.probe		= lan887x_probe,
 		.get_features	= lan887x_get_features,
 		.config_init    = lan887x_phy_init,
@@ -1468,6 +1879,8 @@ static struct phy_driver microchip_t1_phy_driver[] = {
 		.suspend	= genphy_suspend,
 		.resume		= genphy_resume,
 		.read_status	= genphy_c45_read_status,
+		.cable_test_start = lan887x_cable_test_start,
+		.cable_test_get_status = lan887x_cable_test_get_status,
 	}
 };
 
-- 
cgit v1.3-3-g829e


From 7c88f86576f382a5037f7acf2fce796ccafba4db Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:45 +0000
Subject: netdev: add netdev_rx_queue_restart()

Add netdev_rx_queue_restart(), which resets an rx queue using the
queue API recently merged[1].

The queue API was merged to enable the core net stack to reset individual
rx queues to actuate changes in the rx queue's configuration. In later
patches in this series, we will use netdev_rx_queue_restart() to reset
rx queues after binding or unbinding dmabuf configuration, which will
cause reallocation of the page_pool to repopulate its memory using the
new configuration.

[1] https://lore.kernel.org/netdev/20240430231420.699177-1-shailend@google.com/T/

Signed-off-by: David Wei <dw@davidwei.uk>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-2-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netdev_rx_queue.h |  3 ++
 net/core/Makefile             |  1 +
 net/core/netdev_rx_queue.c    | 74 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+)
 create mode 100644 net/core/netdev_rx_queue.c

diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index aa1716fb0e53..e78ca52d67fb 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -54,4 +54,7 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
 	return index;
 }
 #endif
+
+int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq);
+
 #endif
diff --git a/net/core/Makefile b/net/core/Makefile
index 62be9aef2528..f82232b358a2 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 
 obj-y += net-sysfs.o
 obj-y += hotdata.o
+obj-y += netdev_rx_queue.o
 obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o
 obj-$(CONFIG_PROC_FS) += net-procfs.o
 obj-$(CONFIG_NET_PKTGEN) += pktgen.o
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
new file mode 100644
index 000000000000..da11720a5983
--- /dev/null
+++ b/net/core/netdev_rx_queue.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/netdevice.h>
+#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+
+int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
+{
+	void *new_mem, *old_mem;
+	int err;
+
+	if (!dev->queue_mgmt_ops || !dev->queue_mgmt_ops->ndo_queue_stop ||
+	    !dev->queue_mgmt_ops->ndo_queue_mem_free ||
+	    !dev->queue_mgmt_ops->ndo_queue_mem_alloc ||
+	    !dev->queue_mgmt_ops->ndo_queue_start)
+		return -EOPNOTSUPP;
+
+	ASSERT_RTNL();
+
+	new_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL);
+	if (!new_mem)
+		return -ENOMEM;
+
+	old_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL);
+	if (!old_mem) {
+		err = -ENOMEM;
+		goto err_free_new_mem;
+	}
+
+	err = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx);
+	if (err)
+		goto err_free_old_mem;
+
+	err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx);
+	if (err)
+		goto err_free_new_queue_mem;
+
+	err = dev->queue_mgmt_ops->ndo_queue_start(dev, new_mem, rxq_idx);
+	if (err)
+		goto err_start_queue;
+
+	dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem);
+
+	kvfree(old_mem);
+	kvfree(new_mem);
+
+	return 0;
+
+err_start_queue:
+	/* Restarting the queue with old_mem should be successful as we haven't
+	 * changed any of the queue configuration, and there is not much we can
+	 * do to recover from a failure here.
+	 *
+	 * WARN if we fail to recover the old rx queue, and at least free
+	 * old_mem so we don't also leak that.
+	 */
+	if (dev->queue_mgmt_ops->ndo_queue_start(dev, old_mem, rxq_idx)) {
+		WARN(1,
+		     "Failed to restart old queue in error path. RX queue %d may be unhealthy.",
+		     rxq_idx);
+		dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem);
+	}
+
+err_free_new_queue_mem:
+	dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem);
+
+err_free_old_mem:
+	kvfree(old_mem);
+
+err_free_new_mem:
+	kvfree(new_mem);
+
+	return err;
+}
-- 
cgit v1.3-3-g829e


From 3efd7ab46d0aebc3e567a9846e79a98dbad3291c Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:46 +0000
Subject: net: netdev netlink api to bind dma-buf to a net device

API takes the dma-buf fd as input, and binds it to the netdevice. The
user can specify the rx queues to bind the dma-buf to.

Suggested-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-3-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 47 +++++++++++++++++++++++++++++++++
 include/uapi/linux/netdev.h             | 11 ++++++++
 net/core/netdev-genl-gen.c              | 19 +++++++++++++
 net/core/netdev-genl-gen.h              |  2 ++
 net/core/netdev-genl.c                  |  6 +++++
 tools/include/uapi/linux/netdev.h       | 11 ++++++++
 6 files changed, 96 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 959755be4d7f..4930e8142aa6 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -457,6 +457,39 @@ attribute-sets:
           Number of times driver re-started accepting send
           requests to this queue from the stack.
         type: uint
+  -
+    name: queue-id
+    subset-of: queue
+    attributes:
+      -
+        name: id
+      -
+        name: type
+  -
+    name: dmabuf
+    attributes:
+      -
+        name: ifindex
+        doc: netdev ifindex to bind the dmabuf to.
+        type: u32
+        checks:
+          min: 1
+      -
+        name: queues
+        doc: receive queues to bind the dmabuf to.
+        type: nest
+        nested-attributes: queue-id
+        multi-attr: true
+      -
+        name: fd
+        doc: dmabuf file descriptor to bind.
+        type: u32
+      -
+        name: id
+        doc: id of the dmabuf binding
+        type: u32
+        checks:
+          min: 1
 
 operations:
   list:
@@ -619,6 +652,20 @@ operations:
             - rx-bytes
             - tx-packets
             - tx-bytes
+    -
+      name: bind-rx
+      doc: Bind dmabuf to netdev
+      attribute-set: dmabuf
+      flags: [ admin-perm ]
+      do:
+        request:
+          attributes:
+            - ifindex
+            - fd
+            - queues
+        reply:
+          attributes:
+            - id
 
 mcast-groups:
   list:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 43742ac5b00d..91bf3ecc5f1d 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -173,6 +173,16 @@ enum {
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_DMABUF_IFINDEX = 1,
+	NETDEV_A_DMABUF_QUEUES,
+	NETDEV_A_DMABUF_FD,
+	NETDEV_A_DMABUF_ID,
+
+	__NETDEV_A_DMABUF_MAX,
+	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -186,6 +196,7 @@ enum {
 	NETDEV_CMD_QUEUE_GET,
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 8350a0afa9ec..6b7fe6035067 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -27,6 +27,11 @@ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFIND
 	[NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range),
 };
 
+const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = {
+	[NETDEV_A_QUEUE_ID] = { .type = NLA_U32, },
+	[NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1),
+};
+
 /* NETDEV_CMD_DEV_GET - do */
 static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
 	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
@@ -74,6 +79,13 @@ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE
 	[NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1),
 };
 
+/* NETDEV_CMD_BIND_RX - do */
+static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] = {
+	[NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+	[NETDEV_A_DMABUF_FD] = { .type = NLA_U32, },
+	[NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy),
+};
+
 /* Ops table for netdev */
 static const struct genl_split_ops netdev_nl_ops[] = {
 	{
@@ -151,6 +163,13 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.maxattr	= NETDEV_A_QSTATS_SCOPE,
 		.flags		= GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= NETDEV_CMD_BIND_RX,
+		.doit		= netdev_nl_bind_rx_doit,
+		.policy		= netdev_bind_rx_nl_policy,
+		.maxattr	= NETDEV_A_DMABUF_FD,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group netdev_nl_mcgrps[] = {
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 4db40fd5b4a9..67c34005750c 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -13,6 +13,7 @@
 
 /* Common nested types */
 extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
+extern const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1];
 
 int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
@@ -30,6 +31,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info);
 int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 				struct netlink_callback *cb);
+int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info);
 
 enum {
 	NETDEV_NLGRP_MGMT,
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index a17d7eaeb001..699c34b9b03c 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -723,6 +723,12 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 	return err;
 }
 
+/* Stub */
+int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return 0;
+}
+
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
 				       unsigned long event, void *ptr)
 {
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 43742ac5b00d..91bf3ecc5f1d 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -173,6 +173,16 @@ enum {
 	NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1)
 };
 
+enum {
+	NETDEV_A_DMABUF_IFINDEX = 1,
+	NETDEV_A_DMABUF_QUEUES,
+	NETDEV_A_DMABUF_FD,
+	NETDEV_A_DMABUF_ID,
+
+	__NETDEV_A_DMABUF_MAX,
+	NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1)
+};
+
 enum {
 	NETDEV_CMD_DEV_GET = 1,
 	NETDEV_CMD_DEV_ADD_NTF,
@@ -186,6 +196,7 @@ enum {
 	NETDEV_CMD_QUEUE_GET,
 	NETDEV_CMD_NAPI_GET,
 	NETDEV_CMD_QSTATS_GET,
+	NETDEV_CMD_BIND_RX,
 
 	__NETDEV_CMD_MAX,
 	NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
-- 
cgit v1.3-3-g829e


From 170aafe35cb98e0f3fbacb446ea86389fbce22ea Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:47 +0000
Subject: netdev: support binding dma-buf to netdevice

Add a netdev_dmabuf_binding struct which represents the
dma-buf-to-netdevice binding. The netlink API will bind the dma-buf to
rx queues on the netdevice. On the binding, the dma_buf_attach
& dma_buf_map_attachment will occur. The entries in the sg_table from
mapping will be inserted into a genpool to make it ready
for allocation.

The chunks in the genpool are owned by a dmabuf_chunk_owner struct which
holds the dma-buf offset of the base of the chunk and the dma_addr of
the chunk. Both are needed to use allocations that come from this chunk.

We create a new type that represents an allocation from the genpool:
net_iov. We setup the net_iov allocation size in the
genpool to PAGE_SIZE for simplicity: to match the PAGE_SIZE normally
allocated by the page pool and given to the drivers.

The user can unbind the dmabuf from the netdevice by closing the netlink
socket that established the binding. We do this so that the binding is
automatically unbound even if the userspace process crashes.

The binding and unbinding leaves an indicator in struct netdev_rx_queue
that the given queue is bound, and the binding is actuated by resetting
the rx queue using the queue API.

The netdev_dmabuf_binding struct is refcounted, and releases its
resources only when all the refs are released.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com> # excluding netlink
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-4-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml |   4 +
 include/linux/netdevice.h               |   2 +
 include/net/netdev_rx_queue.h           |   2 +
 include/net/netmem.h                    |   8 +
 include/net/page_pool/types.h           |   6 +
 net/Kconfig                             |   5 +
 net/core/Makefile                       |   1 +
 net/core/dev.c                          |  26 +++
 net/core/devmem.c                       | 274 ++++++++++++++++++++++++++++++++
 net/core/devmem.h                       | 124 +++++++++++++++
 net/core/netdev-genl-gen.c              |   4 +
 net/core/netdev-genl-gen.h              |   4 +
 net/core/netdev-genl.c                  | 128 ++++++++++++++-
 net/ethtool/common.c                    |   8 +
 net/xdp/xsk_buff_pool.c                 |   5 +
 15 files changed, 596 insertions(+), 5 deletions(-)
 create mode 100644 net/core/devmem.c
 create mode 100644 net/core/devmem.h

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 4930e8142aa6..0c747530c275 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -667,6 +667,10 @@ operations:
           attributes:
             - id
 
+kernel-family:
+  headers: [ "linux/list.h"]
+  sock-priv: struct list_head
+
 mcast-groups:
   list:
     -
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2465bdb6037f..e87b5e488325 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3953,6 +3953,8 @@ u8 dev_xdp_prog_count(struct net_device *dev);
 int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 
+u32 dev_get_min_mp_channel_count(const struct net_device *dev);
+
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index e78ca52d67fb..ac34f5fb4f71 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/sysfs.h>
 #include <net/xdp.h>
+#include <net/page_pool/types.h>
 
 /* This structure contains an instance of an RX queue. */
 struct netdev_rx_queue {
@@ -25,6 +26,7 @@ struct netdev_rx_queue {
 	 * Readers and writers must hold RTNL
 	 */
 	struct napi_struct		*napi;
+	struct pp_memory_provider_params mp_params;
 } ____cacheline_aligned_in_smp;
 
 /*
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 46cc9b89ac79..c23e224dd6a0 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -8,6 +8,14 @@
 #ifndef _NET_NETMEM_H
 #define _NET_NETMEM_H
 
+/* net_iov */
+
+struct net_iov {
+	struct dmabuf_genpool_chunk_owner *owner;
+};
+
+/* netmem */
+
 /**
  * typedef netmem_ref - a nonexistent type marking a reference to generic
  * network memory.
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 50569fed7868..4afd6dd56351 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -139,6 +139,10 @@ struct page_pool_stats {
  */
 #define PAGE_POOL_FRAG_GROUP_ALIGN	(4 * sizeof(long))
 
+struct pp_memory_provider_params {
+	void *mp_priv;
+};
+
 struct page_pool {
 	struct page_pool_params_fast p;
 
@@ -197,6 +201,8 @@ struct page_pool {
 	 */
 	struct ptr_ring ring;
 
+	void *mp_priv;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* recycle stats are per-cpu to avoid locking */
 	struct page_pool_recycle_stats __percpu *recycle_stats;
diff --git a/net/Kconfig b/net/Kconfig
index d27d0deac0bf..7574b066d7cd 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -66,6 +66,11 @@ config SKB_DECRYPTED
 config SKB_EXTENSIONS
 	bool
 
+config NET_DEVMEM
+	def_bool y
+	depends on DMA_SHARED_BUFFER
+	depends on GENERIC_ALLOCATOR
+
 menu "Networking options"
 
 source "net/packet/Kconfig"
diff --git a/net/core/Makefile b/net/core/Makefile
index f82232b358a2..c3ebbaf9c81e 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -44,3 +44,4 @@ obj-$(CONFIG_BPF_SYSCALL) += sock_map.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
 obj-$(CONFIG_OF)	+= of_net.o
 obj-$(CONFIG_NET_TEST) += net_test.o
+obj-$(CONFIG_NET_DEVMEM) += devmem.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 8f4dead64284..7818d7f6295e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -161,6 +161,7 @@
 #include <linux/phy_link_topology.h>
 
 #include "dev.h"
+#include "devmem.h"
 #include "net-sysfs.h"
 
 static DEFINE_SPINLOCK(ptype_lock);
@@ -9367,6 +9368,11 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 	if (!dev->netdev_ops->ndo_bpf)
 		return -EOPNOTSUPP;
 
+	if (dev_get_min_mp_channel_count(dev)) {
+		NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider");
+		return -EBUSY;
+	}
+
 	return dev->netdev_ops->ndo_bpf(dev, bpf);
 }
 EXPORT_SYMBOL_GPL(dev_xdp_propagate);
@@ -9399,6 +9405,11 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
 	struct netdev_bpf xdp;
 	int err;
 
+	if (dev_get_min_mp_channel_count(dev)) {
+		NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider");
+		return -EBUSY;
+	}
+
 	memset(&xdp, 0, sizeof(xdp));
 	xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG;
 	xdp.extack = extack;
@@ -9823,6 +9834,20 @@ err_out:
 	return err;
 }
 
+u32 dev_get_min_mp_channel_count(const struct net_device *dev)
+{
+	int i;
+
+	ASSERT_RTNL();
+
+	for (i = dev->real_num_rx_queues - 1; i >= 0; i--)
+		if (dev->_rx[i].mp_params.mp_priv)
+			/* The channel count is the idx plus 1. */
+			return i + 1;
+
+	return 0;
+}
+
 /**
  * dev_index_reserve() - allocate an ifindex in a namespace
  * @net: the applicable net namespace
@@ -11359,6 +11384,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		dev_tcx_uninstall(dev);
 		dev_xdp_uninstall(dev);
 		bpf_dev_bound_netdev_unregister(dev);
+		dev_dmabuf_uninstall(dev);
 
 		netdev_offload_xstats_disable_all(dev);
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
new file mode 100644
index 000000000000..8dd7beb080d2
--- /dev/null
+++ b/net/core/devmem.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *      Devmem TCP
+ *
+ *      Authors:	Mina Almasry <almasrymina@google.com>
+ *			Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+ *			Kaiyuan Zhang <kaiyuanz@google.com
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/genalloc.h>
+#include <linux/mm.h>
+#include <linux/netdevice.h>
+#include <linux/types.h>
+#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+#include <net/page_pool/helpers.h>
+#include <trace/events/page_pool.h>
+
+#include "devmem.h"
+
+/* Device memory support */
+
+/* Protected by rtnl_lock() */
+static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
+
+static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
+					       struct gen_pool_chunk *chunk,
+					       void *not_used)
+{
+	struct dmabuf_genpool_chunk_owner *owner = chunk->owner;
+
+	kvfree(owner->niovs);
+	kfree(owner);
+}
+
+void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+{
+	size_t size, avail;
+
+	gen_pool_for_each_chunk(binding->chunk_pool,
+				net_devmem_dmabuf_free_chunk_owner, NULL);
+
+	size = gen_pool_size(binding->chunk_pool);
+	avail = gen_pool_avail(binding->chunk_pool);
+
+	if (!WARN(size != avail, "can't destroy genpool. size=%zu, avail=%zu",
+		  size, avail))
+		gen_pool_destroy(binding->chunk_pool);
+
+	dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt,
+					  DMA_FROM_DEVICE);
+	dma_buf_detach(binding->dmabuf, binding->attachment);
+	dma_buf_put(binding->dmabuf);
+	xa_destroy(&binding->bound_rxqs);
+	kfree(binding);
+}
+
+void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+	struct netdev_rx_queue *rxq;
+	unsigned long xa_idx;
+	unsigned int rxq_idx;
+
+	if (binding->list.next)
+		list_del(&binding->list);
+
+	xa_for_each(&binding->bound_rxqs, xa_idx, rxq) {
+		WARN_ON(rxq->mp_params.mp_priv != binding);
+
+		rxq->mp_params.mp_priv = NULL;
+
+		rxq_idx = get_netdev_rx_queue_index(rxq);
+
+		WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx));
+	}
+
+	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
+
+	net_devmem_dmabuf_binding_put(binding);
+}
+
+int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
+				    struct net_devmem_dmabuf_binding *binding,
+				    struct netlink_ext_ack *extack)
+{
+	struct netdev_rx_queue *rxq;
+	u32 xa_idx;
+	int err;
+
+	if (rxq_idx >= dev->real_num_rx_queues) {
+		NL_SET_ERR_MSG(extack, "rx queue index out of range");
+		return -ERANGE;
+	}
+
+	rxq = __netif_get_rx_queue(dev, rxq_idx);
+	if (rxq->mp_params.mp_priv) {
+		NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
+		return -EEXIST;
+	}
+
+#ifdef CONFIG_XDP_SOCKETS
+	if (rxq->pool) {
+		NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP");
+		return -EBUSY;
+	}
+#endif
+
+	err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b,
+		       GFP_KERNEL);
+	if (err)
+		return err;
+
+	rxq->mp_params.mp_priv = binding;
+
+	err = netdev_rx_queue_restart(dev, rxq_idx);
+	if (err)
+		goto err_xa_erase;
+
+	return 0;
+
+err_xa_erase:
+	rxq->mp_params.mp_priv = NULL;
+	xa_erase(&binding->bound_rxqs, xa_idx);
+
+	return err;
+}
+
+struct net_devmem_dmabuf_binding *
+net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netlink_ext_ack *extack)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	static u32 id_alloc_next;
+	struct scatterlist *sg;
+	struct dma_buf *dmabuf;
+	unsigned int sg_idx, i;
+	unsigned long virtual;
+	int err;
+
+	dmabuf = dma_buf_get(dmabuf_fd);
+	if (IS_ERR(dmabuf))
+		return ERR_CAST(dmabuf);
+
+	binding = kzalloc_node(sizeof(*binding), GFP_KERNEL,
+			       dev_to_node(&dev->dev));
+	if (!binding) {
+		err = -ENOMEM;
+		goto err_put_dmabuf;
+	}
+
+	binding->dev = dev;
+
+	err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id,
+			      binding, xa_limit_32b, &id_alloc_next,
+			      GFP_KERNEL);
+	if (err < 0)
+		goto err_free_binding;
+
+	xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC);
+
+	refcount_set(&binding->ref, 1);
+
+	binding->dmabuf = dmabuf;
+
+	binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent);
+	if (IS_ERR(binding->attachment)) {
+		err = PTR_ERR(binding->attachment);
+		NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device");
+		goto err_free_id;
+	}
+
+	binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment,
+						       DMA_FROM_DEVICE);
+	if (IS_ERR(binding->sgt)) {
+		err = PTR_ERR(binding->sgt);
+		NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment");
+		goto err_detach;
+	}
+
+	/* For simplicity we expect to make PAGE_SIZE allocations, but the
+	 * binding can be much more flexible than that. We may be able to
+	 * allocate MTU sized chunks here. Leave that for future work...
+	 */
+	binding->chunk_pool =
+		gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev));
+	if (!binding->chunk_pool) {
+		err = -ENOMEM;
+		goto err_unmap;
+	}
+
+	virtual = 0;
+	for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) {
+		dma_addr_t dma_addr = sg_dma_address(sg);
+		struct dmabuf_genpool_chunk_owner *owner;
+		size_t len = sg_dma_len(sg);
+		struct net_iov *niov;
+
+		owner = kzalloc_node(sizeof(*owner), GFP_KERNEL,
+				     dev_to_node(&dev->dev));
+		if (!owner) {
+			err = -ENOMEM;
+			goto err_free_chunks;
+		}
+
+		owner->base_virtual = virtual;
+		owner->base_dma_addr = dma_addr;
+		owner->num_niovs = len / PAGE_SIZE;
+		owner->binding = binding;
+
+		err = gen_pool_add_owner(binding->chunk_pool, dma_addr,
+					 dma_addr, len, dev_to_node(&dev->dev),
+					 owner);
+		if (err) {
+			kfree(owner);
+			err = -EINVAL;
+			goto err_free_chunks;
+		}
+
+		owner->niovs = kvmalloc_array(owner->num_niovs,
+					      sizeof(*owner->niovs),
+					      GFP_KERNEL);
+		if (!owner->niovs) {
+			err = -ENOMEM;
+			goto err_free_chunks;
+		}
+
+		for (i = 0; i < owner->num_niovs; i++) {
+			niov = &owner->niovs[i];
+			niov->owner = owner;
+		}
+
+		virtual += len;
+	}
+
+	return binding;
+
+err_free_chunks:
+	gen_pool_for_each_chunk(binding->chunk_pool,
+				net_devmem_dmabuf_free_chunk_owner, NULL);
+	gen_pool_destroy(binding->chunk_pool);
+err_unmap:
+	dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt,
+					  DMA_FROM_DEVICE);
+err_detach:
+	dma_buf_detach(dmabuf, binding->attachment);
+err_free_id:
+	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
+err_free_binding:
+	kfree(binding);
+err_put_dmabuf:
+	dma_buf_put(dmabuf);
+	return ERR_PTR(err);
+}
+
+void dev_dmabuf_uninstall(struct net_device *dev)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	struct netdev_rx_queue *rxq;
+	unsigned long xa_idx;
+	unsigned int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		binding = dev->_rx[i].mp_params.mp_priv;
+		if (!binding)
+			continue;
+
+		xa_for_each(&binding->bound_rxqs, xa_idx, rxq)
+			if (rxq == &dev->_rx[i]) {
+				xa_erase(&binding->bound_rxqs, xa_idx);
+				break;
+			}
+	}
+}
diff --git a/net/core/devmem.h b/net/core/devmem.h
new file mode 100644
index 000000000000..c50f91d858dd
--- /dev/null
+++ b/net/core/devmem.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Device memory TCP support
+ *
+ * Authors:	Mina Almasry <almasrymina@google.com>
+ *		Willem de Bruijn <willemb@google.com>
+ *		Kaiyuan Zhang <kaiyuanz@google.com>
+ *
+ */
+#ifndef _NET_DEVMEM_H
+#define _NET_DEVMEM_H
+
+struct netlink_ext_ack;
+
+struct net_devmem_dmabuf_binding {
+	struct dma_buf *dmabuf;
+	struct dma_buf_attachment *attachment;
+	struct sg_table *sgt;
+	struct net_device *dev;
+	struct gen_pool *chunk_pool;
+
+	/* The user holds a ref (via the netlink API) for as long as they want
+	 * the binding to remain alive. Each page pool using this binding holds
+	 * a ref to keep the binding alive. Each allocated net_iov holds a
+	 * ref.
+	 *
+	 * The binding undos itself and unmaps the underlying dmabuf once all
+	 * those refs are dropped and the binding is no longer desired or in
+	 * use.
+	 */
+	refcount_t ref;
+
+	/* The list of bindings currently active. Used for netlink to notify us
+	 * of the user dropping the bind.
+	 */
+	struct list_head list;
+
+	/* rxq's this binding is active on. */
+	struct xarray bound_rxqs;
+
+	/* ID of this binding. Globally unique to all bindings currently
+	 * active.
+	 */
+	u32 id;
+};
+
+#if defined(CONFIG_NET_DEVMEM)
+/* Owner of the dma-buf chunks inserted into the gen pool. Each scatterlist
+ * entry from the dmabuf is inserted into the genpool as a chunk, and needs
+ * this owner struct to keep track of some metadata necessary to create
+ * allocations from this chunk.
+ */
+struct dmabuf_genpool_chunk_owner {
+	/* Offset into the dma-buf where this chunk starts.  */
+	unsigned long base_virtual;
+
+	/* dma_addr of the start of the chunk.  */
+	dma_addr_t base_dma_addr;
+
+	/* Array of net_iovs for this chunk. */
+	struct net_iov *niovs;
+	size_t num_niovs;
+
+	struct net_devmem_dmabuf_binding *binding;
+};
+
+void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
+struct net_devmem_dmabuf_binding *
+net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netlink_ext_ack *extack);
+void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
+int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
+				    struct net_devmem_dmabuf_binding *binding,
+				    struct netlink_ext_ack *extack);
+void dev_dmabuf_uninstall(struct net_device *dev);
+
+static inline void
+net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
+{
+	refcount_inc(&binding->ref);
+}
+
+static inline void
+net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding)
+{
+	if (!refcount_dec_and_test(&binding->ref))
+		return;
+
+	__net_devmem_dmabuf_binding_free(binding);
+}
+
+#else
+static inline void
+__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
+{
+}
+
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+		       struct netlink_ext_ack *extack)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void
+net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+}
+
+static inline int
+net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
+				struct net_devmem_dmabuf_binding *binding,
+				struct netlink_ext_ack *extack)
+
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void dev_dmabuf_uninstall(struct net_device *dev)
+{
+}
+#endif
+
+#endif /* _NET_DEVMEM_H */
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 6b7fe6035067..b28424ae06d5 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -9,6 +9,7 @@
 #include "netdev-genl-gen.h"
 
 #include <uapi/linux/netdev.h>
+#include <linux/list.h>
 
 /* Integer value ranges */
 static const struct netlink_range_validation netdev_a_page_pool_id_range = {
@@ -187,4 +188,7 @@ struct genl_family netdev_nl_family __ro_after_init = {
 	.n_split_ops	= ARRAY_SIZE(netdev_nl_ops),
 	.mcgrps		= netdev_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(netdev_nl_mcgrps),
+	.sock_priv_size	= sizeof(struct list_head),
+	.sock_priv_init	= (void *)netdev_nl_sock_priv_init,
+	.sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy,
 };
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index 67c34005750c..8cda334fd042 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -10,6 +10,7 @@
 #include <net/genetlink.h>
 
 #include <uapi/linux/netdev.h>
+#include <linux/list.h>
 
 /* Common nested types */
 extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
@@ -40,4 +41,7 @@ enum {
 
 extern struct genl_family netdev_nl_family;
 
+void netdev_nl_sock_priv_init(struct list_head *priv);
+void netdev_nl_sock_priv_destroy(struct list_head *priv);
+
 #endif /* _LINUX_NETDEV_GEN_H */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 699c34b9b03c..9153a8ab0cf8 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -3,16 +3,17 @@
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
 #include <linux/rtnetlink.h>
+#include <net/busy_poll.h>
 #include <net/net_namespace.h>
+#include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
 #include <net/sock.h>
 #include <net/xdp.h>
 #include <net/xdp_sock.h>
-#include <net/netdev_rx_queue.h>
-#include <net/netdev_queues.h>
-#include <net/busy_poll.h>
 
-#include "netdev-genl-gen.h"
 #include "dev.h"
+#include "devmem.h"
+#include "netdev-genl-gen.h"
 
 struct netdev_nl_dump_ctx {
 	unsigned long	ifindex;
@@ -723,10 +724,127 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb,
 	return err;
 }
 
-/* Stub */
 int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 {
+	struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)];
+	struct net_devmem_dmabuf_binding *binding;
+	struct list_head *sock_binding_list;
+	u32 ifindex, dmabuf_fd, rxq_idx;
+	struct net_device *netdev;
+	struct sk_buff *rsp;
+	struct nlattr *attr;
+	int rem, err = 0;
+	void *hdr;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD) ||
+	    GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES))
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+	dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);
+
+	sock_binding_list = genl_sk_priv_get(&netdev_nl_family,
+					     NETLINK_CB(skb).sk);
+	if (IS_ERR(sock_binding_list))
+		return PTR_ERR(sock_binding_list);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(rsp, info);
+	if (!hdr) {
+		err = -EMSGSIZE;
+		goto err_genlmsg_free;
+	}
+
+	rtnl_lock();
+
+	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+	if (!netdev || !netif_device_present(netdev)) {
+		err = -ENODEV;
+		goto err_unlock;
+	}
+
+	if (dev_xdp_prog_count(netdev)) {
+		NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached");
+		err = -EEXIST;
+		goto err_unlock;
+	}
+
+	binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack);
+	if (IS_ERR(binding)) {
+		err = PTR_ERR(binding);
+		goto err_unlock;
+	}
+
+	nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES,
+			       genlmsg_data(info->genlhdr),
+			       genlmsg_len(info->genlhdr), rem) {
+		err = nla_parse_nested(
+			tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr,
+			netdev_queue_id_nl_policy, info->extack);
+		if (err < 0)
+			goto err_unbind;
+
+		if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) ||
+		    NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) {
+			err = -EINVAL;
+			goto err_unbind;
+		}
+
+		if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) {
+			NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]);
+			err = -EINVAL;
+			goto err_unbind;
+		}
+
+		rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]);
+
+		err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding,
+						      info->extack);
+		if (err)
+			goto err_unbind;
+	}
+
+	list_add(&binding->list, sock_binding_list);
+
+	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
+	genlmsg_end(rsp, hdr);
+
+	err = genlmsg_reply(rsp, info);
+	if (err)
+		goto err_unbind;
+
+	rtnl_unlock();
+
 	return 0;
+
+err_unbind:
+	net_devmem_unbind_dmabuf(binding);
+err_unlock:
+	rtnl_unlock();
+err_genlmsg_free:
+	nlmsg_free(rsp);
+	return err;
+}
+
+void netdev_nl_sock_priv_init(struct list_head *priv)
+{
+	INIT_LIST_HEAD(priv);
+}
+
+void netdev_nl_sock_priv_destroy(struct list_head *priv)
+{
+	struct net_devmem_dmabuf_binding *binding;
+	struct net_devmem_dmabuf_binding *temp;
+
+	list_for_each_entry_safe(binding, temp, priv, list) {
+		rtnl_lock();
+		net_devmem_unbind_dmabuf(binding);
+		rtnl_unlock();
+	}
 }
 
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 6c245e59bbc1..dd345efa114b 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -655,6 +655,7 @@ int ethtool_check_max_channel(struct net_device *dev,
 {
 	u64 max_rxnfc_in_use;
 	u32 max_rxfh_in_use;
+	int max_mp_in_use;
 
 	/* ensure the new Rx count fits within the configured Rx flow
 	 * indirection table/rxnfc settings
@@ -673,6 +674,13 @@ int ethtool_check_max_channel(struct net_device *dev,
 		return -EINVAL;
 	}
 
+	max_mp_in_use = dev_get_min_mp_channel_count(dev);
+	if (channels.combined_count + channels.rx_count <= max_mp_in_use) {
+		if (info)
+			GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing memory provider setting (%d)", max_mp_in_use);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index c0e0204b9630..6b2756f95629 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -211,6 +211,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 		goto err_unreg_pool;
 	}
 
+	if (dev_get_min_mp_channel_count(netdev)) {
+		err = -EBUSY;
+		goto err_unreg_pool;
+	}
+
 	bpf.command = XDP_SETUP_XSK_POOL;
 	bpf.xsk.pool = pool;
 	bpf.xsk.queue_id = queue_id;
-- 
cgit v1.3-3-g829e


From 28c5c74eeaa0a2aad8b9cd9ede22a4c623f2a7fc Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:48 +0000
Subject: netdev: netdevice devmem allocator

Implement netdev devmem allocator. The allocator takes a given struct
netdev_dmabuf_binding as input and allocates net_iov from that
binding.

The allocation simply delegates to the binding's genpool for the
allocation logic and wraps the returned memory region in a net_iov
struct.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-5-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/devmem.c | 41 +++++++++++++++++++++++++++++++++++++++++
 net/core/devmem.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/net/core/devmem.c b/net/core/devmem.c
index 8dd7beb080d2..9beb03763dc9 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -34,6 +34,14 @@ static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
 	kfree(owner);
 }
 
+static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov)
+{
+	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+
+	return owner->base_dma_addr +
+	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
+}
+
 void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 {
 	size_t size, avail;
@@ -56,6 +64,39 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 	kfree(binding);
 }
 
+struct net_iov *
+net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+	struct dmabuf_genpool_chunk_owner *owner;
+	unsigned long dma_addr;
+	struct net_iov *niov;
+	ssize_t offset;
+	ssize_t index;
+
+	dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE,
+					(void **)&owner);
+	if (!dma_addr)
+		return NULL;
+
+	offset = dma_addr - owner->base_dma_addr;
+	index = offset / PAGE_SIZE;
+	niov = &owner->niovs[index];
+
+	return niov;
+}
+
+void net_devmem_free_dmabuf(struct net_iov *niov)
+{
+	struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov);
+	unsigned long dma_addr = net_devmem_get_dma_addr(niov);
+
+	if (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr,
+				       PAGE_SIZE)))
+		return;
+
+	gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE);
+}
+
 void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 {
 	struct netdev_rx_queue *rxq;
diff --git a/net/core/devmem.h b/net/core/devmem.h
index c50f91d858dd..b1db4877cff9 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -74,6 +74,23 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 				    struct netlink_ext_ack *extack);
 void dev_dmabuf_uninstall(struct net_device *dev);
 
+static inline struct dmabuf_genpool_chunk_owner *
+net_iov_owner(const struct net_iov *niov)
+{
+	return niov->owner;
+}
+
+static inline unsigned int net_iov_idx(const struct net_iov *niov)
+{
+	return niov - net_iov_owner(niov)->niovs;
+}
+
+static inline struct net_devmem_dmabuf_binding *
+net_iov_binding(const struct net_iov *niov)
+{
+	return net_iov_owner(niov)->binding;
+}
+
 static inline void
 net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
 {
@@ -89,7 +106,13 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding)
 	__net_devmem_dmabuf_binding_free(binding);
 }
 
+struct net_iov *
+net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
+void net_devmem_free_dmabuf(struct net_iov *ppiov);
+
 #else
+struct net_devmem_dmabuf_binding;
+
 static inline void
 __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 {
@@ -119,6 +142,17 @@ net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 static inline void dev_dmabuf_uninstall(struct net_device *dev)
 {
 }
+
+static inline struct net_iov *
+net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+	return NULL;
+}
+
+static inline void net_devmem_free_dmabuf(struct net_iov *ppiov)
+{
+}
+
 #endif
 
 #endif /* _NET_DEVMEM_H */
-- 
cgit v1.3-3-g829e


From 8ab79ed50cf10f338465c296012500de1081646f Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:49 +0000
Subject: page_pool: devmem support

Convert netmem to be a union of struct page and struct netmem. Overload
the LSB of struct netmem* to indicate that it's a net_iov, otherwise
it's a page.

Currently these entries in struct page are rented by the page_pool and
used exclusively by the net stack:

struct {
	unsigned long pp_magic;
	struct page_pool *pp;
	unsigned long _pp_mapping_pad;
	unsigned long dma_addr;
	atomic_long_t pp_ref_count;
};

Mirror these (and only these) entries into struct net_iov and implement
netmem helpers that can access these common fields regardless of
whether the underlying type is page or net_iov.

Implement checks for net_iov in netmem helpers which delegate to mm
APIs, to ensure net_iov are never passed to the mm stack.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-6-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netmem.h             | 124 ++++++++++++++++++++++++++++++++++++---
 include/net/page_pool/helpers.h  |  39 +++---------
 include/trace/events/page_pool.h |  12 ++--
 net/core/devmem.c                |   7 +++
 net/core/netmem_priv.h           |  31 ++++++++++
 net/core/page_pool.c             |  25 ++++----
 net/core/page_pool_priv.h        |  26 ++++++++
 net/core/skbuff.c                |  23 ++++----
 8 files changed, 218 insertions(+), 69 deletions(-)
 create mode 100644 net/core/netmem_priv.h

diff --git a/include/net/netmem.h b/include/net/netmem.h
index c23e224dd6a0..8a6e20be4b9d 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -8,12 +8,52 @@
 #ifndef _NET_NETMEM_H
 #define _NET_NETMEM_H
 
+#include <linux/mm.h>
+#include <net/net_debug.h>
+
 /* net_iov */
 
+DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
+
+/*  We overload the LSB of the struct page pointer to indicate whether it's
+ *  a page or net_iov.
+ */
+#define NET_IOV 0x01UL
+
 struct net_iov {
+	unsigned long __unused_padding;
+	unsigned long pp_magic;
+	struct page_pool *pp;
 	struct dmabuf_genpool_chunk_owner *owner;
+	unsigned long dma_addr;
+	atomic_long_t pp_ref_count;
 };
 
+/* These fields in struct page are used by the page_pool and net stack:
+ *
+ *        struct {
+ *                unsigned long pp_magic;
+ *                struct page_pool *pp;
+ *                unsigned long _pp_mapping_pad;
+ *                unsigned long dma_addr;
+ *                atomic_long_t pp_ref_count;
+ *        };
+ *
+ * We mirror the page_pool fields here so the page_pool can access these fields
+ * without worrying whether the underlying fields belong to a page or net_iov.
+ *
+ * The non-net stack fields of struct page are private to the mm stack and must
+ * never be mirrored to net_iov.
+ */
+#define NET_IOV_ASSERT_OFFSET(pg, iov)             \
+	static_assert(offsetof(struct page, pg) == \
+		      offsetof(struct net_iov, iov))
+NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic);
+NET_IOV_ASSERT_OFFSET(pp, pp);
+NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
+NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
+#undef NET_IOV_ASSERT_OFFSET
+
 /* netmem */
 
 /**
@@ -27,20 +67,37 @@ struct net_iov {
  */
 typedef unsigned long __bitwise netmem_ref;
 
+static inline bool netmem_is_net_iov(const netmem_ref netmem)
+{
+	return (__force unsigned long)netmem & NET_IOV;
+}
+
 /* This conversion fails (returns NULL) if the netmem_ref is not struct page
  * backed.
- *
- * Currently struct page is the only possible netmem, and this helper never
- * fails.
  */
 static inline struct page *netmem_to_page(netmem_ref netmem)
 {
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return NULL;
+
 	return (__force struct page *)netmem;
 }
 
-/* Converting from page to netmem is always safe, because a page can always be
- * a netmem.
- */
+static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem)
+{
+	if (netmem_is_net_iov(netmem))
+		return (struct net_iov *)((__force unsigned long)netmem &
+					  ~NET_IOV);
+
+	DEBUG_NET_WARN_ON_ONCE(true);
+	return NULL;
+}
+
+static inline netmem_ref net_iov_to_netmem(struct net_iov *niov)
+{
+	return (__force netmem_ref)((unsigned long)niov | NET_IOV);
+}
+
 static inline netmem_ref page_to_netmem(struct page *page)
 {
 	return (__force netmem_ref)page;
@@ -48,17 +105,70 @@ static inline netmem_ref page_to_netmem(struct page *page)
 
 static inline int netmem_ref_count(netmem_ref netmem)
 {
+	/* The non-pp refcount of net_iov is always 1. On net_iov, we only
+	 * support pp refcounting which uses the pp_ref_count field.
+	 */
+	if (netmem_is_net_iov(netmem))
+		return 1;
+
 	return page_ref_count(netmem_to_page(netmem));
 }
 
-static inline unsigned long netmem_to_pfn(netmem_ref netmem)
+static inline unsigned long netmem_pfn_trace(netmem_ref netmem)
 {
+	if (netmem_is_net_iov(netmem))
+		return 0;
+
 	return page_to_pfn(netmem_to_page(netmem));
 }
 
+static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem)
+{
+	return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV);
+}
+
+static inline struct page_pool *netmem_get_pp(netmem_ref netmem)
+{
+	return __netmem_clear_lsb(netmem)->pp;
+}
+
+static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem)
+{
+	return &__netmem_clear_lsb(netmem)->pp_ref_count;
+}
+
+static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid)
+{
+	/* NUMA node preference only makes sense if we're allocating
+	 * system memory. Memory providers (which give us net_iovs)
+	 * choose for us.
+	 */
+	if (netmem_is_net_iov(netmem))
+		return true;
+
+	return page_to_nid(netmem_to_page(netmem)) == pref_nid;
+}
+
 static inline netmem_ref netmem_compound_head(netmem_ref netmem)
 {
+	/* niov are never compounded */
+	if (netmem_is_net_iov(netmem))
+		return netmem;
+
 	return page_to_netmem(compound_head(netmem_to_page(netmem)));
 }
 
+static inline void *netmem_address(netmem_ref netmem)
+{
+	if (netmem_is_net_iov(netmem))
+		return NULL;
+
+	return page_address(netmem_to_page(netmem));
+}
+
+static inline unsigned long netmem_get_dma_addr(netmem_ref netmem)
+{
+	return __netmem_clear_lsb(netmem)->dma_addr;
+}
+
 #endif /* _NET_NETMEM_H */
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 2b43a893c619..793e6fd78bc5 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -216,7 +216,7 @@ page_pool_get_dma_dir(const struct page_pool *pool)
 
 static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr)
 {
-	atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr);
+	atomic_long_set(netmem_get_pp_ref_count_ref(netmem), nr);
 }
 
 /**
@@ -244,7 +244,7 @@ static inline void page_pool_fragment_page(struct page *page, long nr)
 
 static inline long page_pool_unref_netmem(netmem_ref netmem, long nr)
 {
-	struct page *page = netmem_to_page(netmem);
+	atomic_long_t *pp_ref_count = netmem_get_pp_ref_count_ref(netmem);
 	long ret;
 
 	/* If nr == pp_ref_count then we have cleared all remaining
@@ -261,19 +261,19 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr)
 	 * initially, and only overwrite it when the page is partitioned into
 	 * more than one piece.
 	 */
-	if (atomic_long_read(&page->pp_ref_count) == nr) {
+	if (atomic_long_read(pp_ref_count) == nr) {
 		/* As we have ensured nr is always one for constant case using
 		 * the BUILD_BUG_ON(), only need to handle the non-constant case
 		 * here for pp_ref_count draining, which is a rare case.
 		 */
 		BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1);
 		if (!__builtin_constant_p(nr))
-			atomic_long_set(&page->pp_ref_count, 1);
+			atomic_long_set(pp_ref_count, 1);
 
 		return 0;
 	}
 
-	ret = atomic_long_sub_return(nr, &page->pp_ref_count);
+	ret = atomic_long_sub_return(nr, pp_ref_count);
 	WARN_ON(ret < 0);
 
 	/* We are the last user here too, reset pp_ref_count back to 1 to
@@ -282,7 +282,7 @@ static inline long page_pool_unref_netmem(netmem_ref netmem, long nr)
 	 * page_pool_unref_page() currently.
 	 */
 	if (unlikely(!ret))
-		atomic_long_set(&page->pp_ref_count, 1);
+		atomic_long_set(pp_ref_count, 1);
 
 	return ret;
 }
@@ -401,9 +401,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va,
 
 static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem)
 {
-	struct page *page = netmem_to_page(netmem);
-
-	dma_addr_t ret = page->dma_addr;
+	dma_addr_t ret = netmem_get_dma_addr(netmem);
 
 	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
 		ret <<= PAGE_SHIFT;
@@ -423,24 +421,6 @@ static inline dma_addr_t page_pool_get_dma_addr(const struct page *page)
 	return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page));
 }
 
-static inline bool page_pool_set_dma_addr_netmem(netmem_ref netmem,
-						 dma_addr_t addr)
-{
-	struct page *page = netmem_to_page(netmem);
-
-	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) {
-		page->dma_addr = addr >> PAGE_SHIFT;
-
-		/* We assume page alignment to shave off bottom bits,
-		 * if this "compression" doesn't work we need to drop.
-		 */
-		return addr != (dma_addr_t)page->dma_addr << PAGE_SHIFT;
-	}
-
-	page->dma_addr = addr;
-	return false;
-}
-
 /**
  * page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW
  * @pool: &page_pool the @page belongs to
@@ -463,11 +443,6 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool,
 				      page_pool_get_dma_dir(pool));
 }
 
-static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
-{
-	return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr);
-}
-
 static inline bool page_pool_put(struct page_pool *pool)
 {
 	return refcount_dec_and_test(&pool->user_cnt);
diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h
index 543e54e432a1..31825ed30032 100644
--- a/include/trace/events/page_pool.h
+++ b/include/trace/events/page_pool.h
@@ -57,12 +57,12 @@ TRACE_EVENT(page_pool_state_release,
 		__entry->pool		= pool;
 		__entry->netmem		= (__force unsigned long)netmem;
 		__entry->release	= release;
-		__entry->pfn		= netmem_to_pfn(netmem);
+		__entry->pfn		= netmem_pfn_trace(netmem);
 	),
 
-	TP_printk("page_pool=%p netmem=%p pfn=0x%lx release=%u",
+	TP_printk("page_pool=%p netmem=%p is_net_iov=%lu pfn=0x%lx release=%u",
 		  __entry->pool, (void *)__entry->netmem,
-		  __entry->pfn, __entry->release)
+		  __entry->netmem & NET_IOV, __entry->pfn, __entry->release)
 );
 
 TRACE_EVENT(page_pool_state_hold,
@@ -83,12 +83,12 @@ TRACE_EVENT(page_pool_state_hold,
 		__entry->pool	= pool;
 		__entry->netmem	= (__force unsigned long)netmem;
 		__entry->hold	= hold;
-		__entry->pfn	= netmem_to_pfn(netmem);
+		__entry->pfn	= netmem_pfn_trace(netmem);
 	),
 
-	TP_printk("page_pool=%p netmem=%p pfn=0x%lx hold=%u",
+	TP_printk("page_pool=%p netmem=%p is_net_iov=%lu, pfn=0x%lx hold=%u",
 		  __entry->pool, (void *)__entry->netmem,
-		  __entry->pfn, __entry->hold)
+		  __entry->netmem & NET_IOV, __entry->pfn, __entry->hold)
 );
 
 TRACE_EVENT(page_pool_update_nid,
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 9beb03763dc9..7efeb602cf45 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -18,6 +18,7 @@
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
+#include "page_pool_priv.h"
 
 /* Device memory support */
 
@@ -82,6 +83,10 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 	index = offset / PAGE_SIZE;
 	niov = &owner->niovs[index];
 
+	niov->pp_magic = 0;
+	niov->pp = NULL;
+	atomic_long_set(&niov->pp_ref_count, 0);
+
 	return niov;
 }
 
@@ -269,6 +274,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 		for (i = 0; i < owner->num_niovs; i++) {
 			niov = &owner->niovs[i];
 			niov->owner = owner;
+			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
+						      net_devmem_get_dma_addr(niov));
 		}
 
 		virtual += len;
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
new file mode 100644
index 000000000000..7eadb8393e00
--- /dev/null
+++ b/net/core/netmem_priv.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __NETMEM_PRIV_H
+#define __NETMEM_PRIV_H
+
+static inline unsigned long netmem_get_pp_magic(netmem_ref netmem)
+{
+	return __netmem_clear_lsb(netmem)->pp_magic;
+}
+
+static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
+{
+	__netmem_clear_lsb(netmem)->pp_magic |= pp_magic;
+}
+
+static inline void netmem_clear_pp_magic(netmem_ref netmem)
+{
+	__netmem_clear_lsb(netmem)->pp_magic = 0;
+}
+
+static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)
+{
+	__netmem_clear_lsb(netmem)->pp = pool;
+}
+
+static inline void netmem_set_dma_addr(netmem_ref netmem,
+				       unsigned long dma_addr)
+{
+	__netmem_clear_lsb(netmem)->dma_addr = dma_addr;
+}
+#endif
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 2abe6e919224..52659db2d765 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -24,8 +24,11 @@
 
 #include <trace/events/page_pool.h>
 
+#include "netmem_priv.h"
 #include "page_pool_priv.h"
 
+DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers);
+
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
@@ -358,7 +361,7 @@ static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool)
 		if (unlikely(!netmem))
 			break;
 
-		if (likely(page_to_nid(netmem_to_page(netmem)) == pref_nid)) {
+		if (likely(netmem_is_pref_nid(netmem, pref_nid))) {
 			pool->alloc.cache[pool->alloc.count++] = netmem;
 		} else {
 			/* NUMA mismatch;
@@ -454,10 +457,8 @@ unmap_failed:
 
 static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 {
-	struct page *page = netmem_to_page(netmem);
-
-	page->pp = pool;
-	page->pp_magic |= PP_SIGNATURE;
+	netmem_set_pp(netmem, pool);
+	netmem_or_pp_magic(netmem, PP_SIGNATURE);
 
 	/* Ensuring all pages have been split into one fragment initially:
 	 * page_pool_set_pp_info() is only called once for every page when it
@@ -472,10 +473,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 
 static void page_pool_clear_pp_info(netmem_ref netmem)
 {
-	struct page *page = netmem_to_page(netmem);
-
-	page->pp_magic = 0;
-	page->pp = NULL;
+	netmem_clear_pp_magic(netmem);
+	netmem_set_pp(netmem, NULL);
 }
 
 static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
@@ -692,8 +691,9 @@ static bool page_pool_recycle_in_cache(netmem_ref netmem,
 
 static bool __page_pool_page_can_be_recycled(netmem_ref netmem)
 {
-	return page_ref_count(netmem_to_page(netmem)) == 1 &&
-	       !page_is_pfmemalloc(netmem_to_page(netmem));
+	return netmem_is_net_iov(netmem) ||
+	       (page_ref_count(netmem_to_page(netmem)) == 1 &&
+		!page_is_pfmemalloc(netmem_to_page(netmem)));
 }
 
 /* If the page refcnt == 1, this will try to recycle the page.
@@ -728,6 +728,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem,
 		/* Page found as candidate for recycling */
 		return netmem;
 	}
+
 	/* Fallback/non-XDP mode: API user have elevated refcnt.
 	 *
 	 * Many drivers split up the page into fragments, and some
@@ -949,7 +950,7 @@ static void page_pool_empty_ring(struct page_pool *pool)
 	/* Empty recycle ring */
 	while ((netmem = (__force netmem_ref)ptr_ring_consume_bh(&pool->ring))) {
 		/* Verify the refcnt invariant of cached pages */
-		if (!(page_ref_count(netmem_to_page(netmem)) == 1))
+		if (!(netmem_ref_count(netmem) == 1))
 			pr_crit("%s() page_pool refcnt %d violation\n",
 				__func__, netmem_ref_count(netmem));
 
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
index 90665d40f1eb..d602c1e728c2 100644
--- a/net/core/page_pool_priv.h
+++ b/net/core/page_pool_priv.h
@@ -3,10 +3,36 @@
 #ifndef __PAGE_POOL_PRIV_H
 #define __PAGE_POOL_PRIV_H
 
+#include <net/page_pool/helpers.h>
+
+#include "netmem_priv.h"
+
 s32 page_pool_inflight(const struct page_pool *pool, bool strict);
 
 int page_pool_list(struct page_pool *pool);
 void page_pool_detached(struct page_pool *pool);
 void page_pool_unlist(struct page_pool *pool);
 
+static inline bool
+page_pool_set_dma_addr_netmem(netmem_ref netmem, dma_addr_t addr)
+{
+	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) {
+		netmem_set_dma_addr(netmem, addr >> PAGE_SHIFT);
+
+		/* We assume page alignment to shave off bottom bits,
+		 * if this "compression" doesn't work we need to drop.
+		 */
+		return addr != (dma_addr_t)netmem_get_dma_addr(netmem)
+				       << PAGE_SHIFT;
+	}
+
+	netmem_set_dma_addr(netmem, addr);
+	return false;
+}
+
+static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+{
+	return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr);
+}
+
 #endif
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 038a059b5924..8abcc28bb189 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -88,6 +88,7 @@
 #include <linux/textsearch.h>
 
 #include "dev.h"
+#include "netmem_priv.h"
 #include "sock_destructor.h"
 
 #ifdef CONFIG_SKB_EXTENSIONS
@@ -920,9 +921,9 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
-static bool is_pp_page(struct page *page)
+static bool is_pp_netmem(netmem_ref netmem)
 {
-	return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
+	return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
 }
 
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
@@ -1020,9 +1021,7 @@ EXPORT_SYMBOL(skb_cow_data_for_xdp);
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 bool napi_pp_put_page(netmem_ref netmem)
 {
-	struct page *page = netmem_to_page(netmem);
-
-	page = compound_head(page);
+	netmem = netmem_compound_head(netmem);
 
 	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
 	 * in order to preserve any existing bits, such as bit 0 for the
@@ -1031,10 +1030,10 @@ bool napi_pp_put_page(netmem_ref netmem)
 	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
 	 * to avoid recycling the pfmemalloc page.
 	 */
-	if (unlikely(!is_pp_page(page)))
+	if (unlikely(!is_pp_netmem(netmem)))
 		return false;
 
-	page_pool_put_full_netmem(page->pp, page_to_netmem(page), false);
+	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
 
 	return true;
 }
@@ -1061,7 +1060,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data)
 static int skb_pp_frag_ref(struct sk_buff *skb)
 {
 	struct skb_shared_info *shinfo;
-	struct page *head_page;
+	netmem_ref head_netmem;
 	int i;
 
 	if (!skb->pp_recycle)
@@ -1070,11 +1069,11 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 	shinfo = skb_shinfo(skb);
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
-		head_page = compound_head(skb_frag_page(&shinfo->frags[i]));
-		if (likely(is_pp_page(head_page)))
-			page_pool_ref_page(head_page);
+		head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
+		if (likely(is_pp_netmem(head_netmem)))
+			page_pool_ref_netmem(head_netmem);
 		else
-			page_ref_inc(head_page);
+			page_ref_inc(netmem_to_page(head_netmem));
 	}
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 0f921404689398943257793f7240db239a23b609 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:50 +0000
Subject: memory-provider: dmabuf devmem memory provider

Implement a memory provider that allocates dmabuf devmem in the form of
net_iov.

The provider receives a reference to the struct netdev_dmabuf_binding
via the pool->mp_priv pointer. The driver needs to set this pointer for
the provider in the net_iov.

The provider obtains a reference on the netdev_dmabuf_binding which
guarantees the binding and the underlying mapping remains alive until
the provider is destroyed.

Usage of PP_FLAG_DMA_MAP is required for this memory provide such that
the page_pool can provide the driver with the dma-addrs of the devmem.

Support for PP_FLAG_DMA_SYNC_DEV is omitted for simplicity & p.order !=
0.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-7-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/types.h |  17 ++++++-
 net/core/devmem.c             |  67 +++++++++++++++++++++++++++
 net/core/mp_dmabuf_devmem.h   |  44 ++++++++++++++++++
 net/core/netdev_rx_queue.c    |   7 +++
 net/core/page_pool.c          | 102 +++++++++++++++++++++++++++++++-----------
 net/core/page_pool_priv.h     |  20 +++++++++
 net/core/page_pool_user.c     |  27 ++++++++++-
 7 files changed, 255 insertions(+), 29 deletions(-)
 create mode 100644 net/core/mp_dmabuf_devmem.h

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 4afd6dd56351..c022c410abe3 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -20,8 +20,18 @@
 					* device driver responsibility
 					*/
 #define PP_FLAG_SYSTEM_POOL	BIT(2) /* Global system page_pool */
+
+/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting
+ * this must be able to support unreadable netmem, where netmem_address() would
+ * return NULL. This flag should not be set for header page_pools.
+ *
+ * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set
+ * page_pool_params.slow.queue_idx.
+ */
+#define PP_FLAG_ALLOW_UNREADABLE_NETMEM BIT(3)
+
 #define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \
-				 PP_FLAG_SYSTEM_POOL)
+				 PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM)
 
 /*
  * Fast allocation side cache array/stack
@@ -57,7 +67,9 @@ struct pp_alloc_cache {
  * @offset:	DMA sync address offset for PP_FLAG_DMA_SYNC_DEV
  * @slow:	params with slowpath access only (initialization and Netlink)
  * @netdev:	netdev this pool will serve (leave as NULL if none or multiple)
- * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL
+ * @queue_idx:	queue idx this page_pool is being created for.
+ * @flags:	PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL,
+ *		PP_FLAG_ALLOW_UNREADABLE_NETMEM.
  */
 struct page_pool_params {
 	struct_group_tagged(page_pool_params_fast, fast,
@@ -72,6 +84,7 @@ struct page_pool_params {
 	);
 	struct_group_tagged(page_pool_params_slow, slow,
 		struct net_device *netdev;
+		unsigned int queue_idx;
 		unsigned int	flags;
 /* private: used by test code only */
 		void (*init_callback)(netmem_ref netmem, void *arg);
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 7efeb602cf45..11b91c12ee11 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -18,6 +18,7 @@
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
+#include "mp_dmabuf_devmem.h"
 #include "page_pool_priv.h"
 
 /* Device memory support */
@@ -320,3 +321,69 @@ void dev_dmabuf_uninstall(struct net_device *dev)
 			}
 	}
 }
+
+/*** "Dmabuf devmem memory provider" ***/
+
+int mp_dmabuf_devmem_init(struct page_pool *pool)
+{
+	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
+
+	if (!binding)
+		return -EINVAL;
+
+	if (!pool->dma_map)
+		return -EOPNOTSUPP;
+
+	if (pool->dma_sync)
+		return -EOPNOTSUPP;
+
+	if (pool->p.order != 0)
+		return -E2BIG;
+
+	net_devmem_dmabuf_binding_get(binding);
+	return 0;
+}
+
+netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp)
+{
+	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
+	struct net_iov *niov;
+	netmem_ref netmem;
+
+	niov = net_devmem_alloc_dmabuf(binding);
+	if (!niov)
+		return 0;
+
+	netmem = net_iov_to_netmem(niov);
+
+	page_pool_set_pp_info(pool, netmem);
+
+	pool->pages_state_hold_cnt++;
+	trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt);
+	return netmem;
+}
+
+void mp_dmabuf_devmem_destroy(struct page_pool *pool)
+{
+	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
+
+	net_devmem_dmabuf_binding_put(binding);
+}
+
+bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem)
+{
+	long refcount = atomic_long_read(netmem_get_pp_ref_count_ref(netmem));
+
+	if (WARN_ON_ONCE(!netmem_is_net_iov(netmem)))
+		return false;
+
+	if (WARN_ON_ONCE(refcount != 1))
+		return false;
+
+	page_pool_clear_pp_info(netmem);
+
+	net_devmem_free_dmabuf(netmem_to_net_iov(netmem));
+
+	/* We don't want the page pool put_page()ing our net_iovs. */
+	return false;
+}
diff --git a/net/core/mp_dmabuf_devmem.h b/net/core/mp_dmabuf_devmem.h
new file mode 100644
index 000000000000..67cd0dd7319c
--- /dev/null
+++ b/net/core/mp_dmabuf_devmem.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Dmabuf device memory provider.
+ *
+ * Authors:	Mina Almasry <almasrymina@google.com>
+ *
+ */
+#ifndef _NET_MP_DMABUF_DEVMEM_H
+#define _NET_MP_DMABUF_DEVMEM_H
+
+#include <net/netmem.h>
+
+#if defined(CONFIG_NET_DEVMEM)
+int mp_dmabuf_devmem_init(struct page_pool *pool);
+
+netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp);
+
+void mp_dmabuf_devmem_destroy(struct page_pool *pool);
+
+bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem);
+#else
+static inline int mp_dmabuf_devmem_init(struct page_pool *pool)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline netmem_ref
+mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp)
+{
+	return 0;
+}
+
+static inline void mp_dmabuf_devmem_destroy(struct page_pool *pool)
+{
+}
+
+static inline bool
+mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem)
+{
+	return false;
+}
+#endif
+
+#endif /* _NET_MP_DMABUF_DEVMEM_H */
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index da11720a5983..e217a5838c87 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -4,8 +4,11 @@
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 
+#include "page_pool_priv.h"
+
 int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 {
+	struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, rxq_idx);
 	void *new_mem, *old_mem;
 	int err;
 
@@ -31,6 +34,10 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	if (err)
 		goto err_free_old_mem;
 
+	err = page_pool_check_memory_provider(dev, rxq);
+	if (err)
+		goto err_free_new_queue_mem;
+
 	err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx);
 	if (err)
 		goto err_free_new_queue_mem;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 52659db2d765..a813d30d2135 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 
+#include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
 #include <net/xdp.h>
 
@@ -24,6 +25,7 @@
 
 #include <trace/events/page_pool.h>
 
+#include "mp_dmabuf_devmem.h"
 #include "netmem_priv.h"
 #include "page_pool_priv.h"
 
@@ -190,6 +192,8 @@ static int page_pool_init(struct page_pool *pool,
 			  int cpuid)
 {
 	unsigned int ring_qsize = 1024; /* Default */
+	struct netdev_rx_queue *rxq;
+	int err;
 
 	page_pool_struct_check();
 
@@ -271,7 +275,37 @@ static int page_pool_init(struct page_pool *pool,
 	if (pool->dma_map)
 		get_device(pool->p.dev);
 
+	if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) {
+		/* We rely on rtnl_lock()ing to make sure netdev_rx_queue
+		 * configuration doesn't change while we're initializing
+		 * the page_pool.
+		 */
+		ASSERT_RTNL();
+		rxq = __netif_get_rx_queue(pool->slow.netdev,
+					   pool->slow.queue_idx);
+		pool->mp_priv = rxq->mp_params.mp_priv;
+	}
+
+	if (pool->mp_priv) {
+		err = mp_dmabuf_devmem_init(pool);
+		if (err) {
+			pr_warn("%s() mem-provider init failed %d\n", __func__,
+				err);
+			goto free_ptr_ring;
+		}
+
+		static_branch_inc(&page_pool_mem_providers);
+	}
+
 	return 0;
+
+free_ptr_ring:
+	ptr_ring_cleanup(&pool->ring, NULL);
+#ifdef CONFIG_PAGE_POOL_STATS
+	if (!pool->system)
+		free_percpu(pool->recycle_stats);
+#endif
+	return err;
 }
 
 static void page_pool_uninit(struct page_pool *pool)
@@ -455,28 +489,6 @@ unmap_failed:
 	return false;
 }
 
-static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
-{
-	netmem_set_pp(netmem, pool);
-	netmem_or_pp_magic(netmem, PP_SIGNATURE);
-
-	/* Ensuring all pages have been split into one fragment initially:
-	 * page_pool_set_pp_info() is only called once for every page when it
-	 * is allocated from the page allocator and page_pool_fragment_page()
-	 * is dirtying the same cache line as the page->pp_magic above, so
-	 * the overhead is negligible.
-	 */
-	page_pool_fragment_netmem(netmem, 1);
-	if (pool->has_init_callback)
-		pool->slow.init_callback(netmem, pool->slow.init_arg);
-}
-
-static void page_pool_clear_pp_info(netmem_ref netmem)
-{
-	netmem_clear_pp_magic(netmem);
-	netmem_set_pp(netmem, NULL);
-}
-
 static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 						 gfp_t gfp)
 {
@@ -572,7 +584,10 @@ netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp)
 		return netmem;
 
 	/* Slow-path: cache empty, do real allocation */
-	netmem = __page_pool_alloc_pages_slow(pool, gfp);
+	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv)
+		netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp);
+	else
+		netmem = __page_pool_alloc_pages_slow(pool, gfp);
 	return netmem;
 }
 EXPORT_SYMBOL(page_pool_alloc_netmem);
@@ -608,6 +623,28 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 	return inflight;
 }
 
+void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
+{
+	netmem_set_pp(netmem, pool);
+	netmem_or_pp_magic(netmem, PP_SIGNATURE);
+
+	/* Ensuring all pages have been split into one fragment initially:
+	 * page_pool_set_pp_info() is only called once for every page when it
+	 * is allocated from the page allocator and page_pool_fragment_page()
+	 * is dirtying the same cache line as the page->pp_magic above, so
+	 * the overhead is negligible.
+	 */
+	page_pool_fragment_netmem(netmem, 1);
+	if (pool->has_init_callback)
+		pool->slow.init_callback(netmem, pool->slow.init_arg);
+}
+
+void page_pool_clear_pp_info(netmem_ref netmem)
+{
+	netmem_clear_pp_magic(netmem);
+	netmem_set_pp(netmem, NULL);
+}
+
 static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 							 netmem_ref netmem)
 {
@@ -636,8 +673,13 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 {
 	int count;
+	bool put;
 
-	__page_pool_release_page_dma(pool, netmem);
+	put = true;
+	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv)
+		put = mp_dmabuf_devmem_release_page(pool, netmem);
+	else
+		__page_pool_release_page_dma(pool, netmem);
 
 	/* This may be the last page returned, releasing the pool, so
 	 * it is not safe to reference pool afterwards.
@@ -645,8 +687,10 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 	count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt);
 	trace_page_pool_state_release(pool, netmem, count);
 
-	page_pool_clear_pp_info(netmem);
-	put_page(netmem_to_page(netmem));
+	if (put) {
+		page_pool_clear_pp_info(netmem);
+		put_page(netmem_to_page(netmem));
+	}
 	/* An optimization would be to call __free_pages(page, pool->p.order)
 	 * knowing page is not part of page-cache (thus avoiding a
 	 * __page_cache_release() call).
@@ -965,6 +1009,12 @@ static void __page_pool_destroy(struct page_pool *pool)
 
 	page_pool_unlist(pool);
 	page_pool_uninit(pool);
+
+	if (pool->mp_priv) {
+		mp_dmabuf_devmem_destroy(pool);
+		static_branch_dec(&page_pool_mem_providers);
+	}
+
 	kfree(pool);
 }
 
diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h
index d602c1e728c2..57439787b9c2 100644
--- a/net/core/page_pool_priv.h
+++ b/net/core/page_pool_priv.h
@@ -35,4 +35,24 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
 	return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr);
 }
 
+#if defined(CONFIG_PAGE_POOL)
+void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem);
+void page_pool_clear_pp_info(netmem_ref netmem);
+int page_pool_check_memory_provider(struct net_device *dev,
+				    struct netdev_rx_queue *rxq);
+#else
+static inline void page_pool_set_pp_info(struct page_pool *pool,
+					 netmem_ref netmem)
+{
+}
+static inline void page_pool_clear_pp_info(netmem_ref netmem)
+{
+}
+static inline int page_pool_check_memory_provider(struct net_device *dev,
+						  struct netdev_rx_queue *rxq)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 3a3277ba167b..cd6267ba6fa3 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -4,8 +4,9 @@
 #include <linux/netdevice.h>
 #include <linux/xarray.h>
 #include <net/net_debug.h>
-#include <net/page_pool/types.h>
+#include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/types.h>
 #include <net/sock.h>
 
 #include "page_pool_priv.h"
@@ -344,6 +345,30 @@ void page_pool_unlist(struct page_pool *pool)
 	mutex_unlock(&page_pools_lock);
 }
 
+int page_pool_check_memory_provider(struct net_device *dev,
+				    struct netdev_rx_queue *rxq)
+{
+	struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv;
+	struct page_pool *pool;
+	struct hlist_node *n;
+
+	if (!binding)
+		return 0;
+
+	mutex_lock(&page_pools_lock);
+	hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) {
+		if (pool->mp_priv != binding)
+			continue;
+
+		if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) {
+			mutex_unlock(&page_pools_lock);
+			return 0;
+		}
+	}
+	mutex_unlock(&page_pools_lock);
+	return -ENODATA;
+}
+
 static void page_pool_unreg_netdev_wipe(struct net_device *netdev)
 {
 	struct page_pool *pool;
-- 
cgit v1.3-3-g829e


From 9f6b619edf2e85746f261b42ae8f818a59d126f7 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:51 +0000
Subject: net: support non paged skb frags

Make skb_frag_page() fail in the case where the frag is not backed
by a page, and fix its relevant callers to handle this case.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-8-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h     | 42 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/skbuff_ref.h |  9 ++++-----
 net/core/dev.c             |  3 ++-
 net/core/gro.c             |  3 ++-
 net/core/skbuff.c          | 11 +++++++++++
 net/ipv4/esp4.c            |  3 ++-
 net/ipv4/tcp.c             |  3 +++
 net/ipv6/esp6.c            |  3 ++-
 8 files changed, 67 insertions(+), 10 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5803eb8a157d..1019f14583c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3524,21 +3524,58 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto,
 	fragto->offset = fragfrom->offset;
 }
 
+/* Return: true if the skb_frag contains a net_iov. */
+static inline bool skb_frag_is_net_iov(const skb_frag_t *frag)
+{
+	return netmem_is_net_iov(frag->netmem);
+}
+
+/**
+ * skb_frag_net_iov - retrieve the net_iov referred to by fragment
+ * @frag: the fragment
+ *
+ * Return: the &struct net_iov associated with @frag. Returns NULL if this
+ * frag has no associated net_iov.
+ */
+static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag)
+{
+	if (!skb_frag_is_net_iov(frag))
+		return NULL;
+
+	return netmem_to_net_iov(frag->netmem);
+}
+
 /**
  * skb_frag_page - retrieve the page referred to by a paged fragment
  * @frag: the paged fragment
  *
- * Returns the &struct page associated with @frag.
+ * Return: the &struct page associated with @frag. Returns NULL if this frag
+ * has no associated page.
  */
 static inline struct page *skb_frag_page(const skb_frag_t *frag)
 {
+	if (skb_frag_is_net_iov(frag))
+		return NULL;
+
 	return netmem_to_page(frag->netmem);
 }
 
+/**
+ * skb_frag_netmem - retrieve the netmem referred to by a fragment
+ * @frag: the fragment
+ *
+ * Return: the &netmem_ref associated with @frag.
+ */
+static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag)
+{
+	return frag->netmem;
+}
+
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom);
 int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
 			 struct bpf_prog *prog);
+
 /**
  * skb_frag_address - gets the address of the data contained in a paged fragment
  * @frag: the paged fragment buffer
@@ -3548,6 +3585,9 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
  */
 static inline void *skb_frag_address(const skb_frag_t *frag)
 {
+	if (!skb_frag_page(frag))
+		return NULL;
+
 	return page_address(skb_frag_page(frag)) + skb_frag_off(frag);
 }
 
diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h
index 16c241a23472..0f3c58007488 100644
--- a/include/linux/skbuff_ref.h
+++ b/include/linux/skbuff_ref.h
@@ -34,14 +34,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
 
 bool napi_pp_put_page(netmem_ref netmem);
 
-static inline void
-skb_page_unref(struct page *page, bool recycle)
+static inline void skb_page_unref(netmem_ref netmem, bool recycle)
 {
 #ifdef CONFIG_PAGE_POOL
-	if (recycle && napi_pp_put_page(page_to_netmem(page)))
+	if (recycle && napi_pp_put_page(netmem))
 		return;
 #endif
-	put_page(page);
+	put_page(netmem_to_page(netmem));
 }
 
 /**
@@ -54,7 +53,7 @@ skb_page_unref(struct page *page, bool recycle)
  */
 static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
 {
-	skb_page_unref(skb_frag_page(frag), recycle);
+	skb_page_unref(skb_frag_netmem(frag), recycle);
 }
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index 7818d7f6295e..517b934bdf9c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3434,8 +3434,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 	if (!(dev->features & NETIF_F_HIGHDMA)) {
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = skb_frag_page(frag);
 
-			if (PageHighMem(skb_frag_page(frag)))
+			if (page && PageHighMem(page))
 				return 1;
 		}
 	}
diff --git a/net/core/gro.c b/net/core/gro.c
index 3abad1b567dd..802b4a062400 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -408,7 +408,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
 	pinfo = skb_shinfo(skb);
 	frag0 = &pinfo->frags[0];
 
-	if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) &&
+	if (pinfo->nr_frags && skb_frag_page(frag0) &&
+	    !PageHighMem(skb_frag_page(frag0)) &&
 	    (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) {
 		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
 		NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8abcc28bb189..671c456b93f5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1371,6 +1371,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
 		struct page *p;
 		u8 *vaddr;
 
+		if (skb_frag_is_net_iov(frag)) {
+			printk("%sskb frag %d: not readable\n", level, i);
+			len -= skb_frag_size(frag);
+			if (!len)
+				break;
+			continue;
+		}
+
 		skb_frag_foreach_page(frag, skb_frag_off(frag),
 				      skb_frag_size(frag), p, p_off, p_len,
 				      copied) {
@@ -3163,6 +3171,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
 	for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
 		const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
 
+		if (WARN_ON_ONCE(!skb_frag_page(f)))
+			return false;
+
 		if (__splice_segment(skb_frag_page(f),
 				     skb_frag_off(f), skb_frag_size(f),
 				     offset, len, spd, false, sk, pipe))
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 47378ca41904..f3281312eb5e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -115,7 +115,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			skb_page_unref(sg_page(sg), skb->pp_recycle);
+			skb_page_unref(page_to_netmem(sg_page(sg)),
+				       skb->pp_recycle);
 }
 
 #ifdef CONFIG_INET_ESPINTCP
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e359a9161445..06dcf89e2cca 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2177,6 +2177,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
 			break;
 		}
 		page = skb_frag_page(frags);
+		if (WARN_ON_ONCE(!page))
+			break;
+
 		prefetchw(page);
 		pages[pages_to_map++] = page;
 		length += PAGE_SIZE;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 3920e8aa1031..b2400c226a32 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -132,7 +132,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			skb_page_unref(sg_page(sg), skb->pp_recycle);
+			skb_page_unref(page_to_netmem(sg_page(sg)),
+				       skb->pp_recycle);
 }
 
 #ifdef CONFIG_INET6_ESPINTCP
-- 
cgit v1.3-3-g829e


From 65249feb6b3df9e17bab5911ee56fa7b0971e231 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:52 +0000
Subject: net: add support for skbs with unreadable frags

For device memory TCP, we expect the skb headers to be available in host
memory for access, and we expect the skb frags to be in device memory
and unaccessible to the host. We expect there to be no mixing and
matching of device memory frags (unaccessible) with host memory frags
(accessible) in the same skb.

Add a skb->devmem flag which indicates whether the frags in this skb
are device memory frags or not.

__skb_fill_netmem_desc() now checks frags added to skbs for net_iov,
and marks the skb as skb->devmem accordingly.

Add checks through the network stack to avoid accessing the frags of
devmem skbs and avoid coalescing devmem skbs with non devmem skbs.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-9-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 19 +++++++++++++++++--
 include/net/tcp.h      |  3 ++-
 net/core/datagram.c    |  6 ++++++
 net/core/dev.c         |  4 ++++
 net/core/skbuff.c      | 43 +++++++++++++++++++++++++++++++++++++++++--
 net/ipv4/tcp.c         |  3 +++
 net/ipv4/tcp_input.c   | 13 ++++++++++---
 net/ipv4/tcp_output.c  |  5 ++++-
 net/packet/af_packet.c |  4 ++--
 9 files changed, 89 insertions(+), 11 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1019f14583c9..39f1d16f3628 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -827,6 +827,8 @@ enum skb_tstamp_type {
  *	@csum_level: indicates the number of consecutive checksums found in
  *		the packet minus one that have been verified as
  *		CHECKSUM_UNNECESSARY (max 3)
+ *	@unreadable: indicates that at least 1 of the fragments in this skb is
+ *		unreadable.
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@slow_gro: state present at GRO time, slower prepare step required
@@ -1008,7 +1010,7 @@ struct sk_buff {
 #if IS_ENABLED(CONFIG_IP_SCTP)
 	__u8			csum_not_inet:1;
 #endif
-
+	__u8			unreadable:1;
 #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS)
 	__u16			tc_index;	/* traffic control index */
 #endif
@@ -1824,6 +1826,12 @@ static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb)
 		__skb_zcopy_downgrade_managed(skb);
 }
 
+/* Return true if frags in this skb are readable by the host. */
+static inline bool skb_frags_readable(const struct sk_buff *skb)
+{
+	return !skb->unreadable;
+}
+
 static inline void skb_mark_not_on_list(struct sk_buff *skb)
 {
 	skb->next = NULL;
@@ -2540,10 +2548,17 @@ static inline void skb_len_add(struct sk_buff *skb, int delta)
 static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i,
 					  netmem_ref netmem, int off, int size)
 {
-	struct page *page = netmem_to_page(netmem);
+	struct page *page;
 
 	__skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size);
 
+	if (netmem_is_net_iov(netmem)) {
+		skb->unreadable = true;
+		return;
+	}
+
+	page = netmem_to_page(netmem);
+
 	/* Propagate page pfmemalloc to the skb if we can. The problem is
 	 * that not all callers have unique ownership of the page but rely
 	 * on page_is_pfmemalloc doing the right thing(tm).
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2aac11e7e1cc..f77f812bfbe7 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1069,7 +1069,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to,
 	/* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */
 	return likely(tcp_skb_can_collapse_to(to) &&
 		      mptcp_skb_can_collapse(to, from) &&
-		      skb_pure_zcopy_same(to, from));
+		      skb_pure_zcopy_same(to, from) &&
+		      skb_frags_readable(to) == skb_frags_readable(from));
 }
 
 static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to,
diff --git a/net/core/datagram.c b/net/core/datagram.c
index a40f733b37d7..f0693707aece 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -407,6 +407,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset,
 			return 0;
 	}
 
+	if (!skb_frags_readable(skb))
+		goto short_copy;
+
 	/* Copy paged appendix. Hmm... why does this look so complicated? */
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
@@ -623,6 +626,9 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
 {
 	int frag = skb_shinfo(skb)->nr_frags;
 
+	if (!skb_frags_readable(skb))
+		return -EFAULT;
+
 	while (length && iov_iter_count(from)) {
 		struct page *head, *last_head = NULL;
 		struct page *pages[MAX_SKB_FRAGS];
diff --git a/net/core/dev.c b/net/core/dev.c
index 517b934bdf9c..1e740faf9e78 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3312,6 +3312,10 @@ int skb_checksum_help(struct sk_buff *skb)
 		return -EINVAL;
 	}
 
+	if (!skb_frags_readable(skb)) {
+		return -EFAULT;
+	}
+
 	/* Before computing a checksum, we should make sure no frag could
 	 * be modified by an external entity : checksum could be wrong.
 	 */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 671c456b93f5..74149dc4ee31 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1972,6 +1972,9 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
 		return -EINVAL;
 
+	if (!skb_frags_readable(skb))
+		return -EFAULT;
+
 	if (!num_frags)
 		goto release;
 
@@ -2145,6 +2148,9 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 	unsigned int size;
 	int headerlen;
 
+	if (!skb_frags_readable(skb))
+		return NULL;
+
 	if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
 		return NULL;
 
@@ -2483,6 +2489,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb,
 	struct sk_buff *n;
 	int oldheadroom;
 
+	if (!skb_frags_readable(skb))
+		return NULL;
+
 	if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
 		return NULL;
 
@@ -2827,6 +2836,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta)
 	 */
 	int i, k, eat = (skb->tail + delta) - skb->end;
 
+	if (!skb_frags_readable(skb))
+		return NULL;
+
 	if (eat > 0 || skb_cloned(skb)) {
 		if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
 				     GFP_ATOMIC))
@@ -2980,6 +2992,9 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
 		to     += copy;
 	}
 
+	if (!skb_frags_readable(skb))
+		goto fault;
+
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
 		skb_frag_t *f = &skb_shinfo(skb)->frags[i];
@@ -3168,6 +3183,9 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
 	/*
 	 * then map the fragments
 	 */
+	if (!skb_frags_readable(skb))
+		return false;
+
 	for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
 		const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
 
@@ -3391,6 +3409,9 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
 		from += copy;
 	}
 
+	if (!skb_frags_readable(skb))
+		goto fault;
+
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		int end;
@@ -3470,6 +3491,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 		pos	= copy;
 	}
 
+	if (WARN_ON_ONCE(!skb_frags_readable(skb)))
+		return 0;
+
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
@@ -3570,6 +3594,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 		pos	= copy;
 	}
 
+	if (!skb_frags_readable(skb))
+		return 0;
+
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
 
@@ -4061,6 +4088,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb,
 		skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];
 
 	skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags;
+	skb1->unreadable	   = skb->unreadable;
 	skb_shinfo(skb)->nr_frags  = 0;
 	skb1->data_len		   = skb->data_len;
 	skb1->len		   += skb1->data_len;
@@ -4108,6 +4136,8 @@ static inline void skb_split_no_header(struct sk_buff *skb,
 		pos += size;
 	}
 	skb_shinfo(skb1)->nr_frags = k;
+
+	skb1->unreadable = skb->unreadable;
 }
 
 /**
@@ -4345,6 +4375,9 @@ next_skb:
 		return block_limit - abs_offset;
 	}
 
+	if (!skb_frags_readable(st->cur_skb))
+		return 0;
+
 	if (st->frag_idx == 0 && !st->frag_data)
 		st->stepped_offset += skb_headlen(st->cur_skb);
 
@@ -5992,7 +6025,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
 	if (to->pp_recycle != from->pp_recycle)
 		return false;
 
-	if (len <= skb_tailroom(to)) {
+	if (skb_frags_readable(from) != skb_frags_readable(to))
+		return false;
+
+	if (len <= skb_tailroom(to) && skb_frags_readable(from)) {
 		if (len)
 			BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
 		*delta_truesize = 0;
@@ -6169,6 +6205,9 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
 
+	if (!skb_frags_readable(skb))
+		return -EFAULT;
+
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 
@@ -6848,7 +6887,7 @@ void skb_condense(struct sk_buff *skb)
 {
 	if (skb->data_len) {
 		if (skb->data_len > skb->end - skb->tail ||
-		    skb_cloned(skb))
+		    skb_cloned(skb) || !skb_frags_readable(skb))
 			return;
 
 		/* Nice, we can free page frag(s) right now */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 06dcf89e2cca..a2fac029a84a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2160,6 +2160,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
 				skb = tcp_recv_skb(sk, seq, &offset);
 			}
 
+			if (!skb_frags_readable(skb))
+				break;
+
 			if (TCP_SKB_CB(skb)->has_rxtstamp) {
 				tcp_update_recv_tstamps(skb, tss);
 				zc->msg_flags |= TCP_CMSG_TS;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e37488d3453f..9f314dfa1490 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5391,6 +5391,9 @@ restart:
 	for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) {
 		n = tcp_skb_next(skb, list);
 
+		if (!skb_frags_readable(skb))
+			goto skip_this;
+
 		/* No new bits? It is possible on ofo queue. */
 		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
 			skb = tcp_collapse_one(sk, skb, list, root);
@@ -5411,17 +5414,20 @@ restart:
 			break;
 		}
 
-		if (n && n != tail && tcp_skb_can_collapse_rx(skb, n) &&
+		if (n && n != tail && skb_frags_readable(n) &&
+		    tcp_skb_can_collapse_rx(skb, n) &&
 		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
 			end_of_skbs = false;
 			break;
 		}
 
+skip_this:
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
 	}
 	if (end_of_skbs ||
-	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
+	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) ||
+	    !skb_frags_readable(skb))
 		return;
 
 	__skb_queue_head_init(&tmp);
@@ -5463,7 +5469,8 @@ restart:
 				if (!skb ||
 				    skb == tail ||
 				    !tcp_skb_can_collapse_rx(nskb, skb) ||
-				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
+				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) ||
+				    !skb_frags_readable(skb))
 					goto end;
 			}
 		}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cdd0def14427..4fd746bd4d54 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2344,7 +2344,8 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 
 		if (unlikely(TCP_SKB_CB(skb)->eor) ||
 		    tcp_has_tx_tstamp(skb) ||
-		    !skb_pure_zcopy_same(skb, next))
+		    !skb_pure_zcopy_same(skb, next) ||
+		    skb_frags_readable(skb) != skb_frags_readable(next))
 			return false;
 
 		len -= skb->len;
@@ -3264,6 +3265,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
 		return false;
 	if (skb_cloned(skb))
 		return false;
+	if (!skb_frags_readable(skb))
+		return false;
 	/* Some heuristics for collapsing over SACK'd could be invented */
 	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
 		return false;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 4a364cdd445e..a705ec214254 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2216,7 +2216,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	snaplen = skb->len;
+	snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);
 
 	res = run_filter(skb, sk, snaplen);
 	if (!res)
@@ -2336,7 +2336,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
-	snaplen = skb->len;
+	snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);
 
 	res = run_filter(skb, sk, snaplen);
 	if (!res)
-- 
cgit v1.3-3-g829e


From 8f0b3cc9a4c102c24808c87f1bc943659d7a7f9f Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:53 +0000
Subject: tcp: RX path for devmem TCP

In tcp_recvmsg_locked(), detect if the skb being received by the user
is a devmem skb. In this case - if the user provided the MSG_SOCK_DEVMEM
flag - pass it to tcp_recvmsg_devmem() for custom handling.

tcp_recvmsg_devmem() copies any data in the skb header to the linear
buffer, and returns a cmsg to the user indicating the number of bytes
returned in the linear buffer.

tcp_recvmsg_devmem() then loops over the unaccessible devmem skb frags,
and returns to the user a cmsg_devmem indicating the location of the
data in the dmabuf device memory. cmsg_devmem contains this information:

1. the offset into the dmabuf where the payload starts. 'frag_offset'.
2. the size of the frag. 'frag_size'.
3. an opaque token 'frag_token' to return to the kernel when the buffer
is to be released.

The pages awaiting freeing are stored in the newly added
sk->sk_user_frags, and each page passed to userspace is get_page()'d.
This reference is dropped once the userspace indicates that it is
done reading this page.  All pages are released when the socket is
destroyed.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240910171458.219195-10-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/alpha/include/uapi/asm/socket.h  |   5 +
 arch/mips/include/uapi/asm/socket.h   |   5 +
 arch/parisc/include/uapi/asm/socket.h |   5 +
 arch/sparc/include/uapi/asm/socket.h  |   5 +
 include/linux/socket.h                |   1 +
 include/net/sock.h                    |   2 +
 include/uapi/asm-generic/socket.h     |   5 +
 include/uapi/linux/uio.h              |  13 ++
 net/core/devmem.h                     |  22 +++
 net/ipv4/tcp.c                        | 257 +++++++++++++++++++++++++++++++++-
 net/ipv4/tcp_ipv4.c                   |  16 +++
 net/ipv4/tcp_minisocks.c              |   2 +
 12 files changed, 333 insertions(+), 5 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index e94f621903fe..ef4656a41058 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -140,6 +140,11 @@
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 60ebaed28a4c..414807d55e33 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -151,6 +151,11 @@
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index be264c2b1a11..2b817efd4544 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -132,6 +132,11 @@
 #define SO_PASSPIDFD		0x404A
 #define SO_PEERPIDFD		0x404B
 
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 682da3714686..00248fc68977 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -133,6 +133,11 @@
 #define SO_PASSPIDFD             0x0055
 #define SO_PEERPIDFD             0x0056
 
+#define SO_DEVMEM_LINEAR         0x0057
+#define SCM_DEVMEM_LINEAR        SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF         0x0058
+#define SCM_DEVMEM_DMABUF        SO_DEVMEM_DMABUF
+
 #if !defined(__KERNEL__)
 
 
diff --git a/include/linux/socket.h b/include/linux/socket.h
index df9cdb8bbfb8..d18cc47e89bd 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -327,6 +327,7 @@ struct ucred {
 					  * plain text and require encryption
 					  */
 
+#define MSG_SOCK_DEVMEM 0x2000000	/* Receive devmem skbs as cmsg */
 #define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
 #define MSG_SPLICE_PAGES 0x8000000	/* Splice the pages from the iterator in sendmsg() */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
diff --git a/include/net/sock.h b/include/net/sock.h
index f51d61fab059..c58ca8dd561b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -337,6 +337,7 @@ struct sk_filter;
   *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
   *	@ns_tracker: tracker for netns reference
+  *	@sk_user_frags: xarray of pages the user is holding a reference on.
   */
 struct sock {
 	/*
@@ -542,6 +543,7 @@ struct sock {
 #endif
 	struct rcu_head		sk_rcu;
 	netns_tracker		ns_tracker;
+	struct xarray		sk_user_frags;
 };
 
 struct sock_bh_locked {
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 8ce8a39a1e5f..e993edc9c0ee 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -135,6 +135,11 @@
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index 059b1a9147f4..3a22ddae376a 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -20,6 +20,19 @@ struct iovec
 	__kernel_size_t iov_len; /* Must be size_t (1003.1g) */
 };
 
+struct dmabuf_cmsg {
+	__u64 frag_offset;	/* offset into the dmabuf where the frag starts.
+				 */
+	__u32 frag_size;	/* size of the frag. */
+	__u32 frag_token;	/* token representing this frag for
+				 * DEVMEM_DONTNEED.
+				 */
+	__u32  dmabuf_id;	/* dmabuf id this frag belongs to. */
+	__u32 flags;		/* Currently unused. Reserved for future
+				 * uses.
+				 */
+};
+
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
diff --git a/net/core/devmem.h b/net/core/devmem.h
index b1db4877cff9..76099ef9c482 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -91,6 +91,19 @@ net_iov_binding(const struct net_iov *niov)
 	return net_iov_owner(niov)->binding;
 }
 
+static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
+{
+	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+
+	return owner->base_virtual +
+	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
+}
+
+static inline u32 net_iov_binding_id(const struct net_iov *niov)
+{
+	return net_iov_owner(niov)->binding->id;
+}
+
 static inline void
 net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
 {
@@ -153,6 +166,15 @@ static inline void net_devmem_free_dmabuf(struct net_iov *ppiov)
 {
 }
 
+static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
+{
+	return 0;
+}
+
+static inline u32 net_iov_binding_id(const struct net_iov *niov)
+{
+	return 0;
+}
 #endif
 
 #endif /* _NET_DEVMEM_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a2fac029a84a..4f77bd862e95 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -285,6 +285,8 @@
 #include <trace/events/tcp.h>
 #include <net/rps.h>
 
+#include "../core/devmem.h"
+
 /* Track pending CMSGs. */
 enum {
 	TCP_CMSG_INQ = 1,
@@ -471,6 +473,7 @@ void tcp_init_sock(struct sock *sk)
 
 	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	sk_sockets_allocated_inc(sk);
+	xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1);
 }
 EXPORT_SYMBOL(tcp_init_sock);
 
@@ -2328,6 +2331,220 @@ static int tcp_inq_hint(struct sock *sk)
 	return inq;
 }
 
+/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */
+struct tcp_xa_pool {
+	u8		max; /* max <= MAX_SKB_FRAGS */
+	u8		idx; /* idx <= max */
+	__u32		tokens[MAX_SKB_FRAGS];
+	netmem_ref	netmems[MAX_SKB_FRAGS];
+};
+
+static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p)
+{
+	int i;
+
+	/* Commit part that has been copied to user space. */
+	for (i = 0; i < p->idx; i++)
+		__xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY,
+			     (__force void *)p->netmems[i], GFP_KERNEL);
+	/* Rollback what has been pre-allocated and is no longer needed. */
+	for (; i < p->max; i++)
+		__xa_erase(&sk->sk_user_frags, p->tokens[i]);
+
+	p->max = 0;
+	p->idx = 0;
+}
+
+static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p)
+{
+	if (!p->max)
+		return;
+
+	xa_lock_bh(&sk->sk_user_frags);
+
+	tcp_xa_pool_commit_locked(sk, p);
+
+	xa_unlock_bh(&sk->sk_user_frags);
+}
+
+static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p,
+			      unsigned int max_frags)
+{
+	int err, k;
+
+	if (p->idx < p->max)
+		return 0;
+
+	xa_lock_bh(&sk->sk_user_frags);
+
+	tcp_xa_pool_commit_locked(sk, p);
+
+	for (k = 0; k < max_frags; k++) {
+		err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k],
+				 XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL);
+		if (err)
+			break;
+	}
+
+	xa_unlock_bh(&sk->sk_user_frags);
+
+	p->max = k;
+	p->idx = 0;
+	return k ? 0 : err;
+}
+
+/* On error, returns the -errno. On success, returns number of bytes sent to the
+ * user. May not consume all of @remaining_len.
+ */
+static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
+			      unsigned int offset, struct msghdr *msg,
+			      int remaining_len)
+{
+	struct dmabuf_cmsg dmabuf_cmsg = { 0 };
+	struct tcp_xa_pool tcp_xa_pool;
+	unsigned int start;
+	int i, copy, n;
+	int sent = 0;
+	int err = 0;
+
+	tcp_xa_pool.max = 0;
+	tcp_xa_pool.idx = 0;
+	do {
+		start = skb_headlen(skb);
+
+		if (skb_frags_readable(skb)) {
+			err = -ENODEV;
+			goto out;
+		}
+
+		/* Copy header. */
+		copy = start - offset;
+		if (copy > 0) {
+			copy = min(copy, remaining_len);
+
+			n = copy_to_iter(skb->data + offset, copy,
+					 &msg->msg_iter);
+			if (n != copy) {
+				err = -EFAULT;
+				goto out;
+			}
+
+			offset += copy;
+			remaining_len -= copy;
+
+			/* First a dmabuf_cmsg for # bytes copied to user
+			 * buffer.
+			 */
+			memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg));
+			dmabuf_cmsg.frag_size = copy;
+			err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR,
+				       sizeof(dmabuf_cmsg), &dmabuf_cmsg);
+			if (err || msg->msg_flags & MSG_CTRUNC) {
+				msg->msg_flags &= ~MSG_CTRUNC;
+				if (!err)
+					err = -ETOOSMALL;
+				goto out;
+			}
+
+			sent += copy;
+
+			if (remaining_len == 0)
+				goto out;
+		}
+
+		/* after that, send information of dmabuf pages through a
+		 * sequence of cmsg
+		 */
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct net_iov *niov;
+			u64 frag_offset;
+			int end;
+
+			/* !skb_frags_readable() should indicate that ALL the
+			 * frags in this skb are dmabuf net_iovs. We're checking
+			 * for that flag above, but also check individual frags
+			 * here. If the tcp stack is not setting
+			 * skb_frags_readable() correctly, we still don't want
+			 * to crash here.
+			 */
+			if (!skb_frag_net_iov(frag)) {
+				net_err_ratelimited("Found non-dmabuf skb with net_iov");
+				err = -ENODEV;
+				goto out;
+			}
+
+			niov = skb_frag_net_iov(frag);
+			end = start + skb_frag_size(frag);
+			copy = end - offset;
+
+			if (copy > 0) {
+				copy = min(copy, remaining_len);
+
+				frag_offset = net_iov_virtual_addr(niov) +
+					      skb_frag_off(frag) + offset -
+					      start;
+				dmabuf_cmsg.frag_offset = frag_offset;
+				dmabuf_cmsg.frag_size = copy;
+				err = tcp_xa_pool_refill(sk, &tcp_xa_pool,
+							 skb_shinfo(skb)->nr_frags - i);
+				if (err)
+					goto out;
+
+				/* Will perform the exchange later */
+				dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx];
+				dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov);
+
+				offset += copy;
+				remaining_len -= copy;
+
+				err = put_cmsg(msg, SOL_SOCKET,
+					       SO_DEVMEM_DMABUF,
+					       sizeof(dmabuf_cmsg),
+					       &dmabuf_cmsg);
+				if (err || msg->msg_flags & MSG_CTRUNC) {
+					msg->msg_flags &= ~MSG_CTRUNC;
+					if (!err)
+						err = -ETOOSMALL;
+					goto out;
+				}
+
+				atomic_long_inc(&niov->pp_ref_count);
+				tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag);
+
+				sent += copy;
+
+				if (remaining_len == 0)
+					goto out;
+			}
+			start = end;
+		}
+
+		tcp_xa_pool_commit(sk, &tcp_xa_pool);
+		if (!remaining_len)
+			goto out;
+
+		/* if remaining_len is not satisfied yet, we need to go to the
+		 * next frag in the frag_list to satisfy remaining_len.
+		 */
+		skb = skb_shinfo(skb)->frag_list ?: skb->next;
+
+		offset = offset - start;
+	} while (skb);
+
+	if (remaining_len) {
+		err = -EFAULT;
+		goto out;
+	}
+
+out:
+	tcp_xa_pool_commit(sk, &tcp_xa_pool);
+	if (!sent)
+		sent = err;
+
+	return sent;
+}
+
 /*
  *	This routine copies from a sock struct into the user buffer.
  *
@@ -2341,6 +2558,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int last_copied_dmabuf = -1; /* uninitialized */
 	int copied = 0;
 	u32 peek_seq;
 	u32 *seq;
@@ -2520,15 +2738,44 @@ found_ok_skb:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-			err = skb_copy_datagram_msg(skb, offset, msg, used);
-			if (err) {
-				/* Exception. Bailout! */
-				if (!copied)
-					copied = -EFAULT;
+			if (last_copied_dmabuf != -1 &&
+			    last_copied_dmabuf != !skb_frags_readable(skb))
 				break;
+
+			if (skb_frags_readable(skb)) {
+				err = skb_copy_datagram_msg(skb, offset, msg,
+							    used);
+				if (err) {
+					/* Exception. Bailout! */
+					if (!copied)
+						copied = -EFAULT;
+					break;
+				}
+			} else {
+				if (!(flags & MSG_SOCK_DEVMEM)) {
+					/* dmabuf skbs can only be received
+					 * with the MSG_SOCK_DEVMEM flag.
+					 */
+					if (!copied)
+						copied = -EFAULT;
+
+					break;
+				}
+
+				err = tcp_recvmsg_dmabuf(sk, skb, offset, msg,
+							 used);
+				if (err <= 0) {
+					if (!copied)
+						copied = -EFAULT;
+
+					break;
+				}
+				used = err;
 			}
 		}
 
+		last_copied_dmabuf = !skb_frags_readable(skb);
+
 		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index eb631e66ee03..5afe5e57c89b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -79,6 +79,7 @@
 #include <linux/seq_file.h>
 #include <linux/inetdevice.h>
 #include <linux/btf_ids.h>
+#include <linux/skbuff_ref.h>
 
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
@@ -2512,10 +2513,25 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head)
 }
 #endif
 
+static void tcp_release_user_frags(struct sock *sk)
+{
+#ifdef CONFIG_PAGE_POOL
+	unsigned long index;
+	void *netmem;
+
+	xa_for_each(&sk->sk_user_frags, index, netmem)
+		WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem));
+#endif
+}
+
 void tcp_v4_destroy_sock(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	tcp_release_user_frags(sk);
+
+	xa_destroy(&sk->sk_user_frags);
+
 	trace_tcp_destroy_sock(sk);
 
 	tcp_clear_xmit_timers(sk);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ad562272db2e..bb1fe1ba867a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -628,6 +628,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 
+	xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1);
+
 	return newsk;
 }
 EXPORT_SYMBOL(tcp_create_openreq_child);
-- 
cgit v1.3-3-g829e


From 678f6e28b5f6fc2316f2c0fed8f8903101f1e128 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:54 +0000
Subject: net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags

Add an interface for the user to notify the kernel that it is done
reading the devmem dmabuf frags returned as cmsg. The kernel will
drop the reference on the frags to make them available for reuse.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240910171458.219195-11-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 arch/alpha/include/uapi/asm/socket.h  |  1 +
 arch/mips/include/uapi/asm/socket.h   |  1 +
 arch/parisc/include/uapi/asm/socket.h |  1 +
 arch/sparc/include/uapi/asm/socket.h  |  1 +
 include/uapi/asm-generic/socket.h     |  1 +
 include/uapi/linux/uio.h              |  5 +++
 net/core/sock.c                       | 68 +++++++++++++++++++++++++++++++++++
 7 files changed, 78 insertions(+)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index ef4656a41058..251b73c5481e 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -144,6 +144,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 414807d55e33..8ab7582291ab 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -155,6 +155,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 2b817efd4544..38fc0b188e08 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -136,6 +136,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 00248fc68977..57084ed2f3c4 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -137,6 +137,7 @@
 #define SCM_DEVMEM_LINEAR        SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF         0x0058
 #define SCM_DEVMEM_DMABUF        SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED       0x0059
 
 #if !defined(__KERNEL__)
 
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index e993edc9c0ee..3b4e3e815602 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -139,6 +139,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index 3a22ddae376a..649739e0c404 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -33,6 +33,11 @@ struct dmabuf_cmsg {
 				 */
 };
 
+struct dmabuf_token {
+	__u32 token_start;
+	__u32 token_count;
+};
+
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
diff --git a/net/core/sock.c b/net/core/sock.c
index 468b1239606c..bbb57b5af0b1 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -124,6 +124,7 @@
 #include <linux/netdevice.h>
 #include <net/protocol.h>
 #include <linux/skbuff.h>
+#include <linux/skbuff_ref.h>
 #include <net/net_namespace.h>
 #include <net/request_sock.h>
 #include <net/sock.h>
@@ -1049,6 +1050,69 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_POOL
+
+/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
+ * 1 syscall. The limit exists to limit the amount of memory the kernel
+ * allocates to copy these tokens.
+ */
+#define MAX_DONTNEED_TOKENS 128
+
+static noinline_for_stack int
+sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+	unsigned int num_tokens, i, j, k, netmem_num = 0;
+	struct dmabuf_token *tokens;
+	netmem_ref netmems[16];
+	int ret = 0;
+
+	if (!sk_is_tcp(sk))
+		return -EBADF;
+
+	if (optlen % sizeof(struct dmabuf_token) ||
+	    optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
+		return -EINVAL;
+
+	tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
+	if (!tokens)
+		return -ENOMEM;
+
+	num_tokens = optlen / sizeof(struct dmabuf_token);
+	if (copy_from_sockptr(tokens, optval, optlen)) {
+		kvfree(tokens);
+		return -EFAULT;
+	}
+
+	xa_lock_bh(&sk->sk_user_frags);
+	for (i = 0; i < num_tokens; i++) {
+		for (j = 0; j < tokens[i].token_count; j++) {
+			netmem_ref netmem = (__force netmem_ref)__xa_erase(
+				&sk->sk_user_frags, tokens[i].token_start + j);
+
+			if (netmem &&
+			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
+				netmems[netmem_num++] = netmem;
+				if (netmem_num == ARRAY_SIZE(netmems)) {
+					xa_unlock_bh(&sk->sk_user_frags);
+					for (k = 0; k < netmem_num; k++)
+						WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+					netmem_num = 0;
+					xa_lock_bh(&sk->sk_user_frags);
+				}
+				ret++;
+			}
+		}
+	}
+
+	xa_unlock_bh(&sk->sk_user_frags);
+	for (k = 0; k < netmem_num; k++)
+		WARN_ON_ONCE(!napi_pp_put_page(netmems[k]));
+
+	kvfree(tokens);
+	return ret;
+}
+#endif
+
 void sockopt_lock_sock(struct sock *sk)
 {
 	/* When current->bpf_ctx is set, the setsockopt is called from
@@ -1211,6 +1275,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 			ret = -EOPNOTSUPP;
 		return ret;
 		}
+#ifdef CONFIG_PAGE_POOL
+	case SO_DEVMEM_DONTNEED:
+		return sock_devmem_dontneed(sk, optval, optlen);
+#endif
 	}
 
 	sockopt_lock_sock(sk);
-- 
cgit v1.3-3-g829e


From 09d1db26b5e52072d703af14a2b65204d167e5a1 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:55 +0000
Subject: net: add devmem TCP documentation

Add documentation outlining the usage and details of devmem TCP.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20240910171458.219195-12-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/devmem.rst | 269 ++++++++++++++++++++++++++++++++++++
 Documentation/networking/index.rst  |   1 +
 2 files changed, 270 insertions(+)
 create mode 100644 Documentation/networking/devmem.rst

diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst
new file mode 100644
index 000000000000..a55bf21f671c
--- /dev/null
+++ b/Documentation/networking/devmem.rst
@@ -0,0 +1,269 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================
+Device Memory TCP
+=================
+
+
+Intro
+=====
+
+Device memory TCP (devmem TCP) enables receiving data directly into device
+memory (dmabuf). The feature is currently implemented for TCP sockets.
+
+
+Opportunity
+-----------
+
+A large number of data transfers have device memory as the source and/or
+destination. Accelerators drastically increased the prevalence of such
+transfers.  Some examples include:
+
+- Distributed training, where ML accelerators, such as GPUs on different hosts,
+  exchange data.
+
+- Distributed raw block storage applications transfer large amounts of data with
+  remote SSDs. Much of this data does not require host processing.
+
+Typically the Device-to-Device data transfers in the network are implemented as
+the following low-level operations: Device-to-Host copy, Host-to-Host network
+transfer, and Host-to-Device copy.
+
+The flow involving host copies is suboptimal, especially for bulk data transfers,
+and can put significant strains on system resources such as host memory
+bandwidth and PCIe bandwidth.
+
+Devmem TCP optimizes this use case by implementing socket APIs that enable
+the user to receive incoming network packets directly into device memory.
+
+Packet payloads go directly from the NIC to device memory.
+
+Packet headers go to host memory and are processed by the TCP/IP stack
+normally. The NIC must support header split to achieve this.
+
+Advantages:
+
+- Alleviate host memory bandwidth pressure, compared to existing
+  network-transfer + device-copy semantics.
+
+- Alleviate PCIe bandwidth pressure, by limiting data transfer to the lowest
+  level of the PCIe tree, compared to the traditional path which sends data
+  through the root complex.
+
+
+More Info
+---------
+
+  slides, video
+    https://netdevconf.org/0x17/sessions/talk/device-memory-tcp.html
+
+  patchset
+    [PATCH net-next v24 00/13] Device Memory TCP
+    https://lore.kernel.org/netdev/20240831004313.3713467-1-almasrymina@google.com/
+
+
+Interface
+=========
+
+
+Example
+-------
+
+tools/testing/selftests/net/ncdevmem.c:do_server shows an example of setting up
+the RX path of this API.
+
+
+NIC Setup
+---------
+
+Header split, flow steering, & RSS are required features for devmem TCP.
+
+Header split is used to split incoming packets into a header buffer in host
+memory, and a payload buffer in device memory.
+
+Flow steering & RSS are used to ensure that only flows targeting devmem land on
+an RX queue bound to devmem.
+
+Enable header split & flow steering::
+
+	# enable header split
+	ethtool -G eth1 tcp-data-split on
+
+
+	# enable flow steering
+	ethtool -K eth1 ntuple on
+
+Configure RSS to steer all traffic away from the target RX queue (queue 15 in
+this example)::
+
+	ethtool --set-rxfh-indir eth1 equal 15
+
+
+The user must bind a dmabuf to any number of RX queues on a given NIC using
+the netlink API::
+
+	/* Bind dmabuf to NIC RX queue 15 */
+	struct netdev_queue *queues;
+	queues = malloc(sizeof(*queues) * 1);
+
+	queues[0]._present.type = 1;
+	queues[0]._present.idx = 1;
+	queues[0].type = NETDEV_RX_QUEUE_TYPE_RX;
+	queues[0].idx = 15;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+
+	req = netdev_bind_rx_req_alloc();
+	netdev_bind_rx_req_set_ifindex(req, 1 /* ifindex */);
+	netdev_bind_rx_req_set_dmabuf_fd(req, dmabuf_fd);
+	__netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
+
+	rsp = netdev_bind_rx(*ys, req);
+
+	dmabuf_id = rsp->dmabuf_id;
+
+
+The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf
+that has been bound.
+
+The user can unbind the dmabuf from the netdevice by closing the netlink socket
+that established the binding. We do this so that the binding is automatically
+unbound even if the userspace process crashes.
+
+Note that any reasonably well-behaved dmabuf from any exporter should work with
+devmem TCP, even if the dmabuf is not actually backed by devmem. An example of
+this is udmabuf, which wraps user memory (non-devmem) in a dmabuf.
+
+
+Socket Setup
+------------
+
+The socket must be flow steered to the dmabuf bound RX queue::
+
+	ethtool -N eth1 flow-type tcp4 ... queue 15
+
+
+Receiving data
+--------------
+
+The user application must signal to the kernel that it is capable of receiving
+devmem data by passing the MSG_SOCK_DEVMEM flag to recvmsg::
+
+	ret = recvmsg(fd, &msg, MSG_SOCK_DEVMEM);
+
+Applications that do not specify the MSG_SOCK_DEVMEM flag will receive an EFAULT
+on devmem data.
+
+Devmem data is received directly into the dmabuf bound to the NIC in 'NIC
+Setup', and the kernel signals such to the user via the SCM_DEVMEM_* cmsgs::
+
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_SOCKET ||
+				(cm->cmsg_type != SCM_DEVMEM_DMABUF &&
+				 cm->cmsg_type != SCM_DEVMEM_LINEAR))
+				continue;
+
+			dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm);
+
+			if (cm->cmsg_type == SCM_DEVMEM_DMABUF) {
+				/* Frag landed in dmabuf.
+				 *
+				 * dmabuf_cmsg->dmabuf_id is the dmabuf the
+				 * frag landed on.
+				 *
+				 * dmabuf_cmsg->frag_offset is the offset into
+				 * the dmabuf where the frag starts.
+				 *
+				 * dmabuf_cmsg->frag_size is the size of the
+				 * frag.
+				 *
+				 * dmabuf_cmsg->frag_token is a token used to
+				 * refer to this frag for later freeing.
+				 */
+
+				struct dmabuf_token token;
+				token.token_start = dmabuf_cmsg->frag_token;
+				token.token_count = 1;
+				continue;
+			}
+
+			if (cm->cmsg_type == SCM_DEVMEM_LINEAR)
+				/* Frag landed in linear buffer.
+				 *
+				 * dmabuf_cmsg->frag_size is the size of the
+				 * frag.
+				 */
+				continue;
+
+		}
+
+Applications may receive 2 cmsgs:
+
+- SCM_DEVMEM_DMABUF: this indicates the fragment landed in the dmabuf indicated
+  by dmabuf_id.
+
+- SCM_DEVMEM_LINEAR: this indicates the fragment landed in the linear buffer.
+  This typically happens when the NIC is unable to split the packet at the
+  header boundary, such that part (or all) of the payload landed in host
+  memory.
+
+Applications may receive no SO_DEVMEM_* cmsgs. That indicates non-devmem,
+regular TCP data that landed on an RX queue not bound to a dmabuf.
+
+
+Freeing frags
+-------------
+
+Frags received via SCM_DEVMEM_DMABUF are pinned by the kernel while the user
+processes the frag. The user must return the frag to the kernel via
+SO_DEVMEM_DONTNEED::
+
+	ret = setsockopt(client_fd, SOL_SOCKET, SO_DEVMEM_DONTNEED, &token,
+			 sizeof(token));
+
+The user must ensure the tokens are returned to the kernel in a timely manner.
+Failure to do so will exhaust the limited dmabuf that is bound to the RX queue
+and will lead to packet drops.
+
+
+Implementation & Caveats
+========================
+
+Unreadable skbs
+---------------
+
+Devmem payloads are inaccessible to the kernel processing the packets. This
+results in a few quirks for payloads of devmem skbs:
+
+- Loopback is not functional. Loopback relies on copying the payload, which is
+  not possible with devmem skbs.
+
+- Software checksum calculation fails.
+
+- TCP Dump and bpf can't access devmem packet payloads.
+
+
+Testing
+=======
+
+More realistic example code can be found in the kernel source under
+``tools/testing/selftests/net/ncdevmem.c``
+
+ncdevmem is a devmem TCP netcat. It works very similarly to netcat, but
+receives data directly into a udmabuf.
+
+To run ncdevmem, you need to run it on a server on the machine under test, and
+you need to run netcat on a peer to provide the TX data.
+
+ncdevmem has a validation mode as well that expects a repeating pattern of
+incoming data and validates it as such. For example, you can launch
+ncdevmem on the server by::
+
+	ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \
+		 -p 5201 -v 7
+
+On client side, use regular netcat to send TX data to ncdevmem process
+on the server::
+
+	yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
+		tr \\n \\0 | head -c 5G | nc <server IP> 5201 -p 5201
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index c71b87346178..08f437c326ab 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -49,6 +49,7 @@ Contents:
    cdc_mbim
    dccp
    dctcp
+   devmem
    dns_resolver
    driver
    eql
-- 
cgit v1.3-3-g829e


From 85585b4bc8d80095a825028e2088b568035ac467 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:56 +0000
Subject: selftests: add ncdevmem, netcat for devmem TCP

ncdevmem is a devmem TCP netcat. It works similarly to netcat, but it
sends and receives data using the devmem TCP APIs. It uses udmabuf as
the dmabuf provider. It is compatible with a regular netcat running on
a peer, or a ncdevmem running on a peer.

In addition to normal netcat support, ncdevmem has a validation mode,
where it sends a specific pattern and validates this pattern on the
receiver side to ensure data integrity.

Suggested-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20240910171458.219195-13-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/lib/.gitignore           |   1 +
 tools/testing/selftests/net/.gitignore |   1 +
 tools/testing/selftests/net/Makefile   |   9 +
 tools/testing/selftests/net/ncdevmem.c | 570 +++++++++++++++++++++++++++++++++
 4 files changed, 581 insertions(+)
 create mode 100644 tools/testing/selftests/net/ncdevmem.c

diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore
index c18dd8d83cee..296c4035dbf2 100644
--- a/tools/net/ynl/lib/.gitignore
+++ b/tools/net/ynl/lib/.gitignore
@@ -1 +1,2 @@
 __pycache__/
+*.d
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 923bf098e2eb..1c04c780db66 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -17,6 +17,7 @@ ipv6_flowlabel
 ipv6_flowlabel_mgr
 log.txt
 msg_zerocopy
+ncdevmem
 nettest
 psock_fanout
 psock_snd
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 22a5d6a7c3f3..649f1fe0dc46 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -97,6 +97,11 @@ TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 TEST_PROGS += bpf_offload.py
 
+# YNL files, must be before "include ..lib.mk"
+EXTRA_CLEAN += $(OUTPUT)/libynl.a
+YNL_GEN_FILES := ncdevmem
+TEST_GEN_FILES += $(YNL_GEN_FILES)
+
 TEST_FILES := settings
 TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
 
@@ -106,6 +111,10 @@ TEST_INCLUDES := forwarding/lib.sh
 
 include ../lib.mk
 
+# YNL build
+YNL_GENS := netdev
+include ynl.mk
+
 $(OUTPUT)/epoll_busy_poll: LDLIBS += -lcap
 $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto
diff --git a/tools/testing/selftests/net/ncdevmem.c b/tools/testing/selftests/net/ncdevmem.c
new file mode 100644
index 000000000000..64d6805381c5
--- /dev/null
+++ b/tools/testing/selftests/net/ncdevmem.c
@@ -0,0 +1,570 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <linux/uio.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#define __iovec_defined
+#include <fcntl.h>
+#include <malloc.h>
+#include <error.h>
+
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+
+#include <linux/memfd.h>
+#include <linux/dma-buf.h>
+#include <linux/udmabuf.h>
+#include <libmnl/libmnl.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+#include <linux/genetlink.h>
+#include <linux/netdev.h>
+#include <time.h>
+#include <net/if.h>
+
+#include "netdev-user.h"
+#include <ynl.h>
+
+#define PAGE_SHIFT 12
+#define TEST_PREFIX "ncdevmem"
+#define NUM_PAGES 16000
+
+#ifndef MSG_SOCK_DEVMEM
+#define MSG_SOCK_DEVMEM 0x2000000
+#endif
+
+/*
+ * tcpdevmem netcat. Works similarly to netcat but does device memory TCP
+ * instead of regular TCP. Uses udmabuf to mock a dmabuf provider.
+ *
+ * Usage:
+ *
+ *	On server:
+ *	ncdevmem -s <server IP> -c <client IP> -f eth1 -l -p 5201 -v 7
+ *
+ *	On client:
+ *	yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
+ *		tr \\n \\0 | \
+ *		head -c 5G | \
+ *		nc <server IP> 5201 -p 5201
+ *
+ * Note this is compatible with regular netcat. i.e. the sender or receiver can
+ * be replaced with regular netcat to test the RX or TX path in isolation.
+ */
+
+static char *server_ip = "192.168.1.4";
+static char *client_ip = "192.168.1.2";
+static char *port = "5201";
+static size_t do_validation;
+static int start_queue = 8;
+static int num_queues = 8;
+static char *ifname = "eth1";
+static unsigned int ifindex;
+static unsigned int dmabuf_id;
+
+void print_bytes(void *ptr, size_t size)
+{
+	unsigned char *p = ptr;
+	int i;
+
+	for (i = 0; i < size; i++)
+		printf("%02hhX ", p[i]);
+	printf("\n");
+}
+
+void print_nonzero_bytes(void *ptr, size_t size)
+{
+	unsigned char *p = ptr;
+	unsigned int i;
+
+	for (i = 0; i < size; i++)
+		putchar(p[i]);
+	printf("\n");
+}
+
+void validate_buffer(void *line, size_t size)
+{
+	static unsigned char seed = 1;
+	unsigned char *ptr = line;
+	int errors = 0;
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		if (ptr[i] != seed) {
+			fprintf(stderr,
+				"Failed validation: expected=%u, actual=%u, index=%lu\n",
+				seed, ptr[i], i);
+			errors++;
+			if (errors > 20)
+				error(1, 0, "validation failed.");
+		}
+		seed++;
+		if (seed == do_validation)
+			seed = 0;
+	}
+
+	fprintf(stdout, "Validated buffer\n");
+}
+
+#define run_command(cmd, ...)                                           \
+	({                                                              \
+		char command[256];                                      \
+		memset(command, 0, sizeof(command));                    \
+		snprintf(command, sizeof(command), cmd, ##__VA_ARGS__); \
+		printf("Running: %s\n", command);                       \
+		system(command);                                        \
+	})
+
+static int reset_flow_steering(void)
+{
+	int ret = 0;
+
+	ret = run_command("sudo ethtool -K %s ntuple off", ifname);
+	if (ret)
+		return ret;
+
+	return run_command("sudo ethtool -K %s ntuple on", ifname);
+}
+
+static int configure_headersplit(bool on)
+{
+	return run_command("sudo ethtool -G %s tcp-data-split %s", ifname,
+			   on ? "on" : "off");
+}
+
+static int configure_rss(void)
+{
+	return run_command("sudo ethtool -X %s equal %d", ifname, start_queue);
+}
+
+static int configure_channels(unsigned int rx, unsigned int tx)
+{
+	return run_command("sudo ethtool -L %s rx %u tx %u", ifname, rx, tx);
+}
+
+static int configure_flow_steering(void)
+{
+	return run_command("sudo ethtool -N %s flow-type tcp4 src-ip %s dst-ip %s src-port %s dst-port %s queue %d",
+			   ifname, client_ip, server_ip, port, port, start_queue);
+}
+
+static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct netdev_queue_id *queues,
+			 unsigned int n_queue_index, struct ynl_sock **ys)
+{
+	struct netdev_bind_rx_req *req = NULL;
+	struct netdev_bind_rx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_rx_req_alloc();
+	netdev_bind_rx_req_set_ifindex(req, ifindex);
+	netdev_bind_rx_req_set_fd(req, dmabuf_fd);
+	__netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
+
+	rsp = netdev_bind_rx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_rx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	printf("got dmabuf id=%d\n", rsp->id);
+	dmabuf_id = rsp->id;
+
+	netdev_bind_rx_req_free(req);
+	netdev_bind_rx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_rx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
+static void create_udmabuf(int *devfd, int *memfd, int *buf, size_t dmabuf_size)
+{
+	struct udmabuf_create create;
+	int ret;
+
+	*devfd = open("/dev/udmabuf", O_RDWR);
+	if (*devfd < 0) {
+		error(70, 0,
+		      "%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
+		      TEST_PREFIX);
+	}
+
+	*memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
+	if (*memfd < 0)
+		error(70, 0, "%s: [skip,no-memfd]\n", TEST_PREFIX);
+
+	/* Required for udmabuf */
+	ret = fcntl(*memfd, F_ADD_SEALS, F_SEAL_SHRINK);
+	if (ret < 0)
+		error(73, 0, "%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+
+	ret = ftruncate(*memfd, dmabuf_size);
+	if (ret == -1)
+		error(74, 0, "%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+
+	memset(&create, 0, sizeof(create));
+
+	create.memfd = *memfd;
+	create.offset = 0;
+	create.size = dmabuf_size;
+	*buf = ioctl(*devfd, UDMABUF_CREATE, &create);
+	if (*buf < 0)
+		error(75, 0, "%s: [FAIL, create udmabuf]\n", TEST_PREFIX);
+}
+
+int do_server(void)
+{
+	char ctrl_data[sizeof(int) * 20000];
+	struct netdev_queue_id *queues;
+	size_t non_page_aligned_frags = 0;
+	struct sockaddr_in client_addr;
+	struct sockaddr_in server_sin;
+	size_t page_aligned_frags = 0;
+	int devfd, memfd, buf, ret;
+	size_t total_received = 0;
+	socklen_t client_addr_len;
+	bool is_devmem = false;
+	char *buf_mem = NULL;
+	struct ynl_sock *ys;
+	size_t dmabuf_size;
+	char iobuf[819200];
+	char buffer[256];
+	int socket_fd;
+	int client_fd;
+	size_t i = 0;
+	int opt = 1;
+
+	dmabuf_size = getpagesize() * NUM_PAGES;
+
+	create_udmabuf(&devfd, &memfd, &buf, dmabuf_size);
+
+	if (reset_flow_steering())
+		error(1, 0, "Failed to reset flow steering\n");
+
+	/* Configure RSS to divert all traffic from our devmem queues */
+	if (configure_rss())
+		error(1, 0, "Failed to configure rss\n");
+
+	/* Flow steer our devmem flows to start_queue */
+	if (configure_flow_steering())
+		error(1, 0, "Failed to configure flow steering\n");
+
+	sleep(1);
+
+	queues = malloc(sizeof(*queues) * num_queues);
+
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	buf_mem = mmap(NULL, dmabuf_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		       buf, 0);
+	if (buf_mem == MAP_FAILED)
+		error(1, 0, "mmap()");
+
+	server_sin.sin_family = AF_INET;
+	server_sin.sin_port = htons(atoi(port));
+
+	ret = inet_pton(server_sin.sin_family, server_ip, &server_sin.sin_addr);
+	if (socket < 0)
+		error(79, 0, "%s: [FAIL, create socket]\n", TEST_PREFIX);
+
+	socket_fd = socket(server_sin.sin_family, SOCK_STREAM, 0);
+	if (socket < 0)
+		error(errno, errno, "%s: [FAIL, create socket]\n", TEST_PREFIX);
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEPORT, &opt,
+			 sizeof(opt));
+	if (ret)
+		error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_REUSEADDR, &opt,
+			 sizeof(opt));
+	if (ret)
+		error(errno, errno, "%s: [FAIL, set sock opt]\n", TEST_PREFIX);
+
+	printf("binding to address %s:%d\n", server_ip,
+	       ntohs(server_sin.sin_port));
+
+	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret)
+		error(errno, errno, "%s: [FAIL, bind]\n", TEST_PREFIX);
+
+	ret = listen(socket_fd, 1);
+	if (ret)
+		error(errno, errno, "%s: [FAIL, listen]\n", TEST_PREFIX);
+
+	client_addr_len = sizeof(client_addr);
+
+	inet_ntop(server_sin.sin_family, &server_sin.sin_addr, buffer,
+		  sizeof(buffer));
+	printf("Waiting or connection on %s:%d\n", buffer,
+	       ntohs(server_sin.sin_port));
+	client_fd = accept(socket_fd, &client_addr, &client_addr_len);
+
+	inet_ntop(client_addr.sin_family, &client_addr.sin_addr, buffer,
+		  sizeof(buffer));
+	printf("Got connection from %s:%d\n", buffer,
+	       ntohs(client_addr.sin_port));
+
+	while (1) {
+		struct iovec iov = { .iov_base = iobuf,
+				     .iov_len = sizeof(iobuf) };
+		struct dmabuf_cmsg *dmabuf_cmsg = NULL;
+		struct dma_buf_sync sync = { 0 };
+		struct cmsghdr *cm = NULL;
+		struct msghdr msg = { 0 };
+		struct dmabuf_token token;
+		ssize_t ret;
+
+		is_devmem = false;
+		printf("\n\n");
+
+		msg.msg_iov = &iov;
+		msg.msg_iovlen = 1;
+		msg.msg_control = ctrl_data;
+		msg.msg_controllen = sizeof(ctrl_data);
+		ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM);
+		printf("recvmsg ret=%ld\n", ret);
+		if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK))
+			continue;
+		if (ret < 0) {
+			perror("recvmsg");
+			continue;
+		}
+		if (ret == 0) {
+			printf("client exited\n");
+			goto cleanup;
+		}
+
+		i++;
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_SOCKET ||
+			    (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
+			     cm->cmsg_type != SCM_DEVMEM_LINEAR)) {
+				fprintf(stdout, "skipping non-devmem cmsg\n");
+				continue;
+			}
+
+			dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm);
+			is_devmem = true;
+
+			if (cm->cmsg_type == SCM_DEVMEM_LINEAR) {
+				/* TODO: process data copied from skb's linear
+				 * buffer.
+				 */
+				fprintf(stdout,
+					"SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n",
+					dmabuf_cmsg->frag_size);
+
+				continue;
+			}
+
+			token.token_start = dmabuf_cmsg->frag_token;
+			token.token_count = 1;
+
+			total_received += dmabuf_cmsg->frag_size;
+			printf("received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n",
+			       dmabuf_cmsg->frag_offset >> PAGE_SHIFT,
+			       dmabuf_cmsg->frag_offset % getpagesize(),
+			       dmabuf_cmsg->frag_offset, dmabuf_cmsg->frag_size,
+			       dmabuf_cmsg->frag_token, total_received,
+			       dmabuf_cmsg->dmabuf_id);
+
+			if (dmabuf_cmsg->dmabuf_id != dmabuf_id)
+				error(1, 0,
+				      "received on wrong dmabuf_id: flow steering error\n");
+
+			if (dmabuf_cmsg->frag_size % getpagesize())
+				non_page_aligned_frags++;
+			else
+				page_aligned_frags++;
+
+			sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_START;
+			ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync);
+
+			if (do_validation)
+				validate_buffer(
+					((unsigned char *)buf_mem) +
+						dmabuf_cmsg->frag_offset,
+					dmabuf_cmsg->frag_size);
+			else
+				print_nonzero_bytes(
+					((unsigned char *)buf_mem) +
+						dmabuf_cmsg->frag_offset,
+					dmabuf_cmsg->frag_size);
+
+			sync.flags = DMA_BUF_SYNC_READ | DMA_BUF_SYNC_END;
+			ioctl(buf, DMA_BUF_IOCTL_SYNC, &sync);
+
+			ret = setsockopt(client_fd, SOL_SOCKET,
+					 SO_DEVMEM_DONTNEED, &token,
+					 sizeof(token));
+			if (ret != 1)
+				error(1, 0,
+				      "SO_DEVMEM_DONTNEED not enough tokens");
+		}
+		if (!is_devmem)
+			error(1, 0, "flow steering error\n");
+
+		printf("total_received=%lu\n", total_received);
+	}
+
+	fprintf(stdout, "%s: ok\n", TEST_PREFIX);
+
+	fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+		page_aligned_frags, non_page_aligned_frags);
+
+	fprintf(stdout, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+		page_aligned_frags, non_page_aligned_frags);
+
+cleanup:
+
+	munmap(buf_mem, dmabuf_size);
+	close(client_fd);
+	close(socket_fd);
+	close(buf);
+	close(memfd);
+	close(devfd);
+	ynl_sock_destroy(ys);
+
+	return 0;
+}
+
+void run_devmem_tests(void)
+{
+	struct netdev_queue_id *queues;
+	int devfd, memfd, buf;
+	struct ynl_sock *ys;
+	size_t dmabuf_size;
+	size_t i = 0;
+
+	dmabuf_size = getpagesize() * NUM_PAGES;
+
+	create_udmabuf(&devfd, &memfd, &buf, dmabuf_size);
+
+	/* Configure RSS to divert all traffic from our devmem queues */
+	if (configure_rss())
+		error(1, 0, "rss error\n");
+
+	queues = calloc(num_queues, sizeof(*queues));
+
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to configure header split\n");
+
+	if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+		error(1, 0, "Binding empty queues array should have failed\n");
+
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	if (configure_headersplit(0))
+		error(1, 0, "Failed to configure header split\n");
+
+	if (!bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+		error(1, 0, "Configure dmabuf with header split off should have failed\n");
+
+	if (configure_headersplit(1))
+		error(1, 0, "Failed to configure header split\n");
+
+	for (i = 0; i < num_queues; i++) {
+		queues[i]._present.type = 1;
+		queues[i]._present.id = 1;
+		queues[i].type = NETDEV_QUEUE_TYPE_RX;
+		queues[i].id = start_queue + i;
+	}
+
+	if (bind_rx_queue(ifindex, buf, queues, num_queues, &ys))
+		error(1, 0, "Failed to bind\n");
+
+	/* Deactivating a bound queue should not be legal */
+	if (!configure_channels(num_queues, num_queues - 1))
+		error(1, 0, "Deactivating a bound queue should be illegal.\n");
+
+	/* Closing the netlink socket does an implicit unbind */
+	ynl_sock_destroy(ys);
+}
+
+int main(int argc, char *argv[])
+{
+	int is_server = 0, opt;
+
+	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:")) != -1) {
+		switch (opt) {
+		case 'l':
+			is_server = 1;
+			break;
+		case 's':
+			server_ip = optarg;
+			break;
+		case 'c':
+			client_ip = optarg;
+			break;
+		case 'p':
+			port = optarg;
+			break;
+		case 'v':
+			do_validation = atoll(optarg);
+			break;
+		case 'q':
+			num_queues = atoi(optarg);
+			break;
+		case 't':
+			start_queue = atoi(optarg);
+			break;
+		case 'f':
+			ifname = optarg;
+			break;
+		case '?':
+			printf("unknown option: %c\n", optopt);
+			break;
+		}
+	}
+
+	ifindex = if_nametoindex(ifname);
+
+	for (; optind < argc; optind++)
+		printf("extra arguments: %s\n", argv[optind]);
+
+	run_devmem_tests();
+
+	if (is_server)
+		return do_server();
+
+	return 0;
+}
-- 
cgit v1.3-3-g829e


From d0caf9876a1c9f844307effb598ad1312d9e0025 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Tue, 10 Sep 2024 17:14:57 +0000
Subject: netdev: add dmabuf introspection

Add dmabuf information to page_pool stats:

$ ./cli.py --spec ../netlink/specs/netdev.yaml --dump page-pool-get
...
 {'dmabuf': 10,
  'id': 456,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 455,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 454,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 453,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 452,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 451,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 450,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},
 {'dmabuf': 10,
  'id': 449,
  'ifindex': 3,
  'inflight': 1023,
  'inflight-mem': 4190208},

And queue stats:

$ ./cli.py --spec ../netlink/specs/netdev.yaml --dump queue-get
...
{'dmabuf': 10, 'id': 8, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 9, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 10, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 11, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 12, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 13, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 14, 'ifindex': 3, 'type': 'rx'},
{'dmabuf': 10, 'id': 15, 'ifindex': 3, 'type': 'rx'},

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-14-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 10 ++++++++++
 include/uapi/linux/netdev.h             |  2 ++
 net/core/netdev-genl.c                  |  7 +++++++
 net/core/page_pool_user.c               |  5 +++++
 tools/include/uapi/linux/netdev.h       |  2 ++
 5 files changed, 26 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 0c747530c275..08412c279297 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -167,6 +167,10 @@ attribute-sets:
           "re-attached", they are just waiting to disappear.
           Attribute is absent if Page Pool has not been detached, and
           can still be used to allocate new memory.
+      -
+        name: dmabuf
+        doc: ID of the dmabuf this page-pool is attached to.
+        type: u32
   -
     name: page-pool-info
     subset-of: page-pool
@@ -268,6 +272,10 @@ attribute-sets:
         name: napi-id
         doc: ID of the NAPI instance which services this queue.
         type: u32
+      -
+        name: dmabuf
+        doc: ID of the dmabuf attached to this queue, if any.
+        type: u32
 
   -
     name: qstats
@@ -543,6 +551,7 @@ operations:
             - inflight
             - inflight-mem
             - detach-time
+            - dmabuf
       dump:
         reply: *pp-reply
       config-cond: page-pool
@@ -607,6 +616,7 @@ operations:
             - type
             - napi-id
             - ifindex
+            - dmabuf
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 91bf3ecc5f1d..7c308f04e7a0 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -93,6 +93,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT,
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
+	NETDEV_A_PAGE_POOL_DMABUF,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -131,6 +132,7 @@ enum {
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
+	NETDEV_A_QUEUE_DMABUF,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 9153a8ab0cf8..1cb954f2d39e 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -295,6 +295,7 @@ static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
 {
+	struct net_devmem_dmabuf_binding *binding;
 	struct netdev_rx_queue *rxq;
 	struct netdev_queue *txq;
 	void *hdr;
@@ -314,6 +315,12 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
 					     rxq->napi->napi_id))
 			goto nla_put_failure;
+
+		binding = rxq->mp_params.mp_priv;
+		if (binding &&
+		    nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id))
+			goto nla_put_failure;
+
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index cd6267ba6fa3..48335766c1bf 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -9,6 +9,7 @@
 #include <net/page_pool/types.h>
 #include <net/sock.h>
 
+#include "devmem.h"
 #include "page_pool_priv.h"
 #include "netdev-genl-gen.h"
 
@@ -213,6 +214,7 @@ static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
 {
+	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
 	size_t inflight, refsz;
 	void *hdr;
 
@@ -242,6 +244,9 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 			 pool->user.detach_time))
 		goto err_cancel;
 
+	if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id))
+		goto err_cancel;
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 91bf3ecc5f1d..7c308f04e7a0 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -93,6 +93,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT,
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
+	NETDEV_A_PAGE_POOL_DMABUF,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -131,6 +132,7 @@ enum {
 	NETDEV_A_QUEUE_IFINDEX,
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
+	NETDEV_A_QUEUE_DMABUF,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
-- 
cgit v1.3-3-g829e


From b3e33f2c54c68318ccf06473a84c79f3c7d29cc1 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:01 +0530
Subject: Documentation: networking: add OPEN Alliance 10BASE-T1x MAC-PHY
 serial interface

The IEEE 802.3cg project defines two 10 Mbit/s PHYs operating over a
single pair of conductors. The 10BASE-T1L (Clause 146) is a long reach
PHY supporting full duplex point-to-point operation over 1 km of single
balanced pair of conductors. The 10BASE-T1S (Clause 147) is a short reach
PHY supporting full / half duplex point-to-point operation over 15 m of
single balanced pair of conductors, or half duplex multidrop bus
operation over 25 m of single balanced pair of conductors.

Furthermore, the IEEE 802.3cg project defines the new Physical Layer
Collision Avoidance (PLCA) Reconciliation Sublayer (Clause 148) meant to
provide improved determinism to the CSMA/CD media access method. PLCA
works in conjunction with the 10BASE-T1S PHY operating in multidrop mode.

The aforementioned PHYs are intended to cover the low-speed / low-cost
applications in industrial and automotive environment. The large number
of pins (16) required by the MII interface, which is specified by the
IEEE 802.3 in Clause 22, is one of the major cost factors that need to be
addressed to fulfil this objective.

The MAC-PHY solution integrates an IEEE Clause 4 MAC and a 10BASE-T1x PHY
exposing a low pin count Serial Peripheral Interface (SPI) to the host
microcontroller. This also enables the addition of Ethernet functionality
to existing low-end microcontrollers which do not integrate a MAC
controller.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-2-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/index.rst            |   1 +
 Documentation/networking/oa-tc6-framework.rst | 497 ++++++++++++++++++++++++++
 MAINTAINERS                                   |   6 +
 3 files changed, 504 insertions(+)
 create mode 100644 Documentation/networking/oa-tc6-framework.rst

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 08f437c326ab..803dfc1efb75 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -88,6 +88,7 @@ Contents:
    nexthop-group-resilient
    nf_conntrack-sysctl
    nf_flowtable
+   oa-tc6-framework
    openvswitch
    operstates
    packet_mmap
diff --git a/Documentation/networking/oa-tc6-framework.rst b/Documentation/networking/oa-tc6-framework.rst
new file mode 100644
index 000000000000..fe2aabde923a
--- /dev/null
+++ b/Documentation/networking/oa-tc6-framework.rst
@@ -0,0 +1,497 @@
+.. SPDX-License-Identifier: GPL-2.0+
+
+=========================================================================
+OPEN Alliance 10BASE-T1x MAC-PHY Serial Interface (TC6) Framework Support
+=========================================================================
+
+Introduction
+------------
+
+The IEEE 802.3cg project defines two 10 Mbit/s PHYs operating over a
+single pair of conductors. The 10BASE-T1L (Clause 146) is a long reach
+PHY supporting full duplex point-to-point operation over 1 km of single
+balanced pair of conductors. The 10BASE-T1S (Clause 147) is a short reach
+PHY supporting full / half duplex point-to-point operation over 15 m of
+single balanced pair of conductors, or half duplex multidrop bus
+operation over 25 m of single balanced pair of conductors.
+
+Furthermore, the IEEE 802.3cg project defines the new Physical Layer
+Collision Avoidance (PLCA) Reconciliation Sublayer (Clause 148) meant to
+provide improved determinism to the CSMA/CD media access method. PLCA
+works in conjunction with the 10BASE-T1S PHY operating in multidrop mode.
+
+The aforementioned PHYs are intended to cover the low-speed / low-cost
+applications in industrial and automotive environment. The large number
+of pins (16) required by the MII interface, which is specified by the
+IEEE 802.3 in Clause 22, is one of the major cost factors that need to be
+addressed to fulfil this objective.
+
+The MAC-PHY solution integrates an IEEE Clause 4 MAC and a 10BASE-T1x PHY
+exposing a low pin count Serial Peripheral Interface (SPI) to the host
+microcontroller. This also enables the addition of Ethernet functionality
+to existing low-end microcontrollers which do not integrate a MAC
+controller.
+
+Overview
+--------
+
+The MAC-PHY is specified to carry both data (Ethernet frames) and control
+(register access) transactions over a single full-duplex serial peripheral
+interface.
+
+Protocol Overview
+-----------------
+
+Two types of transactions are defined in the protocol: data transactions
+for Ethernet frame transfers and control transactions for register
+read/write transfers. A chunk is the basic element of data transactions
+and is composed of 4 bytes of overhead plus 64 bytes of payload size for
+each chunk. Ethernet frames are transferred over one or more data chunks.
+Control transactions consist of one or more register read/write control
+commands.
+
+SPI transactions are initiated by the SPI host with the assertion of CSn
+low to the MAC-PHY and ends with the deassertion of CSn high. In between
+each SPI transaction, the SPI host may need time for additional
+processing and to setup the next SPI data or control transaction.
+
+SPI data transactions consist of an equal number of transmit (TX) and
+receive (RX) chunks. Chunks in both transmit and receive directions may
+or may not contain valid frame data independent from each other, allowing
+for the simultaneous transmission and reception of different length
+frames.
+
+Each transmit data chunk begins with a 32-bit data header followed by a
+data chunk payload on MOSI. The data header indicates whether transmit
+frame data is present and provides the information to determine which
+bytes of the payload contain valid frame data.
+
+In parallel, receive data chunks are received on MISO. Each receive data
+chunk consists of a data chunk payload ending with a 32-bit data footer.
+The data footer indicates if there is receive frame data present within
+the payload or not and provides the information to determine which bytes
+of the payload contain valid frame data.
+
+Reference
+---------
+
+10BASE-T1x MAC-PHY Serial Interface Specification,
+
+Link: https://opensig.org/download/document/OPEN_Alliance_10BASET1x_MAC-PHY_Serial_Interface_V1.1.pdf
+
+Hardware Architecture
+---------------------
+
+.. code-block:: none
+
+  +----------+      +-------------------------------------+
+  |          |      |                MAC-PHY              |
+  |          |<---->| +-----------+  +-------+  +-------+ |
+  | SPI Host |      | | SPI Slave |  |  MAC  |  |  PHY  | |
+  |          |      | +-----------+  +-------+  +-------+ |
+  +----------+      +-------------------------------------+
+
+Software Architecture
+---------------------
+
+.. code-block:: none
+
+  +----------------------------------------------------------+
+  |                 Networking Subsystem                     |
+  +----------------------------------------------------------+
+            / \                             / \
+             |                               |
+             |                               |
+            \ /                              |
+  +----------------------+     +-----------------------------+
+  |     MAC Driver       |<--->| OPEN Alliance TC6 Framework |
+  +----------------------+     +-----------------------------+
+            / \                             / \
+             |                               |
+             |                               |
+             |                              \ /
+  +----------------------------------------------------------+
+  |                    SPI Subsystem                         |
+  +----------------------------------------------------------+
+                          / \
+                           |
+                           |
+                          \ /
+  +----------------------------------------------------------+
+  |                10BASE-T1x MAC-PHY Device                 |
+  +----------------------------------------------------------+
+
+Implementation
+--------------
+
+MAC Driver
+~~~~~~~~~~
+
+- Probed by SPI subsystem.
+
+- Initializes OA TC6 framework for the MAC-PHY.
+
+- Registers and configures the network device.
+
+- Sends the tx ethernet frames from n/w subsystem to OA TC6 framework.
+
+OPEN Alliance TC6 Framework
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+- Initializes PHYLIB interface.
+
+- Registers mac-phy interrupt.
+
+- Performs mac-phy register read/write operation using the control
+  transaction protocol specified in the OPEN Alliance 10BASE-T1x MAC-PHY
+  Serial Interface specification.
+
+- Performs Ethernet frames transaction using the data transaction protocol
+  for Ethernet frames specified in the OPEN Alliance 10BASE-T1x MAC-PHY
+  Serial Interface specification.
+
+- Forwards the received Ethernet frame from 10Base-T1x MAC-PHY to n/w
+  subsystem.
+
+Data Transaction
+~~~~~~~~~~~~~~~~
+
+The Ethernet frames that are typically transferred from the SPI host to
+the MAC-PHY will be converted into multiple transmit data chunks. Each
+transmit data chunk will have a 4 bytes header which contains the
+information needed to determine the validity and the location of the
+transmit frame data within the 64 bytes data chunk payload.
+
+.. code-block:: none
+
+  +---------------------------------------------------+
+  |                     Tx Chunk                      |
+  | +---------------------------+  +----------------+ |   MOSI
+  | | 64 bytes chunk payload    |  | 4 bytes header | |------------>
+  | +---------------------------+  +----------------+ |
+  +---------------------------------------------------+
+
+4 bytes header contains the below fields,
+
+DNC (Bit 31) - Data-Not-Control flag. This flag specifies the type of SPI
+               transaction. For TX data chunks, this bit shall be ’1’.
+               0 - Control command
+               1 - Data chunk
+
+SEQ (Bit 30) - Data Chunk Sequence. This bit is used to indicate an
+               even/odd transmit data chunk sequence to the MAC-PHY.
+
+NORX (Bit 29) - No Receive flag. The SPI host may set this bit to prevent
+                the MAC-PHY from conveying RX data on the MISO for the
+                current chunk (DV = 0 in the footer), indicating that the
+                host would not process it. Typically, the SPI host should
+                set NORX = 0 indicating that it will accept and process
+                any receive frame data within the current chunk.
+
+RSVD (Bit 28..24) - Reserved: All reserved bits shall be ‘0’.
+
+VS (Bit 23..22) - Vendor Specific. These bits are implementation specific.
+                  If the MAC-PHY does not implement these bits, the host
+                  shall set them to ‘0’.
+
+DV (Bit 21) - Data Valid flag. The SPI host uses this bit to indicate
+              whether the current chunk contains valid transmit frame data
+              (DV = 1) or not (DV = 0). When ‘0’, the MAC-PHY ignores the
+              chunk payload. Note that the receive path is unaffected by
+              the setting of the DV bit in the data header.
+
+SV (Bit 20) - Start Valid flag. The SPI host shall set this bit when the
+              beginning of an Ethernet frame is present in the current
+              transmit data chunk payload. Otherwise, this bit shall be
+              zero. This bit is not to be confused with the Start-of-Frame
+              Delimiter (SFD) byte described in IEEE 802.3 [2].
+
+SWO (Bit 19..16) - Start Word Offset. When SV = 1, this field shall
+                   contain the 32-bit word offset into the transmit data
+                   chunk payload that points to the start of a new
+                   Ethernet frame to be transmitted. The host shall write
+                   this field as zero when SV = 0.
+
+RSVD (Bit 15) - Reserved: All reserved bits shall be ‘0’.
+
+EV (Bit 14) - End Valid flag. The SPI host shall set this bit when the end
+              of an Ethernet frame is present in the current transmit data
+              chunk payload. Otherwise, this bit shall be zero.
+
+EBO (Bit 13..8) - End Byte Offset. When EV = 1, this field shall contain
+                  the byte offset into the transmit data chunk payload
+                  that points to the last byte of the Ethernet frame to
+                  transmit. This field shall be zero when EV = 0.
+
+TSC (Bit 7..6) - Timestamp Capture. Request a timestamp capture when the
+                 frame is transmitted onto the network.
+                 00 - Do not capture a timestamp
+                 01 - Capture timestamp into timestamp capture register A
+                 10 - Capture timestamp into timestamp capture register B
+                 11 - Capture timestamp into timestamp capture register C
+
+RSVD (Bit 5..1) - Reserved: All reserved bits shall be ‘0’.
+
+P (Bit 0) - Parity. Parity bit calculated over the transmit data header.
+            Method used is odd parity.
+
+The number of buffers available in the MAC-PHY to store the incoming
+transmit data chunk payloads is represented as transmit credits. The
+available transmit credits in the MAC-PHY can be read either from the
+Buffer Status Register or footer (Refer below for the footer info)
+received from the MAC-PHY. The SPI host should not write more data chunks
+than the available transmit credits as this will lead to transmit buffer
+overflow error.
+
+In case the previous data footer had no transmit credits available and
+once the transmit credits become available for transmitting transmit data
+chunks, the MAC-PHY interrupt is asserted to SPI host. On reception of the
+first data header this interrupt will be deasserted and the received
+footer for the first data chunk will have the transmit credits available
+information.
+
+The Ethernet frames that are typically transferred from MAC-PHY to SPI
+host will be sent as multiple receive data chunks. Each receive data
+chunk will have 64 bytes of data chunk payload followed by 4 bytes footer
+which contains the information needed to determine the validity and the
+location of the receive frame data within the 64 bytes data chunk payload.
+
+.. code-block:: none
+
+  +---------------------------------------------------+
+  |                     Rx Chunk                      |
+  | +----------------+  +---------------------------+ |   MISO
+  | | 4 bytes footer |  | 64 bytes chunk payload    | |------------>
+  | +----------------+  +---------------------------+ |
+  +---------------------------------------------------+
+
+4 bytes footer contains the below fields,
+
+EXST (Bit 31) - Extended Status. This bit is set when any bit in the
+                STATUS0 or STATUS1 registers are set and not masked.
+
+HDRB (Bit 30) - Received Header Bad. When set, indicates that the MAC-PHY
+                received a control or data header with a parity error.
+
+SYNC (Bit 29) - Configuration Synchronized flag. This bit reflects the
+                state of the SYNC bit in the CONFIG0 configuration
+                register (see Table 12). A zero indicates that the MAC-PHY
+                configuration may not be as expected by the SPI host.
+                Following configuration, the SPI host sets the
+                corresponding bitin the configuration register which is
+                reflected in this field.
+
+RCA (Bit 28..24) - Receive Chunks Available. The RCA field indicates to
+                   the SPI host the minimum number of additional receive
+                   data chunks of frame data that are available for
+                   reading beyond the current receive data chunk. This
+                   field is zero when there is no receive frame data
+                   pending in the MAC-PHY’s buffer for reading.
+
+VS (Bit 23..22) - Vendor Specific. These bits are implementation specific.
+                  If not implemented, the MAC-PHY shall set these bits to
+                  ‘0’.
+
+DV (Bit 21) - Data Valid flag. The MAC-PHY uses this bit to indicate
+              whether the current receive data chunk contains valid
+              receive frame data (DV = 1) or not (DV = 0). When ‘0’, the
+              SPI host shall ignore the chunk payload.
+
+SV (Bit 20) - Start Valid flag. The MAC-PHY sets this bit when the current
+              chunk payload contains the start of an Ethernet frame.
+              Otherwise, this bit is zero. The SV bit is not to be
+              confused with the Start-of-Frame Delimiter (SFD) byte
+              described in IEEE 802.3 [2].
+
+SWO (Bit 19..16) - Start Word Offset. When SV = 1, this field contains the
+                   32-bit word offset into the receive data chunk payload
+                   containing the first byte of a new received Ethernet
+                   frame. When a receive timestamp has been added to the
+                   beginning of the received Ethernet frame (RTSA = 1)
+                   then SWO points to the most significant byte of the
+                   timestamp. This field will be zero when SV = 0.
+
+FD (Bit 15) - Frame Drop. When set, this bit indicates that the MAC has
+              detected a condition for which the SPI host should drop the
+              received Ethernet frame. This bit is only valid at the end
+              of a received Ethernet frame (EV = 1) and shall be zero at
+              all other times.
+
+EV (Bit 14) - End Valid flag. The MAC-PHY sets this bit when the end of a
+              received Ethernet frame is present in this receive data
+              chunk payload.
+
+EBO (Bit 13..8) - End Byte Offset: When EV = 1, this field contains the
+                  byte offset into the receive data chunk payload that
+                  locates the last byte of the received Ethernet frame.
+                  This field is zero when EV = 0.
+
+RTSA (Bit 7) - Receive Timestamp Added. This bit is set when a 32-bit or
+               64-bit timestamp has been added to the beginning of the
+               received Ethernet frame. The MAC-PHY shall set this bit to
+               zero when SV = 0.
+
+RTSP (Bit 6) - Receive Timestamp Parity. Parity bit calculated over the
+               32-bit/64-bit timestamp added to the beginning of the
+               received Ethernet frame. Method used is odd parity. The
+               MAC-PHY shall set this bit to zero when RTSA = 0.
+
+TXC (Bit 5..1) - Transmit Credits. This field contains the minimum number
+                 of transmit data chunks of frame data that the SPI host
+                 can write in a single transaction without incurring a
+                 transmit buffer overflow error.
+
+P (Bit 0) - Parity. Parity bit calculated over the receive data footer.
+            Method used is odd parity.
+
+SPI host will initiate the data receive transaction based on the receive
+chunks available in the MAC-PHY which is provided in the receive chunk
+footer (RCA - Receive Chunks Available). SPI host will create data invalid
+transmit data chunks (empty chunks) or data valid transmit data chunks in
+case there are valid Ethernet frames to transmit to the MAC-PHY. The
+receive chunks available in MAC-PHY can be read either from the Buffer
+Status Register or footer.
+
+In case the previous data footer had no receive data chunks available and
+once the receive data chunks become available again for reading, the
+MAC-PHY interrupt is asserted to SPI host. On reception of the first data
+header this interrupt will be deasserted and the received footer for the
+first data chunk will have the receive chunks available information.
+
+MAC-PHY Interrupt
+~~~~~~~~~~~~~~~~~
+
+The MAC-PHY interrupt is asserted when the following conditions are met.
+
+Receive chunks available - This interrupt is asserted when the previous
+data footer had no receive data chunks available and once the receive
+data chunks become available for reading. On reception of the first data
+header this interrupt will be deasserted.
+
+Transmit chunk credits available - This interrupt is asserted when the
+previous data footer indicated no transmit credits available and once the
+transmit credits become available for transmitting transmit data chunks.
+On reception of the first data header this interrupt will be deasserted.
+
+Extended status event - This interrupt is asserted when the previous data
+footer indicated no extended status and once the extended event become
+available. In this case the host should read status #0 register to know
+the corresponding error/event. On reception of the first data header this
+interrupt will be deasserted.
+
+Control Transaction
+~~~~~~~~~~~~~~~~~~~
+
+4 bytes control header contains the below fields,
+
+DNC (Bit 31) - Data-Not-Control flag. This flag specifies the type of SPI
+               transaction. For control commands, this bit shall be ‘0’.
+               0 - Control command
+               1 - Data chunk
+
+HDRB (Bit 30) - Received Header Bad. When set by the MAC-PHY, indicates
+                that a header was received with a parity error. The SPI
+                host should always clear this bit. The MAC-PHY ignores the
+                HDRB value sent by the SPI host on MOSI.
+
+WNR (Bit 29) - Write-Not-Read. This bit indicates if data is to be written
+               to registers (when set) or read from registers
+               (when clear).
+
+AID (Bit 28) - Address Increment Disable. When clear, the address will be
+               automatically post-incremented by one following each
+               register read or write. When set, address auto increment is
+               disabled allowing successive reads and writes to occur at
+               the same register address.
+
+MMS (Bit 27..24) - Memory Map Selector. This field selects the specific
+                   register memory map to access.
+
+ADDR (Bit 23..8) - Address. Address of the first register within the
+                   selected memory map to access.
+
+LEN (Bit 7..1) - Length. Specifies the number of registers to read/write.
+                 This field is interpreted as the number of registers
+                 minus 1 allowing for up to 128 consecutive registers read
+                 or written starting at the address specified in ADDR. A
+                 length of zero shall read or write a single register.
+
+P (Bit 0) - Parity. Parity bit calculated over the control command header.
+            Method used is odd parity.
+
+Control transactions consist of one or more control commands. Control
+commands are used by the SPI host to read and write registers within the
+MAC-PHY. Each control commands are composed of a 4 bytes control command
+header followed by register write data in case of control write command.
+
+The MAC-PHY ignores the final 4 bytes of data from the SPI host at the end
+of the control write command. The control write command is also echoed
+from the MAC-PHY back to the SPI host to identify which register write
+failed in case of any bus errors. The echoed Control write command will
+have the first 4 bytes unused value to be ignored by the SPI host
+followed by 4 bytes echoed control header followed by echoed register
+write data. Control write commands can write either a single register or
+multiple consecutive registers. When multiple consecutive registers are
+written, the address is automatically post-incremented by the MAC-PHY.
+Writing to any unimplemented or undefined registers shall be ignored and
+yield no effect.
+
+The MAC-PHY ignores all data from the SPI host following the control
+header for the remainder of the control read command. The control read
+command is also echoed from the MAC-PHY back to the SPI host to identify
+which register read is failed in case of any bus errors. The echoed
+Control read command will have the first 4 bytes of unused value to be
+ignored by the SPI host followed by 4 bytes echoed control header followed
+by register read data. Control read commands can read either a single
+register or multiple consecutive registers. When multiple consecutive
+registers are read, the address is automatically post-incremented by the
+MAC-PHY. Reading any unimplemented or undefined registers shall return
+zero.
+
+Device drivers API
+==================
+
+The include/linux/oa_tc6.h defines the following functions:
+
+.. c:function:: struct oa_tc6 *oa_tc6_init(struct spi_device *spi, \
+                                           struct net_device *netdev)
+
+Initialize OA TC6 lib.
+
+.. c:function:: void oa_tc6_exit(struct oa_tc6 *tc6)
+
+Free allocated OA TC6 lib.
+
+.. c:function:: int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, \
+                                          u32 value)
+
+Write a single register in the MAC-PHY.
+
+.. c:function:: int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, \
+                                           u32 value[], u8 length)
+
+Writing multiple consecutive registers starting from @address in the MAC-PHY.
+Maximum of 128 consecutive registers can be written starting at @address.
+
+.. c:function:: int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, \
+                                         u32 *value)
+
+Read a single register in the MAC-PHY.
+
+.. c:function:: int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, \
+                                          u32 value[], u8 length)
+
+Reading multiple consecutive registers starting from @address in the MAC-PHY.
+Maximum of 128 consecutive registers can be read starting at @address.
+
+.. c:function:: netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, \
+                                              struct sk_buff *skb);
+
+The transmit Ethernet frame in the skb is or going to be transmitted through
+the MAC-PHY.
+
+.. c:function:: int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6);
+
+Zero align receive frame feature can be enabled to align all receive ethernet
+frames data to start at the beginning of any receive data chunk payload with a
+start word offset (SWO) of zero.
diff --git a/MAINTAINERS b/MAINTAINERS
index 4053168fdc12..c291fe45e191 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17113,6 +17113,12 @@ L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/ulp/opa_vnic
 
+OPEN ALLIANCE 10BASE-T1S MACPHY SERIAL INTERFACE FRAMEWORK
+M:	Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/networking/oa-tc6-framework.rst
+
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Rob Herring <robh@kernel.org>
 M:	Saravana Kannan <saravanak@google.com>
-- 
cgit v1.3-3-g829e


From aa58bec064ab16224645776ce8e0af2fee46136a Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:02 +0530
Subject: net: ethernet: oa_tc6: implement register write operation

Implement register write operation according to the control communication
specified in the OPEN Alliance 10BASE-T1x MACPHY Serial Interface
document. Control write commands are used by the SPI host to write
registers within the MAC-PHY. Each control write commands are composed of
a 32 bits control command header followed by register write data.

The MAC-PHY ignores the final 32 bits of data from the SPI host at the
end of the control write command. The write command and data is also
echoed from the MAC-PHY back to the SPI host to enable the SPI host to
identify which register write failed in the case of any bus errors.
Control write commands can write either a single register or multiple
consecutive registers. When multiple consecutive registers are written,
the address is automatically post-incremented by the MAC-PHY. Writing to
any unimplemented or undefined registers shall be ignored and yield no
effect.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-3-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                   |   2 +
 drivers/net/ethernet/Kconfig  |  11 ++
 drivers/net/ethernet/Makefile |   1 +
 drivers/net/ethernet/oa_tc6.c | 242 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/oa_tc6.h        |  17 +++
 5 files changed, 273 insertions(+)
 create mode 100644 drivers/net/ethernet/oa_tc6.c
 create mode 100644 include/linux/oa_tc6.h

diff --git a/MAINTAINERS b/MAINTAINERS
index c291fe45e191..6c2315c1297c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17118,6 +17118,8 @@ M:	Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/oa-tc6-framework.rst
+F:	drivers/include/linux/oa_tc6.h
+F:	drivers/net/ethernet/oa_tc6.c
 
 OPEN FIRMWARE AND FLATTENED DEVICE TREE
 M:	Rob Herring <robh@kernel.org>
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 0baac25db4f8..9a542e3c9b05 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -158,6 +158,17 @@ config ETHOC
 	help
 	  Say Y here if you want to use the OpenCores 10/100 Mbps Ethernet MAC.
 
+config OA_TC6
+	tristate "OPEN Alliance TC6 10BASE-T1x MAC-PHY support"
+	depends on SPI
+	select PHYLIB
+	help
+	  This library implements OPEN Alliance TC6 10BASE-T1x MAC-PHY
+	  Serial Interface protocol for supporting 10BASE-T1x MAC-PHYs.
+
+	  To know the implementation details, refer documentation in
+	  <file:Documentation/networking/oa-tc6-framework.rst>.
+
 source "drivers/net/ethernet/packetengines/Kconfig"
 source "drivers/net/ethernet/pasemi/Kconfig"
 source "drivers/net/ethernet/pensando/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index c03203439c0e..99fa180dedb8 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -105,3 +105,4 @@ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/
 obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/
 obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/
 obj-$(CONFIG_NET_VENDOR_PENSANDO) += pensando/
+obj-$(CONFIG_OA_TC6) += oa_tc6.o
diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
new file mode 100644
index 000000000000..24e9fd92d717
--- /dev/null
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface framework
+ *
+ * Author: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/oa_tc6.h>
+
+/* Control command header */
+#define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL	BIT(31)
+#define OA_TC6_CTRL_HEADER_WRITE_NOT_READ	BIT(29)
+#define OA_TC6_CTRL_HEADER_MEM_MAP_SELECTOR	GENMASK(27, 24)
+#define OA_TC6_CTRL_HEADER_ADDR			GENMASK(23, 8)
+#define OA_TC6_CTRL_HEADER_LENGTH		GENMASK(7, 1)
+#define OA_TC6_CTRL_HEADER_PARITY		BIT(0)
+
+#define OA_TC6_CTRL_HEADER_SIZE			4
+#define OA_TC6_CTRL_REG_VALUE_SIZE		4
+#define OA_TC6_CTRL_IGNORED_SIZE		4
+#define OA_TC6_CTRL_MAX_REGISTERS		128
+#define OA_TC6_CTRL_SPI_BUF_SIZE		(OA_TC6_CTRL_HEADER_SIZE +\
+						(OA_TC6_CTRL_MAX_REGISTERS *\
+						OA_TC6_CTRL_REG_VALUE_SIZE) +\
+						OA_TC6_CTRL_IGNORED_SIZE)
+
+/* Internal structure for MAC-PHY drivers */
+struct oa_tc6 {
+	struct spi_device *spi;
+	struct mutex spi_ctrl_lock; /* Protects spi control transfer */
+	void *spi_ctrl_tx_buf;
+	void *spi_ctrl_rx_buf;
+};
+
+enum oa_tc6_header_type {
+	OA_TC6_CTRL_HEADER,
+};
+
+enum oa_tc6_register_op {
+	OA_TC6_CTRL_REG_WRITE = 1,
+};
+
+static int oa_tc6_spi_transfer(struct oa_tc6 *tc6,
+			       enum oa_tc6_header_type header_type, u16 length)
+{
+	struct spi_transfer xfer = { 0 };
+	struct spi_message msg;
+
+	xfer.tx_buf = tc6->spi_ctrl_tx_buf;
+	xfer.rx_buf = tc6->spi_ctrl_rx_buf;
+	xfer.len = length;
+
+	spi_message_init(&msg);
+	spi_message_add_tail(&xfer, &msg);
+
+	return spi_sync(tc6->spi, &msg);
+}
+
+static int oa_tc6_get_parity(u32 p)
+{
+	/* Public domain code snippet, lifted from
+	 * http://www-graphics.stanford.edu/~seander/bithacks.html
+	 */
+	p ^= p >> 1;
+	p ^= p >> 2;
+	p = (p & 0x11111111U) * 0x11111111U;
+
+	/* Odd parity is used here */
+	return !((p >> 28) & 1);
+}
+
+static __be32 oa_tc6_prepare_ctrl_header(u32 addr, u8 length,
+					 enum oa_tc6_register_op reg_op)
+{
+	u32 header;
+
+	header = FIELD_PREP(OA_TC6_CTRL_HEADER_DATA_NOT_CTRL,
+			    OA_TC6_CTRL_HEADER) |
+		 FIELD_PREP(OA_TC6_CTRL_HEADER_WRITE_NOT_READ, reg_op) |
+		 FIELD_PREP(OA_TC6_CTRL_HEADER_MEM_MAP_SELECTOR, addr >> 16) |
+		 FIELD_PREP(OA_TC6_CTRL_HEADER_ADDR, addr) |
+		 FIELD_PREP(OA_TC6_CTRL_HEADER_LENGTH, length - 1);
+	header |= FIELD_PREP(OA_TC6_CTRL_HEADER_PARITY,
+			     oa_tc6_get_parity(header));
+
+	return cpu_to_be32(header);
+}
+
+static void oa_tc6_update_ctrl_write_data(struct oa_tc6 *tc6, u32 value[],
+					  u8 length)
+{
+	__be32 *tx_buf = tc6->spi_ctrl_tx_buf + OA_TC6_CTRL_HEADER_SIZE;
+
+	for (int i = 0; i < length; i++)
+		*tx_buf++ = cpu_to_be32(value[i]);
+}
+
+static u16 oa_tc6_calculate_ctrl_buf_size(u8 length)
+{
+	/* Control command consists 4 bytes header + 4 bytes register value for
+	 * each register + 4 bytes ignored value.
+	 */
+	return OA_TC6_CTRL_HEADER_SIZE + OA_TC6_CTRL_REG_VALUE_SIZE * length +
+	       OA_TC6_CTRL_IGNORED_SIZE;
+}
+
+static void oa_tc6_prepare_ctrl_spi_buf(struct oa_tc6 *tc6, u32 address,
+					u32 value[], u8 length,
+					enum oa_tc6_register_op reg_op)
+{
+	__be32 *tx_buf = tc6->spi_ctrl_tx_buf;
+
+	*tx_buf = oa_tc6_prepare_ctrl_header(address, length, reg_op);
+
+	oa_tc6_update_ctrl_write_data(tc6, value, length);
+}
+
+static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size)
+{
+	u8 *tx_buf = tc6->spi_ctrl_tx_buf;
+	u8 *rx_buf = tc6->spi_ctrl_rx_buf;
+
+	rx_buf += OA_TC6_CTRL_IGNORED_SIZE;
+
+	/* The echoed control write must match with the one that was
+	 * transmitted.
+	 */
+	if (memcmp(tx_buf, rx_buf, size - OA_TC6_CTRL_IGNORED_SIZE))
+		return -EPROTO;
+
+	return 0;
+}
+
+static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[],
+			       u8 length, enum oa_tc6_register_op reg_op)
+{
+	u16 size;
+	int ret;
+
+	/* Prepare control command and copy to SPI control buffer */
+	oa_tc6_prepare_ctrl_spi_buf(tc6, address, value, length, reg_op);
+
+	size = oa_tc6_calculate_ctrl_buf_size(length);
+
+	/* Perform SPI transfer */
+	ret = oa_tc6_spi_transfer(tc6, OA_TC6_CTRL_HEADER, size);
+	if (ret) {
+		dev_err(&tc6->spi->dev, "SPI transfer failed for control: %d\n",
+			ret);
+		return ret;
+	}
+
+	/* Check echoed/received control write command reply for errors */
+	return oa_tc6_check_ctrl_write_reply(tc6, size);
+}
+
+/**
+ * oa_tc6_write_registers - function for writing multiple consecutive registers.
+ * @tc6: oa_tc6 struct.
+ * @address: address of the first register to be written in the MAC-PHY.
+ * @value: values to be written from the starting register address @address.
+ * @length: number of consecutive registers to be written from @address.
+ *
+ * Maximum of 128 consecutive registers can be written starting at @address.
+ *
+ * Return: 0 on success otherwise failed.
+ */
+int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
+			   u8 length)
+{
+	int ret;
+
+	if (!length || length > OA_TC6_CTRL_MAX_REGISTERS) {
+		dev_err(&tc6->spi->dev, "Invalid register length parameter\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&tc6->spi_ctrl_lock);
+	ret = oa_tc6_perform_ctrl(tc6, address, value, length,
+				  OA_TC6_CTRL_REG_WRITE);
+	mutex_unlock(&tc6->spi_ctrl_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(oa_tc6_write_registers);
+
+/**
+ * oa_tc6_write_register - function for writing a MAC-PHY register.
+ * @tc6: oa_tc6 struct.
+ * @address: register address of the MAC-PHY to be written.
+ * @value: value to be written in the @address register address of the MAC-PHY.
+ *
+ * Return: 0 on success otherwise failed.
+ */
+int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value)
+{
+	return oa_tc6_write_registers(tc6, address, &value, 1);
+}
+EXPORT_SYMBOL_GPL(oa_tc6_write_register);
+
+/**
+ * oa_tc6_init - allocates and initializes oa_tc6 structure.
+ * @spi: device with which data will be exchanged.
+ *
+ * Return: pointer reference to the oa_tc6 structure if the MAC-PHY
+ * initialization is successful otherwise NULL.
+ */
+struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
+{
+	struct oa_tc6 *tc6;
+
+	tc6 = devm_kzalloc(&spi->dev, sizeof(*tc6), GFP_KERNEL);
+	if (!tc6)
+		return NULL;
+
+	tc6->spi = spi;
+	mutex_init(&tc6->spi_ctrl_lock);
+
+	/* Set the SPI controller to pump at realtime priority */
+	tc6->spi->rt = true;
+	spi_setup(tc6->spi);
+
+	tc6->spi_ctrl_tx_buf = devm_kzalloc(&tc6->spi->dev,
+					    OA_TC6_CTRL_SPI_BUF_SIZE,
+					    GFP_KERNEL);
+	if (!tc6->spi_ctrl_tx_buf)
+		return NULL;
+
+	tc6->spi_ctrl_rx_buf = devm_kzalloc(&tc6->spi->dev,
+					    OA_TC6_CTRL_SPI_BUF_SIZE,
+					    GFP_KERNEL);
+	if (!tc6->spi_ctrl_rx_buf)
+		return NULL;
+
+	return tc6;
+}
+EXPORT_SYMBOL_GPL(oa_tc6_init);
+
+MODULE_DESCRIPTION("OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface Lib");
+MODULE_AUTHOR("Parthiban Veerasooran <parthiban.veerasooran@microchip.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h
new file mode 100644
index 000000000000..99c490f1c8a8
--- /dev/null
+++ b/include/linux/oa_tc6.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface framework
+ *
+ * Link: https://opensig.org/download/document/OPEN_Alliance_10BASET1x_MAC-PHY_Serial_Interface_V1.1.pdf
+ *
+ * Author: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+ */
+
+#include <linux/spi/spi.h>
+
+struct oa_tc6;
+
+struct oa_tc6 *oa_tc6_init(struct spi_device *spi);
+int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value);
+int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
+			   u8 length);
-- 
cgit v1.3-3-g829e


From 375d1e0278cca70ce801d52c6b95c7a3c00f249c Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:03 +0530
Subject: net: ethernet: oa_tc6: implement register read operation

Implement register read operation according to the control communication
specified in the OPEN Alliance 10BASE-T1x MACPHY Serial Interface
document. Control read commands are used by the SPI host to read
registers within the MAC-PHY. Each control read commands are composed of
a 32 bits control command header.

The MAC-PHY ignores all data from the SPI host following the control
header for the remainder of the control read command. Control read
commands can read either a single register or multiple consecutive
registers. When multiple consecutive registers are read, the address is
automatically post-incremented by the MAC-PHY. Reading any unimplemented
or undefined registers shall return zero.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-4-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 84 +++++++++++++++++++++++++++++++++++++++++--
 include/linux/oa_tc6.h        |  3 ++
 2 files changed, 85 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index 24e9fd92d717..72bab9234436 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -38,6 +38,7 @@ enum oa_tc6_header_type {
 };
 
 enum oa_tc6_register_op {
+	OA_TC6_CTRL_REG_READ = 0,
 	OA_TC6_CTRL_REG_WRITE = 1,
 };
 
@@ -113,7 +114,8 @@ static void oa_tc6_prepare_ctrl_spi_buf(struct oa_tc6 *tc6, u32 address,
 
 	*tx_buf = oa_tc6_prepare_ctrl_header(address, length, reg_op);
 
-	oa_tc6_update_ctrl_write_data(tc6, value, length);
+	if (reg_op == OA_TC6_CTRL_REG_WRITE)
+		oa_tc6_update_ctrl_write_data(tc6, value, length);
 }
 
 static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size)
@@ -132,6 +134,30 @@ static int oa_tc6_check_ctrl_write_reply(struct oa_tc6 *tc6, u8 size)
 	return 0;
 }
 
+static int oa_tc6_check_ctrl_read_reply(struct oa_tc6 *tc6, u8 size)
+{
+	u32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE;
+	u32 *tx_buf = tc6->spi_ctrl_tx_buf;
+
+	/* The echoed control read header must match with the one that was
+	 * transmitted.
+	 */
+	if (*tx_buf != *rx_buf)
+		return -EPROTO;
+
+	return 0;
+}
+
+static void oa_tc6_copy_ctrl_read_data(struct oa_tc6 *tc6, u32 value[],
+				       u8 length)
+{
+	__be32 *rx_buf = tc6->spi_ctrl_rx_buf + OA_TC6_CTRL_IGNORED_SIZE +
+			 OA_TC6_CTRL_HEADER_SIZE;
+
+	for (int i = 0; i < length; i++)
+		value[i] = be32_to_cpu(*rx_buf++);
+}
+
 static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[],
 			       u8 length, enum oa_tc6_register_op reg_op)
 {
@@ -152,8 +178,62 @@ static int oa_tc6_perform_ctrl(struct oa_tc6 *tc6, u32 address, u32 value[],
 	}
 
 	/* Check echoed/received control write command reply for errors */
-	return oa_tc6_check_ctrl_write_reply(tc6, size);
+	if (reg_op == OA_TC6_CTRL_REG_WRITE)
+		return oa_tc6_check_ctrl_write_reply(tc6, size);
+
+	/* Check echoed/received control read command reply for errors */
+	ret = oa_tc6_check_ctrl_read_reply(tc6, size);
+	if (ret)
+		return ret;
+
+	oa_tc6_copy_ctrl_read_data(tc6, value, length);
+
+	return 0;
+}
+
+/**
+ * oa_tc6_read_registers - function for reading multiple consecutive registers.
+ * @tc6: oa_tc6 struct.
+ * @address: address of the first register to be read in the MAC-PHY.
+ * @value: values to be read from the starting register address @address.
+ * @length: number of consecutive registers to be read from @address.
+ *
+ * Maximum of 128 consecutive registers can be read starting at @address.
+ *
+ * Return: 0 on success otherwise failed.
+ */
+int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
+			  u8 length)
+{
+	int ret;
+
+	if (!length || length > OA_TC6_CTRL_MAX_REGISTERS) {
+		dev_err(&tc6->spi->dev, "Invalid register length parameter\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&tc6->spi_ctrl_lock);
+	ret = oa_tc6_perform_ctrl(tc6, address, value, length,
+				  OA_TC6_CTRL_REG_READ);
+	mutex_unlock(&tc6->spi_ctrl_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(oa_tc6_read_registers);
+
+/**
+ * oa_tc6_read_register - function for reading a MAC-PHY register.
+ * @tc6: oa_tc6 struct.
+ * @address: register address of the MAC-PHY to be read.
+ * @value: value read from the @address register address of the MAC-PHY.
+ *
+ * Return: 0 on success otherwise failed.
+ */
+int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value)
+{
+	return oa_tc6_read_registers(tc6, address, value, 1);
 }
+EXPORT_SYMBOL_GPL(oa_tc6_read_register);
 
 /**
  * oa_tc6_write_registers - function for writing multiple consecutive registers.
diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h
index 99c490f1c8a8..85aeecf87306 100644
--- a/include/linux/oa_tc6.h
+++ b/include/linux/oa_tc6.h
@@ -15,3 +15,6 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi);
 int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value);
 int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
 			   u8 length);
+int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value);
+int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
+			  u8 length);
-- 
cgit v1.3-3-g829e


From 1f9c4eed9c115960b485fca42ad49c1a713dd099 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:04 +0530
Subject: net: ethernet: oa_tc6: implement software reset

Reset complete bit is set when the MAC-PHY reset completes and ready for
configuration. Additionally reset complete bit in the STS0 register has
to be written by one upon reset complete to clear the interrupt.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-5-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 56 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index 72bab9234436..f774ed397213 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -6,8 +6,18 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/iopoll.h>
 #include <linux/oa_tc6.h>
 
+/* OPEN Alliance TC6 registers */
+/* Reset Control and Status Register */
+#define OA_TC6_REG_RESET			0x0003
+#define RESET_SWRESET				BIT(0)	/* Software Reset */
+
+/* Status Register #0 */
+#define OA_TC6_REG_STATUS0			0x0008
+#define STATUS0_RESETC				BIT(6)	/* Reset Complete */
+
 /* Control command header */
 #define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL	BIT(31)
 #define OA_TC6_CTRL_HEADER_WRITE_NOT_READ	BIT(29)
@@ -24,6 +34,8 @@
 						(OA_TC6_CTRL_MAX_REGISTERS *\
 						OA_TC6_CTRL_REG_VALUE_SIZE) +\
 						OA_TC6_CTRL_IGNORED_SIZE)
+#define STATUS0_RESETC_POLL_DELAY		1000
+#define STATUS0_RESETC_POLL_TIMEOUT		1000000
 
 /* Internal structure for MAC-PHY drivers */
 struct oa_tc6 {
@@ -279,6 +291,42 @@ int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(oa_tc6_write_register);
 
+static int oa_tc6_read_status0(struct oa_tc6 *tc6)
+{
+	u32 regval;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, &regval);
+	if (ret) {
+		dev_err(&tc6->spi->dev, "STATUS0 register read failed: %d\n",
+			ret);
+		return 0;
+	}
+
+	return regval;
+}
+
+static int oa_tc6_sw_reset_macphy(struct oa_tc6 *tc6)
+{
+	u32 regval = RESET_SWRESET;
+	int ret;
+
+	ret = oa_tc6_write_register(tc6, OA_TC6_REG_RESET, regval);
+	if (ret)
+		return ret;
+
+	/* Poll for soft reset complete for every 1ms until 1s timeout */
+	ret = readx_poll_timeout(oa_tc6_read_status0, tc6, regval,
+				 regval & STATUS0_RESETC,
+				 STATUS0_RESETC_POLL_DELAY,
+				 STATUS0_RESETC_POLL_TIMEOUT);
+	if (ret)
+		return -ENODEV;
+
+	/* Clear the reset complete status */
+	return oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, regval);
+}
+
 /**
  * oa_tc6_init - allocates and initializes oa_tc6 structure.
  * @spi: device with which data will be exchanged.
@@ -289,6 +337,7 @@ EXPORT_SYMBOL_GPL(oa_tc6_write_register);
 struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
 {
 	struct oa_tc6 *tc6;
+	int ret;
 
 	tc6 = devm_kzalloc(&spi->dev, sizeof(*tc6), GFP_KERNEL);
 	if (!tc6)
@@ -313,6 +362,13 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
 	if (!tc6->spi_ctrl_rx_buf)
 		return NULL;
 
+	ret = oa_tc6_sw_reset_macphy(tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev,
+			"MAC-PHY software reset failed: %d\n", ret);
+		return NULL;
+	}
+
 	return tc6;
 }
 EXPORT_SYMBOL_GPL(oa_tc6_init);
-- 
cgit v1.3-3-g829e


From 86c03a0f07f4c9874f58826a9956bda30993a358 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:05 +0530
Subject: net: ethernet: oa_tc6: implement error interrupts unmasking

This will unmask the following error interrupts from the MAC-PHY.
  tx protocol error
  rx buffer overflow error
  loss of framing error
  header error
The MAC-PHY will signal an error by setting the EXST bit in the receive
data footer which will then allow the host to read the STATUS0 register
to find the source of the error.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-6-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index f774ed397213..86b032cdbee1 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -18,6 +18,13 @@
 #define OA_TC6_REG_STATUS0			0x0008
 #define STATUS0_RESETC				BIT(6)	/* Reset Complete */
 
+/* Interrupt Mask Register #0 */
+#define OA_TC6_REG_INT_MASK0			0x000C
+#define INT_MASK0_HEADER_ERR_MASK		BIT(5)
+#define INT_MASK0_LOSS_OF_FRAME_ERR_MASK	BIT(4)
+#define INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK	BIT(3)
+#define INT_MASK0_TX_PROTOCOL_ERR_MASK		BIT(0)
+
 /* Control command header */
 #define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL	BIT(31)
 #define OA_TC6_CTRL_HEADER_WRITE_NOT_READ	BIT(29)
@@ -327,6 +334,23 @@ static int oa_tc6_sw_reset_macphy(struct oa_tc6 *tc6)
 	return oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, regval);
 }
 
+static int oa_tc6_unmask_macphy_error_interrupts(struct oa_tc6 *tc6)
+{
+	u32 regval;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_INT_MASK0, &regval);
+	if (ret)
+		return ret;
+
+	regval &= ~(INT_MASK0_TX_PROTOCOL_ERR_MASK |
+		    INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK |
+		    INT_MASK0_LOSS_OF_FRAME_ERR_MASK |
+		    INT_MASK0_HEADER_ERR_MASK);
+
+	return oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval);
+}
+
 /**
  * oa_tc6_init - allocates and initializes oa_tc6 structure.
  * @spi: device with which data will be exchanged.
@@ -369,6 +393,13 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
 		return NULL;
 	}
 
+	ret = oa_tc6_unmask_macphy_error_interrupts(tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev,
+			"MAC-PHY error interrupts unmask failed: %d\n", ret);
+		return NULL;
+	}
+
 	return tc6;
 }
 EXPORT_SYMBOL_GPL(oa_tc6_init);
-- 
cgit v1.3-3-g829e


From 8f9bf857e43b3f75a098e3af3a6fec2d03203a1e Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:06 +0530
Subject: net: ethernet: oa_tc6: implement internal PHY initialization

Internal PHY is initialized as per the PHY register capability supported
by the MAC-PHY. Direct PHY Register Access Capability indicates if PHY
registers are directly accessible within the SPI register memory space.
Indirect PHY Register Access Capability indicates if PHY registers are
indirectly accessible through the MDIO/MDC registers MDIOACCn defined in
OPEN Alliance specification. Currently the direct register access is only
supported.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-7-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 230 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/oa_tc6.h        |   4 +-
 include/uapi/linux/mdio.h     |   1 +
 3 files changed, 233 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index 86b032cdbee1..fc276d881dc9 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -7,9 +7,15 @@
 
 #include <linux/bitfield.h>
 #include <linux/iopoll.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
 #include <linux/oa_tc6.h>
 
 /* OPEN Alliance TC6 registers */
+/* Standard Capabilities Register */
+#define OA_TC6_REG_STDCAP			0x0002
+#define STDCAP_DIRECT_PHY_REG_ACCESS		BIT(8)
+
 /* Reset Control and Status Register */
 #define OA_TC6_REG_RESET			0x0003
 #define RESET_SWRESET				BIT(0)	/* Software Reset */
@@ -25,6 +31,10 @@
 #define INT_MASK0_RX_BUFFER_OVERFLOW_ERR_MASK	BIT(3)
 #define INT_MASK0_TX_PROTOCOL_ERR_MASK		BIT(0)
 
+/* PHY Clause 22 registers base address and mask */
+#define OA_TC6_PHY_STD_REG_ADDR_BASE		0xFF00
+#define OA_TC6_PHY_STD_REG_ADDR_MASK		0x1F
+
 /* Control command header */
 #define OA_TC6_CTRL_HEADER_DATA_NOT_CTRL	BIT(31)
 #define OA_TC6_CTRL_HEADER_WRITE_NOT_READ	BIT(29)
@@ -33,6 +43,15 @@
 #define OA_TC6_CTRL_HEADER_LENGTH		GENMASK(7, 1)
 #define OA_TC6_CTRL_HEADER_PARITY		BIT(0)
 
+/* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the
+ * OPEN Alliance specification.
+ */
+#define OA_TC6_PHY_C45_PCS_MMS2			2	/* MMD 3 */
+#define OA_TC6_PHY_C45_PMA_PMD_MMS3		3	/* MMD 1 */
+#define OA_TC6_PHY_C45_VS_PLCA_MMS4		4	/* MMD 31 */
+#define OA_TC6_PHY_C45_AUTO_NEG_MMS5		5	/* MMD 7 */
+#define OA_TC6_PHY_C45_POWER_UNIT_MMS6		6	/* MMD 13 */
+
 #define OA_TC6_CTRL_HEADER_SIZE			4
 #define OA_TC6_CTRL_REG_VALUE_SIZE		4
 #define OA_TC6_CTRL_IGNORED_SIZE		4
@@ -46,6 +65,10 @@
 
 /* Internal structure for MAC-PHY drivers */
 struct oa_tc6 {
+	struct device *dev;
+	struct net_device *netdev;
+	struct phy_device *phydev;
+	struct mii_bus *mdiobus;
 	struct spi_device *spi;
 	struct mutex spi_ctrl_lock; /* Protects spi control transfer */
 	void *spi_ctrl_tx_buf;
@@ -298,6 +321,191 @@ int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(oa_tc6_write_register);
 
+static int oa_tc6_check_phy_reg_direct_access_capability(struct oa_tc6 *tc6)
+{
+	u32 regval;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_STDCAP, &regval);
+	if (ret)
+		return ret;
+
+	if (!(regval & STDCAP_DIRECT_PHY_REG_ACCESS))
+		return -ENODEV;
+
+	return 0;
+}
+
+static void oa_tc6_handle_link_change(struct net_device *netdev)
+{
+	phy_print_status(netdev->phydev);
+}
+
+static int oa_tc6_mdiobus_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct oa_tc6 *tc6 = bus->priv;
+	u32 regval;
+	bool ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE |
+				   (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK),
+				   &regval);
+	if (ret)
+		return ret;
+
+	return regval;
+}
+
+static int oa_tc6_mdiobus_write(struct mii_bus *bus, int addr, int regnum,
+				u16 val)
+{
+	struct oa_tc6 *tc6 = bus->priv;
+
+	return oa_tc6_write_register(tc6, OA_TC6_PHY_STD_REG_ADDR_BASE |
+				     (regnum & OA_TC6_PHY_STD_REG_ADDR_MASK),
+				     val);
+}
+
+static int oa_tc6_get_phy_c45_mms(int devnum)
+{
+	switch (devnum) {
+	case MDIO_MMD_PCS:
+		return OA_TC6_PHY_C45_PCS_MMS2;
+	case MDIO_MMD_PMAPMD:
+		return OA_TC6_PHY_C45_PMA_PMD_MMS3;
+	case MDIO_MMD_VEND2:
+		return OA_TC6_PHY_C45_VS_PLCA_MMS4;
+	case MDIO_MMD_AN:
+		return OA_TC6_PHY_C45_AUTO_NEG_MMS5;
+	case MDIO_MMD_POWER_UNIT:
+		return OA_TC6_PHY_C45_POWER_UNIT_MMS6;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int oa_tc6_mdiobus_read_c45(struct mii_bus *bus, int addr, int devnum,
+				   int regnum)
+{
+	struct oa_tc6 *tc6 = bus->priv;
+	u32 regval;
+	int ret;
+
+	ret = oa_tc6_get_phy_c45_mms(devnum);
+	if (ret < 0)
+		return ret;
+
+	ret = oa_tc6_read_register(tc6, (ret << 16) | regnum, &regval);
+	if (ret)
+		return ret;
+
+	return regval;
+}
+
+static int oa_tc6_mdiobus_write_c45(struct mii_bus *bus, int addr, int devnum,
+				    int regnum, u16 val)
+{
+	struct oa_tc6 *tc6 = bus->priv;
+	int ret;
+
+	ret = oa_tc6_get_phy_c45_mms(devnum);
+	if (ret < 0)
+		return ret;
+
+	return oa_tc6_write_register(tc6, (ret << 16) | regnum, val);
+}
+
+static int oa_tc6_mdiobus_register(struct oa_tc6 *tc6)
+{
+	int ret;
+
+	tc6->mdiobus = mdiobus_alloc();
+	if (!tc6->mdiobus) {
+		netdev_err(tc6->netdev, "MDIO bus alloc failed\n");
+		return -ENOMEM;
+	}
+
+	tc6->mdiobus->priv = tc6;
+	tc6->mdiobus->read = oa_tc6_mdiobus_read;
+	tc6->mdiobus->write = oa_tc6_mdiobus_write;
+	/* OPEN Alliance 10BASE-T1x compliance MAC-PHYs will have both C22 and
+	 * C45 registers space. If the PHY is discovered via C22 bus protocol it
+	 * assumes it uses C22 protocol and always uses C22 registers indirect
+	 * access to access C45 registers. This is because, we don't have a
+	 * clean separation between C22/C45 register space and C22/C45 MDIO bus
+	 * protocols. Resulting, PHY C45 registers direct access can't be used
+	 * which can save multiple SPI bus access. To support this feature, PHY
+	 * drivers can set .read_mmd/.write_mmd in the PHY driver to call
+	 * .read_c45/.write_c45. Ex: drivers/net/phy/microchip_t1s.c
+	 */
+	tc6->mdiobus->read_c45 = oa_tc6_mdiobus_read_c45;
+	tc6->mdiobus->write_c45 = oa_tc6_mdiobus_write_c45;
+	tc6->mdiobus->name = "oa-tc6-mdiobus";
+	tc6->mdiobus->parent = tc6->dev;
+
+	snprintf(tc6->mdiobus->id, ARRAY_SIZE(tc6->mdiobus->id), "%s",
+		 dev_name(&tc6->spi->dev));
+
+	ret = mdiobus_register(tc6->mdiobus);
+	if (ret) {
+		netdev_err(tc6->netdev, "Could not register MDIO bus\n");
+		mdiobus_free(tc6->mdiobus);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void oa_tc6_mdiobus_unregister(struct oa_tc6 *tc6)
+{
+	mdiobus_unregister(tc6->mdiobus);
+	mdiobus_free(tc6->mdiobus);
+}
+
+static int oa_tc6_phy_init(struct oa_tc6 *tc6)
+{
+	int ret;
+
+	ret = oa_tc6_check_phy_reg_direct_access_capability(tc6);
+	if (ret) {
+		netdev_err(tc6->netdev,
+			   "Direct PHY register access is not supported by the MAC-PHY\n");
+		return ret;
+	}
+
+	ret = oa_tc6_mdiobus_register(tc6);
+	if (ret)
+		return ret;
+
+	tc6->phydev = phy_find_first(tc6->mdiobus);
+	if (!tc6->phydev) {
+		netdev_err(tc6->netdev, "No PHY found\n");
+		oa_tc6_mdiobus_unregister(tc6);
+		return -ENODEV;
+	}
+
+	tc6->phydev->is_internal = true;
+	ret = phy_connect_direct(tc6->netdev, tc6->phydev,
+				 &oa_tc6_handle_link_change,
+				 PHY_INTERFACE_MODE_INTERNAL);
+	if (ret) {
+		netdev_err(tc6->netdev, "Can't attach PHY to %s\n",
+			   tc6->mdiobus->id);
+		oa_tc6_mdiobus_unregister(tc6);
+		return ret;
+	}
+
+	phy_attached_info(tc6->netdev->phydev);
+
+	return 0;
+}
+
+static void oa_tc6_phy_exit(struct oa_tc6 *tc6)
+{
+	phy_disconnect(tc6->phydev);
+	oa_tc6_mdiobus_unregister(tc6);
+}
+
 static int oa_tc6_read_status0(struct oa_tc6 *tc6)
 {
 	u32 regval;
@@ -354,11 +562,12 @@ static int oa_tc6_unmask_macphy_error_interrupts(struct oa_tc6 *tc6)
 /**
  * oa_tc6_init - allocates and initializes oa_tc6 structure.
  * @spi: device with which data will be exchanged.
+ * @netdev: network device interface structure.
  *
  * Return: pointer reference to the oa_tc6 structure if the MAC-PHY
  * initialization is successful otherwise NULL.
  */
-struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
+struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 {
 	struct oa_tc6 *tc6;
 	int ret;
@@ -368,6 +577,8 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
 		return NULL;
 
 	tc6->spi = spi;
+	tc6->netdev = netdev;
+	SET_NETDEV_DEV(netdev, &spi->dev);
 	mutex_init(&tc6->spi_ctrl_lock);
 
 	/* Set the SPI controller to pump at realtime priority */
@@ -400,10 +611,27 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi)
 		return NULL;
 	}
 
+	ret = oa_tc6_phy_init(tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev,
+			"MAC internal PHY initialization failed: %d\n", ret);
+		return NULL;
+	}
+
 	return tc6;
 }
 EXPORT_SYMBOL_GPL(oa_tc6_init);
 
+/**
+ * oa_tc6_exit - exit function.
+ * @tc6: oa_tc6 struct.
+ */
+void oa_tc6_exit(struct oa_tc6 *tc6)
+{
+	oa_tc6_phy_exit(tc6);
+}
+EXPORT_SYMBOL_GPL(oa_tc6_exit);
+
 MODULE_DESCRIPTION("OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface Lib");
 MODULE_AUTHOR("Parthiban Veerasooran <parthiban.veerasooran@microchip.com>");
 MODULE_LICENSE("GPL");
diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h
index 85aeecf87306..606ba9f1e663 100644
--- a/include/linux/oa_tc6.h
+++ b/include/linux/oa_tc6.h
@@ -7,11 +7,13 @@
  * Author: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
  */
 
+#include <linux/etherdevice.h>
 #include <linux/spi/spi.h>
 
 struct oa_tc6;
 
-struct oa_tc6 *oa_tc6_init(struct spi_device *spi);
+struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev);
+void oa_tc6_exit(struct oa_tc6 *tc6);
 int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value);
 int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
 			   u8 length);
diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h
index c0c8ec995b06..f0d3f268240d 100644
--- a/include/uapi/linux/mdio.h
+++ b/include/uapi/linux/mdio.h
@@ -23,6 +23,7 @@
 #define MDIO_MMD_DTEXS		5	/* DTE Extender Sublayer */
 #define MDIO_MMD_TC		6	/* Transmission Convergence */
 #define MDIO_MMD_AN		7	/* Auto-Negotiation */
+#define MDIO_MMD_POWER_UNIT	13	/* PHY Power Unit */
 #define MDIO_MMD_C22EXT		29	/* Clause 22 extension */
 #define MDIO_MMD_VEND1		30	/* Vendor specific 1 */
 #define MDIO_MMD_VEND2		31	/* Vendor specific 2 */
-- 
cgit v1.3-3-g829e


From 18a918762fab8248e504edbe03c8df966d9666c9 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:07 +0530
Subject: net: phy: microchip_t1s: add c45 direct access in LAN865x internal
 PHY

This patch adds c45 registers direct access support in Microchip's
LAN865x internal PHY.

OPEN Alliance 10BASE-T1x compliance MAC-PHYs will have both C22 and C45
registers space. If the PHY is discovered via C22 bus protocol it assumes
it uses C22 protocol and always uses C22 registers indirect access to
access C45 registers. This is because, we don't have a clean separation
between C22/C45 register space and C22/C45 MDIO bus protocols. Resulting,
PHY C45 registers direct access can't be used which can save multiple SPI
bus access. To support this feature, set .read_mmd/.write_mmd in the PHY
driver to call .read_c45/.write_c45 in the OPEN Alliance framework
drivers/net/ethernet/oa_tc6.c

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-8-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/microchip_t1s.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/net/phy/microchip_t1s.c b/drivers/net/phy/microchip_t1s.c
index 534ca7d1b061..3614839a8e51 100644
--- a/drivers/net/phy/microchip_t1s.c
+++ b/drivers/net/phy/microchip_t1s.c
@@ -268,6 +268,34 @@ static int lan86xx_read_status(struct phy_device *phydev)
 	return 0;
 }
 
+/* OPEN Alliance 10BASE-T1x compliance MAC-PHYs will have both C22 and
+ * C45 registers space. If the PHY is discovered via C22 bus protocol it assumes
+ * it uses C22 protocol and always uses C22 registers indirect access to access
+ * C45 registers. This is because, we don't have a clean separation between
+ * C22/C45 register space and C22/C45 MDIO bus protocols. Resulting, PHY C45
+ * registers direct access can't be used which can save multiple SPI bus access.
+ * To support this feature, set .read_mmd/.write_mmd in the PHY driver to call
+ * .read_c45/.write_c45 in the OPEN Alliance framework
+ * drivers/net/ethernet/oa_tc6.c
+ */
+static int lan865x_phy_read_mmd(struct phy_device *phydev, int devnum,
+				u16 regnum)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	int addr = phydev->mdio.addr;
+
+	return __mdiobus_c45_read(bus, addr, devnum, regnum);
+}
+
+static int lan865x_phy_write_mmd(struct phy_device *phydev, int devnum,
+				 u16 regnum, u16 val)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	int addr = phydev->mdio.addr;
+
+	return __mdiobus_c45_write(bus, addr, devnum, regnum, val);
+}
+
 static struct phy_driver microchip_t1s_driver[] = {
 	{
 		PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1),
@@ -285,6 +313,8 @@ static struct phy_driver microchip_t1s_driver[] = {
 		.features           = PHY_BASIC_T1S_P2MP_FEATURES,
 		.config_init        = lan865x_revb0_config_init,
 		.read_status        = lan86xx_read_status,
+		.read_mmd           = lan865x_phy_read_mmd,
+		.write_mmd          = lan865x_phy_write_mmd,
 		.get_plca_cfg	    = genphy_c45_plca_get_cfg,
 		.set_plca_cfg	    = genphy_c45_plca_set_cfg,
 		.get_plca_status    = genphy_c45_plca_get_status,
-- 
cgit v1.3-3-g829e


From f845a027de66d1efeb8cb22020e2c50baebdc441 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:08 +0530
Subject: net: ethernet: oa_tc6: enable open alliance tc6 data communication

Enabling Configuration Synchronization bit (SYNC) in the Configuration
Register #0 enables data communication in the MAC-PHY. The state of this
bit is reflected in the data footer SYNC bit.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-9-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index fc276d881dc9..8958af863b6e 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -20,6 +20,10 @@
 #define OA_TC6_REG_RESET			0x0003
 #define RESET_SWRESET				BIT(0)	/* Software Reset */
 
+/* Configuration Register #0 */
+#define OA_TC6_REG_CONFIG0			0x0004
+#define CONFIG0_SYNC				BIT(15)
+
 /* Status Register #0 */
 #define OA_TC6_REG_STATUS0			0x0008
 #define STATUS0_RESETC				BIT(6)	/* Reset Complete */
@@ -559,6 +563,21 @@ static int oa_tc6_unmask_macphy_error_interrupts(struct oa_tc6 *tc6)
 	return oa_tc6_write_register(tc6, OA_TC6_REG_INT_MASK0, regval);
 }
 
+static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6)
+{
+	u32 value;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_CONFIG0, &value);
+	if (ret)
+		return ret;
+
+	/* Enable configuration synchronization for data transfer */
+	value |= CONFIG0_SYNC;
+
+	return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value);
+}
+
 /**
  * oa_tc6_init - allocates and initializes oa_tc6 structure.
  * @spi: device with which data will be exchanged.
@@ -618,7 +637,18 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 		return NULL;
 	}
 
+	ret = oa_tc6_enable_data_transfer(tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev, "Failed to enable data transfer: %d\n",
+			ret);
+		goto phy_exit;
+	}
+
 	return tc6;
+
+phy_exit:
+	oa_tc6_phy_exit(tc6);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(oa_tc6_init);
 
-- 
cgit v1.3-3-g829e


From 53fbde8ab21e8c2c6187159cc17fc10cbf20900a Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:09 +0530
Subject: net: ethernet: oa_tc6: implement transmit path to transfer tx
 ethernet frames

The transmit ethernet frame will be converted into multiple transmit data
chunks. Each transmit data chunk consists of a 4 bytes header followed by
a 64 bytes transmit data chunk payload. The 4 bytes data header occurs at
the beginning of each transmit data chunk on MOSI. The data header
contains the information needed to determine the validity and location of
the transmit frame data within the data chunk payload. The number of
transmit data chunks transmitted to mac-phy is limited to the number
transmit credits available in the mac-phy. Initially the transmit credits
will be updated from the buffer status register and then it will be
updated from the footer received on each spi data transfer. The received
footer will be examined for the transmit errors if any.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-10-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 399 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/oa_tc6.h        |   1 +
 2 files changed, 398 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index 8958af863b6e..bbc4b7fce64c 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -27,6 +27,13 @@
 /* Status Register #0 */
 #define OA_TC6_REG_STATUS0			0x0008
 #define STATUS0_RESETC				BIT(6)	/* Reset Complete */
+#define STATUS0_HEADER_ERROR			BIT(5)
+#define STATUS0_LOSS_OF_FRAME_ERROR		BIT(4)
+#define STATUS0_TX_PROTOCOL_ERROR		BIT(0)
+
+/* Buffer Status Register */
+#define OA_TC6_REG_BUFFER_STATUS		0x000B
+#define BUFFER_STATUS_TX_CREDITS_AVAILABLE	GENMASK(15, 8)
 
 /* Interrupt Mask Register #0 */
 #define OA_TC6_REG_INT_MASK0			0x000C
@@ -47,6 +54,21 @@
 #define OA_TC6_CTRL_HEADER_LENGTH		GENMASK(7, 1)
 #define OA_TC6_CTRL_HEADER_PARITY		BIT(0)
 
+/* Data header */
+#define OA_TC6_DATA_HEADER_DATA_NOT_CTRL	BIT(31)
+#define OA_TC6_DATA_HEADER_DATA_VALID		BIT(21)
+#define OA_TC6_DATA_HEADER_START_VALID		BIT(20)
+#define OA_TC6_DATA_HEADER_START_WORD_OFFSET	GENMASK(19, 16)
+#define OA_TC6_DATA_HEADER_END_VALID		BIT(14)
+#define OA_TC6_DATA_HEADER_END_BYTE_OFFSET	GENMASK(13, 8)
+#define OA_TC6_DATA_HEADER_PARITY		BIT(0)
+
+/* Data footer */
+#define OA_TC6_DATA_FOOTER_EXTENDED_STS		BIT(31)
+#define OA_TC6_DATA_FOOTER_RXD_HEADER_BAD	BIT(30)
+#define OA_TC6_DATA_FOOTER_CONFIG_SYNC		BIT(29)
+#define OA_TC6_DATA_FOOTER_TX_CREDITS		GENMASK(5, 1)
+
 /* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the
  * OPEN Alliance specification.
  */
@@ -64,6 +86,13 @@
 						(OA_TC6_CTRL_MAX_REGISTERS *\
 						OA_TC6_CTRL_REG_VALUE_SIZE) +\
 						OA_TC6_CTRL_IGNORED_SIZE)
+#define OA_TC6_CHUNK_PAYLOAD_SIZE		64
+#define OA_TC6_DATA_HEADER_SIZE			4
+#define OA_TC6_CHUNK_SIZE			(OA_TC6_DATA_HEADER_SIZE +\
+						OA_TC6_CHUNK_PAYLOAD_SIZE)
+#define OA_TC6_MAX_TX_CHUNKS			48
+#define OA_TC6_SPI_DATA_BUF_SIZE		(OA_TC6_MAX_TX_CHUNKS *\
+						OA_TC6_CHUNK_SIZE)
 #define STATUS0_RESETC_POLL_DELAY		1000
 #define STATUS0_RESETC_POLL_TIMEOUT		1000000
 
@@ -77,10 +106,20 @@ struct oa_tc6 {
 	struct mutex spi_ctrl_lock; /* Protects spi control transfer */
 	void *spi_ctrl_tx_buf;
 	void *spi_ctrl_rx_buf;
+	void *spi_data_tx_buf;
+	void *spi_data_rx_buf;
+	struct sk_buff *ongoing_tx_skb;
+	struct sk_buff *waiting_tx_skb;
+	struct task_struct *spi_thread;
+	wait_queue_head_t spi_wq;
+	u16 tx_skb_offset;
+	u16 spi_data_tx_buf_offset;
+	u16 tx_credits;
 };
 
 enum oa_tc6_header_type {
 	OA_TC6_CTRL_HEADER,
+	OA_TC6_DATA_HEADER,
 };
 
 enum oa_tc6_register_op {
@@ -88,14 +127,34 @@ enum oa_tc6_register_op {
 	OA_TC6_CTRL_REG_WRITE = 1,
 };
 
+enum oa_tc6_data_valid_info {
+	OA_TC6_DATA_INVALID,
+	OA_TC6_DATA_VALID,
+};
+
+enum oa_tc6_data_start_valid_info {
+	OA_TC6_DATA_START_INVALID,
+	OA_TC6_DATA_START_VALID,
+};
+
+enum oa_tc6_data_end_valid_info {
+	OA_TC6_DATA_END_INVALID,
+	OA_TC6_DATA_END_VALID,
+};
+
 static int oa_tc6_spi_transfer(struct oa_tc6 *tc6,
 			       enum oa_tc6_header_type header_type, u16 length)
 {
 	struct spi_transfer xfer = { 0 };
 	struct spi_message msg;
 
-	xfer.tx_buf = tc6->spi_ctrl_tx_buf;
-	xfer.rx_buf = tc6->spi_ctrl_rx_buf;
+	if (header_type == OA_TC6_DATA_HEADER) {
+		xfer.tx_buf = tc6->spi_data_tx_buf;
+		xfer.rx_buf = tc6->spi_data_rx_buf;
+	} else {
+		xfer.tx_buf = tc6->spi_ctrl_tx_buf;
+		xfer.rx_buf = tc6->spi_ctrl_rx_buf;
+	}
 	xfer.len = length;
 
 	spi_message_init(&msg);
@@ -578,6 +637,309 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6)
 	return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value);
 }
 
+static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6)
+{
+	if (tc6->ongoing_tx_skb) {
+		tc6->netdev->stats.tx_dropped++;
+		kfree_skb(tc6->ongoing_tx_skb);
+		tc6->ongoing_tx_skb = NULL;
+	}
+}
+
+static int oa_tc6_process_extended_status(struct oa_tc6 *tc6)
+{
+	u32 value;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_STATUS0, &value);
+	if (ret) {
+		netdev_err(tc6->netdev, "STATUS0 register read failed: %d\n",
+			   ret);
+		return ret;
+	}
+
+	/* Clear the error interrupts status */
+	ret = oa_tc6_write_register(tc6, OA_TC6_REG_STATUS0, value);
+	if (ret) {
+		netdev_err(tc6->netdev, "STATUS0 register write failed: %d\n",
+			   ret);
+		return ret;
+	}
+
+	if (FIELD_GET(STATUS0_TX_PROTOCOL_ERROR, value)) {
+		netdev_err(tc6->netdev, "Transmit protocol error\n");
+		return -ENODEV;
+	}
+	/* TODO: Currently loss of frame and header errors are treated as
+	 * non-recoverable errors. They will be handled in the next version.
+	 */
+	if (FIELD_GET(STATUS0_LOSS_OF_FRAME_ERROR, value)) {
+		netdev_err(tc6->netdev, "Loss of frame error\n");
+		return -ENODEV;
+	}
+	if (FIELD_GET(STATUS0_HEADER_ERROR, value)) {
+		netdev_err(tc6->netdev, "Header error\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer)
+{
+	/* Process rx chunk footer for the following,
+	 * 1. tx credits
+	 * 2. errors if any from MAC-PHY
+	 */
+	tc6->tx_credits = FIELD_GET(OA_TC6_DATA_FOOTER_TX_CREDITS, footer);
+
+	if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) {
+		int ret = oa_tc6_process_extended_status(tc6);
+
+		if (ret)
+			return ret;
+	}
+
+	/* TODO: Currently received header bad and configuration unsync errors
+	 * are treated as non-recoverable errors. They will be handled in the
+	 * next version.
+	 */
+	if (FIELD_GET(OA_TC6_DATA_FOOTER_RXD_HEADER_BAD, footer)) {
+		netdev_err(tc6->netdev, "Rxd header bad error\n");
+		return -ENODEV;
+	}
+
+	if (!FIELD_GET(OA_TC6_DATA_FOOTER_CONFIG_SYNC, footer)) {
+		netdev_err(tc6->netdev, "Config unsync error\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset)
+{
+	u8 *rx_buf = tc6->spi_data_rx_buf;
+	__be32 footer;
+
+	footer = *((__be32 *)&rx_buf[footer_offset]);
+
+	return be32_to_cpu(footer);
+}
+
+static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length)
+{
+	u16 no_of_rx_chunks = length / OA_TC6_CHUNK_SIZE;
+	u32 footer;
+	int ret;
+
+	/* All the rx chunks in the receive SPI data buffer are examined here */
+	for (int i = 0; i < no_of_rx_chunks; i++) {
+		/* Last 4 bytes in each received chunk consist footer info */
+		footer = oa_tc6_get_rx_chunk_footer(tc6, i * OA_TC6_CHUNK_SIZE +
+						    OA_TC6_CHUNK_PAYLOAD_SIZE);
+
+		ret = oa_tc6_process_rx_chunk_footer(tc6, footer);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static __be32 oa_tc6_prepare_data_header(bool data_valid, bool start_valid,
+					 bool end_valid, u8 end_byte_offset)
+{
+	u32 header = FIELD_PREP(OA_TC6_DATA_HEADER_DATA_NOT_CTRL,
+				OA_TC6_DATA_HEADER) |
+		     FIELD_PREP(OA_TC6_DATA_HEADER_DATA_VALID, data_valid) |
+		     FIELD_PREP(OA_TC6_DATA_HEADER_START_VALID, start_valid) |
+		     FIELD_PREP(OA_TC6_DATA_HEADER_END_VALID, end_valid) |
+		     FIELD_PREP(OA_TC6_DATA_HEADER_END_BYTE_OFFSET,
+				end_byte_offset);
+
+	header |= FIELD_PREP(OA_TC6_DATA_HEADER_PARITY,
+			     oa_tc6_get_parity(header));
+
+	return cpu_to_be32(header);
+}
+
+static void oa_tc6_add_tx_skb_to_spi_buf(struct oa_tc6 *tc6)
+{
+	enum oa_tc6_data_end_valid_info end_valid = OA_TC6_DATA_END_INVALID;
+	__be32 *tx_buf = tc6->spi_data_tx_buf + tc6->spi_data_tx_buf_offset;
+	u16 remaining_len = tc6->ongoing_tx_skb->len - tc6->tx_skb_offset;
+	u8 *tx_skb_data = tc6->ongoing_tx_skb->data + tc6->tx_skb_offset;
+	enum oa_tc6_data_start_valid_info start_valid;
+	u8 end_byte_offset = 0;
+	u16 length_to_copy;
+
+	/* Initial value is assigned here to avoid more than 80 characters in
+	 * the declaration place.
+	 */
+	start_valid = OA_TC6_DATA_START_INVALID;
+
+	/* Set start valid if the current tx chunk contains the start of the tx
+	 * ethernet frame.
+	 */
+	if (!tc6->tx_skb_offset)
+		start_valid = OA_TC6_DATA_START_VALID;
+
+	/* If the remaining tx skb length is more than the chunk payload size of
+	 * 64 bytes then copy only 64 bytes and leave the ongoing tx skb for
+	 * next tx chunk.
+	 */
+	length_to_copy = min_t(u16, remaining_len, OA_TC6_CHUNK_PAYLOAD_SIZE);
+
+	/* Copy the tx skb data to the tx chunk payload buffer */
+	memcpy(tx_buf + 1, tx_skb_data, length_to_copy);
+	tc6->tx_skb_offset += length_to_copy;
+
+	/* Set end valid if the current tx chunk contains the end of the tx
+	 * ethernet frame.
+	 */
+	if (tc6->ongoing_tx_skb->len == tc6->tx_skb_offset) {
+		end_valid = OA_TC6_DATA_END_VALID;
+		end_byte_offset = length_to_copy - 1;
+		tc6->tx_skb_offset = 0;
+		tc6->netdev->stats.tx_bytes += tc6->ongoing_tx_skb->len;
+		tc6->netdev->stats.tx_packets++;
+		kfree_skb(tc6->ongoing_tx_skb);
+		tc6->ongoing_tx_skb = NULL;
+	}
+
+	*tx_buf = oa_tc6_prepare_data_header(OA_TC6_DATA_VALID, start_valid,
+					     end_valid, end_byte_offset);
+	tc6->spi_data_tx_buf_offset += OA_TC6_CHUNK_SIZE;
+}
+
+static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6)
+{
+	u16 used_tx_credits;
+
+	/* Get tx skbs and convert them into tx chunks based on the tx credits
+	 * available.
+	 */
+	for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits;
+	     used_tx_credits++) {
+		if (!tc6->ongoing_tx_skb) {
+			tc6->ongoing_tx_skb = tc6->waiting_tx_skb;
+			tc6->waiting_tx_skb = NULL;
+		}
+		if (!tc6->ongoing_tx_skb)
+			break;
+		oa_tc6_add_tx_skb_to_spi_buf(tc6);
+	}
+
+	return used_tx_credits * OA_TC6_CHUNK_SIZE;
+}
+
+static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6)
+{
+	int ret;
+
+	while (true) {
+		u16 spi_length = 0;
+
+		tc6->spi_data_tx_buf_offset = 0;
+
+		if (tc6->ongoing_tx_skb || tc6->waiting_tx_skb)
+			spi_length = oa_tc6_prepare_spi_tx_buf_for_tx_skbs(tc6);
+
+		if (spi_length == 0)
+			break;
+
+		ret = oa_tc6_spi_transfer(tc6, OA_TC6_DATA_HEADER, spi_length);
+		if (ret) {
+			netdev_err(tc6->netdev, "SPI data transfer failed: %d\n",
+				   ret);
+			return ret;
+		}
+
+		ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_length);
+		if (ret) {
+			oa_tc6_cleanup_ongoing_tx_skb(tc6);
+			netdev_err(tc6->netdev, "Device error: %d\n", ret);
+			return ret;
+		}
+
+		if (!tc6->waiting_tx_skb && netif_queue_stopped(tc6->netdev))
+			netif_wake_queue(tc6->netdev);
+	}
+
+	return 0;
+}
+
+static int oa_tc6_spi_thread_handler(void *data)
+{
+	struct oa_tc6 *tc6 = data;
+	int ret;
+
+	while (likely(!kthread_should_stop())) {
+		/* This kthread will be waken up if there is a tx skb */
+		wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb ||
+					 kthread_should_stop());
+
+		if (kthread_should_stop())
+			break;
+
+		ret = oa_tc6_try_spi_transfer(tc6);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int oa_tc6_update_buffer_status_from_register(struct oa_tc6 *tc6)
+{
+	u32 value;
+	int ret;
+
+	/* Initially tx credits to be updated from the register as there is no
+	 * data transfer performed yet. Later it will be updated from the rx
+	 * footer.
+	 */
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_BUFFER_STATUS, &value);
+	if (ret)
+		return ret;
+
+	tc6->tx_credits = FIELD_GET(BUFFER_STATUS_TX_CREDITS_AVAILABLE, value);
+
+	return 0;
+}
+
+/**
+ * oa_tc6_start_xmit - function for sending the tx skb which consists ethernet
+ * frame.
+ * @tc6: oa_tc6 struct.
+ * @skb: socket buffer in which the ethernet frame is stored.
+ *
+ * Return: NETDEV_TX_OK if the transmit ethernet frame skb added in the tx_skb_q
+ * otherwise returns NETDEV_TX_BUSY.
+ */
+netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb)
+{
+	if (tc6->waiting_tx_skb) {
+		netif_stop_queue(tc6->netdev);
+		return NETDEV_TX_BUSY;
+	}
+
+	if (skb_linearize(skb)) {
+		dev_kfree_skb_any(skb);
+		tc6->netdev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	tc6->waiting_tx_skb = skb;
+
+	/* Wake spi kthread to perform spi transfer */
+	wake_up_interruptible(&tc6->spi_wq);
+
+	return NETDEV_TX_OK;
+}
+EXPORT_SYMBOL_GPL(oa_tc6_start_xmit);
+
 /**
  * oa_tc6_init - allocates and initializes oa_tc6 structure.
  * @spi: device with which data will be exchanged.
@@ -616,6 +978,18 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 	if (!tc6->spi_ctrl_rx_buf)
 		return NULL;
 
+	tc6->spi_data_tx_buf = devm_kzalloc(&tc6->spi->dev,
+					    OA_TC6_SPI_DATA_BUF_SIZE,
+					    GFP_KERNEL);
+	if (!tc6->spi_data_tx_buf)
+		return NULL;
+
+	tc6->spi_data_rx_buf = devm_kzalloc(&tc6->spi->dev,
+					    OA_TC6_SPI_DATA_BUF_SIZE,
+					    GFP_KERNEL);
+	if (!tc6->spi_data_rx_buf)
+		return NULL;
+
 	ret = oa_tc6_sw_reset_macphy(tc6);
 	if (ret) {
 		dev_err(&tc6->spi->dev,
@@ -644,6 +1018,24 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 		goto phy_exit;
 	}
 
+	ret = oa_tc6_update_buffer_status_from_register(tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev,
+			"Failed to update buffer status: %d\n", ret);
+		goto phy_exit;
+	}
+
+	init_waitqueue_head(&tc6->spi_wq);
+
+	tc6->spi_thread = kthread_run(oa_tc6_spi_thread_handler, tc6,
+				      "oa-tc6-spi-thread");
+	if (IS_ERR(tc6->spi_thread)) {
+		dev_err(&tc6->spi->dev, "Failed to create SPI thread\n");
+		goto phy_exit;
+	}
+
+	sched_set_fifo(tc6->spi_thread);
+
 	return tc6;
 
 phy_exit:
@@ -659,6 +1051,9 @@ EXPORT_SYMBOL_GPL(oa_tc6_init);
 void oa_tc6_exit(struct oa_tc6 *tc6)
 {
 	oa_tc6_phy_exit(tc6);
+	kthread_stop(tc6->spi_thread);
+	dev_kfree_skb_any(tc6->ongoing_tx_skb);
+	dev_kfree_skb_any(tc6->waiting_tx_skb);
 }
 EXPORT_SYMBOL_GPL(oa_tc6_exit);
 
diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h
index 606ba9f1e663..5c7811ac9cbe 100644
--- a/include/linux/oa_tc6.h
+++ b/include/linux/oa_tc6.h
@@ -20,3 +20,4 @@ int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
 int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value);
 int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
 			  u8 length);
+netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb);
-- 
cgit v1.3-3-g829e


From d70a0d8f2f2d1b9bb6e3e9dfed25ae3ca3303770 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:10 +0530
Subject: net: ethernet: oa_tc6: implement receive path to receive rx ethernet
 frames

SPI rx data buffer can contain one or more receive data chunks. A receive
data chunk consists a 64 bytes receive data chunk payload followed a
4 bytes data footer at the end. The data footer contains the information
needed to determine the validity and location of the receive frame data
within the receive data chunk payload and the host can use these
information to generate ethernet frame. Initially the receive chunks
available will be updated from the buffer status register and then it
will be updated from the footer received on each spi data transfer. Tx
data valid or empty chunks equal to the number receive chunks available
will be transmitted in the MOSI to receive all the rx chunks.
Additionally the receive data footer contains the below information as
well. The received footer will be examined for the receive errors if any.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-11-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 241 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 233 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index bbc4b7fce64c..72d95bad669f 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -29,11 +29,13 @@
 #define STATUS0_RESETC				BIT(6)	/* Reset Complete */
 #define STATUS0_HEADER_ERROR			BIT(5)
 #define STATUS0_LOSS_OF_FRAME_ERROR		BIT(4)
+#define STATUS0_RX_BUFFER_OVERFLOW_ERROR	BIT(3)
 #define STATUS0_TX_PROTOCOL_ERROR		BIT(0)
 
 /* Buffer Status Register */
 #define OA_TC6_REG_BUFFER_STATUS		0x000B
 #define BUFFER_STATUS_TX_CREDITS_AVAILABLE	GENMASK(15, 8)
+#define BUFFER_STATUS_RX_CHUNKS_AVAILABLE	GENMASK(7, 0)
 
 /* Interrupt Mask Register #0 */
 #define OA_TC6_REG_INT_MASK0			0x000C
@@ -67,6 +69,12 @@
 #define OA_TC6_DATA_FOOTER_EXTENDED_STS		BIT(31)
 #define OA_TC6_DATA_FOOTER_RXD_HEADER_BAD	BIT(30)
 #define OA_TC6_DATA_FOOTER_CONFIG_SYNC		BIT(29)
+#define OA_TC6_DATA_FOOTER_RX_CHUNKS		GENMASK(28, 24)
+#define OA_TC6_DATA_FOOTER_DATA_VALID		BIT(21)
+#define OA_TC6_DATA_FOOTER_START_VALID		BIT(20)
+#define OA_TC6_DATA_FOOTER_START_WORD_OFFSET	GENMASK(19, 16)
+#define OA_TC6_DATA_FOOTER_END_VALID		BIT(14)
+#define OA_TC6_DATA_FOOTER_END_BYTE_OFFSET	GENMASK(13, 8)
 #define OA_TC6_DATA_FOOTER_TX_CREDITS		GENMASK(5, 1)
 
 /* PHY – Clause 45 registers memory map selector (MMS) as per table 6 in the
@@ -110,11 +118,14 @@ struct oa_tc6 {
 	void *spi_data_rx_buf;
 	struct sk_buff *ongoing_tx_skb;
 	struct sk_buff *waiting_tx_skb;
+	struct sk_buff *rx_skb;
 	struct task_struct *spi_thread;
 	wait_queue_head_t spi_wq;
 	u16 tx_skb_offset;
 	u16 spi_data_tx_buf_offset;
 	u16 tx_credits;
+	u8 rx_chunks_available;
+	bool rx_buf_overflow;
 };
 
 enum oa_tc6_header_type {
@@ -637,6 +648,15 @@ static int oa_tc6_enable_data_transfer(struct oa_tc6 *tc6)
 	return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, value);
 }
 
+static void oa_tc6_cleanup_ongoing_rx_skb(struct oa_tc6 *tc6)
+{
+	if (tc6->rx_skb) {
+		tc6->netdev->stats.rx_dropped++;
+		kfree_skb(tc6->rx_skb);
+		tc6->rx_skb = NULL;
+	}
+}
+
 static void oa_tc6_cleanup_ongoing_tx_skb(struct oa_tc6 *tc6)
 {
 	if (tc6->ongoing_tx_skb) {
@@ -666,6 +686,13 @@ static int oa_tc6_process_extended_status(struct oa_tc6 *tc6)
 		return ret;
 	}
 
+	if (FIELD_GET(STATUS0_RX_BUFFER_OVERFLOW_ERROR, value)) {
+		tc6->rx_buf_overflow = true;
+		oa_tc6_cleanup_ongoing_rx_skb(tc6);
+		net_err_ratelimited("%s: Receive buffer overflow error\n",
+				    tc6->netdev->name);
+		return -EAGAIN;
+	}
 	if (FIELD_GET(STATUS0_TX_PROTOCOL_ERROR, value)) {
 		netdev_err(tc6->netdev, "Transmit protocol error\n");
 		return -ENODEV;
@@ -690,8 +717,11 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer)
 	/* Process rx chunk footer for the following,
 	 * 1. tx credits
 	 * 2. errors if any from MAC-PHY
+	 * 3. receive chunks available
 	 */
 	tc6->tx_credits = FIELD_GET(OA_TC6_DATA_FOOTER_TX_CREDITS, footer);
+	tc6->rx_chunks_available = FIELD_GET(OA_TC6_DATA_FOOTER_RX_CHUNKS,
+					     footer);
 
 	if (FIELD_GET(OA_TC6_DATA_FOOTER_EXTENDED_STS, footer)) {
 		int ret = oa_tc6_process_extended_status(tc6);
@@ -717,6 +747,141 @@ static int oa_tc6_process_rx_chunk_footer(struct oa_tc6 *tc6, u32 footer)
 	return 0;
 }
 
+static void oa_tc6_submit_rx_skb(struct oa_tc6 *tc6)
+{
+	tc6->rx_skb->protocol = eth_type_trans(tc6->rx_skb, tc6->netdev);
+	tc6->netdev->stats.rx_packets++;
+	tc6->netdev->stats.rx_bytes += tc6->rx_skb->len;
+
+	netif_rx(tc6->rx_skb);
+
+	tc6->rx_skb = NULL;
+}
+
+static void oa_tc6_update_rx_skb(struct oa_tc6 *tc6, u8 *payload, u8 length)
+{
+	memcpy(skb_put(tc6->rx_skb, length), payload, length);
+}
+
+static int oa_tc6_allocate_rx_skb(struct oa_tc6 *tc6)
+{
+	tc6->rx_skb = netdev_alloc_skb_ip_align(tc6->netdev, tc6->netdev->mtu +
+						ETH_HLEN + ETH_FCS_LEN);
+	if (!tc6->rx_skb) {
+		tc6->netdev->stats.rx_dropped++;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int oa_tc6_prcs_complete_rx_frame(struct oa_tc6 *tc6, u8 *payload,
+					 u16 size)
+{
+	int ret;
+
+	ret = oa_tc6_allocate_rx_skb(tc6);
+	if (ret)
+		return ret;
+
+	oa_tc6_update_rx_skb(tc6, payload, size);
+
+	oa_tc6_submit_rx_skb(tc6);
+
+	return 0;
+}
+
+static int oa_tc6_prcs_rx_frame_start(struct oa_tc6 *tc6, u8 *payload, u16 size)
+{
+	int ret;
+
+	ret = oa_tc6_allocate_rx_skb(tc6);
+	if (ret)
+		return ret;
+
+	oa_tc6_update_rx_skb(tc6, payload, size);
+
+	return 0;
+}
+
+static void oa_tc6_prcs_rx_frame_end(struct oa_tc6 *tc6, u8 *payload, u16 size)
+{
+	oa_tc6_update_rx_skb(tc6, payload, size);
+
+	oa_tc6_submit_rx_skb(tc6);
+}
+
+static void oa_tc6_prcs_ongoing_rx_frame(struct oa_tc6 *tc6, u8 *payload,
+					 u32 footer)
+{
+	oa_tc6_update_rx_skb(tc6, payload, OA_TC6_CHUNK_PAYLOAD_SIZE);
+}
+
+static int oa_tc6_prcs_rx_chunk_payload(struct oa_tc6 *tc6, u8 *data,
+					u32 footer)
+{
+	u8 start_byte_offset = FIELD_GET(OA_TC6_DATA_FOOTER_START_WORD_OFFSET,
+					 footer) * sizeof(u32);
+	u8 end_byte_offset = FIELD_GET(OA_TC6_DATA_FOOTER_END_BYTE_OFFSET,
+				       footer);
+	bool start_valid = FIELD_GET(OA_TC6_DATA_FOOTER_START_VALID, footer);
+	bool end_valid = FIELD_GET(OA_TC6_DATA_FOOTER_END_VALID, footer);
+	u16 size;
+
+	/* Restart the new rx frame after receiving rx buffer overflow error */
+	if (start_valid && tc6->rx_buf_overflow)
+		tc6->rx_buf_overflow = false;
+
+	if (tc6->rx_buf_overflow)
+		return 0;
+
+	/* Process the chunk with complete rx frame */
+	if (start_valid && end_valid && start_byte_offset < end_byte_offset) {
+		size = end_byte_offset + 1 - start_byte_offset;
+		return oa_tc6_prcs_complete_rx_frame(tc6,
+						     &data[start_byte_offset],
+						     size);
+	}
+
+	/* Process the chunk with only rx frame start */
+	if (start_valid && !end_valid) {
+		size = OA_TC6_CHUNK_PAYLOAD_SIZE - start_byte_offset;
+		return oa_tc6_prcs_rx_frame_start(tc6,
+						  &data[start_byte_offset],
+						  size);
+	}
+
+	/* Process the chunk with only rx frame end */
+	if (end_valid && !start_valid) {
+		size = end_byte_offset + 1;
+		oa_tc6_prcs_rx_frame_end(tc6, data, size);
+		return 0;
+	}
+
+	/* Process the chunk with previous rx frame end and next rx frame
+	 * start.
+	 */
+	if (start_valid && end_valid && start_byte_offset > end_byte_offset) {
+		/* After rx buffer overflow error received, there might be a
+		 * possibility of getting an end valid of a previously
+		 * incomplete rx frame along with the new rx frame start valid.
+		 */
+		if (tc6->rx_skb) {
+			size = end_byte_offset + 1;
+			oa_tc6_prcs_rx_frame_end(tc6, data, size);
+		}
+		size = OA_TC6_CHUNK_PAYLOAD_SIZE - start_byte_offset;
+		return oa_tc6_prcs_rx_frame_start(tc6,
+						  &data[start_byte_offset],
+						  size);
+	}
+
+	/* Process the chunk with ongoing rx frame data */
+	oa_tc6_prcs_ongoing_rx_frame(tc6, data, footer);
+
+	return 0;
+}
+
 static u32 oa_tc6_get_rx_chunk_footer(struct oa_tc6 *tc6, u16 footer_offset)
 {
 	u8 *rx_buf = tc6->spi_data_rx_buf;
@@ -742,6 +907,20 @@ static int oa_tc6_process_spi_data_rx_buf(struct oa_tc6 *tc6, u16 length)
 		ret = oa_tc6_process_rx_chunk_footer(tc6, footer);
 		if (ret)
 			return ret;
+
+		/* If there is a data valid chunks then process it for the
+		 * information needed to determine the validity and the location
+		 * of the receive frame data.
+		 */
+		if (FIELD_GET(OA_TC6_DATA_FOOTER_DATA_VALID, footer)) {
+			u8 *payload = tc6->spi_data_rx_buf + i *
+				      OA_TC6_CHUNK_SIZE;
+
+			ret = oa_tc6_prcs_rx_chunk_payload(tc6, payload,
+							   footer);
+			if (ret)
+				return ret;
+		}
 	}
 
 	return 0;
@@ -834,31 +1013,74 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6)
 	return used_tx_credits * OA_TC6_CHUNK_SIZE;
 }
 
+static void oa_tc6_add_empty_chunks_to_spi_buf(struct oa_tc6 *tc6,
+					       u16 needed_empty_chunks)
+{
+	__be32 header;
+
+	header = oa_tc6_prepare_data_header(OA_TC6_DATA_INVALID,
+					    OA_TC6_DATA_START_INVALID,
+					    OA_TC6_DATA_END_INVALID, 0);
+
+	while (needed_empty_chunks--) {
+		__be32 *tx_buf = tc6->spi_data_tx_buf +
+				 tc6->spi_data_tx_buf_offset;
+
+		*tx_buf = header;
+		tc6->spi_data_tx_buf_offset += OA_TC6_CHUNK_SIZE;
+	}
+}
+
+static u16 oa_tc6_prepare_spi_tx_buf_for_rx_chunks(struct oa_tc6 *tc6, u16 len)
+{
+	u16 tx_chunks = len / OA_TC6_CHUNK_SIZE;
+	u16 needed_empty_chunks;
+
+	/* If there are more chunks to receive than to transmit, we need to add
+	 * enough empty tx chunks to allow the reception of the excess rx
+	 * chunks.
+	 */
+	if (tx_chunks >= tc6->rx_chunks_available)
+		return len;
+
+	needed_empty_chunks = tc6->rx_chunks_available - tx_chunks;
+
+	oa_tc6_add_empty_chunks_to_spi_buf(tc6, needed_empty_chunks);
+
+	return needed_empty_chunks * OA_TC6_CHUNK_SIZE + len;
+}
+
 static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6)
 {
 	int ret;
 
 	while (true) {
-		u16 spi_length = 0;
+		u16 spi_len = 0;
 
 		tc6->spi_data_tx_buf_offset = 0;
 
 		if (tc6->ongoing_tx_skb || tc6->waiting_tx_skb)
-			spi_length = oa_tc6_prepare_spi_tx_buf_for_tx_skbs(tc6);
+			spi_len = oa_tc6_prepare_spi_tx_buf_for_tx_skbs(tc6);
 
-		if (spi_length == 0)
+		spi_len = oa_tc6_prepare_spi_tx_buf_for_rx_chunks(tc6, spi_len);
+
+		if (spi_len == 0)
 			break;
 
-		ret = oa_tc6_spi_transfer(tc6, OA_TC6_DATA_HEADER, spi_length);
+		ret = oa_tc6_spi_transfer(tc6, OA_TC6_DATA_HEADER, spi_len);
 		if (ret) {
 			netdev_err(tc6->netdev, "SPI data transfer failed: %d\n",
 				   ret);
 			return ret;
 		}
 
-		ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_length);
+		ret = oa_tc6_process_spi_data_rx_buf(tc6, spi_len);
 		if (ret) {
+			if (ret == -EAGAIN)
+				continue;
+
 			oa_tc6_cleanup_ongoing_tx_skb(tc6);
+			oa_tc6_cleanup_ongoing_rx_skb(tc6);
 			netdev_err(tc6->netdev, "Device error: %d\n", ret);
 			return ret;
 		}
@@ -896,15 +1118,17 @@ static int oa_tc6_update_buffer_status_from_register(struct oa_tc6 *tc6)
 	u32 value;
 	int ret;
 
-	/* Initially tx credits to be updated from the register as there is no
-	 * data transfer performed yet. Later it will be updated from the rx
-	 * footer.
+	/* Initially tx credits and rx chunks available to be updated from the
+	 * register as there is no data transfer performed yet. Later they will
+	 * be updated from the rx footer.
 	 */
 	ret = oa_tc6_read_register(tc6, OA_TC6_REG_BUFFER_STATUS, &value);
 	if (ret)
 		return ret;
 
 	tc6->tx_credits = FIELD_GET(BUFFER_STATUS_TX_CREDITS_AVAILABLE, value);
+	tc6->rx_chunks_available = FIELD_GET(BUFFER_STATUS_RX_CHUNKS_AVAILABLE,
+					     value);
 
 	return 0;
 }
@@ -1054,6 +1278,7 @@ void oa_tc6_exit(struct oa_tc6 *tc6)
 	kthread_stop(tc6->spi_thread);
 	dev_kfree_skb_any(tc6->ongoing_tx_skb);
 	dev_kfree_skb_any(tc6->waiting_tx_skb);
+	dev_kfree_skb_any(tc6->rx_skb);
 }
 EXPORT_SYMBOL_GPL(oa_tc6_exit);
 
-- 
cgit v1.3-3-g829e


From 2c6ce535445362dc58a58c9813e58bb3da28eab7 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:11 +0530
Subject: net: ethernet: oa_tc6: implement mac-phy interrupt

The MAC-PHY interrupt is asserted when the following conditions are met.

Receive chunks available - This interrupt is asserted when the previous
data footer had no receive data chunks available and once the receive
data chunks become available for reading. On reception of the first data
header this interrupt will be deasserted.

Transmit chunk credits available - This interrupt is asserted when the
previous data footer indicated no transmit credits available and once the
transmit credits become available for transmitting transmit data chunks.
On reception of the first data header this interrupt will be deasserted.

Extended status event - This interrupt is asserted when the previous data
footer indicated no extended status and once the extended event become
available. In this case the host should read status #0 register to know
the corresponding error/event. On reception of the first data header this
interrupt will be deasserted.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-12-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 52 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index 72d95bad669f..d3510dc19273 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -126,6 +126,7 @@ struct oa_tc6 {
 	u16 tx_credits;
 	u8 rx_chunks_available;
 	bool rx_buf_overflow;
+	bool int_flag;
 };
 
 enum oa_tc6_header_type {
@@ -1064,6 +1065,14 @@ static int oa_tc6_try_spi_transfer(struct oa_tc6 *tc6)
 
 		spi_len = oa_tc6_prepare_spi_tx_buf_for_rx_chunks(tc6, spi_len);
 
+		if (tc6->int_flag) {
+			tc6->int_flag = false;
+			if (spi_len == 0) {
+				oa_tc6_add_empty_chunks_to_spi_buf(tc6, 1);
+				spi_len = OA_TC6_CHUNK_SIZE;
+			}
+		}
+
 		if (spi_len == 0)
 			break;
 
@@ -1098,8 +1107,11 @@ static int oa_tc6_spi_thread_handler(void *data)
 	int ret;
 
 	while (likely(!kthread_should_stop())) {
-		/* This kthread will be waken up if there is a tx skb */
+		/* This kthread will be waken up if there is a tx skb or mac-phy
+		 * interrupt to perform spi transfer with tx chunks.
+		 */
 		wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb ||
+					 tc6->int_flag ||
 					 kthread_should_stop());
 
 		if (kthread_should_stop())
@@ -1133,6 +1145,24 @@ static int oa_tc6_update_buffer_status_from_register(struct oa_tc6 *tc6)
 	return 0;
 }
 
+static irqreturn_t oa_tc6_macphy_isr(int irq, void *data)
+{
+	struct oa_tc6 *tc6 = data;
+
+	/* MAC-PHY interrupt can occur for the following reasons.
+	 * - availability of tx credits if it was 0 before and not reported in
+	 *   the previous rx footer.
+	 * - availability of rx chunks if it was 0 before and not reported in
+	 *   the previous rx footer.
+	 * - extended status event not reported in the previous rx footer.
+	 */
+	tc6->int_flag = true;
+	/* Wake spi kthread to perform spi transfer */
+	wake_up_interruptible(&tc6->spi_wq);
+
+	return IRQ_HANDLED;
+}
+
 /**
  * oa_tc6_start_xmit - function for sending the tx skb which consists ethernet
  * frame.
@@ -1260,8 +1290,28 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev)
 
 	sched_set_fifo(tc6->spi_thread);
 
+	ret = devm_request_irq(&tc6->spi->dev, tc6->spi->irq, oa_tc6_macphy_isr,
+			       IRQF_TRIGGER_FALLING, dev_name(&tc6->spi->dev),
+			       tc6);
+	if (ret) {
+		dev_err(&tc6->spi->dev, "Failed to request macphy isr %d\n",
+			ret);
+		goto kthread_stop;
+	}
+
+	/* oa_tc6_sw_reset_macphy() function resets and clears the MAC-PHY reset
+	 * complete status. IRQ is also asserted on reset completion and it is
+	 * remain asserted until MAC-PHY receives a data chunk. So performing an
+	 * empty data chunk transmission will deassert the IRQ. Refer section
+	 * 7.7 and 9.2.8.8 in the OPEN Alliance specification for more details.
+	 */
+	tc6->int_flag = true;
+	wake_up_interruptible(&tc6->spi_wq);
+
 	return tc6;
 
+kthread_stop:
+	kthread_stop(tc6->spi_thread);
 phy_exit:
 	oa_tc6_phy_exit(tc6);
 	return NULL;
-- 
cgit v1.3-3-g829e


From afd42170c8a6e68edd3f3a7f2aacd2bfbedb58b2 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:12 +0530
Subject: net: ethernet: oa_tc6: add helper function to enable zero align rx
 frame

Zero align receive frame feature can be enabled to align all receive
ethernet frames data to start at the beginning of any receive data chunk
payload with a start word offset (SWO) of zero. Receive frames may begin
anywhere within the receive data chunk payload when this feature is not
enabled.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-13-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/oa_tc6.c | 24 ++++++++++++++++++++++++
 include/linux/oa_tc6.h        |  1 +
 2 files changed, 25 insertions(+)

diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c
index d3510dc19273..f9c0dcd965c2 100644
--- a/drivers/net/ethernet/oa_tc6.c
+++ b/drivers/net/ethernet/oa_tc6.c
@@ -23,6 +23,7 @@
 /* Configuration Register #0 */
 #define OA_TC6_REG_CONFIG0			0x0004
 #define CONFIG0_SYNC				BIT(15)
+#define CONFIG0_ZARFE_ENABLE			BIT(12)
 
 /* Status Register #0 */
 #define OA_TC6_REG_STATUS0			0x0008
@@ -1163,6 +1164,29 @@ static irqreturn_t oa_tc6_macphy_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+/**
+ * oa_tc6_zero_align_receive_frame_enable - function to enable zero align
+ * receive frame feature.
+ * @tc6: oa_tc6 struct.
+ *
+ * Return: 0 on success otherwise failed.
+ */
+int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6)
+{
+	u32 regval;
+	int ret;
+
+	ret = oa_tc6_read_register(tc6, OA_TC6_REG_CONFIG0, &regval);
+	if (ret)
+		return ret;
+
+	/* Set Zero-Align Receive Frame Enable */
+	regval |= CONFIG0_ZARFE_ENABLE;
+
+	return oa_tc6_write_register(tc6, OA_TC6_REG_CONFIG0, regval);
+}
+EXPORT_SYMBOL_GPL(oa_tc6_zero_align_receive_frame_enable);
+
 /**
  * oa_tc6_start_xmit - function for sending the tx skb which consists ethernet
  * frame.
diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h
index 5c7811ac9cbe..15f58e3c56c7 100644
--- a/include/linux/oa_tc6.h
+++ b/include/linux/oa_tc6.h
@@ -21,3 +21,4 @@ int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value);
 int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
 			  u8 length);
 netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb);
+int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6);
-- 
cgit v1.3-3-g829e


From 5cd2340cb6a383d04fd88e48fabc2a21a909d6a1 Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:13 +0530
Subject: microchip: lan865x: add driver support for Microchip's LAN865X
 MAC-PHY

The LAN8650/1 is designed to conform to the OPEN Alliance 10BASE-T1x
MAC-PHY Serial Interface specification, Version 1.1. The IEEE Clause 4
MAC integration provides the low pin count standard SPI interface to any
microcontroller therefore providing Ethernet functionality without
requiring MAC integration within the microcontroller. The LAN8650/1
operates as an SPI client supporting SCLK clock rates up to a maximum of
25 MHz. This SPI interface supports the transfer of both data (Ethernet
frames) and control (register access).

By default, the chunk data payload is 64 bytes in size. The Ethernet
Media Access Controller (MAC) module implements a 10 Mbps half duplex
Ethernet MAC, compatible with the IEEE 802.3 standard. 10BASE-T1S
physical layer transceiver integrated is into the LAN8650/1. The PHY and
MAC are connected via an internal Media Independent Interface (MII).

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-14-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                                      |   6 +
 drivers/net/ethernet/microchip/Kconfig           |   1 +
 drivers/net/ethernet/microchip/Makefile          |   1 +
 drivers/net/ethernet/microchip/lan865x/Kconfig   |  19 +
 drivers/net/ethernet/microchip/lan865x/Makefile  |   6 +
 drivers/net/ethernet/microchip/lan865x/lan865x.c | 429 +++++++++++++++++++++++
 6 files changed, 462 insertions(+)
 create mode 100644 drivers/net/ethernet/microchip/lan865x/Kconfig
 create mode 100644 drivers/net/ethernet/microchip/lan865x/Makefile
 create mode 100644 drivers/net/ethernet/microchip/lan865x/lan865x.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 6c2315c1297c..492807274c3b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14980,6 +14980,12 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/microchip/lan743x_*
 
+MICROCHIP LAN8650/1 10BASE-T1S MACPHY ETHERNET DRIVER
+M:	Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/microchip/lan865x/lan865x.c
+
 MICROCHIP LAN87xx/LAN937x T1 PHY DRIVER
 M:	Arun Ramadoss <arun.ramadoss@microchip.com>
 R:	UNGLinuxDriver@microchip.com
diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index 2e3eb37a45cd..ee046468652c 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -57,6 +57,7 @@ config LAN743X
 	  To compile this driver as a module, choose M here. The module will be
 	  called lan743x.
 
+source "drivers/net/ethernet/microchip/lan865x/Kconfig"
 source "drivers/net/ethernet/microchip/lan966x/Kconfig"
 source "drivers/net/ethernet/microchip/sparx5/Kconfig"
 source "drivers/net/ethernet/microchip/vcap/Kconfig"
diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index 94045537b643..3c65baed9fd8 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_LAN743X) += lan743x.o
 
 lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o
 
+obj-$(CONFIG_LAN865X) += lan865x/
 obj-$(CONFIG_LAN966X_SWITCH) += lan966x/
 obj-$(CONFIG_SPARX5_SWITCH) += sparx5/
 obj-$(CONFIG_VCAP) += vcap/
diff --git a/drivers/net/ethernet/microchip/lan865x/Kconfig b/drivers/net/ethernet/microchip/lan865x/Kconfig
new file mode 100644
index 000000000000..7f2a4e7e1915
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan865x/Kconfig
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Microchip LAN865x Driver Support
+#
+
+if NET_VENDOR_MICROCHIP
+
+config LAN865X
+	tristate "LAN865x support"
+	depends on SPI
+	select OA_TC6
+	help
+	  Support for the Microchip LAN8650/1 Rev.B0/B1 MACPHY Ethernet chip. It
+	  uses OPEN Alliance 10BASE-T1x Serial Interface specification.
+
+	  To compile this driver as a module, choose M here. The module will be
+	  called lan865x.
+
+endif # NET_VENDOR_MICROCHIP
diff --git a/drivers/net/ethernet/microchip/lan865x/Makefile b/drivers/net/ethernet/microchip/lan865x/Makefile
new file mode 100644
index 000000000000..9f5dd89c1eb8
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan865x/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the Microchip LAN865x Driver
+#
+
+obj-$(CONFIG_LAN865X) += lan865x.o
diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c
new file mode 100644
index 000000000000..dd436bdff0f8
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c
@@ -0,0 +1,429 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Microchip's LAN865x 10BASE-T1S MAC-PHY driver
+ *
+ * Author: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/phy.h>
+#include <linux/oa_tc6.h>
+
+#define DRV_NAME			"lan8650"
+
+/* MAC Network Control Register */
+#define LAN865X_REG_MAC_NET_CTL		0x00010000
+#define MAC_NET_CTL_TXEN		BIT(3) /* Transmit Enable */
+#define MAC_NET_CTL_RXEN		BIT(2) /* Receive Enable */
+
+/* MAC Network Configuration Reg */
+#define LAN865X_REG_MAC_NET_CFG		0x00010001
+#define MAC_NET_CFG_PROMISCUOUS_MODE	BIT(4)
+#define MAC_NET_CFG_MULTICAST_MODE	BIT(6)
+#define MAC_NET_CFG_UNICAST_MODE	BIT(7)
+
+/* MAC Hash Register Bottom */
+#define LAN865X_REG_MAC_L_HASH		0x00010020
+/* MAC Hash Register Top */
+#define LAN865X_REG_MAC_H_HASH		0x00010021
+/* MAC Specific Addr 1 Bottom Reg */
+#define LAN865X_REG_MAC_L_SADDR1	0x00010022
+/* MAC Specific Addr 1 Top Reg */
+#define LAN865X_REG_MAC_H_SADDR1	0x00010023
+
+struct lan865x_priv {
+	struct work_struct multicast_work;
+	struct net_device *netdev;
+	struct spi_device *spi;
+	struct oa_tc6 *tc6;
+};
+
+static int lan865x_set_hw_macaddr_low_bytes(struct oa_tc6 *tc6, const u8 *mac)
+{
+	u32 regval;
+
+	regval = (mac[3] << 24) | (mac[2] << 16) | (mac[1] << 8) | mac[0];
+
+	return oa_tc6_write_register(tc6, LAN865X_REG_MAC_L_SADDR1, regval);
+}
+
+static int lan865x_set_hw_macaddr(struct lan865x_priv *priv, const u8 *mac)
+{
+	int restore_ret;
+	u32 regval;
+	int ret;
+
+	/* Configure MAC address low bytes */
+	ret = lan865x_set_hw_macaddr_low_bytes(priv->tc6, mac);
+	if (ret)
+		return ret;
+
+	/* Prepare and configure MAC address high bytes */
+	regval = (mac[5] << 8) | mac[4];
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_H_SADDR1,
+				    regval);
+	if (!ret)
+		return 0;
+
+	/* Restore the old MAC address low bytes from netdev if the new MAC
+	 * address high bytes setting failed.
+	 */
+	restore_ret = lan865x_set_hw_macaddr_low_bytes(priv->tc6,
+						       priv->netdev->dev_addr);
+	if (restore_ret)
+		return restore_ret;
+
+	return ret;
+}
+
+static const struct ethtool_ops lan865x_ethtool_ops = {
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+};
+
+static int lan865x_set_mac_address(struct net_device *netdev, void *addr)
+{
+	struct lan865x_priv *priv = netdev_priv(netdev);
+	struct sockaddr *address = addr;
+	int ret;
+
+	ret = eth_prepare_mac_addr_change(netdev, addr);
+	if (ret < 0)
+		return ret;
+
+	if (ether_addr_equal(address->sa_data, netdev->dev_addr))
+		return 0;
+
+	ret = lan865x_set_hw_macaddr(priv, address->sa_data);
+	if (ret)
+		return ret;
+
+	eth_commit_mac_addr_change(netdev, addr);
+
+	return 0;
+}
+
+static u32 get_address_bit(u8 addr[ETH_ALEN], u32 bit)
+{
+	return ((addr[bit / 8]) >> (bit % 8)) & 1;
+}
+
+static u32 lan865x_hash(u8 addr[ETH_ALEN])
+{
+	u32 hash_index = 0;
+
+	for (int i = 0; i < 6; i++) {
+		u32 hash = 0;
+
+		for (int j = 0; j < 8; j++)
+			hash ^= get_address_bit(addr, (j * 6) + i);
+
+		hash_index |= (hash << i);
+	}
+
+	return hash_index;
+}
+
+static int lan865x_set_specific_multicast_addr(struct lan865x_priv *priv)
+{
+	struct netdev_hw_addr *ha;
+	u32 hash_lo = 0;
+	u32 hash_hi = 0;
+	int ret;
+
+	netdev_for_each_mc_addr(ha, priv->netdev) {
+		u32 bit_num = lan865x_hash(ha->addr);
+
+		if (bit_num >= BIT(5))
+			hash_hi |= (1 << (bit_num - BIT(5)));
+		else
+			hash_lo |= (1 << bit_num);
+	}
+
+	/* Enabling specific multicast addresses */
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_H_HASH, hash_hi);
+	if (ret) {
+		netdev_err(priv->netdev, "Failed to write reg_hashh: %d\n",
+			   ret);
+		return ret;
+	}
+
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_L_HASH, hash_lo);
+	if (ret)
+		netdev_err(priv->netdev, "Failed to write reg_hashl: %d\n",
+			   ret);
+
+	return ret;
+}
+
+static int lan865x_set_all_multicast_addr(struct lan865x_priv *priv)
+{
+	int ret;
+
+	/* Enabling all multicast addresses */
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_H_HASH,
+				    0xffffffff);
+	if (ret) {
+		netdev_err(priv->netdev, "Failed to write reg_hashh: %d\n",
+			   ret);
+		return ret;
+	}
+
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_L_HASH,
+				    0xffffffff);
+	if (ret)
+		netdev_err(priv->netdev, "Failed to write reg_hashl: %d\n",
+			   ret);
+
+	return ret;
+}
+
+static int lan865x_clear_all_multicast_addr(struct lan865x_priv *priv)
+{
+	int ret;
+
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_H_HASH, 0);
+	if (ret) {
+		netdev_err(priv->netdev, "Failed to write reg_hashh: %d\n",
+			   ret);
+		return ret;
+	}
+
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_L_HASH, 0);
+	if (ret)
+		netdev_err(priv->netdev, "Failed to write reg_hashl: %d\n",
+			   ret);
+
+	return ret;
+}
+
+static void lan865x_multicast_work_handler(struct work_struct *work)
+{
+	struct lan865x_priv *priv = container_of(work, struct lan865x_priv,
+						 multicast_work);
+	u32 regval = 0;
+	int ret;
+
+	if (priv->netdev->flags & IFF_PROMISC) {
+		/* Enabling promiscuous mode */
+		regval |= MAC_NET_CFG_PROMISCUOUS_MODE;
+		regval &= (~MAC_NET_CFG_MULTICAST_MODE);
+		regval &= (~MAC_NET_CFG_UNICAST_MODE);
+	} else if (priv->netdev->flags & IFF_ALLMULTI) {
+		/* Enabling all multicast mode */
+		if (lan865x_set_all_multicast_addr(priv))
+			return;
+
+		regval &= (~MAC_NET_CFG_PROMISCUOUS_MODE);
+		regval |= MAC_NET_CFG_MULTICAST_MODE;
+		regval &= (~MAC_NET_CFG_UNICAST_MODE);
+	} else if (!netdev_mc_empty(priv->netdev)) {
+		/* Enabling specific multicast mode */
+		if (lan865x_set_specific_multicast_addr(priv))
+			return;
+
+		regval &= (~MAC_NET_CFG_PROMISCUOUS_MODE);
+		regval |= MAC_NET_CFG_MULTICAST_MODE;
+		regval &= (~MAC_NET_CFG_UNICAST_MODE);
+	} else {
+		/* Enabling local mac address only */
+		if (lan865x_clear_all_multicast_addr(priv))
+			return;
+	}
+	ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_NET_CFG, regval);
+	if (ret)
+		netdev_err(priv->netdev, "Failed to enable promiscuous/multicast/normal mode: %d\n",
+			   ret);
+}
+
+static void lan865x_set_multicast_list(struct net_device *netdev)
+{
+	struct lan865x_priv *priv = netdev_priv(netdev);
+
+	schedule_work(&priv->multicast_work);
+}
+
+static netdev_tx_t lan865x_send_packet(struct sk_buff *skb,
+				       struct net_device *netdev)
+{
+	struct lan865x_priv *priv = netdev_priv(netdev);
+
+	return oa_tc6_start_xmit(priv->tc6, skb);
+}
+
+static int lan865x_hw_disable(struct lan865x_priv *priv)
+{
+	u32 regval;
+
+	if (oa_tc6_read_register(priv->tc6, LAN865X_REG_MAC_NET_CTL, &regval))
+		return -ENODEV;
+
+	regval &= ~(MAC_NET_CTL_TXEN | MAC_NET_CTL_RXEN);
+
+	if (oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_NET_CTL, regval))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int lan865x_net_close(struct net_device *netdev)
+{
+	struct lan865x_priv *priv = netdev_priv(netdev);
+	int ret;
+
+	netif_stop_queue(netdev);
+	phy_stop(netdev->phydev);
+	ret = lan865x_hw_disable(priv);
+	if (ret) {
+		netdev_err(netdev, "Failed to disable the hardware: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int lan865x_hw_enable(struct lan865x_priv *priv)
+{
+	u32 regval;
+
+	if (oa_tc6_read_register(priv->tc6, LAN865X_REG_MAC_NET_CTL, &regval))
+		return -ENODEV;
+
+	regval |= MAC_NET_CTL_TXEN | MAC_NET_CTL_RXEN;
+
+	if (oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_NET_CTL, regval))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int lan865x_net_open(struct net_device *netdev)
+{
+	struct lan865x_priv *priv = netdev_priv(netdev);
+	int ret;
+
+	ret = lan865x_hw_enable(priv);
+	if (ret) {
+		netdev_err(netdev, "Failed to enable hardware: %d\n", ret);
+		return ret;
+	}
+
+	phy_start(netdev->phydev);
+
+	return 0;
+}
+
+static const struct net_device_ops lan865x_netdev_ops = {
+	.ndo_open		= lan865x_net_open,
+	.ndo_stop		= lan865x_net_close,
+	.ndo_start_xmit		= lan865x_send_packet,
+	.ndo_set_rx_mode	= lan865x_set_multicast_list,
+	.ndo_set_mac_address	= lan865x_set_mac_address,
+};
+
+static int lan865x_probe(struct spi_device *spi)
+{
+	struct net_device *netdev;
+	struct lan865x_priv *priv;
+	int ret;
+
+	netdev = alloc_etherdev(sizeof(struct lan865x_priv));
+	if (!netdev)
+		return -ENOMEM;
+
+	priv = netdev_priv(netdev);
+	priv->netdev = netdev;
+	priv->spi = spi;
+	spi_set_drvdata(spi, priv);
+	INIT_WORK(&priv->multicast_work, lan865x_multicast_work_handler);
+
+	priv->tc6 = oa_tc6_init(spi, netdev);
+	if (!priv->tc6) {
+		ret = -ENODEV;
+		goto free_netdev;
+	}
+
+	/* As per the point s3 in the below errata, SPI receive Ethernet frame
+	 * transfer may halt when starting the next frame in the same data block
+	 * (chunk) as the end of a previous frame. The RFA field should be
+	 * configured to 01b or 10b for proper operation. In these modes, only
+	 * one receive Ethernet frame will be placed in a single data block.
+	 * When the RFA field is written to 01b, received frames will be forced
+	 * to only start in the first word of the data block payload (SWO=0). As
+	 * recommended, enable zero align receive frame feature for proper
+	 * operation.
+	 *
+	 * https://ww1.microchip.com/downloads/aemDocuments/documents/AIS/ProductDocuments/Errata/LAN8650-1-Errata-80001075.pdf
+	 */
+	ret = oa_tc6_zero_align_receive_frame_enable(priv->tc6);
+	if (ret) {
+		dev_err(&spi->dev, "Failed to set ZARFE: %d\n", ret);
+		goto oa_tc6_exit;
+	}
+
+	/* Get the MAC address from the SPI device tree node */
+	if (device_get_ethdev_address(&spi->dev, netdev))
+		eth_hw_addr_random(netdev);
+
+	ret = lan865x_set_hw_macaddr(priv, netdev->dev_addr);
+	if (ret) {
+		dev_err(&spi->dev, "Failed to configure MAC: %d\n", ret);
+		goto oa_tc6_exit;
+	}
+
+	netdev->if_port = IF_PORT_10BASET;
+	netdev->irq = spi->irq;
+	netdev->netdev_ops = &lan865x_netdev_ops;
+	netdev->ethtool_ops = &lan865x_ethtool_ops;
+
+	ret = register_netdev(netdev);
+	if (ret) {
+		dev_err(&spi->dev, "Register netdev failed (ret = %d)", ret);
+		goto oa_tc6_exit;
+	}
+
+	return 0;
+
+oa_tc6_exit:
+	oa_tc6_exit(priv->tc6);
+free_netdev:
+	free_netdev(priv->netdev);
+	return ret;
+}
+
+static void lan865x_remove(struct spi_device *spi)
+{
+	struct lan865x_priv *priv = spi_get_drvdata(spi);
+
+	cancel_work_sync(&priv->multicast_work);
+	unregister_netdev(priv->netdev);
+	oa_tc6_exit(priv->tc6);
+	free_netdev(priv->netdev);
+}
+
+static const struct spi_device_id spidev_spi_ids[] = {
+	{ .name = "lan8650" },
+	{},
+};
+
+static const struct of_device_id lan865x_dt_ids[] = {
+	{ .compatible = "microchip,lan8650" },
+	{ /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, lan865x_dt_ids);
+
+static struct spi_driver lan865x_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table = lan865x_dt_ids,
+	 },
+	.probe = lan865x_probe,
+	.remove = lan865x_remove,
+	.id_table = spidev_spi_ids,
+};
+module_spi_driver(lan865x_driver);
+
+MODULE_DESCRIPTION(DRV_NAME " 10Base-T1S MACPHY Ethernet Driver");
+MODULE_AUTHOR("Parthiban Veerasooran <parthiban.veerasooran@microchip.com>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.3-3-g829e


From ac49b950bea9e76ae435b9f9c340a4da7261364b Mon Sep 17 00:00:00 2001
From: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Date: Mon, 9 Sep 2024 13:55:14 +0530
Subject: dt-bindings: net: add Microchip's LAN865X 10BASE-T1S MACPHY

The LAN8650/1 combines a Media Access Controller (MAC) and an Ethernet
PHY to enable 10BASE-T1S networks. The Ethernet Media Access Controller
(MAC) module implements a 10 Mbps half duplex Ethernet MAC, compatible
with the IEEE 802.3 standard and a 10BASE-T1S physical layer transceiver
integrated into the LAN8650/1. The communication between the Host and the
MAC-PHY is specified in the OPEN Alliance 10BASE-T1x MACPHY Serial
Interface (TC6).

Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Parthiban Veerasooran <Parthiban.Veerasooran@microchip.com>
Link: https://patch.msgid.link/20240909082514.262942-15-Parthiban.Veerasooran@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/microchip,lan8650.yaml | 74 ++++++++++++++++++++++
 MAINTAINERS                                        |  1 +
 2 files changed, 75 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/microchip,lan8650.yaml

diff --git a/Documentation/devicetree/bindings/net/microchip,lan8650.yaml b/Documentation/devicetree/bindings/net/microchip,lan8650.yaml
new file mode 100644
index 000000000000..61e11d4a07c4
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/microchip,lan8650.yaml
@@ -0,0 +1,74 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/microchip,lan8650.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Microchip LAN8650/1 10BASE-T1S MACPHY Ethernet Controllers
+
+maintainers:
+  - Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+
+description:
+  The LAN8650/1 combines a Media Access Controller (MAC) and an Ethernet
+  PHY to enable 10BASE‑T1S networks. The Ethernet Media Access Controller
+  (MAC) module implements a 10 Mbps half duplex Ethernet MAC, compatible
+  with the IEEE 802.3 standard and a 10BASE-T1S physical layer transceiver
+  integrated into the LAN8650/1. The communication between the Host and
+  the MAC-PHY is specified in the OPEN Alliance 10BASE-T1x MACPHY Serial
+  Interface (TC6).
+
+allOf:
+  - $ref: /schemas/net/ethernet-controller.yaml#
+  - $ref: /schemas/spi/spi-peripheral-props.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: microchip,lan8650
+      - items:
+          - const: microchip,lan8651
+          - const: microchip,lan8650
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description:
+      Interrupt from MAC-PHY asserted in the event of Receive Chunks
+      Available, Transmit Chunk Credits Available and Extended Status
+      Event.
+    maxItems: 1
+
+  spi-max-frequency:
+    minimum: 15000000
+    maximum: 25000000
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - spi-max-frequency
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/gpio/gpio.h>
+
+    spi {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      ethernet@0 {
+        compatible = "microchip,lan8651", "microchip,lan8650";
+        reg = <0>;
+        pinctrl-names = "default";
+        pinctrl-0 = <&eth0_pins>;
+        interrupt-parent = <&gpio>;
+        interrupts = <6 IRQ_TYPE_EDGE_FALLING>;
+        local-mac-address = [04 05 06 01 02 03];
+        spi-max-frequency = <15000000>;
+      };
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index 492807274c3b..2b65f8cec148 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14984,6 +14984,7 @@ MICROCHIP LAN8650/1 10BASE-T1S MACPHY ETHERNET DRIVER
 M:	Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+F:	Documentation/devicetree/bindings/net/microchip,lan8650.yaml
 F:	drivers/net/ethernet/microchip/lan865x/lan865x.c
 
 MICROCHIP LAN87xx/LAN937x T1 PHY DRIVER
-- 
cgit v1.3-3-g829e


From 94b0818fa63555a65f6ba107080659ea6bcca63e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 4 Sep 2024 18:22:37 -0700
Subject: can: bcm: Clear bo->bcm_proc_read after remove_proc_entry().

syzbot reported a warning in bcm_release(). [0]

The blamed change fixed another warning that is triggered when
connect() is issued again for a socket whose connect()ed device has
been unregistered.

However, if the socket is just close()d without the 2nd connect(), the
remaining bo->bcm_proc_read triggers unnecessary remove_proc_entry()
in bcm_release().

Let's clear bo->bcm_proc_read after remove_proc_entry() in bcm_notify().

[0]
name '4986'
WARNING: CPU: 0 PID: 5234 at fs/proc/generic.c:711 remove_proc_entry+0x2e7/0x5d0 fs/proc/generic.c:711
Modules linked in:
CPU: 0 UID: 0 PID: 5234 Comm: syz-executor606 Not tainted 6.11.0-rc5-syzkaller-00178-g5517ae241919 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024
RIP: 0010:remove_proc_entry+0x2e7/0x5d0 fs/proc/generic.c:711
Code: ff eb 05 e8 cb 1e 5e ff 48 8b 5c 24 10 48 c7 c7 e0 f7 aa 8e e8 2a 38 8e 09 90 48 c7 c7 60 3a 1b 8c 48 89 de e8 da 42 20 ff 90 <0f> 0b 90 90 48 8b 44 24 18 48 c7 44 24 40 0e 36 e0 45 49 c7 04 07
RSP: 0018:ffffc9000345fa20 EFLAGS: 00010246
RAX: 2a2d0aee2eb64600 RBX: ffff888032f1f548 RCX: ffff888029431e00
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffffc9000345fb08 R08: ffffffff8155b2f2 R09: 1ffff1101710519a
R10: dffffc0000000000 R11: ffffed101710519b R12: ffff888011d38640
R13: 0000000000000004 R14: 0000000000000000 R15: dffffc0000000000
FS:  0000000000000000(0000) GS:ffff8880b8800000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fcfb52722f0 CR3: 000000000e734000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 bcm_release+0x250/0x880 net/can/bcm.c:1578
 __sock_release net/socket.c:659 [inline]
 sock_close+0xbc/0x240 net/socket.c:1421
 __fput+0x24a/0x8a0 fs/file_table.c:422
 task_work_run+0x24f/0x310 kernel/task_work.c:228
 exit_task_work include/linux/task_work.h:40 [inline]
 do_exit+0xa2f/0x27f0 kernel/exit.c:882
 do_group_exit+0x207/0x2c0 kernel/exit.c:1031
 __do_sys_exit_group kernel/exit.c:1042 [inline]
 __se_sys_exit_group kernel/exit.c:1040 [inline]
 __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1040
 x64_sys_call+0x2634/0x2640 arch/x86/include/generated/asm/syscalls_64.h:232
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fcfb51ee969
Code: Unable to access opcode bytes at 0x7fcfb51ee93f.
RSP: 002b:00007ffce0109ca8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007fcfb51ee969
RDX: 000000000000003c RSI: 00000000000000e7 RDI: 0000000000000001
RBP: 00007fcfb526f3b0 R08: ffffffffffffffb8 R09: 0000555500000000
R10: 0000555500000000 R11: 0000000000000246 R12: 00007fcfb526f3b0
R13: 0000000000000000 R14: 00007fcfb5271ee0 R15: 00007fcfb51bf160
 </TASK>

Fixes: 76fe372ccb81 ("can: bcm: Remove proc entry when dev is unregistered.")
Reported-by: syzbot+0532ac7a06fb1a03187e@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=0532ac7a06fb1a03187e
Tested-by: syzbot+0532ac7a06fb1a03187e@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20240905012237.79683-1-kuniyu@amazon.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/bcm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c
index 46d3ec3aa44b..217049fa496e 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1471,8 +1471,10 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 		/* remove device reference, if this is our bound device */
 		if (bo->bound && bo->ifindex == dev->ifindex) {
 #if IS_ENABLED(CONFIG_PROC_FS)
-			if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read)
+			if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) {
 				remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir);
+				bo->bcm_proc_read = NULL;
+			}
 #endif
 			bo->bound   = 0;
 			bo->ifindex = 0;
-- 
cgit v1.3-3-g829e


From 75b3189540578f96b4996e4849b6649998f49455 Mon Sep 17 00:00:00 2001
From: Stefan Mätje <stefan.maetje@esd.eu>
Date: Thu, 5 Sep 2024 00:27:40 +0200
Subject: can: esd_usb: Remove CAN_CTRLMODE_3_SAMPLES for CAN-USB/3-FD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the CAN_CTRLMODE_3_SAMPLES announcement for CAN-USB/3-FD devices
because these devices don't support it.

The hardware has a Microchip SAM E70 microcontroller that uses a Bosch
MCAN IP core as CAN FD controller. But this MCAN core doesn't support
triple sampling.

Fixes: 80662d943075 ("can: esd_usb: Add support for esd CAN-USB/3")
Cc: stable@vger.kernel.org
Signed-off-by: Stefan Mätje <stefan.maetje@esd.eu>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20240904222740.2985864-2-stefan.maetje@esd.eu
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/esd_usb.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
index 41a0e4261d15..03ad10b01867 100644
--- a/drivers/net/can/usb/esd_usb.c
+++ b/drivers/net/can/usb/esd_usb.c
@@ -3,7 +3,7 @@
  * CAN driver for esd electronics gmbh CAN-USB/2, CAN-USB/3 and CAN-USB/Micro
  *
  * Copyright (C) 2010-2012 esd electronic system design gmbh, Matthias Fuchs <socketcan@esd.eu>
- * Copyright (C) 2022-2023 esd electronics gmbh, Frank Jungclaus <frank.jungclaus@esd.eu>
+ * Copyright (C) 2022-2024 esd electronics gmbh, Frank Jungclaus <frank.jungclaus@esd.eu>
  */
 
 #include <linux/can.h>
@@ -1116,9 +1116,6 @@ static int esd_usb_3_set_bittiming(struct net_device *netdev)
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
 		flags |= ESD_USB_3_BAUDRATE_FLAG_LOM;
 
-	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
-		flags |= ESD_USB_3_BAUDRATE_FLAG_TRS;
-
 	baud_x->nom.brp = cpu_to_le16(nom_bt->brp & (nom_btc->brp_max - 1));
 	baud_x->nom.sjw = cpu_to_le16(nom_bt->sjw & (nom_btc->sjw_max - 1));
 	baud_x->nom.tseg1 = cpu_to_le16((nom_bt->prop_seg + nom_bt->phase_seg1)
@@ -1219,7 +1216,6 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
 	switch (le16_to_cpu(dev->udev->descriptor.idProduct)) {
 	case ESD_USB_CANUSB3_PRODUCT_ID:
 		priv->can.clock.freq = ESD_USB_3_CAN_CLOCK;
-		priv->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
 		priv->can.bittiming_const = &esd_usb_3_nom_bittiming_const;
 		priv->can.data_bittiming_const = &esd_usb_3_data_bittiming_const;
-- 
cgit v1.3-3-g829e


From d0fa06408ccf96b1d3d93d97fad6618e942efd38 Mon Sep 17 00:00:00 2001
From: Martin Jocic <martin.jocic@kvaser.com>
Date: Mon, 9 Sep 2024 13:35:12 +0200
Subject: can: kvaser_pciefd: Enable 64-bit DMA addressing

Enabling 64-bit addressing for DMA buffers will prevent issues
on some memory constrained platforms like e.g. Raspberry Pi 5,
where the driver won't load because it cannot allocate enough
continuous memory in the default 32-bit memory address range.

Signed-off-by: Martin Jocic <martin.jocic@kvaser.com>
Link: https://patch.msgid.link/d7340f78e3db305bfeeb8229d2dd1c9077e10b92.1725875278.git.martin.jocic@kvaser.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/kvaser_pciefd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 9ffc3ffb4e8f..f86c9671a03a 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -1104,6 +1104,9 @@ static int kvaser_pciefd_setup_dma(struct kvaser_pciefd *pcie)
 
 	/* Disable the DMA */
 	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
+
+	dma_set_mask_and_coherent(&pcie->pci->dev, DMA_BIT_MASK(64));
+
 	for (i = 0; i < KVASER_PCIEFD_DMA_COUNT; i++) {
 		pcie->dma_data[i] = dmam_alloc_coherent(&pcie->pci->dev,
 							KVASER_PCIEFD_DMA_SIZE,
-- 
cgit v1.3-3-g829e


From 801ad2f87b0c6d0c34a75a4efd6bfd3a2d9f9298 Mon Sep 17 00:00:00 2001
From: Jake Hamby <Jake.Hamby@Teledyne.com>
Date: Fri, 6 Sep 2024 23:19:51 +0000
Subject: can: m_can: enable NAPI before enabling interrupts

If an interrupt (RX-complete or error flag) is set when bringing up
the CAN device, e.g. due to CAN bus traffic before initializing the
device, when m_can_start() is called and interrupts are enabled,
m_can_isr() is called immediately, which disables all CAN interrupts
and calls napi_schedule().

Because napi_enable() isn't called until later in m_can_open(), the
call to napi_schedule() never schedules the m_can_poll() callback and
the device is left with interrupts disabled and can't receive any CAN
packets until rebooted.

This can be verified by running "cansend" from another device before
setting the bitrate and calling "ip link set up can0" on the test
device. Adding debug lines to m_can_isr() shows it's called with flags
(IR_EP | IR_EW | IR_CRCE), which calls m_can_disable_all_interrupts()
and napi_schedule(), and then m_can_poll() is never called.

Move the call to napi_enable() above the call to m_can_start() to
enable any initial interrupt flags to be handled by m_can_poll() so
that interrupts are reenabled. Add a call to napi_disable() in the
error handling section of m_can_open(), to handle the case where later
functions return errors.

Also, in m_can_close(), move the call to napi_disable() below the call
to m_can_stop() to ensure all interrupts are handled when bringing
down the device. This race condition is much less likely to occur.

Tested on a Microchip SAMA7G54 MPU. The fix should be applicable to
any SoC with a Bosch M_CAN controller.

Signed-off-by: Jake Hamby <Jake.Hamby@Teledyne.com>
Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Link: https://patch.msgid.link/20240910-can-m_can-fix-ifup-v3-1-6c1720ba45ce@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 012c3d22b01d..c1a07013433e 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1763,9 +1763,6 @@ static int m_can_close(struct net_device *dev)
 
 	netif_stop_queue(dev);
 
-	if (!cdev->is_peripheral)
-		napi_disable(&cdev->napi);
-
 	m_can_stop(dev);
 	m_can_clk_stop(cdev);
 	free_irq(dev->irq, dev);
@@ -1776,6 +1773,8 @@ static int m_can_close(struct net_device *dev)
 		destroy_workqueue(cdev->tx_wq);
 		cdev->tx_wq = NULL;
 		can_rx_offload_disable(&cdev->offload);
+	} else {
+		napi_disable(&cdev->napi);
 	}
 
 	close_candev(dev);
@@ -2030,6 +2029,8 @@ static int m_can_open(struct net_device *dev)
 
 	if (cdev->is_peripheral)
 		can_rx_offload_enable(&cdev->offload);
+	else
+		napi_enable(&cdev->napi);
 
 	/* register interrupt handler */
 	if (cdev->is_peripheral) {
@@ -2063,9 +2064,6 @@ static int m_can_open(struct net_device *dev)
 	if (err)
 		goto exit_start_fail;
 
-	if (!cdev->is_peripheral)
-		napi_enable(&cdev->napi);
-
 	netif_start_queue(dev);
 
 	return 0;
@@ -2079,6 +2077,8 @@ exit_irq_fail:
 out_wq_fail:
 	if (cdev->is_peripheral)
 		can_rx_offload_disable(&cdev->offload);
+	else
+		napi_disable(&cdev->napi);
 	close_candev(dev);
 exit_disable_clks:
 	m_can_clk_stop(cdev);
-- 
cgit v1.3-3-g829e


From 2c09b50efcad985cf920ca88baa9aa52b1999dcc Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Mon, 9 Sep 2024 15:07:41 +0200
Subject: can: m_can: m_can_close(): stop clocks after device has been shut
 down

After calling m_can_stop() an interrupt may be pending or NAPI might
still be executed. This means the driver might still touch registers
of the IP core after the clocks have been disabled. This is not good
practice and might lead to aborts depending on the SoC integration.

To avoid these potential problems, make m_can_close() symmetric to
m_can_open(), i.e. stop the clocks at the end, right before shutting
down the transceiver.

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Link: https://patch.msgid.link/20240910-can-m_can-fix-ifup-v3-2-6c1720ba45ce@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index c1a07013433e..7fec04b024d5 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -1764,7 +1764,6 @@ static int m_can_close(struct net_device *dev)
 	netif_stop_queue(dev);
 
 	m_can_stop(dev);
-	m_can_clk_stop(cdev);
 	free_irq(dev->irq, dev);
 
 	m_can_clean(dev);
@@ -1779,6 +1778,7 @@ static int m_can_close(struct net_device *dev)
 
 	close_candev(dev);
 
+	m_can_clk_stop(cdev);
 	phy_power_off(cdev->transceiver);
 
 	return 0;
-- 
cgit v1.3-3-g829e


From 9a53d1ff631f5b85019bb243ccb8c66af5010e97 Mon Sep 17 00:00:00 2001
From: Scott Ehlert <ehlert@battelle.org>
Date: Thu, 5 Sep 2024 11:01:00 -0700
Subject: Bluetooth: btsdio: Do not bind to non-removable CYW4373

CYW4373 devices soldered onto the PCB (non-removable),
use a UART connection for Bluetooth and the advertised btsdio
support as an SDIO function should be ignored.

Signed-off-by: Scott Ehlert <ehlert@battelle.org>
Signed-off-by: Tim Harvey <tharvey@gateworks.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btsdio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c
index fdcfe9c50313..a69feb08486a 100644
--- a/drivers/bluetooth/btsdio.c
+++ b/drivers/bluetooth/btsdio.c
@@ -295,6 +295,7 @@ static int btsdio_probe(struct sdio_func *func,
 		case SDIO_DEVICE_ID_BROADCOM_4345:
 		case SDIO_DEVICE_ID_BROADCOM_43455:
 		case SDIO_DEVICE_ID_BROADCOM_4356:
+		case SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373:
 			return -ENODEV;
 		}
 	}
-- 
cgit v1.3-3-g829e


From 39e4bfb466741a1364e0f690ea22961b93d2e73b Mon Sep 17 00:00:00 2001
From: Michael Burch <me@michaelburch.net>
Date: Sun, 1 Sep 2024 04:28:47 +0000
Subject: Bluetooth: btusb: Add 2 USB HW IDs for MT7925 (0xe118/e)

Add 2 USB HW IDs for MT7925 (0xe118/e) to ensure proper recognition.

These HW IDs are extracted from Windows driver inf file:
https://dlcdnets.asus.com/pub/ASUS/nb/Image/Driver/Bluetooth/39389/Bluetooth_DCH_MediaTek_B_V1.1037.0.433Sub2_39389.exe?model=H7606WV

Patch has been tested successfully on an Asus ProArt P16 model H7606WV.
Controller is recognized devices pair successfully.

Signed-off-by: Michael Burch <me@michaelburch.net>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 36a869a57910..d9286feacef8 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -632,6 +632,10 @@ static const struct usb_device_id quirks_table[] = {
 	/* Additional MediaTek MT7925 Bluetooth devices */
 	{ USB_DEVICE(0x0489, 0xe113), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe118), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11e), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3602), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3603), .driver_info = BTUSB_MEDIATEK |
-- 
cgit v1.3-3-g829e


From 7b05933340f4490ef5b09e84d644d12484b05fdf Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 9 Sep 2024 16:51:52 -0400
Subject: Bluetooth: btusb: Fix not handling ZPL/short-transfer

Requesting transfers of the exact same size of wMaxPacketSize may result
in ZPL/short-transfer since the USB stack cannot handle it as we are
limiting the buffer size to be the same as wMaxPacketSize.

Also, in terms of throughput this change has the same effect to
interrupt endpoint as 290ba200815f "Bluetooth: Improve USB driver throughput
by increasing the frame size" had for the bulk endpoint, so users of the
advertisement bearer (e.g. BT Mesh) may benefit from this change.

Fixes: 5e23b923da03 ("[Bluetooth] Add generic driver for Bluetooth USB devices")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Tested-by: Kiran K <kiran.k@intel.com>
---
 drivers/bluetooth/btusb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index d9286feacef8..6c9c761d5b93 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -1345,7 +1345,10 @@ static int btusb_submit_intr_urb(struct hci_dev *hdev, gfp_t mem_flags)
 	if (!urb)
 		return -ENOMEM;
 
-	size = le16_to_cpu(data->intr_ep->wMaxPacketSize);
+	/* Use maximum HCI Event size so the USB stack handles
+	 * ZPL/short-transfer automatically.
+	 */
+	size = HCI_MAX_EVENT_SIZE;
 
 	buf = kmalloc(size, mem_flags);
 	if (!buf) {
-- 
cgit v1.3-3-g829e


From 7ffaa200251871980af12e57649ad57c70bf0f43 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Thu, 12 Sep 2024 16:21:00 +0530
Subject: Bluetooth: btintel_pcie: Allocate memory for driver private data

Fix driver not allocating memory for struct btintel_data which is used
to store internal data.

Fixes: 6e65a09f9275 ("Bluetooth: btintel_pcie: Add *setup* function to download firmware")
Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index d255bdf777b4..fda47948c35d 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -1224,7 +1224,7 @@ static int btintel_pcie_setup_hdev(struct btintel_pcie_data *data)
 	int err;
 	struct hci_dev *hdev;
 
-	hdev = hci_alloc_dev();
+	hdev = hci_alloc_dev_priv(sizeof(struct btintel_data));
 	if (!hdev)
 		return -ENOMEM;
 
-- 
cgit v1.3-3-g829e


From 49f66e1216ff9d616247189a90581306de641da9 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 9 Sep 2024 11:47:03 +0300
Subject: net: ena: Add ENA Express metrics support

ENA Express metrics, called `ena_srd` are exposed to
customers via `ethtool`.
The metrics allow customers to check the configuration
(mode), tx/rx counters as well as resource utilization.

The documentation is also updated to provide a general
explanation about ENA Express as well as links for further
information about metrics and configurations.

Signed-off-by: Igor Chauskin <igorch@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Link: https://patch.msgid.link/20240909084704.13856-2-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../device_drivers/ethernet/amazon/ena.rst         |  5 ++
 drivers/net/ethernet/amazon/ena/ena_admin_defs.h   | 42 +++++++++++
 drivers/net/ethernet/amazon/ena/ena_com.c          | 21 ++++++
 drivers/net/ethernet/amazon/ena/ena_com.h          |  9 +++
 drivers/net/ethernet/amazon/ena/ena_ethtool.c      | 84 ++++++++++++++++------
 drivers/net/ethernet/amazon/ena/ena_netdev.c       | 13 ----
 drivers/net/ethernet/amazon/ena/ena_netdev.h       |  2 +-
 7 files changed, 142 insertions(+), 34 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
index a4c7d0c65fd7..4561e8ab9e08 100644
--- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
+++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst
@@ -230,6 +230,11 @@ per-queue stats) from the device.
 
 In addition the driver logs the stats to syslog upon device reset.
 
+On supported instance types, the statistics will also include the
+ENA Express data (fields prefixed with `ena_srd`). For a complete
+documentation of ENA Express data refer to
+https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ena-express.html#ena-express-monitor
+
 MTU
 ===
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 6de0d590be34..74772b0068ea 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -51,6 +51,8 @@ enum ena_admin_aq_feature_id {
 /* device capabilities */
 enum ena_admin_aq_caps_id {
 	ENA_ADMIN_ENI_STATS                         = 0,
+	/* ENA SRD customer metrics */
+	ENA_ADMIN_ENA_SRD_INFO                      = 1,
 };
 
 enum ena_admin_placement_policy_type {
@@ -99,6 +101,8 @@ enum ena_admin_get_stats_type {
 	ENA_ADMIN_GET_STATS_TYPE_EXTENDED           = 1,
 	/* extra HW stats for specific network interface */
 	ENA_ADMIN_GET_STATS_TYPE_ENI                = 2,
+	/* extra HW stats for ENA SRD */
+	ENA_ADMIN_GET_STATS_TYPE_ENA_SRD            = 3,
 };
 
 enum ena_admin_get_stats_scope {
@@ -106,6 +110,16 @@ enum ena_admin_get_stats_scope {
 	ENA_ADMIN_ETH_TRAFFIC                       = 1,
 };
 
+/* ENA SRD configuration for ENI */
+enum ena_admin_ena_srd_flags {
+	/* Feature enabled */
+	ENA_ADMIN_ENA_SRD_ENABLED                   = BIT(0),
+	/* UDP support enabled */
+	ENA_ADMIN_ENA_SRD_UDP_ENABLED               = BIT(1),
+	/* Bypass Rx UDP ordering */
+	ENA_ADMIN_ENA_SRD_UDP_ORDERING_BYPASS_ENABLED = BIT(2),
+};
+
 struct ena_admin_aq_common_desc {
 	/* 11:0 : command_id
 	 * 15:12 : reserved12
@@ -419,6 +433,32 @@ struct ena_admin_eni_stats {
 	u64 linklocal_allowance_exceeded;
 };
 
+struct ena_admin_ena_srd_stats {
+	/* Number of packets transmitted over ENA SRD */
+	u64 ena_srd_tx_pkts;
+
+	/* Number of packets transmitted or could have been
+	 * transmitted over ENA SRD
+	 */
+	u64 ena_srd_eligible_tx_pkts;
+
+	/* Number of packets received over ENA SRD */
+	u64 ena_srd_rx_pkts;
+
+	/* Percentage of the ENA SRD resources that is in use */
+	u64 ena_srd_resource_utilization;
+};
+
+/* ENA SRD Statistics Command */
+struct ena_admin_ena_srd_info {
+	/* ENA SRD configuration bitmap. See ena_admin_ena_srd_flags for
+	 * details
+	 */
+	u64 flags;
+
+	struct ena_admin_ena_srd_stats ena_srd_stats;
+};
+
 struct ena_admin_acq_get_stats_resp {
 	struct ena_admin_acq_common_desc acq_common_desc;
 
@@ -428,6 +468,8 @@ struct ena_admin_acq_get_stats_resp {
 		struct ena_admin_basic_stats basic_stats;
 
 		struct ena_admin_eni_stats eni_stats;
+
+		struct ena_admin_ena_srd_info ena_srd_info;
 	} u;
 };
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 713a595370bf..3cc3830de482 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2152,6 +2152,27 @@ int ena_com_get_eni_stats(struct ena_com_dev *ena_dev,
 	return ret;
 }
 
+int ena_com_get_ena_srd_info(struct ena_com_dev *ena_dev,
+			     struct ena_admin_ena_srd_info *info)
+{
+	struct ena_com_stats_ctx ctx;
+	int ret;
+
+	if (!ena_com_get_cap(ena_dev, ENA_ADMIN_ENA_SRD_INFO)) {
+		netdev_err(ena_dev->net_device, "Capability %d isn't supported\n",
+			   ENA_ADMIN_ENA_SRD_INFO);
+		return -EOPNOTSUPP;
+	}
+
+	memset(&ctx, 0x0, sizeof(ctx));
+	ret = ena_get_dev_stats(ena_dev, &ctx, ENA_ADMIN_GET_STATS_TYPE_ENA_SRD);
+	if (likely(ret == 0))
+		memcpy(info, &ctx.get_resp.u.ena_srd_info,
+		       sizeof(ctx.get_resp.u.ena_srd_info));
+
+	return ret;
+}
+
 int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev,
 				struct ena_admin_basic_stats *stats)
 {
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 924f03f5a6c7..372066e039bf 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -595,6 +595,15 @@ int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev,
 int ena_com_get_eni_stats(struct ena_com_dev *ena_dev,
 			  struct ena_admin_eni_stats *stats);
 
+/* ena_com_get_ena_srd_info - Get ENA SRD network interface statistics
+ * @ena_dev: ENA communication layer struct
+ * @info: ena srd stats and flags
+ *
+ * @return: 0 on Success and negative value otherwise.
+ */
+int ena_com_get_ena_srd_info(struct ena_com_dev *ena_dev,
+			     struct ena_admin_ena_srd_info *info);
+
 /* ena_com_set_dev_mtu - Configure the device mtu.
  * @ena_dev: ENA communication layer struct
  * @mtu: mtu value
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index b24cc3f05248..5efd3e43ffa6 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -41,6 +41,14 @@ struct ena_stats {
 #define ENA_STAT_ENI_ENTRY(stat) \
 	ENA_STAT_HW_ENTRY(stat, eni_stats)
 
+#define ENA_STAT_ENA_SRD_ENTRY(stat) \
+	ENA_STAT_HW_ENTRY(stat, ena_srd_stats)
+
+#define ENA_STAT_ENA_SRD_MODE_ENTRY(stat) { \
+	.name = #stat, \
+	.stat_offset = offsetof(struct ena_admin_ena_srd_info, flags) / sizeof(u64) \
+}
+
 static const struct ena_stats ena_stats_global_strings[] = {
 	ENA_STAT_GLOBAL_ENTRY(tx_timeout),
 	ENA_STAT_GLOBAL_ENTRY(suspend),
@@ -60,6 +68,14 @@ static const struct ena_stats ena_stats_eni_strings[] = {
 	ENA_STAT_ENI_ENTRY(linklocal_allowance_exceeded),
 };
 
+static const struct ena_stats ena_srd_info_strings[] = {
+	ENA_STAT_ENA_SRD_MODE_ENTRY(ena_srd_mode),
+	ENA_STAT_ENA_SRD_ENTRY(ena_srd_tx_pkts),
+	ENA_STAT_ENA_SRD_ENTRY(ena_srd_eligible_tx_pkts),
+	ENA_STAT_ENA_SRD_ENTRY(ena_srd_rx_pkts),
+	ENA_STAT_ENA_SRD_ENTRY(ena_srd_resource_utilization)
+};
+
 static const struct ena_stats ena_stats_tx_strings[] = {
 	ENA_STAT_TX_ENTRY(cnt),
 	ENA_STAT_TX_ENTRY(bytes),
@@ -112,7 +128,8 @@ static const struct ena_stats ena_stats_ena_com_strings[] = {
 #define ENA_STATS_ARRAY_TX		ARRAY_SIZE(ena_stats_tx_strings)
 #define ENA_STATS_ARRAY_RX		ARRAY_SIZE(ena_stats_rx_strings)
 #define ENA_STATS_ARRAY_ENA_COM		ARRAY_SIZE(ena_stats_ena_com_strings)
-#define ENA_STATS_ARRAY_ENI(adapter)	ARRAY_SIZE(ena_stats_eni_strings)
+#define ENA_STATS_ARRAY_ENI		ARRAY_SIZE(ena_stats_eni_strings)
+#define ENA_STATS_ARRAY_ENA_SRD		ARRAY_SIZE(ena_srd_info_strings)
 
 static void ena_safe_update_stat(u64 *src, u64 *dst,
 				 struct u64_stats_sync *syncp)
@@ -179,7 +196,7 @@ static void ena_dev_admin_queue_stats(struct ena_adapter *adapter, u64 **data)
 
 static void ena_get_stats(struct ena_adapter *adapter,
 			  u64 *data,
-			  bool eni_stats_needed)
+			  bool hw_stats_needed)
 {
 	const struct ena_stats *ena_stats;
 	u64 *ptr;
@@ -193,15 +210,37 @@ static void ena_get_stats(struct ena_adapter *adapter,
 		ena_safe_update_stat(ptr, data++, &adapter->syncp);
 	}
 
-	if (eni_stats_needed) {
-		ena_update_hw_stats(adapter);
-		for (i = 0; i < ENA_STATS_ARRAY_ENI(adapter); i++) {
-			ena_stats = &ena_stats_eni_strings[i];
+	if (hw_stats_needed) {
+		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS)) {
+			ena_com_get_eni_stats(adapter->ena_dev, &adapter->eni_stats);
+			/* Updating regardless of rc - once we told ethtool how many stats we have
+			 * it will print that much stats. We can't leave holes in the stats
+			 */
+			for (i = 0; i < ENA_STATS_ARRAY_ENI; i++) {
+				ena_stats = &ena_stats_eni_strings[i];
 
-			ptr = (u64 *)&adapter->eni_stats +
-				ena_stats->stat_offset;
+				ptr = (u64 *)&adapter->eni_stats +
+					ena_stats->stat_offset;
 
+				ena_safe_update_stat(ptr, data++, &adapter->syncp);
+			}
+		}
+
+		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENA_SRD_INFO)) {
+			ena_com_get_ena_srd_info(adapter->ena_dev, &adapter->ena_srd_info);
+			/* Get ENA SRD mode */
+			ptr = (u64 *)&adapter->ena_srd_info;
 			ena_safe_update_stat(ptr, data++, &adapter->syncp);
+			for (i = 1; i < ENA_STATS_ARRAY_ENA_SRD; i++) {
+				ena_stats = &ena_srd_info_strings[i];
+				/* Wrapped within an outer struct - need to accommodate an
+				 * additional offset of the ENA SRD mode that was already processed
+				 */
+				ptr = (u64 *)&adapter->ena_srd_info +
+					ena_stats->stat_offset + 1;
+
+				ena_safe_update_stat(ptr, data++, &adapter->syncp);
+			}
 		}
 	}
 
@@ -214,9 +253,8 @@ static void ena_get_ethtool_stats(struct net_device *netdev,
 				  u64 *data)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
-	struct ena_com_dev *dev = adapter->ena_dev;
 
-	ena_get_stats(adapter, data, ena_com_get_cap(dev, ENA_ADMIN_ENI_STATS));
+	ena_get_stats(adapter, data, true);
 }
 
 static int ena_get_sw_stats_count(struct ena_adapter *adapter)
@@ -228,9 +266,8 @@ static int ena_get_sw_stats_count(struct ena_adapter *adapter)
 
 static int ena_get_hw_stats_count(struct ena_adapter *adapter)
 {
-	bool supported = ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS);
-
-	return ENA_STATS_ARRAY_ENI(adapter) * supported;
+	return ENA_STATS_ARRAY_ENI * ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS) +
+	       ENA_STATS_ARRAY_ENA_SRD * ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENA_SRD_INFO);
 }
 
 int ena_get_sset_count(struct net_device *netdev, int sset)
@@ -291,7 +328,7 @@ static void ena_com_dev_strings(u8 **data)
 
 static void ena_get_strings(struct ena_adapter *adapter,
 			    u8 *data,
-			    bool eni_stats_needed)
+			    bool hw_stats_needed)
 {
 	const struct ena_stats *ena_stats;
 	int i;
@@ -301,10 +338,18 @@ static void ena_get_strings(struct ena_adapter *adapter,
 		ethtool_puts(&data, ena_stats->name);
 	}
 
-	if (eni_stats_needed) {
-		for (i = 0; i < ENA_STATS_ARRAY_ENI(adapter); i++) {
-			ena_stats = &ena_stats_eni_strings[i];
-			ethtool_puts(&data, ena_stats->name);
+	if (hw_stats_needed) {
+		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS)) {
+			for (i = 0; i < ENA_STATS_ARRAY_ENI; i++) {
+				ena_stats = &ena_stats_eni_strings[i];
+				ethtool_puts(&data, ena_stats->name);
+			}
+		}
+		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENA_SRD_INFO)) {
+			for (i = 0; i < ENA_STATS_ARRAY_ENA_SRD; i++) {
+				ena_stats = &ena_srd_info_strings[i];
+				ethtool_puts(&data, ena_stats->name);
+			}
 		}
 	}
 
@@ -317,11 +362,10 @@ static void ena_get_ethtool_strings(struct net_device *netdev,
 				    u8 *data)
 {
 	struct ena_adapter *adapter = netdev_priv(netdev);
-	struct ena_com_dev *dev = adapter->ena_dev;
 
 	switch (sset) {
 	case ETH_SS_STATS:
-		ena_get_strings(adapter, data, ena_com_get_cap(dev, ENA_ADMIN_ENI_STATS));
+		ena_get_strings(adapter, data, true);
 		break;
 	}
 }
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 184b6e6cbed4..0883c9a230f2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2798,19 +2798,6 @@ err:
 	ena_com_delete_debug_area(adapter->ena_dev);
 }
 
-int ena_update_hw_stats(struct ena_adapter *adapter)
-{
-	int rc;
-
-	rc = ena_com_get_eni_stats(adapter->ena_dev, &adapter->eni_stats);
-	if (rc) {
-		netdev_err(adapter->netdev, "Failed to get ENI stats\n");
-		return rc;
-	}
-
-	return 0;
-}
-
 static void ena_get_stats64(struct net_device *netdev,
 			    struct rtnl_link_stats64 *stats)
 {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index d59509747d1a..6e12ae3b12e5 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -373,6 +373,7 @@ struct ena_adapter {
 	struct u64_stats_sync syncp;
 	struct ena_stats_dev dev_stats;
 	struct ena_admin_eni_stats eni_stats;
+	struct ena_admin_ena_srd_info ena_srd_info;
 
 	/* last queue index that was checked for uncompleted tx packets */
 	u32 last_monitored_tx_qid;
@@ -390,7 +391,6 @@ void ena_dump_stats_to_dmesg(struct ena_adapter *adapter);
 
 void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf);
 
-int ena_update_hw_stats(struct ena_adapter *adapter);
 
 int ena_update_queue_params(struct ena_adapter *adapter,
 			    u32 new_tx_size,
-- 
cgit v1.3-3-g829e


From 403cdc41773b4b2c58e4f204ffe72f9aa1d0b9a1 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 9 Sep 2024 11:47:04 +0300
Subject: net: ena: Extend customer metrics reporting support

ENA currently supports the following customer metrics:
- `bw_in_allowance_exceeded`
- `bw_out_allowance_exceeded`
- `conntrack_allowance_exceeded`
- `linklocal_allowance_exceeded`
- `pps_allowance_exceeded`

This patch adds a new metric named:
`conntrack_allowance_available`.

Information about these metrics is available in [1].

In addition, the interface between the driver and the
device has been upgraded to allow more flexibility and
expendability to additional metrics in the future.

[1]: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/monitoring-network-performance-ena.html#network-performance-metrics

Signed-off-by: Ron Beider <rbeider@amazon.com>
Signed-off-by: Shahar Itzko <itzko@amazon.com>
Signed-off-by: David Arinzon <darinzon@amazon.com>
Link: https://patch.msgid.link/20240909084704.13856-3-darinzon@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_admin_defs.h |  30 +++++
 drivers/net/ethernet/amazon/ena/ena_com.c        | 154 +++++++++++++++++----
 drivers/net/ethernet/amazon/ena/ena_com.h        |  59 ++++++++
 drivers/net/ethernet/amazon/ena/ena_ethtool.c    | 165 ++++++++++++++++-------
 drivers/net/ethernet/amazon/ena/ena_netdev.c     |  14 +-
 5 files changed, 344 insertions(+), 78 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 74772b0068ea..9d9fa6559354 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -7,6 +7,21 @@
 
 #define ENA_ADMIN_RSS_KEY_PARTS              10
 
+#define ENA_ADMIN_CUSTOMER_METRICS_SUPPORT_MASK 0x3F
+#define ENA_ADMIN_CUSTOMER_METRICS_MIN_SUPPORT_MASK 0x1F
+
+ /* customer metrics - in correlation with
+  * ENA_ADMIN_CUSTOMER_METRICS_SUPPORT_MASK
+  */
+enum ena_admin_customer_metrics_id {
+	ENA_ADMIN_BW_IN_ALLOWANCE_EXCEEDED         = 0,
+	ENA_ADMIN_BW_OUT_ALLOWANCE_EXCEEDED        = 1,
+	ENA_ADMIN_PPS_ALLOWANCE_EXCEEDED           = 2,
+	ENA_ADMIN_CONNTRACK_ALLOWANCE_EXCEEDED     = 3,
+	ENA_ADMIN_LINKLOCAL_ALLOWANCE_EXCEEDED     = 4,
+	ENA_ADMIN_CONNTRACK_ALLOWANCE_AVAILABLE    = 5,
+};
+
 enum ena_admin_aq_opcode {
 	ENA_ADMIN_CREATE_SQ                         = 1,
 	ENA_ADMIN_DESTROY_SQ                        = 2,
@@ -53,6 +68,7 @@ enum ena_admin_aq_caps_id {
 	ENA_ADMIN_ENI_STATS                         = 0,
 	/* ENA SRD customer metrics */
 	ENA_ADMIN_ENA_SRD_INFO                      = 1,
+	ENA_ADMIN_CUSTOMER_METRICS                  = 2,
 };
 
 enum ena_admin_placement_policy_type {
@@ -103,6 +119,7 @@ enum ena_admin_get_stats_type {
 	ENA_ADMIN_GET_STATS_TYPE_ENI                = 2,
 	/* extra HW stats for ENA SRD */
 	ENA_ADMIN_GET_STATS_TYPE_ENA_SRD            = 3,
+	ENA_ADMIN_GET_STATS_TYPE_CUSTOMER_METRICS   = 4,
 };
 
 enum ena_admin_get_stats_scope {
@@ -377,6 +394,9 @@ struct ena_admin_aq_get_stats_cmd {
 	 * stats of other device
 	 */
 	u16 device_id;
+
+	/* a bitmap representing the requested metric values */
+	u64 requested_metrics;
 };
 
 /* Basic Statistics Command. */
@@ -459,6 +479,14 @@ struct ena_admin_ena_srd_info {
 	struct ena_admin_ena_srd_stats ena_srd_stats;
 };
 
+/* Customer Metrics Command. */
+struct ena_admin_customer_metrics {
+	/* A bitmap representing the reported customer metrics according to
+	 * the order they are reported
+	 */
+	u64 reported_metrics;
+};
+
 struct ena_admin_acq_get_stats_resp {
 	struct ena_admin_acq_common_desc acq_common_desc;
 
@@ -470,6 +498,8 @@ struct ena_admin_acq_get_stats_resp {
 		struct ena_admin_eni_stats eni_stats;
 
 		struct ena_admin_ena_srd_info ena_srd_info;
+
+		struct ena_admin_customer_metrics customer_metrics;
 	} u;
 };
 
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 3cc3830de482..d958cda9e58b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -1881,6 +1881,56 @@ int ena_com_get_link_params(struct ena_com_dev *ena_dev,
 	return ena_com_get_feature(ena_dev, resp, ENA_ADMIN_LINK_CONFIG, 0);
 }
 
+static int ena_get_dev_stats(struct ena_com_dev *ena_dev,
+			     struct ena_com_stats_ctx *ctx,
+			     enum ena_admin_get_stats_type type)
+{
+	struct ena_admin_acq_get_stats_resp *get_resp = &ctx->get_resp;
+	struct ena_admin_aq_get_stats_cmd *get_cmd = &ctx->get_cmd;
+	struct ena_com_admin_queue *admin_queue;
+	int ret;
+
+	admin_queue = &ena_dev->admin_queue;
+
+	get_cmd->aq_common_descriptor.opcode = ENA_ADMIN_GET_STATS;
+	get_cmd->aq_common_descriptor.flags = 0;
+	get_cmd->type = type;
+
+	ret = ena_com_execute_admin_command(admin_queue,
+					    (struct ena_admin_aq_entry *)get_cmd,
+					    sizeof(*get_cmd),
+					    (struct ena_admin_acq_entry *)get_resp,
+					    sizeof(*get_resp));
+
+	if (unlikely(ret))
+		netdev_err(ena_dev->net_device, "Failed to get stats. error: %d\n", ret);
+
+	return ret;
+}
+
+static void ena_com_set_supported_customer_metrics(struct ena_com_dev *ena_dev)
+{
+	struct ena_customer_metrics *customer_metrics;
+	struct ena_com_stats_ctx ctx;
+	int ret;
+
+	customer_metrics = &ena_dev->customer_metrics;
+	if (!ena_com_get_cap(ena_dev, ENA_ADMIN_CUSTOMER_METRICS)) {
+		customer_metrics->supported_metrics = ENA_ADMIN_CUSTOMER_METRICS_MIN_SUPPORT_MASK;
+		return;
+	}
+
+	memset(&ctx, 0x0, sizeof(ctx));
+	ctx.get_cmd.requested_metrics = ENA_ADMIN_CUSTOMER_METRICS_SUPPORT_MASK;
+	ret = ena_get_dev_stats(ena_dev, &ctx, ENA_ADMIN_GET_STATS_TYPE_CUSTOMER_METRICS);
+	if (likely(ret == 0))
+		customer_metrics->supported_metrics =
+			ctx.get_resp.u.customer_metrics.reported_metrics;
+	else
+		netdev_err(ena_dev->net_device,
+			   "Failed to query customer metrics support. error: %d\n", ret);
+}
+
 int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 			      struct ena_com_dev_get_features_ctx *get_feat_ctx)
 {
@@ -1960,6 +2010,8 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev,
 	else
 		return rc;
 
+	ena_com_set_supported_customer_metrics(ena_dev);
+
 	return 0;
 }
 
@@ -2104,33 +2156,6 @@ int ena_com_dev_reset(struct ena_com_dev *ena_dev,
 	return 0;
 }
 
-static int ena_get_dev_stats(struct ena_com_dev *ena_dev,
-			     struct ena_com_stats_ctx *ctx,
-			     enum ena_admin_get_stats_type type)
-{
-	struct ena_admin_aq_get_stats_cmd *get_cmd = &ctx->get_cmd;
-	struct ena_admin_acq_get_stats_resp *get_resp = &ctx->get_resp;
-	struct ena_com_admin_queue *admin_queue;
-	int ret;
-
-	admin_queue = &ena_dev->admin_queue;
-
-	get_cmd->aq_common_descriptor.opcode = ENA_ADMIN_GET_STATS;
-	get_cmd->aq_common_descriptor.flags = 0;
-	get_cmd->type = type;
-
-	ret =  ena_com_execute_admin_command(admin_queue,
-					     (struct ena_admin_aq_entry *)get_cmd,
-					     sizeof(*get_cmd),
-					     (struct ena_admin_acq_entry *)get_resp,
-					     sizeof(*get_resp));
-
-	if (unlikely(ret))
-		netdev_err(ena_dev->net_device, "Failed to get stats. error: %d\n", ret);
-
-	return ret;
-}
-
 int ena_com_get_eni_stats(struct ena_com_dev *ena_dev,
 			  struct ena_admin_eni_stats *stats)
 {
@@ -2188,6 +2213,50 @@ int ena_com_get_dev_basic_stats(struct ena_com_dev *ena_dev,
 	return ret;
 }
 
+int ena_com_get_customer_metrics(struct ena_com_dev *ena_dev, char *buffer, u32 len)
+{
+	struct ena_admin_aq_get_stats_cmd *get_cmd;
+	struct ena_com_stats_ctx ctx;
+	int ret;
+
+	if (unlikely(len > ena_dev->customer_metrics.buffer_len)) {
+		netdev_err(ena_dev->net_device,
+			   "Invalid buffer size %u. The given buffer is too big.\n", len);
+		return -EINVAL;
+	}
+
+	if (!ena_com_get_cap(ena_dev, ENA_ADMIN_CUSTOMER_METRICS)) {
+		netdev_err(ena_dev->net_device, "Capability %d not supported.\n",
+			   ENA_ADMIN_CUSTOMER_METRICS);
+		return -EOPNOTSUPP;
+	}
+
+	if (!ena_dev->customer_metrics.supported_metrics) {
+		netdev_err(ena_dev->net_device, "No supported customer metrics.\n");
+		return -EOPNOTSUPP;
+	}
+
+	get_cmd = &ctx.get_cmd;
+	memset(&ctx, 0x0, sizeof(ctx));
+	ret = ena_com_mem_addr_set(ena_dev,
+				   &get_cmd->u.control_buffer.address,
+				   ena_dev->customer_metrics.buffer_dma_addr);
+	if (unlikely(ret)) {
+		netdev_err(ena_dev->net_device, "Memory address set failed.\n");
+		return ret;
+	}
+
+	get_cmd->u.control_buffer.length = ena_dev->customer_metrics.buffer_len;
+	get_cmd->requested_metrics = ena_dev->customer_metrics.supported_metrics;
+	ret = ena_get_dev_stats(ena_dev, &ctx, ENA_ADMIN_GET_STATS_TYPE_CUSTOMER_METRICS);
+	if (likely(ret == 0))
+		memcpy(buffer, ena_dev->customer_metrics.buffer_virt_addr, len);
+	else
+		netdev_err(ena_dev->net_device, "Failed to get customer metrics. error: %d\n", ret);
+
+	return ret;
+}
+
 int ena_com_set_dev_mtu(struct ena_com_dev *ena_dev, u32 mtu)
 {
 	struct ena_com_admin_queue *admin_queue;
@@ -2727,6 +2796,24 @@ int ena_com_allocate_debug_area(struct ena_com_dev *ena_dev,
 	return 0;
 }
 
+int ena_com_allocate_customer_metrics_buffer(struct ena_com_dev *ena_dev)
+{
+	struct ena_customer_metrics *customer_metrics = &ena_dev->customer_metrics;
+
+	customer_metrics->buffer_len = ENA_CUSTOMER_METRICS_BUFFER_SIZE;
+	customer_metrics->buffer_virt_addr = NULL;
+
+	customer_metrics->buffer_virt_addr =
+		dma_alloc_coherent(ena_dev->dmadev, customer_metrics->buffer_len,
+				   &customer_metrics->buffer_dma_addr, GFP_KERNEL);
+	if (!customer_metrics->buffer_virt_addr) {
+		customer_metrics->buffer_len = 0;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 void ena_com_delete_host_info(struct ena_com_dev *ena_dev)
 {
 	struct ena_host_attribute *host_attr = &ena_dev->host_attr;
@@ -2749,6 +2836,19 @@ void ena_com_delete_debug_area(struct ena_com_dev *ena_dev)
 	}
 }
 
+void ena_com_delete_customer_metrics_buffer(struct ena_com_dev *ena_dev)
+{
+	struct ena_customer_metrics *customer_metrics = &ena_dev->customer_metrics;
+
+	if (customer_metrics->buffer_virt_addr) {
+		dma_free_coherent(ena_dev->dmadev, customer_metrics->buffer_len,
+				  customer_metrics->buffer_virt_addr,
+				  customer_metrics->buffer_dma_addr);
+		customer_metrics->buffer_virt_addr = NULL;
+		customer_metrics->buffer_len = 0;
+	}
+}
+
 int ena_com_set_host_attributes(struct ena_com_dev *ena_dev)
 {
 	struct ena_host_attribute *host_attr = &ena_dev->host_attr;
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index 372066e039bf..a372c5e768a7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -42,6 +42,8 @@
 #define ADMIN_CQ_SIZE(depth)	((depth) * sizeof(struct ena_admin_acq_entry))
 #define ADMIN_AENQ_SIZE(depth)	((depth) * sizeof(struct ena_admin_aenq_entry))
 
+#define ENA_CUSTOMER_METRICS_BUFFER_SIZE 512
+
 /*****************************************************************************/
 /*****************************************************************************/
 /* ENA adaptive interrupt moderation settings */
@@ -278,6 +280,16 @@ struct ena_rss {
 
 };
 
+struct ena_customer_metrics {
+	/* in correlation with ENA_ADMIN_CUSTOMER_METRICS_SUPPORT_MASK
+	 * and ena_admin_customer_metrics_id
+	 */
+	u64 supported_metrics;
+	dma_addr_t buffer_dma_addr;
+	void *buffer_virt_addr;
+	u32 buffer_len;
+};
+
 struct ena_host_attribute {
 	/* Debug area */
 	u8 *debug_area_virt_addr;
@@ -327,6 +339,8 @@ struct ena_com_dev {
 	struct ena_intr_moder_entry *intr_moder_tbl;
 
 	struct ena_com_llq_info llq_info;
+
+	struct ena_customer_metrics customer_metrics;
 };
 
 struct ena_com_dev_get_features_ctx {
@@ -604,6 +618,15 @@ int ena_com_get_eni_stats(struct ena_com_dev *ena_dev,
 int ena_com_get_ena_srd_info(struct ena_com_dev *ena_dev,
 			     struct ena_admin_ena_srd_info *info);
 
+/* ena_com_get_customer_metrics - Get customer metrics for network interface
+ * @ena_dev: ENA communication layer struct
+ * @buffer: buffer for returned customer metrics
+ * @len: size of the buffer
+ *
+ * @return: 0 on Success and negative value otherwise.
+ */
+int ena_com_get_customer_metrics(struct ena_com_dev *ena_dev, char *buffer, u32 len);
+
 /* ena_com_set_dev_mtu - Configure the device mtu.
  * @ena_dev: ENA communication layer struct
  * @mtu: mtu value
@@ -814,6 +837,13 @@ int ena_com_allocate_host_info(struct ena_com_dev *ena_dev);
 int ena_com_allocate_debug_area(struct ena_com_dev *ena_dev,
 				u32 debug_area_size);
 
+/* ena_com_allocate_customer_metrics_buffer - Allocate customer metrics resources.
+ * @ena_dev: ENA communication layer struct
+ *
+ * @return: 0 on Success and negative value otherwise.
+ */
+int ena_com_allocate_customer_metrics_buffer(struct ena_com_dev *ena_dev);
+
 /* ena_com_delete_debug_area - Free the debug area resources.
  * @ena_dev: ENA communication layer struct
  *
@@ -828,6 +858,13 @@ void ena_com_delete_debug_area(struct ena_com_dev *ena_dev);
  */
 void ena_com_delete_host_info(struct ena_com_dev *ena_dev);
 
+/* ena_com_delete_customer_metrics_buffer - Free the customer metrics resources.
+ * @ena_dev: ENA communication layer struct
+ *
+ * Free the allocated customer metrics area.
+ */
+void ena_com_delete_customer_metrics_buffer(struct ena_com_dev *ena_dev);
+
 /* ena_com_set_host_attributes - Update the device with the host
  * attributes (debug area and host info) base address.
  * @ena_dev: ENA communication layer struct
@@ -984,6 +1021,28 @@ static inline bool ena_com_get_cap(struct ena_com_dev *ena_dev,
 	return !!(ena_dev->capabilities & BIT(cap_id));
 }
 
+/* ena_com_get_customer_metric_support - query whether device supports a given customer metric.
+ * @ena_dev: ENA communication layer struct
+ * @metric_id: enum value representing the customer metric
+ *
+ * @return - true if customer metric is supported or false otherwise
+ */
+static inline bool ena_com_get_customer_metric_support(struct ena_com_dev *ena_dev,
+						       enum ena_admin_customer_metrics_id metric_id)
+{
+	return !!(ena_dev->customer_metrics.supported_metrics & BIT(metric_id));
+}
+
+/* ena_com_get_customer_metric_count - return the number of supported customer metrics.
+ * @ena_dev: ENA communication layer struct
+ *
+ * @return - the number of supported customer metrics
+ */
+static inline int ena_com_get_customer_metric_count(struct ena_com_dev *ena_dev)
+{
+	return hweight64(ena_dev->customer_metrics.supported_metrics);
+}
+
 /* ena_com_update_intr_reg - Prepare interrupt register
  * @intr_reg: interrupt register to update.
  * @rx_delay_interval: Rx interval in usecs
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 5efd3e43ffa6..60fb35ec4b15 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -14,6 +14,10 @@ struct ena_stats {
 	int stat_offset;
 };
 
+struct ena_hw_metrics {
+	char name[ETH_GSTRING_LEN];
+};
+
 #define ENA_STAT_ENA_COM_ENTRY(stat) { \
 	.name = #stat, \
 	.stat_offset = offsetof(struct ena_com_stats_admin, stat) / sizeof(u64) \
@@ -49,6 +53,10 @@ struct ena_stats {
 	.stat_offset = offsetof(struct ena_admin_ena_srd_info, flags) / sizeof(u64) \
 }
 
+#define ENA_METRIC_ENI_ENTRY(stat) { \
+	.name = #stat \
+}
+
 static const struct ena_stats ena_stats_global_strings[] = {
 	ENA_STAT_GLOBAL_ENTRY(tx_timeout),
 	ENA_STAT_GLOBAL_ENTRY(suspend),
@@ -60,6 +68,9 @@ static const struct ena_stats ena_stats_global_strings[] = {
 	ENA_STAT_GLOBAL_ENTRY(reset_fail),
 };
 
+/* A partial list of hw stats. Used when admin command
+ * with type ENA_ADMIN_GET_STATS_TYPE_CUSTOMER_METRICS is not supported
+ */
 static const struct ena_stats ena_stats_eni_strings[] = {
 	ENA_STAT_ENI_ENTRY(bw_in_allowance_exceeded),
 	ENA_STAT_ENI_ENTRY(bw_out_allowance_exceeded),
@@ -68,6 +79,15 @@ static const struct ena_stats ena_stats_eni_strings[] = {
 	ENA_STAT_ENI_ENTRY(linklocal_allowance_exceeded),
 };
 
+static const struct ena_hw_metrics ena_hw_stats_strings[] = {
+	ENA_METRIC_ENI_ENTRY(bw_in_allowance_exceeded),
+	ENA_METRIC_ENI_ENTRY(bw_out_allowance_exceeded),
+	ENA_METRIC_ENI_ENTRY(pps_allowance_exceeded),
+	ENA_METRIC_ENI_ENTRY(conntrack_allowance_exceeded),
+	ENA_METRIC_ENI_ENTRY(linklocal_allowance_exceeded),
+	ENA_METRIC_ENI_ENTRY(conntrack_allowance_available),
+};
+
 static const struct ena_stats ena_srd_info_strings[] = {
 	ENA_STAT_ENA_SRD_MODE_ENTRY(ena_srd_mode),
 	ENA_STAT_ENA_SRD_ENTRY(ena_srd_tx_pkts),
@@ -130,6 +150,7 @@ static const struct ena_stats ena_stats_ena_com_strings[] = {
 #define ENA_STATS_ARRAY_ENA_COM		ARRAY_SIZE(ena_stats_ena_com_strings)
 #define ENA_STATS_ARRAY_ENI		ARRAY_SIZE(ena_stats_eni_strings)
 #define ENA_STATS_ARRAY_ENA_SRD		ARRAY_SIZE(ena_srd_info_strings)
+#define ENA_METRICS_ARRAY_ENI		ARRAY_SIZE(ena_hw_stats_strings)
 
 static void ena_safe_update_stat(u64 *src, u64 *dst,
 				 struct u64_stats_sync *syncp)
@@ -142,6 +163,57 @@ static void ena_safe_update_stat(u64 *src, u64 *dst,
 	} while (u64_stats_fetch_retry(syncp, start));
 }
 
+static void ena_metrics_stats(struct ena_adapter *adapter, u64 **data)
+{
+	struct ena_com_dev *dev = adapter->ena_dev;
+	const struct ena_stats *ena_stats;
+	u64 *ptr;
+	int i;
+
+	if (ena_com_get_cap(dev, ENA_ADMIN_CUSTOMER_METRICS)) {
+		u32 supported_metrics_count;
+		int len;
+
+		supported_metrics_count = ena_com_get_customer_metric_count(dev);
+		len = supported_metrics_count * sizeof(u64);
+
+		/* Fill the data buffer, and advance its pointer */
+		ena_com_get_customer_metrics(dev, (char *)(*data), len);
+		(*data) += supported_metrics_count;
+
+	} else if (ena_com_get_cap(dev, ENA_ADMIN_ENI_STATS)) {
+		ena_com_get_eni_stats(dev, &adapter->eni_stats);
+		/* Updating regardless of rc - once we told ethtool how many stats we have
+		 * it will print that much stats. We can't leave holes in the stats
+		 */
+		for (i = 0; i < ENA_STATS_ARRAY_ENI; i++) {
+			ena_stats = &ena_stats_eni_strings[i];
+
+			ptr = (u64 *)&adapter->eni_stats +
+				ena_stats->stat_offset;
+
+			ena_safe_update_stat(ptr, (*data)++, &adapter->syncp);
+		}
+	}
+
+	if (ena_com_get_cap(dev, ENA_ADMIN_ENA_SRD_INFO)) {
+		ena_com_get_ena_srd_info(dev, &adapter->ena_srd_info);
+		/* Get ENA SRD mode */
+		ptr = (u64 *)&adapter->ena_srd_info;
+		ena_safe_update_stat(ptr, (*data)++, &adapter->syncp);
+		for (i = 1; i < ENA_STATS_ARRAY_ENA_SRD; i++) {
+			ena_stats = &ena_srd_info_strings[i];
+			/* Wrapped within an outer struct - need to accommodate an
+			 * additional offset of the ENA SRD mode that was already processed
+			 */
+			ptr = (u64 *)&adapter->ena_srd_info +
+				ena_stats->stat_offset + 1;
+
+			ena_safe_update_stat(ptr, (*data)++, &adapter->syncp);
+		}
+	}
+}
+
 static void ena_queue_stats(struct ena_adapter *adapter, u64 **data)
 {
 	const struct ena_stats *ena_stats;
@@ -210,39 +282,8 @@ static void ena_get_stats(struct ena_adapter *adapter,
 		ena_safe_update_stat(ptr, data++, &adapter->syncp);
 	}
 
-	if (hw_stats_needed) {
-		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS)) {
-			ena_com_get_eni_stats(adapter->ena_dev, &adapter->eni_stats);
-			/* Updating regardless of rc - once we told ethtool how many stats we have
-			 * it will print that much stats. We can't leave holes in the stats
-			 */
-			for (i = 0; i < ENA_STATS_ARRAY_ENI; i++) {
-				ena_stats = &ena_stats_eni_strings[i];
-
-				ptr = (u64 *)&adapter->eni_stats +
-					ena_stats->stat_offset;
-
-				ena_safe_update_stat(ptr, data++, &adapter->syncp);
-			}
-		}
-
-		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENA_SRD_INFO)) {
-			ena_com_get_ena_srd_info(adapter->ena_dev, &adapter->ena_srd_info);
-			/* Get ENA SRD mode */
-			ptr = (u64 *)&adapter->ena_srd_info;
-			ena_safe_update_stat(ptr, data++, &adapter->syncp);
-			for (i = 1; i < ENA_STATS_ARRAY_ENA_SRD; i++) {
-				ena_stats = &ena_srd_info_strings[i];
-				/* Wrapped within an outer struct - need to accommodate an
-				 * additional offset of the ENA SRD mode that was already processed
-				 */
-				ptr = (u64 *)&adapter->ena_srd_info +
-					ena_stats->stat_offset + 1;
-
-				ena_safe_update_stat(ptr, data++, &adapter->syncp);
-			}
-		}
-	}
+	if (hw_stats_needed)
+		ena_metrics_stats(adapter, &data);
 
 	ena_queue_stats(adapter, &data);
 	ena_dev_admin_queue_stats(adapter, &data);
@@ -266,8 +307,17 @@ static int ena_get_sw_stats_count(struct ena_adapter *adapter)
 
 static int ena_get_hw_stats_count(struct ena_adapter *adapter)
 {
-	return ENA_STATS_ARRAY_ENI * ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS) +
-	       ENA_STATS_ARRAY_ENA_SRD * ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENA_SRD_INFO);
+	struct ena_com_dev *dev = adapter->ena_dev;
+	int count;
+
+	count = ENA_STATS_ARRAY_ENA_SRD * ena_com_get_cap(dev, ENA_ADMIN_ENA_SRD_INFO);
+
+	if (ena_com_get_cap(dev, ENA_ADMIN_CUSTOMER_METRICS))
+		count += ena_com_get_customer_metric_count(dev);
+	else if (ena_com_get_cap(dev, ENA_ADMIN_ENI_STATS))
+		count += ENA_STATS_ARRAY_ENI;
+
+	return count;
 }
 
 int ena_get_sset_count(struct net_device *netdev, int sset)
@@ -283,6 +333,35 @@ int ena_get_sset_count(struct net_device *netdev, int sset)
 	return -EOPNOTSUPP;
 }
 
+static void ena_metrics_stats_strings(struct ena_adapter *adapter, u8 **data)
+{
+	struct ena_com_dev *dev = adapter->ena_dev;
+	const struct ena_hw_metrics *ena_metrics;
+	const struct ena_stats *ena_stats;
+	int i;
+
+	if (ena_com_get_cap(dev, ENA_ADMIN_CUSTOMER_METRICS)) {
+		for (i = 0; i < ENA_METRICS_ARRAY_ENI; i++) {
+			if (ena_com_get_customer_metric_support(dev, i)) {
+				ena_metrics = &ena_hw_stats_strings[i];
+				ethtool_puts(data, ena_metrics->name);
+			}
+		}
+	} else if (ena_com_get_cap(dev, ENA_ADMIN_ENI_STATS)) {
+		for (i = 0; i < ENA_STATS_ARRAY_ENI; i++) {
+			ena_stats = &ena_stats_eni_strings[i];
+			ethtool_puts(data, ena_stats->name);
+		}
+	}
+
+	if (ena_com_get_cap(dev, ENA_ADMIN_ENA_SRD_INFO)) {
+		for (i = 0; i < ENA_STATS_ARRAY_ENA_SRD; i++) {
+			ena_stats = &ena_srd_info_strings[i];
+			ethtool_puts(data, ena_stats->name);
+		}
+	}
+}
+
 static void ena_queue_strings(struct ena_adapter *adapter, u8 **data)
 {
 	const struct ena_stats *ena_stats;
@@ -338,20 +417,8 @@ static void ena_get_strings(struct ena_adapter *adapter,
 		ethtool_puts(&data, ena_stats->name);
 	}
 
-	if (hw_stats_needed) {
-		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENI_STATS)) {
-			for (i = 0; i < ENA_STATS_ARRAY_ENI; i++) {
-				ena_stats = &ena_stats_eni_strings[i];
-				ethtool_puts(&data, ena_stats->name);
-			}
-		}
-		if (ena_com_get_cap(adapter->ena_dev, ENA_ADMIN_ENA_SRD_INFO)) {
-			for (i = 0; i < ENA_STATS_ARRAY_ENA_SRD; i++) {
-				ena_stats = &ena_srd_info_strings[i];
-				ethtool_puts(&data, ena_stats->name);
-			}
-		}
-	}
+	if (hw_stats_needed)
+		ena_metrics_stats_strings(adapter, &data);
 
 	ena_queue_strings(adapter, &data);
 	ena_com_dev_strings(&data);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 0883c9a230f2..c5b50cfa935a 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3931,10 +3931,16 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, adapter);
 
+	rc = ena_com_allocate_customer_metrics_buffer(ena_dev);
+	if (rc) {
+		netdev_err(netdev, "ena_com_allocate_customer_metrics_buffer failed\n");
+		goto err_netdev_destroy;
+	}
+
 	rc = ena_map_llq_mem_bar(pdev, ena_dev, bars);
 	if (rc) {
 		dev_err(&pdev->dev, "ENA LLQ bar mapping failed\n");
-		goto err_netdev_destroy;
+		goto err_metrics_destroy;
 	}
 
 	rc = ena_device_init(adapter, pdev, &get_feat_ctx, &wd_state);
@@ -3942,7 +3948,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(&pdev->dev, "ENA device init failed\n");
 		if (rc == -ETIME)
 			rc = -EPROBE_DEFER;
-		goto err_netdev_destroy;
+		goto err_metrics_destroy;
 	}
 
 	/* Initial TX and RX interrupt delay. Assumes 1 usec granularity.
@@ -4063,6 +4069,8 @@ err_worker_destroy:
 err_device_destroy:
 	ena_com_delete_host_info(ena_dev);
 	ena_com_admin_destroy(ena_dev);
+err_metrics_destroy:
+	ena_com_delete_customer_metrics_buffer(ena_dev);
 err_netdev_destroy:
 	free_netdev(netdev);
 err_free_region:
@@ -4126,6 +4134,8 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 
 	ena_com_delete_host_info(ena_dev);
 
+	ena_com_delete_customer_metrics_buffer(ena_dev);
+
 	ena_release_bars(ena_dev, pdev);
 
 	pci_disable_device(pdev);
-- 
cgit v1.3-3-g829e


From cded7e0479c9340d7859841f2c0fd1aabf8f6294 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 11 Sep 2024 20:52:40 -0400
Subject: selftests/net: packetdrill: run in netns and expand config

Run packetdrill tests inside netns.
They may change system settings, such as sysctl.

Also expand config with a few more needed CONFIGs.

Link: https://lore.kernel.org/netdev/20240910152640.429920be@kernel.org/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240912005317.1253001-2-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/packetdrill/config         | 5 +++++
 tools/testing/selftests/net/packetdrill/ksft_runner.sh | 4 ++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/packetdrill/config b/tools/testing/selftests/net/packetdrill/config
index 0d402830f18d..a7877819081f 100644
--- a/tools/testing/selftests/net/packetdrill/config
+++ b/tools/testing/selftests/net/packetdrill/config
@@ -1,5 +1,10 @@
 CONFIG_IPV6=y
+CONFIG_HZ_1000=y
+CONFIG_HZ=1000
+CONFIG_NET_NS=y
 CONFIG_NET_SCH_FIFO=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_SYN_COOKIES=y
+CONFIG_TCP_CONG_CUBIC=y
 CONFIG_TCP_MD5SIG=y
 CONFIG_TUN=y
diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
index 2f62caccbbbc..7478c0c0c9aa 100755
--- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh
+++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh
@@ -33,9 +33,9 @@ fi
 ktap_print_header
 ktap_set_plan 2
 
-packetdrill ${ipv4_args[@]} $(basename $script) > /dev/null \
+unshare -n packetdrill ${ipv4_args[@]} $(basename $script) > /dev/null \
 	&& ktap_test_pass "ipv4" || ktap_test_fail "ipv4"
-packetdrill ${ipv6_args[@]} $(basename $script) > /dev/null \
+unshare -n packetdrill ${ipv6_args[@]} $(basename $script) > /dev/null \
 	&& ktap_test_pass "ipv6" || ktap_test_fail "ipv6"
 
 ktap_finished
-- 
cgit v1.3-3-g829e


From 1e42f73fd3c26e567c910e2ab9c91e9f56eae315 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 11 Sep 2024 20:52:41 -0400
Subject: selftests/net: packetdrill: import tcp/zerocopy

Same as initial tests, import verbatim from
github.com/google/packetdrill, aside from:

- update `source ./defaults.sh` path to adjust for flat dir
- add SPDX headers
- remove author statements if any
- drop blank lines at EOF (new)

Also import set_sysctls.py, which many scripts depend on to set
sysctls and then restore them later. This is no longer strictly needed
for namespacified sysctl. But not all sysctls are namespacified, and
doesn't hurt if they are.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240912005317.1253001-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/packetdrill/Makefile   |   1 +
 .../selftests/net/packetdrill/set_sysctls.py       |  38 +++++++
 .../net/packetdrill/tcp_zerocopy_basic.pkt         |  55 ++++++++++
 .../net/packetdrill/tcp_zerocopy_batch.pkt         |  41 +++++++
 .../net/packetdrill/tcp_zerocopy_client.pkt        |  30 ++++++
 .../net/packetdrill/tcp_zerocopy_closed.pkt        |  44 ++++++++
 .../net/packetdrill/tcp_zerocopy_epoll_edge.pkt    |  61 +++++++++++
 .../packetdrill/tcp_zerocopy_epoll_exclusive.pkt   |  63 +++++++++++
 .../net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt |  66 ++++++++++++
 .../packetdrill/tcp_zerocopy_fastopen-client.pkt   |  56 ++++++++++
 .../packetdrill/tcp_zerocopy_fastopen-server.pkt   |  44 ++++++++
 .../net/packetdrill/tcp_zerocopy_maxfrags.pkt      | 118 +++++++++++++++++++++
 .../net/packetdrill/tcp_zerocopy_small.pkt         |  57 ++++++++++
 13 files changed, 674 insertions(+)
 create mode 100755 tools/testing/selftests/net/packetdrill/set_sysctls.py
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt

diff --git a/tools/testing/selftests/net/packetdrill/Makefile b/tools/testing/selftests/net/packetdrill/Makefile
index 870f7258dc8d..31cfb666ba8b 100644
--- a/tools/testing/selftests/net/packetdrill/Makefile
+++ b/tools/testing/selftests/net/packetdrill/Makefile
@@ -2,6 +2,7 @@
 
 TEST_INCLUDES := ksft_runner.sh \
 		 defaults.sh \
+		 set_sysctls.py \
 		 ../../kselftest/ktap_helpers.sh
 
 TEST_PROGS := $(wildcard *.pkt)
diff --git a/tools/testing/selftests/net/packetdrill/set_sysctls.py b/tools/testing/selftests/net/packetdrill/set_sysctls.py
new file mode 100755
index 000000000000..5ddf456ae973
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/set_sysctls.py
@@ -0,0 +1,38 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Sets sysctl values and writes a file that restores them.
+
+The arguments are of the form "<proc-file>=<val>" separated by spaces.
+The program first reads the current value of the proc-file and creates
+a shell script named "/tmp/sysctl_restore_${PACKETDRILL_PID}.sh" which
+restores the values when executed. It then sets the new values.
+
+PACKETDRILL_PID is set by packetdrill to the pid of itself, so a .pkt
+file could restore sysctls by running `/tmp/sysctl_restore_${PPID}.sh`
+at the end.
+"""
+
+import os
+import subprocess
+import sys
+
+filename = '/tmp/sysctl_restore_%s.sh' % os.environ['PACKETDRILL_PID']
+
+# Open file for restoring sysctl values
+restore_file = open(filename, 'w')
+print('#!/bin/bash', file=restore_file)
+
+for a in sys.argv[1:]:
+  sysctl = a.split('=')
+  # sysctl[0] contains the proc-file name, sysctl[1] the new value
+
+  # read current value and add restore command to file
+  cur_val = subprocess.check_output(['cat', sysctl[0]], universal_newlines=True)
+  print('echo "%s" > %s' % (cur_val.strip(), sysctl[0]), file=restore_file)
+
+  # set new value
+  cmd = 'echo "%s" > %s' % (sysctl[1], sysctl[0])
+  os.system(cmd)
+
+os.system('chmod u+x %s' % filename)
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt
new file mode 100644
index 000000000000..a82c8899d36b
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_basic.pkt
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+// basic zerocopy test:
+//
+// send a packet with MSG_ZEROCOPY and receive the notification ID
+// repeat and verify IDs are consecutive
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=1,
+                                    ee_data=1}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt
new file mode 100644
index 000000000000..c01915e7f4a1
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_batch.pkt
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+// batch zerocopy test:
+//
+// send multiple packets, then read one range of all notifications.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_MARK, [666], 4) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=1}}
+                  ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt
new file mode 100644
index 000000000000..6509882932e9
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_client.pkt
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Minimal client-side zerocopy test
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0...0 connect(4, ..., ...) = 0
+
+   +0 > S 0:0(0) <mss 1460,sackOK,TS val 0 ecr 0,nop,wscale 8>
+   +0 < S. 0:0(0) ack 1 win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > . 1:1(0) ack 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt
new file mode 100644
index 000000000000..2cd78755cb2a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_closed.pkt
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+// send with MSG_ZEROCOPY on a non-established socket
+//
+// verify that a send in state TCP_CLOSE correctly aborts the zerocopy
+// operation, specifically it does not increment the zerocopy counter.
+//
+// First send on a closed socket and wait for (absent) notification.
+// Then connect and send and verify that notification nr. is zero.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = -1 EPIPE (Broken pipe)
+
+   +0.1 recvmsg(4, {msg_name(...)=...,
+                    msg_iov(1)=[{...,0}],
+                    msg_flags=MSG_ERRQUEUE,
+                    msg_control=[]}, MSG_ERRQUEUE) = -1 EAGAIN (Resource temporarily unavailable)
+
+   +0...0 connect(4, ..., ...) = 0
+
+   +0 > S 0:0(0) <mss 1460,sackOK,TS val 0 ecr 0,nop,wscale 8>
+   +0 < S. 0:0(0) ack 1 win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > . 1:1(0) ack 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt
new file mode 100644
index 000000000000..7671c20e01cf
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_edge.pkt
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+// epoll zerocopy test:
+//
+// EPOLLERR is known to be not edge-triggered unlike EPOLLIN and EPOLLOUT but
+// it is not level-triggered either.
+//
+// fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR
+// is correctly fired only once, when EPOLLET is set. send another packet with
+// MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 epoll_create(1) = 5
+   +0 epoll_ctl(5, EPOLL_CTL_ADD, 4, {events=EPOLLOUT|EPOLLET, fd=4}) = 0
+   +0 epoll_wait(5, {events=EPOLLOUT, fd=4}, 1, 0) = 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+// receive only one EPOLLERR for the two sends above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 8001:12001(4000) ack 1
+   +0 < . 1:1(0) ack 12001 win 257
+
+// receive only one EPOLLERR for the third send above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=2}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt
new file mode 100644
index 000000000000..fadc480fdb7f
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_exclusive.pkt
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+// epoll zerocopy test:
+//
+// EPOLLERR is known to be not edge-triggered unlike EPOLLIN and EPOLLOUT but
+// it is not level-triggered either. this tests verify that the same behavior is
+// maintained when we have EPOLLEXCLUSIVE.
+//
+// fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR
+// is correctly fired only once, when EPOLLET is set. send another packet with
+// MSG_ZEROCOPY. confirm that EPOLLERR is correctly fired again only once.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 epoll_create(1) = 5
+   +0 epoll_ctl(5, EPOLL_CTL_ADD, 4,
+		{events=EPOLLOUT|EPOLLET|EPOLLEXCLUSIVE, fd=4}) = 0
+   +0 epoll_wait(5, {events=EPOLLOUT, fd=4}, 1, 0) = 1
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+// receive only one EPOLLERR for the two sends above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 8001:12001(4000) ack 1
+   +0 < . 1:1(0) ack 12001 win 257
+
+// receive only one EPOLLERR for the third send above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=2}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt
new file mode 100644
index 000000000000..5bfa0d1d2f4a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_epoll_oneshot.pkt
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+// epoll zerocopy test:
+//
+// This is a test to confirm that EPOLLERR is only fired once for an FD when
+// EPOLLONESHOT is set.
+//
+// fire two sends with MSG_ZEROCOPY and receive the acks. confirm that EPOLLERR
+// is correctly fired only once, when EPOLLONESHOT is set. send another packet
+// with MSG_ZEROCOPY. confirm that EPOLLERR is not fired. Rearm the FD and
+// confirm that EPOLLERR is correctly set.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   +0 fcntl(4, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 epoll_create(1) = 5
+   +0 epoll_ctl(5, EPOLL_CTL_ADD, 4,
+		{events=EPOLLOUT|EPOLLET|EPOLLONESHOT, fd=4}) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 1:4001(4000) ack 1
+   +0 < . 1:1(0) ack 4001 win 257
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 4001:8001(4000) ack 1
+   +0 < . 1:1(0) ack 8001 win 257
+
+// receive only one EPOLLERR for the two sends above.
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 send(4, ..., 4000, MSG_ZEROCOPY) = 4000
+   +0 > P. 8001:12001(4000) ack 1
+   +0 < . 1:1(0) ack 12001 win 257
+
+// receive no EPOLLERR for the third send above.
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+// rearm the FD and verify the EPOLLERR is fired again.
+   +0 epoll_ctl(5, EPOLL_CTL_MOD, 4, {events=EPOLLOUT|EPOLLONESHOT, fd=4}) = 0
+   +0 epoll_wait(5, {events=EPOLLERR|EPOLLOUT, fd=4}, 1, 0) = 1
+   +0 epoll_wait(5, {events=0, ptr=0}, 1, 0) = 0
+
+   +0 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=2}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt
new file mode 100644
index 000000000000..4a73bbf46961
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-client.pkt
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+// Fastopen client zerocopy test:
+//
+// send data with MSG_FASTOPEN | MSG_ZEROCOPY and verify that the
+// kernel returns the notification ID.
+//
+// Fastopen requires a stored cookie. Create two sockets. The first
+// one will have no data in the initial send. On return 0 the
+// zerocopy notification counter is not incremented. Verify this too.
+
+`./defaults.sh`
+
+// Send a FastOpen request, no cookie yet so no data in SYN
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 sendto(3, ..., 500, MSG_FASTOPEN|MSG_ZEROCOPY, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+   +0 > S 0:0(0) <mss 1460,sackOK,TS val 1000 ecr 0,nop,wscale 8,FO,nop,nop>
+ +.01 < S. 123:123(0) ack 1 win 14600 <mss 940,TS val 2000 ecr 1000,sackOK,nop,wscale 6, FO abcd1234,nop,nop>
+   +0 > . 1:1(0) ack 1 <nop,nop,TS val 1001 ecr 2000>
+
+// Read from error queue: no zerocopy notification
+   +1 recvmsg(3, {msg_name(...)=...,
+                    msg_iov(1)=[{...,0}],
+                    msg_flags=MSG_ERRQUEUE,
+                    msg_control=[]}, MSG_ERRQUEUE) = -1 EAGAIN (Resource temporarily unavailable)
+
+ +.01 close(3) = 0
+   +0 > F. 1:1(0) ack 1 <nop,nop,TS val 1002 ecr 2000>
+ +.01 < F. 1:1(0) ack 2 win 92 <nop,nop,TS val 2001 ecr 1002>
+   +0 > .  2:2(0) ack 2 <nop,nop,TS val 1003 ecr 2001>
+
+// Send another Fastopen request, now SYN will have data
+ +.07 `sysctl -q net.ipv4.tcp_timestamps=0`
+  +.1 socket(..., SOCK_STREAM, IPPROTO_TCP) = 5
+   +0 fcntl(5, F_SETFL, O_RDWR|O_NONBLOCK) = 0
+   +0 setsockopt(5, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 sendto(5, ..., 500, MSG_FASTOPEN|MSG_ZEROCOPY, ..., ...) = 500
+   +0 > S 0:500(500) <mss 1460,nop,nop,sackOK,nop,wscale 8,FO abcd1234,nop,nop>
+ +.05 < S. 5678:5678(0) ack 501 win 14600 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+   +0 > . 501:501(0) ack 1
+
+// Read from error queue: now has first zerocopy notification
+   +0.5 recvmsg(5, {msg_name(...)=...,
+                    msg_iov(1)=[{...,0}],
+                    msg_flags=MSG_ERRQUEUE,
+                    msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt
new file mode 100644
index 000000000000..36086c5877ce
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_fastopen-server.pkt
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+// Fastopen server zerocopy test:
+//
+// send data with MSG_FASTOPEN | MSG_ZEROCOPY and verify that the
+// kernel returns the notification ID.
+
+`./defaults.sh
+ ./set_sysctls.py /proc/sys/net/ipv4/tcp_fastopen=0x207`
+
+// Set up a TFO server listening socket.
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+  +.1 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+   +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [2], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+
+// Client sends a SYN with data.
+  +.1 < S 0:1000(1000) win 32792 <mss 1460,sackOK,nop,nop>
+   +0 > S. 0:0(0) ack 1001 <mss 1460,nop,nop,sackOK>
+
+// Server accepts and replies with data.
++.005 accept(3, ..., ...) = 4
+   +0 read(4, ..., 1024) = 1000
+   +0 sendto(4, ..., 1000, MSG_ZEROCOPY, ..., ...) = 1000
+   +0 > P. 1:1001(1000) ack 1001
+ +.05 < . 1001:1001(0) ack 1001 win 32792
+
+// Read from error queue: now has first zerocopy notification
+  +0.1 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                      {cmsg_level=CMSG_LEVEL_IP,
+                       cmsg_type=CMSG_TYPE_RECVERR,
+                       cmsg_data={ee_errno=0,
+                                  ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                  ee_type=0,
+                                  ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                  ee_info=0,
+                                  ee_data=0}}
+                  ]}, MSG_ERRQUEUE) = 0
+
+`/tmp/sysctl_restore_${PPID}.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt
new file mode 100644
index 000000000000..672f817faca0
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_maxfrags.pkt
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+// tcp_MAX_SKB_FRAGS test
+//
+// Verify that sending an iovec of tcp_MAX_SKB_FRAGS + 1 elements will
+// 1) fit in a single packet without zerocopy
+// 2) spill over into a second packet with zerocopy,
+//    because each iovec element becomes a frag
+// 3) the PSH bit is set on an skb when it runs out of fragments
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+
+   // Each pinned zerocopy page is fully accounted to skb->truesize.
+   // This test generates a worst case packet with each frag storing
+   // one byte, but increasing truesize with a page (64KB on PPC).
+   +0 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [2000000], 4) = 0
+
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   // send an iov of 18 elements: just becomes a linear skb
+   +0 sendmsg(4, {msg_name(...)=...,
+		  msg_iov(18)=[{..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}],
+		  msg_flags=0}, 0) = 18
+
+   +0 > P. 1:19(18) ack 1
+   +0 < . 1:1(0) ack 19 win 257
+
+   // send a zerocopy iov of 18 elements:
+   +1 sendmsg(4, {msg_name(...)=...,
+		  msg_iov(18)=[{..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}],
+		  msg_flags=0}, MSG_ZEROCOPY) = 18
+
+   // verify that it is split in one skb of 17 frags + 1 of 1 frag
+   // verify that both have the PSH bit set
+   +0 > P. 19:36(17) ack 1
+   +0 < . 1:1(0) ack 36 win 257
+
+   +0 > P. 36:37(1) ack 1
+   +0 < . 1:1(0) ack 37 win 257
+
+   +1 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
+
+   // send a zerocopy iov of 64 elements:
+   +0 sendmsg(4, {msg_name(...)=...,
+                  msg_iov(64)=[{..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1},
+			       {..., 1}, {..., 1}, {..., 1}, {..., 1}],
+                  msg_flags=0}, MSG_ZEROCOPY) = 64
+
+   // verify that it is split in skbs with 17 frags
+   +0 > P. 37:54(17) ack 1
+   +0 < . 1:1(0) ack 54 win 257
+
+   +0 > P. 54:71(17) ack 1
+   +0 < . 1:1(0) ack 71 win 257
+
+   +0 > P. 71:88(17) ack 1
+   +0 < . 1:1(0) ack 88 win 257
+
+   +0 > P. 88:101(13) ack 1
+   +0 < . 1:1(0) ack 101 win 257
+
+   +1 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=1,
+                                    ee_data=1}}
+                   ]}, MSG_ERRQUEUE) = 0
diff --git a/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt
new file mode 100644
index 000000000000..a9a1ac0aea4f
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_zerocopy_small.pkt
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+// small packet zerocopy test:
+//
+// verify that SO_EE_CODE_ZEROCOPY_COPIED is set on zerocopy
+// packets of all sizes, including the smallest payload, 1B.
+
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 setsockopt(3, SOL_SOCKET, SO_ZEROCOPY, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+   // send 1B
+   +0 send(4, ..., 1, MSG_ZEROCOPY) = 1
+   +0 > P. 1:2(1) ack 1
+   +0 < . 1:1(0) ack 2 win 257
+
+   +1 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=0,
+                                    ee_data=0}}
+                   ]}, MSG_ERRQUEUE) = 0
+
+   // send 1B again
+   +0 send(4, ..., 1, MSG_ZEROCOPY) = 1
+   +0 > P. 2:3(1) ack 1
+   +0 < . 1:1(0) ack 3 win 257
+
+   +1 recvmsg(4, {msg_name(...)=...,
+                  msg_iov(1)=[{...,0}],
+                  msg_flags=MSG_ERRQUEUE,
+                  msg_control=[
+                        {cmsg_level=CMSG_LEVEL_IP,
+                         cmsg_type=CMSG_TYPE_RECVERR,
+                         cmsg_data={ee_errno=0,
+                                    ee_origin=SO_EE_ORIGIN_ZEROCOPY,
+                                    ee_type=0,
+                                    ee_code=SO_EE_CODE_ZEROCOPY_COPIED,
+                                    ee_info=1,
+                                    ee_data=1}}
+                   ]}, MSG_ERRQUEUE) = 0
-- 
cgit v1.3-3-g829e


From e874be276ee4f22de2bdf3c3a876a41a71c3207f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 11 Sep 2024 20:52:42 -0400
Subject: selftests/net: packetdrill: import tcp/slow_start

Same import process as previous tests.

Also add CONFIG_NET_SCH_FQ to config, as one test uses that.

Same test process as previous tests. Both with and without debug mode.
Recording the steps once:

make mrproper
vng --build \
        --config tools/testing/selftests/net/packetdrill/config \
        --config kernel/configs/debug.config
vng -v --run . --user root --cpus 4 -- \
	make -C tools/testing/selftests TARGETS=net/packetdrill run_tests

Link: https://github.com/linux-netdev/nipa/wiki/How-to-run-netdev-selftests-CI-style#how-to-build
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240912005317.1253001-4-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/packetdrill/config     |  1 +
 .../tcp_slow_start_slow-start-ack-per-1pkt.pkt     | 56 +++++++++++++++++++
 ...low_start_slow-start-ack-per-2pkt-send-5pkt.pkt | 33 ++++++++++++
 ...low_start_slow-start-ack-per-2pkt-send-6pkt.pkt | 34 ++++++++++++
 .../tcp_slow_start_slow-start-ack-per-2pkt.pkt     | 42 +++++++++++++++
 .../tcp_slow_start_slow-start-ack-per-4pkt.pkt     | 35 ++++++++++++
 .../tcp_slow_start_slow-start-after-idle.pkt       | 39 ++++++++++++++
 .../tcp_slow_start_slow-start-after-win-update.pkt | 50 +++++++++++++++++
 ..._start_slow-start-app-limited-9-packets-out.pkt | 38 +++++++++++++
 .../tcp_slow_start_slow-start-app-limited.pkt      | 36 +++++++++++++
 .../tcp_slow_start_slow-start-fq-ack-per-2pkt.pkt  | 63 ++++++++++++++++++++++
 11 files changed, 427 insertions(+)
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-1pkt.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-5pkt.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-6pkt.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-4pkt.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-idle.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-win-update.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited-9-packets-out.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited.pkt
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-fq-ack-per-2pkt.pkt

diff --git a/tools/testing/selftests/net/packetdrill/config b/tools/testing/selftests/net/packetdrill/config
index a7877819081f..0237ed98f3c0 100644
--- a/tools/testing/selftests/net/packetdrill/config
+++ b/tools/testing/selftests/net/packetdrill/config
@@ -3,6 +3,7 @@ CONFIG_HZ_1000=y
 CONFIG_HZ=1000
 CONFIG_NET_NS=y
 CONFIG_NET_SCH_FIFO=y
+CONFIG_NET_SCH_FQ=y
 CONFIG_PROC_SYSCTL=y
 CONFIG_SYN_COOKIES=y
 CONFIG_TCP_CONG_CUBIC=y
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-1pkt.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-1pkt.pkt
new file mode 100644
index 000000000000..795c476d222d
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-1pkt.pkt
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when not application-limited, so that
+// the cwnd continues to grow.
+// In this variant, the receiver ACKs every packet.
+
+// Set up config. To keep things simple, disable the
+// mechanism that defers sending in order to send bigger TSO packets.
+`./defaults.sh
+sysctl -q net.ipv4.tcp_tso_win_divisor=100`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 30000) = 30000
+   +0 > P. 1:10001(10000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
++.105 < . 1:1(0) ack 1001 win 257
+   +0 > P. 10001:12001(2000) ack 1
+
+   +0 < . 1:1(0) ack 2001 win 257
+   +0 > P. 12001:14001(2000) ack 1
+
++.005 < . 1:1(0) ack 3001 win 257
+   +0 > P. 14001:16001(2000) ack 1
+
+   +0 < . 1:1(0) ack 4001 win 257
+   +0 > P. 16001:18001(2000) ack 1
+
++.005 < . 1:1(0) ack 5001 win 257
+   +0 > P. 18001:20001(2000) ack 1
+
+   +0 < . 1:1(0) ack 6001 win 257
+   +0 > P. 20001:22001(2000) ack 1
+
++.005 < . 1:1(0) ack 7001 win 257
+   +0 > P. 22001:24001(2000) ack 1
+
+   +0 < . 1:1(0) ack 8001 win 257
+   +0 > P. 24001:26001(2000) ack 1
+
++.005 < . 1:1(0) ack 9001 win 257
+   +0 > P. 26001:28001(2000) ack 1
+
+   +0 < . 1:1(0) ack 10001 win 257
+   +0 > P. 28001:30001(2000) ack 1
+
+   +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-5pkt.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-5pkt.pkt
new file mode 100644
index 000000000000..9212ae1fd0f2
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-5pkt.pkt
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when an outstanding flight of packets is
+// less than the current cwnd, and not big enough to bump up cwnd.
+//
+// In this variant, the receiver ACKs every other packet,
+// approximating standard delayed ACKs.
+
+// Set up config.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+
+// Only send 5 packets.
+   +0 write(4, ..., 5000) = 5000
+   +0 > P. 1:5001(5000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+   +0 < . 1:1(0) ack 2001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 10, 'cwnd=%d' % tcpi_snd_cwnd }%
+
+   +0 < . 1:1(0) ack 4001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 10, 'cwnd=%d' % tcpi_snd_cwnd }%
+
+   +0 < . 1:1(0) ack 5001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 10, 'cwnd=%d' % tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-6pkt.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-6pkt.pkt
new file mode 100644
index 000000000000..416c901ddf51
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt-send-6pkt.pkt
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when an outstanding flight of packets is
+// less than the current cwnd, but still big enough that in slow
+// start we want to increase our cwnd a little.
+//
+// In this variant, the receiver ACKs every other packet,
+// approximating standard delayed ACKs.
+
+// Set up config.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+   +0 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+
+// Only send 6 packets.
+   +0 write(4, ..., 6000) = 6000
+   +0 > P. 1:6001(6000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+   +0 < . 1:1(0) ack 2001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 12, 'cwnd=%d' % tcpi_snd_cwnd }%
+
+   +0 < . 1:1(0) ack 4001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 12, 'cwnd=%d' % tcpi_snd_cwnd }%
+
+   +0 < . 1:1(0) ack 6001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 12, 'cwnd=%d' % tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt.pkt
new file mode 100644
index 000000000000..a894b7d4559c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-2pkt.pkt
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when not application-limited, so that
+// the cwnd continues to grow.
+// In this variant, the receiver ACKs every other packet,
+// approximating standard delayed ACKs.
+
+// Set up config. To keep things simple, disable the
+// mechanism that defers sending in order to send bigger TSO packets.
+`./defaults.sh
+sysctl -q net.ipv4.tcp_tso_win_divisor=100`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 30000) = 30000
+   +0 > P. 1:10001(10000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
++.105 < . 1:1(0) ack 2001 win 257
+   +0 > P. 10001:14001(4000) ack 1
+
++.005 < . 1:1(0) ack 4001 win 257
+   +0 > P. 14001:18001(4000) ack 1
+
++.005 < . 1:1(0) ack 6001 win 257
+   +0 > P. 18001:22001(4000) ack 1
+
++.005 < . 1:1(0) ack 8001 win 257
+   +0 > P. 22001:26001(4000) ack 1
+
++.005 < . 1:1(0) ack 10001 win 257
+   +0 > P. 26001:30001(4000) ack 1
+
+   +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-4pkt.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-4pkt.pkt
new file mode 100644
index 000000000000..065fae9e9abd
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-ack-per-4pkt.pkt
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when not application-limited, so that
+// the cwnd continues to grow.
+// In this variant, the receiver sends one ACK per 4 packets.
+
+// Set up config. To keep things simple, disable the
+// mechanism that defers sending in order to send bigger TSO packets.
+`./defaults.sh
+sysctl -q net.ipv4.tcp_tso_win_divisor=100`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 30000) = 30000
+   +0 > P. 1:10001(10000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+ +.11 < . 1:1(0) ack 4001 win 257
+   +0 > P. 10001:18001(8000) ack 1
+
+ +.01 < . 1:1(0) ack 8001 win 257
+   +0 > P. 18001:26001(8000) ack 1
+
++.005 < . 1:1(0) ack 10001 win 257
+   +0 > P. 26001:30001(4000) ack 1
+
+   +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-idle.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-idle.pkt
new file mode 100644
index 000000000000..11b213be1138
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-idle.pkt
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start after idle
+// This test expects tso size to be at least initial cwnd * mss
+
+`./defaults.sh
+./set_sysctls.py /proc/sys/net/ipv4/tcp_slow_start_after_idle=1 \
+		 /proc/sys/net/ipv4/tcp_min_tso_segs=10`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 511
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 26000) = 26000
+   +0 > P. 1:5001(5000) ack 1
+   +0 > P. 5001:10001(5000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+  +.1 < . 1:1(0) ack 10001 win 511
+   +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
+   +0 > P. 10001:20001(10000) ack 1
+   +0 > P. 20001:26001(6000) ack 1
+
+  +.1 < . 1:1(0) ack 26001 win 511
+   +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%
+
+   +2 write(4, ..., 20000) = 20000
+// If slow start after idle works properly, we should send 5 MSS here (cwnd/2)
+   +0 > P. 26001:31001(5000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+// Reset sysctls
+`/tmp/sysctl_restore_${PPID}.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-win-update.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-win-update.pkt
new file mode 100644
index 000000000000..577ed8c8852c
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-after-win-update.pkt
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start after window update
+// This test expects tso size to be at least initial cwnd * mss
+
+`./defaults.sh
+./set_sysctls.py /proc/sys/net/ipv4/tcp_slow_start_after_idle=1 \
+		 /proc/sys/net/ipv4/tcp_min_tso_segs=10`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 511
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 26000) = 26000
+   +0 > P. 1:5001(5000) ack 1
+   +0 > P. 5001:10001(5000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
+  +.1 < . 1:1(0) ack 10001 win 511
+   +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
+   +0 > P. 10001:20001(10000) ack 1
+   +0 > P. 20001:26001(6000) ack 1
+
+  +.1 < . 1:1(0) ack 26001 win 0
+   +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%
+
+   +0 write(4, ..., 20000) = 20000
+// 1st win0 probe
++.3~+.310 > . 26000:26000(0) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%
+
+// 2nd win0 probe
++.6~+.620 > . 26000:26000(0) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%
+
+// 3rd win0 probe
++1.2~+1.240 > . 26000:26000(0) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%
+
+  +.9 < . 1:1(0) ack 26001 win 511
+   +0 > P. 26001:31001(5000) ack 1
+
+// Reset sysctls
+`/tmp/sysctl_restore_${PPID}.sh`
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited-9-packets-out.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited-9-packets-out.pkt
new file mode 100644
index 000000000000..869f32c35a2a
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited-9-packets-out.pkt
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when application-limited: in this case,
+// with IW10, if we don't fully use our cwnd but instead
+// send just 9 packets, then cwnd should grow to twice that
+// value, or 18 packets.
+
+// Set up config.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 9000) = 9000
+   +0 > P. 1:9001(9000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
++.105 < . 1:1(0) ack 2001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 12, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 4001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 14, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 6001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 16, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 8001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 18, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 9001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 18, tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited.pkt
new file mode 100644
index 000000000000..0f77b7955db6
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-app-limited.pkt
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when application-limited: in this case,
+// with IW10, if we send exactly 10 packets then cwnd should grow to 20.
+
+// Set up config.
+`./defaults.sh`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+  +.1 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 257
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 10000) = 10000
+   +0 > P. 1:10001(10000) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
++.105 < . 1:1(0) ack 2001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 12, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 4001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 14, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 6001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 16, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 8001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 18, tcpi_snd_cwnd }%
+
++.005 < . 1:1(0) ack 10001 win 257
+   +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
diff --git a/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-fq-ack-per-2pkt.pkt b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-fq-ack-per-2pkt.pkt
new file mode 100644
index 000000000000..7e9c83d617c2
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_slow_start_slow-start-fq-ack-per-2pkt.pkt
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+// Test of slow start when not application-limited, so that
+// the cwnd continues to grow, even if TSQ triggers.
+// In this variant, the receiver ACKs every other packet,
+// approximating standard delayed ACKs.
+
+// Note we use FQ/pacing to check if TCP Small Queues is not hurting
+
+`./defaults.sh
+tc qdisc replace dev tun0 root fq
+sysctl -q net/ipv4/tcp_pacing_ss_ratio=200
+sysctl -e -q net.ipv4.tcp_min_tso_segs=2`
+
+    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+  +.1 < S 0:0(0) win 32792 <mss 1460,sackOK,nop,nop,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
+  +.1 < . 1:1(0) ack 1 win 500
+   +0 accept(3, ..., ...) = 4
+   +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+
+   +0 write(4, ..., 40000) = 40000
+// This might change if we cook the initial packet with 10 MSS.
+   +0 > P. 1:2921(2920) ack 1
+   +0 > P. 2921:5841(2920) ack 1
+   +0 > P. 5841:8761(2920) ack 1
+   +0 > P. 8761:11681(2920) ack 1
+   +0 > P. 11681:14601(2920) ack 1
+   +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+
++.105 < . 1:1(0) ack 2921 win 500
+   +0 %{ assert tcpi_snd_cwnd == 12, tcpi_snd_cwnd }%
+
+// Note: after this commit : "net_sched: sch_fq: account for schedule/timers drifts"
+// FQ notices that this packet missed the 'time to send next packet' computed
+// when prior packet (11681:14601(2920)) was sent.
+// So FQ will allow following packet to be sent a bit earlier (quantum/2)
+// (FQ commit allows an application/cwnd limited flow to get at most quantum/2 extra credit)
+   +0 > P. 14601:17521(2920) ack 1
+
++.003 < . 1:1(0) ack 5841 win 500
+   +0 %{ assert tcpi_snd_cwnd == 14, tcpi_snd_cwnd }%
+
++.001 > P. 17521:20441(2920) ack 1
+
++.001 < . 1:1(0) ack 8761 win 500
+   +0 %{ assert tcpi_snd_cwnd == 16, tcpi_snd_cwnd }%
+
+// remaining packets are delivered at a constant rate.
++.007 > P. 20441:23361(2920) ack 1
+
++.002 < . 1:1(0) ack 11681 win 500
+   +0 %{ assert tcpi_snd_cwnd == 18, tcpi_snd_cwnd }%
++.001 < . 1:1(0) ack 14601 win 500
+
++.004 > P. 23361:26281(2920) ack 1
+
++.007 > P. 26281:29201(2920) ack 1
+
+   +0 %{ assert tcpi_snd_cwnd == 20, 'cwnd=%d' % tcpi_snd_cwnd }%
-- 
cgit v1.3-3-g829e


From b2155807893aac40f1a1cdf43f7fcc270cbfc05a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 10 Sep 2024 17:21:42 -0700
Subject: uapi: libc-compat: remove ipx leftovers

The uAPI headers for IPX were deleted 3 years ago in
commit 6c9b40844751 ("net: Remove net/ipx.h and uapi/linux/ipx.h header files")
Delete the leftover defines from libc-compat.h

Link: https://patch.msgid.link/20240911002142.1508694-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/libc-compat.h | 36 ------------------------------------
 1 file changed, 36 deletions(-)

diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h
index 8254c937c9f4..0eca95ccb41e 100644
--- a/include/uapi/linux/libc-compat.h
+++ b/include/uapi/linux/libc-compat.h
@@ -140,25 +140,6 @@
 
 #endif /* _NETINET_IN_H */
 
-/* Coordinate with glibc netipx/ipx.h header. */
-#if defined(__NETIPX_IPX_H)
-
-#define __UAPI_DEF_SOCKADDR_IPX			0
-#define __UAPI_DEF_IPX_ROUTE_DEFINITION		0
-#define __UAPI_DEF_IPX_INTERFACE_DEFINITION	0
-#define __UAPI_DEF_IPX_CONFIG_DATA		0
-#define __UAPI_DEF_IPX_ROUTE_DEF		0
-
-#else /* defined(__NETIPX_IPX_H) */
-
-#define __UAPI_DEF_SOCKADDR_IPX			1
-#define __UAPI_DEF_IPX_ROUTE_DEFINITION		1
-#define __UAPI_DEF_IPX_INTERFACE_DEFINITION	1
-#define __UAPI_DEF_IPX_CONFIG_DATA		1
-#define __UAPI_DEF_IPX_ROUTE_DEF		1
-
-#endif /* defined(__NETIPX_IPX_H) */
-
 /* Definitions for xattr.h */
 #if defined(_SYS_XATTR_H)
 #define __UAPI_DEF_XATTR		0
@@ -240,23 +221,6 @@
 #define __UAPI_DEF_IP6_MTUINFO		1
 #endif
 
-/* Definitions for ipx.h */
-#ifndef __UAPI_DEF_SOCKADDR_IPX
-#define __UAPI_DEF_SOCKADDR_IPX			1
-#endif
-#ifndef __UAPI_DEF_IPX_ROUTE_DEFINITION
-#define __UAPI_DEF_IPX_ROUTE_DEFINITION		1
-#endif
-#ifndef __UAPI_DEF_IPX_INTERFACE_DEFINITION
-#define __UAPI_DEF_IPX_INTERFACE_DEFINITION	1
-#endif
-#ifndef __UAPI_DEF_IPX_CONFIG_DATA
-#define __UAPI_DEF_IPX_CONFIG_DATA		1
-#endif
-#ifndef __UAPI_DEF_IPX_ROUTE_DEF
-#define __UAPI_DEF_IPX_ROUTE_DEF		1
-#endif
-
 /* Definitions for xattr.h */
 #ifndef __UAPI_DEF_XATTR
 #define __UAPI_DEF_XATTR		1
-- 
cgit v1.3-3-g829e


From 5905c024a776c7f592581551993817aaf0cd1f36 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 10 Sep 2024 18:52:28 -0700
Subject: net: caif: remove unused name

Justin sent a patch to use strscpy_pad() instead of strncpy()
on the name field. Simon rightly asked why the _pad() version
is used, and looking closer name seems completely unused,
the last code which referred to it was removed in
commit 8391c4aab1aa ("caif: Bugfixes in CAIF netdevice for close and flow control")

Link: https://lore.kernel.org/20240909-strncpy-net-caif-chnl_net-c-v1-1-438eb870c155@google.com
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Justin Stitt <justinstitt@google.com>
Link: https://patch.msgid.link/20240911015228.1555779-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/caif/chnl_net.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 47901bd4def1..94ad09e36df2 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -47,7 +47,6 @@ struct chnl_net {
 	struct caif_connect_request conn_req;
 	struct list_head list_field;
 	struct net_device *netdev;
-	char name[256];
 	wait_queue_head_t netmgmt_wq;
 	/* Flow status to remember and control the transmission. */
 	bool flowenabled;
@@ -347,7 +346,6 @@ static int chnl_net_init(struct net_device *dev)
 	struct chnl_net *priv;
 	ASSERT_RTNL();
 	priv = netdev_priv(dev);
-	strncpy(priv->name, dev->name, sizeof(priv->name));
 	INIT_LIST_HEAD(&priv->list_field);
 	return 0;
 }
-- 
cgit v1.3-3-g829e


From 45fa29c85117170b0508790f878b13ec6593c888 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 11 Sep 2024 11:20:58 +0200
Subject: bareudp: Pull inner IP header in bareudp_udp_encap_recv().

Bareudp reads the inner IP header to get the ECN value. Therefore, it
needs to ensure that it's part of the skb's linear data.

This is similar to the vxlan and geneve fixes for that same problem:
  * commit f7789419137b ("vxlan: Pull inner IP header in vxlan_rcv().")
  * commit 1ca1ba465e55 ("geneve: make sure to pull inner header in
    geneve_rx()")

Fixes: 571912c69f0e ("net: UDP tunnel encapsulation module for tunnelling different protocols like MPLS, IP, NSH etc.")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/5205940067c40218a70fbb888080466b2fc288db.1726046181.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bareudp.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 7aca0544fb29..b4e820a123ca 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -68,6 +68,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	__be16 proto;
 	void *oiph;
 	int err;
+	int nh;
 
 	bareudp = rcu_dereference_sk_user_data(sk);
 	if (!bareudp)
@@ -148,10 +149,25 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	}
 	skb_dst_set(skb, &tun_dst->dst);
 	skb->dev = bareudp->dev;
-	oiph = skb_network_header(skb);
-	skb_reset_network_header(skb);
 	skb_reset_mac_header(skb);
 
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
+	skb_reset_network_header(skb);
+
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(bareudp->dev, rx_length_errors);
+		DEV_STATS_INC(bareudp->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	oiph = skb->head + nh;
+
 	if (!ipv6_mod_enabled() || family == AF_INET)
 		err = IP_ECN_decapsulate(oiph, skb);
 	else
-- 
cgit v1.3-3-g829e


From c471236b2359e6b27388475dd04fff0a5e2bf922 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 11 Sep 2024 11:21:05 +0200
Subject: bareudp: Pull inner IP header on xmit.

Both bareudp_xmit_skb() and bareudp6_xmit_skb() read their skb's inner
IP header to get its ECN value (with ip_tunnel_ecn_encap()). Therefore
we need to ensure that the inner IP header is part of the skb's linear
data.

Fixes: 571912c69f0e ("net: UDP tunnel encapsulation module for tunnelling different protocols like MPLS, IP, NSH etc.")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/267328222f0a11519c6de04c640a4f87a38ea9ed.1726046181.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bareudp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index b4e820a123ca..e80992b4f9de 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -317,6 +317,9 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be32 saddr;
 	int err;
 
+	if (!skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB)))
+		return -EINVAL;
+
 	if (!sock)
 		return -ESHUTDOWN;
 
@@ -384,6 +387,9 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 	__be16 sport;
 	int err;
 
+	if (!skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB)))
+		return -EINVAL;
+
 	if (!sock)
 		return -ESHUTDOWN;
 
-- 
cgit v1.3-3-g829e


From e08ec0597badf325ad103c447cedeb5b7d7add45 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Wed, 11 Sep 2024 17:44:43 +0800
Subject: net: apple: bmac: Use IRQF_NO_AUTOEN flag in request_irq()

disable_irq() after request_irq() still has a time gap in which
interrupts can come. request_irq() with IRQF_NO_AUTOEN flag will
disable IRQ auto-enable when request IRQ.

Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://patch.msgid.link/20240911094445.1922476-2-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/apple/bmac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 292b1f9cd9e7..785f4b4ff758 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -1317,7 +1317,7 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match)
 
 	timer_setup(&bp->tx_timeout, bmac_tx_timeout, 0);
 
-	ret = request_irq(dev->irq, bmac_misc_intr, 0, "BMAC-misc", dev);
+	ret = request_irq(dev->irq, bmac_misc_intr, IRQF_NO_AUTOEN, "BMAC-misc", dev);
 	if (ret) {
 		printk(KERN_ERR "BMAC: can't get irq %d\n", dev->irq);
 		goto err_out_iounmap_rx;
@@ -1336,7 +1336,6 @@ static int bmac_probe(struct macio_dev *mdev, const struct of_device_id *match)
 	/* Mask chip interrupts and disable chip, will be
 	 * re-enabled on open()
 	 */
-	disable_irq(dev->irq);
 	pmac_call_feature(PMAC_FTR_BMAC_ENABLE, macio_get_of_node(bp->mdev), 0, 0);
 
 	if (register_netdev(dev) != 0) {
-- 
cgit v1.3-3-g829e


From 799a9225997799f7b1b579bc50a93b78b4fb2a01 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Wed, 11 Sep 2024 17:44:44 +0800
Subject: net: enetc: Use IRQF_NO_AUTOEN flag in request_irq()

disable_irq() after request_irq() still has a time gap in which
interrupts can come. request_irq() with IRQF_NO_AUTOEN flag will
disable IRQ auto-enable when request IRQ.

Fixes: bbb96dc7fa1a ("enetc: Factor out the traffic start/stop procedures")
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://patch.msgid.link/20240911094445.1922476-3-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 5c45f42232d3..f04f42ea60c0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2305,12 +2305,11 @@ static int enetc_setup_irqs(struct enetc_ndev_priv *priv)
 
 		snprintf(v->name, sizeof(v->name), "%s-rxtx%d",
 			 priv->ndev->name, i);
-		err = request_irq(irq, enetc_msix, 0, v->name, v);
+		err = request_irq(irq, enetc_msix, IRQF_NO_AUTOEN, v->name, v);
 		if (err) {
 			dev_err(priv->dev, "request_irq() failed!\n");
 			goto irq_err;
 		}
-		disable_irq(irq);
 
 		v->tbier_base = hw->reg + ENETC_BDR(TX, 0, ENETC_TBIER);
 		v->rbier = hw->reg + ENETC_BDR(RX, i, ENETC_RBIER);
-- 
cgit v1.3-3-g829e


From daaba19d357f0900b303a530ced96c78086267ea Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Wed, 11 Sep 2024 17:44:45 +0800
Subject: nfp: Use IRQF_NO_AUTOEN flag in request_irq()

disable_irq() after request_irq() still has a time gap in which
interrupts can come. request_irq() with IRQF_NO_AUTOEN flag will
disable IRQ auto-enable when request IRQ.

Reviewed-by: Louis Peens <louis.peens@corigine.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Link: https://patch.msgid.link/20240911094445.1922476-4-ruanjinjie@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 182ba0a8b095..6e0929af0f72 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -821,14 +821,13 @@ nfp_net_prepare_vector(struct nfp_net *nn, struct nfp_net_r_vector *r_vec,
 
 	snprintf(r_vec->name, sizeof(r_vec->name),
 		 "%s-rxtx-%d", nfp_net_name(nn), idx);
-	err = request_irq(r_vec->irq_vector, r_vec->handler, 0, r_vec->name,
-			  r_vec);
+	err = request_irq(r_vec->irq_vector, r_vec->handler, IRQF_NO_AUTOEN,
+			  r_vec->name, r_vec);
 	if (err) {
 		nfp_net_napi_del(&nn->dp, r_vec);
 		nn_err(nn, "Error requesting IRQ %d\n", r_vec->irq_vector);
 		return err;
 	}
-	disable_irq(r_vec->irq_vector);
 
 	irq_set_affinity_hint(r_vec->irq_vector, &r_vec->affinity_mask);
 
-- 
cgit v1.3-3-g829e


From e2e9ddf8775b2f6c28e24b2fabbf2fc8302a679e Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:43 -0700
Subject: net/mlx5: HWS, updated API functions comments to kernel doc

Changed all the functions comments to adhere with kernel-doc formatting.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-2-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/steering/hws/mlx5hws.h      | 756 ++++++++++-----------
 1 file changed, 364 insertions(+), 392 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index 9a85d4e12f77..f39d636ff39a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -214,11 +214,12 @@ struct mlx5hws_action_dest_attr {
 	struct mlx5hws_action *reformat;
 };
 
-/* Check whether HWS is supported
+/**
+ * mlx5hws_is_supported - Check whether HWS is supported
  *
- * @param[in] mdev
- *	The device to check.
- * @return true if supported, false otherwise.
+ * @mdev: The device to check.
+ *
+ * Return: true if supported, false otherwise.
  */
 static inline bool mlx5hws_is_supported(struct mlx5_core_dev *mdev)
 {
@@ -234,92 +235,94 @@ static inline bool mlx5hws_is_supported(struct mlx5_core_dev *mdev)
 	return wqe_based_flow_table_update && ignore_flow_level_rtc_valid;
 }
 
-/* Open a context used for direct rule insertion using hardware steering.
- * Each context can contain multiple tables of different types.
+/**
+ * mlx5hws_context_open - Open a context used for direct rule insertion
+ * using hardware steering.
+ *
+ * @mdev: The device to be used for HWS.
+ * @attr: Attributes used for context open.
  *
- * @param[in] mdev
- *	The device to be used for HWS.
- * @param[in] attr
- *	Attributes used for context open.
- * @return pointer to mlx5hws_context on success NULL otherwise.
+ * Return: pointer to mlx5hws_context on success NULL otherwise.
  */
 struct mlx5hws_context *
 mlx5hws_context_open(struct mlx5_core_dev *mdev,
 		     struct mlx5hws_context_attr *attr);
 
-/* Close a context used for direct hardware steering.
+/**
+ * mlx5hws_context_close - Close a context used for direct hardware steering.
  *
- * @param[in] ctx
- *	mlx5hws context to close.
- * @return zero on success non zero otherwise.
+ * @ctx: mlx5hws context to close.
+ *
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_context_close(struct mlx5hws_context *ctx);
 
-/* Set a peer context, each context can have multiple contexts as peers.
+/**
+ * mlx5hws_context_set_peer - Set a peer context.
+ * Each context can have multiple contexts as peers.
  *
- * @param[in] ctx
- *	The context in which the peer_ctx will be peered to it.
- * @param[in] peer_ctx
- *	The peer context.
- * @param[in] peer_vhca_id
- *	The peer context vhca id.
+ * @ctx: The context in which the peer_ctx will be peered to it.
+ * @peer_ctx: The peer context.
+ * @peer_vhca_id: The peer context vhca id.
  */
 void mlx5hws_context_set_peer(struct mlx5hws_context *ctx,
 			      struct mlx5hws_context *peer_ctx,
 			      u16 peer_vhca_id);
 
-/* Create a new direct rule table. Each table can contain multiple matchers.
+/**
+ * mlx5hws_table_create - Create a new direct rule table.
+ * Each table can contain multiple matchers.
+ *
+ * @ctx: The context in which the new table will be opened.
+ * @attr: Attributes used for table creation.
  *
- * @param[in] ctx
- *	The context in which the new table will be opened.
- * @param[in] attr
- *	Attributes used for table creation.
- * @return pointer to mlx5hws_table on success NULL otherwise.
+ * Return: pointer to mlx5hws_table on success NULL otherwise.
  */
 struct mlx5hws_table *
 mlx5hws_table_create(struct mlx5hws_context *ctx,
 		     struct mlx5hws_table_attr *attr);
 
-/* Destroy direct rule table.
+/**
+ * mlx5hws_table_destroy - Destroy direct rule table.
  *
- * @param[in] tbl
- *	Table to destroy.
- * @return zero on success non zero otherwise.
+ * @tbl: Table to destroy.
+ *
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_table_destroy(struct mlx5hws_table *tbl);
 
-/* Get ID of the flow table.
+/**
+ * mlx5hws_table_get_id() - Get ID of the flow table.
+ *
+ * @tbl:Table to get ID of.
  *
- * @param[in] tbl
- *	Table to get ID of.
- * @return ID of the table.
+ * Return: ID of the table.
  */
 u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl);
 
-/* Set default miss table for mlx5hws_table by using another mlx5hws_table
+/**
+ * mlx5hws_table_set_default_miss - Set default miss table for mlx5hws_table
+ * by using another mlx5hws_table.
  * Traffic which all table matchers miss will be forwarded to miss table.
  *
- * @param[in] tbl
- *	Source table
- * @param[in] miss_tbl
- *	Target (miss) table, or NULL to remove current miss table
- * @return zero on success non zero otherwise.
+ * @tbl: Source table
+ * @miss_tbl: Target (miss) table, or NULL to remove current miss table
+ *
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
 				   struct mlx5hws_table *miss_tbl);
 
-/* Create new match template based on items mask, the match template
- * will be used for matcher creation.
+/**
+ * mlx5hws_match_template_create - Create a new match template based on items mask.
+ * The match template will be used for matcher creation.
+ *
+ * @ctx: The context in which the new template will be created.
+ * @match_param: Describe the mask based on PRM match parameters.
+ * @match_param_sz: Size of match param buffer.
+ * @match_criteria_enable: Bitmap for each sub-set in match_criteria buffer.
  *
- * @param[in] ctx
- *	The context in which the new template will be created.
- * @param[in] match_param
- *	Describe the mask based on PRM match parameters
- * @param[in] match_param_sz
- *	Size of match param buffer
- * @param[in] match_criteria_enable
- *	Bitmap for each sub-set in match_criteria buffer
- * @return pointer to mlx5hws_match_template on success NULL otherwise
+ * Return: Pointer to mlx5hws_match_template on success, NULL otherwise.
  */
 struct mlx5hws_match_template *
 mlx5hws_match_template_create(struct mlx5hws_context *ctx,
@@ -327,52 +330,53 @@ mlx5hws_match_template_create(struct mlx5hws_context *ctx,
 			      u32 match_param_sz,
 			      u8 match_criteria_enable);
 
-/* Destroy match template.
+/**
+ * mlx5hws_match_template_destroy - Destroy a match template.
  *
- * @param[in] mt
- *	Match template to destroy.
- * @return zero on success non zero otherwise.
+ * @mt: Match template to destroy.
+ *
+ * Return: Zero on success, non-zero otherwise.
  */
 int mlx5hws_match_template_destroy(struct mlx5hws_match_template *mt);
 
-/* Create new action template based on action_type array, the action template
- * will be used for matcher creation.
+/**
+ * mlx5hws_action_template_create - Create a new action template based on an action_type array.
+ *
+ * @action_type: An array of actions based on the order of actions which will be provided
+ *               with rule_actions to mlx5hws_rule_create. The last action is marked
+ *               using MLX5HWS_ACTION_TYP_LAST.
  *
- * @param[in] action_type
- *	An array of actions based on the order of actions which will be provided
- *	with rule_actions to mlx5hws_rule_create. The last action is marked
- *	using MLX5HWS_ACTION_TYP_LAST.
- * @return pointer to mlx5hws_action_template on success NULL otherwise
+ * Return: Pointer to mlx5hws_action_template on success, NULL otherwise.
  */
 struct mlx5hws_action_template *
 mlx5hws_action_template_create(enum mlx5hws_action_type action_type[]);
 
-/* Destroy action template.
+/**
+ * mlx5hws_action_template_destroy - Destroy action template.
  *
- * @param[in] at
- *	Action template to destroy.
- * @return zero on success non zero otherwise.
+ * @at: Action template to destroy.
+ *
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_action_template_destroy(struct mlx5hws_action_template *at);
 
-/* Create a new direct rule matcher. Each matcher can contain multiple rules.
- * Matchers on the table will be processed by priority. Matching fields and
- * mask are described by the match template. In some cases multiple match
- * templates can be used on the same matcher.
- *
- * @param[in] table
- *	The table in which the new matcher will be opened.
- * @param[in] mt
- *	Array of match templates to be used on matcher.
- * @param[in] num_of_mt
- *	Number of match templates in mt array.
- * @param[in] at
- *	Array of action templates to be used on matcher.
- * @param[in] num_of_at
- *	Number of action templates in mt array.
- * @param[in] attr
- *	Attributes used for matcher creation.
- * @return pointer to mlx5hws_matcher on success NULL otherwise.
+/**
+ * mlx5hws_matcher_create - Create a new direct rule matcher.
+ *
+ * Each matcher can contain multiple rules. Matchers on the table will be
+ * processed by priority. Matching fields and mask are described by the
+ * match template. In some cases, multiple match templates can be used on
+ * the same matcher.
+ *
+ * @table: The table in which the new matcher will be opened.
+ * @mt: Array of match templates to be used on matcher.
+ * @num_of_mt: Number of match templates in mt array.
+ * @at: Array of action templates to be used on matcher.
+ * @num_of_at: Number of action templates in at array.
+ * @attr: Attributes used for matcher creation.
+ *
+ * Return: Pointer to mlx5hws_matcher on success, NULL otherwise.
+ *
  */
 struct mlx5hws_matcher *
 mlx5hws_matcher_create(struct mlx5hws_table *table,
@@ -382,81 +386,77 @@ mlx5hws_matcher_create(struct mlx5hws_table *table,
 		       u8 num_of_at,
 		       struct mlx5hws_matcher_attr *attr);
 
-/* Destroy direct rule matcher.
+/**
+ * mlx5hws_matcher_destroy - Destroy a direct rule matcher.
  *
- * @param[in] matcher
- *	Matcher to destroy.
- * @return zero on success non zero otherwise.
+ * @matcher: Matcher to destroy.
+ *
+ * Return: Zero on success, non-zero otherwise.
  */
 int mlx5hws_matcher_destroy(struct mlx5hws_matcher *matcher);
 
-/* Attach new action template to direct rule matcher.
+/**
+ * mlx5hws_matcher_attach_at - Attach a new action template to a direct rule matcher.
+ *
+ * @matcher: Matcher to attach the action template to.
+ * @at: Action template to be attached to the matcher.
  *
- * @param[in] matcher
- *	Matcher to attach at to.
- * @param[in] at
- *	Action template to be attached to the matcher.
- * @return zero on success non zero otherwise.
+ * Return: Zero on success, non-zero otherwise.
  */
 int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 			      struct mlx5hws_action_template *at);
 
-/* Link two matchers and enable moving rules from src matcher to dst matcher.
- * Both matchers must be in the same table type, must be created with 'resizable'
- * property, and should have the same characteristics (e.g. same mt, same at).
+/**
+ * mlx5hws_matcher_resize_set_target - Link two matchers and enable moving rules.
  *
- * It is the user's responsibility to make sure that the dst matcher
- * was allocated with the appropriate size.
+ * Both matchers must be in the same table type, must be created with the
+ * 'resizable' property, and should have the same characteristics (e.g., same
+ * match templates and action templates). It is the user's responsibility to
+ * ensure that the destination matcher is allocated with the appropriate size.
  *
  * Once the function is completed, the user is:
- *  - allowed to move rules from src into dst matcher
- *  - no longer allowed to insert rules to the src matcher
+ * - Allowed to move rules from the source into the destination matcher.
+ * - No longer allowed to insert rules into the source matcher.
  *
- * The user is always allowed to insert rules to the dst matcher and
+ * The user is always allowed to insert rules into the destination matcher and
  * to delete rules from any matcher.
  *
- * @param[in] src_matcher
- *	source matcher for moving rules from
- * @param[in] dst_matcher
- *	destination matcher for moving rules to
- * @return zero on successful move, non zero otherwise.
+ * @src_matcher: Source matcher for moving rules from.
+ * @dst_matcher: Destination matcher for moving rules to.
+ *
+ * Return: Zero on successful move, non-zero otherwise.
  */
 int mlx5hws_matcher_resize_set_target(struct mlx5hws_matcher *src_matcher,
 				      struct mlx5hws_matcher *dst_matcher);
 
-/* Enqueue moving rule operation: moving rule from src matcher to a dst matcher
+/**
+ * mlx5hws_matcher_resize_rule_move - Enqueue moving rule operation.
+ *
+ * This function enqueues the operation of moving a rule from the source
+ * matcher to the destination matcher.
  *
- * @param[in] src_matcher
- *	matcher that the rule belongs to
- * @param[in] rule
- *	the rule to move
- * @param[in] attr
- *	rule attributes
- * @return zero on success, non zero otherwise.
+ * @src_matcher: Matcher that the rule belongs to.
+ * @rule: The rule to move.
+ * @attr: Rule attributes.
+ *
+ * Return: Zero on success, non-zero otherwise.
  */
 int mlx5hws_matcher_resize_rule_move(struct mlx5hws_matcher *src_matcher,
 				     struct mlx5hws_rule *rule,
 				     struct mlx5hws_rule_attr *attr);
 
-/* Enqueue create rule operation.
- *
- * @param[in] matcher
- *	The matcher in which the new rule will be created.
- * @param[in] mt_idx
- *	Match template index to create the match with.
- * @param[in] match_param
- *	The match parameter PRM buffer used for the value matching.
- * @param[in] rule_actions
- *	Rule action to be executed on match.
- * @param[in] at_idx
- *	Action template index to apply the actions with.
- * @param[in] num_of_actions
- *	Number of rule actions.
- * @param[in] attr
- *	Rule creation attributes.
- * @param[in, out] rule_handle
- *	A valid rule handle. The handle doesn't require any initialization.
- * @return zero on successful enqueue non zero otherwise.
+/**
+ * mlx5hws_rule_create - Enqueue create rule operation.
+ *
+ * @matcher: The matcher in which the new rule will be created.
+ * @mt_idx: Match template index to create the match with.
+ * @match_param: The match parameter PRM buffer used for value matching.
+ * @at_idx: Action template index to apply the actions with.
+ * @rule_actions: Rule actions to be executed on match.
+ * @attr: Rule creation attributes.
+ * @rule_handle: A valid rule handle. The handle doesn't require any initialization.
+ *
+ * Return: Zero on successful enqueue, non-zero otherwise.
  */
 int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 			u8 mt_idx,
@@ -466,114 +466,106 @@ int mlx5hws_rule_create(struct mlx5hws_matcher *matcher,
 			struct mlx5hws_rule_attr *attr,
 			struct mlx5hws_rule *rule_handle);
 
-/* Enqueue destroy rule operation.
+/**
+ * mlx5hws_rule_destroy - Enqueue destroy rule operation.
+ *
+ * @rule: The rule destruction to enqueue.
+ * @attr: Rule destruction attributes.
  *
- * @param[in] rule
- *	The rule destruction to enqueue.
- * @param[in] attr
- *	Rule destruction attributes.
- * @return zero on successful enqueue non zero otherwise.
+ * Return: Zero on successful enqueue, non-zero otherwise.
  */
 int mlx5hws_rule_destroy(struct mlx5hws_rule *rule,
 			 struct mlx5hws_rule_attr *attr);
 
-/* Enqueue update actions on an existing rule.
+/**
+ * mlx5hws_rule_action_update - Enqueue update actions on an existing rule.
  *
- * @param[in, out] rule_handle
- *	A valid rule handle to update.
- * @param[in] at_idx
- *	Action template index to update the actions with.
- *  @param[in] rule_actions
- *	Rule action to be executed on match.
- * @param[in] attr
- *	Rule update attributes.
- * @return zero on successful enqueue non zero otherwise.
+ * @rule: A valid rule handle to update.
+ * @at_idx: Action template index to update the actions with.
+ * @rule_actions: Rule actions to be executed on match.
+ * @attr: Rule update attributes.
+ *
+ * Return: Zero on successful enqueue, non-zero otherwise.
  */
 int mlx5hws_rule_action_update(struct mlx5hws_rule *rule,
 			       u8 at_idx,
 			       struct mlx5hws_rule_action rule_actions[],
 			       struct mlx5hws_rule_attr *attr);
 
-/* Get action type.
+/**
+ * mlx5hws_action_get_type - Get action type.
+ *
+ * @action: The action to get the type of.
  *
- * @param[in] action
- *	The action to get the type of.
- * @return action type.
+ * Return: action type.
  */
 enum mlx5hws_action_type
 mlx5hws_action_get_type(struct mlx5hws_action *action);
 
-/* Create direct rule drop action.
+/**
+ * mlx5hws_action_create_dest_drop - Create a direct rule drop action.
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * @ctx: The context in which the new action will be created.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: Pointer to mlx5hws_action on success, NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_dest_drop(struct mlx5hws_context *ctx,
 				u32 flags);
 
-/* Create direct rule default miss action.
- * Defaults are RX: Drop TX: Wire.
+/**
+ * mlx5hws_action_create_default_miss - Create a direct rule default miss action.
+ * Defaults are RX: Drop, TX: Wire.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: Pointer to mlx5hws_action on success, NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_default_miss(struct mlx5hws_context *ctx,
 				   u32 flags);
 
-/* Create direct rule goto table action.
+/**
+ * mlx5hws_action_create_dest_table - Create direct rule goto table action.
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] tbl
- *	Destination table.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * @ctx: The context in which the new action will be created.
+ * @tbl: Destination table.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_dest_table(struct mlx5hws_context *ctx,
 				 struct mlx5hws_table *tbl,
 				 u32 flags);
 
-/* Create direct rule goto table number action.
+/**
+ * mlx5hws_action_create_dest_table_num - Create direct rule goto table number action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @tbl_num: Destination table number.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] tbl_num
- *	Destination table number.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_dest_table_num(struct mlx5hws_context *ctx,
-				     u32 table_num, u32 flags);
-
-/* Create direct rule range match action.
- *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] field
- *	Field to comapare the value.
- * @param[in] hit_ft
- *	Flow table to go to on hit.
- * @param[in] miss_ft
- *	Flow table to go to on miss.
- * @param[in] min
- *	Minimal value of the field to be considered as hit.
- * @param[in] max
- *	Maximal value of the field to be considered as hit.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+				     u32 tbl_num, u32 flags);
+
+/**
+ * mlx5hws_action_create_dest_match_range - Create direct rule range match action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @field: Field to comapare the value.
+ * @hit_ft: Flow table to go to on hit.
+ * @miss_ft: Flow table to go to on miss.
+ * @min: Minimal value of the field to be considered as hit.
+ * @max: Maximal value of the field to be considered as hit.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
@@ -582,33 +574,29 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 				       struct mlx5_flow_table *miss_ft,
 				       u32 min, u32 max, u32 flags);
 
-/* Create direct rule flow sampler action.
+/**
+ * mlx5hws_action_create_flow_sampler - Create direct rule flow sampler action.
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] sampler_id
- *	Flow sampler object ID.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * @ctx: The context in which the new action will be created.
+ * @sampler_id: Flow sampler object ID.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx,
 				   u32 sampler_id, u32 flags);
 
-/* Create direct rule goto vport action.
+/**
+ * mlx5hws_action_create_dest_vport - Create direct rule goto vport action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @vport_num: Destination vport number.
+ * @vhca_id_valid: Tells if the vhca_id parameter is valid.
+ * @vhca_id: VHCA ID of the destination vport.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] vport_num
- *	Destination vport number.
- * @param[in] vhca_id_valid
- *	Tells if the vhca_id parameter is valid.
- * @param[in] vhca_id
- *	VHCA ID of the destination vport.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_dest_vport(struct mlx5hws_context *ctx,
@@ -617,48 +605,42 @@ mlx5hws_action_create_dest_vport(struct mlx5hws_context *ctx,
 				 u16 vhca_id,
 				 u32 flags);
 
-/* Create direct rule TAG action.
+/**
+ * mlx5hws_action_create_tag - Create direct rule TAG action.
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * @ctx: The context in which the new action will be created.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
-mlx5hws_action_create_tag(struct mlx5hws_context *ctx,
-			  u32 flags);
+mlx5hws_action_create_tag(struct mlx5hws_context *ctx, u32 flags);
 
-/* Create direct rule counter action.
+/**
+ * mlx5hws_action_create_counter - Create direct rule counter action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @obj_id: Direct rule counter object ID.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] obj_id
- *	Direct rule counter object ID.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_counter(struct mlx5hws_context *ctx,
 			      u32 obj_id,
 			      u32 flags);
 
-/* Create direct rule reformat action.
- *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] reformat_type
- *	Type of reformat prefixed with MLX5HWS_ACTION_TYP_REFORMAT.
- * @param[in] num_of_hdrs
- *	Number of provided headers in "hdrs" array.
- * @param[in] hdrs
- *	Headers array containing header information.
- * @param[in] log_bulk_size
- *	Number of unique values used with this reformat.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+/**
+ * mlx5hws_action_create_reformat - Create direct rule reformat action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @reformat_type: Type of reformat prefixed with MLX5HWS_ACTION_TYP_REFORMAT.
+ * @num_of_hdrs: Number of provided headers in "hdrs" array.
+ * @hdrs: Headers array containing header information.
+ * @log_bulk_size: Number of unique values used with this reformat.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_reformat(struct mlx5hws_context *ctx,
@@ -668,19 +650,16 @@ mlx5hws_action_create_reformat(struct mlx5hws_context *ctx,
 			       u32 log_bulk_size,
 			       u32 flags);
 
-/* Create direct rule modify header action.
+/**
+ * mlx5hws_action_create_modify_header - Create direct rule modify header action.
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] num_of_patterns
- *	Number of provided patterns in "patterns" array.
- * @param[in] patterns
- *	Patterns array containing pattern information.
- * @param[in] log_bulk_size
- *	Number of unique values used with this pattern.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * @ctx: The context in which the new action will be created.
+ * @num_of_patterns: Number of provided patterns in "patterns" array.
+ * @patterns: Patterns array containing pattern information.
+ * @log_bulk_size: Number of unique values used with this pattern.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_modify_header(struct mlx5hws_context *ctx,
@@ -689,17 +668,16 @@ mlx5hws_action_create_modify_header(struct mlx5hws_context *ctx,
 				    u32 log_bulk_size,
 				    u32 flags);
 
-/* Create direct rule ASO flow meter action.
+/**
+ * mlx5hws_action_create_aso_meter - Create direct rule ASO flow meter action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @obj_id: ASO object ID.
+ * @return_reg_c: Copy the ASO object value into this reg_c,
+ *		  after a packet hits a rule with this ASO object.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] obj_id
- *	ASO object ID.
- * @param[in] return_reg_c
- *	Copy the ASO object value into this reg_c, after a packet hits a rule with this ASO object.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_aso_meter(struct mlx5hws_context *ctx,
@@ -707,42 +685,41 @@ mlx5hws_action_create_aso_meter(struct mlx5hws_context *ctx,
 				u8 return_reg_c,
 				u32 flags);
 
-/* Create direct rule pop vlan action.
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+/**
+ * mlx5hws_action_create_pop_vlan - Create direct rule pop vlan action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_pop_vlan(struct mlx5hws_context *ctx, u32 flags);
 
-/* Create direct rule push vlan action.
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+/**
+ * mlx5hws_action_create_push_vlan - Create direct rule push vlan action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_push_vlan(struct mlx5hws_context *ctx, u32 flags);
 
-/* Create a dest array action, this action can duplicate packets and forward to
- * multiple destinations in the destination list.
- * @param[in] ctx
- *     The context in which the new action will be created.
- * @param[in] num_dest
- *     The number of dests attributes.
- * @param[in] dests
- *     The destination array. Each contains a destination action and can have
- *     additional actions.
- * @param[in] ignore_flow_level
- *     Boolean that says whether to turn on 'ignore_flow_level' for this dest.
- * @param[in] flow_source
- *     Source port of the traffic for this actions.
- * @param[in] flags
- *     Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+/**
+ * mlx5hws_action_create_dest_array - Create a dest array action, this action can
+ * duplicate packets and forward to multiple destinations in the destination list.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @num_dest: The number of dests attributes.
+ * @dests: The destination array. Each contains a destination action and can
+ *	   have additional actions.
+ * @ignore_flow_level: Whether to turn on 'ignore_flow_level' for this dest.
+ * @flow_source: Source port of the traffic for this actions.
+ * @flags: Action creation flags (enum mlx5hws_action_flags).
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
@@ -752,19 +729,16 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 				 u32 flow_source,
 				 u32 flags);
 
-/* Create insert header action.
+/**
+ * mlx5hws_action_create_insert_header - Create insert header action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @num_of_hdrs: Number of provided headers in "hdrs" array.
+ * @hdrs: Headers array containing header information.
+ * @log_bulk_size: Number of unique values used with this insert header.
+ * @flags: Action creation flags. (enum mlx5hws_action_flags)
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] num_of_hdrs
- *	Number of provided headers in "hdrs" array.
- * @param[in] hdrs
- *	Headers array containing header information.
- * @param[in] log_bulk_size
- *	Number of unique values used with this insert header.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_insert_header(struct mlx5hws_context *ctx,
@@ -773,38 +747,38 @@ mlx5hws_action_create_insert_header(struct mlx5hws_context *ctx,
 				    u32 log_bulk_size,
 				    u32 flags);
 
-/* Create remove header action.
+/**
+ * mlx5hws_action_create_remove_header - Create remove header action.
  *
- * @param[in] ctx
- *	The context in which the new action will be created.
- * @param[in] attr
- *	attributes: specifies the remove header type, PRM start anchor and
- *	the PRM end anchor or the PRM start anchor and remove size in bytes.
- * @param[in] flags
- *	Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * @ctx: The context in which the new action will be created.
+ * @attr: attributes that specifie the remove header type, PRM start anchor and
+ *	  the PRM end anchor or the PRM start anchor and remove size in bytes.
+ * @flags: Action creation flags. (enum mlx5hws_action_flags)
+ *
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_remove_header(struct mlx5hws_context *ctx,
 				    struct mlx5hws_action_remove_header_attr *attr,
 				    u32 flags);
 
-/* Create direct rule LAST action.
+/**
+ * mlx5hws_action_create_last - Create direct rule LAST action.
+ *
+ * @ctx: The context in which the new action will be created.
+ * @flags: Action creation flags. (enum mlx5hws_action_flags)
  *
- * @param[in] ctx
- *     The context in which the new action will be created.
- * @param[in] flags
- *     Action creation flags. (enum mlx5hws_action_flags)
- * @return pointer to mlx5hws_action on success NULL otherwise.
+ * Return: pointer to mlx5hws_action on success NULL otherwise.
  */
 struct mlx5hws_action *
 mlx5hws_action_create_last(struct mlx5hws_context *ctx, u32 flags);
 
-/* Destroy direct rule action.
+/**
+ * mlx5hws_action_destroy - Destroy direct rule action.
  *
- * @param[in] action
- *	The action to destroy.
- * @return zero on success non zero otherwise.
+ * @action: The action to destroy.
+ *
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_action_destroy(struct mlx5hws_action *action);
 
@@ -818,42 +792,40 @@ struct mlx5hws_flow_op_result {
 	void *user_data;
 };
 
-/* Poll queue for rule creation and deletions completions.
+/**
+ * mlx5hws_send_queue_poll - Poll queue for rule creation and deletions completions.
+ *
+ * @ctx: The context to which the queue belong to.
+ * @queue_id: The id of the queue to poll.
+ * @res: Completion array.
+ * @res_nb: Maximum number of results to return.
  *
- * @param[in] ctx
- *	The context to which the queue belong to.
- * @param[in] queue_id
- *	The id of the queue to poll.
- * @param[in, out] res
- *	Completion array.
- * @param[in] res_nb
- *	Maximum number of results to return.
- * @return negative number on failure, the number of completions otherwise.
+ * Return: negative number on failure, the number of completions otherwise.
  */
 int mlx5hws_send_queue_poll(struct mlx5hws_context *ctx,
 			    u16 queue_id,
 			    struct mlx5hws_flow_op_result res[],
 			    u32 res_nb);
 
-/* Perform an action on the queue
+/**
+ * mlx5hws_send_queue_action - Perform an action on the queue
  *
- * @param[in] ctx
- *	The context to which the queue belong to.
- * @param[in] queue_id
- *	The id of the queue to perform the action on.
- * @param[in] actions
- *	Actions to perform on the queue. (enum mlx5hws_send_queue_actions)
- * @return zero on success non zero otherwise.
+ * @ctx: The context to which the queue belong to.
+ * @queue_id: The id of the queue to perform the action on.
+ * @actions: Actions to perform on the queue (enum mlx5hws_send_queue_actions)
+ *
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_send_queue_action(struct mlx5hws_context *ctx,
 			      u16 queue_id,
 			      u32 actions);
 
-/* Dump HWS info
+/**
+ * mlx5hws_debug_dump - Dump HWS info
+ *
+ * @ctx: The context which to dump the info from.
  *
- * @param[in] ctx
- *	The context which to dump the info from.
- * @return zero on success non zero otherwise.
+ * Return: zero on success non zero otherwise.
  */
 int mlx5hws_debug_dump(struct mlx5hws_context *ctx);
 
@@ -865,7 +837,9 @@ struct mlx5hws_match_parameters {
 	u32 *match_buf; /* Device spec format */
 };
 
-/* Create a new BWC direct rule matcher.
+/**
+ * mlx5hws_bwc_matcher_create - Create a new BWC direct rule matcher.
+ *
  * This function does the following:
  *   - creates match template based on flow items
  *   - creates an empty action template
@@ -875,15 +849,12 @@ struct mlx5hws_match_parameters {
  *   - table->ctx must have BWC support
  *   - complex rules are not supported
  *
- * @param[in] table
- *	The table in which the new matcher will be opened
- * @param[in] priority
- *	Priority for this BWC matcher
- * @param[in] match_criteria_enable
- *	Bitmask that defines matching criteria
- * @param[in] mask
- *	Match parameters
- * @return pointer to mlx5hws_bwc_matcher on success or NULL otherwise.
+ * @table: The table in which the new matcher will be opened
+ * @priority: Priority for this BWC matcher
+ * @match_criteria_enable: Bitmask that defines matching criteria
+ * @mask: Match parameters
+ *
+ * Return: pointer to mlx5hws_bwc_matcher on success or NULL otherwise.
  */
 struct mlx5hws_bwc_matcher *
 mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
@@ -891,15 +862,18 @@ mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
 			   u8 match_criteria_enable,
 			   struct mlx5hws_match_parameters *mask);
 
-/* Destroy BWC direct rule matcher.
+/**
+ * mlx5hws_bwc_matcher_destroy - Destroy BWC direct rule matcher.
  *
- * @param[in] bwc_matcher
- *	Matcher to destroy
- * @return zero on success, non zero otherwise
+ * @bwc_matcher: Matcher to destroy
+ *
+ * Return: zero on success, non zero otherwise
  */
 int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher);
 
-/* Create a new BWC rule.
+/**
+ * mlx5hws_bwc_rule_create - Create a new BWC rule.
+ *
  * Unlike the usual rule creation function, this one is blocking: when the
  * function returns, the rule is written to its place (no need to poll).
  * This function does the following:
@@ -916,15 +890,12 @@ int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher);
  *   - matcher->tbl->ctx must have BWC support
  *   - separate BWC ctx queues are used
  *
- * @param[in] bwc_matcher
- *	The BWC matcher in which the new rule will be created.
- * @param[in] params
- *	Match perameters
- * @param[in] flow_source
- *	Flow source for this rule
- * @param[in] rule_actions
- *	Rule action to be executed on match
- * @return valid BWC rule handle on success, NULL otherwise
+ * @bwc_matcher: The BWC matcher in which the new rule will be created.
+ * @params: Match perameters
+ * @flow_source: Flow source for this rule
+ * @rule_actions: Rule action to be executed on match
+ *
+ * Return: valid BWC rule handle on success, NULL otherwise
  */
 struct mlx5hws_bwc_rule *
 mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
@@ -932,21 +903,22 @@ mlx5hws_bwc_rule_create(struct mlx5hws_bwc_matcher *bwc_matcher,
 			u32 flow_source,
 			struct mlx5hws_rule_action rule_actions[]);
 
-/* Destroy BWC direct rule.
+/**
+ * mlx5hws_bwc_rule_destroy - Destroy BWC direct rule.
+ *
+ * @bwc_rule: Rule to destroy.
  *
- * @param[in] bwc_rule
- *	Rule to destroy
- * @return zero on success, non zero otherwise
+ * Return: zero on success, non zero otherwise.
  */
 int mlx5hws_bwc_rule_destroy(struct mlx5hws_bwc_rule *bwc_rule);
 
-/* Update actions on an existing BWC rule.
+/**
+ * mlx5hws_bwc_rule_action_update - Update actions on an existing BWC rule.
+ *
+ * @bwc_rule: Rule to update
+ * @rule_actions: Rule action to update with
  *
- * @param[in] bwc_rule
- *	Rule to update
- * @param[in] rule_actions
- *	Rule action to update with
- * @return zero on successful update, non zero otherwise.
+ * Return: zero on successful update, non zero otherwise.
  */
 int mlx5hws_bwc_rule_action_update(struct mlx5hws_bwc_rule *bwc_rule,
 				   struct mlx5hws_rule_action rule_actions[]);
-- 
cgit v1.3-3-g829e


From 3f4c38df5b0f51823df48851a56fd489f0e97545 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:44 -0700
Subject: net/mlx5: HWS, fixed error flow return values of some functions

Fixed all the '-ret' returns in error flow of functions to 'ret',
as the internal functions are already returning negative error values
(e.g. -EINVAL)

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-3-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c    | 2 +-
 .../net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c   | 8 ++++----
 .../net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c  | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c
index 1964261415aa..33d2b31e4b46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_matcher.c
@@ -967,7 +967,7 @@ int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher,
 
 	ret = hws_matcher_check_and_process_at(matcher, at);
 	if (ret)
-		return -ret;
+		return ret;
 
 	required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term);
 	if (matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes < required_stes) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c
index c79ee70edf03..8a011b958b43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_rule.c
@@ -751,11 +751,11 @@ int mlx5hws_rule_destroy(struct mlx5hws_rule *rule,
 
 	ret = hws_rule_enqueue_precheck(rule, attr);
 	if (unlikely(ret))
-		return -ret;
+		return ret;
 
 	ret = hws_rule_destroy_hws(rule, attr);
 
-	return -ret;
+	return ret;
 }
 
 int mlx5hws_rule_action_update(struct mlx5hws_rule *rule,
@@ -767,7 +767,7 @@ int mlx5hws_rule_action_update(struct mlx5hws_rule *rule,
 
 	ret = hws_rule_enqueue_precheck_update(rule, attr);
 	if (unlikely(ret))
-		return -ret;
+		return ret;
 
 	ret = hws_rule_create_hws(rule,
 				  attr,
@@ -776,5 +776,5 @@ int mlx5hws_rule_action_update(struct mlx5hws_rule *rule,
 				  at_idx,
 				  rule_actions);
 
-	return -ret;
+	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c
index 9dbc3e9da5ea..8c063a8d87d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_table.c
@@ -489,5 +489,5 @@ int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
 	return 0;
 out:
 	mutex_unlock(&ctx->ctrl_lock);
-	return -ret;
+	return ret;
 }
-- 
cgit v1.3-3-g829e


From 48eb74e878e0ef9b173e3a99d9c7c64280c4e749 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:45 -0700
Subject: net/mlx5: fs, move steering common function to fs_cmd.h

As preparation for HW steering support in fs core level, move SW
steering helper function that can be reused by HW steering to fs_cmd.h.
The function mlx5_fs_cmd_is_fw_term_table() checks if a flow table is a
flow steering termination table and so should be handled by FW steering.

Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-4-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h   |  8 ++++++++
 .../ethernet/mellanox/mlx5/core/steering/fs_dr.c   | 24 ++++++++--------------
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index 53e0e5137d3f..7eb7b3ffe3d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -124,4 +124,12 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
 
 int mlx5_fs_cmd_set_l2table_entry_silent(struct mlx5_core_dev *dev, u8 silent_mode);
 int mlx5_fs_cmd_set_tx_flow_table_root(struct mlx5_core_dev *dev, u32 ft_id, bool disconnect);
+
+static inline bool mlx5_fs_cmd_is_fw_term_table(struct mlx5_flow_table *ft)
+{
+	if (ft->flags & MLX5_FLOW_TABLE_TERMINATION)
+		return true;
+
+	return false;
+}
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 50c2554c9ccf..40d06051cdc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -9,14 +9,6 @@
 #include "fs_dr.h"
 #include "dr_types.h"
 
-static bool dr_is_fw_term_table(struct mlx5_flow_table *ft)
-{
-	if (ft->flags & MLX5_FLOW_TABLE_TERMINATION)
-		return true;
-
-	return false;
-}
-
 static int mlx5_cmd_dr_update_root_ft(struct mlx5_flow_root_namespace *ns,
 				      struct mlx5_flow_table *ft,
 				      u32 underlay_qpn,
@@ -70,7 +62,7 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
 	u32 flags;
 	int err;
 
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
 								    ft_attr,
 								    next_ft);
@@ -110,7 +102,7 @@ static int mlx5_cmd_dr_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
 	struct mlx5dr_action *action = ft->fs_dr_table.miss_action;
 	int err;
 
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
 
 	err = mlx5dr_table_destroy(ft->fs_dr_table.dr_table);
@@ -135,7 +127,7 @@ static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns,
 					 struct mlx5_flow_table *ft,
 					 struct mlx5_flow_table *next_ft)
 {
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft);
 
 	return set_miss_action(ns, ft, next_ft);
@@ -154,7 +146,7 @@ static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns,
 					    match_criteria_enable);
 	struct mlx5dr_match_parameters mask;
 
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in,
 								    fg);
 
@@ -179,7 +171,7 @@ static int mlx5_cmd_dr_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
 					  struct mlx5_flow_table *ft,
 					  struct mlx5_flow_group *fg)
 {
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg);
 
 	return mlx5dr_matcher_destroy(fg->fs_dr_matcher.dr_matcher);
@@ -279,7 +271,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 	int err = 0;
 	int i;
 
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte);
 
 	actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions),
@@ -740,7 +732,7 @@ static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
 	int err;
 	int i;
 
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte);
 
 	err = mlx5dr_rule_destroy(rule->dr_rule);
@@ -765,7 +757,7 @@ static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns,
 	struct fs_fte fte_tmp = {};
 	int ret;
 
-	if (dr_is_fw_term_table(ft))
+	if (mlx5_fs_cmd_is_fw_term_table(ft))
 		return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group, modify_mask, fte);
 
 	/* Backup current dr rule details */
-- 
cgit v1.3-3-g829e


From da2f660b3ba1be33310452959ab72d1d7ce39350 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:46 -0700
Subject: net/mlx5: fs, make get_root_namespace API function

As preparation for HW Steering support, where the function
get_root_namespace() is needed to get root FDB, make it an API function
and rename it to mlx5_get_root_namespace().

Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20240911201757.1505453-5-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 16 ++++++++--------
 include/linux/mlx5/fs.h                           |  3 +++
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a47d6419160d..e32725487702 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3590,8 +3590,8 @@ out:
 }
 EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn);
 
-static struct mlx5_flow_root_namespace
-*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type)
+struct mlx5_flow_root_namespace *
+mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type)
 {
 	struct mlx5_flow_namespace *ns;
 
@@ -3614,7 +3614,7 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 	struct mlx5_modify_hdr *modify_hdr;
 	int err;
 
-	root = get_root_namespace(dev, ns_type);
+	root = mlx5_get_root_namespace(dev, ns_type);
 	if (!root)
 		return ERR_PTR(-EOPNOTSUPP);
 
@@ -3639,7 +3639,7 @@ void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
 {
 	struct mlx5_flow_root_namespace *root;
 
-	root = get_root_namespace(dev, modify_hdr->ns_type);
+	root = mlx5_get_root_namespace(dev, modify_hdr->ns_type);
 	if (WARN_ON(!root))
 		return;
 	root->cmds->modify_header_dealloc(root, modify_hdr);
@@ -3655,7 +3655,7 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
 	struct mlx5_flow_root_namespace *root;
 	int err;
 
-	root = get_root_namespace(dev, ns_type);
+	root = mlx5_get_root_namespace(dev, ns_type);
 	if (!root)
 		return ERR_PTR(-EOPNOTSUPP);
 
@@ -3681,7 +3681,7 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
 {
 	struct mlx5_flow_root_namespace *root;
 
-	root = get_root_namespace(dev, pkt_reformat->ns_type);
+	root = mlx5_get_root_namespace(dev, pkt_reformat->ns_type);
 	if (WARN_ON(!root))
 		return;
 	root->cmds->packet_reformat_dealloc(root, pkt_reformat);
@@ -3703,7 +3703,7 @@ mlx5_create_match_definer(struct mlx5_core_dev *dev,
 	struct mlx5_flow_definer *definer;
 	int id;
 
-	root = get_root_namespace(dev, ns_type);
+	root = mlx5_get_root_namespace(dev, ns_type);
 	if (!root)
 		return ERR_PTR(-EOPNOTSUPP);
 
@@ -3727,7 +3727,7 @@ void mlx5_destroy_match_definer(struct mlx5_core_dev *dev,
 {
 	struct mlx5_flow_root_namespace *root;
 
-	root = get_root_namespace(dev, definer->ns_type);
+	root = mlx5_get_root_namespace(dev, definer->ns_type);
 	if (WARN_ON(!root))
 		return;
 
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 3fb428ce7d1c..b744e554f014 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -342,4 +342,7 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
 				  struct mlx5_pkt_reformat *reformat);
 
 u32 mlx5_flow_table_id(struct mlx5_flow_table *ft);
+
+struct mlx5_flow_root_namespace *
+mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type);
 #endif
-- 
cgit v1.3-3-g829e


From 940390d976902e184e1186d0f7dab3ba884dec84 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:47 -0700
Subject: net/mlx5: fs, move hardware fte deletion function reset

Downstream patches will need this as we might not want to reset
it when a pending rule is connected to the FTE.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-6-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index e32725487702..899d91577a54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -683,6 +683,8 @@ static void del_hw_fte(struct fs_node *node)
 				       fte->index, fg->id);
 		node->active = false;
 	}
+	/* Avoid double call to del_hw_fte */
+	fte->node.del_hw_func = NULL;
 }
 
 static void del_sw_fte(struct fs_node *node)
@@ -2265,8 +2267,6 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 		tree_remove_node(&handle->rule[i]->node, true);
 	if (list_empty(&fte->node.children)) {
 		fte->node.del_hw_func(&fte->node);
-		/* Avoid double call to del_hw_fte */
-		fte->node.del_hw_func = NULL;
 		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
 	} else if (fte->dests_size) {
-- 
cgit v1.3-3-g829e


From 8ad0e9608c2c528e708a622952657d4450b04f7f Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:48 -0700
Subject: net/mlx5: fs, remove unused member

Counter is in struct fte, remove it.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-7-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 6201647d6156..5eacf64232f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -241,7 +241,6 @@ struct fs_fte {
 	struct mlx5_flow_context	flow_context;
 	struct mlx5_flow_act		action;
 	enum fs_fte_status		status;
-	struct mlx5_fc			*counter;
 	struct rhash_head		hash;
 	int				modify_mask;
 };
-- 
cgit v1.3-3-g829e


From ef7b79b924e50bef444dfdc04bb24693ad50365d Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:49 -0700
Subject: net/mlx5: fs, separate action and destination into distinct struct

Introduce a dedicated structure to encapsulate flow context, actions,
destination count, and modification mask. This refactoring lays the
groundwork for forthcoming patches that will integrate the NO APPEND
software logic. Future modifications should focus solely on these
specific fields.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-8-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/diag/fs_tracepoint.h        |  8 +--
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c   | 60 ++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  | 56 +++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h  | 14 +++--
 .../ethernet/mellanox/mlx5/core/steering/fs_dr.c   | 64 +++++++++++-----------
 5 files changed, 104 insertions(+), 98 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index ddf1b87f1bc0..9aed29fa4900 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -203,10 +203,10 @@ TRACE_EVENT(mlx5_fs_set_fte,
 			   fs_get_obj(__entry->fg, fte->node.parent);
 			   __entry->group_index = __entry->fg->id;
 			   __entry->index = fte->index;
-			   __entry->action = fte->action.action;
+			   __entry->action = fte->act_dests.action.action;
 			   __entry->mask_enable = __entry->fg->mask.match_criteria_enable;
-			   __entry->flow_tag = fte->flow_context.flow_tag;
-			   __entry->flow_source = fte->flow_context.flow_source;
+			   __entry->flow_tag = fte->act_dests.flow_context.flow_tag;
+			   __entry->flow_source = fte->act_dests.flow_context.flow_source;
 			   memcpy(__entry->mask_outer,
 				  MLX5_ADDR_OF(fte_match_param,
 					       &__entry->fg->mask.match_criteria,
@@ -284,7 +284,7 @@ TRACE_EVENT(mlx5_fs_add_rule,
 	    TP_fast_assign(
 			   __entry->rule = rule;
 			   fs_get_obj(__entry->fte, rule->node.parent);
-			   __entry->index = __entry->fte->dests_size - 1;
+			   __entry->index = __entry->fte->act_dests.dests_size - 1;
 			   __entry->sw_action = rule->sw_action;
 			   memcpy(__entry->destination,
 				  &rule->dest_attr,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 9b8599c200e2..1a14f8dd878f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -463,7 +463,7 @@ static int mlx5_set_extended_dest(struct mlx5_core_dev *dev,
 	int num_encap = 0;
 
 	*extended_dest = false;
-	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+	if (!(fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return 0;
 
 	list_for_each_entry(dst, &fte->node.children, node.list) {
@@ -502,17 +502,17 @@ mlx5_cmd_set_fte_flow_meter(struct fs_fte *fte, void *in_flow_context)
 				   execute_aso[0]);
 	MLX5_SET(execute_aso, execute_aso, valid, 1);
 	MLX5_SET(execute_aso, execute_aso, aso_object_id,
-		 fte->action.exe_aso.object_id);
+		 fte->act_dests.action.exe_aso.object_id);
 
 	exe_aso_ctrl = MLX5_ADDR_OF(execute_aso, execute_aso, exe_aso_ctrl);
 	MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, return_reg_id,
-		 fte->action.exe_aso.return_reg_id);
+		 fte->act_dests.action.exe_aso.return_reg_id);
 	MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, aso_type,
-		 fte->action.exe_aso.type);
+		 fte->act_dests.action.exe_aso.type);
 	MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, init_color,
-		 fte->action.exe_aso.flow_meter.init_color);
+		 fte->act_dests.action.exe_aso.flow_meter.init_color);
 	MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, meter_id,
-		 fte->action.exe_aso.flow_meter.meter_idx);
+		 fte->act_dests.action.exe_aso.flow_meter.meter_idx);
 }
 
 static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
@@ -541,7 +541,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	else
 		dst_cnt_size = MLX5_ST_SZ_BYTES(extended_dest_format);
 
-	inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fte->dests_size * dst_cnt_size;
+	inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fte->act_dests.dests_size * dst_cnt_size;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -553,7 +553,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(set_fte_in, in, table_id,   ft->id);
 	MLX5_SET(set_fte_in, in, flow_index, fte->index);
 	MLX5_SET(set_fte_in, in, ignore_flow_level,
-		 !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL));
+		 !!(fte->act_dests.action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL));
 
 	MLX5_SET(set_fte_in, in, vport_number, ft->vport);
 	MLX5_SET(set_fte_in, in, other_vport,
@@ -563,23 +563,23 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
 
 	MLX5_SET(flow_context, in_flow_context, flow_tag,
-		 fte->flow_context.flow_tag);
+		 fte->act_dests.flow_context.flow_tag);
 	MLX5_SET(flow_context, in_flow_context, flow_source,
-		 fte->flow_context.flow_source);
+		 fte->act_dests.flow_context.flow_source);
 	MLX5_SET(flow_context, in_flow_context, uplink_hairpin_en,
-		 !!(fte->flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN));
+		 !!(fte->act_dests.flow_context.flags & FLOW_CONTEXT_UPLINK_HAIRPIN_EN));
 
 	MLX5_SET(flow_context, in_flow_context, extended_destination,
 		 extended_dest);
 
-	action = fte->action.action;
+	action = fte->act_dests.action.action;
 	if (extended_dest)
 		action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
 
 	MLX5_SET(flow_context, in_flow_context, action, action);
 
-	if (!extended_dest && fte->action.pkt_reformat) {
-		struct mlx5_pkt_reformat *pkt_reformat = fte->action.pkt_reformat;
+	if (!extended_dest && fte->act_dests.action.pkt_reformat) {
+		struct mlx5_pkt_reformat *pkt_reformat = fte->act_dests.action.pkt_reformat;
 
 		if (pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
 			reformat_id = mlx5_fs_dr_action_get_pkt_reformat_id(pkt_reformat);
@@ -591,46 +591,46 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				goto err_out;
 			}
 		} else {
-			reformat_id = fte->action.pkt_reformat->id;
+			reformat_id = fte->act_dests.action.pkt_reformat->id;
 		}
 	}
 
 	MLX5_SET(flow_context, in_flow_context, packet_reformat_id, (u32)reformat_id);
 
-	if (fte->action.modify_hdr) {
-		if (fte->action.modify_hdr->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
+	if (fte->act_dests.action.modify_hdr) {
+		if (fte->act_dests.action.modify_hdr->owner == MLX5_FLOW_RESOURCE_OWNER_SW) {
 			mlx5_core_err(dev, "Can't use SW-owned modify_hdr in FW-owned table\n");
 			err = -EOPNOTSUPP;
 			goto err_out;
 		}
 
 		MLX5_SET(flow_context, in_flow_context, modify_header_id,
-			 fte->action.modify_hdr->id);
+			 fte->act_dests.action.modify_hdr->id);
 	}
 
 	MLX5_SET(flow_context, in_flow_context, encrypt_decrypt_type,
-		 fte->action.crypto.type);
+		 fte->act_dests.action.crypto.type);
 	MLX5_SET(flow_context, in_flow_context, encrypt_decrypt_obj_id,
-		 fte->action.crypto.obj_id);
+		 fte->act_dests.action.crypto.obj_id);
 
 	vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan);
 
-	MLX5_SET(vlan, vlan, ethtype, fte->action.vlan[0].ethtype);
-	MLX5_SET(vlan, vlan, vid, fte->action.vlan[0].vid);
-	MLX5_SET(vlan, vlan, prio, fte->action.vlan[0].prio);
+	MLX5_SET(vlan, vlan, ethtype, fte->act_dests.action.vlan[0].ethtype);
+	MLX5_SET(vlan, vlan, vid, fte->act_dests.action.vlan[0].vid);
+	MLX5_SET(vlan, vlan, prio, fte->act_dests.action.vlan[0].prio);
 
 	vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan_2);
 
-	MLX5_SET(vlan, vlan, ethtype, fte->action.vlan[1].ethtype);
-	MLX5_SET(vlan, vlan, vid, fte->action.vlan[1].vid);
-	MLX5_SET(vlan, vlan, prio, fte->action.vlan[1].prio);
+	MLX5_SET(vlan, vlan, ethtype, fte->act_dests.action.vlan[1].ethtype);
+	MLX5_SET(vlan, vlan, vid, fte->act_dests.action.vlan[1].vid);
+	MLX5_SET(vlan, vlan, prio, fte->act_dests.action.vlan[1].prio);
 
 	in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context,
 				      match_value);
 	memcpy(in_match_value, &fte->val, sizeof(fte->val));
 
 	in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination);
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		int list_size = 0;
 
 		list_for_each_entry(dst, &fte->node.children, node.list) {
@@ -706,7 +706,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			 list_size);
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		int max_list_size = BIT(MLX5_CAP_FLOWTABLE_TYPE(dev,
 					log_max_flow_counter,
 					ft->type));
@@ -731,8 +731,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			 list_size);
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
-		if (fte->action.exe_aso.type == MLX5_EXE_ASO_FLOW_METER) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
+		if (fte->act_dests.action.exe_aso.type == MLX5_EXE_ASO_FLOW_METER) {
 			mlx5_cmd_set_fte_flow_meter(fte, in_flow_context);
 		} else {
 			err = -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 899d91577a54..57df2a6bcb42 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -605,12 +605,12 @@ static void modify_fte(struct fs_fte *fte)
 	dev = get_dev(&fte->node);
 
 	root = find_root(&ft->node);
-	err = root->cmds->update_fte(root, ft, fg, fte->modify_mask, fte);
+	err = root->cmds->update_fte(root, ft, fg, fte->act_dests.modify_mask, fte);
 	if (err)
 		mlx5_core_warn(dev,
 			       "%s can't del rule fg id=%d fte_index=%d\n",
 			       __func__, fg->id, fte->index);
-	fte->modify_mask = 0;
+	fte->act_dests.modify_mask = 0;
 }
 
 static void del_sw_hw_rule(struct fs_node *node)
@@ -628,29 +628,29 @@ static void del_sw_hw_rule(struct fs_node *node)
 	}
 
 	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) {
-		--fte->dests_size;
-		fte->modify_mask |=
+		--fte->act_dests.dests_size;
+		fte->act_dests.modify_mask |=
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
-		fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		fte->act_dests.action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
 		goto out;
 	}
 
 	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_PORT) {
-		--fte->dests_size;
-		fte->modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
-		fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+		--fte->act_dests.dests_size;
+		fte->act_dests.modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+		fte->act_dests.action.action &= ~MLX5_FLOW_CONTEXT_ACTION_ALLOW;
 		goto out;
 	}
 
 	if (is_fwd_dest_type(rule->dest_attr.type)) {
-		--fte->dests_size;
-		--fte->fwd_dests;
+		--fte->act_dests.dests_size;
+		--fte->act_dests.fwd_dests;
 
-		if (!fte->fwd_dests)
-			fte->action.action &=
+		if (!fte->act_dests.fwd_dests)
+			fte->act_dests.action.action &=
 				~MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-		fte->modify_mask |=
+		fte->act_dests.modify_mask |=
 			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
 		goto out;
 	}
@@ -672,7 +672,7 @@ static void del_hw_fte(struct fs_node *node)
 	fs_get_obj(ft, fg->node.parent);
 
 	trace_mlx5_fs_del_fte(fte);
-	WARN_ON(fte->dests_size);
+	WARN_ON(fte->act_dests.dests_size);
 	dev = get_dev(&ft->node);
 	root = find_root(&ft->node);
 	if (node->active) {
@@ -784,8 +784,8 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 
 	memcpy(fte->val, &spec->match_value, sizeof(fte->val));
 	fte->node.type =  FS_TYPE_FLOW_ENTRY;
-	fte->action = *flow_act;
-	fte->flow_context = spec->flow_context;
+	fte->act_dests.action = *flow_act;
+	fte->act_dests.flow_context = spec->flow_context;
 
 	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
 
@@ -1116,7 +1116,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 	int err = 0;
 
 	fs_get_obj(fte, rule->node.parent);
-	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+	if (!(fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return -EINVAL;
 	down_write_ref_node(&fte->node, false);
 	fs_get_obj(fg, fte->node.parent);
@@ -1462,7 +1462,7 @@ static void destroy_flow_handle(struct fs_fte *fte,
 {
 	for (; --i >= 0;) {
 		if (refcount_dec_and_test(&handle->rule[i]->node.refcount)) {
-			fte->dests_size--;
+			fte->act_dests.dests_size--;
 			list_del(&handle->rule[i]->node.list);
 			kfree(handle->rule[i]);
 		}
@@ -1512,10 +1512,10 @@ create_flow_handle(struct fs_fte *fte,
 		else
 			list_add_tail(&rule->node.list, &fte->node.children);
 		if (dest) {
-			fte->dests_size++;
+			fte->act_dests.dests_size++;
 
 			if (is_fwd_dest_type(dest[i].type))
-				fte->fwd_dests++;
+				fte->act_dests.fwd_dests++;
 
 			type = dest[i].type ==
 				MLX5_FLOW_DESTINATION_TYPE_COUNTER;
@@ -1776,17 +1776,17 @@ static int check_conflicting_ftes(struct fs_fte *fte,
 				  const struct mlx5_flow_context *flow_context,
 				  const struct mlx5_flow_act *flow_act)
 {
-	if (check_conflicting_actions(flow_act, &fte->action)) {
+	if (check_conflicting_actions(flow_act, &fte->act_dests.action)) {
 		mlx5_core_warn(get_dev(&fte->node),
 			       "Found two FTEs with conflicting actions\n");
 		return -EEXIST;
 	}
 
 	if ((flow_context->flags & FLOW_CONTEXT_HAS_TAG) &&
-	    fte->flow_context.flow_tag != flow_context->flow_tag) {
+	    fte->act_dests.flow_context.flow_tag != flow_context->flow_tag) {
 		mlx5_core_warn(get_dev(&fte->node),
 			       "FTE flow tag %u already exists with different flow tag %u\n",
-			       fte->flow_context.flow_tag,
+			       fte->act_dests.flow_context.flow_tag,
 			       flow_context->flow_tag);
 		return -EEXIST;
 	}
@@ -1810,12 +1810,12 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
 	if (ret)
 		return ERR_PTR(ret);
 
-	old_action = fte->action.action;
-	fte->action.action |= flow_act->action;
+	old_action = fte->act_dests.action.action;
+	fte->act_dests.action.action |= flow_act->action;
 	handle = add_rule_fte(fte, fg, dest, dest_num,
 			      old_action != flow_act->action);
 	if (IS_ERR(handle)) {
-		fte->action.action = old_action;
+		fte->act_dests.action.action = old_action;
 		return handle;
 	}
 	trace_mlx5_fs_set_fte(fte, false);
@@ -2269,8 +2269,8 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 		fte->node.del_hw_func(&fte->node);
 		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
-	} else if (fte->dests_size) {
-		if (fte->modify_mask)
+	} else if (fte->act_dests.dests_size) {
+		if (fte->act_dests.modify_mask)
 			modify_fte(fte);
 		up_write_ref_node(&fte->node, false);
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 5eacf64232f7..19ba63063d09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -230,19 +230,23 @@ struct mlx5_ft_underlay_qp {
 			   MLX5_BYTE_OFF(fte_match_param,		     \
 					 MLX5_FTE_MATCH_PARAM_RESERVED)))
 
+struct fs_fte_action {
+	int				modify_mask;
+	u32				dests_size;
+	u32				fwd_dests;
+	struct mlx5_flow_context	flow_context;
+	struct mlx5_flow_act		action;
+};
+
 /* Type of children is mlx5_flow_rule */
 struct fs_fte {
 	struct fs_node			node;
 	struct mlx5_fs_dr_rule		fs_dr_rule;
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
-	u32				dests_size;
-	u32				fwd_dests;
+	struct fs_fte_action		act_dests;
 	u32				index;
-	struct mlx5_flow_context	flow_context;
-	struct mlx5_flow_act		action;
 	enum fs_fte_status		status;
 	struct rhash_head		hash;
-	int				modify_mask;
 };
 
 /* Type of children is mlx5_flow_table/namespace */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 40d06051cdc6..15ef118eade0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -298,12 +298,12 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 	match_sz = sizeof(fte->val);
 
 	/* Drop reformat action bit if destination vport set with reformat */
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		list_for_each_entry(dst, &fte->node.children, node.list) {
 			if (!contain_vport_reformat_action(dst))
 				continue;
 
-			fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+			fte->act_dests.action.action &= ~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
 			break;
 		}
 	}
@@ -313,7 +313,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 	 * TX: modify header -> push vlan -> encap
 	 * RX: decap -> pop vlan -> modify header
 	 */
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
 		enum mlx5dr_action_reformat_type decap_type =
 			DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2;
 
@@ -329,26 +329,26 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		actions[num_actions++] = tmp_action;
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
 		bool is_decap;
 
-		if (fte->action.pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) {
+		if (fte->act_dests.action.pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) {
 			err = -EINVAL;
 			mlx5dr_err(domain, "FW-owned reformat can't be used in SW rule\n");
 			goto free_actions;
 		}
 
-		is_decap = fte->action.pkt_reformat->reformat_type ==
+		is_decap = fte->act_dests.action.pkt_reformat->reformat_type ==
 			   MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2;
 
 		if (is_decap)
 			actions[num_actions++] =
-				fte->action.pkt_reformat->action.dr_action;
+				fte->act_dests.action.pkt_reformat->action.dr_action;
 		else
 			delay_encap_set = true;
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
 		tmp_action =
 			mlx5dr_action_create_pop_vlan();
 		if (!tmp_action) {
@@ -359,7 +359,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		actions[num_actions++] = tmp_action;
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) {
 		tmp_action =
 			mlx5dr_action_create_pop_vlan();
 		if (!tmp_action) {
@@ -370,12 +370,12 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		actions[num_actions++] = tmp_action;
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		actions[num_actions++] =
-			fte->action.modify_hdr->action.dr_action;
+			fte->act_dests.action.modify_hdr->action.dr_action;
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
-		tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]);
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
+		tmp_action = create_action_push_vlan(domain, &fte->act_dests.action.vlan[0]);
 		if (!tmp_action) {
 			err = -ENOMEM;
 			goto free_actions;
@@ -384,8 +384,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		actions[num_actions++] = tmp_action;
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
-		tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]);
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+		tmp_action = create_action_push_vlan(domain, &fte->act_dests.action.vlan[1]);
 		if (!tmp_action) {
 			err = -ENOMEM;
 			goto free_actions;
@@ -396,11 +396,11 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 
 	if (delay_encap_set)
 		actions[num_actions++] =
-			fte->action.pkt_reformat->action.dr_action;
+			fte->act_dests.action.pkt_reformat->action.dr_action;
 
 	/* The order of the actions below is not important */
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
 		tmp_action = mlx5dr_action_create_drop();
 		if (!tmp_action) {
 			err = -ENOMEM;
@@ -410,9 +410,9 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		term_actions[num_term_actions++].dest = tmp_action;
 	}
 
-	if (fte->flow_context.flow_tag) {
+	if (fte->act_dests.flow_context.flow_tag) {
 		tmp_action =
-			mlx5dr_action_create_tag(fte->flow_context.flow_tag);
+			mlx5dr_action_create_tag(fte->act_dests.flow_context.flow_tag);
 		if (!tmp_action) {
 			err = -ENOMEM;
 			goto free_actions;
@@ -421,7 +421,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		actions[num_actions++] = tmp_action;
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
 		list_for_each_entry(dst, &fte->node.children, node.list) {
 			enum mlx5_flow_destination_type type = dst->dest_attr.type;
 			u32 id;
@@ -502,7 +502,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		}
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
 		list_for_each_entry(dst, &fte->node.children, node.list) {
 			u32 id;
 
@@ -529,19 +529,21 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		}
 	}
 
-	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
-		if (fte->action.exe_aso.type != MLX5_EXE_ASO_FLOW_METER) {
+	if (fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
+		struct mlx5_flow_act *action = &fte->act_dests.action;
+
+		if (fte->act_dests.action.exe_aso.type != MLX5_EXE_ASO_FLOW_METER) {
 			err = -EOPNOTSUPP;
 			goto free_actions;
 		}
 
 		tmp_action =
 			mlx5dr_action_create_aso(domain,
-						 fte->action.exe_aso.object_id,
-						 fte->action.exe_aso.return_reg_id,
-						 fte->action.exe_aso.type,
-						 fte->action.exe_aso.flow_meter.init_color,
-						 fte->action.exe_aso.flow_meter.meter_idx);
+						 action->exe_aso.object_id,
+						 action->exe_aso.return_reg_id,
+						 action->exe_aso.type,
+						 action->exe_aso.flow_meter.init_color,
+						 action->exe_aso.flow_meter.meter_idx);
 		if (!tmp_action) {
 			err = -ENOMEM;
 			goto free_actions;
@@ -568,8 +570,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 		actions[num_actions++] = term_actions->dest;
 	} else if (num_term_actions > 1) {
 		bool ignore_flow_level =
-			!!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL);
-		u32 flow_source = fte->flow_context.flow_source;
+			!!(fte->act_dests.action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL);
+		u32 flow_source = fte->act_dests.flow_context.flow_source;
 
 		if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX ||
 		    fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
@@ -593,7 +595,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
 				  &params,
 				  num_actions,
 				  actions,
-				  fte->flow_context.flow_source);
+				  fte->act_dests.flow_context.flow_source);
 	if (!rule) {
 		err = -EINVAL;
 		goto free_actions;
-- 
cgit v1.3-3-g829e


From 1217e6989c99c1c4b76866ea395dda757c79deb4 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:50 -0700
Subject: net/mlx5: fs, add support for no append at software level

Native capability for some steering engines lacks support for adding an
additional match with the same value to the same flow group. To accommodate
the NO APPEND flag in these scenarios, we include the new rule in the
existing flow table entry (fte) without immediate hardware commitment. When
a request is made to delete the corresponding hardware rule, we then commit
the pending rule to hardware.

Only one pending rule is supported because NO_APPEND is primarily used
during replacement operations. In this scenario, a rule is initially added.
When it needs replacement, the new rule is added with NO_APPEND set. Only
after the insertion of the new rule is the original rule deleted.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-9-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  | 245 +++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h  |   7 +
 .../ethernet/mellanox/mlx5/core/steering/fs_dr.c   |   4 +-
 4 files changed, 242 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 1a14f8dd878f..676005854dad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -1071,7 +1071,7 @@ static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns,
 static u32 mlx5_cmd_get_capabilities(struct mlx5_flow_root_namespace *ns,
 				     enum fs_flow_table_type ft_type)
 {
-	return 0;
+	return MLX5_FLOW_STEERING_CAP_DUPLICATE_MATCH;
 }
 
 static const struct mlx5_flow_cmds mlx5_flow_cmds = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 57df2a6bcb42..8505d5e241e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -613,6 +613,31 @@ static void modify_fte(struct fs_fte *fte)
 	fte->act_dests.modify_mask = 0;
 }
 
+static void del_sw_hw_dup_rule(struct fs_node *node)
+{
+	struct mlx5_flow_rule *rule;
+	struct fs_fte *fte;
+
+	fs_get_obj(rule, node);
+	fs_get_obj(fte, rule->node.parent);
+	trace_mlx5_fs_del_rule(rule);
+
+	if (is_fwd_next_action(rule->sw_action)) {
+		mutex_lock(&rule->dest_attr.ft->lock);
+		list_del(&rule->next_ft);
+		mutex_unlock(&rule->dest_attr.ft->lock);
+	}
+
+	/* If a pending rule is being deleted it means
+	 * this is a NO APPEND rule, so there are no partial deletions,
+	 * all the rules of the mlx5_flow_handle are going to be deleted
+	 * and the rules aren't shared with any other mlx5_flow_handle instance
+	 * so no need to do any bookkeeping like in del_sw_hw_rule().
+	 */
+
+	kfree(rule);
+}
+
 static void del_sw_hw_rule(struct fs_node *node)
 {
 	struct mlx5_flow_rule *rule;
@@ -658,12 +683,33 @@ out:
 	kfree(rule);
 }
 
+static void switch_to_pending_act_dests(struct fs_fte *fte)
+{
+	struct fs_node *iter;
+
+	memcpy(&fte->act_dests, &fte->dup->act_dests, sizeof(fte->act_dests));
+
+	list_bulk_move_tail(&fte->node.children,
+			    fte->dup->children.next,
+			    fte->dup->children.prev);
+
+	list_for_each_entry(iter, &fte->node.children, list)
+		iter->del_sw_func = del_sw_hw_rule;
+
+	/* Make sure the fte isn't deleted
+	 * as mlx5_del_flow_rules() decreases the refcount
+	 * of the fte to trigger deletion.
+	 */
+	tree_get_node(&fte->node);
+}
+
 static void del_hw_fte(struct fs_node *node)
 {
 	struct mlx5_flow_root_namespace *root;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *fg;
 	struct mlx5_core_dev *dev;
+	bool pending_used = false;
 	struct fs_fte *fte;
 	int err;
 
@@ -675,16 +721,33 @@ static void del_hw_fte(struct fs_node *node)
 	WARN_ON(fte->act_dests.dests_size);
 	dev = get_dev(&ft->node);
 	root = find_root(&ft->node);
+
+	if (fte->dup && !list_empty(&fte->dup->children)) {
+		switch_to_pending_act_dests(fte);
+		pending_used = true;
+	} else {
+		/* Avoid double call to del_hw_fte */
+		node->del_hw_func = NULL;
+	}
+
 	if (node->active) {
-		err = root->cmds->delete_fte(root, ft, fte);
-		if (err)
-			mlx5_core_warn(dev,
-				       "flow steering can't delete fte in index %d of flow group id %d\n",
-				       fte->index, fg->id);
-		node->active = false;
+		if (pending_used) {
+			err = root->cmds->update_fte(root, ft, fg,
+						     fte->act_dests.modify_mask, fte);
+			if (err)
+				mlx5_core_warn(dev,
+					       "flow steering can't update to pending rule in index %d of flow group id %d\n",
+					       fte->index, fg->id);
+			fte->act_dests.modify_mask = 0;
+		} else {
+			err = root->cmds->delete_fte(root, ft, fte);
+			if (err)
+				mlx5_core_warn(dev,
+					       "flow steering can't delete fte in index %d of flow group id %d\n",
+					       fte->index, fg->id);
+			node->active = false;
+		}
 	}
-	/* Avoid double call to del_hw_fte */
-	fte->node.del_hw_func = NULL;
 }
 
 static void del_sw_fte(struct fs_node *node)
@@ -702,6 +765,7 @@ static void del_sw_fte(struct fs_node *node)
 				     rhash_fte);
 	WARN_ON(err);
 	ida_free(&fg->fte_allocator, fte->index - fg->start_index);
+	kvfree(fte->dup);
 	kmem_cache_free(steering->ftes_cache, fte);
 }
 
@@ -1105,18 +1169,45 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio
 	return err;
 }
 
+static bool rule_is_pending(struct fs_fte *fte, struct mlx5_flow_rule *rule)
+{
+	struct mlx5_flow_rule *tmp_rule;
+	struct fs_node *iter;
+
+	if (!fte->dup || list_empty(&fte->dup->children))
+		return false;
+
+	list_for_each_entry(iter, &fte->dup->children, list) {
+		tmp_rule = container_of(iter, struct mlx5_flow_rule, node);
+
+		if (tmp_rule == rule)
+			return true;
+	}
+
+	return false;
+}
+
 static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 					 struct mlx5_flow_destination *dest)
 {
 	struct mlx5_flow_root_namespace *root;
+	struct fs_fte_action *act_dests;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *fg;
+	bool pending = false;
 	struct fs_fte *fte;
 	int modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
 	int err = 0;
 
 	fs_get_obj(fte, rule->node.parent);
-	if (!(fte->act_dests.action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+
+	pending = rule_is_pending(fte, rule);
+	if (pending)
+		act_dests = &fte->dup->act_dests;
+	else
+		act_dests = &fte->act_dests;
+
+	if (!(act_dests->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return -EINVAL;
 	down_write_ref_node(&fte->node, false);
 	fs_get_obj(fg, fte->node.parent);
@@ -1124,8 +1215,9 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 
 	memcpy(&rule->dest_attr, dest, sizeof(*dest));
 	root = find_root(&ft->node);
-	err = root->cmds->update_fte(root, ft, fg,
-				     modify_mask, fte);
+	if (!pending)
+		err = root->cmds->update_fte(root, ft, fg,
+					     modify_mask, fte);
 	up_write_ref_node(&fte->node, false);
 
 	return err;
@@ -1455,6 +1547,16 @@ static struct mlx5_flow_handle *alloc_handle(int num_rules)
 	return handle;
 }
 
+static void destroy_flow_handle_dup(struct mlx5_flow_handle *handle,
+				    int i)
+{
+	for (; --i >= 0;) {
+		list_del(&handle->rule[i]->node.list);
+		kfree(handle->rule[i]);
+	}
+	kfree(handle);
+}
+
 static void destroy_flow_handle(struct fs_fte *fte,
 				struct mlx5_flow_handle *handle,
 				struct mlx5_flow_destination *dest,
@@ -1470,6 +1572,61 @@ static void destroy_flow_handle(struct fs_fte *fte,
 	kfree(handle);
 }
 
+static struct mlx5_flow_handle *
+create_flow_handle_dup(struct list_head *children,
+		       struct mlx5_flow_destination *dest,
+		       int dest_num,
+		       struct fs_fte_action *act_dests)
+{
+	static int dst = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
+	static int count = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+	struct mlx5_flow_rule *rule = NULL;
+	struct mlx5_flow_handle *handle;
+	int i = 0;
+	int type;
+
+	handle = alloc_handle((dest_num) ? dest_num : 1);
+	if (!handle)
+		return NULL;
+
+	do {
+		rule = alloc_rule(dest + i);
+		if (!rule)
+			goto free_rules;
+
+		/* Add dest to dests list- we need flow tables to be in the
+		 * end of the list for forward to next prio rules.
+		 */
+		tree_init_node(&rule->node, NULL, del_sw_hw_dup_rule);
+		if (dest &&
+		    dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE)
+			list_add(&rule->node.list, children);
+		else
+			list_add_tail(&rule->node.list, children);
+
+		if (dest) {
+			act_dests->dests_size++;
+
+			if (is_fwd_dest_type(dest[i].type))
+				act_dests->fwd_dests++;
+
+			type = dest[i].type ==
+				MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+			act_dests->modify_mask |= type ? count : dst;
+		}
+		handle->rule[i] = rule;
+	} while (++i < dest_num);
+
+	return handle;
+
+free_rules:
+	destroy_flow_handle_dup(handle, i);
+	act_dests->dests_size = 0;
+	act_dests->fwd_dests = 0;
+
+	return NULL;
+}
+
 static struct mlx5_flow_handle *
 create_flow_handle(struct fs_fte *fte,
 		   struct mlx5_flow_destination *dest,
@@ -1963,6 +2120,62 @@ out:
 	return fte_tmp;
 }
 
+/* Native capability lacks support for adding an additional match with the same value
+ * to the same flow group. To accommodate the NO APPEND flag in these scenarios,
+ * we include the new rule in the existing flow table entry (fte) without immediate
+ * hardware commitment. When a request is made to delete the corresponding hardware rule,
+ * we then commit the pending rule to hardware.
+ */
+static struct mlx5_flow_handle *
+add_rule_dup_match_fte(struct fs_fte *fte,
+		       const struct mlx5_flow_spec *spec,
+		       struct mlx5_flow_act *flow_act,
+		       struct mlx5_flow_destination *dest,
+		       int dest_num)
+{
+	struct mlx5_flow_handle *handle;
+	struct fs_fte_dup *dup;
+	int i = 0;
+
+	if (!fte->dup) {
+		dup = kvzalloc(sizeof(*dup), GFP_KERNEL);
+		if (!dup)
+			return ERR_PTR(-ENOMEM);
+		/* dup will be freed when the fte is freed
+		 * this way we don't allocate / free dup on every rule deletion
+		 * or creation
+		 */
+		INIT_LIST_HEAD(&dup->children);
+		fte->dup = dup;
+	}
+
+	if (!list_empty(&fte->dup->children)) {
+		mlx5_core_warn(get_dev(&fte->node),
+			       "Can have only a single duplicate rule\n");
+
+		return ERR_PTR(-EEXIST);
+	}
+
+	fte->dup->act_dests.action = *flow_act;
+	fte->dup->act_dests.flow_context = spec->flow_context;
+	fte->dup->act_dests.dests_size = 0;
+	fte->dup->act_dests.fwd_dests = 0;
+	fte->dup->act_dests.modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION);
+
+	handle = create_flow_handle_dup(&fte->dup->children,
+					dest, dest_num,
+					&fte->dup->act_dests);
+	if (!handle)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < handle->num_rules; i++) {
+		tree_add_node(&handle->rule[i]->node, &fte->node);
+		trace_mlx5_fs_add_rule(handle->rule[i]);
+	}
+
+	return handle;
+}
+
 static struct mlx5_flow_handle *
 try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		       struct list_head *match_head,
@@ -1973,6 +2186,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		       int ft_version)
 {
 	struct mlx5_flow_steering *steering = get_steering(&ft->node);
+	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
 	struct mlx5_flow_group *g;
 	struct mlx5_flow_handle *rule;
 	struct match_list *iter;
@@ -1986,7 +2200,9 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		return  ERR_PTR(-ENOMEM);
 
 search_again_locked:
-	if (flow_act->flags & FLOW_ACT_NO_APPEND)
+	if (flow_act->flags & FLOW_ACT_NO_APPEND &&
+	    (root->cmds->get_capabilities(root, root->table_type) &
+	     MLX5_FLOW_STEERING_CAP_DUPLICATE_MATCH))
 		goto skip_search;
 	version = matched_fgs_get_version(match_head);
 	/* Try to find an fte with identical match value and attempt update its
@@ -1999,7 +2215,10 @@ search_again_locked:
 		fte_tmp = lookup_fte_locked(g, spec->match_value, take_write);
 		if (!fte_tmp)
 			continue;
-		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp);
+		if (flow_act->flags & FLOW_ACT_NO_APPEND)
+			rule = add_rule_dup_match_fte(fte_tmp, spec, flow_act, dest, dest_num);
+		else
+			rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp);
 		/* No error check needed here, because insert_fte() is not called */
 		up_write_ref_node(&fte_tmp->node, false);
 		tree_put_node(&fte_tmp->node, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 19ba63063d09..964937f17cf5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -133,6 +133,7 @@ enum mlx5_flow_steering_capabilty {
 	MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX = 1UL << 0,
 	MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX = 1UL << 1,
 	MLX5_FLOW_STEERING_CAP_MATCH_RANGES = 1UL << 2,
+	MLX5_FLOW_STEERING_CAP_DUPLICATE_MATCH = 1UL << 3,
 };
 
 struct mlx5_flow_steering {
@@ -238,12 +239,18 @@ struct fs_fte_action {
 	struct mlx5_flow_act		action;
 };
 
+struct fs_fte_dup {
+	struct list_head children;
+	struct fs_fte_action act_dests;
+};
+
 /* Type of children is mlx5_flow_rule */
 struct fs_fte {
 	struct fs_node			node;
 	struct mlx5_fs_dr_rule		fs_dr_rule;
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
 	struct fs_fte_action		act_dests;
+	struct fs_fte_dup		*dup;
 	u32				index;
 	enum fs_fte_status		status;
 	struct rhash_head		hash;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 15ef118eade0..833cb68c744f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -813,11 +813,11 @@ static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns)
 static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns,
 					enum fs_flow_table_type ft_type)
 {
-	u32 steering_caps = 0;
+	u32 steering_caps = MLX5_FLOW_STEERING_CAP_DUPLICATE_MATCH;
 
 	if (ft_type != FS_FT_FDB ||
 	    MLX5_CAP_GEN(ns->dev, steering_format_version) == MLX5_STEERING_FORMAT_CONNECTX_5)
-		return 0;
+		return steering_caps;
 
 	steering_caps |= MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX;
 	steering_caps |= MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX;
-- 
cgit v1.3-3-g829e


From 9947204cdad97d22d171039019a4aad4d6899cdd Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:51 -0700
Subject: net/mlx5: Add device cap for supporting hot reset in sync reset flow

New devices with new FW can support sync reset for firmware activate
using hot reset. Add capability for supporting it and add MFRL field to
query from FW which type of PCI reset method to use while handling sync
reset events.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-10-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 2045575b70d4..620a5c305123 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1856,7 +1856,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_328[0x2];
 	u8	   relaxed_ordering_read[0x1];
 	u8         log_max_pd[0x5];
-	u8         reserved_at_330[0x6];
+	u8         reserved_at_330[0x5];
+	u8         pcie_reset_using_hotreset_method[0x1];
 	u8         pci_sync_for_fw_update_with_driver_unload[0x1];
 	u8         vnic_env_cnt_steering_fail[0x1];
 	u8         vport_counter_local_loopback[0x1];
@@ -11188,6 +11189,11 @@ struct mlx5_ifc_mcda_reg_bits {
 	u8         data[][0x20];
 };
 
+enum {
+	MLX5_MFRL_REG_PCI_RESET_METHOD_LINK_TOGGLE = 0,
+	MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET = 1,
+};
+
 enum {
 	MLX5_MFRL_REG_RESET_STATE_IDLE = 0,
 	MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1,
@@ -11215,7 +11221,8 @@ struct mlx5_ifc_mfrl_reg_bits {
 	u8         pci_sync_for_fw_update_start[0x1];
 	u8         pci_sync_for_fw_update_resp[0x2];
 	u8         rst_type_sel[0x3];
-	u8         reserved_at_28[0x4];
+	u8         pci_reset_req_method[0x3];
+	u8         reserved_at_2b[0x1];
 	u8         reset_state[0x4];
 	u8         reset_type[0x8];
 	u8         reset_level[0x8];
-- 
cgit v1.3-3-g829e


From 57502f62678ced0149d415324931bde37b42885a Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:52 -0700
Subject: net/mlx5: Add support for sync reset using hot reset

On device that supports sync reset for firmware activate using hot
reset, the driver queries the required reset method while handling the
sync reset request. If the required reset method is hot reset, the
driver will use pci_reset_bus() to reset the PCI link instead of the
link toggle.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-11-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 82 +++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  3 +
 2 files changed, 69 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index b43ca0b762c3..bda74cb9c975 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -26,6 +26,7 @@ struct mlx5_fw_reset {
 	struct work_struct reset_now_work;
 	struct work_struct reset_abort_work;
 	unsigned long reset_flags;
+	u8 reset_method;
 	struct timer_list timer;
 	struct completion done;
 	int ret;
@@ -95,7 +96,7 @@ static int mlx5_reg_mfrl_set(struct mlx5_core_dev *dev, u8 reset_level,
 }
 
 static int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level,
-			       u8 *reset_type, u8 *reset_state)
+			       u8 *reset_type, u8 *reset_state, u8 *reset_method)
 {
 	u32 out[MLX5_ST_SZ_DW(mfrl_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mfrl_reg)] = {};
@@ -111,13 +112,26 @@ static int mlx5_reg_mfrl_query(struct mlx5_core_dev *dev, u8 *reset_level,
 		*reset_type = MLX5_GET(mfrl_reg, out, reset_type);
 	if (reset_state)
 		*reset_state = MLX5_GET(mfrl_reg, out, reset_state);
+	if (reset_method)
+		*reset_method = MLX5_GET(mfrl_reg, out, pci_reset_req_method);
 
 	return 0;
 }
 
 int mlx5_fw_reset_query(struct mlx5_core_dev *dev, u8 *reset_level, u8 *reset_type)
 {
-	return mlx5_reg_mfrl_query(dev, reset_level, reset_type, NULL);
+	return mlx5_reg_mfrl_query(dev, reset_level, reset_type, NULL, NULL);
+}
+
+static int mlx5_fw_reset_get_reset_method(struct mlx5_core_dev *dev,
+					  u8 *reset_method)
+{
+	if (!MLX5_CAP_GEN(dev, pcie_reset_using_hotreset_method)) {
+		*reset_method = MLX5_MFRL_REG_PCI_RESET_METHOD_LINK_TOGGLE;
+		return 0;
+	}
+
+	return mlx5_reg_mfrl_query(dev, NULL, NULL, NULL, reset_method);
 }
 
 static int mlx5_fw_reset_get_reset_state_err(struct mlx5_core_dev *dev,
@@ -125,7 +139,7 @@ static int mlx5_fw_reset_get_reset_state_err(struct mlx5_core_dev *dev,
 {
 	u8 reset_state;
 
-	if (mlx5_reg_mfrl_query(dev, NULL, NULL, &reset_state))
+	if (mlx5_reg_mfrl_query(dev, NULL, NULL, &reset_state, NULL))
 		goto out;
 
 	if (!reset_state)
@@ -427,7 +441,11 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 	struct mlx5_core_dev *dev = fw_reset->dev;
 	int err;
 
-	if (test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) ||
+	err = mlx5_fw_reset_get_reset_method(dev, &fw_reset->reset_method);
+	if (err)
+		mlx5_core_warn(dev, "Failed reading MFRL, err %d\n", err);
+
+	if (err || test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) ||
 	    !mlx5_is_reset_now_capable(dev)) {
 		err = mlx5_fw_reset_set_reset_sync_nack(dev);
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s",
@@ -444,21 +462,15 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Ack. Device reset is expected.\n");
 }
 
-static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev)
+static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev, u16 dev_id)
 {
 	struct pci_bus *bridge_bus = dev->pdev->bus;
 	struct pci_dev *bridge = bridge_bus->self;
 	unsigned long timeout;
 	struct pci_dev *sdev;
-	u16 reg16, dev_id;
 	int cap, err;
+	u16 reg16;
 
-	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
-	if (err)
-		return pcibios_err_to_errno(err);
-	err = mlx5_check_dev_ids(dev, dev_id);
-	if (err)
-		return err;
 	cap = pci_find_capability(bridge, PCI_CAP_ID_EXP);
 	if (!cap)
 		return -EOPNOTSUPP;
@@ -528,6 +540,44 @@ restore:
 	return err;
 }
 
+static int mlx5_pci_reset_bus(struct mlx5_core_dev *dev)
+{
+	if (!MLX5_CAP_GEN(dev, pcie_reset_using_hotreset_method))
+		return -EOPNOTSUPP;
+
+	return pci_reset_bus(dev->pdev);
+}
+
+static int mlx5_sync_pci_reset(struct mlx5_core_dev *dev, u8 reset_method)
+{
+	u16 dev_id;
+	int err;
+
+	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
+	if (err)
+		return pcibios_err_to_errno(err);
+	err = mlx5_check_dev_ids(dev, dev_id);
+	if (err)
+		return err;
+
+	switch (reset_method) {
+	case MLX5_MFRL_REG_PCI_RESET_METHOD_LINK_TOGGLE:
+		err = mlx5_pci_link_toggle(dev, dev_id);
+		if (err)
+			mlx5_core_warn(dev, "mlx5_pci_link_toggle failed\n");
+		break;
+	case MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET:
+		err = mlx5_pci_reset_bus(dev);
+		if (err)
+			mlx5_core_warn(dev, "mlx5_pci_reset_bus failed\n");
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
 static void mlx5_sync_reset_now_event(struct work_struct *work)
 {
 	struct mlx5_fw_reset *fw_reset = container_of(work, struct mlx5_fw_reset,
@@ -546,9 +596,9 @@ static void mlx5_sync_reset_now_event(struct work_struct *work)
 		goto done;
 	}
 
-	err = mlx5_pci_link_toggle(dev);
+	err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
 	if (err) {
-		mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, no reset done, err %d\n", err);
+		mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, no reset done, err %d\n", err);
 		set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags);
 	}
 
@@ -610,9 +660,9 @@ static void mlx5_sync_reset_unload_event(struct work_struct *work)
 
 	mlx5_core_warn(dev, "Sync Reset, got reset action. rst_state = %u\n", rst_state);
 	if (rst_state == MLX5_FW_RST_STATE_TOGGLE_REQ) {
-		err = mlx5_pci_link_toggle(dev);
+		err = mlx5_sync_pci_reset(dev, fw_reset->reset_method);
 		if (err) {
-			mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, err %d\n", err);
+			mlx5_core_warn(dev, "mlx5_sync_pci_reset failed, err %d\n", err);
 			fw_reset->ret = err;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c6e951b8ebdb..8b0abd61eca6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -619,6 +619,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN_MAX(dev, pci_sync_for_fw_update_with_driver_unload))
 		MLX5_SET(cmd_hca_cap, set_hca_cap,
 			 pci_sync_for_fw_update_with_driver_unload, 1);
+	if (MLX5_CAP_GEN_MAX(dev, pcie_reset_using_hotreset_method))
+		MLX5_SET(cmd_hca_cap, set_hca_cap,
+			 pcie_reset_using_hotreset_method, 1);
 
 	if (MLX5_CAP_GEN_MAX(dev, num_vhca_ports))
 		MLX5_SET(cmd_hca_cap,
-- 
cgit v1.3-3-g829e


From 48bb52b0bc6693afb17a6024bab925b25fec44a1 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:53 -0700
Subject: net/mlx5: Skip HotPlug check on sync reset using hot reset

Sync reset request is nacked by the driver when PCIe bridge connected to
mlx5 device has HotPlug interrupt enabled. However, when using reset
method of hot reset this check can be skipped as Hotplug is supported on
this reset method.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-12-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index bda74cb9c975..4f55e55ecb55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -412,7 +412,8 @@ static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 	return 0;
 }
 
-static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev)
+static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
+				      u8 reset_method)
 {
 	u16 dev_id;
 	int err;
@@ -423,9 +424,11 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev)
 	}
 
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
-	err = mlx5_check_hotplug_interrupt(dev);
-	if (err)
-		return false;
+	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
+		err = mlx5_check_hotplug_interrupt(dev);
+		if (err)
+			return false;
+	}
 #endif
 
 	err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id);
@@ -446,7 +449,7 @@ static void mlx5_sync_reset_request_event(struct work_struct *work)
 		mlx5_core_warn(dev, "Failed reading MFRL, err %d\n", err);
 
 	if (err || test_bit(MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, &fw_reset->reset_flags) ||
-	    !mlx5_is_reset_now_capable(dev)) {
+	    !mlx5_is_reset_now_capable(dev, fw_reset->reset_method)) {
 		err = mlx5_fw_reset_set_reset_sync_nack(dev);
 		mlx5_core_warn(dev, "PCI Sync FW Update Reset Nack %s",
 			       err ? "Failed" : "Sent");
-- 
cgit v1.3-3-g829e


From 9c754d0970736539de9c4773fa813ad8b9bb04e2 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:54 -0700
Subject: net/mlx5: Allow users to configure affinity for SFs

SFs didn't allow to configure IRQ affinity for its vectors. Allow users
to configure the affinity of the SFs irqs.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20240911201757.1505453-13-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index f15ecaef1331..2505f90c0b39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -896,7 +896,7 @@ static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 	if (!mlx5_irq_pool_is_sf_pool(pool))
 		return comp_irq_request_pci(dev, vecidx);
 
-	af_desc.is_managed = 1;
+	af_desc.is_managed = false;
 	cpumask_copy(&af_desc.mask, cpu_online_mask);
 	cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus);
 	irq = mlx5_irq_affinity_request(dev, pool, &af_desc);
-- 
cgit v1.3-3-g829e


From 5bd877093fd0b2e9e5f0c03b466669f761b5849c Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:55 -0700
Subject: net/mlx5: Add NOT_READY command return status

Add a new command status MLX5_CMD_STAT_NOT_READY to handle cases
where the firmware is not ready.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20240911201757.1505453-14-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 7 ++++++-
 include/linux/mlx5/device.h                   | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 20768ef2e9d2..9af8ddb4a78f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -754,6 +754,8 @@ static const char *cmd_status_str(u8 status)
 		return "bad resource";
 	case MLX5_CMD_STAT_RES_BUSY:
 		return "resource busy";
+	case MLX5_CMD_STAT_NOT_READY:
+		return "FW not ready";
 	case MLX5_CMD_STAT_LIM_ERR:
 		return "limits exceeded";
 	case MLX5_CMD_STAT_BAD_RES_STATE_ERR:
@@ -787,6 +789,7 @@ static int cmd_status_to_err(u8 status)
 	case MLX5_CMD_STAT_BAD_SYS_STATE_ERR:		return -EIO;
 	case MLX5_CMD_STAT_BAD_RES_ERR:			return -EINVAL;
 	case MLX5_CMD_STAT_RES_BUSY:			return -EBUSY;
+	case MLX5_CMD_STAT_NOT_READY:			return -EAGAIN;
 	case MLX5_CMD_STAT_LIM_ERR:			return -ENOMEM;
 	case MLX5_CMD_STAT_BAD_RES_STATE_ERR:		return -EINVAL;
 	case MLX5_CMD_STAT_IX_ERR:			return -EINVAL;
@@ -815,14 +818,16 @@ EXPORT_SYMBOL(mlx5_cmd_out_err);
 static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 {
 	u16 opcode, op_mod;
+	u8 status;
 	u16 uid;
 
 	opcode = in_to_opcode(in);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
 	uid    = MLX5_GET(mbox_in, in, uid);
+	status = MLX5_GET(mbox_out, out, status);
 
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY &&
-	    opcode != MLX5_CMD_OP_CREATE_UCTX)
+	    opcode != MLX5_CMD_OP_CREATE_UCTX && status != MLX5_CMD_STAT_NOT_READY)
 		mlx5_cmd_out_err(dev, opcode, op_mod, out);
 }
 
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index a94bc9e3af96..d0f7d1f36c5e 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1449,6 +1449,7 @@ enum {
 	MLX5_CMD_STAT_BAD_SYS_STATE_ERR		= 0x4,
 	MLX5_CMD_STAT_BAD_RES_ERR		= 0x5,
 	MLX5_CMD_STAT_RES_BUSY			= 0x6,
+	MLX5_CMD_STAT_NOT_READY			= 0x7,
 	MLX5_CMD_STAT_LIM_ERR			= 0x8,
 	MLX5_CMD_STAT_BAD_RES_STATE_ERR		= 0x9,
 	MLX5_CMD_STAT_IX_ERR			= 0xa,
-- 
cgit v1.3-3-g829e


From 909fc8d107b77c6dee43d063b50c15ddbec0fea1 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:56 -0700
Subject: net/mlx5e: SHAMPO, Add no-split ethtool counters for header/data
 split

When SHAMPO can't identify the protocol/header of a packet, it will
yield a packet that is not split - all the packet is in the data part.
Count this value in packets and bytes.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-15-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../device_drivers/ethernet/mellanox/mlx5/counters.rst   | 16 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c          |  3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c       |  6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h       |  4 ++++
 4 files changed, 29 insertions(+)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index 3bd72577af9a..99d95be4d159 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -218,6 +218,22 @@ the software port.
        [#accel]_.
      - Informative
 
+   * - `rx[i]_hds_nosplit_packets`
+     - Number of packets that were not split in header/data split mode. A
+       packet will not get split when the hardware does not support its
+       protocol splitting. An example such a protocol is ICMPv4/v6. Currently
+       TCP and UDP with IPv4/IPv6 are supported for header/data split
+       [#accel]_.
+     - Informative
+
+   * - `rx[i]_hds_nosplit_bytes`
+     - Number of bytes for packets that were not split in header/data split
+       mode. A packet will not get split when the hardware does not support its
+       protocol splitting. An example such a protocol is ICMPv4/v6. Currently
+       TCP and UDP with IPv4/IPv6 are supported for header/data split
+       [#accel]_.
+     - Informative
+
    * - `rx[i]_lro_packets`
      - The number of LRO packets received on ring i [#accel]_.
      - Acceleration
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index de9d01036c28..8e24ba96c779 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2346,6 +2346,9 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 			stats->hds_nodata_packets++;
 			stats->hds_nodata_bytes += head_size;
 		}
+	} else {
+		stats->hds_nosplit_packets++;
+		stats->hds_nosplit_bytes += data_bcnt;
 	}
 
 	mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index e7a3290a708a..611ec4b6f370 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -144,6 +144,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_gro_large_hds) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_hds_nodata_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_hds_nodata_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_hds_nosplit_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_hds_nosplit_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
@@ -347,6 +349,8 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_gro_large_hds           += rq_stats->gro_large_hds;
 	s->rx_hds_nodata_packets      += rq_stats->hds_nodata_packets;
 	s->rx_hds_nodata_bytes        += rq_stats->hds_nodata_bytes;
+	s->rx_hds_nosplit_packets     += rq_stats->hds_nosplit_packets;
+	s->rx_hds_nosplit_bytes       += rq_stats->hds_nosplit_bytes;
 	s->rx_ecn_mark                += rq_stats->ecn_mark;
 	s->rx_removed_vlan_packets    += rq_stats->removed_vlan_packets;
 	s->rx_csum_none               += rq_stats->csum_none;
@@ -2062,6 +2066,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, gro_large_hds) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, hds_nodata_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, hds_nodata_bytes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, hds_nosplit_packets) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, hds_nosplit_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 4c5858c1dd82..5961c569cfe0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -156,6 +156,8 @@ struct mlx5e_sw_stats {
 	u64 rx_gro_large_hds;
 	u64 rx_hds_nodata_packets;
 	u64 rx_hds_nodata_bytes;
+	u64 rx_hds_nosplit_packets;
+	u64 rx_hds_nosplit_bytes;
 	u64 rx_mcast_packets;
 	u64 rx_ecn_mark;
 	u64 rx_removed_vlan_packets;
@@ -356,6 +358,8 @@ struct mlx5e_rq_stats {
 	u64 gro_large_hds;
 	u64 hds_nodata_packets;
 	u64 hds_nodata_bytes;
+	u64 hds_nosplit_packets;
+	u64 hds_nosplit_bytes;
 	u64 mcast_packets;
 	u64 ecn_mark;
 	u64 removed_vlan_packets;
-- 
cgit v1.3-3-g829e


From cc1812918930036af55ba4b4c29b8c8a96ee2086 Mon Sep 17 00:00:00 2001
From: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Date: Wed, 11 Sep 2024 13:17:57 -0700
Subject: net/mlx5e: Match cleanup order in mlx5e_free_rq in reverse of
 mlx5e_alloc_rq

mlx5e_free_rq previously cleaned resources in an order that was not the
reverse of the resource allocation order in mlx5e_alloc_rq.

Signed-off-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240911201757.1505453-16-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 25 ++++++++++++-----------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 47e7a80d221b..a5659c0c4236 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1016,30 +1016,31 @@ err_rq_xdp_prog:
 
 static void mlx5e_free_rq(struct mlx5e_rq *rq)
 {
-	struct bpf_prog *old_prog;
-
-	if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) {
-		old_prog = rcu_dereference_protected(rq->xdp_prog,
-						     lockdep_is_held(&rq->priv->state_lock));
-		if (old_prog)
-			bpf_prog_put(old_prog);
-	}
+	kvfree(rq->dim);
+	page_pool_destroy(rq->page_pool);
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
+		mlx5e_rq_free_shampo(rq);
 		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, be32_to_cpu(rq->mpwqe.umr_mkey_be));
 		mlx5e_free_mpwqe_rq_drop_page(rq);
-		mlx5e_rq_free_shampo(rq);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		mlx5e_free_wqe_alloc_info(rq);
 	}
 
-	kvfree(rq->dim);
-	xdp_rxq_info_unreg(&rq->xdp_rxq);
-	page_pool_destroy(rq->page_pool);
 	mlx5_wq_destroy(&rq->wq_ctrl);
+
+	if (xdp_rxq_info_is_reg(&rq->xdp_rxq)) {
+		struct bpf_prog *old_prog;
+
+		old_prog = rcu_dereference_protected(rq->xdp_prog,
+						     lockdep_is_held(&rq->priv->state_lock));
+		if (old_prog)
+			bpf_prog_put(old_prog);
+	}
+	xdp_rxq_info_unreg(&rq->xdp_rxq);
 }
 
 int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_counter)
-- 
cgit v1.3-3-g829e


From 52fa3b6532ec6f3a1e39bf869b304d3560dd983b Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Fri, 13 Sep 2024 03:28:24 +0000
Subject: memory-provider: fix compilation issue without SYSFS

When CONFIG_SYSFS is not set, the kernel fails to compile:

     net/core/page_pool_user.c:368:45: error: implicit declaration of function 'get_netdev_rx_queue_index' [-Werror=implicit-function-declaration]
      368 |                 if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) {
          |                                             ^~~~~~~~~~~~~~~~~~~~~~~~~

When CONFIG_SYSFS is not set, get_netdev_rx_queue_index() is not defined
as well.

Fix by removing the ifdef around get_netdev_rx_queue_index(). It is not
needed anymore after commit e817f85652c1 ("xdp: generic XDP handling of
xdp_rxq_info") removed most of the CONFIG_SYSFS ifdefs.

Fixes: 0f9214046893 ("memory-provider: dmabuf devmem memory provider")
Cc: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20240913032824.2117095-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netdev_rx_queue.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index ac34f5fb4f71..596836abf7bf 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -45,7 +45,6 @@ __netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
 	return dev->_rx + rxq;
 }
 
-#ifdef CONFIG_SYSFS
 static inline unsigned int
 get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
 {
@@ -55,7 +54,6 @@ get_netdev_rx_queue_index(struct netdev_rx_queue *queue)
 	BUG_ON(index >= dev->num_rx_queues);
 	return index;
 }
-#endif
 
 int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq);
 
-- 
cgit v1.3-3-g829e


From da70d184a8c330d6945ed98f39265dada61850a0 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Tue, 10 Sep 2024 12:23:58 +0300
Subject: net: ethernet: ti: am65-cpsw: Introduce multi queue Rx

am65-cpsw can support up to 8 queues at Rx.
Use a macro AM65_CPSW_MAX_RX_QUEUES to indicate that.
As there is only one DMA channel for RX traffic, the
8 queues come as 8 flows in that channel.

By default, we will start with 1 flow as defined by the
macro AM65_CPSW_DEFAULT_RX_CHN_FLOWS.

User can change the number of flows by ethtool like so
'ethtool -L ethx rx <N>'

All traffic will still come on flow 0. To get traffic on
different flows the Classifiers will need to be set up.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-ethtool.c |  75 +++---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c    | 385 ++++++++++++++++------------
 drivers/net/ethernet/ti/am65-cpsw-nuss.h    |  39 +--
 3 files changed, 269 insertions(+), 230 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
index 539d5ca82f52..9032444435e9 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c
@@ -427,9 +427,9 @@ static void am65_cpsw_get_channels(struct net_device *ndev,
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 
-	ch->max_rx = AM65_CPSW_MAX_RX_QUEUES;
-	ch->max_tx = AM65_CPSW_MAX_TX_QUEUES;
-	ch->rx_count = AM65_CPSW_MAX_RX_QUEUES;
+	ch->max_rx = AM65_CPSW_MAX_QUEUES;
+	ch->max_tx = AM65_CPSW_MAX_QUEUES;
+	ch->rx_count = common->rx_ch_num_flows;
 	ch->tx_count = common->tx_ch_num;
 }
 
@@ -447,9 +447,8 @@ static int am65_cpsw_set_channels(struct net_device *ndev,
 	if (common->usage_count)
 		return -EBUSY;
 
-	am65_cpsw_nuss_remove_tx_chns(common);
-
-	return am65_cpsw_nuss_update_tx_chns(common, chs->tx_count);
+	return am65_cpsw_nuss_update_tx_rx_chns(common, chs->tx_count,
+						chs->rx_count);
 }
 
 static void
@@ -913,80 +912,64 @@ static void am65_cpsw_get_mm_stats(struct net_device *ndev,
 	s->MACMergeHoldCount = readl(base + AM65_CPSW_STATN_IET_TX_HOLD);
 }
 
-static int am65_cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
-				  struct kernel_ethtool_coalesce *kernel_coal,
-				  struct netlink_ext_ack *extack)
-{
-	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
-	struct am65_cpsw_tx_chn *tx_chn;
-
-	tx_chn = &common->tx_chns[0];
-
-	coal->rx_coalesce_usecs = common->rx_pace_timeout / 1000;
-	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout / 1000;
-
-	return 0;
-}
-
 static int am65_cpsw_get_per_queue_coalesce(struct net_device *ndev, u32 queue,
 					    struct ethtool_coalesce *coal)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_rx_flow *rx_flow;
 	struct am65_cpsw_tx_chn *tx_chn;
 
-	if (queue >= AM65_CPSW_MAX_TX_QUEUES)
+	if (queue >= AM65_CPSW_MAX_QUEUES)
 		return -EINVAL;
 
 	tx_chn = &common->tx_chns[queue];
-
 	coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout / 1000;
 
+	rx_flow = &common->rx_chns.flows[queue];
+	coal->rx_coalesce_usecs = rx_flow->rx_pace_timeout / 1000;
+
 	return 0;
 }
 
-static int am65_cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+static int am65_cpsw_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
 				  struct kernel_ethtool_coalesce *kernel_coal,
 				  struct netlink_ext_ack *extack)
 {
-	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
-	struct am65_cpsw_tx_chn *tx_chn;
-
-	tx_chn = &common->tx_chns[0];
-
-	if (coal->rx_coalesce_usecs && coal->rx_coalesce_usecs < 20)
-		return -EINVAL;
-
-	if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20)
-		return -EINVAL;
-
-	common->rx_pace_timeout = coal->rx_coalesce_usecs * 1000;
-	tx_chn->tx_pace_timeout = coal->tx_coalesce_usecs * 1000;
-
-	return 0;
+	return am65_cpsw_get_per_queue_coalesce(ndev, 0, coal);
 }
 
 static int am65_cpsw_set_per_queue_coalesce(struct net_device *ndev, u32 queue,
 					    struct ethtool_coalesce *coal)
 {
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+	struct am65_cpsw_rx_flow *rx_flow;
 	struct am65_cpsw_tx_chn *tx_chn;
 
-	if (queue >= AM65_CPSW_MAX_TX_QUEUES)
+	if (queue >= AM65_CPSW_MAX_QUEUES)
 		return -EINVAL;
 
 	tx_chn = &common->tx_chns[queue];
-
-	if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20) {
-		dev_info(common->dev, "defaulting to min value of 20us for tx-usecs for tx-%u\n",
-			 queue);
-		coal->tx_coalesce_usecs = 20;
-	}
+	if (coal->tx_coalesce_usecs && coal->tx_coalesce_usecs < 20)
+		return -EINVAL;
 
 	tx_chn->tx_pace_timeout = coal->tx_coalesce_usecs * 1000;
 
+	rx_flow = &common->rx_chns.flows[queue];
+	if (coal->rx_coalesce_usecs && coal->rx_coalesce_usecs < 20)
+		return -EINVAL;
+
+	rx_flow->rx_pace_timeout = coal->rx_coalesce_usecs * 1000;
+
 	return 0;
 }
 
+static int am65_cpsw_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *coal,
+				  struct kernel_ethtool_coalesce *kernel_coal,
+				  struct netlink_ext_ack *extack)
+{
+	return am65_cpsw_set_per_queue_coalesce(ndev, 0, coal);
+}
+
 const struct ethtool_ops am65_cpsw_ethtool_ops_slave = {
 	.begin			= am65_cpsw_ethtool_op_begin,
 	.complete		= am65_cpsw_ethtool_op_complete,
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index b7e5d0fb5d19..76e62351b30b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -138,7 +138,7 @@
 	 AM65_CPSW_PN_TS_CTL_RX_ANX_F_EN)
 
 #define AM65_CPSW_ALE_AGEOUT_DEFAULT	30
-/* Number of TX/RX descriptors */
+/* Number of TX/RX descriptors per channel/flow */
 #define AM65_CPSW_MAX_TX_DESC	500
 #define AM65_CPSW_MAX_RX_DESC	500
 
@@ -150,6 +150,7 @@
 			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
 
 #define AM65_CPSW_DEFAULT_TX_CHNS	8
+#define AM65_CPSW_DEFAULT_RX_CHN_FLOWS	1
 
 /* CPPI streaming packet interface */
 #define AM65_CPSW_CPPI_TX_FLOW_ID  0x3FFF
@@ -331,7 +332,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev,
 }
 
 static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common,
-				  struct page *page)
+				  struct page *page, u32 flow_idx)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
 	struct cppi5_host_desc_t *desc_rx;
@@ -364,7 +365,8 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common,
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	*((void **)swdata) = page_address(page);
 
-	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0, desc_rx, desc_dma);
+	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, flow_idx,
+					desc_rx, desc_dma);
 }
 
 void am65_cpsw_nuss_set_p0_ptype(struct am65_cpsw_common *common)
@@ -399,22 +401,27 @@ static void am65_cpsw_init_port_emac_ale(struct am65_cpsw_port *port);
 static void am65_cpsw_destroy_xdp_rxqs(struct am65_cpsw_common *common)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct am65_cpsw_rx_flow *flow;
 	struct xdp_rxq_info *rxq;
-	int i;
+	int id, port;
 
-	for (i = 0; i < common->port_num; i++) {
-		if (!common->ports[i].ndev)
-			continue;
+	for (id = 0; id < common->rx_ch_num_flows; id++) {
+		flow = &rx_chn->flows[id];
 
-		rxq = &common->ports[i].xdp_rxq;
+		for (port = 0; port < common->port_num; port++) {
+			if (!common->ports[port].ndev)
+				continue;
 
-		if (xdp_rxq_info_is_reg(rxq))
-			xdp_rxq_info_unreg(rxq);
-	}
+			rxq = &common->ports[port].xdp_rxq[id];
+
+			if (xdp_rxq_info_is_reg(rxq))
+				xdp_rxq_info_unreg(rxq);
+		}
 
-	if (rx_chn->page_pool) {
-		page_pool_destroy(rx_chn->page_pool);
-		rx_chn->page_pool = NULL;
+		if (flow->page_pool) {
+			page_pool_destroy(flow->page_pool);
+			flow->page_pool = NULL;
+		}
 	}
 }
 
@@ -428,31 +435,44 @@ static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common)
 		.nid = dev_to_node(common->dev),
 		.dev = common->dev,
 		.dma_dir = DMA_BIDIRECTIONAL,
-		.napi = &common->napi_rx,
+		/* .napi set dynamically */
 	};
+	struct am65_cpsw_rx_flow *flow;
 	struct xdp_rxq_info *rxq;
 	struct page_pool *pool;
-	int i, ret;
-
-	pool = page_pool_create(&pp_params);
-	if (IS_ERR(pool))
-		return PTR_ERR(pool);
+	int id, port, ret;
+
+	for (id = 0; id < common->rx_ch_num_flows; id++) {
+		flow = &rx_chn->flows[id];
+		pp_params.napi = &flow->napi_rx;
+		pool = page_pool_create(&pp_params);
+		if (IS_ERR(pool)) {
+			ret = PTR_ERR(pool);
+			goto err;
+		}
 
-	rx_chn->page_pool = pool;
+		flow->page_pool = pool;
 
-	for (i = 0; i < common->port_num; i++) {
-		if (!common->ports[i].ndev)
-			continue;
+		/* using same page pool is allowed as no running rx handlers
+		 * simultaneously for both ndevs
+		 */
+		for (port = 0; port < common->port_num; port++) {
+			if (!common->ports[port].ndev)
+				continue;
 
-		rxq = &common->ports[i].xdp_rxq;
+			rxq = &common->ports[port].xdp_rxq[id];
 
-		ret = xdp_rxq_info_reg(rxq, common->ports[i].ndev, i, 0);
-		if (ret)
-			goto err;
+			ret = xdp_rxq_info_reg(rxq, common->ports[port].ndev,
+					       id, flow->napi_rx.napi_id);
+			if (ret)
+				goto err;
 
-		ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
-		if (ret)
-			goto err;
+			ret = xdp_rxq_info_reg_mem_model(rxq,
+							 MEM_TYPE_PAGE_POOL,
+							 pool);
+			if (ret)
+				goto err;
+		}
 	}
 
 	return 0;
@@ -497,25 +517,27 @@ static enum am65_cpsw_tx_buf_type am65_cpsw_nuss_buf_type(struct am65_cpsw_tx_ch
 								       desc_idx);
 }
 
-static inline void am65_cpsw_put_page(struct am65_cpsw_rx_chn *rx_chn,
+static inline void am65_cpsw_put_page(struct am65_cpsw_rx_flow *flow,
 				      struct page *page,
 				      bool allow_direct,
 				      int desc_idx)
 {
-	page_pool_put_full_page(rx_chn->page_pool, page, allow_direct);
-	rx_chn->pages[desc_idx] = NULL;
+	page_pool_put_full_page(flow->page_pool, page, allow_direct);
+	flow->pages[desc_idx] = NULL;
 }
 
 static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
 {
-	struct am65_cpsw_rx_chn *rx_chn = data;
+	struct am65_cpsw_rx_flow *flow = data;
 	struct cppi5_host_desc_t *desc_rx;
+	struct am65_cpsw_rx_chn *rx_chn;
 	dma_addr_t buf_dma;
 	u32 buf_dma_len;
 	void *page_addr;
 	void **swdata;
 	int desc_idx;
 
+	rx_chn = &flow->common->rx_chns;
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
 	page_addr = *swdata;
@@ -526,7 +548,7 @@ static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma)
 
 	desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx,
 					   rx_chn->dsize_log2);
-	am65_cpsw_put_page(rx_chn, virt_to_page(page_addr), false, desc_idx);
+	am65_cpsw_put_page(flow, virt_to_page(page_addr), false, desc_idx);
 }
 
 static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn,
@@ -602,7 +624,8 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 	struct am65_cpsw_host *host_p = am65_common_get_host(common);
 	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
 	struct am65_cpsw_tx_chn *tx_chn = common->tx_chns;
-	int port_idx, i, ret, tx;
+	int port_idx, i, ret, tx, flow_idx;
+	struct am65_cpsw_rx_flow *flow;
 	u32 val, port_mask;
 	struct page *page;
 
@@ -670,27 +693,26 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 		return ret;
 	}
 
-	for (i = 0; i < rx_chn->descs_num; i++) {
-		page = page_pool_dev_alloc_pages(rx_chn->page_pool);
-		if (!page) {
-			ret = -ENOMEM;
-			if (i)
+	for (flow_idx = 0; flow_idx < common->rx_ch_num_flows; flow_idx++) {
+		flow = &rx_chn->flows[flow_idx];
+		for (i = 0; i < AM65_CPSW_MAX_RX_DESC; i++) {
+			page = page_pool_dev_alloc_pages(flow->page_pool);
+			if (!page) {
+				dev_err(common->dev, "cannot allocate page in flow %d\n",
+					flow_idx);
+				ret = -ENOMEM;
 				goto fail_rx;
+			}
+			flow->pages[i] = page;
 
-			return ret;
-		}
-		rx_chn->pages[i] = page;
-
-		ret = am65_cpsw_nuss_rx_push(common, page);
-		if (ret < 0) {
-			dev_err(common->dev,
-				"cannot submit page to channel rx: %d\n",
-				ret);
-			am65_cpsw_put_page(rx_chn, page, false, i);
-			if (i)
+			ret = am65_cpsw_nuss_rx_push(common, page, flow_idx);
+			if (ret < 0) {
+				dev_err(common->dev,
+					"cannot submit page to rx channel flow %d, error %d\n",
+					flow_idx, ret);
+				am65_cpsw_put_page(flow, page, false, i);
 				goto fail_rx;
-
-			return ret;
+			}
 		}
 	}
 
@@ -700,6 +722,14 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 		goto fail_rx;
 	}
 
+	for (i = 0; i < common->rx_ch_num_flows ; i++) {
+		napi_enable(&rx_chn->flows[i].napi_rx);
+		if (rx_chn->flows[i].irq_disabled) {
+			rx_chn->flows[i].irq_disabled = false;
+			enable_irq(rx_chn->flows[i].irq);
+		}
+	}
+
 	for (tx = 0; tx < common->tx_ch_num; tx++) {
 		ret = k3_udma_glue_enable_tx_chn(tx_chn[tx].tx_chn);
 		if (ret) {
@@ -711,12 +741,6 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common)
 		napi_enable(&tx_chn[tx].napi_tx);
 	}
 
-	napi_enable(&common->napi_rx);
-	if (common->rx_irq_disabled) {
-		common->rx_irq_disabled = false;
-		enable_irq(rx_chn->irq);
-	}
-
 	dev_dbg(common->dev, "cpsw_nuss started\n");
 	return 0;
 
@@ -727,11 +751,24 @@ fail_tx:
 		tx--;
 	}
 
+	for (flow_idx = 0; i < common->rx_ch_num_flows; flow_idx++) {
+		flow = &rx_chn->flows[flow_idx];
+		if (!flow->irq_disabled) {
+			disable_irq(flow->irq);
+			flow->irq_disabled = true;
+		}
+		napi_disable(&flow->napi_rx);
+	}
+
 	k3_udma_glue_disable_rx_chn(rx_chn->rx_chn);
 
 fail_rx:
-	k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, 0, rx_chn,
-				  am65_cpsw_nuss_rx_cleanup, 0);
+	for (i = 0; i < common->rx_ch_num_flows; i--)
+		k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, &rx_chn->flows[i],
+					  am65_cpsw_nuss_rx_cleanup, 0);
+
+	am65_cpsw_destroy_xdp_rxqs(common);
+
 	return ret;
 }
 
@@ -780,12 +817,12 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 			dev_err(common->dev, "rx teardown timeout\n");
 	}
 
-	napi_disable(&common->napi_rx);
-	hrtimer_cancel(&common->rx_hrtimer);
-
-	for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++)
-		k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn,
-					  am65_cpsw_nuss_rx_cleanup, !!i);
+	for (i = 0; i < common->rx_ch_num_flows; i++) {
+		napi_disable(&rx_chn->flows[i].napi_rx);
+		hrtimer_cancel(&rx_chn->flows[i].rx_hrtimer);
+		k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, &rx_chn->flows[i],
+					  am65_cpsw_nuss_rx_cleanup, 0);
+	}
 
 	k3_udma_glue_disable_rx_chn(rx_chn->rx_chn);
 
@@ -794,10 +831,6 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common)
 	writel(0, common->cpsw_base + AM65_CPSW_REG_CTL);
 	writel(0, common->cpsw_base + AM65_CPSW_REG_STAT_PORT_EN);
 
-	for (i = 0; i < rx_chn->descs_num; i++) {
-		if (rx_chn->pages[i])
-			am65_cpsw_put_page(rx_chn, rx_chn->pages[i], false, i);
-	}
 	am65_cpsw_destroy_xdp_rxqs(common);
 
 	dev_dbg(common->dev, "cpsw_nuss stopped\n");
@@ -868,7 +901,7 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev)
 		goto runtime_put;
 	}
 
-	ret = netif_set_real_num_rx_queues(ndev, AM65_CPSW_MAX_RX_QUEUES);
+	ret = netif_set_real_num_rx_queues(ndev, common->rx_ch_num_flows);
 	if (ret) {
 		dev_err(common->dev, "cannot set real number of rx queues\n");
 		goto runtime_put;
@@ -992,12 +1025,12 @@ pool_free:
 	return ret;
 }
 
-static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 			     struct am65_cpsw_port *port,
 			     struct xdp_buff *xdp,
 			     int desc_idx, int cpu, int *len)
 {
-	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct am65_cpsw_common *common = flow->common;
 	struct am65_cpsw_ndev_priv *ndev_priv;
 	struct net_device *ndev = port->ndev;
 	struct am65_cpsw_ndev_stats *stats;
@@ -1026,7 +1059,7 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
 		ret = AM65_CPSW_XDP_PASS;
 		goto out;
 	case XDP_TX:
-		tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES];
+		tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_QUEUES];
 		netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
 
 		xdpf = xdp_convert_buff_to_frame(xdp);
@@ -1068,7 +1101,8 @@ drop:
 	}
 
 	page = virt_to_head_page(xdp->data);
-	am65_cpsw_put_page(rx_chn, page, true, desc_idx);
+	am65_cpsw_put_page(flow, page, true, desc_idx);
+
 out:
 	return ret;
 }
@@ -1106,11 +1140,12 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info)
 	}
 }
 
-static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
-				     u32 flow_idx, int cpu, int *xdp_state)
+static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
+				     int cpu, int *xdp_state)
 {
-	struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+	struct am65_cpsw_rx_chn *rx_chn = &flow->common->rx_chns;
 	u32 buf_dma_len, pkt_len, port_id = 0, csum_info;
+	struct am65_cpsw_common *common = flow->common;
 	struct am65_cpsw_ndev_priv *ndev_priv;
 	struct am65_cpsw_ndev_stats *stats;
 	struct cppi5_host_desc_t *desc_rx;
@@ -1120,6 +1155,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	struct am65_cpsw_port *port;
 	int headroom, desc_idx, ret;
 	struct net_device *ndev;
+	u32 flow_idx = flow->id;
 	struct sk_buff *skb;
 	struct xdp_buff	xdp;
 	void *page_addr;
@@ -1174,10 +1210,10 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	}
 
 	if (port->xdp_prog) {
-		xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq);
+		xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]);
 		xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
 				 pkt_len, false);
-		*xdp_state = am65_cpsw_run_xdp(common, port, &xdp, desc_idx,
+		*xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, desc_idx,
 					       cpu, &pkt_len);
 		if (*xdp_state != AM65_CPSW_XDP_PASS)
 			goto allocate;
@@ -1195,7 +1231,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	skb_mark_for_recycle(skb);
 	skb->protocol = eth_type_trans(skb, ndev);
 	am65_cpsw_nuss_rx_csum(skb, csum_info);
-	napi_gro_receive(&common->napi_rx, skb);
+	napi_gro_receive(&flow->napi_rx, skb);
 
 	stats = this_cpu_ptr(ndev_priv->stats);
 
@@ -1205,24 +1241,24 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
 	u64_stats_update_end(&stats->syncp);
 
 allocate:
-	new_page = page_pool_dev_alloc_pages(rx_chn->page_pool);
+	new_page = page_pool_dev_alloc_pages(flow->page_pool);
 	if (unlikely(!new_page)) {
 		dev_err(dev, "page alloc failed\n");
 		return -ENOMEM;
 	}
 
-	rx_chn->pages[desc_idx] = new_page;
+	flow->pages[desc_idx] = new_page;
 
 	if (netif_dormant(ndev)) {
-		am65_cpsw_put_page(rx_chn, new_page, true, desc_idx);
+		am65_cpsw_put_page(flow, new_page, true, desc_idx);
 		ndev->stats.rx_dropped++;
 		return 0;
 	}
 
 requeue:
-	ret = am65_cpsw_nuss_rx_push(common, new_page);
+	ret = am65_cpsw_nuss_rx_push(common, new_page, flow_idx);
 	if (WARN_ON(ret < 0)) {
-		am65_cpsw_put_page(rx_chn, new_page, true, desc_idx);
+		am65_cpsw_put_page(flow, new_page, true, desc_idx);
 		ndev->stats.rx_errors++;
 		ndev->stats.rx_dropped++;
 	}
@@ -1232,38 +1268,32 @@ requeue:
 
 static enum hrtimer_restart am65_cpsw_nuss_rx_timer_callback(struct hrtimer *timer)
 {
-	struct am65_cpsw_common *common =
-			container_of(timer, struct am65_cpsw_common, rx_hrtimer);
+	struct am65_cpsw_rx_flow *flow = container_of(timer,
+						      struct am65_cpsw_rx_flow,
+						      rx_hrtimer);
 
-	enable_irq(common->rx_chns.irq);
+	enable_irq(flow->irq);
 	return HRTIMER_NORESTART;
 }
 
 static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 {
-	struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx);
-	int flow = AM65_CPSW_MAX_RX_FLOWS;
+	struct am65_cpsw_rx_flow *flow = am65_cpsw_napi_to_rx_flow(napi_rx);
+	struct am65_cpsw_common *common = flow->common;
 	int cpu = smp_processor_id();
 	int xdp_state_or = 0;
 	int cur_budget, ret;
 	int xdp_state;
 	int num_rx = 0;
 
-	/* process every flow */
-	while (flow--) {
-		cur_budget = budget - num_rx;
-
-		while (cur_budget--) {
-			ret = am65_cpsw_nuss_rx_packets(common, flow, cpu,
-							&xdp_state);
-			xdp_state_or |= xdp_state;
-			if (ret)
-				break;
-			num_rx++;
-		}
-
-		if (num_rx >= budget)
+	/* process only this flow */
+	cur_budget = budget;
+	while (cur_budget--) {
+		ret = am65_cpsw_nuss_rx_packets(flow, cpu, &xdp_state);
+		xdp_state_or |= xdp_state;
+		if (ret)
 			break;
+		num_rx++;
 	}
 
 	if (xdp_state_or & AM65_CPSW_XDP_REDIRECT)
@@ -1272,14 +1302,14 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 	dev_dbg(common->dev, "%s num_rx:%d %d\n", __func__, num_rx, budget);
 
 	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
-		if (common->rx_irq_disabled) {
-			common->rx_irq_disabled = false;
-			if (unlikely(common->rx_pace_timeout)) {
-				hrtimer_start(&common->rx_hrtimer,
-					      ns_to_ktime(common->rx_pace_timeout),
+		if (flow->irq_disabled) {
+			flow->irq_disabled = false;
+			if (unlikely(flow->rx_pace_timeout)) {
+				hrtimer_start(&flow->rx_hrtimer,
+					      ns_to_ktime(flow->rx_pace_timeout),
 					      HRTIMER_MODE_REL_PINNED);
 			} else {
-				enable_irq(common->rx_chns.irq);
+				enable_irq(flow->irq);
 			}
 		}
 	}
@@ -1527,11 +1557,11 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget)
 
 static irqreturn_t am65_cpsw_nuss_rx_irq(int irq, void *dev_id)
 {
-	struct am65_cpsw_common *common = dev_id;
+	struct am65_cpsw_rx_flow *flow = dev_id;
 
-	common->rx_irq_disabled = true;
+	flow->irq_disabled = true;
 	disable_irq_nosync(irq);
-	napi_schedule(&common->napi_rx);
+	napi_schedule(&flow->napi_rx);
 
 	return IRQ_HANDLED;
 }
@@ -2176,7 +2206,7 @@ static void am65_cpsw_nuss_free_tx_chns(void *data)
 	}
 }
 
-void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
+static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
 	int i;
@@ -2191,15 +2221,9 @@ void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 			devm_free_irq(dev, tx_chn->irq, tx_chn);
 
 		netif_napi_del(&tx_chn->napi_tx);
-
-		if (!IS_ERR_OR_NULL(tx_chn->desc_pool))
-			k3_cppi_desc_pool_destroy(tx_chn->desc_pool);
-
-		if (!IS_ERR_OR_NULL(tx_chn->tx_chn))
-			k3_udma_glue_release_tx_chn(tx_chn->tx_chn);
-
-		memset(tx_chn, 0, sizeof(*tx_chn));
 	}
+
+	am65_cpsw_nuss_free_tx_chns(common);
 }
 
 static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
@@ -2331,19 +2355,22 @@ static void am65_cpsw_nuss_free_rx_chns(void *data)
 		k3_udma_glue_release_rx_chn(rx_chn->rx_chn);
 }
 
-static void am65_cpsw_nuss_remove_rx_chns(void *data)
+static void am65_cpsw_nuss_remove_rx_chns(struct am65_cpsw_common *common)
 {
-	struct am65_cpsw_common *common = data;
 	struct device *dev = common->dev;
 	struct am65_cpsw_rx_chn *rx_chn;
+	struct am65_cpsw_rx_flow *flows;
+	int i;
 
 	rx_chn = &common->rx_chns;
+	flows = rx_chn->flows;
 	devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common);
 
-	if (!(rx_chn->irq < 0))
-		devm_free_irq(dev, rx_chn->irq, common);
-
-	netif_napi_del(&common->napi_rx);
+	for (i = 0; i < common->rx_ch_num_flows; i++) {
+		if (!(flows[i].irq < 0))
+			devm_free_irq(dev, flows[i].irq, &flows[i]);
+		netif_napi_del(&flows[i].napi_rx);
+	}
 
 	am65_cpsw_nuss_free_rx_chns(common);
 
@@ -2356,6 +2383,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 	struct k3_udma_glue_rx_channel_cfg rx_cfg = { 0 };
 	u32  max_desc_num = AM65_CPSW_MAX_RX_DESC;
 	struct device *dev = common->dev;
+	struct am65_cpsw_rx_flow *flow;
 	u32 hdesc_size, hdesc_size_out;
 	u32 fdqring_id;
 	int i, ret = 0;
@@ -2364,12 +2392,21 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 					   AM65_CPSW_NAV_SW_DATA_SIZE);
 
 	rx_cfg.swdata_size = AM65_CPSW_NAV_SW_DATA_SIZE;
-	rx_cfg.flow_id_num = AM65_CPSW_MAX_RX_FLOWS;
+	rx_cfg.flow_id_num = common->rx_ch_num_flows;
 	rx_cfg.flow_id_base = common->rx_flow_id_base;
 
 	/* init all flows */
 	rx_chn->dev = dev;
-	rx_chn->descs_num = max_desc_num;
+	rx_chn->descs_num = max_desc_num * rx_cfg.flow_id_num;
+
+	for (i = 0; i < common->rx_ch_num_flows; i++) {
+		flow = &rx_chn->flows[i];
+		flow->page_pool = NULL;
+		flow->pages = devm_kcalloc(dev, AM65_CPSW_MAX_RX_DESC,
+					   sizeof(*flow->pages), GFP_KERNEL);
+		if (!flow->pages)
+			return -ENOMEM;
+	}
 
 	rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, "rx", &rx_cfg);
 	if (IS_ERR(rx_chn->rx_chn)) {
@@ -2392,13 +2429,6 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 	rx_chn->dsize_log2 = __fls(hdesc_size_out);
 	WARN_ON(hdesc_size_out != (1 << rx_chn->dsize_log2));
 
-	rx_chn->page_pool = NULL;
-
-	rx_chn->pages = devm_kcalloc(dev, rx_chn->descs_num,
-				     sizeof(*rx_chn->pages), GFP_KERNEL);
-	if (!rx_chn->pages)
-		return -ENOMEM;
-
 	common->rx_flow_id_base =
 			k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn);
 	dev_info(dev, "set new flow-id-base %u\n", common->rx_flow_id_base);
@@ -2422,6 +2452,10 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 				K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG,
 		};
 
+		flow = &rx_chn->flows[i];
+		flow->id = i;
+		flow->common = common;
+
 		rx_flow_cfg.ring_rxfdq0_id = fdqring_id;
 		rx_flow_cfg.rx_cfg.size = max_desc_num;
 		rx_flow_cfg.rxfdq_cfg.size = max_desc_num;
@@ -2438,28 +2472,32 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 				k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn,
 								i);
 
-		rx_chn->irq = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
-
-		if (rx_chn->irq < 0) {
+		flow->irq = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i);
+		if (flow->irq <= 0) {
 			dev_err(dev, "Failed to get rx dma irq %d\n",
-				rx_chn->irq);
-			ret = rx_chn->irq;
+				flow->irq);
+			ret = flow->irq;
 			goto err;
 		}
-	}
-
-	netif_napi_add(common->dma_ndev, &common->napi_rx,
-		       am65_cpsw_nuss_rx_poll);
-	hrtimer_init(&common->rx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	common->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
 
-	ret = devm_request_irq(dev, rx_chn->irq,
-			       am65_cpsw_nuss_rx_irq,
-			       IRQF_TRIGGER_HIGH, dev_name(dev), common);
-	if (ret) {
-		dev_err(dev, "failure requesting rx irq %u, %d\n",
-			rx_chn->irq, ret);
-		goto err;
+		snprintf(flow->name,
+			 sizeof(flow->name), "%s-rx%d",
+			 dev_name(dev), i);
+		netif_napi_add(common->dma_ndev, &flow->napi_rx,
+			       am65_cpsw_nuss_rx_poll);
+		hrtimer_init(&flow->rx_hrtimer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL_PINNED);
+		flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
+
+		ret = devm_request_irq(dev, flow->irq,
+				       am65_cpsw_nuss_rx_irq,
+				       IRQF_TRIGGER_HIGH,
+				       flow->name, flow);
+		if (ret) {
+			dev_err(dev, "failure requesting rx %d irq %u, %d\n",
+				i, flow->irq, ret);
+			goto err;
+		}
 	}
 
 err:
@@ -2705,8 +2743,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx)
 	/* alloc netdev */
 	port->ndev = devm_alloc_etherdev_mqs(common->dev,
 					     sizeof(struct am65_cpsw_ndev_priv),
-					     AM65_CPSW_MAX_TX_QUEUES,
-					     AM65_CPSW_MAX_RX_QUEUES);
+					     AM65_CPSW_MAX_QUEUES,
+					     AM65_CPSW_MAX_QUEUES);
 	if (!port->ndev) {
 		dev_err(dev, "error allocating slave net_device %u\n",
 			port->port_id);
@@ -3303,9 +3341,10 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common)
 		k3_udma_glue_disable_tx_chn(tx_chan[i].tx_chn);
 	}
 
-	for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++)
-		k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i, rx_chan,
-					  am65_cpsw_nuss_rx_cleanup, !!i);
+	for (i = 0; i < common->rx_ch_num_flows; i++)
+		k3_udma_glue_reset_rx_chn(rx_chan->rx_chn, i,
+					  &rx_chan->flows[i],
+					  am65_cpsw_nuss_rx_cleanup, 0);
 
 	k3_udma_glue_disable_rx_chn(rx_chan->rx_chn);
 
@@ -3346,12 +3385,21 @@ err_cleanup_ndev:
 	return ret;
 }
 
-int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx)
+int am65_cpsw_nuss_update_tx_rx_chns(struct am65_cpsw_common *common,
+				     int num_tx, int num_rx)
 {
 	int ret;
 
+	am65_cpsw_nuss_remove_tx_chns(common);
+	am65_cpsw_nuss_remove_rx_chns(common);
+
 	common->tx_ch_num = num_tx;
+	common->rx_ch_num_flows = num_rx;
 	ret = am65_cpsw_nuss_init_tx_chns(common);
+	if (ret)
+		return ret;
+
+	ret = am65_cpsw_nuss_init_rx_chns(common);
 
 	return ret;
 }
@@ -3481,6 +3529,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	common->rx_flow_id_base = -1;
 	init_completion(&common->tdown_complete);
 	common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS;
+	common->rx_ch_num_flows = AM65_CPSW_DEFAULT_RX_CHN_FLOWS;
 	common->pf_p0_rx_ptype_rrobin = false;
 	common->default_vlan = 1;
 
@@ -3672,8 +3721,10 @@ static int am65_cpsw_nuss_resume(struct device *dev)
 		return ret;
 
 	/* If RX IRQ was disabled before suspend, keep it disabled */
-	if (common->rx_irq_disabled)
-		disable_irq(common->rx_chns.irq);
+	for (i = 0; i < common->rx_ch_num_flows; i++) {
+		if (common->rx_chns.flows[i].irq_disabled)
+			disable_irq(common->rx_chns.flows[i].irq);
+	}
 
 	am65_cpts_resume(common->cpts);
 
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index e2ce2be320bd..dc8d544230dc 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -21,9 +21,7 @@ struct am65_cpts;
 
 #define HOST_PORT_NUM		0
 
-#define AM65_CPSW_MAX_TX_QUEUES	8
-#define AM65_CPSW_MAX_RX_QUEUES	1
-#define AM65_CPSW_MAX_RX_FLOWS	1
+#define AM65_CPSW_MAX_QUEUES	8	/* both TX & RX */
 
 #define AM65_CPSW_PORT_VLAN_REG_OFFSET	0x014
 
@@ -58,7 +56,7 @@ struct am65_cpsw_port {
 	struct am65_cpsw_qos		qos;
 	struct devlink_port		devlink_port;
 	struct bpf_prog			*xdp_prog;
-	struct xdp_rxq_info		xdp_rxq;
+	struct xdp_rxq_info		xdp_rxq[AM65_CPSW_MAX_QUEUES];
 	/* Only for suspend resume context */
 	u32				vid_context;
 };
@@ -94,16 +92,27 @@ struct am65_cpsw_tx_chn {
 	u32 rate_mbps;
 };
 
+struct am65_cpsw_rx_flow {
+	u32 id;
+	struct napi_struct napi_rx;
+	struct am65_cpsw_common	*common;
+	int irq;
+	bool irq_disabled;
+	struct hrtimer rx_hrtimer;
+	unsigned long rx_pace_timeout;
+	struct page_pool *page_pool;
+	struct page **pages;
+	char name[32];
+};
+
 struct am65_cpsw_rx_chn {
 	struct device *dev;
 	struct device *dma_dev;
 	struct k3_cppi_desc_pool *desc_pool;
 	struct k3_udma_glue_rx_channel *rx_chn;
-	struct page_pool *page_pool;
-	struct page **pages;
 	u32 descs_num;
 	unsigned char dsize_log2;
-	int irq;
+	struct am65_cpsw_rx_flow flows[AM65_CPSW_MAX_QUEUES];
 };
 
 #define AM65_CPSW_QUIRK_I2027_NO_TX_CSUM BIT(0)
@@ -145,16 +154,12 @@ struct am65_cpsw_common {
 	u32			tx_ch_rate_msk;
 	u32			rx_flow_id_base;
 
-	struct am65_cpsw_tx_chn	tx_chns[AM65_CPSW_MAX_TX_QUEUES];
+	struct am65_cpsw_tx_chn	tx_chns[AM65_CPSW_MAX_QUEUES];
 	struct completion	tdown_complete;
 	atomic_t		tdown_cnt;
 
+	int			rx_ch_num_flows;
 	struct am65_cpsw_rx_chn	rx_chns;
-	struct napi_struct	napi_rx;
-
-	bool			rx_irq_disabled;
-	struct hrtimer		rx_hrtimer;
-	unsigned long		rx_pace_timeout;
 
 	u32			nuss_ver;
 	u32			cpsw_ver;
@@ -203,8 +208,8 @@ struct am65_cpsw_ndev_priv {
 #define am65_common_get_host(common) (&(common)->host)
 #define am65_common_get_port(common, id) (&(common)->ports[(id) - 1])
 
-#define am65_cpsw_napi_to_common(pnapi) \
-	container_of(pnapi, struct am65_cpsw_common, napi_rx)
+#define am65_cpsw_napi_to_rx_flow(pnapi) \
+	container_of(pnapi, struct am65_cpsw_rx_flow, napi_rx)
 #define am65_cpsw_napi_to_tx_chn(pnapi) \
 	container_of(pnapi, struct am65_cpsw_tx_chn, napi_tx)
 
@@ -215,8 +220,8 @@ struct am65_cpsw_ndev_priv {
 extern const struct ethtool_ops am65_cpsw_ethtool_ops_slave;
 
 void am65_cpsw_nuss_set_p0_ptype(struct am65_cpsw_common *common);
-void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common);
-int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx);
+int am65_cpsw_nuss_update_tx_rx_chns(struct am65_cpsw_common *common,
+				     int num_tx, int num_rx);
 
 bool am65_cpsw_port_dev_check(const struct net_device *dev);
 
-- 
cgit v1.3-3-g829e


From bbfc7e2b9ebe16669e33d9332275d87b660a3c8b Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Tue, 10 Sep 2024 12:23:59 +0300
Subject: net: ethernet: ti: cpsw_ale: use regfields for ALE registers

Map the entire ALE registerspace using regmap.

Add regfields for Major and Minor Version fields.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ale.c | 84 ++++++++++++++++++++++++++++++--------
 drivers/net/ethernet/ti/cpsw_ale.h | 17 ++++++--
 2 files changed, 79 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 64bf22cd860c..979f741a231d 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/err.h>
@@ -76,7 +77,7 @@ enum {
  * @dev_id: ALE version/SoC id
  * @features: features supported by ALE
  * @tbl_entries: number of ALE entries
- * @major_ver_mask: mask of ALE Major Version Value in ALE_IDVER reg.
+ * @reg_fields: pointer to array of register field configuration
  * @nu_switch_ale: NU Switch ALE
  * @vlan_entry_tbl: ALE vlan entry fields description tbl
  */
@@ -84,7 +85,7 @@ struct cpsw_ale_dev_id {
 	const char *dev_id;
 	u32 features;
 	u32 tbl_entries;
-	u32 major_ver_mask;
+	const struct reg_field *reg_fields;
 	bool nu_switch_ale;
 	const struct ale_entry_fld *vlan_entry_tbl;
 };
@@ -1292,25 +1293,37 @@ void cpsw_ale_stop(struct cpsw_ale *ale)
 	cpsw_ale_control_set(ale, 0, ALE_ENABLE, 0);
 }
 
+static const struct reg_field ale_fields_cpsw[] = {
+	/* CPSW_ALE_IDVER_REG */
+	[MINOR_VER]	= REG_FIELD(ALE_IDVER, 0, 7),
+	[MAJOR_VER]	= REG_FIELD(ALE_IDVER, 8, 15),
+};
+
+static const struct reg_field ale_fields_cpsw_nu[] = {
+	/* CPSW_ALE_IDVER_REG */
+	[MINOR_VER]	= REG_FIELD(ALE_IDVER, 0, 7),
+	[MAJOR_VER]	= REG_FIELD(ALE_IDVER, 8, 10),
+};
+
 static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = {
 	{
 		/* am3/4/5, dra7. dm814x, 66ak2hk-gbe */
 		.dev_id = "cpsw",
 		.tbl_entries = 1024,
-		.major_ver_mask = 0xff,
+		.reg_fields = ale_fields_cpsw,
 		.vlan_entry_tbl = vlan_entry_cpsw,
 	},
 	{
 		/* 66ak2h_xgbe */
 		.dev_id = "66ak2h-xgbe",
 		.tbl_entries = 2048,
-		.major_ver_mask = 0xff,
+		.reg_fields = ale_fields_cpsw,
 		.vlan_entry_tbl = vlan_entry_cpsw,
 	},
 	{
 		.dev_id = "66ak2el",
 		.features = CPSW_ALE_F_STATUS_REG,
-		.major_ver_mask = 0x7,
+		.reg_fields = ale_fields_cpsw_nu,
 		.nu_switch_ale = true,
 		.vlan_entry_tbl = vlan_entry_nu,
 	},
@@ -1318,7 +1331,7 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = {
 		.dev_id = "66ak2g",
 		.features = CPSW_ALE_F_STATUS_REG,
 		.tbl_entries = 64,
-		.major_ver_mask = 0x7,
+		.reg_fields = ale_fields_cpsw_nu,
 		.nu_switch_ale = true,
 		.vlan_entry_tbl = vlan_entry_nu,
 	},
@@ -1326,20 +1339,20 @@ static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = {
 		.dev_id = "am65x-cpsw2g",
 		.features = CPSW_ALE_F_STATUS_REG | CPSW_ALE_F_HW_AUTOAGING,
 		.tbl_entries = 64,
-		.major_ver_mask = 0x7,
+		.reg_fields = ale_fields_cpsw_nu,
 		.nu_switch_ale = true,
 		.vlan_entry_tbl = vlan_entry_nu,
 	},
 	{
 		.dev_id = "j721e-cpswxg",
 		.features = CPSW_ALE_F_STATUS_REG | CPSW_ALE_F_HW_AUTOAGING,
-		.major_ver_mask = 0x7,
+		.reg_fields = ale_fields_cpsw_nu,
 		.vlan_entry_tbl = vlan_entry_k3_cpswxg,
 	},
 	{
 		.dev_id = "am64-cpswxg",
 		.features = CPSW_ALE_F_STATUS_REG | CPSW_ALE_F_HW_AUTOAGING,
-		.major_ver_mask = 0x7,
+		.reg_fields = ale_fields_cpsw_nu,
 		.vlan_entry_tbl = vlan_entry_k3_cpswxg,
 		.tbl_entries = 512,
 	},
@@ -1361,41 +1374,76 @@ cpsw_ale_dev_id *cpsw_ale_match_id(const struct cpsw_ale_dev_id *id,
 	return NULL;
 }
 
+static const struct regmap_config ale_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.name = "cpsw-ale",
+};
+
+static int cpsw_ale_regfield_init(struct cpsw_ale *ale)
+{
+	const struct reg_field *reg_fields = ale->params.reg_fields;
+	struct device *dev = ale->params.dev;
+	struct regmap *regmap = ale->regmap;
+	int i;
+
+	for (i = 0; i < ALE_FIELDS_MAX; i++) {
+		ale->fields[i] = devm_regmap_field_alloc(dev, regmap,
+							 reg_fields[i]);
+		if (IS_ERR(ale->fields[i])) {
+			dev_err(dev, "Unable to allocate regmap field %d\n", i);
+			return PTR_ERR(ale->fields[i]);
+		}
+	}
+
+	return 0;
+}
+
 struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 {
 	const struct cpsw_ale_dev_id *ale_dev_id;
+	u32 ale_entries, rev_major, rev_minor;
 	struct cpsw_ale *ale;
-	u32 rev, ale_entries;
+	int ret;
 
 	ale_dev_id = cpsw_ale_match_id(cpsw_ale_id_match, params->dev_id);
 	if (!ale_dev_id)
 		return ERR_PTR(-EINVAL);
 
 	params->ale_entries = ale_dev_id->tbl_entries;
-	params->major_ver_mask = ale_dev_id->major_ver_mask;
 	params->nu_switch_ale = ale_dev_id->nu_switch_ale;
+	params->reg_fields = ale_dev_id->reg_fields;
 
 	ale = devm_kzalloc(params->dev, sizeof(*ale), GFP_KERNEL);
 	if (!ale)
 		return ERR_PTR(-ENOMEM);
+	ale->regmap = devm_regmap_init_mmio(params->dev, params->ale_regs,
+					    &ale_regmap_cfg);
+	if (IS_ERR(ale->regmap)) {
+		dev_err(params->dev, "Couldn't create CPSW ALE regmap\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	ale->params = *params;
+	ret = cpsw_ale_regfield_init(ale);
+	if (ret)
+		return ERR_PTR(ret);
 
 	ale->p0_untag_vid_mask = devm_bitmap_zalloc(params->dev, VLAN_N_VID,
 						    GFP_KERNEL);
 	if (!ale->p0_untag_vid_mask)
 		return ERR_PTR(-ENOMEM);
 
-	ale->params = *params;
 	ale->ageout = ale->params.ale_ageout * HZ;
 	ale->features = ale_dev_id->features;
 	ale->vlan_entry_tbl = ale_dev_id->vlan_entry_tbl;
 
-	rev = readl_relaxed(ale->params.ale_regs + ALE_IDVER);
-	ale->version =
-		(ALE_VERSION_MAJOR(rev, ale->params.major_ver_mask) << 8) |
-		 ALE_VERSION_MINOR(rev);
+	regmap_field_read(ale->fields[MINOR_VER], &rev_minor);
+	regmap_field_read(ale->fields[MAJOR_VER], &rev_major);
+	ale->version = rev_major << 8 | rev_minor;
 	dev_info(ale->params.dev, "initialized cpsw ale version %d.%d\n",
-		 ALE_VERSION_MAJOR(rev, ale->params.major_ver_mask),
-		 ALE_VERSION_MINOR(rev));
+		 rev_major, rev_minor);
 
 	if (ale->features & CPSW_ALE_F_STATUS_REG &&
 	    !ale->params.ale_entries) {
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index 6779ee111d57..58d377dd7496 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -8,6 +8,8 @@
 #ifndef __TI_CPSW_ALE_H__
 #define __TI_CPSW_ALE_H__
 
+struct reg_fields;
+
 struct cpsw_ale_params {
 	struct device		*dev;
 	void __iomem		*ale_regs;
@@ -20,19 +22,26 @@ struct cpsw_ale_params {
 	 * to identify this hardware.
 	 */
 	bool			nu_switch_ale;
-	/* mask bit used in NU Switch ALE is 3 bits instead of 8 bits. So
-	 * pass it from caller.
-	 */
-	u32			major_ver_mask;
+	const struct reg_field *reg_fields;
 	const char		*dev_id;
 	unsigned long		bus_freq;
 };
 
 struct ale_entry_fld;
+struct regmap;
+
+enum ale_fields {
+	MINOR_VER,
+	MAJOR_VER,
+	/* terminator */
+	ALE_FIELDS_MAX,
+};
 
 struct cpsw_ale {
 	struct cpsw_ale_params	params;
 	struct timer_list	timer;
+	struct regmap		*regmap;
+	struct regmap_field	*fields[ALE_FIELDS_MAX];
 	unsigned long		ageout;
 	u32			version;
 	u32			features;
-- 
cgit v1.3-3-g829e


From 11cbcfeaa79e5c76cb3bce85dfc10de61b0b0a2b Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Tue, 10 Sep 2024 12:24:00 +0300
Subject: net: ethernet: ti: cpsw_ale: use regfields for number of Entries and
 Policers

Use regfields for number of ALE Entries and Policers.

The variants that support Policers/Classifiers have the number
of policers encoded in the ALE_STATUS register.

Use that and show the number of Policers in the ALE info message.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ale.c | 25 +++++++++++++++++++------
 drivers/net/ethernet/ti/cpsw_ale.h |  3 +++
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 979f741a231d..9e45470b4eb9 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -103,7 +103,7 @@ struct cpsw_ale_dev_id {
 #define ALE_UCAST_TOUCHED		3
 
 #define ALE_TABLE_SIZE_MULTIPLIER	1024
-#define ALE_STATUS_SIZE_MASK		0x1f
+#define ALE_POLICER_SIZE_MULTIPLIER	8
 
 static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits)
 {
@@ -1303,6 +1303,9 @@ static const struct reg_field ale_fields_cpsw_nu[] = {
 	/* CPSW_ALE_IDVER_REG */
 	[MINOR_VER]	= REG_FIELD(ALE_IDVER, 0, 7),
 	[MAJOR_VER]	= REG_FIELD(ALE_IDVER, 8, 10),
+	/* CPSW_ALE_STATUS_REG */
+	[ALE_ENTRIES]	= REG_FIELD(ALE_STATUS, 0, 7),
+	[ALE_POLICERS]	= REG_FIELD(ALE_STATUS, 8, 15),
 };
 
 static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = {
@@ -1402,8 +1405,8 @@ static int cpsw_ale_regfield_init(struct cpsw_ale *ale)
 
 struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 {
+	u32 ale_entries, rev_major, rev_minor, policers;
 	const struct cpsw_ale_dev_id *ale_dev_id;
-	u32 ale_entries, rev_major, rev_minor;
 	struct cpsw_ale *ale;
 	int ret;
 
@@ -1447,9 +1450,7 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 
 	if (ale->features & CPSW_ALE_F_STATUS_REG &&
 	    !ale->params.ale_entries) {
-		ale_entries =
-			readl_relaxed(ale->params.ale_regs + ALE_STATUS) &
-			ALE_STATUS_SIZE_MASK;
+		regmap_field_read(ale->fields[ALE_ENTRIES], &ale_entries);
 		/* ALE available on newer NetCP switches has introduced
 		 * a register, ALE_STATUS, to indicate the size of ALE
 		 * table which shows the size as a multiple of 1024 entries.
@@ -1463,8 +1464,20 @@ struct cpsw_ale *cpsw_ale_create(struct cpsw_ale_params *params)
 		ale_entries *= ALE_TABLE_SIZE_MULTIPLIER;
 		ale->params.ale_entries = ale_entries;
 	}
+
+	if (ale->features & CPSW_ALE_F_STATUS_REG &&
+	    !ale->params.num_policers) {
+		regmap_field_read(ale->fields[ALE_POLICERS], &policers);
+		if (!policers)
+			return ERR_PTR(-EINVAL);
+
+		policers *= ALE_POLICER_SIZE_MULTIPLIER;
+		ale->params.num_policers = policers;
+	}
+
 	dev_info(ale->params.dev,
-		 "ALE Table size %ld\n", ale->params.ale_entries);
+		 "ALE Table size %ld, Policers %ld\n", ale->params.ale_entries,
+		 ale->params.num_policers);
 
 	/* set default bits for existing h/w */
 	ale->port_mask_bits = ale->params.ale_ports;
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index 58d377dd7496..e12bb2caf016 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -15,6 +15,7 @@ struct cpsw_ale_params {
 	void __iomem		*ale_regs;
 	unsigned long		ale_ageout;	/* in secs */
 	unsigned long		ale_entries;
+	unsigned long		num_policers;
 	unsigned long		ale_ports;
 	/* NU Switch has specific handling as number of bits in ALE entries
 	 * are different than other versions of ALE. Also there are specific
@@ -33,6 +34,8 @@ struct regmap;
 enum ale_fields {
 	MINOR_VER,
 	MAJOR_VER,
+	ALE_ENTRIES,
+	ALE_POLICERS,
 	/* terminator */
 	ALE_FIELDS_MAX,
 };
-- 
cgit v1.3-3-g829e


From eb41dd76abce6a13bd7ad9c779dd560136caf60a Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Tue, 10 Sep 2024 12:24:01 +0300
Subject: net: ethernet: ti: cpsw_ale: add Policer and Thread control register
 fields

Adds regfileds for Policer registers and Thread mapping/control registers.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ale.c | 86 ++++++++++++++++++++++++++++++++++++++
 drivers/net/ethernet/ti/cpsw_ale.h | 41 ++++++++++++++++++
 2 files changed, 127 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index 9e45470b4eb9..aafe1210de52 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -46,6 +46,24 @@
 #define ALE_UNKNOWNVLAN_FORCE_UNTAG_EGRESS	0x9C
 #define ALE_VLAN_MASK_MUX(reg)			(0xc0 + (0x4 * (reg)))
 
+#define ALE_POLICER_PORT_OUI		0x100
+#define ALE_POLICER_DA_SA		0x104
+#define ALE_POLICER_VLAN		0x108
+#define ALE_POLICER_ETHERTYPE_IPSA	0x10c
+#define ALE_POLICER_IPDA		0x110
+#define ALE_POLICER_PIR			0x118
+#define ALE_POLICER_CIR			0x11c
+#define ALE_POLICER_TBL_CTL		0x120
+#define ALE_POLICER_CTL			0x124
+#define ALE_POLICER_TEST_CTL		0x128
+#define ALE_POLICER_HIT_STATUS		0x12c
+#define ALE_THREAD_DEF			0x134
+#define ALE_THREAD_CTL			0x138
+#define ALE_THREAD_VAL			0x13c
+
+#define ALE_POLICER_TBL_WRITE_ENABLE	BIT(31)
+#define ALE_POLICER_TBL_INDEX_MASK	GENMASK(4, 0)
+
 #define AM65_CPSW_ALE_THREAD_DEF_REG 0x134
 
 /* ALE_AGING_TIMER */
@@ -1306,6 +1324,74 @@ static const struct reg_field ale_fields_cpsw_nu[] = {
 	/* CPSW_ALE_STATUS_REG */
 	[ALE_ENTRIES]	= REG_FIELD(ALE_STATUS, 0, 7),
 	[ALE_POLICERS]	= REG_FIELD(ALE_STATUS, 8, 15),
+	/* CPSW_ALE_POLICER_PORT_OUI_REG */
+	[POL_PORT_MEN]	= REG_FIELD(ALE_POLICER_PORT_OUI, 31, 31),
+	[POL_TRUNK_ID]	= REG_FIELD(ALE_POLICER_PORT_OUI, 30, 30),
+	[POL_PORT_NUM]	= REG_FIELD(ALE_POLICER_PORT_OUI, 25, 25),
+	[POL_PRI_MEN]	= REG_FIELD(ALE_POLICER_PORT_OUI, 19, 19),
+	[POL_PRI_VAL]	= REG_FIELD(ALE_POLICER_PORT_OUI, 16, 18),
+	[POL_OUI_MEN]	= REG_FIELD(ALE_POLICER_PORT_OUI, 15, 15),
+	[POL_OUI_INDEX]	= REG_FIELD(ALE_POLICER_PORT_OUI, 0, 5),
+
+	/* CPSW_ALE_POLICER_DA_SA_REG */
+	[POL_DST_MEN]	= REG_FIELD(ALE_POLICER_DA_SA, 31, 31),
+	[POL_DST_INDEX]	= REG_FIELD(ALE_POLICER_DA_SA, 16, 21),
+	[POL_SRC_MEN]	= REG_FIELD(ALE_POLICER_DA_SA, 15, 15),
+	[POL_SRC_INDEX]	= REG_FIELD(ALE_POLICER_DA_SA, 0, 5),
+
+	/* CPSW_ALE_POLICER_VLAN_REG */
+	[POL_OVLAN_MEN]		= REG_FIELD(ALE_POLICER_VLAN, 31, 31),
+	[POL_OVLAN_INDEX]	= REG_FIELD(ALE_POLICER_VLAN, 16, 21),
+	[POL_IVLAN_MEN]		= REG_FIELD(ALE_POLICER_VLAN, 15, 15),
+	[POL_IVLAN_INDEX]	= REG_FIELD(ALE_POLICER_VLAN, 0, 5),
+
+	/* CPSW_ALE_POLICER_ETHERTYPE_IPSA_REG */
+	[POL_ETHERTYPE_MEN]	= REG_FIELD(ALE_POLICER_ETHERTYPE_IPSA, 31, 31),
+	[POL_ETHERTYPE_INDEX]	= REG_FIELD(ALE_POLICER_ETHERTYPE_IPSA, 16, 21),
+	[POL_IPSRC_MEN]		= REG_FIELD(ALE_POLICER_ETHERTYPE_IPSA, 15, 15),
+	[POL_IPSRC_INDEX]	= REG_FIELD(ALE_POLICER_ETHERTYPE_IPSA, 0, 5),
+
+	/* CPSW_ALE_POLICER_IPDA_REG */
+	[POL_IPDST_MEN]		= REG_FIELD(ALE_POLICER_IPDA, 31, 31),
+	[POL_IPDST_INDEX]	= REG_FIELD(ALE_POLICER_IPDA, 16, 21),
+
+	/* CPSW_ALE_POLICER_TBL_CTL_REG */
+	/**
+	 * REG_FIELDS not defined for this as fields cannot be correctly
+	 * used independently
+	 */
+
+	/* CPSW_ALE_POLICER_CTL_REG */
+	[POL_EN]		= REG_FIELD(ALE_POLICER_CTL, 31, 31),
+	[POL_RED_DROP_EN]	= REG_FIELD(ALE_POLICER_CTL, 29, 29),
+	[POL_YELLOW_DROP_EN]	= REG_FIELD(ALE_POLICER_CTL, 28, 28),
+	[POL_YELLOW_THRESH]	= REG_FIELD(ALE_POLICER_CTL, 24, 26),
+	[POL_POL_MATCH_MODE]	= REG_FIELD(ALE_POLICER_CTL, 22, 23),
+	[POL_PRIORITY_THREAD_EN] = REG_FIELD(ALE_POLICER_CTL, 21, 21),
+	[POL_MAC_ONLY_DEF_DIS]	= REG_FIELD(ALE_POLICER_CTL, 20, 20),
+
+	/* CPSW_ALE_POLICER_TEST_CTL_REG */
+	[POL_TEST_CLR]		= REG_FIELD(ALE_POLICER_TEST_CTL, 31, 31),
+	[POL_TEST_CLR_RED]	= REG_FIELD(ALE_POLICER_TEST_CTL, 30, 30),
+	[POL_TEST_CLR_YELLOW]	= REG_FIELD(ALE_POLICER_TEST_CTL, 29, 29),
+	[POL_TEST_CLR_SELECTED]	= REG_FIELD(ALE_POLICER_TEST_CTL, 28, 28),
+	[POL_TEST_ENTRY]	= REG_FIELD(ALE_POLICER_TEST_CTL, 0, 4),
+
+	/* CPSW_ALE_POLICER_HIT_STATUS_REG */
+	[POL_STATUS_HIT]	= REG_FIELD(ALE_POLICER_HIT_STATUS, 31, 31),
+	[POL_STATUS_HIT_RED]	= REG_FIELD(ALE_POLICER_HIT_STATUS, 30, 30),
+	[POL_STATUS_HIT_YELLOW]	= REG_FIELD(ALE_POLICER_HIT_STATUS, 29, 29),
+
+	/* CPSW_ALE_THREAD_DEF_REG */
+	[ALE_DEFAULT_THREAD_EN]		= REG_FIELD(ALE_THREAD_DEF, 15, 15),
+	[ALE_DEFAULT_THREAD_VAL]	= REG_FIELD(ALE_THREAD_DEF, 0, 5),
+
+	/* CPSW_ALE_THREAD_CTL_REG */
+	[ALE_THREAD_CLASS_INDEX] = REG_FIELD(ALE_THREAD_CTL, 0, 4),
+
+	/* CPSW_ALE_THREAD_VAL_REG */
+	[ALE_THREAD_ENABLE]	= REG_FIELD(ALE_THREAD_VAL, 15, 15),
+	[ALE_THREAD_VALUE]	= REG_FIELD(ALE_THREAD_VAL, 0, 5),
 };
 
 static const struct cpsw_ale_dev_id cpsw_ale_id_match[] = {
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index e12bb2caf016..2cb76acc6d16 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -36,6 +36,47 @@ enum ale_fields {
 	MAJOR_VER,
 	ALE_ENTRIES,
 	ALE_POLICERS,
+	POL_PORT_MEN,
+	POL_TRUNK_ID,
+	POL_PORT_NUM,
+	POL_PRI_MEN,
+	POL_PRI_VAL,
+	POL_OUI_MEN,
+	POL_OUI_INDEX,
+	POL_DST_MEN,
+	POL_DST_INDEX,
+	POL_SRC_MEN,
+	POL_SRC_INDEX,
+	POL_OVLAN_MEN,
+	POL_OVLAN_INDEX,
+	POL_IVLAN_MEN,
+	POL_IVLAN_INDEX,
+	POL_ETHERTYPE_MEN,
+	POL_ETHERTYPE_INDEX,
+	POL_IPSRC_MEN,
+	POL_IPSRC_INDEX,
+	POL_IPDST_MEN,
+	POL_IPDST_INDEX,
+	POL_EN,
+	POL_RED_DROP_EN,
+	POL_YELLOW_DROP_EN,
+	POL_YELLOW_THRESH,
+	POL_POL_MATCH_MODE,
+	POL_PRIORITY_THREAD_EN,
+	POL_MAC_ONLY_DEF_DIS,
+	POL_TEST_CLR,
+	POL_TEST_CLR_RED,
+	POL_TEST_CLR_YELLOW,
+	POL_TEST_CLR_SELECTED,
+	POL_TEST_ENTRY,
+	POL_STATUS_HIT,
+	POL_STATUS_HIT_RED,
+	POL_STATUS_HIT_YELLOW,
+	ALE_DEFAULT_THREAD_EN,
+	ALE_DEFAULT_THREAD_VAL,
+	ALE_THREAD_CLASS_INDEX,
+	ALE_THREAD_ENABLE,
+	ALE_THREAD_VALUE,
 	/* terminator */
 	ALE_FIELDS_MAX,
 };
-- 
cgit v1.3-3-g829e


From 961d4187c7029a55cf72d991b40c0b820f398887 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Tue, 10 Sep 2024 12:24:02 +0300
Subject: net: ethernet: ti: cpsw_ale: add policer/classifier helpers and setup
 defaults

The Policer registers in the ALE register space are just shadow registers
and use an index field in the policer table control register to read/write
to the actual Polier registers.
Add helper functions to Read and Write to Policer registers.

Also add a helper function to set the thread value to classifier/policer
mapping. Any packet that first matches the classifier will be sent to the
thread (flow) that is set in the classifier to thread mapping table.
If not set then it goes to the default flow.

Default behaviour is to have 8 classifiers to map 8 DSCP/PCP
priorities to N receive threads (flows). N depends on number of
RX channels enabled for the port.
As per the standard [1] User prioritie 1 (Background) and 2 (Spare) have
lower priority than the user priority 0 (default). User priority 1 being
of the lowest priority.

[1] IEEE802.1D-2004, IEEE Standard for Local and metropolitan area networks
Table G-2 - Traffic type acronyms
Table G-3 - Defining traffic types

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw_ale.c | 94 ++++++++++++++++++++++++++++++++++++++
 drivers/net/ethernet/ti/cpsw_ale.h |  1 +
 2 files changed, 95 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c
index aafe1210de52..0d5d8917c70b 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.c
+++ b/drivers/net/ethernet/ti/cpsw_ale.c
@@ -1627,3 +1627,97 @@ u32 cpsw_ale_get_num_entries(struct cpsw_ale *ale)
 {
 	return ale ? ale->params.ale_entries : 0;
 }
+
+/* Reads the specified policer index into ALE POLICER registers */
+static void cpsw_ale_policer_read_idx(struct cpsw_ale *ale, u32 idx)
+{
+	idx &= ALE_POLICER_TBL_INDEX_MASK;
+	writel_relaxed(idx, ale->params.ale_regs + ALE_POLICER_TBL_CTL);
+}
+
+/* Writes the ALE POLICER registers into the specified policer index */
+static void cpsw_ale_policer_write_idx(struct cpsw_ale *ale, u32 idx)
+{
+	idx &= ALE_POLICER_TBL_INDEX_MASK;
+	idx |= ALE_POLICER_TBL_WRITE_ENABLE;
+	writel_relaxed(idx, ale->params.ale_regs + ALE_POLICER_TBL_CTL);
+}
+
+/* enables/disables the custom thread value for the specified policer index */
+static void cpsw_ale_policer_thread_idx_enable(struct cpsw_ale *ale, u32 idx,
+					       u32 thread_id, bool enable)
+{
+	regmap_field_write(ale->fields[ALE_THREAD_CLASS_INDEX], idx);
+	regmap_field_write(ale->fields[ALE_THREAD_VALUE], thread_id);
+	regmap_field_write(ale->fields[ALE_THREAD_ENABLE], enable ? 1 : 0);
+}
+
+/* Disable all policer entries and thread mappings */
+static void cpsw_ale_policer_reset(struct cpsw_ale *ale)
+{
+	int i;
+
+	for (i = 0; i < ale->params.num_policers ; i++) {
+		cpsw_ale_policer_read_idx(ale, i);
+		regmap_field_write(ale->fields[POL_PORT_MEN], 0);
+		regmap_field_write(ale->fields[POL_PRI_MEN], 0);
+		regmap_field_write(ale->fields[POL_OUI_MEN], 0);
+		regmap_field_write(ale->fields[POL_DST_MEN], 0);
+		regmap_field_write(ale->fields[POL_SRC_MEN], 0);
+		regmap_field_write(ale->fields[POL_OVLAN_MEN], 0);
+		regmap_field_write(ale->fields[POL_IVLAN_MEN], 0);
+		regmap_field_write(ale->fields[POL_ETHERTYPE_MEN], 0);
+		regmap_field_write(ale->fields[POL_IPSRC_MEN], 0);
+		regmap_field_write(ale->fields[POL_IPDST_MEN], 0);
+		regmap_field_write(ale->fields[POL_EN], 0);
+		regmap_field_write(ale->fields[POL_RED_DROP_EN], 0);
+		regmap_field_write(ale->fields[POL_YELLOW_DROP_EN], 0);
+		regmap_field_write(ale->fields[POL_PRIORITY_THREAD_EN], 0);
+
+		cpsw_ale_policer_thread_idx_enable(ale, i, 0, 0);
+	}
+}
+
+/* Default classifier is to map 8 user priorities to N receive channels */
+void cpsw_ale_classifier_setup_default(struct cpsw_ale *ale, int num_rx_ch)
+{
+	int pri, idx;
+	/* IEEE802.1D-2004, Standard for Local and metropolitan area networks
+	 *    Table G-2 - Traffic type acronyms
+	 *    Table G-3 - Defining traffic types
+	 * User priority values 1 and 2 effectively communicate a lower
+	 * priority than 0. In the below table 0 is assigned to higher priority
+	 * thread than 1 and 2 wherever possible.
+	 * The below table maps which thread the user priority needs to be
+	 * sent to for a given number of threads (RX channels). Upper threads
+	 * have higher priority.
+	 * e.g. if number of threads is 8 then user priority 0 will map to
+	 * pri_thread_map[8-1][0] i.e. thread 2
+	 */
+	int pri_thread_map[8][8] = {	{ 0, 0, 0, 0, 0, 0, 0, 0, },
+					{ 0, 0, 0, 0, 1, 1, 1, 1, },
+					{ 0, 0, 0, 0, 1, 1, 2, 2, },
+					{ 1, 0, 0, 1, 2, 2, 3, 3, },
+					{ 1, 0, 0, 1, 2, 3, 4, 4, },
+					{ 1, 0, 0, 2, 3, 4, 5, 5, },
+					{ 1, 0, 0, 2, 3, 4, 5, 6, },
+					{ 2, 0, 1, 3, 4, 5, 6, 7, } };
+
+	cpsw_ale_policer_reset(ale);
+
+	/* use first 8 classifiers to map 8 (DSCP/PCP) priorities to channels */
+	for (pri = 0; pri < 8; pri++) {
+		idx = pri;
+
+		/* Classifier 'idx' match on priority 'pri' */
+		cpsw_ale_policer_read_idx(ale, idx);
+		regmap_field_write(ale->fields[POL_PRI_VAL], pri);
+		regmap_field_write(ale->fields[POL_PRI_MEN], 1);
+		cpsw_ale_policer_write_idx(ale, idx);
+
+		/* Map Classifier 'idx' to thread provided by the map */
+		cpsw_ale_policer_thread_idx_enable(ale, idx,
+						   pri_thread_map[num_rx_ch - 1][pri],
+						   1);
+	}
+}
diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h
index 2cb76acc6d16..1e4e9a3dd234 100644
--- a/drivers/net/ethernet/ti/cpsw_ale.h
+++ b/drivers/net/ethernet/ti/cpsw_ale.h
@@ -193,5 +193,6 @@ int cpsw_ale_vlan_add_modify(struct cpsw_ale *ale, u16 vid, int port_mask,
 int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask);
 void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask,
 			      bool add);
+void cpsw_ale_classifier_setup_default(struct cpsw_ale *ale, int num_rx_ch);
 
 #endif
-- 
cgit v1.3-3-g829e


From b7468c0fe148f9f627921357f8cb97690c19d480 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Tue, 10 Sep 2024 12:24:03 +0300
Subject: net: ethernet: ti: am65-cpsw: setup priority to flow mapping

Now that we support multiple RX queues, enable default priority
to flow mapping so that higher priority packets come on higher
channels (flows).

The Classifier checks for PCP/DSCP priority in the packet and
routes them to the appropriate flow.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 76e62351b30b..cbe99017cbfa 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2500,6 +2500,9 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 		}
 	}
 
+	/* setup classifier to route priorities to flows */
+	cpsw_ale_classifier_setup_default(common->ale, common->rx_ch_num_flows);
+
 err:
 	i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common);
 	if (i) {
-- 
cgit v1.3-3-g829e


From 26d7460222a0be34ff61a92a1fcc4469797ad937 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Fri, 13 Sep 2024 06:07:45 +0000
Subject: memory-provider: disable building dmabuf mp on !CONFIG_PAGE_POOL

When CONFIG_TRACEPOINTS=y but CONFIG_PAGE_POOL=n, we end up with this
build failure that is reported by the 0-day bot:

ld: vmlinux.o: in function `mp_dmabuf_devmem_alloc_netmems':
>> (.text+0xc37286): undefined reference to `__tracepoint_page_pool_state_hold'
>> ld: (.text+0xc3729a): undefined reference to `__SCT__tp_func_page_pool_state_hold'
>> ld: vmlinux.o:(__jump_table+0x10c48): undefined reference to `__tracepoint_page_pool_state_hold'
>> ld: vmlinux.o:(.static_call_sites+0xb824): undefined reference to `__SCK__tp_func_page_pool_state_hold'

The root cause is that in this configuration, traces are enabled but the
page_pool specific trace_page_pool_state_hold is not registered.

There is no reason to build the dmabuf memory provider when
CONFIG_PAGE_POOL is not present, as it's really a provider to the
page_pool.

In fact the whole NET_DEVMEM is RX path-only at the moment, so we can
make the entire config dependent on the PAGE_POOL.

Note that this may need to be revisited after/while devmem TX is
added,  as devmem TX likely does not need CONFIG_PAGE_POOL. For now this
build fix is sufficient.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202409131239.ysHQh4Tv-lkp@intel.com/
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Simon Horman <horms@kernel.org> # build-tested
Link: https://patch.msgid.link/20240913060746.2574191-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/Kconfig b/net/Kconfig
index 7574b066d7cd..a629f92dc86b 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -70,6 +70,7 @@ config NET_DEVMEM
 	def_bool y
 	depends on DMA_SHARED_BUFFER
 	depends on GENERIC_ALLOCATOR
+	depends on PAGE_POOL
 
 menu "Networking options"
 
-- 
cgit v1.3-3-g829e


From 4144a1059b47e821c82c3c82eb23a4c7312dce3a Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 11 Sep 2024 21:10:19 +0200
Subject: xsk: fix batch alloc API on non-coherent systems

In cases when synchronizing DMA operations is necessary,
xsk_buff_alloc_batch() returns a single buffer instead of the requested
count. This puts the pressure on drivers that use batch API as they have
to check for this corner case on their side and take care of allocations
by themselves, which feels counter productive. Let us improve the core
by looping over xp_alloc() @max times when slow path needs to be taken.

Another issue with current interface, as spotted and fixed by Dries, was
that when driver called xsk_buff_alloc_batch() with @max == 0, for slow
path case it still allocated and returned a single buffer, which should
not happen. By introducing the logic from first paragraph we kill two
birds with one stone and address this problem as well.

Fixes: 47e4075df300 ("xsk: Batched buffer allocation for the pool")
Reported-and-tested-by: Dries De Winter <ddewinter@synamedia.com>
Co-developed-by: Dries De Winter <ddewinter@synamedia.com>
Signed-off-by: Dries De Winter <ddewinter@synamedia.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Link: https://patch.msgid.link/20240911191019.296480-1-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xdp/xsk_buff_pool.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index c0e0204b9630..b0f24ebd05f0 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -623,20 +623,31 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3
 	return nb_entries;
 }
 
-u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+static u32 xp_alloc_slow(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+			 u32 max)
 {
-	u32 nb_entries1 = 0, nb_entries2;
+	int i;
 
-	if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) {
+	for (i = 0; i < max; i++) {
 		struct xdp_buff *buff;
 
-		/* Slow path */
 		buff = xp_alloc(pool);
-		if (buff)
-			*xdp = buff;
-		return !!buff;
+		if (unlikely(!buff))
+			return i;
+		*xdp = buff;
+		xdp++;
 	}
 
+	return max;
+}
+
+u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
+{
+	u32 nb_entries1 = 0, nb_entries2;
+
+	if (unlikely(pool->dev && dma_dev_need_sync(pool->dev)))
+		return xp_alloc_slow(pool, xdp, max);
+
 	if (unlikely(pool->free_list_cnt)) {
 		nb_entries1 = xp_alloc_reused(pool, xdp, max);
 		if (nb_entries1 == max)
-- 
cgit v1.3-3-g829e


From 157f29152b61ca41809dd7ead29f5733adeced19 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 12 Sep 2024 08:56:19 -0700
Subject: netkit: Assign missing bpf_net_context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During the introduction of struct bpf_net_context handling for
XDP-redirect, the netkit driver has been missed, which also requires it
because NETKIT_REDIRECT invokes skb_do_redirect() which is accessing the
per-CPU variables. Otherwise we see the following crash:

	BUG: kernel NULL pointer dereference, address: 0000000000000038
	bpf_redirect()
	netkit_xmit()
	dev_hard_start_xmit()

Set the bpf_net_context before invoking netkit_xmit() program within the
netkit driver.

Fixes: 401cb7dae813 ("net: Reference bpf_redirect_info via task_struct on PREEMPT_RT.")
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20240912155620.1334587-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netkit.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 16789cd446e9..3f4187102e77 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -65,6 +65,7 @@ static struct netkit *netkit_priv(const struct net_device *dev)
 
 static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct netkit *nk = netkit_priv(dev);
 	enum netkit_action ret = READ_ONCE(nk->policy);
 	netdev_tx_t ret_dev = NET_XMIT_SUCCESS;
@@ -72,6 +73,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_device *peer;
 	int len = skb->len;
 
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 	rcu_read_lock();
 	peer = rcu_dereference(nk->peer);
 	if (unlikely(!peer || !(peer->flags & IFF_UP) ||
@@ -110,6 +112,7 @@ drop_stats:
 		break;
 	}
 	rcu_read_unlock();
+	bpf_net_ctx_clear(bpf_net_ctx);
 	return ret_dev;
 }
 
-- 
cgit v1.3-3-g829e


From 7fd551a87ba427fee2df8af4d83f4b7c220cc9dd Mon Sep 17 00:00:00 2001
From: Qianqiang Liu <qianqiang.liu@163.com>
Date: Fri, 13 Sep 2024 09:47:32 +0800
Subject: net: ag71xx: remove dead code path

The "err" is always zero, so the following branch can never be executed:
if (err) {
	ndev->stats.rx_dropped++;
	kfree_skb(skb);
}
Therefore, the "if" statement can be removed.

Use "ndev->stats.rx_errors" to count "napi_build_skb()" failure

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://lore.kernel.org/20240911135828.378317-1-usama.anjum@collabora.com
Signed-off-by: Qianqiang Liu <qianqiang.liu@163.com>
Link: https://patch.msgid.link/20240913014731.149739-1-qianqiang.liu@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/ag71xx.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 96a6189cc31e..9586b6894f7e 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -1616,7 +1616,6 @@ static int ag71xx_rx_packets(struct ag71xx *ag, int limit)
 		unsigned int i = ring->curr & ring_mask;
 		struct ag71xx_desc *desc = ag71xx_ring_desc(ring, i);
 		int pktlen;
-		int err = 0;
 
 		if (ag71xx_desc_empty(desc))
 			break;
@@ -1639,6 +1638,7 @@ static int ag71xx_rx_packets(struct ag71xx *ag, int limit)
 
 		skb = napi_build_skb(ring->buf[i].rx.rx_buf, ag71xx_buffer_size(ag));
 		if (!skb) {
+			ndev->stats.rx_errors++;
 			skb_free_frag(ring->buf[i].rx.rx_buf);
 			goto next;
 		}
@@ -1646,14 +1646,9 @@ static int ag71xx_rx_packets(struct ag71xx *ag, int limit)
 		skb_reserve(skb, offset);
 		skb_put(skb, pktlen);
 
-		if (err) {
-			ndev->stats.rx_dropped++;
-			kfree_skb(skb);
-		} else {
-			skb->dev = ndev;
-			skb->ip_summed = CHECKSUM_NONE;
-			list_add_tail(&skb->list, &rx_list);
-		}
+		skb->dev = ndev;
+		skb->ip_summed = CHECKSUM_NONE;
+		list_add_tail(&skb->list, &rx_list);
 
 next:
 		ring->buf[i].rx.rx_buf = NULL;
-- 
cgit v1.3-3-g829e


From b9c7ac4fe22c608acf6153a3329df2b6b6cd416c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 11 Sep 2024 15:51:11 +0200
Subject: r8169: disable ALDPS per default for RTL8125

En-Wei reported that traffic breaks if cable is unplugged for more
than 3s and then re-plugged. This was supposed to be fixed by
621735f59064 ("r8169: fix rare issue with broken rx after link-down on
RTL8125"). But apparently this didn't fix the issue for everybody.
The 3s threshold rang a bell, as this is the delay after which ALDPS
kicks in. And indeed disabling ALDPS fixes the issue for this user.
Maybe this fixes the issue in general. In a follow-up step we could
remove the first fix attempt and see whether anybody complains.

Fixes: f1bce4ad2f1c ("r8169: add support for RTL8125")
Tested-by: En-Wei WU <en-wei.wu@canonical.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/778b9d86-05c4-4856-be59-cde4487b9e52@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_phy_config.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
index 1f74317beb88..e1e5d9672ae4 100644
--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
+++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
@@ -1060,6 +1060,7 @@ static void rtl8125a_2_hw_phy_config(struct rtl8169_private *tp,
 	phy_modify_paged(phydev, 0xa86, 0x15, 0x0001, 0x0000);
 	rtl8168g_enable_gphy_10m(phydev);
 
+	rtl8168g_disable_aldps(phydev);
 	rtl8125a_config_eee_phy(phydev);
 }
 
@@ -1099,6 +1100,7 @@ static void rtl8125b_hw_phy_config(struct rtl8169_private *tp,
 	phy_modify_paged(phydev, 0xbf8, 0x12, 0xe000, 0xa000);
 
 	rtl8125_legacy_force_mode(phydev);
+	rtl8168g_disable_aldps(phydev);
 	rtl8125b_config_eee_phy(phydev);
 }
 
-- 
cgit v1.3-3-g829e


From 2c84b0aa28b9e73e8c4b4ce038269469434ae372 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Wed, 11 Sep 2024 19:45:57 +0200
Subject: net: ipv6: rpl_iptunnel: Fix memory leak in rpl_input

Free the skb before returning from rpl_input when skb_cow_head() fails.
Use a "drop" label and goto instructions.

Fixes: a7a29f9c361f ("net: ipv6: add rpl sr tunnel")
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240911174557.11536-1-justin.iurman@uliege.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/rpl_iptunnel.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 2c83b7586422..db3c19a42e1c 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -263,10 +263,8 @@ static int rpl_input(struct sk_buff *skb)
 	rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
 
 	err = rpl_do_srh(skb, rlwt);
-	if (unlikely(err)) {
-		kfree_skb(skb);
-		return err;
-	}
+	if (unlikely(err))
+		goto drop;
 
 	local_bh_disable();
 	dst = dst_cache_get(&rlwt->cache);
@@ -286,9 +284,13 @@ static int rpl_input(struct sk_buff *skb)
 
 	err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
 	if (unlikely(err))
-		return err;
+		goto drop;
 
 	return dst_input(skb);
+
+drop:
+	kfree_skb(skb);
+	return err;
 }
 
 static int nla_put_rpl_srh(struct sk_buff *skb, int attrtype,
-- 
cgit v1.3-3-g829e


From 9297886f9fcd20176a2eb68961c79f4f0b99e117 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Thu, 12 Sep 2024 11:05:50 +0200
Subject: Documentation: networking: Fix missing PSE documentation and grammar
 issues

Fix a missing end of phrase in the documentation. It describes the
ETHTOOL_A_C33_PSE_ACTUAL_PW attribute, which was not fully explained.

Also, fix grammar issues by using simple present tense instead of
present continuous.

Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240912090550.743174-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ethtool-netlink.rst | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index ba90457b8b2d..295563e91082 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1768,7 +1768,7 @@ Kernel response contents:
 When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies
 the operational state of the PoDL PSE functions.  The operational state of the
 PSE function can be changed using the ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL``
-action. This option is corresponding to ``IEEE 802.3-2018`` 30.15.1.1.2
+action. This attribute corresponds to ``IEEE 802.3-2018`` 30.15.1.1.2
 aPoDLPSEAdminState. Possible values are:
 
 .. kernel-doc:: include/uapi/linux/ethtool.h
@@ -1782,8 +1782,8 @@ The same goes for ``ETHTOOL_A_C33_PSE_ADMIN_STATE`` implementing
 
 When set, the optional ``ETHTOOL_A_PODL_PSE_PW_D_STATUS`` attribute identifies
 the power detection status of the PoDL PSE.  The status depend on internal PSE
-state machine and automatic PD classification support. This option is
-corresponding to ``IEEE 802.3-2018`` 30.15.1.1.3 aPoDLPSEPowerDetectionStatus.
+state machine and automatic PD classification support. This attribute
+corresponds to ``IEEE 802.3-2018`` 30.15.1.1.3 aPoDLPSEPowerDetectionStatus.
 Possible values are:
 
 .. kernel-doc:: include/uapi/linux/ethtool.h
@@ -1797,12 +1797,13 @@ The same goes for ``ETHTOOL_A_C33_PSE_ADMIN_PW_D_STATUS`` implementing
 
 When set, the optional ``ETHTOOL_A_C33_PSE_PW_CLASS`` attribute identifies
 the power class of the C33 PSE. It depends on the class negotiated between
-the PSE and the PD. This option is corresponding to ``IEEE 802.3-2022``
+the PSE and the PD. This attribute corresponds to ``IEEE 802.3-2022``
 30.9.1.1.8 aPSEPowerClassification.
 
 When set, the optional ``ETHTOOL_A_C33_PSE_ACTUAL_PW`` attribute identifies
-This option is corresponding to ``IEEE 802.3-2022`` 30.9.1.1.23 aPSEActualPower.
-Actual power is reported in mW.
+the actual power drawn by the C33 PSE. This attribute corresponds to
+``IEEE 802.3-2022`` 30.9.1.1.23 aPSEActualPower. Actual power is reported
+in mW.
 
 When set, the optional ``ETHTOOL_A_C33_PSE_EXT_STATE`` attribute identifies
 the extended error state of the C33 PSE. Possible values are:
@@ -1851,7 +1852,7 @@ Request contents:
   ======================================  ======  =============================
 
 When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_CONTROL`` attribute is used
-to control PoDL PSE Admin functions. This option is implementing
+to control PoDL PSE Admin functions. This option implements
 ``IEEE 802.3-2018`` 30.15.1.2.1 acPoDLPSEAdminControl. See
 ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` for supported values.
 
-- 
cgit v1.3-3-g829e


From 9f3e7f11f21ac83cd99428390165177d4953b005 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Thu, 12 Sep 2024 10:49:22 -0700
Subject: fbnic: Set napi irq value after calling netif_napi_add

The driver calls netif_napi_set_irq() and then calls netif_napi_add(),
which calls netif_napi_add_weight(). At the end of
netif_napi_add_weight() is a call to netif_napi_set_irq(napi, -1), which
clears the previously set napi->irq value. Fix this by calling
netif_napi_set_irq() after calling netif_napi_add().

This was found when reviewing another patch and I have no way to test
this, but the fix seemed relatively straight forward.

Fixes: bc6107771bb4 ("eth: fbnic: Allocate a netdevice and napi vectors with queues")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20240912174922.10550-1-brett.creeley@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 0ed4c9fff5d8..72f88ae7815f 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -1012,14 +1012,14 @@ static int fbnic_alloc_napi_vector(struct fbnic_dev *fbd, struct fbnic_net *fbn,
 	nv->fbd = fbd;
 	nv->v_idx = v_idx;
 
-	/* Record IRQ to NAPI struct */
-	netif_napi_set_irq(&nv->napi,
-			   pci_irq_vector(to_pci_dev(fbd->dev), nv->v_idx));
-
 	/* Tie napi to netdev */
 	list_add(&nv->napis, &fbn->napis);
 	netif_napi_add(fbn->netdev, &nv->napi, fbnic_poll);
 
+	/* Record IRQ to NAPI struct */
+	netif_napi_set_irq(&nv->napi,
+			   pci_irq_vector(to_pci_dev(fbd->dev), nv->v_idx));
+
 	/* Tie nv back to PCIe dev */
 	nv->dev = fbd->dev;
 
-- 
cgit v1.3-3-g829e


From 9c699a8f3b273c62f7b364ff999e873501a1e834 Mon Sep 17 00:00:00 2001
From: Martyn Welch <martyn.welch@collabora.com>
Date: Thu, 12 Sep 2024 18:37:40 +0100
Subject: net: enetc: Replace ifdef with IS_ENABLED

The enetc driver uses ifdefs when checking whether
CONFIG_FSL_ENETC_PTP_CLOCK is enabled in a number of places. This works
if the driver is built-in but fails if the driver is available as a
kernel module. Replace the instances of ifdef with use of the IS_ENABLED
macro, that will evaluate as true when this feature is built as a kernel
module and follows the kernel's coding style.

Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: Martyn Welch <martyn.welch@collabora.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240912173742.484549-1-martyn.welch@collabora.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c       | 22 +++++++++-------------
 drivers/net/ethernet/freescale/enetc/enetc.h       |  9 +++------
 .../net/ethernet/freescale/enetc/enetc_ethtool.c   | 12 ++++++++----
 3 files changed, 20 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index f04f42ea60c0..032d8eadd003 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -977,7 +977,6 @@ static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt)
 	return j;
 }
 
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
 static void enetc_get_rx_tstamp(struct net_device *ndev,
 				union enetc_rx_bd *rxbd,
 				struct sk_buff *skb)
@@ -1001,7 +1000,6 @@ static void enetc_get_rx_tstamp(struct net_device *ndev,
 		shhwtstamps->hwtstamp = ns_to_ktime(tstamp);
 	}
 }
-#endif
 
 static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 			       union enetc_rx_bd *rxbd, struct sk_buff *skb)
@@ -1041,10 +1039,9 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring,
 		__vlan_hwaccel_put_tag(skb, tpid, le16_to_cpu(rxbd->r.vlan_opt));
 	}
 
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
-	if (priv->active_offloads & ENETC_F_RX_TSTAMP)
+	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK) &&
+	    (priv->active_offloads & ENETC_F_RX_TSTAMP))
 		enetc_get_rx_tstamp(rx_ring->ndev, rxbd, skb);
-#endif
 }
 
 /* This gets called during the non-XDP NAPI poll cycle as well as on XDP_PASS,
@@ -2881,7 +2878,6 @@ void enetc_set_features(struct net_device *ndev, netdev_features_t features)
 }
 EXPORT_SYMBOL_GPL(enetc_set_features);
 
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
 static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -2950,17 +2946,17 @@ static int enetc_hwtstamp_get(struct net_device *ndev, struct ifreq *ifr)
 	return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
 	       -EFAULT : 0;
 }
-#endif
 
 int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
 {
 	struct enetc_ndev_priv *priv = netdev_priv(ndev);
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
-	if (cmd == SIOCSHWTSTAMP)
-		return enetc_hwtstamp_set(ndev, rq);
-	if (cmd == SIOCGHWTSTAMP)
-		return enetc_hwtstamp_get(ndev, rq);
-#endif
+
+	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK)) {
+		if (cmd == SIOCSHWTSTAMP)
+			return enetc_hwtstamp_set(ndev, rq);
+		if (cmd == SIOCGHWTSTAMP)
+			return enetc_hwtstamp_get(ndev, rq);
+	}
 
 	if (!priv->phylink)
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
index a9c2ff22431c..97524dfa234c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -184,10 +184,9 @@ static inline union enetc_rx_bd *enetc_rxbd(struct enetc_bdr *rx_ring, int i)
 {
 	int hw_idx = i;
 
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
-	if (rx_ring->ext_en)
+	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK) && rx_ring->ext_en)
 		hw_idx = 2 * i;
-#endif
+
 	return &(((union enetc_rx_bd *)rx_ring->bd_base)[hw_idx]);
 }
 
@@ -199,10 +198,8 @@ static inline void enetc_rxbd_next(struct enetc_bdr *rx_ring,
 
 	new_rxbd++;
 
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
-	if (rx_ring->ext_en)
+	if (IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK) && rx_ring->ext_en)
 		new_rxbd++;
-#endif
 
 	if (unlikely(++new_index == rx_ring->bd_count)) {
 		new_rxbd = rx_ring->bd_base;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index 47c478e08d44..2563eb8ac7b6 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -851,7 +851,12 @@ static int enetc_get_ts_info(struct net_device *ndev,
 		symbol_put(enetc_phc_index);
 	}
 
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
+	if (!IS_ENABLED(CONFIG_FSL_ENETC_PTP_CLOCK)) {
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
+
+		return 0;
+	}
+
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
 				SOF_TIMESTAMPING_RAW_HARDWARE |
@@ -860,11 +865,10 @@ static int enetc_get_ts_info(struct net_device *ndev,
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
 			 (1 << HWTSTAMP_TX_ON) |
 			 (1 << HWTSTAMP_TX_ONESTEP_SYNC);
+
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);
-#else
-	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE;
-#endif
+
 	return 0;
 }
 
-- 
cgit v1.3-3-g829e


From 99655a304e450baaae6b396cb942b9e47659d644 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Thu, 12 Sep 2024 19:01:20 +0800
Subject: net: tipc: avoid possible garbage value

Clang static checker (scan-build) warning:
net/tipc/bcast.c:305:4:
The expression is an uninitialized value. The computed value will also
be garbage [core.uninitialized.Assign]
  305 |                         (*cong_link_cnt)++;
      |                         ^~~~~~~~~~~~~~~~~~

tipc_rcast_xmit() will increase cong_link_cnt's value, but cong_link_cnt
is uninitialized. Although it won't really cause a problem, it's better
to fix it.

Fixes: dca4a17d24ee ("tipc: fix potential hanging after b/rcast changing")
Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Justin Stitt <justinstitt@google.com>
Link: https://patch.msgid.link/20240912110119.2025503-1-suhui@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/bcast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 593846d25214..114fef65f92e 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -320,8 +320,8 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
 {
 	struct tipc_msg *hdr, *_hdr;
 	struct sk_buff_head tmpq;
+	u16 cong_link_cnt = 0;
 	struct sk_buff *_skb;
-	u16 cong_link_cnt;
 	int rc = 0;
 
 	/* Is a cluster supporting with new capabilities ? */
-- 
cgit v1.3-3-g829e


From 04ccecfa959d3b9ae7348780d8e379c6486176ac Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 13 Sep 2024 08:31:47 +0000
Subject: ipv6: avoid possible NULL deref in rt6_uncached_list_flush_dev()

Blamed commit accidentally removed a check for rt->rt6i_idev being NULL,
as spotted by syzbot:

Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
CPU: 1 UID: 0 PID: 10998 Comm: syz-executor Not tainted 6.11.0-rc6-syzkaller-00208-g625403177711 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024
 RIP: 0010:rt6_uncached_list_flush_dev net/ipv6/route.c:177 [inline]
 RIP: 0010:rt6_disable_ip+0x33e/0x7e0 net/ipv6/route.c:4914
Code: 41 80 3c 04 00 74 0a e8 90 d0 9b f7 48 8b 7c 24 08 48 8b 07 48 89 44 24 10 4c 89 f0 48 c1 e8 03 48 b9 00 00 00 00 00 fc ff df <80> 3c 08 00 74 08 4c 89 f7 e8 64 d0 9b f7 48 8b 44 24 18 49 39 06
RSP: 0018:ffffc900047374e0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 1ffff1100fdf8f33 RCX: dffffc0000000000
RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff88807efc78c0
RBP: ffffc900047375d0 R08: 0000000000000003 R09: fffff520008e6e8c
R10: dffffc0000000000 R11: fffff520008e6e8c R12: 1ffff1100fdf8f18
R13: ffff88807efc7998 R14: 0000000000000000 R15: ffff88807efc7930
FS:  0000000000000000(0000) GS:ffff8880b8900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020002a80 CR3: 0000000022f62000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
  addrconf_ifdown+0x15d/0x1bd0 net/ipv6/addrconf.c:3856
 addrconf_notify+0x3cb/0x1020
  notifier_call_chain+0x19f/0x3e0 kernel/notifier.c:93
  call_netdevice_notifiers_extack net/core/dev.c:2032 [inline]
  call_netdevice_notifiers net/core/dev.c:2046 [inline]
  unregister_netdevice_many_notify+0xd81/0x1c40 net/core/dev.c:11352
  unregister_netdevice_many net/core/dev.c:11414 [inline]
  unregister_netdevice_queue+0x303/0x370 net/core/dev.c:11289
  unregister_netdevice include/linux/netdevice.h:3129 [inline]
  __tun_detach+0x6b9/0x1600 drivers/net/tun.c:685
  tun_detach drivers/net/tun.c:701 [inline]
  tun_chr_close+0x108/0x1b0 drivers/net/tun.c:3510
  __fput+0x24a/0x8a0 fs/file_table.c:422
  task_work_run+0x24f/0x310 kernel/task_work.c:228
  exit_task_work include/linux/task_work.h:40 [inline]
  do_exit+0xa2f/0x27f0 kernel/exit.c:882
  do_group_exit+0x207/0x2c0 kernel/exit.c:1031
  __do_sys_exit_group kernel/exit.c:1042 [inline]
  __se_sys_exit_group kernel/exit.c:1040 [inline]
  __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1040
  x64_sys_call+0x2634/0x2640 arch/x86/include/generated/asm/syscalls_64.h:232
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f1acc77def9
Code: Unable to access opcode bytes at 0x7f1acc77decf.
RSP: 002b:00007ffeb26fa738 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f1acc77def9
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000043
RBP: 00007f1acc7dd508 R08: 00007ffeb26f84d7 R09: 0000000000000003
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001
R13: 0000000000000003 R14: 00000000ffffffff R15: 00007ffeb26fa8e0
 </TASK>
Modules linked in:
---[ end trace 0000000000000000 ]---
 RIP: 0010:rt6_uncached_list_flush_dev net/ipv6/route.c:177 [inline]
 RIP: 0010:rt6_disable_ip+0x33e/0x7e0 net/ipv6/route.c:4914
Code: 41 80 3c 04 00 74 0a e8 90 d0 9b f7 48 8b 7c 24 08 48 8b 07 48 89 44 24 10 4c 89 f0 48 c1 e8 03 48 b9 00 00 00 00 00 fc ff df <80> 3c 08 00 74 08 4c 89 f7 e8 64 d0 9b f7 48 8b 44 24 18 49 39 06
RSP: 0018:ffffc900047374e0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 1ffff1100fdf8f33 RCX: dffffc0000000000
RDX: 0000000000000000 RSI: 0000000000000004 RDI: ffff88807efc78c0
RBP: ffffc900047375d0 R08: 0000000000000003 R09: fffff520008e6e8c
R10: dffffc0000000000 R11: fffff520008e6e8c R12: 1ffff1100fdf8f18
R13: ffff88807efc7998 R14: 0000000000000000 R15: ffff88807efc7930
FS:  0000000000000000(0000) GS:ffff8880b8900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020002a80 CR3: 0000000022f62000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes: e332bc67cf5e ("ipv6: Don't call with rt6_uncached_list_flush_dev")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20240913083147.3095442-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 219701caba1e..b4dcd8f3e7ba 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -174,7 +174,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
 			struct net_device *rt_dev = rt->dst.dev;
 			bool handled = false;
 
-			if (rt_idev->dev == dev) {
+			if (rt_idev && rt_idev->dev == dev) {
 				rt->rt6i_idev = in6_dev_get(blackhole_netdev);
 				in6_dev_put(rt_idev);
 				handled = true;
-- 
cgit v1.3-3-g829e


From 6503734916cc751bec825ff314d7cadaa587f2d0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 13 Sep 2024 15:51:46 +0300
Subject: net: macb: Use predefined PCI vendor ID constant

The PCI vendor ID for Cadence is defined in pci_ids.h. Use it.
While at it, move to PCI_VDEVICE() macro and usual pattern for
PCI device ID.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20240913125146.3628751-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_pci.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c
index f66d22de5168..fc4f5aee6ab3 100644
--- a/drivers/net/ethernet/cadence/macb_pci.c
+++ b/drivers/net/ethernet/cadence/macb_pci.c
@@ -19,8 +19,7 @@
 #define PCI_DRIVER_NAME "macb_pci"
 #define PLAT_DRIVER_NAME "macb"
 
-#define CDNS_VENDOR_ID 0x17cd
-#define CDNS_DEVICE_ID 0xe007
+#define PCI_DEVICE_ID_CDNS_MACB 0xe007
 
 #define GEM_PCLK_RATE 50000000
 #define GEM_HCLK_RATE 50000000
@@ -117,7 +116,7 @@ static void macb_remove(struct pci_dev *pdev)
 }
 
 static const struct pci_device_id dev_id_table[] = {
-	{ PCI_DEVICE(CDNS_VENDOR_ID, CDNS_DEVICE_ID), },
+	{ PCI_VDEVICE(CDNS, PCI_DEVICE_ID_CDNS_MACB) },
 	{ 0, }
 };
 
-- 
cgit v1.3-3-g829e


From 716425d6f3fb7354023069042f240eddbc557504 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Tue, 10 Sep 2024 12:10:44 +0300
Subject: net: ethtool: Enhance error messages sent to user space

During the firmware flashing process, notifications are sent to user
space to provide progress updates. When an error occurs, an error
message is sent to indicate what went wrong.

In some cases, appropriate error messages are missing.

Add relevant error messages where applicable, allowing user space to better
understand the issues encountered.

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240910091044.3044568-1-danieller@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/cmis_cdb.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/ethtool/cmis_cdb.c b/net/ethtool/cmis_cdb.c
index 1bb08783b60d..4d5581147952 100644
--- a/net/ethtool/cmis_cdb.c
+++ b/net/ethtool/cmis_cdb.c
@@ -100,7 +100,8 @@ static u8 cmis_cdb_advert_rpl_inst_supported(struct cmis_cdb_advert_rpl *rpl)
 }
 
 static int cmis_cdb_advertisement_get(struct ethtool_cmis_cdb *cdb,
-				      struct net_device *dev)
+				      struct net_device *dev,
+				      struct ethnl_module_fw_flash_ntf_params *ntf_params)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	struct ethtool_module_eeprom page_data = {};
@@ -119,8 +120,12 @@ static int cmis_cdb_advertisement_get(struct ethtool_cmis_cdb *cdb,
 		return err;
 	}
 
-	if (!cmis_cdb_advert_rpl_inst_supported(&rpl))
+	if (!cmis_cdb_advert_rpl_inst_supported(&rpl)) {
+		ethnl_module_fw_flash_ntf_err(dev, ntf_params,
+					      "CDB functionality is not supported",
+					      NULL);
 		return -EOPNOTSUPP;
+	}
 
 	cdb->read_write_len_ext = rpl.read_write_len_ext;
 
@@ -282,7 +287,7 @@ ethtool_cmis_cdb_init(struct net_device *dev,
 		goto err;
 	}
 
-	err = cmis_cdb_advertisement_get(cdb, dev);
+	err = cmis_cdb_advertisement_get(cdb, dev, ntf_params);
 	if (err < 0)
 		goto err;
 
@@ -444,6 +449,9 @@ static void cmis_cdb_status_fail_msg_get(u8 status, char **err_msg)
 	case 0b01000101:
 		*err_msg = "CDB status failed: CdbChkCode error";
 		break;
+	case 0b01000110:
+		*err_msg = "CDB status failed: Password error";
+		break;
 	default:
 		*err_msg = "Unknown failure reason";
 	}
-- 
cgit v1.3-3-g829e


From c951a29f6ba52b86223eb00bbcff43142d59a901 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 11 Sep 2024 12:37:43 +0300
Subject: net: fib_rules: Add DSCP selector attribute

The FIB rule TOS selector is implemented differently between IPv4 and
IPv6. In IPv4 it is used to match on the three "Type of Services" bits
specified in RFC 791, while in IPv6 is it is used to match on the six
DSCP bits specified in RFC 2474.

Add a new FIB rule attribute to allow matching on DSCP. The attribute
will be used to implement a 'dscp' selector in ip-rule with a consistent
behavior between IPv4 and IPv6.

For now, set the type of the attribute to 'NLA_REJECT' so that user
space will not be able to configure it. This restriction will be lifted
once both IPv4 and IPv6 support the new attribute.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240911093748.3662015-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/fib_rules.h | 1 +
 net/core/fib_rules.c           | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 232df14e1287..a6924dd3aff1 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -67,6 +67,7 @@ enum {
 	FRA_IP_PROTO,	/* ip proto */
 	FRA_SPORT_RANGE, /* sport */
 	FRA_DPORT_RANGE, /* dport */
+	FRA_DSCP,	/* dscp */
 	__FRA_MAX
 };
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 5a4eb744758c..df41c05f7234 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -766,7 +766,8 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_PROTOCOL]  = { .type = NLA_U8 },
 	[FRA_IP_PROTO]  = { .type = NLA_U8 },
 	[FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
-	[FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }
+	[FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
+	[FRA_DSCP]	= { .type = NLA_REJECT },
 };
 
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
cgit v1.3-3-g829e


From b9455fef8b1fc662369d982fe97dc66e6c332699 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 11 Sep 2024 12:37:44 +0300
Subject: ipv4: fib_rules: Add DSCP selector support

Implement support for the new DSCP selector that allows IPv4 FIB rules
to match on the entire DSCP field, unlike the existing TOS selector that
only matches on the three lower DSCP bits.

Differentiate between both selectors by adding a new bit in the IPv4 FIB
rule structure (in an existing one byte hole) that is only set when the
'FRA_DSCP' attribute is specified by user space. Reject rules that use
both selectors.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240911093748.3662015-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_rules.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 50 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index c26776b71e97..b07292d50ee7 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -37,6 +37,7 @@ struct fib4_rule {
 	u8			dst_len;
 	u8			src_len;
 	dscp_t			dscp;
+	u8			dscp_full:1;	/* DSCP or TOS selector */
 	__be32			src;
 	__be32			srcmask;
 	__be32			dst;
@@ -186,7 +187,15 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule,
 	    ((daddr ^ r->dst) & r->dstmask))
 		return 0;
 
-	if (r->dscp && !fib_dscp_masked_match(r->dscp, fl4))
+	/* When DSCP selector is used we need to match on the entire DSCP field
+	 * in the flow information structure. When TOS selector is used we need
+	 * to mask the upper three DSCP bits prior to matching to maintain
+	 * legacy behavior.
+	 */
+	if (r->dscp_full && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos))
+		return 0;
+	else if (!r->dscp_full && r->dscp &&
+		 !fib_dscp_masked_match(r->dscp, fl4))
 		return 0;
 
 	if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
@@ -217,6 +226,20 @@ static struct fib_table *fib_empty_table(struct net *net)
 	return NULL;
 }
 
+static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4,
+			     struct netlink_ext_ack *extack)
+{
+	if (rule4->dscp) {
+		NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP");
+		return -EINVAL;
+	}
+
+	rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	rule4->dscp_full = true;
+
+	return 0;
+}
+
 static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 			       struct fib_rule_hdr *frh,
 			       struct nlattr **tb,
@@ -238,6 +261,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	}
 	rule4->dscp = inet_dsfield_to_dscp(frh->tos);
 
+	if (tb[FRA_DSCP] &&
+	    fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0)
+		goto errout;
+
 	/* split local/main if they are not already split */
 	err = fib_unmerge(net);
 	if (err)
@@ -320,9 +347,19 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->dst_len && (rule4->dst_len != frh->dst_len))
 		return 0;
 
-	if (frh->tos && inet_dscp_to_dsfield(rule4->dscp) != frh->tos)
+	if (frh->tos &&
+	    (rule4->dscp_full ||
+	     inet_dscp_to_dsfield(rule4->dscp) != frh->tos))
 		return 0;
 
+	if (tb[FRA_DSCP]) {
+		dscp_t dscp;
+
+		dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2);
+		if (!rule4->dscp_full || rule4->dscp != dscp)
+			return 0;
+	}
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
 		return 0;
@@ -344,7 +381,15 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 
 	frh->dst_len = rule4->dst_len;
 	frh->src_len = rule4->src_len;
-	frh->tos = inet_dscp_to_dsfield(rule4->dscp);
+
+	if (rule4->dscp_full) {
+		frh->tos = 0;
+		if (nla_put_u8(skb, FRA_DSCP,
+			       inet_dscp_to_dsfield(rule4->dscp) >> 2))
+			goto nla_put_failure;
+	} else {
+		frh->tos = inet_dscp_to_dsfield(rule4->dscp);
+	}
 
 	if ((rule4->dst_len &&
 	     nla_put_in_addr(skb, FRA_DST, rule4->dst)) ||
@@ -366,7 +411,8 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
 {
 	return nla_total_size(4) /* dst */
 	       + nla_total_size(4) /* src */
-	       + nla_total_size(4); /* flow */
+	       + nla_total_size(4) /* flow */
+	       + nla_total_size(1); /* dscp */
 }
 
 static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
-- 
cgit v1.3-3-g829e


From 2cf630034e4ebcc52e0b69b776cafd90dc4f3919 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 11 Sep 2024 12:37:45 +0300
Subject: ipv6: fib_rules: Add DSCP selector support

Implement support for the new DSCP selector that allows IPv6 FIB rules
to match on the entire DSCP field. This is done despite the fact that
the above can be achieved using the existing TOS selector, so that user
space program will be able to work with IPv4 and IPv6 rules in the same
way.

Differentiate between both selectors by adding a new bit in the IPv6 FIB
rule structure that is only set when the 'FRA_DSCP' attribute is
specified by user space. Reject rules that use both selectors.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240911093748.3662015-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/fib6_rules.c | 43 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 9e254de7462f..04a9ed5e8310 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -27,6 +27,7 @@ struct fib6_rule {
 	struct rt6key		src;
 	struct rt6key		dst;
 	dscp_t			dscp;
+	u8			dscp_full:1;	/* DSCP or TOS selector */
 };
 
 static bool fib6_rule_matchall(const struct fib_rule *rule)
@@ -345,6 +346,20 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
 	return 1;
 }
 
+static int fib6_nl2rule_dscp(const struct nlattr *nla, struct fib6_rule *rule6,
+			     struct netlink_ext_ack *extack)
+{
+	if (rule6->dscp) {
+		NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP");
+		return -EINVAL;
+	}
+
+	rule6->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	rule6->dscp_full = true;
+
+	return 0;
+}
+
 static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 			       struct fib_rule_hdr *frh,
 			       struct nlattr **tb,
@@ -361,6 +376,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	}
 	rule6->dscp = inet_dsfield_to_dscp(frh->tos);
 
+	if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0)
+		goto errout;
+
 	if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) {
 		if (rule->table == RT6_TABLE_UNSPEC) {
 			NL_SET_ERR_MSG(extack, "Invalid table");
@@ -413,9 +431,19 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->dst_len && (rule6->dst.plen != frh->dst_len))
 		return 0;
 
-	if (frh->tos && inet_dscp_to_dsfield(rule6->dscp) != frh->tos)
+	if (frh->tos &&
+	    (rule6->dscp_full ||
+	     inet_dscp_to_dsfield(rule6->dscp) != frh->tos))
 		return 0;
 
+	if (tb[FRA_DSCP]) {
+		dscp_t dscp;
+
+		dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2);
+		if (!rule6->dscp_full || rule6->dscp != dscp)
+			return 0;
+	}
+
 	if (frh->src_len &&
 	    nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
 		return 0;
@@ -434,7 +462,15 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 
 	frh->dst_len = rule6->dst.plen;
 	frh->src_len = rule6->src.plen;
-	frh->tos = inet_dscp_to_dsfield(rule6->dscp);
+
+	if (rule6->dscp_full) {
+		frh->tos = 0;
+		if (nla_put_u8(skb, FRA_DSCP,
+			       inet_dscp_to_dsfield(rule6->dscp) >> 2))
+			goto nla_put_failure;
+	} else {
+		frh->tos = inet_dscp_to_dsfield(rule6->dscp);
+	}
 
 	if ((rule6->dst.plen &&
 	     nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) ||
@@ -450,7 +486,8 @@ nla_put_failure:
 static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
 {
 	return nla_total_size(16) /* dst */
-	       + nla_total_size(16); /* src */
+	       + nla_total_size(16) /* src */
+	       + nla_total_size(1); /* dscp */
 }
 
 static void fib6_rule_flush_cache(struct fib_rules_ops *ops)
-- 
cgit v1.3-3-g829e


From 4b041d286e918340a21d778e83c00649da2b58cb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 11 Sep 2024 12:37:46 +0300
Subject: net: fib_rules: Enable DSCP selector usage

Now that both IPv4 and IPv6 support the new DSCP selector, enable user
space to configure FIB rules that make use of it by changing the policy
of the new DSCP attribute so that it accepts values in the range of [0,
63].

Use NLA_U8 rather than NLA_UINT as the field is of fixed size.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240911093748.3662015-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index df41c05f7234..154a2681f55c 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -11,6 +11,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <net/net_namespace.h>
+#include <net/inet_dscp.h>
 #include <net/sock.h>
 #include <net/fib_rules.h>
 #include <net/ip_tunnels.h>
@@ -767,7 +768,7 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_IP_PROTO]  = { .type = NLA_U8 },
 	[FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
 	[FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) },
-	[FRA_DSCP]	= { .type = NLA_REJECT },
+	[FRA_DSCP]	= NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2),
 };
 
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
-- 
cgit v1.3-3-g829e


From ac6ad3f3b5b11731312d9a4d3cfda74e22421b14 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 11 Sep 2024 12:37:47 +0300
Subject: selftests: fib_rule_tests: Add DSCP selector match tests

Add tests for the new FIB rule DSCP selector. Test with both IPv4 and
IPv6 and with both input and output routes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240911093748.3662015-6-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 34 +++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 53c5c1ad437e..21d11d23fab7 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -274,6 +274,23 @@ fib_rule6_test()
 			"$getnomatch" "ipproto ipv6-icmp match" \
 			"ipproto ipv6-tcp no match"
 	fi
+
+	fib_check_iproute_support "dscp" "tos"
+	if [ $? -eq 0 ]; then
+		match="dscp 0x3f"
+		getmatch="tos 0xfc"
+		getnomatch="tos 0xf4"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "dscp redirect to table" \
+			"dscp no redirect to table"
+
+		match="dscp 0x3f"
+		getmatch="from $SRC_IP6 iif $DEV tos 0xfc"
+		getnomatch="from $SRC_IP6 iif $DEV tos 0xf4"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "iif dscp redirect to table" \
+			"iif dscp no redirect to table"
+	fi
 }
 
 fib_rule6_vrf_test()
@@ -468,6 +485,23 @@ fib_rule4_test()
 			"$getnomatch" "ipproto icmp match" \
 			"ipproto tcp no match"
 	fi
+
+	fib_check_iproute_support "dscp" "tos"
+	if [ $? -eq 0 ]; then
+		match="dscp 0x3f"
+		getmatch="tos 0xfc"
+		getnomatch="tos 0xf4"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "dscp redirect to table" \
+			"dscp no redirect to table"
+
+		match="dscp 0x3f"
+		getmatch="from $SRC_IP iif $DEV tos 0xfc"
+		getnomatch="from $SRC_IP iif $DEV tos 0xf4"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "iif dscp redirect to table" \
+			"iif dscp no redirect to table"
+	fi
 }
 
 fib_rule4_vrf_test()
-- 
cgit v1.3-3-g829e


From 2bf1259a6ea1104c55d1a5318eec1ef29e85cf76 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Wed, 11 Sep 2024 12:37:48 +0300
Subject: selftests: fib_rule_tests: Add DSCP selector connect tests

Test that locally generated traffic from a socket that specifies a DS
Field using the IP_TOS / IPV6_TCLASS socket options is correctly
redirected using a FIB rule that matches on DSCP. Add negative tests to
verify that the rule is not it when it should not. Test with both IPv4
and IPv6 and with both TCP and UDP sockets.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240911093748.3662015-7-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 56 +++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 21d11d23fab7..1d58b3b87465 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -336,6 +336,34 @@ fib_rule6_connect_test()
 	log_test $? 1 "rule6 dsfield tcp no connect (dsfield 0x20)"
 
 	$IP -6 rule del dsfield 0x04 table $RTABLE_PEER
+
+	ip rule help 2>&1 | grep -q dscp
+	if [ $? -ne 0 ]; then
+		echo "SKIP: iproute2 iprule too old, missing dscp match"
+		cleanup_peer
+		return
+	fi
+
+	$IP -6 rule add dscp 0x3f table $RTABLE_PEER
+
+	nettest -q -6 -B -t 5 -N $testns -O $peerns -U -D -Q 0xfc \
+		-l 2001:db8::1:11 -r 2001:db8::1:11
+	log_test $? 0 "rule6 dscp udp connect"
+
+	nettest -q -6 -B -t 5 -N $testns -O $peerns -Q 0xfc \
+		-l 2001:db8::1:11 -r 2001:db8::1:11
+	log_test $? 0 "rule6 dscp tcp connect"
+
+	nettest -q -6 -B -t 5 -N $testns -O $peerns -U -D -Q 0xf4 \
+		-l 2001:db8::1:11 -r 2001:db8::1:11
+	log_test $? 1 "rule6 dscp udp no connect"
+
+	nettest -q -6 -B -t 5 -N $testns -O $peerns -Q 0xf4 \
+		-l 2001:db8::1:11 -r 2001:db8::1:11
+	log_test $? 1 "rule6 dscp tcp no connect"
+
+	$IP -6 rule del dscp 0x3f table $RTABLE_PEER
+
 	cleanup_peer
 }
 
@@ -547,6 +575,34 @@ fib_rule4_connect_test()
 	log_test $? 1 "rule4 dsfield tcp no connect (dsfield 0x20)"
 
 	$IP -4 rule del dsfield 0x04 table $RTABLE_PEER
+
+	ip rule help 2>&1 | grep -q dscp
+	if [ $? -ne 0 ]; then
+		echo "SKIP: iproute2 iprule too old, missing dscp match"
+		cleanup_peer
+		return
+	fi
+
+	$IP -4 rule add dscp 0x3f table $RTABLE_PEER
+
+	nettest -q -B -t 5 -N $testns -O $peerns -D -U -Q 0xfc \
+		-l 198.51.100.11 -r 198.51.100.11
+	log_test $? 0 "rule4 dscp udp connect"
+
+	nettest -q -B -t 5 -N $testns -O $peerns -Q 0xfc \
+		-l 198.51.100.11 -r 198.51.100.11
+	log_test $? 0 "rule4 dscp tcp connect"
+
+	nettest -q -B -t 5 -N $testns -O $peerns -D -U -Q 0xf4 \
+		-l 198.51.100.11 -r 198.51.100.11
+	log_test $? 1 "rule4 dscp udp no connect"
+
+	nettest -q -B -t 5 -N $testns -O $peerns -Q 0xf4 \
+		-l 198.51.100.11 -r 198.51.100.11
+	log_test $? 1 "rule4 dscp tcp no connect"
+
+	$IP -4 rule del dscp 0x3f table $RTABLE_PEER
+
 	cleanup_peer
 }
 ################################################################################
-- 
cgit v1.3-3-g829e


From a59571ad6dfcd830c6a9ca12ac0e1484584a7223 Mon Sep 17 00:00:00 2001
From: Nelson Escobar <neescoba@cisco.com>
Date: Wed, 11 Sep 2024 17:50:36 -0700
Subject: enic: Use macro instead of static const variables for array sizes

In enic_ethtool.c there is no need to use static const variables to store
array sizes when a macro can be used instead.

Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20240912005039.10797-2-neescoba@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic_ethtool.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 31685ee304c6..e49543d97a83 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -46,6 +46,8 @@ static const struct enic_stat enic_tx_stats[] = {
 	ENIC_TX_STAT(tx_tso),
 };
 
+#define NUM_ENIC_TX_STATS	ARRAY_SIZE(enic_tx_stats)
+
 static const struct enic_stat enic_rx_stats[] = {
 	ENIC_RX_STAT(rx_frames_ok),
 	ENIC_RX_STAT(rx_frames_total),
@@ -70,13 +72,13 @@ static const struct enic_stat enic_rx_stats[] = {
 	ENIC_RX_STAT(rx_frames_to_max),
 };
 
+#define NUM_ENIC_RX_STATS	ARRAY_SIZE(enic_rx_stats)
+
 static const struct enic_stat enic_gen_stats[] = {
 	ENIC_GEN_STAT(dma_map_error),
 };
 
-static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats);
-static const unsigned int enic_n_rx_stats = ARRAY_SIZE(enic_rx_stats);
-static const unsigned int enic_n_gen_stats = ARRAY_SIZE(enic_gen_stats);
+#define NUM_ENIC_GEN_STATS	ARRAY_SIZE(enic_gen_stats)
 
 static void enic_intr_coal_set_rx(struct enic *enic, u32 timer)
 {
@@ -145,15 +147,15 @@ static void enic_get_strings(struct net_device *netdev, u32 stringset,
 
 	switch (stringset) {
 	case ETH_SS_STATS:
-		for (i = 0; i < enic_n_tx_stats; i++) {
+		for (i = 0; i < NUM_ENIC_TX_STATS; i++) {
 			memcpy(data, enic_tx_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < enic_n_rx_stats; i++) {
+		for (i = 0; i < NUM_ENIC_RX_STATS; i++) {
 			memcpy(data, enic_rx_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
-		for (i = 0; i < enic_n_gen_stats; i++) {
+		for (i = 0; i < NUM_ENIC_GEN_STATS; i++) {
 			memcpy(data, enic_gen_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
@@ -244,7 +246,8 @@ static int enic_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
 	case ETH_SS_STATS:
-		return enic_n_tx_stats + enic_n_rx_stats + enic_n_gen_stats;
+		return NUM_ENIC_TX_STATS + NUM_ENIC_RX_STATS +
+			NUM_ENIC_GEN_STATS;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -266,11 +269,11 @@ static void enic_get_ethtool_stats(struct net_device *netdev,
 	if (err == -ENOMEM)
 		return;
 
-	for (i = 0; i < enic_n_tx_stats; i++)
+	for (i = 0; i < NUM_ENIC_TX_STATS; i++)
 		*(data++) = ((u64 *)&vstats->tx)[enic_tx_stats[i].index];
-	for (i = 0; i < enic_n_rx_stats; i++)
+	for (i = 0; i < NUM_ENIC_RX_STATS; i++)
 		*(data++) = ((u64 *)&vstats->rx)[enic_rx_stats[i].index];
-	for (i = 0; i < enic_n_gen_stats; i++)
+	for (i = 0; i < NUM_ENIC_GEN_STATS; i++)
 		*(data++) = ((u64 *)&enic->gen_stats)[enic_gen_stats[i].index];
 }
 
-- 
cgit v1.3-3-g829e


From f3f9150994961e8252008d8c669846c144dbde27 Mon Sep 17 00:00:00 2001
From: Nelson Escobar <neescoba@cisco.com>
Date: Wed, 11 Sep 2024 17:50:37 -0700
Subject: enic: Collect per queue statistics

Collect and per rq/wq statistics.

Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20240912005039.10797-3-neescoba@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic.h      |  38 ++++++++++-
 drivers/net/ethernet/cisco/enic/enic_main.c | 101 +++++++++++++++++++++++-----
 2 files changed, 121 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 300ad05ee05b..0cc3644ee855 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -128,6 +128,40 @@ struct vxlan_offload {
 	u8 flags;
 };
 
+struct enic_wq_stats {
+	u64 packets;		/* pkts queued for Tx */
+	u64 stopped;		/* Tx ring almost full, queue stopped */
+	u64 wake;		/* Tx ring no longer full, queue woken up*/
+	u64 tso;		/* non-encap tso pkt */
+	u64 encap_tso;		/* encap tso pkt */
+	u64 encap_csum;		/* encap HW csum */
+	u64 csum_partial;	/* skb->ip_summed = CHECKSUM_PARTIAL */
+	u64 csum_none;		/* HW csum not required */
+	u64 bytes;		/* bytes queued for Tx */
+	u64 add_vlan;		/* HW adds vlan tag */
+	u64 cq_work;		/* Tx completions processed */
+	u64 cq_bytes;		/* Tx bytes processed */
+	u64 null_pkt;		/* skb length <= 0 */
+	u64 skb_linear_fail;	/* linearize failures */
+	u64 desc_full_awake;	/* TX ring full while queue awake */
+};
+
+struct enic_rq_stats {
+	u64 packets;			/* pkts received */
+	u64 bytes;			/* bytes received */
+	u64 l4_rss_hash;		/* hashed on l4 */
+	u64 l3_rss_hash;		/* hashed on l3 */
+	u64 csum_unnecessary;		/* HW verified csum */
+	u64 csum_unnecessary_encap;	/* HW verified csum on encap packet */
+	u64 vlan_stripped;		/* HW stripped vlan */
+	u64 napi_complete;		/* napi complete intr reenabled */
+	u64 napi_repoll;		/* napi poll again */
+	u64 bad_fcs;			/* bad pkts */
+	u64 pkt_truncated;		/* truncated pkts */
+	u64 no_skb;			/* out of skbs */
+	u64 desc_skip;			/* Rx pkt went into later buffer */
+};
+
 /* Per-instance private data structure */
 struct enic {
 	struct net_device *netdev;
@@ -162,16 +196,16 @@ struct enic {
 	/* work queue cache line section */
 	____cacheline_aligned struct vnic_wq wq[ENIC_WQ_MAX];
 	spinlock_t wq_lock[ENIC_WQ_MAX];
+	struct enic_wq_stats wq_stats[ENIC_WQ_MAX];
 	unsigned int wq_count;
 	u16 loop_enable;
 	u16 loop_tag;
 
 	/* receive queue cache line section */
 	____cacheline_aligned struct vnic_rq rq[ENIC_RQ_MAX];
+	struct enic_rq_stats rq_stats[ENIC_RQ_MAX];
 	unsigned int rq_count;
 	struct vxlan_offload vxlan;
-	u64 rq_truncated_pkts;
-	u64 rq_bad_fcs;
 	struct napi_struct napi[ENIC_RQ_MAX + ENIC_WQ_MAX];
 
 	/* interrupt resource cache line section */
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 5f26fc3ad655..8f05ad3a4ccc 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -339,6 +339,10 @@ static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
 static void enic_wq_free_buf(struct vnic_wq *wq,
 	struct cq_desc *cq_desc, struct vnic_wq_buf *buf, void *opaque)
 {
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	enic->wq_stats[wq->index].cq_work++;
+	enic->wq_stats[wq->index].cq_bytes += buf->len;
 	enic_free_wq_buf(wq, buf);
 }
 
@@ -355,8 +359,10 @@ static int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
 
 	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number)) &&
 	    vnic_wq_desc_avail(&enic->wq[q_number]) >=
-	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS))
+	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
 		netif_wake_subqueue(enic->netdev, q_number);
+		enic->wq_stats[q_number].wake++;
+	}
 
 	spin_unlock(&enic->wq_lock[q_number]);
 
@@ -590,6 +596,11 @@ static int enic_queue_wq_skb_vlan(struct enic *enic, struct vnic_wq *wq,
 	if (!eop)
 		err = enic_queue_wq_skb_cont(enic, wq, skb, len_left, loopback);
 
+	/* The enic_queue_wq_desc() above does not do HW checksum */
+	enic->wq_stats[wq->index].csum_none++;
+	enic->wq_stats[wq->index].packets++;
+	enic->wq_stats[wq->index].bytes += skb->len;
+
 	return err;
 }
 
@@ -622,6 +633,10 @@ static int enic_queue_wq_skb_csum_l4(struct enic *enic, struct vnic_wq *wq,
 	if (!eop)
 		err = enic_queue_wq_skb_cont(enic, wq, skb, len_left, loopback);
 
+	enic->wq_stats[wq->index].csum_partial++;
+	enic->wq_stats[wq->index].packets++;
+	enic->wq_stats[wq->index].bytes += skb->len;
+
 	return err;
 }
 
@@ -676,15 +691,18 @@ static int enic_queue_wq_skb_tso(struct enic *enic, struct vnic_wq *wq,
 	unsigned int offset = 0;
 	unsigned int hdr_len;
 	dma_addr_t dma_addr;
+	unsigned int pkts;
 	unsigned int len;
 	skb_frag_t *frag;
 
 	if (skb->encapsulation) {
 		hdr_len = skb_inner_tcp_all_headers(skb);
 		enic_preload_tcp_csum_encap(skb);
+		enic->wq_stats[wq->index].encap_tso++;
 	} else {
 		hdr_len = skb_tcp_all_headers(skb);
 		enic_preload_tcp_csum(skb);
+		enic->wq_stats[wq->index].tso++;
 	}
 
 	/* Queue WQ_ENET_MAX_DESC_LEN length descriptors
@@ -705,7 +723,7 @@ static int enic_queue_wq_skb_tso(struct enic *enic, struct vnic_wq *wq,
 	}
 
 	if (eop)
-		return 0;
+		goto tso_out_stats;
 
 	/* Queue WQ_ENET_MAX_DESC_LEN length descriptors
 	 * for additional data fragments
@@ -732,6 +750,15 @@ static int enic_queue_wq_skb_tso(struct enic *enic, struct vnic_wq *wq,
 		}
 	}
 
+tso_out_stats:
+	/* calculate how many packets tso sent */
+	len = skb->len - hdr_len;
+	pkts = len / mss;
+	if ((len % mss) > 0)
+		pkts++;
+	enic->wq_stats[wq->index].packets += pkts;
+	enic->wq_stats[wq->index].bytes += (len + (pkts * hdr_len));
+
 	return 0;
 }
 
@@ -764,6 +791,10 @@ static inline int enic_queue_wq_skb_encap(struct enic *enic, struct vnic_wq *wq,
 	if (!eop)
 		err = enic_queue_wq_skb_cont(enic, wq, skb, len_left, loopback);
 
+	enic->wq_stats[wq->index].encap_csum++;
+	enic->wq_stats[wq->index].packets++;
+	enic->wq_stats[wq->index].bytes += skb->len;
+
 	return err;
 }
 
@@ -780,6 +811,7 @@ static inline int enic_queue_wq_skb(struct enic *enic,
 		/* VLAN tag from trunking driver */
 		vlan_tag_insert = 1;
 		vlan_tag = skb_vlan_tag_get(skb);
+		enic->wq_stats[wq->index].add_vlan++;
 	} else if (enic->loop_enable) {
 		vlan_tag = enic->loop_tag;
 		loopback = 1;
@@ -792,7 +824,7 @@ static inline int enic_queue_wq_skb(struct enic *enic,
 	else if (skb->encapsulation)
 		err = enic_queue_wq_skb_encap(enic, wq, skb, vlan_tag_insert,
 					      vlan_tag, loopback);
-	else if	(skb->ip_summed == CHECKSUM_PARTIAL)
+	else if (skb->ip_summed == CHECKSUM_PARTIAL)
 		err = enic_queue_wq_skb_csum_l4(enic, wq, skb, vlan_tag_insert,
 						vlan_tag, loopback);
 	else
@@ -825,13 +857,15 @@ static netdev_tx_t enic_hard_start_xmit(struct sk_buff *skb,
 	unsigned int txq_map;
 	struct netdev_queue *txq;
 
+	txq_map = skb_get_queue_mapping(skb) % enic->wq_count;
+	wq = &enic->wq[txq_map];
+
 	if (skb->len <= 0) {
 		dev_kfree_skb_any(skb);
+		enic->wq_stats[wq->index].null_pkt++;
 		return NETDEV_TX_OK;
 	}
 
-	txq_map = skb_get_queue_mapping(skb) % enic->wq_count;
-	wq = &enic->wq[txq_map];
 	txq = netdev_get_tx_queue(netdev, txq_map);
 
 	/* Non-TSO sends must fit within ENIC_NON_TSO_MAX_DESC descs,
@@ -843,6 +877,7 @@ static netdev_tx_t enic_hard_start_xmit(struct sk_buff *skb,
 	    skb_shinfo(skb)->nr_frags + 1 > ENIC_NON_TSO_MAX_DESC &&
 	    skb_linearize(skb)) {
 		dev_kfree_skb_any(skb);
+		enic->wq_stats[wq->index].skb_linear_fail++;
 		return NETDEV_TX_OK;
 	}
 
@@ -854,14 +889,17 @@ static netdev_tx_t enic_hard_start_xmit(struct sk_buff *skb,
 		/* This is a hard error, log it */
 		netdev_err(netdev, "BUG! Tx ring full when queue awake!\n");
 		spin_unlock(&enic->wq_lock[txq_map]);
+		enic->wq_stats[wq->index].desc_full_awake++;
 		return NETDEV_TX_BUSY;
 	}
 
 	if (enic_queue_wq_skb(enic, wq, skb))
 		goto error;
 
-	if (vnic_wq_desc_avail(wq) < MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)
+	if (vnic_wq_desc_avail(wq) < MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS) {
 		netif_tx_stop_queue(txq);
+		enic->wq_stats[wq->index].stopped++;
+	}
 	skb_tx_timestamp(skb);
 	if (!netdev_xmit_more() || netif_xmit_stopped(txq))
 		vnic_wq_doorbell(wq);
@@ -878,7 +916,10 @@ static void enic_get_stats(struct net_device *netdev,
 {
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_stats *stats;
+	u64 pkt_truncated = 0;
+	u64 bad_fcs = 0;
 	int err;
+	int i;
 
 	err = enic_dev_stats_dump(enic, &stats);
 	/* return only when dma_alloc_coherent fails in vnic_dev_stats_dump
@@ -897,8 +938,17 @@ static void enic_get_stats(struct net_device *netdev,
 	net_stats->rx_bytes = stats->rx.rx_bytes_ok;
 	net_stats->rx_errors = stats->rx.rx_errors;
 	net_stats->multicast = stats->rx.rx_multicast_frames_ok;
-	net_stats->rx_over_errors = enic->rq_truncated_pkts;
-	net_stats->rx_crc_errors = enic->rq_bad_fcs;
+
+	for (i = 0; i < ENIC_RQ_MAX; i++) {
+		struct enic_rq_stats *rqs = &enic->rq_stats[i];
+
+		if (!enic->rq->ctrl)
+			break;
+		pkt_truncated += rqs->pkt_truncated;
+		bad_fcs += rqs->bad_fcs;
+	}
+	net_stats->rx_over_errors = pkt_truncated;
+	net_stats->rx_crc_errors = bad_fcs;
 	net_stats->rx_dropped = stats->rx.rx_no_bufs + stats->rx.rx_drop;
 }
 
@@ -1261,8 +1311,10 @@ static int enic_rq_alloc_buf(struct vnic_rq *rq)
 		return 0;
 	}
 	skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!skb)
+	if (!skb) {
+		enic->rq_stats[rq->index].no_skb++;
 		return -ENOMEM;
+	}
 
 	dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len,
 				  DMA_FROM_DEVICE);
@@ -1313,6 +1365,7 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 	struct net_device *netdev = enic->netdev;
 	struct sk_buff *skb;
 	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
+	struct enic_rq_stats *rqstats = &enic->rq_stats[rq->index];
 
 	u8 type, color, eop, sop, ingress_port, vlan_stripped;
 	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
@@ -1323,8 +1376,11 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 	u32 rss_hash;
 	bool outer_csum_ok = true, encap = false;
 
-	if (skipped)
+	rqstats->packets++;
+	if (skipped) {
+		rqstats->desc_skip++;
 		return;
+	}
 
 	skb = buf->os_buf;
 
@@ -1342,9 +1398,9 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 
 		if (!fcs_ok) {
 			if (bytes_written > 0)
-				enic->rq_bad_fcs++;
+				rqstats->bad_fcs++;
 			else if (bytes_written == 0)
-				enic->rq_truncated_pkts++;
+				rqstats->pkt_truncated++;
 		}
 
 		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
@@ -1359,7 +1415,7 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 
 		/* Good receive
 		 */
-
+		rqstats->bytes += bytes_written;
 		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
 			buf->os_buf = NULL;
 			dma_unmap_single(&enic->pdev->dev, buf->dma_addr,
@@ -1377,11 +1433,13 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
 			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
 				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
+				rqstats->l4_rss_hash++;
 				break;
 			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
 			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
 			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
 				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
+				rqstats->l3_rss_hash++;
 				break;
 			}
 		}
@@ -1418,11 +1476,16 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		    (ipv4_csum_ok || ipv6)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			skb->csum_level = encap;
+			if (encap)
+				rqstats->csum_unnecessary_encap++;
+			else
+				rqstats->csum_unnecessary++;
 		}
 
-		if (vlan_stripped)
+		if (vlan_stripped) {
 			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
-
+			rqstats->vlan_stripped++;
+		}
 		skb_mark_napi_id(skb, &enic->napi[rq->index]);
 		if (!(netdev->features & NETIF_F_GRO))
 			netif_receive_skb(skb);
@@ -1435,7 +1498,7 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 
 		/* Buffer overflow
 		 */
-
+		rqstats->pkt_truncated++;
 		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
 				 DMA_FROM_DEVICE);
 		dev_kfree_skb_any(skb);
@@ -1568,6 +1631,9 @@ static int enic_poll(struct napi_struct *napi, int budget)
 		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
 			enic_set_int_moderation(enic, &enic->rq[0]);
 		vnic_intr_unmask(&enic->intr[intr]);
+		enic->rq_stats[0].napi_complete++;
+	} else {
+		enic->rq_stats[0].napi_repoll++;
 	}
 
 	return rq_work_done;
@@ -1693,6 +1759,9 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
 			enic_set_int_moderation(enic, &enic->rq[rq]);
 		vnic_intr_unmask(&enic->intr[intr]);
+		enic->rq_stats[rq].napi_complete++;
+	} else {
+		enic->rq_stats[rq].napi_repoll++;
 	}
 
 	return work_done;
-- 
cgit v1.3-3-g829e


From 77805ddb57552ae4606a8d738ac240188c52a9e1 Mon Sep 17 00:00:00 2001
From: Nelson Escobar <neescoba@cisco.com>
Date: Wed, 11 Sep 2024 17:50:38 -0700
Subject: enic: Report per queue statistics in netdev qstats

Report per queue wq/rq statistics in netdev qstats.

Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20240912005039.10797-4-neescoba@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 56 +++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 8f05ad3a4ccc..ffed14b63d41 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -46,6 +46,7 @@
 #include <linux/crash_dump.h>
 #include <net/busy_poll.h>
 #include <net/vxlan.h>
+#include <net/netdev_queues.h>
 
 #include "cq_enet_desc.h"
 #include "vnic_dev.h"
@@ -2571,6 +2572,54 @@ static void enic_clear_intr_mode(struct enic *enic)
 	vnic_dev_set_intr_mode(enic->vdev, VNIC_DEV_INTR_MODE_UNKNOWN);
 }
 
+static void enic_get_queue_stats_rx(struct net_device *dev, int idx,
+				    struct netdev_queue_stats_rx *rxs)
+{
+	struct enic *enic = netdev_priv(dev);
+	struct enic_rq_stats *rqstats = &enic->rq_stats[idx];
+
+	rxs->bytes = rqstats->bytes;
+	rxs->packets = rqstats->packets;
+	rxs->hw_drops = rqstats->bad_fcs + rqstats->pkt_truncated;
+	rxs->hw_drop_overruns = rqstats->pkt_truncated;
+	rxs->csum_unnecessary = rqstats->csum_unnecessary +
+				rqstats->csum_unnecessary_encap;
+}
+
+static void enic_get_queue_stats_tx(struct net_device *dev, int idx,
+				    struct netdev_queue_stats_tx *txs)
+{
+	struct enic *enic = netdev_priv(dev);
+	struct enic_wq_stats *wqstats = &enic->wq_stats[idx];
+
+	txs->bytes = wqstats->bytes;
+	txs->packets = wqstats->packets;
+	txs->csum_none = wqstats->csum_none;
+	txs->needs_csum = wqstats->csum_partial + wqstats->encap_csum +
+			  wqstats->tso;
+	txs->hw_gso_packets = wqstats->tso;
+	txs->stop = wqstats->stopped;
+	txs->wake = wqstats->wake;
+}
+
+static void enic_get_base_stats(struct net_device *dev,
+				struct netdev_queue_stats_rx *rxs,
+				struct netdev_queue_stats_tx *txs)
+{
+	rxs->bytes = 0;
+	rxs->packets = 0;
+	rxs->hw_drops = 0;
+	rxs->hw_drop_overruns = 0;
+	rxs->csum_unnecessary = 0;
+	txs->bytes = 0;
+	txs->packets = 0;
+	txs->csum_none = 0;
+	txs->needs_csum = 0;
+	txs->hw_gso_packets = 0;
+	txs->stop = 0;
+	txs->wake = 0;
+}
+
 static const struct net_device_ops enic_netdev_dynamic_ops = {
 	.ndo_open		= enic_open,
 	.ndo_stop		= enic_stop,
@@ -2619,6 +2668,12 @@ static const struct net_device_ops enic_netdev_ops = {
 	.ndo_features_check	= enic_features_check,
 };
 
+static const struct netdev_stat_ops enic_netdev_stat_ops = {
+	.get_queue_stats_rx	= enic_get_queue_stats_rx,
+	.get_queue_stats_tx	= enic_get_queue_stats_tx,
+	.get_base_stats		= enic_get_base_stats,
+};
+
 static void enic_dev_deinit(struct enic *enic)
 {
 	unsigned int i;
@@ -2961,6 +3016,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		netdev->netdev_ops = &enic_netdev_dynamic_ops;
 	else
 		netdev->netdev_ops = &enic_netdev_ops;
+	netdev->stat_ops = &enic_netdev_stat_ops;
 
 	netdev->watchdog_timeo = 2 * HZ;
 	enic_set_ethtool_ops(netdev);
-- 
cgit v1.3-3-g829e


From bde04d9876c05e5fdb8fdf7c6db84ac26a9800b0 Mon Sep 17 00:00:00 2001
From: Nelson Escobar <neescoba@cisco.com>
Date: Wed, 11 Sep 2024 17:50:39 -0700
Subject: enic: Report some per queue statistics in ethtool

Make 'ethtool -S <intf>' output show some per rq/wq statistics that
don't exist in the netdev qstats.

Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20240912005039.10797-5-neescoba@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic_ethtool.c | 83 +++++++++++++++++++++++++-
 1 file changed, 81 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index e49543d97a83..f7986f2b6a17 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -32,6 +32,41 @@ struct enic_stat {
 	.index = offsetof(struct vnic_gen_stats, stat) / sizeof(u64)\
 }
 
+#define ENIC_PER_RQ_STAT(stat) { \
+	.name = "rq[%d]_"#stat, \
+	.index = offsetof(struct enic_rq_stats, stat) / sizeof(u64) \
+}
+
+#define ENIC_PER_WQ_STAT(stat) { \
+	.name = "wq[%d]_"#stat, \
+	.index = offsetof(struct enic_wq_stats, stat) / sizeof(u64) \
+}
+
+static const struct enic_stat enic_per_rq_stats[] = {
+	ENIC_PER_RQ_STAT(l4_rss_hash),
+	ENIC_PER_RQ_STAT(l3_rss_hash),
+	ENIC_PER_RQ_STAT(csum_unnecessary_encap),
+	ENIC_PER_RQ_STAT(vlan_stripped),
+	ENIC_PER_RQ_STAT(napi_complete),
+	ENIC_PER_RQ_STAT(napi_repoll),
+	ENIC_PER_RQ_STAT(no_skb),
+	ENIC_PER_RQ_STAT(desc_skip),
+};
+
+#define NUM_ENIC_PER_RQ_STATS   ARRAY_SIZE(enic_per_rq_stats)
+
+static const struct enic_stat enic_per_wq_stats[] = {
+	ENIC_PER_WQ_STAT(encap_tso),
+	ENIC_PER_WQ_STAT(encap_csum),
+	ENIC_PER_WQ_STAT(add_vlan),
+	ENIC_PER_WQ_STAT(cq_work),
+	ENIC_PER_WQ_STAT(cq_bytes),
+	ENIC_PER_WQ_STAT(null_pkt),
+	ENIC_PER_WQ_STAT(skb_linear_fail),
+	ENIC_PER_WQ_STAT(desc_full_awake),
+};
+
+#define NUM_ENIC_PER_WQ_STATS   ARRAY_SIZE(enic_per_wq_stats)
 static const struct enic_stat enic_tx_stats[] = {
 	ENIC_TX_STAT(tx_frames_ok),
 	ENIC_TX_STAT(tx_unicast_frames_ok),
@@ -143,7 +178,9 @@ static void enic_get_drvinfo(struct net_device *netdev,
 static void enic_get_strings(struct net_device *netdev, u32 stringset,
 	u8 *data)
 {
+	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
+	unsigned int j;
 
 	switch (stringset) {
 	case ETH_SS_STATS:
@@ -159,6 +196,20 @@ static void enic_get_strings(struct net_device *netdev, u32 stringset,
 			memcpy(data, enic_gen_stats[i].name, ETH_GSTRING_LEN);
 			data += ETH_GSTRING_LEN;
 		}
+		for (i = 0; i < enic->rq_count; i++) {
+			for (j = 0; j < NUM_ENIC_PER_RQ_STATS; j++) {
+				snprintf(data, ETH_GSTRING_LEN,
+					 enic_per_rq_stats[j].name, i);
+				data += ETH_GSTRING_LEN;
+			}
+		}
+		for (i = 0; i < enic->wq_count; i++) {
+			for (j = 0; j < NUM_ENIC_PER_WQ_STATS; j++) {
+				snprintf(data, ETH_GSTRING_LEN,
+					 enic_per_wq_stats[j].name, i);
+				data += ETH_GSTRING_LEN;
+			}
+		}
 		break;
 	}
 }
@@ -244,10 +295,19 @@ err_out:
 
 static int enic_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct enic *enic = netdev_priv(netdev);
+	unsigned int n_per_rq_stats;
+	unsigned int n_per_wq_stats;
+	unsigned int n_stats;
+
 	switch (sset) {
 	case ETH_SS_STATS:
-		return NUM_ENIC_TX_STATS + NUM_ENIC_RX_STATS +
-			NUM_ENIC_GEN_STATS;
+		n_per_rq_stats = NUM_ENIC_PER_RQ_STATS * enic->rq_count;
+		n_per_wq_stats = NUM_ENIC_PER_WQ_STATS * enic->wq_count;
+		n_stats = NUM_ENIC_TX_STATS + NUM_ENIC_RX_STATS +
+			NUM_ENIC_GEN_STATS +
+			n_per_rq_stats + n_per_wq_stats;
+		return n_stats;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -259,6 +319,7 @@ static void enic_get_ethtool_stats(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_stats *vstats;
 	unsigned int i;
+	unsigned int j;
 	int err;
 
 	err = enic_dev_stats_dump(enic, &vstats);
@@ -275,6 +336,24 @@ static void enic_get_ethtool_stats(struct net_device *netdev,
 		*(data++) = ((u64 *)&vstats->rx)[enic_rx_stats[i].index];
 	for (i = 0; i < NUM_ENIC_GEN_STATS; i++)
 		*(data++) = ((u64 *)&enic->gen_stats)[enic_gen_stats[i].index];
+	for (i = 0; i < enic->rq_count; i++) {
+		struct enic_rq_stats *rqstats = &enic->rq_stats[i];
+		int index;
+
+		for (j = 0; j < NUM_ENIC_PER_RQ_STATS; j++) {
+			index = enic_per_rq_stats[j].index;
+			*(data++) = ((u64 *)rqstats)[index];
+		}
+	}
+	for (i = 0; i < enic->wq_count; i++) {
+		struct enic_wq_stats *wqstats = &enic->wq_stats[i];
+		int index;
+
+		for (j = 0; j < NUM_ENIC_PER_WQ_STATS; j++) {
+			index = enic_per_wq_stats[j].index;
+			*(data++) = ((u64 *)wqstats)[index];
+		}
+	}
 }
 
 static u32 enic_get_msglevel(struct net_device *netdev)
-- 
cgit v1.3-3-g829e


From 1b8c9cb3151a541a4197d2bb449233064f747832 Mon Sep 17 00:00:00 2001
From: Gaosheng Cui <cuigaosheng1@huawei.com>
Date: Thu, 12 Sep 2024 09:19:49 +0800
Subject: MIPS: Remove the obsoleted code for include/linux/mv643xx.h

Most of the drivers which used this header have been deleted, most
of these code is obsoleted, move the only defines that are actually
used into arch/powerpc/platforms/chrp/pegasos_eth.c and delete the
file completely.

Signed-off-by: Gaosheng Cui <cuigaosheng1@huawei.com>
Link: https://patch.msgid.link/20240912011949.2726928-1-cuigaosheng1@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                               |   1 -
 arch/powerpc/platforms/chrp/pegasos_eth.c |   7 +-
 include/linux/mv643xx.h                   | 921 ------------------------------
 3 files changed, 5 insertions(+), 924 deletions(-)
 delete mode 100644 include/linux/mv643xx.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 0b1c49bf558d..77fcd6f802a5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13593,7 +13593,6 @@ M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/marvell/mv643xx_eth.*
-F:	include/linux/mv643xx.h
 
 MARVELL MV88X3310 PHY DRIVER
 M:	Russell King <linux@armlinux.org.uk>
diff --git a/arch/powerpc/platforms/chrp/pegasos_eth.c b/arch/powerpc/platforms/chrp/pegasos_eth.c
index 5c4f1a9ca154..6f4a41a9352a 100644
--- a/arch/powerpc/platforms/chrp/pegasos_eth.c
+++ b/arch/powerpc/platforms/chrp/pegasos_eth.c
@@ -14,7 +14,7 @@
 #include <linux/ioport.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
-#include <linux/mv643xx.h>
+#include <linux/mv643xx_eth.h>
 #include <linux/pci.h>
 
 #define PEGASOS2_MARVELL_REGBASE 		(0xf1000000)
@@ -25,12 +25,15 @@
 #define PEGASOS2_SRAM_BASE_ETH_PORT0			(PEGASOS2_SRAM_BASE)
 #define PEGASOS2_SRAM_BASE_ETH_PORT1			(PEGASOS2_SRAM_BASE_ETH_PORT0 + (PEGASOS2_SRAM_SIZE / 2) )
 
-
 #define PEGASOS2_SRAM_RXRING_SIZE		(PEGASOS2_SRAM_SIZE/4)
 #define PEGASOS2_SRAM_TXRING_SIZE		(PEGASOS2_SRAM_SIZE/4)
 
 #undef BE_VERBOSE
 
+#define MV64340_BASE_ADDR_ENABLE                                    0x278
+#define MV64340_INTEGRATED_SRAM_BASE_ADDR                           0x268
+#define MV64340_SRAM_CONFIG                                         0x380
+
 static struct resource mv643xx_eth_shared_resources[] = {
 	[0] = {
 		.name	= "ethernet shared base",
diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h
deleted file mode 100644
index 000b126acfb6..000000000000
--- a/include/linux/mv643xx.h
+++ /dev/null
@@ -1,921 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * mv643xx.h - MV-643XX Internal registers definition file.
- *
- * Copyright 2002 Momentum Computer, Inc.
- * 	Author: Matthew Dharm <mdharm@momenco.com>
- * Copyright 2002 GALILEO TECHNOLOGY, LTD. 
- */
-#ifndef __ASM_MV643XX_H
-#define __ASM_MV643XX_H
-
-#include <asm/types.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/mv643xx_i2c.h>
-
-/****************************************/
-/* Processor Address Space              */
-/****************************************/
-
-/* DDR SDRAM BAR and size registers */
-
-#define MV64340_CS_0_BASE_ADDR                                      0x008
-#define MV64340_CS_0_SIZE                                           0x010
-#define MV64340_CS_1_BASE_ADDR                                      0x208
-#define MV64340_CS_1_SIZE                                           0x210
-#define MV64340_CS_2_BASE_ADDR                                      0x018
-#define MV64340_CS_2_SIZE                                           0x020
-#define MV64340_CS_3_BASE_ADDR                                      0x218
-#define MV64340_CS_3_SIZE                                           0x220
-
-/* Devices BAR and size registers */
-
-#define MV64340_DEV_CS0_BASE_ADDR                                   0x028
-#define MV64340_DEV_CS0_SIZE                                        0x030
-#define MV64340_DEV_CS1_BASE_ADDR                                   0x228
-#define MV64340_DEV_CS1_SIZE                                        0x230
-#define MV64340_DEV_CS2_BASE_ADDR                                   0x248
-#define MV64340_DEV_CS2_SIZE                                        0x250
-#define MV64340_DEV_CS3_BASE_ADDR                                   0x038
-#define MV64340_DEV_CS3_SIZE                                        0x040
-#define MV64340_BOOTCS_BASE_ADDR                                    0x238
-#define MV64340_BOOTCS_SIZE                                         0x240
-
-/* PCI 0 BAR and size registers */
-
-#define MV64340_PCI_0_IO_BASE_ADDR                                  0x048
-#define MV64340_PCI_0_IO_SIZE                                       0x050
-#define MV64340_PCI_0_MEMORY0_BASE_ADDR                             0x058
-#define MV64340_PCI_0_MEMORY0_SIZE                                  0x060
-#define MV64340_PCI_0_MEMORY1_BASE_ADDR                             0x080
-#define MV64340_PCI_0_MEMORY1_SIZE                                  0x088
-#define MV64340_PCI_0_MEMORY2_BASE_ADDR                             0x258
-#define MV64340_PCI_0_MEMORY2_SIZE                                  0x260
-#define MV64340_PCI_0_MEMORY3_BASE_ADDR                             0x280
-#define MV64340_PCI_0_MEMORY3_SIZE                                  0x288
-
-/* PCI 1 BAR and size registers */
-#define MV64340_PCI_1_IO_BASE_ADDR                                  0x090
-#define MV64340_PCI_1_IO_SIZE                                       0x098
-#define MV64340_PCI_1_MEMORY0_BASE_ADDR                             0x0a0
-#define MV64340_PCI_1_MEMORY0_SIZE                                  0x0a8
-#define MV64340_PCI_1_MEMORY1_BASE_ADDR                             0x0b0
-#define MV64340_PCI_1_MEMORY1_SIZE                                  0x0b8
-#define MV64340_PCI_1_MEMORY2_BASE_ADDR                             0x2a0
-#define MV64340_PCI_1_MEMORY2_SIZE                                  0x2a8
-#define MV64340_PCI_1_MEMORY3_BASE_ADDR                             0x2b0
-#define MV64340_PCI_1_MEMORY3_SIZE                                  0x2b8
-
-/* SRAM base address */
-#define MV64340_INTEGRATED_SRAM_BASE_ADDR                           0x268
-
-/* internal registers space base address */
-#define MV64340_INTERNAL_SPACE_BASE_ADDR                            0x068
-
-/* Enables the CS , DEV_CS , PCI 0 and PCI 1 
-   windows above */
-#define MV64340_BASE_ADDR_ENABLE                                    0x278
-
-/****************************************/
-/* PCI remap registers                  */
-/****************************************/
-      /* PCI 0 */
-#define MV64340_PCI_0_IO_ADDR_REMAP                                 0x0f0
-#define MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP                        0x0f8
-#define MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP                       0x320
-#define MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP                        0x100
-#define MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP                       0x328
-#define MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP                        0x2f8
-#define MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP                       0x330
-#define MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP                        0x300
-#define MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP                       0x338
-      /* PCI 1 */
-#define MV64340_PCI_1_IO_ADDR_REMAP                                 0x108
-#define MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP                        0x110
-#define MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP                       0x340
-#define MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP                        0x118
-#define MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP                       0x348
-#define MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP                        0x310
-#define MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP                       0x350
-#define MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP                        0x318
-#define MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP                       0x358
- 
-#define MV64340_CPU_PCI_0_HEADERS_RETARGET_CONTROL                  0x3b0
-#define MV64340_CPU_PCI_0_HEADERS_RETARGET_BASE                     0x3b8
-#define MV64340_CPU_PCI_1_HEADERS_RETARGET_CONTROL                  0x3c0
-#define MV64340_CPU_PCI_1_HEADERS_RETARGET_BASE                     0x3c8
-#define MV64340_CPU_GE_HEADERS_RETARGET_CONTROL                     0x3d0
-#define MV64340_CPU_GE_HEADERS_RETARGET_BASE                        0x3d8
-#define MV64340_CPU_IDMA_HEADERS_RETARGET_CONTROL                   0x3e0
-#define MV64340_CPU_IDMA_HEADERS_RETARGET_BASE                      0x3e8
-
-/****************************************/
-/*         CPU Control Registers        */
-/****************************************/
-
-#define MV64340_CPU_CONFIG                                          0x000
-#define MV64340_CPU_MODE                                            0x120
-#define MV64340_CPU_MASTER_CONTROL                                  0x160
-#define MV64340_CPU_CROSS_BAR_CONTROL_LOW                           0x150
-#define MV64340_CPU_CROSS_BAR_CONTROL_HIGH                          0x158
-#define MV64340_CPU_CROSS_BAR_TIMEOUT                               0x168
-
-/****************************************/
-/* SMP RegisterS                        */
-/****************************************/
-
-#define MV64340_SMP_WHO_AM_I                                        0x200
-#define MV64340_SMP_CPU0_DOORBELL                                   0x214
-#define MV64340_SMP_CPU0_DOORBELL_CLEAR                             0x21C
-#define MV64340_SMP_CPU1_DOORBELL                                   0x224
-#define MV64340_SMP_CPU1_DOORBELL_CLEAR                             0x22C
-#define MV64340_SMP_CPU0_DOORBELL_MASK                              0x234
-#define MV64340_SMP_CPU1_DOORBELL_MASK                              0x23C
-#define MV64340_SMP_SEMAPHOR0                                       0x244
-#define MV64340_SMP_SEMAPHOR1                                       0x24c
-#define MV64340_SMP_SEMAPHOR2                                       0x254
-#define MV64340_SMP_SEMAPHOR3                                       0x25c
-#define MV64340_SMP_SEMAPHOR4                                       0x264
-#define MV64340_SMP_SEMAPHOR5                                       0x26c
-#define MV64340_SMP_SEMAPHOR6                                       0x274
-#define MV64340_SMP_SEMAPHOR7                                       0x27c
-
-/****************************************/
-/*  CPU Sync Barrier Register           */
-/****************************************/
-
-#define MV64340_CPU_0_SYNC_BARRIER_TRIGGER                          0x0c0
-#define MV64340_CPU_0_SYNC_BARRIER_VIRTUAL                          0x0c8
-#define MV64340_CPU_1_SYNC_BARRIER_TRIGGER                          0x0d0
-#define MV64340_CPU_1_SYNC_BARRIER_VIRTUAL                          0x0d8
-
-/****************************************/
-/* CPU Access Protect                   */
-/****************************************/
-
-#define MV64340_CPU_PROTECT_WINDOW_0_BASE_ADDR                      0x180
-#define MV64340_CPU_PROTECT_WINDOW_0_SIZE                           0x188
-#define MV64340_CPU_PROTECT_WINDOW_1_BASE_ADDR                      0x190
-#define MV64340_CPU_PROTECT_WINDOW_1_SIZE                           0x198
-#define MV64340_CPU_PROTECT_WINDOW_2_BASE_ADDR                      0x1a0
-#define MV64340_CPU_PROTECT_WINDOW_2_SIZE                           0x1a8
-#define MV64340_CPU_PROTECT_WINDOW_3_BASE_ADDR                      0x1b0
-#define MV64340_CPU_PROTECT_WINDOW_3_SIZE                           0x1b8
-
-
-/****************************************/
-/*          CPU Error Report            */
-/****************************************/
-
-#define MV64340_CPU_ERROR_ADDR_LOW                                  0x070
-#define MV64340_CPU_ERROR_ADDR_HIGH                                 0x078
-#define MV64340_CPU_ERROR_DATA_LOW                                  0x128
-#define MV64340_CPU_ERROR_DATA_HIGH                                 0x130
-#define MV64340_CPU_ERROR_PARITY                                    0x138
-#define MV64340_CPU_ERROR_CAUSE                                     0x140
-#define MV64340_CPU_ERROR_MASK                                      0x148
-
-/****************************************/
-/*      CPU Interface Debug Registers 	*/
-/****************************************/
-
-#define MV64340_PUNIT_SLAVE_DEBUG_LOW                               0x360
-#define MV64340_PUNIT_SLAVE_DEBUG_HIGH                              0x368
-#define MV64340_PUNIT_MASTER_DEBUG_LOW                              0x370
-#define MV64340_PUNIT_MASTER_DEBUG_HIGH                             0x378
-#define MV64340_PUNIT_MMASK                                         0x3e4
-
-/****************************************/
-/*  Integrated SRAM Registers           */
-/****************************************/
-
-#define MV64340_SRAM_CONFIG                                         0x380
-#define MV64340_SRAM_TEST_MODE                                      0X3F4
-#define MV64340_SRAM_ERROR_CAUSE                                    0x388
-#define MV64340_SRAM_ERROR_ADDR                                     0x390
-#define MV64340_SRAM_ERROR_ADDR_HIGH                                0X3F8
-#define MV64340_SRAM_ERROR_DATA_LOW                                 0x398
-#define MV64340_SRAM_ERROR_DATA_HIGH                                0x3a0
-#define MV64340_SRAM_ERROR_DATA_PARITY                              0x3a8
-
-/****************************************/
-/* SDRAM Configuration                  */
-/****************************************/
-
-#define MV64340_SDRAM_CONFIG                                        0x1400
-#define MV64340_D_UNIT_CONTROL_LOW                                  0x1404
-#define MV64340_D_UNIT_CONTROL_HIGH                                 0x1424
-#define MV64340_SDRAM_TIMING_CONTROL_LOW                            0x1408
-#define MV64340_SDRAM_TIMING_CONTROL_HIGH                           0x140c
-#define MV64340_SDRAM_ADDR_CONTROL                                  0x1410
-#define MV64340_SDRAM_OPEN_PAGES_CONTROL                            0x1414
-#define MV64340_SDRAM_OPERATION                                     0x1418
-#define MV64340_SDRAM_MODE                                          0x141c
-#define MV64340_EXTENDED_DRAM_MODE                                  0x1420
-#define MV64340_SDRAM_CROSS_BAR_CONTROL_LOW                         0x1430
-#define MV64340_SDRAM_CROSS_BAR_CONTROL_HIGH                        0x1434
-#define MV64340_SDRAM_CROSS_BAR_TIMEOUT                             0x1438
-#define MV64340_SDRAM_ADDR_CTRL_PADS_CALIBRATION                    0x14c0
-#define MV64340_SDRAM_DATA_PADS_CALIBRATION                         0x14c4
-
-/****************************************/
-/* SDRAM Error Report                   */
-/****************************************/
-
-#define MV64340_SDRAM_ERROR_DATA_LOW                                0x1444
-#define MV64340_SDRAM_ERROR_DATA_HIGH                               0x1440
-#define MV64340_SDRAM_ERROR_ADDR                                    0x1450
-#define MV64340_SDRAM_RECEIVED_ECC                                  0x1448
-#define MV64340_SDRAM_CALCULATED_ECC                                0x144c
-#define MV64340_SDRAM_ECC_CONTROL                                   0x1454
-#define MV64340_SDRAM_ECC_ERROR_COUNTER                             0x1458
-
-/******************************************/
-/*  Controlled Delay Line (CDL) Registers */
-/******************************************/
-
-#define MV64340_DFCDL_CONFIG0                                       0x1480
-#define MV64340_DFCDL_CONFIG1                                       0x1484
-#define MV64340_DLL_WRITE                                           0x1488
-#define MV64340_DLL_READ                                            0x148c
-#define MV64340_SRAM_ADDR                                           0x1490
-#define MV64340_SRAM_DATA0                                          0x1494
-#define MV64340_SRAM_DATA1                                          0x1498
-#define MV64340_SRAM_DATA2                                          0x149c
-#define MV64340_DFCL_PROBE                                          0x14a0
-
-/******************************************/
-/*   Debug Registers                      */
-/******************************************/
-
-#define MV64340_DUNIT_DEBUG_LOW                                     0x1460
-#define MV64340_DUNIT_DEBUG_HIGH                                    0x1464
-#define MV64340_DUNIT_MMASK                                         0X1b40
-
-/****************************************/
-/* Device Parameters			*/
-/****************************************/
-
-#define MV64340_DEVICE_BANK0_PARAMETERS				    0x45c
-#define MV64340_DEVICE_BANK1_PARAMETERS				    0x460
-#define MV64340_DEVICE_BANK2_PARAMETERS				    0x464
-#define MV64340_DEVICE_BANK3_PARAMETERS				    0x468
-#define MV64340_DEVICE_BOOT_BANK_PARAMETERS			    0x46c
-#define MV64340_DEVICE_INTERFACE_CONTROL                            0x4c0
-#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_LOW              0x4c8
-#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_HIGH             0x4cc
-#define MV64340_DEVICE_INTERFACE_CROSS_BAR_TIMEOUT                  0x4c4
-
-/****************************************/
-/* Device interrupt registers		*/
-/****************************************/
-
-#define MV64340_DEVICE_INTERRUPT_CAUSE				    0x4d0
-#define MV64340_DEVICE_INTERRUPT_MASK				    0x4d4
-#define MV64340_DEVICE_ERROR_ADDR				    0x4d8
-#define MV64340_DEVICE_ERROR_DATA   				    0x4dc
-#define MV64340_DEVICE_ERROR_PARITY     			    0x4e0
-
-/****************************************/
-/* Device debug registers   		*/
-/****************************************/
-
-#define MV64340_DEVICE_DEBUG_LOW     				    0x4e4
-#define MV64340_DEVICE_DEBUG_HIGH     				    0x4e8
-#define MV64340_RUNIT_MMASK                                         0x4f0
-
-/****************************************/
-/* PCI Slave Address Decoding registers */
-/****************************************/
-
-#define MV64340_PCI_0_CS_0_BANK_SIZE                                0xc08
-#define MV64340_PCI_1_CS_0_BANK_SIZE                                0xc88
-#define MV64340_PCI_0_CS_1_BANK_SIZE                                0xd08
-#define MV64340_PCI_1_CS_1_BANK_SIZE                                0xd88
-#define MV64340_PCI_0_CS_2_BANK_SIZE                                0xc0c
-#define MV64340_PCI_1_CS_2_BANK_SIZE                                0xc8c
-#define MV64340_PCI_0_CS_3_BANK_SIZE                                0xd0c
-#define MV64340_PCI_1_CS_3_BANK_SIZE                                0xd8c
-#define MV64340_PCI_0_DEVCS_0_BANK_SIZE                             0xc10
-#define MV64340_PCI_1_DEVCS_0_BANK_SIZE                             0xc90
-#define MV64340_PCI_0_DEVCS_1_BANK_SIZE                             0xd10
-#define MV64340_PCI_1_DEVCS_1_BANK_SIZE                             0xd90
-#define MV64340_PCI_0_DEVCS_2_BANK_SIZE                             0xd18
-#define MV64340_PCI_1_DEVCS_2_BANK_SIZE                             0xd98
-#define MV64340_PCI_0_DEVCS_3_BANK_SIZE                             0xc14
-#define MV64340_PCI_1_DEVCS_3_BANK_SIZE                             0xc94
-#define MV64340_PCI_0_DEVCS_BOOT_BANK_SIZE                          0xd14
-#define MV64340_PCI_1_DEVCS_BOOT_BANK_SIZE                          0xd94
-#define MV64340_PCI_0_P2P_MEM0_BAR_SIZE                             0xd1c
-#define MV64340_PCI_1_P2P_MEM0_BAR_SIZE                             0xd9c
-#define MV64340_PCI_0_P2P_MEM1_BAR_SIZE                             0xd20
-#define MV64340_PCI_1_P2P_MEM1_BAR_SIZE                             0xda0
-#define MV64340_PCI_0_P2P_I_O_BAR_SIZE                              0xd24
-#define MV64340_PCI_1_P2P_I_O_BAR_SIZE                              0xda4
-#define MV64340_PCI_0_CPU_BAR_SIZE                                  0xd28
-#define MV64340_PCI_1_CPU_BAR_SIZE                                  0xda8
-#define MV64340_PCI_0_INTERNAL_SRAM_BAR_SIZE                        0xe00
-#define MV64340_PCI_1_INTERNAL_SRAM_BAR_SIZE                        0xe80
-#define MV64340_PCI_0_EXPANSION_ROM_BAR_SIZE                        0xd2c
-#define MV64340_PCI_1_EXPANSION_ROM_BAR_SIZE                        0xd9c
-#define MV64340_PCI_0_BASE_ADDR_REG_ENABLE                          0xc3c
-#define MV64340_PCI_1_BASE_ADDR_REG_ENABLE                          0xcbc
-#define MV64340_PCI_0_CS_0_BASE_ADDR_REMAP			    0xc48
-#define MV64340_PCI_1_CS_0_BASE_ADDR_REMAP			    0xcc8
-#define MV64340_PCI_0_CS_1_BASE_ADDR_REMAP			    0xd48
-#define MV64340_PCI_1_CS_1_BASE_ADDR_REMAP			    0xdc8
-#define MV64340_PCI_0_CS_2_BASE_ADDR_REMAP			    0xc4c
-#define MV64340_PCI_1_CS_2_BASE_ADDR_REMAP			    0xccc
-#define MV64340_PCI_0_CS_3_BASE_ADDR_REMAP			    0xd4c
-#define MV64340_PCI_1_CS_3_BASE_ADDR_REMAP			    0xdcc
-#define MV64340_PCI_0_CS_0_BASE_HIGH_ADDR_REMAP			    0xF04
-#define MV64340_PCI_1_CS_0_BASE_HIGH_ADDR_REMAP			    0xF84
-#define MV64340_PCI_0_CS_1_BASE_HIGH_ADDR_REMAP			    0xF08
-#define MV64340_PCI_1_CS_1_BASE_HIGH_ADDR_REMAP			    0xF88
-#define MV64340_PCI_0_CS_2_BASE_HIGH_ADDR_REMAP			    0xF0C
-#define MV64340_PCI_1_CS_2_BASE_HIGH_ADDR_REMAP			    0xF8C
-#define MV64340_PCI_0_CS_3_BASE_HIGH_ADDR_REMAP			    0xF10
-#define MV64340_PCI_1_CS_3_BASE_HIGH_ADDR_REMAP			    0xF90
-#define MV64340_PCI_0_DEVCS_0_BASE_ADDR_REMAP			    0xc50
-#define MV64340_PCI_1_DEVCS_0_BASE_ADDR_REMAP			    0xcd0
-#define MV64340_PCI_0_DEVCS_1_BASE_ADDR_REMAP			    0xd50
-#define MV64340_PCI_1_DEVCS_1_BASE_ADDR_REMAP			    0xdd0
-#define MV64340_PCI_0_DEVCS_2_BASE_ADDR_REMAP			    0xd58
-#define MV64340_PCI_1_DEVCS_2_BASE_ADDR_REMAP			    0xdd8
-#define MV64340_PCI_0_DEVCS_3_BASE_ADDR_REMAP           	    0xc54
-#define MV64340_PCI_1_DEVCS_3_BASE_ADDR_REMAP           	    0xcd4
-#define MV64340_PCI_0_DEVCS_BOOTCS_BASE_ADDR_REMAP      	    0xd54
-#define MV64340_PCI_1_DEVCS_BOOTCS_BASE_ADDR_REMAP      	    0xdd4
-#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_LOW                  0xd5c
-#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_LOW                  0xddc
-#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_HIGH                 0xd60
-#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_HIGH                 0xde0
-#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_LOW                  0xd64
-#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_LOW                  0xde4
-#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_HIGH                 0xd68
-#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_HIGH                 0xde8
-#define MV64340_PCI_0_P2P_I_O_BASE_ADDR_REMAP                       0xd6c
-#define MV64340_PCI_1_P2P_I_O_BASE_ADDR_REMAP                       0xdec 
-#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_LOW                       0xd70
-#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_LOW                       0xdf0
-#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_HIGH                      0xd74
-#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_HIGH                      0xdf4
-#define MV64340_PCI_0_INTEGRATED_SRAM_BASE_ADDR_REMAP               0xf00
-#define MV64340_PCI_1_INTEGRATED_SRAM_BASE_ADDR_REMAP               0xf80
-#define MV64340_PCI_0_EXPANSION_ROM_BASE_ADDR_REMAP                 0xf38
-#define MV64340_PCI_1_EXPANSION_ROM_BASE_ADDR_REMAP                 0xfb8
-#define MV64340_PCI_0_ADDR_DECODE_CONTROL                           0xd3c
-#define MV64340_PCI_1_ADDR_DECODE_CONTROL                           0xdbc
-#define MV64340_PCI_0_HEADERS_RETARGET_CONTROL                      0xF40
-#define MV64340_PCI_1_HEADERS_RETARGET_CONTROL                      0xFc0
-#define MV64340_PCI_0_HEADERS_RETARGET_BASE                         0xF44
-#define MV64340_PCI_1_HEADERS_RETARGET_BASE                         0xFc4
-#define MV64340_PCI_0_HEADERS_RETARGET_HIGH                         0xF48
-#define MV64340_PCI_1_HEADERS_RETARGET_HIGH                         0xFc8
-
-/***********************************/
-/*   PCI Control Register Map      */
-/***********************************/
-
-#define MV64340_PCI_0_DLL_STATUS_AND_COMMAND                        0x1d20
-#define MV64340_PCI_1_DLL_STATUS_AND_COMMAND                        0x1da0
-#define MV64340_PCI_0_MPP_PADS_DRIVE_CONTROL                        0x1d1C
-#define MV64340_PCI_1_MPP_PADS_DRIVE_CONTROL                        0x1d9C
-#define MV64340_PCI_0_COMMAND			         	    0xc00
-#define MV64340_PCI_1_COMMAND					    0xc80
-#define MV64340_PCI_0_MODE                                          0xd00
-#define MV64340_PCI_1_MODE                                          0xd80
-#define MV64340_PCI_0_RETRY	        	 		    0xc04
-#define MV64340_PCI_1_RETRY				            0xc84
-#define MV64340_PCI_0_READ_BUFFER_DISCARD_TIMER                     0xd04
-#define MV64340_PCI_1_READ_BUFFER_DISCARD_TIMER                     0xd84
-#define MV64340_PCI_0_MSI_TRIGGER_TIMER                             0xc38
-#define MV64340_PCI_1_MSI_TRIGGER_TIMER                             0xcb8
-#define MV64340_PCI_0_ARBITER_CONTROL                               0x1d00
-#define MV64340_PCI_1_ARBITER_CONTROL                               0x1d80
-#define MV64340_PCI_0_CROSS_BAR_CONTROL_LOW                         0x1d08
-#define MV64340_PCI_1_CROSS_BAR_CONTROL_LOW                         0x1d88
-#define MV64340_PCI_0_CROSS_BAR_CONTROL_HIGH                        0x1d0c
-#define MV64340_PCI_1_CROSS_BAR_CONTROL_HIGH                        0x1d8c
-#define MV64340_PCI_0_CROSS_BAR_TIMEOUT                             0x1d04
-#define MV64340_PCI_1_CROSS_BAR_TIMEOUT                             0x1d84
-#define MV64340_PCI_0_SYNC_BARRIER_TRIGGER_REG                      0x1D18
-#define MV64340_PCI_1_SYNC_BARRIER_TRIGGER_REG                      0x1D98
-#define MV64340_PCI_0_SYNC_BARRIER_VIRTUAL_REG                      0x1d10
-#define MV64340_PCI_1_SYNC_BARRIER_VIRTUAL_REG                      0x1d90
-#define MV64340_PCI_0_P2P_CONFIG                                    0x1d14
-#define MV64340_PCI_1_P2P_CONFIG                                    0x1d94
-
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_LOW                     0x1e00
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_HIGH                    0x1e04
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_0                         0x1e08
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_LOW                     0x1e10
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_HIGH                    0x1e14
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_1                         0x1e18
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_LOW                     0x1e20
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_HIGH                    0x1e24
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_2                         0x1e28
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_LOW                     0x1e30
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_HIGH                    0x1e34
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_3                         0x1e38
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_LOW                     0x1e40
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_HIGH                    0x1e44
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_4                         0x1e48
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_LOW                     0x1e50
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_HIGH                    0x1e54
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_5                         0x1e58
-
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_LOW                     0x1e80
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_HIGH                    0x1e84
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_0                         0x1e88
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_LOW                     0x1e90
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_HIGH                    0x1e94
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_1                         0x1e98
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_LOW                     0x1ea0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_HIGH                    0x1ea4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_2                         0x1ea8
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_LOW                     0x1eb0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_HIGH                    0x1eb4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_3                         0x1eb8
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_LOW                     0x1ec0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_HIGH                    0x1ec4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_4                         0x1ec8
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_LOW                     0x1ed0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_HIGH                    0x1ed4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_5                         0x1ed8
-
-/****************************************/
-/*   PCI Configuration Access Registers */
-/****************************************/
-
-#define MV64340_PCI_0_CONFIG_ADDR 				    0xcf8
-#define MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG                       0xcfc
-#define MV64340_PCI_1_CONFIG_ADDR 				    0xc78
-#define MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG                       0xc7c
-#define MV64340_PCI_0_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG	            0xc34
-#define MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG	            0xcb4
-
-/****************************************/
-/*   PCI Error Report Registers         */
-/****************************************/
-
-#define MV64340_PCI_0_SERR_MASK					    0xc28
-#define MV64340_PCI_1_SERR_MASK					    0xca8
-#define MV64340_PCI_0_ERROR_ADDR_LOW                                0x1d40
-#define MV64340_PCI_1_ERROR_ADDR_LOW                                0x1dc0
-#define MV64340_PCI_0_ERROR_ADDR_HIGH                               0x1d44
-#define MV64340_PCI_1_ERROR_ADDR_HIGH                               0x1dc4
-#define MV64340_PCI_0_ERROR_ATTRIBUTE                               0x1d48
-#define MV64340_PCI_1_ERROR_ATTRIBUTE                               0x1dc8
-#define MV64340_PCI_0_ERROR_COMMAND                                 0x1d50
-#define MV64340_PCI_1_ERROR_COMMAND                                 0x1dd0
-#define MV64340_PCI_0_ERROR_CAUSE                                   0x1d58
-#define MV64340_PCI_1_ERROR_CAUSE                                   0x1dd8
-#define MV64340_PCI_0_ERROR_MASK                                    0x1d5c
-#define MV64340_PCI_1_ERROR_MASK                                    0x1ddc
-
-/****************************************/
-/*   PCI Debug Registers                */
-/****************************************/
-
-#define MV64340_PCI_0_MMASK                                         0X1D24
-#define MV64340_PCI_1_MMASK                                         0X1DA4
-
-/*********************************************/
-/* PCI Configuration, Function 0, Registers  */
-/*********************************************/
-
-#define MV64340_PCI_DEVICE_AND_VENDOR_ID 			    0x000
-#define MV64340_PCI_STATUS_AND_COMMAND				    0x004
-#define MV64340_PCI_CLASS_CODE_AND_REVISION_ID			    0x008
-#define MV64340_PCI_BIST_HEADER_TYPE_LATENCY_TIMER_CACHE_LINE 	    0x00C
-
-#define MV64340_PCI_SCS_0_BASE_ADDR_LOW   	      		    0x010
-#define MV64340_PCI_SCS_0_BASE_ADDR_HIGH   		            0x014
-#define MV64340_PCI_SCS_1_BASE_ADDR_LOW  	     	            0x018
-#define MV64340_PCI_SCS_1_BASE_ADDR_HIGH 		            0x01C
-#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_LOW      	    0x020
-#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_HIGH     	    0x024
-#define MV64340_PCI_SUBSYSTEM_ID_AND_SUBSYSTEM_VENDOR_ID	    0x02c
-#define MV64340_PCI_EXPANSION_ROM_BASE_ADDR_REG	                    0x030
-#define MV64340_PCI_CAPABILTY_LIST_POINTER                          0x034
-#define MV64340_PCI_INTERRUPT_PIN_AND_LINE 			    0x03C
-       /* capability list */
-#define MV64340_PCI_POWER_MANAGEMENT_CAPABILITY                     0x040
-#define MV64340_PCI_POWER_MANAGEMENT_STATUS_AND_CONTROL             0x044
-#define MV64340_PCI_VPD_ADDR                                        0x048
-#define MV64340_PCI_VPD_DATA                                        0x04c
-#define MV64340_PCI_MSI_MESSAGE_CONTROL                             0x050
-#define MV64340_PCI_MSI_MESSAGE_ADDR                                0x054
-#define MV64340_PCI_MSI_MESSAGE_UPPER_ADDR                          0x058
-#define MV64340_PCI_MSI_MESSAGE_DATA                                0x05c
-#define MV64340_PCI_X_COMMAND                                       0x060
-#define MV64340_PCI_X_STATUS                                        0x064
-#define MV64340_PCI_COMPACT_PCI_HOT_SWAP                            0x068
-
-/***********************************************/
-/*   PCI Configuration, Function 1, Registers  */
-/***********************************************/
-
-#define MV64340_PCI_SCS_2_BASE_ADDR_LOW   			    0x110
-#define MV64340_PCI_SCS_2_BASE_ADDR_HIGH			    0x114
-#define MV64340_PCI_SCS_3_BASE_ADDR_LOW 			    0x118
-#define MV64340_PCI_SCS_3_BASE_ADDR_HIGH			    0x11c
-#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_LOW          	    0x120
-#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_HIGH         	    0x124
-
-/***********************************************/
-/*  PCI Configuration, Function 2, Registers   */
-/***********************************************/
-
-#define MV64340_PCI_DEVCS_0_BASE_ADDR_LOW	    		    0x210
-#define MV64340_PCI_DEVCS_0_BASE_ADDR_HIGH 			    0x214
-#define MV64340_PCI_DEVCS_1_BASE_ADDR_LOW 			    0x218
-#define MV64340_PCI_DEVCS_1_BASE_ADDR_HIGH      		    0x21c
-#define MV64340_PCI_DEVCS_2_BASE_ADDR_LOW 			    0x220
-#define MV64340_PCI_DEVCS_2_BASE_ADDR_HIGH      		    0x224
-
-/***********************************************/
-/*  PCI Configuration, Function 3, Registers   */
-/***********************************************/
-
-#define MV64340_PCI_DEVCS_3_BASE_ADDR_LOW	    		    0x310
-#define MV64340_PCI_DEVCS_3_BASE_ADDR_HIGH 			    0x314
-#define MV64340_PCI_BOOT_CS_BASE_ADDR_LOW			    0x318
-#define MV64340_PCI_BOOT_CS_BASE_ADDR_HIGH      		    0x31c
-#define MV64340_PCI_CPU_BASE_ADDR_LOW 				    0x220
-#define MV64340_PCI_CPU_BASE_ADDR_HIGH      			    0x224
-
-/***********************************************/
-/*  PCI Configuration, Function 4, Registers   */
-/***********************************************/
-
-#define MV64340_PCI_P2P_MEM0_BASE_ADDR_LOW  			    0x410
-#define MV64340_PCI_P2P_MEM0_BASE_ADDR_HIGH 			    0x414
-#define MV64340_PCI_P2P_MEM1_BASE_ADDR_LOW   			    0x418
-#define MV64340_PCI_P2P_MEM1_BASE_ADDR_HIGH 			    0x41c
-#define MV64340_PCI_P2P_I_O_BASE_ADDR                 	            0x420
-#define MV64340_PCI_INTERNAL_REGS_I_O_MAPPED_BASE_ADDR              0x424
-
-/****************************************/
-/* Messaging Unit Registers (I20)   	*/
-/****************************************/
-
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_0_SIDE		    0x010
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_0_SIDE  		    0x014
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_0_SIDE 		    0x018
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_0_SIDE  		    0x01C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_0_SIDE  		    0x020
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE          0x024
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE	    0x028
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_0_SIDE 		    0x02C
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE         0x030
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE          0x034
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE       0x040
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE      0x044
-#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_0_SIDE 		    0x050
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_0_SIDE 		    0x054
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE        0x060
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE        0x064
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE        0x068
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE        0x06C
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE       0x070
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE       0x074
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE       0x0F8
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE       0x0FC
-
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_1_SIDE		    0x090
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_1_SIDE  		    0x094
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_1_SIDE 		    0x098
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_1_SIDE  		    0x09C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_1_SIDE  		    0x0A0
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE          0x0A4
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE	    0x0A8
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_1_SIDE 		    0x0AC
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE         0x0B0
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE          0x0B4
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE       0x0C0
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE      0x0C4
-#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_1_SIDE 		    0x0D0
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_1_SIDE 		    0x0D4
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE        0x0E0
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE        0x0E4
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE        0x0E8
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE        0x0EC
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE       0x0F0
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE       0x0F4
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE       0x078
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE       0x07C
-
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU0_SIDE		    0x1C10
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU0_SIDE  		    0x1C14
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU0_SIDE 		    0x1C18
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU0_SIDE  		    0x1C1C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU0_SIDE  		    0x1C20
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE  	    0x1C24
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU0_SIDE	    0x1C28
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU0_SIDE 		    0x1C2C
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE          0x1C30
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU0_SIDE           0x1C34
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE        0x1C40
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE       0x1C44
-#define MV64340_I2O_QUEUE_CONTROL_REG_CPU0_SIDE 		    0x1C50
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU0_SIDE 		    0x1C54
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE         0x1C60
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE         0x1C64
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE         0x1C68
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE         0x1C6C
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE        0x1C70
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE        0x1C74
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE        0x1CF8
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE        0x1CFC
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU1_SIDE		    0x1C90
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU1_SIDE  		    0x1C94
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU1_SIDE 		    0x1C98
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU1_SIDE  		    0x1C9C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU1_SIDE  		    0x1CA0
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE  	    0x1CA4
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU1_SIDE	    0x1CA8
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU1_SIDE 		    0x1CAC
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE          0x1CB0
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU1_SIDE           0x1CB4
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE        0x1CC0
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE       0x1CC4
-#define MV64340_I2O_QUEUE_CONTROL_REG_CPU1_SIDE 		    0x1CD0
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU1_SIDE 		    0x1CD4
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE         0x1CE0
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE         0x1CE4
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE         0x1CE8
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE         0x1CEC
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE        0x1CF0
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE        0x1CF4
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE        0x1C78
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE        0x1C7C
-
-/****************************************/
-/*        Ethernet Unit Registers  		*/
-/****************************************/
-
-/*******************************************/
-/*          CUNIT  Registers               */
-/*******************************************/
-
-         /* Address Decoding Register Map */
-           
-#define MV64340_CUNIT_BASE_ADDR_REG0                                0xf200
-#define MV64340_CUNIT_BASE_ADDR_REG1                                0xf208
-#define MV64340_CUNIT_BASE_ADDR_REG2                                0xf210
-#define MV64340_CUNIT_BASE_ADDR_REG3                                0xf218
-#define MV64340_CUNIT_SIZE0                                         0xf204
-#define MV64340_CUNIT_SIZE1                                         0xf20c
-#define MV64340_CUNIT_SIZE2                                         0xf214
-#define MV64340_CUNIT_SIZE3                                         0xf21c
-#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG0                          0xf240
-#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG1                          0xf244
-#define MV64340_CUNIT_BASE_ADDR_ENABLE_REG                          0xf250
-#define MV64340_MPSC0_ACCESS_PROTECTION_REG                         0xf254
-#define MV64340_MPSC1_ACCESS_PROTECTION_REG                         0xf258
-#define MV64340_CUNIT_INTERNAL_SPACE_BASE_ADDR_REG                  0xf25C
-
-        /*  Error Report Registers  */
-
-#define MV64340_CUNIT_INTERRUPT_CAUSE_REG                           0xf310
-#define MV64340_CUNIT_INTERRUPT_MASK_REG                            0xf314
-#define MV64340_CUNIT_ERROR_ADDR                                    0xf318
-
-        /*  Cunit Control Registers */
-
-#define MV64340_CUNIT_ARBITER_CONTROL_REG                           0xf300
-#define MV64340_CUNIT_CONFIG_REG                                    0xb40c
-#define MV64340_CUNIT_CRROSBAR_TIMEOUT_REG                          0xf304
-
-        /*  Cunit Debug Registers   */
-
-#define MV64340_CUNIT_DEBUG_LOW                                     0xf340
-#define MV64340_CUNIT_DEBUG_HIGH                                    0xf344
-#define MV64340_CUNIT_MMASK                                         0xf380
-
-        /*  MPSCs Clocks Routing Registers  */
-
-#define MV64340_MPSC_ROUTING_REG                                    0xb400
-#define MV64340_MPSC_RX_CLOCK_ROUTING_REG                           0xb404
-#define MV64340_MPSC_TX_CLOCK_ROUTING_REG                           0xb408
-
-        /*  MPSCs Interrupts Registers    */
-
-#define MV64340_MPSC_CAUSE_REG(port)                               (0xb804 + (port<<3))
-#define MV64340_MPSC_MASK_REG(port)                                (0xb884 + (port<<3))
- 
-#define MV64340_MPSC_MAIN_CONFIG_LOW(port)                         (0x8000 + (port<<12))
-#define MV64340_MPSC_MAIN_CONFIG_HIGH(port)                        (0x8004 + (port<<12))    
-#define MV64340_MPSC_PROTOCOL_CONFIG(port)                         (0x8008 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG1(port)                            (0x800c + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG2(port)                            (0x8010 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG3(port)                            (0x8014 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG4(port)                            (0x8018 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG5(port)                            (0x801c + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG6(port)                            (0x8020 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG7(port)                            (0x8024 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG8(port)                            (0x8028 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG9(port)                            (0x802c + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG10(port)                           (0x8030 + (port<<12))    
-        
-        /*  MPSC0 Registers      */
-
-
-/***************************************/
-/*          SDMA Registers             */
-/***************************************/
-
-#define MV64340_SDMA_CONFIG_REG(channel)                        (0x4000 + (channel<<13))        
-#define MV64340_SDMA_COMMAND_REG(channel)                       (0x4008 + (channel<<13))        
-#define MV64340_SDMA_CURRENT_RX_DESCRIPTOR_POINTER(channel)     (0x4810 + (channel<<13))        
-#define MV64340_SDMA_CURRENT_TX_DESCRIPTOR_POINTER(channel)     (0x4c10 + (channel<<13))        
-#define MV64340_SDMA_FIRST_TX_DESCRIPTOR_POINTER(channel)       (0x4c14 + (channel<<13)) 
-
-#define MV64340_SDMA_CAUSE_REG                                      0xb800
-#define MV64340_SDMA_MASK_REG                                       0xb880
-         
-/* BRG Interrupts */
-
-#define MV64340_BRG_CONFIG_REG(brg)                              (0xb200 + (brg<<3))
-#define MV64340_BRG_BAUDE_TUNING_REG(brg)                        (0xb208 + (brg<<3))
-#define MV64340_BRG_CAUSE_REG                                       0xb834
-#define MV64340_BRG_MASK_REG                                        0xb8b4
-
-/****************************************/
-/* DMA Channel Control			*/
-/****************************************/
-
-#define MV64340_DMA_CHANNEL0_CONTROL 				    0x840
-#define MV64340_DMA_CHANNEL0_CONTROL_HIGH			    0x880
-#define MV64340_DMA_CHANNEL1_CONTROL 				    0x844
-#define MV64340_DMA_CHANNEL1_CONTROL_HIGH			    0x884
-#define MV64340_DMA_CHANNEL2_CONTROL 				    0x848
-#define MV64340_DMA_CHANNEL2_CONTROL_HIGH			    0x888
-#define MV64340_DMA_CHANNEL3_CONTROL 				    0x84C
-#define MV64340_DMA_CHANNEL3_CONTROL_HIGH			    0x88C
-
-
-/****************************************/
-/*           IDMA Registers             */
-/****************************************/
-
-#define MV64340_DMA_CHANNEL0_BYTE_COUNT                             0x800
-#define MV64340_DMA_CHANNEL1_BYTE_COUNT                             0x804
-#define MV64340_DMA_CHANNEL2_BYTE_COUNT                             0x808
-#define MV64340_DMA_CHANNEL3_BYTE_COUNT                             0x80C
-#define MV64340_DMA_CHANNEL0_SOURCE_ADDR                            0x810
-#define MV64340_DMA_CHANNEL1_SOURCE_ADDR                            0x814
-#define MV64340_DMA_CHANNEL2_SOURCE_ADDR                            0x818
-#define MV64340_DMA_CHANNEL3_SOURCE_ADDR                            0x81c
-#define MV64340_DMA_CHANNEL0_DESTINATION_ADDR                       0x820
-#define MV64340_DMA_CHANNEL1_DESTINATION_ADDR                       0x824
-#define MV64340_DMA_CHANNEL2_DESTINATION_ADDR                       0x828
-#define MV64340_DMA_CHANNEL3_DESTINATION_ADDR                       0x82C
-#define MV64340_DMA_CHANNEL0_NEXT_DESCRIPTOR_POINTER                0x830
-#define MV64340_DMA_CHANNEL1_NEXT_DESCRIPTOR_POINTER                0x834
-#define MV64340_DMA_CHANNEL2_NEXT_DESCRIPTOR_POINTER                0x838
-#define MV64340_DMA_CHANNEL3_NEXT_DESCRIPTOR_POINTER                0x83C
-#define MV64340_DMA_CHANNEL0_CURRENT_DESCRIPTOR_POINTER             0x870
-#define MV64340_DMA_CHANNEL1_CURRENT_DESCRIPTOR_POINTER             0x874
-#define MV64340_DMA_CHANNEL2_CURRENT_DESCRIPTOR_POINTER             0x878
-#define MV64340_DMA_CHANNEL3_CURRENT_DESCRIPTOR_POINTER             0x87C
-
- /*  IDMA Address Decoding Base Address Registers  */
- 
-#define MV64340_DMA_BASE_ADDR_REG0                                  0xa00
-#define MV64340_DMA_BASE_ADDR_REG1                                  0xa08
-#define MV64340_DMA_BASE_ADDR_REG2                                  0xa10
-#define MV64340_DMA_BASE_ADDR_REG3                                  0xa18
-#define MV64340_DMA_BASE_ADDR_REG4                                  0xa20
-#define MV64340_DMA_BASE_ADDR_REG5                                  0xa28
-#define MV64340_DMA_BASE_ADDR_REG6                                  0xa30
-#define MV64340_DMA_BASE_ADDR_REG7                                  0xa38
- 
- /*  IDMA Address Decoding Size Address Register   */
- 
-#define MV64340_DMA_SIZE_REG0                                       0xa04
-#define MV64340_DMA_SIZE_REG1                                       0xa0c
-#define MV64340_DMA_SIZE_REG2                                       0xa14
-#define MV64340_DMA_SIZE_REG3                                       0xa1c
-#define MV64340_DMA_SIZE_REG4                                       0xa24
-#define MV64340_DMA_SIZE_REG5                                       0xa2c
-#define MV64340_DMA_SIZE_REG6                                       0xa34
-#define MV64340_DMA_SIZE_REG7                                       0xa3C
-
- /* IDMA Address Decoding High Address Remap and Access 
-                  Protection Registers                    */
-                  
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG0                            0xa60
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG1                            0xa64
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG2                            0xa68
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG3                            0xa6C
-#define MV64340_DMA_BASE_ADDR_ENABLE_REG                            0xa80
-#define MV64340_DMA_CHANNEL0_ACCESS_PROTECTION_REG                  0xa70
-#define MV64340_DMA_CHANNEL1_ACCESS_PROTECTION_REG                  0xa74
-#define MV64340_DMA_CHANNEL2_ACCESS_PROTECTION_REG                  0xa78
-#define MV64340_DMA_CHANNEL3_ACCESS_PROTECTION_REG                  0xa7c
-#define MV64340_DMA_ARBITER_CONTROL                                 0x860
-#define MV64340_DMA_CROSS_BAR_TIMEOUT                               0x8d0
-
- /*  IDMA Headers Retarget Registers   */
-
-#define MV64340_DMA_HEADERS_RETARGET_CONTROL                        0xa84
-#define MV64340_DMA_HEADERS_RETARGET_BASE                           0xa88
-
- /*  IDMA Interrupt Register  */
-
-#define MV64340_DMA_INTERRUPT_CAUSE_REG                             0x8c0
-#define MV64340_DMA_INTERRUPT_CAUSE_MASK                            0x8c4
-#define MV64340_DMA_ERROR_ADDR                                      0x8c8
-#define MV64340_DMA_ERROR_SELECT                                    0x8cc
-
- /*  IDMA Debug Register ( for internal use )    */
-
-#define MV64340_DMA_DEBUG_LOW                                       0x8e0
-#define MV64340_DMA_DEBUG_HIGH                                      0x8e4
-#define MV64340_DMA_SPARE                                           0xA8C
-
-/****************************************/
-/* Timer_Counter 			*/
-/****************************************/
-
-#define MV64340_TIMER_COUNTER0					    0x850
-#define MV64340_TIMER_COUNTER1					    0x854
-#define MV64340_TIMER_COUNTER2					    0x858
-#define MV64340_TIMER_COUNTER3					    0x85C
-#define MV64340_TIMER_COUNTER_0_3_CONTROL			    0x864
-#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_CAUSE		    0x868
-#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_MASK      		    0x86c
-
-/****************************************/
-/*         Watchdog registers  	        */
-/****************************************/
-
-#define MV64340_WATCHDOG_CONFIG_REG                                 0xb410
-#define MV64340_WATCHDOG_VALUE_REG                                  0xb414
-
-/****************************************/
-/* I2C Registers                        */
-/****************************************/
-
-#define MV64XXX_I2C_OFFSET                                          0xc000
-#define MV64XXX_I2C_REG_BLOCK_SIZE                                  0x0020
-
-/****************************************/
-/* GPP Interface Registers              */
-/****************************************/
-
-#define MV64340_GPP_IO_CONTROL                                      0xf100
-#define MV64340_GPP_LEVEL_CONTROL                                   0xf110
-#define MV64340_GPP_VALUE                                           0xf104
-#define MV64340_GPP_INTERRUPT_CAUSE                                 0xf108
-#define MV64340_GPP_INTERRUPT_MASK0                                 0xf10c
-#define MV64340_GPP_INTERRUPT_MASK1                                 0xf114
-#define MV64340_GPP_VALUE_SET                                       0xf118
-#define MV64340_GPP_VALUE_CLEAR                                     0xf11c
-
-/****************************************/
-/* Interrupt Controller Registers       */
-/****************************************/
-
-/****************************************/
-/* Interrupts	  			*/
-/****************************************/
-
-#define MV64340_MAIN_INTERRUPT_CAUSE_LOW                            0x004
-#define MV64340_MAIN_INTERRUPT_CAUSE_HIGH                           0x00c
-#define MV64340_CPU_INTERRUPT0_MASK_LOW                             0x014
-#define MV64340_CPU_INTERRUPT0_MASK_HIGH                            0x01c
-#define MV64340_CPU_INTERRUPT0_SELECT_CAUSE                         0x024
-#define MV64340_CPU_INTERRUPT1_MASK_LOW                             0x034
-#define MV64340_CPU_INTERRUPT1_MASK_HIGH                            0x03c
-#define MV64340_CPU_INTERRUPT1_SELECT_CAUSE                         0x044
-#define MV64340_INTERRUPT0_MASK_0_LOW                               0x054
-#define MV64340_INTERRUPT0_MASK_0_HIGH                              0x05c
-#define MV64340_INTERRUPT0_SELECT_CAUSE                             0x064
-#define MV64340_INTERRUPT1_MASK_0_LOW                               0x074
-#define MV64340_INTERRUPT1_MASK_0_HIGH                              0x07c
-#define MV64340_INTERRUPT1_SELECT_CAUSE                             0x084
-
-/****************************************/
-/*      MPP Interface Registers         */
-/****************************************/
-
-#define MV64340_MPP_CONTROL0                                        0xf000
-#define MV64340_MPP_CONTROL1                                        0xf004
-#define MV64340_MPP_CONTROL2                                        0xf008
-#define MV64340_MPP_CONTROL3                                        0xf00c
-
-/****************************************/
-/*    Serial Initialization registers   */
-/****************************************/
-
-#define MV64340_SERIAL_INIT_LAST_DATA                               0xf324
-#define MV64340_SERIAL_INIT_CONTROL                                 0xf328
-#define MV64340_SERIAL_INIT_STATUS                                  0xf32c
-
-extern void mv64340_irq_init(unsigned int base);
-
-#endif /* __ASM_MV643XX_H */
-- 
cgit v1.3-3-g829e


From 37551b4540bdc14c9fc530eca824124cf4ccfd35 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 12 Sep 2024 11:57:06 +0300
Subject: rtase: Fix error code in rtase_init_board()

Return an error if dma_set_mask_and_coherent() fails.  Don't return
success.

Fixes: a36e9f5cfe9e ("rtase: Add support for a pci table in this module")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/f53ed942-5ac2-424b-a1ed-9473c599905e@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 869183e1565e..f8777b7663d3 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -2023,7 +2023,8 @@ static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out,
 	if (ret < 0)
 		goto err_out_disable;
 
-	if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret) {
 		dev_err(&pdev->dev, "no usable dma addressing method\n");
 		goto err_out_free_res;
 	}
-- 
cgit v1.3-3-g829e


From 1ad84a151af7f4b3933983677bc75074f957bdf5 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 13 Sep 2024 12:05:14 +0200
Subject: net: ethtool: phy: Don't set the context dev pointer for unfiltered
 DUMP

The context info allows continuing DUMP requests, shall they fill the
netlink buffer.

In the case of filtered DUMP requests, a reference on the netdev is
grabbed in the .start() callback and release in .done().

Unfiltered DUMP request don't need the dev pointer to be set in the context
info, doing so will trigger an unwanted netdev_put() in .done().

Reported-by: syzbot+e9ed4e4368d450c8f9db@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/000000000000d3bf150621d361a7@google.com/
Fixes: 17194be4c8e1 ("net: ethtool: Introduce a command to list PHYs on an interface")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20240913100515.167341-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/phy.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index 4ef7c6e32d10..ed8f690f6bac 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -251,8 +251,6 @@ static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
 	int ret = 0;
 	void *ehdr;
 
-	pri->base.dev = dev;
-
 	if (!dev->link_topo)
 		return 0;
 
-- 
cgit v1.3-3-g829e


From beb2baa9e54d7383618589f2f78721654231452e Mon Sep 17 00:00:00 2001
From: Linu Cherian <lcherian@marvell.com>
Date: Thu, 12 Sep 2024 21:44:50 +0530
Subject: octeontx2-af: debugfs: Add Channel info to RPM map

Display channel info in the RPM map debugfs output.

With this, cat /sys/kernel/debug/cn10k/rvu_pf_rpm_map
would display channel number for each device in addition to
the existing data.

Sample output:
PCI dev         RVU PF Func     NIX block       rpm     LMAC    CHAN
0002:02:00.0    0x400           NIX0            rpm0    LMAC0   256

Signed-off-by: Linu Cherian <lcherian@marvell.com>
Link: https://patch.msgid.link/20240912161450.164402-3-lcherian@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 4a4ef5bd9e0b..87ba77e5026a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -838,10 +838,10 @@ RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL);
 
 static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 {
+	char cgx[10], lmac[10], chan[10];
 	struct rvu *rvu = filp->private;
 	struct pci_dev *pdev = NULL;
 	struct mac_ops *mac_ops;
-	char cgx[10], lmac[10];
 	struct rvu_pfvf *pfvf;
 	int pf, domain, blkid;
 	u8 cgx_id, lmac_id;
@@ -852,7 +852,7 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 	/* There can be no CGX devices at all */
 	if (!mac_ops)
 		return 0;
-	seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\n",
+	seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\tCHAN\n",
 		   mac_ops->name);
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		if (!is_pf_cgxmapped(rvu, pf))
@@ -876,8 +876,11 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 				    &lmac_id);
 		sprintf(cgx, "%s%d", mac_ops->name, cgx_id);
 		sprintf(lmac, "LMAC%d", lmac_id);
-		seq_printf(filp, "%s\t0x%x\t\tNIX%d\t\t%s\t%s\n",
-			   dev_name(&pdev->dev), pcifunc, blkid, cgx, lmac);
+		sprintf(chan, "%d",
+			rvu_nix_chan_cgx(rvu, cgx_id, lmac_id, 0));
+		seq_printf(filp, "%s\t0x%x\t\tNIX%d\t\t%s\t%s\t%s\n",
+			   dev_name(&pdev->dev), pcifunc, blkid, cgx, lmac,
+			   chan);
 
 		pci_dev_put(pdev);
 	}
-- 
cgit v1.3-3-g829e


From b9758c434284272e24d6fdc9e71166c7e4f40ffb Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:48:55 -0700
Subject: net: ibm: emac: use devm for alloc_etherdev

Allows to simplify the code slightly. This is safe to do as free_netdev
gets called last.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-2-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 6ace55837172..0e94b3899078 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -3053,7 +3053,7 @@ static int emac_probe(struct platform_device *ofdev)
 
 	/* Allocate our net_device structure */
 	err = -ENOMEM;
-	ndev = alloc_etherdev(sizeof(struct emac_instance));
+	ndev = devm_alloc_etherdev(&ofdev->dev, sizeof(struct emac_instance));
 	if (!ndev)
 		goto err_gone;
 
@@ -3072,7 +3072,7 @@ static int emac_probe(struct platform_device *ofdev)
 	/* Init various config data based on device-tree */
 	err = emac_init_config(dev);
 	if (err)
-		goto err_free;
+		goto err_gone;
 
 	/* Get interrupts. EMAC irq is mandatory, WOL irq is optional */
 	dev->emac_irq = irq_of_parse_and_map(np, 0);
@@ -3080,7 +3080,7 @@ static int emac_probe(struct platform_device *ofdev)
 	if (!dev->emac_irq) {
 		printk(KERN_ERR "%pOF: Can't map main interrupt\n", np);
 		err = -ENODEV;
-		goto err_free;
+		goto err_gone;
 	}
 	ndev->irq = dev->emac_irq;
 
@@ -3239,8 +3239,6 @@ static int emac_probe(struct platform_device *ofdev)
 		irq_dispose_mapping(dev->wol_irq);
 	if (dev->emac_irq)
 		irq_dispose_mapping(dev->emac_irq);
- err_free:
-	free_netdev(ndev);
  err_gone:
 	/* if we were on the bootlist, remove us as we won't show up and
 	 * wake up all waiters to notify them in case they were waiting
@@ -3289,7 +3287,6 @@ static void emac_remove(struct platform_device *ofdev)
 	if (dev->emac_irq)
 		irq_dispose_mapping(dev->emac_irq);
 
-	free_netdev(dev->ndev);
 }
 
 /* XXX Features in here should be replaced by properties... */
-- 
cgit v1.3-3-g829e


From dcc34ef7c83473222027f475014a2bf8ab798372 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:48:56 -0700
Subject: net: ibm: emac: manage emac_irq with devm

It's the last to go in remove. Safe to let devm handle it.

Also move request_irq to probe for clarity. It's removed in _remove not
close.

Use dev_err_probe instead of printk. Handles EPROBE_DEFER automatically.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-3-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 0e94b3899078..d1e1b3a09209 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1228,18 +1228,10 @@ static void emac_print_link_status(struct emac_instance *dev)
 static int emac_open(struct net_device *ndev)
 {
 	struct emac_instance *dev = netdev_priv(ndev);
-	int err, i;
+	int i;
 
 	DBG(dev, "open" NL);
 
-	/* Setup error IRQ handler */
-	err = request_irq(dev->emac_irq, emac_irq, 0, "EMAC", dev);
-	if (err) {
-		printk(KERN_ERR "%s: failed to request IRQ %d\n",
-		       ndev->name, dev->emac_irq);
-		return err;
-	}
-
 	/* Allocate RX ring */
 	for (i = 0; i < NUM_RX_BUFF; ++i)
 		if (emac_alloc_rx_skb(dev, i)) {
@@ -1293,8 +1285,6 @@ static int emac_open(struct net_device *ndev)
 	return 0;
  oom:
 	emac_clean_rx_ring(dev);
-	free_irq(dev->emac_irq, dev);
-
 	return -ENOMEM;
 }
 
@@ -1408,8 +1398,6 @@ static int emac_close(struct net_device *ndev)
 	emac_clean_tx_ring(dev);
 	emac_clean_rx_ring(dev);
 
-	free_irq(dev->emac_irq, dev);
-
 	netif_carrier_off(ndev);
 
 	return 0;
@@ -3082,6 +3070,16 @@ static int emac_probe(struct platform_device *ofdev)
 		err = -ENODEV;
 		goto err_gone;
 	}
+
+	/* Setup error IRQ handler */
+	err = devm_request_irq(&ofdev->dev, dev->emac_irq, emac_irq, 0, "EMAC",
+			       dev);
+	if (err) {
+		dev_err_probe(&ofdev->dev, err, "failed to request IRQ %d",
+			      dev->emac_irq);
+		goto err_gone;
+	}
+
 	ndev->irq = dev->emac_irq;
 
 	/* Map EMAC regs */
@@ -3237,8 +3235,6 @@ static int emac_probe(struct platform_device *ofdev)
  err_irq_unmap:
 	if (dev->wol_irq)
 		irq_dispose_mapping(dev->wol_irq);
-	if (dev->emac_irq)
-		irq_dispose_mapping(dev->emac_irq);
  err_gone:
 	/* if we were on the bootlist, remove us as we won't show up and
 	 * wake up all waiters to notify them in case they were waiting
@@ -3284,9 +3280,6 @@ static void emac_remove(struct platform_device *ofdev)
 
 	if (dev->wol_irq)
 		irq_dispose_mapping(dev->wol_irq);
-	if (dev->emac_irq)
-		irq_dispose_mapping(dev->emac_irq);
-
 }
 
 /* XXX Features in here should be replaced by properties... */
-- 
cgit v1.3-3-g829e


From 969b002d7b65062ab16fc6b6a444602a56b1e628 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:48:57 -0700
Subject: net: ibm: emac: use devm for of_iomap

Allows removing manual iounmap.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-4-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index d1e1b3a09209..ad361202e805 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -3084,9 +3084,9 @@ static int emac_probe(struct platform_device *ofdev)
 
 	/* Map EMAC regs */
 	// TODO : platform_get_resource() and devm_ioremap_resource()
-	dev->emacp = of_iomap(np, 0);
-	if (dev->emacp == NULL) {
-		printk(KERN_ERR "%pOF: Can't map device registers!\n", np);
+	dev->emacp = devm_of_iomap(&ofdev->dev, np, 0, NULL);
+	if (!dev->emacp) {
+		dev_err(&ofdev->dev, "can't map device registers");
 		err = -ENOMEM;
 		goto err_irq_unmap;
 	}
@@ -3097,7 +3097,7 @@ static int emac_probe(struct platform_device *ofdev)
 		printk(KERN_ERR
 		       "%pOF: Timeout waiting for dependent devices\n", np);
 		/*  display more info about what's missing ? */
-		goto err_reg_unmap;
+		goto err_irq_unmap;
 	}
 	dev->mal = platform_get_drvdata(dev->mal_dev);
 	if (dev->mdio_dev != NULL)
@@ -3230,8 +3230,6 @@ static int emac_probe(struct platform_device *ofdev)
 	mal_unregister_commac(dev->mal, &dev->commac);
  err_rel_deps:
 	emac_put_deps(dev);
- err_reg_unmap:
-	iounmap(dev->emacp);
  err_irq_unmap:
 	if (dev->wol_irq)
 		irq_dispose_mapping(dev->wol_irq);
@@ -3276,8 +3274,6 @@ static void emac_remove(struct platform_device *ofdev)
 	mal_unregister_commac(dev->mal, &dev->commac);
 	emac_put_deps(dev);
 
-	iounmap(dev->emacp);
-
 	if (dev->wol_irq)
 		irq_dispose_mapping(dev->wol_irq);
 }
-- 
cgit v1.3-3-g829e


From 93a6d4e03629067590219189eae6feba218650e1 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:48:58 -0700
Subject: net: ibm: emac: remove mii_bus with devm

Switching to devm management of mii_bus allows to remove
mdiobus_unregister calls and thus avoids needing a mii_bus global struct
member.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-5-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 32 +++++++++++++-------------------
 drivers/net/ethernet/ibm/emac/core.h |  1 -
 2 files changed, 13 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index ad361202e805..9596eca20317 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2581,6 +2581,7 @@ static const struct mii_phy_ops emac_dt_mdio_phy_ops = {
 static int emac_dt_mdio_probe(struct emac_instance *dev)
 {
 	struct device_node *mii_np;
+	struct mii_bus *bus;
 	int res;
 
 	mii_np = of_get_child_by_name(dev->ofdev->dev.of_node, "mdio");
@@ -2594,23 +2595,23 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
 		goto put_node;
 	}
 
-	dev->mii_bus = devm_mdiobus_alloc(&dev->ofdev->dev);
-	if (!dev->mii_bus) {
+	bus = devm_mdiobus_alloc(&dev->ofdev->dev);
+	if (!bus) {
 		res = -ENOMEM;
 		goto put_node;
 	}
 
-	dev->mii_bus->priv = dev->ndev;
-	dev->mii_bus->parent = dev->ndev->dev.parent;
-	dev->mii_bus->name = "emac_mdio";
-	dev->mii_bus->read = &emac_mii_bus_read;
-	dev->mii_bus->write = &emac_mii_bus_write;
-	dev->mii_bus->reset = &emac_mii_bus_reset;
-	snprintf(dev->mii_bus->id, MII_BUS_ID_SIZE, "%s", dev->ofdev->name);
-	res = of_mdiobus_register(dev->mii_bus, mii_np);
+	bus->priv = dev->ndev;
+	bus->parent = dev->ndev->dev.parent;
+	bus->name = "emac_mdio";
+	bus->read = &emac_mii_bus_read;
+	bus->write = &emac_mii_bus_write;
+	bus->reset = &emac_mii_bus_reset;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev->ofdev->name);
+	res = devm_of_mdiobus_register(&dev->ofdev->dev, bus, mii_np);
 	if (res) {
 		dev_err(&dev->ofdev->dev, "cannot register MDIO bus %s (%d)",
-			dev->mii_bus->name, res);
+			bus->name, res);
 	}
 
  put_node:
@@ -2656,8 +2657,6 @@ static int emac_dt_phy_probe(struct emac_instance *dev)
 		res = emac_dt_mdio_probe(dev);
 		if (!res) {
 			res = emac_dt_phy_connect(dev, phy_handle);
-			if (res)
-				mdiobus_unregister(dev->mii_bus);
 		}
 	}
 
@@ -2697,10 +2696,8 @@ static int emac_init_phy(struct emac_instance *dev)
 
 			res = of_phy_register_fixed_link(np);
 			dev->phy_dev = of_phy_find_device(np);
-			if (res || !dev->phy_dev) {
-				mdiobus_unregister(dev->mii_bus);
+			if (res || !dev->phy_dev)
 				return res ? res : -EINVAL;
-			}
 			emac_adjust_link(dev->ndev);
 			put_device(&dev->phy_dev->mdio.dev);
 		}
@@ -3265,9 +3262,6 @@ static void emac_remove(struct platform_device *ofdev)
 	if (dev->phy_dev)
 		phy_disconnect(dev->phy_dev);
 
-	if (dev->mii_bus)
-		mdiobus_unregister(dev->mii_bus);
-
 	busy_phy_map &= ~(1 << dev->phy.address);
 	DBG(dev, "busy_phy_map now %#x" NL, busy_phy_map);
 
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index d8664bd65e1f..5a9d4b56d7cf 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -189,7 +189,6 @@ struct emac_instance {
 	struct mutex			mdio_lock;
 
 	/* Device-tree based phy configuration */
-	struct mii_bus			*mii_bus;
 	struct phy_device		*phy_dev;
 
 	/* ZMII infos if any */
-- 
cgit v1.3-3-g829e


From a4dd8535a527061a01f2fd335596fa77ca240a96 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:48:59 -0700
Subject: net: ibm: emac: use devm for register_netdev

Cleans it up automatically. No need to handle manually.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-6-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 9596eca20317..65e78f9a5038 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -3182,7 +3182,7 @@ static int emac_probe(struct platform_device *ofdev)
 
 	netif_carrier_off(ndev);
 
-	err = register_netdev(ndev);
+	err = devm_register_netdev(&ofdev->dev, ndev);
 	if (err) {
 		printk(KERN_ERR "%pOF: failed to register net device (%d)!\n",
 		       np, err);
@@ -3248,8 +3248,6 @@ static void emac_remove(struct platform_device *ofdev)
 
 	DBG(dev, "remove" NL);
 
-	unregister_netdev(dev->ndev);
-
 	cancel_work_sync(&dev->reset_work);
 
 	if (emac_has_feature(dev, EMAC_FTR_HAS_TAH))
-- 
cgit v1.3-3-g829e


From baab9de385a880d1ce9c5fe6108b79e13f8a106d Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:49:00 -0700
Subject: net: ibm: emac: use netdev's phydev directly

Avoids having to use own struct member.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-7-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 49 ++++++++++++++++--------------------
 drivers/net/ethernet/ibm/emac/core.h |  3 ---
 2 files changed, 22 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 65e78f9a5038..f79481b6da30 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2459,7 +2459,7 @@ static int emac_read_uint_prop(struct device_node *np, const char *name,
 static void emac_adjust_link(struct net_device *ndev)
 {
 	struct emac_instance *dev = netdev_priv(ndev);
-	struct phy_device *phy = dev->phy_dev;
+	struct phy_device *phy = ndev->phydev;
 
 	dev->phy.autoneg = phy->autoneg;
 	dev->phy.speed = phy->speed;
@@ -2510,22 +2510,20 @@ static int emac_mdio_phy_start_aneg(struct mii_phy *phy,
 static int emac_mdio_setup_aneg(struct mii_phy *phy, u32 advertise)
 {
 	struct net_device *ndev = phy->dev;
-	struct emac_instance *dev = netdev_priv(ndev);
 
 	phy->autoneg = AUTONEG_ENABLE;
 	phy->advertising = advertise;
-	return emac_mdio_phy_start_aneg(phy, dev->phy_dev);
+	return emac_mdio_phy_start_aneg(phy, ndev->phydev);
 }
 
 static int emac_mdio_setup_forced(struct mii_phy *phy, int speed, int fd)
 {
 	struct net_device *ndev = phy->dev;
-	struct emac_instance *dev = netdev_priv(ndev);
 
 	phy->autoneg = AUTONEG_DISABLE;
 	phy->speed = speed;
 	phy->duplex = fd;
-	return emac_mdio_phy_start_aneg(phy, dev->phy_dev);
+	return emac_mdio_phy_start_aneg(phy, ndev->phydev);
 }
 
 static int emac_mdio_poll_link(struct mii_phy *phy)
@@ -2534,20 +2532,19 @@ static int emac_mdio_poll_link(struct mii_phy *phy)
 	struct emac_instance *dev = netdev_priv(ndev);
 	int res;
 
-	res = phy_read_status(dev->phy_dev);
+	res = phy_read_status(ndev->phydev);
 	if (res) {
 		dev_err(&dev->ofdev->dev, "link update failed (%d).", res);
 		return ethtool_op_get_link(ndev);
 	}
 
-	return dev->phy_dev->link;
+	return ndev->phydev->link;
 }
 
 static int emac_mdio_read_link(struct mii_phy *phy)
 {
 	struct net_device *ndev = phy->dev;
-	struct emac_instance *dev = netdev_priv(ndev);
-	struct phy_device *phy_dev = dev->phy_dev;
+	struct phy_device *phy_dev = ndev->phydev;
 	int res;
 
 	res = phy_read_status(phy_dev);
@@ -2564,10 +2561,9 @@ static int emac_mdio_read_link(struct mii_phy *phy)
 static int emac_mdio_init_phy(struct mii_phy *phy)
 {
 	struct net_device *ndev = phy->dev;
-	struct emac_instance *dev = netdev_priv(ndev);
 
-	phy_start(dev->phy_dev);
-	return phy_init_hw(dev->phy_dev);
+	phy_start(ndev->phydev);
+	return phy_init_hw(ndev->phydev);
 }
 
 static const struct mii_phy_ops emac_dt_mdio_phy_ops = {
@@ -2622,26 +2618,28 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
 static int emac_dt_phy_connect(struct emac_instance *dev,
 			       struct device_node *phy_handle)
 {
+	struct phy_device *phy_dev;
+
 	dev->phy.def = devm_kzalloc(&dev->ofdev->dev, sizeof(*dev->phy.def),
 				    GFP_KERNEL);
 	if (!dev->phy.def)
 		return -ENOMEM;
 
-	dev->phy_dev = of_phy_connect(dev->ndev, phy_handle, &emac_adjust_link,
-				      0, dev->phy_mode);
-	if (!dev->phy_dev) {
+	phy_dev = of_phy_connect(dev->ndev, phy_handle, &emac_adjust_link, 0,
+				 dev->phy_mode);
+	if (!phy_dev) {
 		dev_err(&dev->ofdev->dev, "failed to connect to PHY.\n");
 		return -ENODEV;
 	}
 
-	dev->phy.def->phy_id = dev->phy_dev->drv->phy_id;
-	dev->phy.def->phy_id_mask = dev->phy_dev->drv->phy_id_mask;
-	dev->phy.def->name = dev->phy_dev->drv->name;
+	dev->phy.def->phy_id = phy_dev->drv->phy_id;
+	dev->phy.def->phy_id_mask = phy_dev->drv->phy_id_mask;
+	dev->phy.def->name = phy_dev->drv->name;
 	dev->phy.def->ops = &emac_dt_mdio_phy_ops;
 	ethtool_convert_link_mode_to_legacy_u32(&dev->phy.features,
-						dev->phy_dev->supported);
-	dev->phy.address = dev->phy_dev->mdio.addr;
-	dev->phy.mode = dev->phy_dev->interface;
+						phy_dev->supported);
+	dev->phy.address = phy_dev->mdio.addr;
+	dev->phy.mode = phy_dev->interface;
 	return 0;
 }
 
@@ -2695,11 +2693,11 @@ static int emac_init_phy(struct emac_instance *dev)
 				return res;
 
 			res = of_phy_register_fixed_link(np);
-			dev->phy_dev = of_phy_find_device(np);
-			if (res || !dev->phy_dev)
+			ndev->phydev = of_phy_find_device(np);
+			if (res || !ndev->phydev)
 				return res ? res : -EINVAL;
 			emac_adjust_link(dev->ndev);
-			put_device(&dev->phy_dev->mdio.dev);
+			put_device(&ndev->phydev->mdio.dev);
 		}
 		return 0;
 	}
@@ -3257,9 +3255,6 @@ static void emac_remove(struct platform_device *ofdev)
 	if (emac_has_feature(dev, EMAC_FTR_HAS_ZMII))
 		zmii_detach(dev->zmii_dev, dev->zmii_port);
 
-	if (dev->phy_dev)
-		phy_disconnect(dev->phy_dev);
-
 	busy_phy_map &= ~(1 << dev->phy.address);
 	DBG(dev, "busy_phy_map now %#x" NL, busy_phy_map);
 
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 5a9d4b56d7cf..89fa1683ec3c 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -188,9 +188,6 @@ struct emac_instance {
 	struct emac_instance		*mdio_instance;
 	struct mutex			mdio_lock;
 
-	/* Device-tree based phy configuration */
-	struct phy_device		*phy_dev;
-
 	/* ZMII infos if any */
 	u32				zmii_ph;
 	u32				zmii_port;
-- 
cgit v1.3-3-g829e


From cc0c92ff662d642dec2e3b85ef14265677ba7fb9 Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:49:01 -0700
Subject: net: ibm: emac: replace of_get_property

of_property_read_u32 can be used.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-8-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index f79481b6da30..6556f9b2b48f 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2444,15 +2444,14 @@ static int emac_wait_deps(struct emac_instance *dev)
 static int emac_read_uint_prop(struct device_node *np, const char *name,
 			       u32 *val, int fatal)
 {
-	int len;
-	const u32 *prop = of_get_property(np, name, &len);
-	if (prop == NULL || len < sizeof(u32)) {
+	int err;
+
+	err = of_property_read_u32(np, name, val);
+	if (err) {
 		if (fatal)
-			printk(KERN_ERR "%pOF: missing %s property\n",
-			       np, name);
-		return -ENODEV;
+			pr_err("%pOF: missing %s property", np, name);
+		return err;
 	}
-	*val = *prop;
 	return 0;
 }
 
@@ -3301,16 +3300,15 @@ static void __init emac_make_bootlist(void)
 
 	/* Collect EMACs */
 	while((np = of_find_all_nodes(np)) != NULL) {
-		const u32 *idx;
+		u32 idx;
 
 		if (of_match_node(emac_match, np) == NULL)
 			continue;
 		if (of_property_read_bool(np, "unused"))
 			continue;
-		idx = of_get_property(np, "cell-index", NULL);
-		if (idx == NULL)
+		if (of_property_read_u32(np, "cell-index", &idx))
 			continue;
-		cell_indices[i] = *idx;
+		cell_indices[i] = idx;
 		emac_boot_list[i++] = of_node_get(np);
 		if (i >= EMAC_BOOT_LIST_SIZE) {
 			of_node_put(np);
-- 
cgit v1.3-3-g829e


From c092d0be38f4f754cdbdc76dc6df628ca48ac0eb Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:49:02 -0700
Subject: net: ibm: emac: remove all waiting code

EPROBE_DEFER, which probably wasn't available when this driver was
written, can be used instead of waiting manually.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Link: https://patch.msgid.link/20240912024903.6201-9-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 55 +++++-------------------------------
 1 file changed, 7 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 6556f9b2b48f..60c4943ca09d 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -32,7 +32,6 @@
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/bitops.h>
-#include <linux/workqueue.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -96,11 +95,6 @@ MODULE_LICENSE("GPL");
 static u32 busy_phy_map;
 static DEFINE_MUTEX(emac_phy_map_lock);
 
-/* This is the wait queue used to wait on any event related to probe, that
- * is discovery of MALs, other EMACs, ZMII/RGMIIs, etc...
- */
-static DECLARE_WAIT_QUEUE_HEAD(emac_probe_wait);
-
 /* Having stable interface names is a doomed idea. However, it would be nice
  * if we didn't have completely random interface names at boot too :-) It's
  * just a matter of making everybody's life easier. Since we are doing
@@ -116,9 +110,6 @@ static DECLARE_WAIT_QUEUE_HEAD(emac_probe_wait);
 #define EMAC_BOOT_LIST_SIZE	4
 static struct device_node *emac_boot_list[EMAC_BOOT_LIST_SIZE];
 
-/* How long should I wait for dependent devices ? */
-#define EMAC_PROBE_DEP_TIMEOUT	(HZ * 5)
-
 /* I don't want to litter system log with timeout errors
  * when we have brain-damaged PHY.
  */
@@ -973,8 +964,6 @@ static void __emac_set_multicast_list(struct emac_instance *dev)
 	 * we need is just to stop RX channel. This seems to work on all
 	 * tested SoCs.                                                --ebs
 	 *
-	 * If we need the full reset, we might just trigger the workqueue
-	 * and do it async... a bit nasty but should work --BenH
 	 */
 	dev->mcast_pending = 0;
 	emac_rx_disable(dev);
@@ -2378,7 +2367,9 @@ static int emac_check_deps(struct emac_instance *dev,
 		if (deps[i].drvdata != NULL)
 			there++;
 	}
-	return there == EMAC_DEP_COUNT;
+	if (there != EMAC_DEP_COUNT)
+		return -EPROBE_DEFER;
+	return 0;
 }
 
 static void emac_put_deps(struct emac_instance *dev)
@@ -2390,19 +2381,6 @@ static void emac_put_deps(struct emac_instance *dev)
 	platform_device_put(dev->tah_dev);
 }
 
-static int emac_of_bus_notify(struct notifier_block *nb, unsigned long action,
-			      void *data)
-{
-	/* We are only intereted in device addition */
-	if (action == BUS_NOTIFY_BOUND_DRIVER)
-		wake_up_all(&emac_probe_wait);
-	return 0;
-}
-
-static struct notifier_block emac_of_bus_notifier = {
-	.notifier_call = emac_of_bus_notify
-};
-
 static int emac_wait_deps(struct emac_instance *dev)
 {
 	struct emac_depentry deps[EMAC_DEP_COUNT];
@@ -2419,18 +2397,13 @@ static int emac_wait_deps(struct emac_instance *dev)
 		deps[EMAC_DEP_MDIO_IDX].phandle = dev->mdio_ph;
 	if (dev->blist && dev->blist > emac_boot_list)
 		deps[EMAC_DEP_PREV_IDX].phandle = 0xffffffffu;
-	bus_register_notifier(&platform_bus_type, &emac_of_bus_notifier);
-	wait_event_timeout(emac_probe_wait,
-			   emac_check_deps(dev, deps),
-			   EMAC_PROBE_DEP_TIMEOUT);
-	bus_unregister_notifier(&platform_bus_type, &emac_of_bus_notifier);
-	err = emac_check_deps(dev, deps) ? 0 : -ENODEV;
+	err = emac_check_deps(dev, deps);
 	for (i = 0; i < EMAC_DEP_COUNT; i++) {
 		of_node_put(deps[i].node);
 		if (err)
 			platform_device_put(deps[i].ofdev);
 	}
-	if (err == 0) {
+	if (!err) {
 		dev->mal_dev = deps[EMAC_DEP_MAL_IDX].ofdev;
 		dev->zmii_dev = deps[EMAC_DEP_ZMII_IDX].ofdev;
 		dev->rgmii_dev = deps[EMAC_DEP_RGMII_IDX].ofdev;
@@ -3087,12 +3060,8 @@ static int emac_probe(struct platform_device *ofdev)
 
 	/* Wait for dependent devices */
 	err = emac_wait_deps(dev);
-	if (err) {
-		printk(KERN_ERR
-		       "%pOF: Timeout waiting for dependent devices\n", np);
-		/*  display more info about what's missing ? */
+	if (err)
 		goto err_irq_unmap;
-	}
 	dev->mal = platform_get_drvdata(dev->mal_dev);
 	if (dev->mdio_dev != NULL)
 		dev->mdio_instance = platform_get_drvdata(dev->mdio_dev);
@@ -3192,10 +3161,6 @@ static int emac_probe(struct platform_device *ofdev)
 	wmb();
 	platform_set_drvdata(ofdev, dev);
 
-	/* There's a new kid in town ! Let's tell everybody */
-	wake_up_all(&emac_probe_wait);
-
-
 	printk(KERN_INFO "%s: EMAC-%d %pOF, MAC %pM\n",
 	       ndev->name, dev->cell_index, np, ndev->dev_addr);
 
@@ -3228,14 +3193,8 @@ static int emac_probe(struct platform_device *ofdev)
 	if (dev->wol_irq)
 		irq_dispose_mapping(dev->wol_irq);
  err_gone:
-	/* if we were on the bootlist, remove us as we won't show up and
-	 * wake up all waiters to notify them in case they were waiting
-	 * on us
-	 */
-	if (blist) {
+	if (blist)
 		*blist = NULL;
-		wake_up_all(&emac_probe_wait);
-	}
 	return err;
 }
 
-- 
cgit v1.3-3-g829e


From 39b9b78065cdf4a701879bbe471aa7a0794a8b0f Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Wed, 11 Sep 2024 19:49:03 -0700
Subject: net: ibm: emac: get rid of wol_irq

This is completely unused.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240912024903.6201-10-rosenp@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/emac/core.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 60c4943ca09d..dac570f3c110 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -3029,9 +3029,8 @@ static int emac_probe(struct platform_device *ofdev)
 	if (err)
 		goto err_gone;
 
-	/* Get interrupts. EMAC irq is mandatory, WOL irq is optional */
+	/* Get interrupts. EMAC irq is mandatory */
 	dev->emac_irq = irq_of_parse_and_map(np, 0);
-	dev->wol_irq = irq_of_parse_and_map(np, 1);
 	if (!dev->emac_irq) {
 		printk(KERN_ERR "%pOF: Can't map main interrupt\n", np);
 		err = -ENODEV;
@@ -3055,13 +3054,13 @@ static int emac_probe(struct platform_device *ofdev)
 	if (!dev->emacp) {
 		dev_err(&ofdev->dev, "can't map device registers");
 		err = -ENOMEM;
-		goto err_irq_unmap;
+		goto err_gone;
 	}
 
 	/* Wait for dependent devices */
 	err = emac_wait_deps(dev);
 	if (err)
-		goto err_irq_unmap;
+		goto err_gone;
 	dev->mal = platform_get_drvdata(dev->mal_dev);
 	if (dev->mdio_dev != NULL)
 		dev->mdio_instance = platform_get_drvdata(dev->mdio_dev);
@@ -3189,9 +3188,6 @@ static int emac_probe(struct platform_device *ofdev)
 	mal_unregister_commac(dev->mal, &dev->commac);
  err_rel_deps:
 	emac_put_deps(dev);
- err_irq_unmap:
-	if (dev->wol_irq)
-		irq_dispose_mapping(dev->wol_irq);
  err_gone:
 	if (blist)
 		*blist = NULL;
@@ -3218,9 +3214,6 @@ static void emac_remove(struct platform_device *ofdev)
 
 	mal_unregister_commac(dev->mal, &dev->commac);
 	emac_put_deps(dev);
-
-	if (dev->wol_irq)
-		irq_dispose_mapping(dev->wol_irq);
 }
 
 /* XXX Features in here should be replaced by properties... */
-- 
cgit v1.3-3-g829e


From 8f88c072c2ba9201c1db27dec35f5015489776ec Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 11 Sep 2024 13:45:59 +0530
Subject: net: ti: icss-iep: Move icss_iep structure

Move icss_iep structure definition and to icss_iep.h file so that the
structure members can be used / accessed by all icssg driver files.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20240911081603.2521729-2-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 72 -------------------------------
 drivers/net/ethernet/ti/icssg/icss_iep.h | 73 +++++++++++++++++++++++++++++++-
 2 files changed, 72 insertions(+), 73 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 75c294ce6fb6..5d6d1cf78e93 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -53,78 +53,6 @@
 #define IEP_CAP_CFG_CAPNR_1ST_EVENT_EN(n)	BIT(LATCH_INDEX(n))
 #define IEP_CAP_CFG_CAP_ASYNC_EN(n)		BIT(LATCH_INDEX(n) + 10)
 
-enum {
-	ICSS_IEP_GLOBAL_CFG_REG,
-	ICSS_IEP_GLOBAL_STATUS_REG,
-	ICSS_IEP_COMPEN_REG,
-	ICSS_IEP_SLOW_COMPEN_REG,
-	ICSS_IEP_COUNT_REG0,
-	ICSS_IEP_COUNT_REG1,
-	ICSS_IEP_CAPTURE_CFG_REG,
-	ICSS_IEP_CAPTURE_STAT_REG,
-
-	ICSS_IEP_CAP6_RISE_REG0,
-	ICSS_IEP_CAP6_RISE_REG1,
-
-	ICSS_IEP_CAP7_RISE_REG0,
-	ICSS_IEP_CAP7_RISE_REG1,
-
-	ICSS_IEP_CMP_CFG_REG,
-	ICSS_IEP_CMP_STAT_REG,
-	ICSS_IEP_CMP0_REG0,
-	ICSS_IEP_CMP0_REG1,
-	ICSS_IEP_CMP1_REG0,
-	ICSS_IEP_CMP1_REG1,
-
-	ICSS_IEP_CMP8_REG0,
-	ICSS_IEP_CMP8_REG1,
-	ICSS_IEP_SYNC_CTRL_REG,
-	ICSS_IEP_SYNC0_STAT_REG,
-	ICSS_IEP_SYNC1_STAT_REG,
-	ICSS_IEP_SYNC_PWIDTH_REG,
-	ICSS_IEP_SYNC0_PERIOD_REG,
-	ICSS_IEP_SYNC1_DELAY_REG,
-	ICSS_IEP_SYNC_START_REG,
-	ICSS_IEP_MAX_REGS,
-};
-
-/**
- * struct icss_iep_plat_data - Plat data to handle SoC variants
- * @config: Regmap configuration data
- * @reg_offs: register offsets to capture offset differences across SoCs
- * @flags: Flags to represent IEP properties
- */
-struct icss_iep_plat_data {
-	const struct regmap_config *config;
-	u32 reg_offs[ICSS_IEP_MAX_REGS];
-	u32 flags;
-};
-
-struct icss_iep {
-	struct device *dev;
-	void __iomem *base;
-	const struct icss_iep_plat_data *plat_data;
-	struct regmap *map;
-	struct device_node *client_np;
-	unsigned long refclk_freq;
-	int clk_tick_time;	/* one refclk tick time in ns */
-	struct ptp_clock_info ptp_info;
-	struct ptp_clock *ptp_clock;
-	struct mutex ptp_clk_mutex;	/* PHC access serializer */
-	u32 def_inc;
-	s16 slow_cmp_inc;
-	u32 slow_cmp_count;
-	const struct icss_iep_clockops *ops;
-	void *clockops_data;
-	u32 cycle_time_ns;
-	u32 perout_enabled;
-	bool pps_enabled;
-	int cap_cmp_irq;
-	u64 period;
-	u32 latch_enable;
-	struct work_struct work;
-};
-
 /**
  * icss_iep_get_count_hi() - Get the upper 32 bit IEP counter
  * @iep: Pointer to structure representing IEP.
diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.h b/drivers/net/ethernet/ti/icssg/icss_iep.h
index 803a4b714893..0bdca0155abd 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.h
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.h
@@ -12,7 +12,78 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/regmap.h>
 
-struct icss_iep;
+enum {
+	ICSS_IEP_GLOBAL_CFG_REG,
+	ICSS_IEP_GLOBAL_STATUS_REG,
+	ICSS_IEP_COMPEN_REG,
+	ICSS_IEP_SLOW_COMPEN_REG,
+	ICSS_IEP_COUNT_REG0,
+	ICSS_IEP_COUNT_REG1,
+	ICSS_IEP_CAPTURE_CFG_REG,
+	ICSS_IEP_CAPTURE_STAT_REG,
+
+	ICSS_IEP_CAP6_RISE_REG0,
+	ICSS_IEP_CAP6_RISE_REG1,
+
+	ICSS_IEP_CAP7_RISE_REG0,
+	ICSS_IEP_CAP7_RISE_REG1,
+
+	ICSS_IEP_CMP_CFG_REG,
+	ICSS_IEP_CMP_STAT_REG,
+	ICSS_IEP_CMP0_REG0,
+	ICSS_IEP_CMP0_REG1,
+	ICSS_IEP_CMP1_REG0,
+	ICSS_IEP_CMP1_REG1,
+
+	ICSS_IEP_CMP8_REG0,
+	ICSS_IEP_CMP8_REG1,
+	ICSS_IEP_SYNC_CTRL_REG,
+	ICSS_IEP_SYNC0_STAT_REG,
+	ICSS_IEP_SYNC1_STAT_REG,
+	ICSS_IEP_SYNC_PWIDTH_REG,
+	ICSS_IEP_SYNC0_PERIOD_REG,
+	ICSS_IEP_SYNC1_DELAY_REG,
+	ICSS_IEP_SYNC_START_REG,
+	ICSS_IEP_MAX_REGS,
+};
+
+/**
+ * struct icss_iep_plat_data - Plat data to handle SoC variants
+ * @config: Regmap configuration data
+ * @reg_offs: register offsets to capture offset differences across SoCs
+ * @flags: Flags to represent IEP properties
+ */
+struct icss_iep_plat_data {
+	const struct regmap_config *config;
+	u32 reg_offs[ICSS_IEP_MAX_REGS];
+	u32 flags;
+};
+
+struct icss_iep {
+	struct device *dev;
+	void __iomem *base;
+	const struct icss_iep_plat_data *plat_data;
+	struct regmap *map;
+	struct device_node *client_np;
+	unsigned long refclk_freq;
+	int clk_tick_time;	/* one refclk tick time in ns */
+	struct ptp_clock_info ptp_info;
+	struct ptp_clock *ptp_clock;
+	struct mutex ptp_clk_mutex;	/* PHC access serializer */
+	u32 def_inc;
+	s16 slow_cmp_inc;
+	u32 slow_cmp_count;
+	const struct icss_iep_clockops *ops;
+	void *clockops_data;
+	u32 cycle_time_ns;
+	u32 perout_enabled;
+	bool pps_enabled;
+	int cap_cmp_irq;
+	u64 period;
+	u32 latch_enable;
+	struct work_struct work;
+};
+
 extern const struct icss_iep_clockops prueth_iep_clockops;
 
 /* Firmware specific clock operations */
-- 
cgit v1.3-3-g829e


From 4ebe0599fc36ea3ff51e76e8554a2127e8126778 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 11 Sep 2024 13:46:00 +0530
Subject: net: ti: icssg-prueth: Stop hardcoding def_inc

The def_inc is stored in icss_iep structure. Currently default increment
(ns per clock tick) is hardcoded to 4 (Clock frequency being 250 MHz).
Change this to use the iep->def_inc variable as the iep structure is now
accessible to the driver files.

Reviewed-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20240911081603.2521729-3-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 6644203d6bb7..5343d8754edd 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -365,7 +365,8 @@ static void prueth_iep_settime(void *clockops_data, u64 ns)
 	sc_desc.cyclecounter0_set = cyclecount & GENMASK(31, 0);
 	sc_desc.cyclecounter1_set = (cyclecount & GENMASK(63, 32)) >> 32;
 	sc_desc.iepcount_set = ns % cycletime;
-	sc_desc.CMP0_current = cycletime - 4; //Count from 0 to (cycle time)-4
+	/* Count from 0 to (cycle time) - emac->iep->def_inc */
+	sc_desc.CMP0_current = cycletime - emac->iep->def_inc;
 
 	memcpy_toio(sc_descp, &sc_desc, sizeof(sc_desc));
 
-- 
cgit v1.3-3-g829e


From 95540ad6747c09225e21800d9ce325921645dda2 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 11 Sep 2024 13:46:01 +0530
Subject: net: ti: icssg-prueth: Add support for HSR frame forward offload

Add support for offloading HSR port-to-port frame forward to hardware.
When the slave interfaces are added to the HSR interface, the PRU cores
will be stopped and ICSSG HSR firmwares will be loaded to them.

Similarly, when HSR interface is deleted, the PRU cores will be
restarted and the last used firmwares will be reloaded. PRUeth
interfaces will be back to the last used mode.

This commit also renames some APIs that are common between switch and
hsr mode with '_fw_offload' suffix.

Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://patch.msgid.link/20240911081603.2521729-4-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_classifier.c |   1 +
 drivers/net/ethernet/ti/icssg/icssg_config.c     |  18 ++--
 drivers/net/ethernet/ti/icssg/icssg_prueth.c     | 106 ++++++++++++++++++++++-
 drivers/net/ethernet/ti/icssg/icssg_prueth.h     |   6 ++
 4 files changed, 119 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
index 9ec504d976d6..833ca86d0b71 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c
@@ -290,6 +290,7 @@ void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac)
 		     mac[2] << 16 | mac[3] << 24));
 	regmap_write(miig_rt, MAC_INTERFACE_1, (u32)(mac[4] | mac[5] << 8));
 }
+EXPORT_SYMBOL_GPL(icssg_class_set_host_mac_addr);
 
 void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac)
 {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index dae52a83a378..7b2e6c192ff3 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -107,7 +107,7 @@ static const struct map hwq_map[2][ICSSG_NUM_OTHER_QUEUES] = {
 	},
 };
 
-static void icssg_config_mii_init_switch(struct prueth_emac *emac)
+static void icssg_config_mii_init_fw_offload(struct prueth_emac *emac)
 {
 	struct prueth *prueth = emac->prueth;
 	int mii = prueth_emac_slice(emac);
@@ -278,7 +278,7 @@ static int emac_r30_is_done(struct prueth_emac *emac)
 	return 1;
 }
 
-static int prueth_switch_buffer_setup(struct prueth_emac *emac)
+static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac)
 {
 	struct icssg_buffer_pool_cfg __iomem *bpool_cfg;
 	struct icssg_rxq_ctx __iomem *rxq_ctx;
@@ -424,7 +424,7 @@ static void icssg_init_emac_mode(struct prueth *prueth)
 	icssg_class_set_host_mac_addr(prueth->miig_rt, mac);
 }
 
-static void icssg_init_switch_mode(struct prueth *prueth)
+static void icssg_init_fw_offload_mode(struct prueth *prueth)
 {
 	u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET;
 	int i;
@@ -455,8 +455,8 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	struct icssg_flow_cfg __iomem *flow_cfg;
 	int ret;
 
-	if (prueth->is_switch_mode)
-		icssg_init_switch_mode(prueth);
+	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
+		icssg_init_fw_offload_mode(prueth);
 	else
 		icssg_init_emac_mode(prueth);
 
@@ -472,8 +472,8 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	regmap_update_bits(prueth->miig_rt, ICSSG_CFG_OFFSET,
 			   ICSSG_CFG_DEFAULT, ICSSG_CFG_DEFAULT);
 	icssg_miig_set_interface_mode(prueth->miig_rt, slice, emac->phy_if);
-	if (prueth->is_switch_mode)
-		icssg_config_mii_init_switch(emac);
+	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
+		icssg_config_mii_init_fw_offload(emac);
 	else
 		icssg_config_mii_init(emac);
 	icssg_config_ipg(emac);
@@ -498,8 +498,8 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	writeb(0, config + SPL_PKT_DEFAULT_PRIORITY);
 	writeb(0, config + QUEUE_NUM_UNTAGGED);
 
-	if (prueth->is_switch_mode)
-		ret = prueth_switch_buffer_setup(emac);
+	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
+		ret = prueth_fw_offload_buffer_setup(emac);
 	else
 		ret = prueth_emac_buffer_setup(emac);
 	if (ret)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 5343d8754edd..b38a4a6072c4 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -13,6 +13,7 @@
 #include <linux/dma/ti-cppi5.h>
 #include <linux/etherdevice.h>
 #include <linux/genalloc.h>
+#include <linux/if_hsr.h>
 #include <linux/if_vlan.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
@@ -40,6 +41,8 @@
 #define DEFAULT_PORT_MASK	1
 #define DEFAULT_UNTAG_MASK	1
 
+#define NETIF_PRUETH_HSR_OFFLOAD_FEATURES	NETIF_F_HW_HSR_FWD
+
 /* CTRLMMR_ICSSG_RGMII_CTRL register bits */
 #define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
 
@@ -118,6 +121,19 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static struct icssg_firmwares icssg_hsr_firmwares[] = {
+	{
+		.pru = "ti-pruss/am65x-sr2-pru0-pruhsr-fw.elf",
+		.rtu = "ti-pruss/am65x-sr2-rtu0-pruhsr-fw.elf",
+		.txpru = "ti-pruss/am65x-sr2-txpru0-pruhsr-fw.elf",
+	},
+	{
+		.pru = "ti-pruss/am65x-sr2-pru1-pruhsr-fw.elf",
+		.rtu = "ti-pruss/am65x-sr2-rtu1-pruhsr-fw.elf",
+		.txpru = "ti-pruss/am65x-sr2-txpru1-pruhsr-fw.elf",
+	}
+};
+
 static struct icssg_firmwares icssg_switch_firmwares[] = {
 	{
 		.pru = "ti-pruss/am65x-sr2-pru0-prusw-fw.elf",
@@ -152,6 +168,8 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
 
 	if (prueth->is_switch_mode)
 		firmwares = icssg_switch_firmwares;
+	else if (prueth->is_hsr_offload_mode)
+		firmwares = icssg_hsr_firmwares;
 	else
 		firmwares = icssg_emac_firmwares;
 
@@ -865,6 +883,7 @@ static int prueth_netdev_init(struct prueth *prueth,
 	ndev->ethtool_ops = &icssg_ethtool_ops;
 	ndev->hw_features = NETIF_F_SG;
 	ndev->features = ndev->hw_features;
+	ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES;
 
 	netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll);
 	hrtimer_init(&emac->rx_hrtimer, CLOCK_MONOTONIC,
@@ -953,7 +972,7 @@ static void prueth_emac_restart(struct prueth *prueth)
 	netif_device_attach(emac1->ndev);
 }
 
-static void icssg_enable_switch_mode(struct prueth *prueth)
+static void icssg_change_mode(struct prueth *prueth)
 {
 	struct prueth_emac *emac;
 	int mac;
@@ -973,8 +992,13 @@ static void icssg_enable_switch_mode(struct prueth *prueth)
 					  BIT(emac->port_id) | DEFAULT_PORT_MASK,
 					  BIT(emac->port_id) | DEFAULT_UNTAG_MASK,
 					  true);
+			if (prueth->is_hsr_offload_mode)
+				icssg_vtbl_modify(emac, DEFAULT_VID,
+						  DEFAULT_PORT_MASK,
+						  DEFAULT_UNTAG_MASK, true);
 			icssg_set_pvid(prueth, emac->port_vlan, emac->port_id);
-			icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE);
+			if (prueth->is_switch_mode)
+				icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE);
 		}
 	}
 }
@@ -1012,7 +1036,7 @@ static int prueth_netdevice_port_link(struct net_device *ndev,
 			prueth->is_switch_mode = true;
 			prueth->default_vlan = 1;
 			emac->port_vlan = prueth->default_vlan;
-			icssg_enable_switch_mode(prueth);
+			icssg_change_mode(prueth);
 		}
 	}
 
@@ -1040,6 +1064,61 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev)
 		prueth->hw_bridge_dev = NULL;
 }
 
+static int prueth_hsr_port_link(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	struct prueth_emac *emac0;
+	struct prueth_emac *emac1;
+
+	emac0 = prueth->emac[PRUETH_MAC0];
+	emac1 = prueth->emac[PRUETH_MAC1];
+
+	if (prueth->is_switch_mode)
+		return -EOPNOTSUPP;
+
+	prueth->hsr_members |= BIT(emac->port_id);
+	if (!prueth->is_hsr_offload_mode) {
+		if (prueth->hsr_members & BIT(PRUETH_PORT_MII0) &&
+		    prueth->hsr_members & BIT(PRUETH_PORT_MII1)) {
+			if (!(emac0->ndev->features &
+			      NETIF_PRUETH_HSR_OFFLOAD_FEATURES) &&
+			    !(emac1->ndev->features &
+			      NETIF_PRUETH_HSR_OFFLOAD_FEATURES))
+				return -EOPNOTSUPP;
+			prueth->is_hsr_offload_mode = true;
+			prueth->default_vlan = 1;
+			emac0->port_vlan = prueth->default_vlan;
+			emac1->port_vlan = prueth->default_vlan;
+			icssg_change_mode(prueth);
+			netdev_dbg(ndev, "Enabling HSR offload mode\n");
+		}
+	}
+
+	return 0;
+}
+
+static void prueth_hsr_port_unlink(struct net_device *ndev)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+	struct prueth_emac *emac0;
+	struct prueth_emac *emac1;
+
+	emac0 = prueth->emac[PRUETH_MAC0];
+	emac1 = prueth->emac[PRUETH_MAC1];
+
+	prueth->hsr_members &= ~BIT(emac->port_id);
+	if (prueth->is_hsr_offload_mode) {
+		prueth->is_hsr_offload_mode = false;
+		emac0->port_vlan = 0;
+		emac1->port_vlan = 0;
+		prueth->hsr_dev = NULL;
+		prueth_emac_restart(prueth);
+		netdev_dbg(ndev, "Disabling HSR Offload mode\n");
+	}
+}
+
 /* netdev notifier */
 static int prueth_netdevice_event(struct notifier_block *unused,
 				  unsigned long event, void *ptr)
@@ -1047,6 +1126,8 @@ static int prueth_netdevice_event(struct notifier_block *unused,
 	struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr);
 	struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
 	int ret = NOTIFY_DONE;
 
 	if (ndev->netdev_ops != &emac_netdev_ops)
@@ -1056,6 +1137,25 @@ static int prueth_netdevice_event(struct notifier_block *unused,
 	case NETDEV_CHANGEUPPER:
 		info = ptr;
 
+		if ((ndev->features & NETIF_PRUETH_HSR_OFFLOAD_FEATURES) &&
+		    is_hsr_master(info->upper_dev)) {
+			if (info->linking) {
+				if (!prueth->hsr_dev) {
+					prueth->hsr_dev = info->upper_dev;
+					icssg_class_set_host_mac_addr(prueth->miig_rt,
+								      prueth->hsr_dev->dev_addr);
+				} else {
+					if (prueth->hsr_dev != info->upper_dev) {
+						netdev_dbg(ndev, "Both interfaces must be linked to same upper device\n");
+						return -EOPNOTSUPP;
+					}
+				}
+				prueth_hsr_port_link(ndev);
+			} else {
+				prueth_hsr_port_unlink(ndev);
+			}
+		}
+
 		if (netif_is_bridge_master(info->upper_dev)) {
 			if (info->linking)
 				ret = prueth_netdevice_port_link(ndev, info->upper_dev, extack);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 786bd1ba34ab..a4b025fae797 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -243,11 +243,14 @@ struct icssg_firmwares {
  * @iep1: pointer to IEP1 device
  * @vlan_tbl: VLAN-FID table pointer
  * @hw_bridge_dev: pointer to HW bridge net device
+ * @hsr_dev: pointer to the HSR net device
  * @br_members: bitmask of bridge member ports
+ * @hsr_members: bitmask of hsr member ports
  * @prueth_netdevice_nb: netdevice notifier block
  * @prueth_switchdev_nb: switchdev notifier block
  * @prueth_switchdev_bl_nb: switchdev blocking notifier block
  * @is_switch_mode: flag to indicate if device is in Switch mode
+ * @is_hsr_offload_mode: flag to indicate if device is in hsr offload mode
  * @is_switchmode_supported: indicates platform support for switch mode
  * @switch_id: ID for mapping switch ports to bridge
  * @default_vlan: Default VLAN for host
@@ -279,11 +282,14 @@ struct prueth {
 	struct prueth_vlan_tbl *vlan_tbl;
 
 	struct net_device *hw_bridge_dev;
+	struct net_device *hsr_dev;
 	u8 br_members;
+	u8 hsr_members;
 	struct notifier_block prueth_netdevice_nb;
 	struct notifier_block prueth_switchdev_nb;
 	struct notifier_block prueth_switchdev_bl_nb;
 	bool is_switch_mode;
+	bool is_hsr_offload_mode;
 	bool is_switchmode_supported;
 	unsigned char switch_id[MAX_PHYS_ITEM_ID_LEN];
 	int default_vlan;
-- 
cgit v1.3-3-g829e


From 56375086d093478d67366bdbafee4db657b9d1b1 Mon Sep 17 00:00:00 2001
From: Ravi Gunasekaran <r-gunasekaran@ti.com>
Date: Wed, 11 Sep 2024 13:46:02 +0530
Subject: net: ti: icssg-prueth: Enable HSR Tx duplication, Tx Tag and Rx Tag
 offload

The HSR stack allows to offload its Tx packet duplication functionality to
the hardware. Enable this offloading feature for ICSSG driver. Add support
to offload HSR Tx Tag Insertion and Rx Tag Removal and duplicate discard.

hsr tag insertion offload and hsr dup offload are tightly coupled in
firmware implementation. Both these features need to be enabled / disabled
together.

Duplicate discard is done as part of RX tag removal and it is
done by the firmware. When driver sends the r30 command
ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE, firmware does RX tag removal as well as
duplicate discard.

Signed-off-by: Ravi Gunasekaran <r-gunasekaran@ti.com>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://patch.msgid.link/20240911081603.2521729-5-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 18 +++++++++++---
 drivers/net/ethernet/ti/icssg/icssg_config.c |  4 +++-
 drivers/net/ethernet/ti/icssg/icssg_config.h |  2 ++
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 36 +++++++++++++++++++++++++++-
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |  3 +++
 5 files changed, 58 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index b9d8a93d1680..fdebeb2f84e0 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -660,14 +660,15 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 {
 	struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc;
 	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
 	struct netdev_queue *netif_txq;
 	struct prueth_tx_chn *tx_chn;
 	dma_addr_t desc_dma, buf_dma;
+	u32 pkt_len, dst_tag_id;
 	int i, ret = 0, q_idx;
 	bool in_tx_ts = 0;
 	int tx_ts_cookie;
 	void **swdata;
-	u32 pkt_len;
 	u32 *epib;
 
 	pkt_len = skb_headlen(skb);
@@ -712,9 +713,20 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 
 	/* set dst tag to indicate internal qid at the firmware which is at
 	 * bit8..bit15. bit0..bit7 indicates port num for directed
-	 * packets in case of switch mode operation
+	 * packets in case of switch mode operation and port num 0
+	 * for undirected packets in case of HSR offload mode
 	 */
-	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8)));
+	dst_tag_id = emac->port_id | (q_idx << 8);
+
+	if (prueth->is_hsr_offload_mode &&
+	    (ndev->features & NETIF_F_HW_HSR_DUP))
+		dst_tag_id = PRUETH_UNDIRECTED_PKT_DST_TAG;
+
+	if (prueth->is_hsr_offload_mode &&
+	    (ndev->features & NETIF_F_HW_HSR_TAG_INS))
+		epib[1] |= PRUETH_UNDIRECTED_PKT_TAG_INS;
+
+	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, dst_tag_id);
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 7b2e6c192ff3..72ace151d8e9 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -531,7 +531,9 @@ static const struct icssg_r30_cmd emac_r32_bitmask[] = {
 	{{EMAC_NONE,  0xffff4000, EMAC_NONE, EMAC_NONE}},	/* Preemption on Tx ENABLE*/
 	{{EMAC_NONE,  0xbfff0000, EMAC_NONE, EMAC_NONE}},	/* Preemption on Tx DISABLE*/
 	{{0xffff0010,  EMAC_NONE, 0xffff0010, EMAC_NONE}},	/* VLAN AWARE*/
-	{{0xffef0000,  EMAC_NONE, 0xffef0000, EMAC_NONE}}	/* VLAN UNWARE*/
+	{{0xffef0000,  EMAC_NONE, 0xffef0000, EMAC_NONE}},	/* VLAN UNWARE*/
+	{{0xffff2000, EMAC_NONE, EMAC_NONE, EMAC_NONE}},	/* HSR_RX_OFFLOAD_ENABLE */
+	{{0xdfff0000, EMAC_NONE, EMAC_NONE, EMAC_NONE}}		/* HSR_RX_OFFLOAD_DISABLE */
 };
 
 int icssg_set_port_state(struct prueth_emac *emac,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index 1ac60283923b..92c2deaa3068 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -80,6 +80,8 @@ enum icssg_port_state_cmd {
 	ICSSG_EMAC_PORT_PREMPT_TX_DISABLE,
 	ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE,
 	ICSSG_EMAC_PORT_VLAN_AWARE_DISABLE,
+	ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE,
+	ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE,
 	ICSSG_EMAC_PORT_MAX_COMMANDS
 };
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index b38a4a6072c4..d128764982ae 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -41,7 +41,10 @@
 #define DEFAULT_PORT_MASK	1
 #define DEFAULT_UNTAG_MASK	1
 
-#define NETIF_PRUETH_HSR_OFFLOAD_FEATURES	NETIF_F_HW_HSR_FWD
+#define NETIF_PRUETH_HSR_OFFLOAD_FEATURES	(NETIF_F_HW_HSR_FWD | \
+						 NETIF_F_HW_HSR_DUP | \
+						 NETIF_F_HW_HSR_TAG_INS | \
+						 NETIF_F_HW_HSR_TAG_RM)
 
 /* CTRLMMR_ICSSG_RGMII_CTRL register bits */
 #define ICSSG_CTRL_RGMII_ID_MODE                BIT(24)
@@ -744,6 +747,29 @@ static void emac_ndo_set_rx_mode(struct net_device *ndev)
 	queue_work(emac->cmd_wq, &emac->rx_mode_work);
 }
 
+static netdev_features_t emac_ndo_fix_features(struct net_device *ndev,
+					       netdev_features_t features)
+{
+	/* hsr tag insertion offload and hsr dup offload are tightly coupled in
+	 * firmware implementation. Both these features need to be enabled /
+	 * disabled together.
+	 */
+	if (!(ndev->features & (NETIF_F_HW_HSR_DUP | NETIF_F_HW_HSR_TAG_INS)))
+		if ((features & NETIF_F_HW_HSR_DUP) ||
+		    (features & NETIF_F_HW_HSR_TAG_INS))
+			features |= NETIF_F_HW_HSR_DUP |
+				    NETIF_F_HW_HSR_TAG_INS;
+
+	if ((ndev->features & NETIF_F_HW_HSR_DUP) ||
+	    (ndev->features & NETIF_F_HW_HSR_TAG_INS))
+		if (!(features & NETIF_F_HW_HSR_DUP) ||
+		    !(features & NETIF_F_HW_HSR_TAG_INS))
+			features &= ~(NETIF_F_HW_HSR_DUP |
+				      NETIF_F_HW_HSR_TAG_INS);
+
+	return features;
+}
+
 static const struct net_device_ops emac_netdev_ops = {
 	.ndo_open = emac_ndo_open,
 	.ndo_stop = emac_ndo_stop,
@@ -755,6 +781,7 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_eth_ioctl = icssg_ndo_ioctl,
 	.ndo_get_stats64 = icssg_ndo_get_stats64,
 	.ndo_get_phys_port_name = icssg_ndo_get_phys_port_name,
+	.ndo_fix_features = emac_ndo_fix_features,
 };
 
 static int prueth_netdev_init(struct prueth *prueth,
@@ -981,6 +1008,13 @@ static void icssg_change_mode(struct prueth *prueth)
 
 	for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) {
 		emac = prueth->emac[mac];
+		if (prueth->is_hsr_offload_mode) {
+			if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM)
+				icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE);
+			else
+				icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE);
+		}
+
 		if (netif_running(emac->ndev)) {
 			icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan,
 					  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index a4b025fae797..bba6da2e6bd8 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -59,6 +59,9 @@
 
 #define IEP_DEFAULT_CYCLE_TIME_NS	1000000	/* 1 ms */
 
+#define PRUETH_UNDIRECTED_PKT_DST_TAG	0
+#define PRUETH_UNDIRECTED_PKT_TAG_INS	BIT(30)
+
 /* Firmware status codes */
 #define ICSS_HS_FW_READY 0x55555555
 #define ICSS_HS_FW_DEAD 0xDEAD0000	/* lower 16 bits contain error code */
-- 
cgit v1.3-3-g829e


From 1d6ae9652780e97302b7e02610d9b6b74020b9ff Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Wed, 11 Sep 2024 13:46:03 +0530
Subject: net: ti: icssg-prueth: Add multicast filtering support in HSR mode

Add support for multicast filtering in HSR mode

Reviewed-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Link: https://patch.msgid.link/20240911081603.2521729-6-danishanwar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 42 ++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index d128764982ae..5fd9902ab181 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -492,6 +492,36 @@ static int icssg_prueth_del_mcast(struct net_device *ndev, const u8 *addr)
 	return 0;
 }
 
+static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+
+	icssg_fdb_add_del(emac, addr, prueth->default_vlan,
+			  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
+			  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
+			  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
+			  ICSSG_FDB_ENTRY_BLOCK, true);
+
+	icssg_vtbl_modify(emac, emac->port_vlan, BIT(emac->port_id),
+			  BIT(emac->port_id), true);
+	return 0;
+}
+
+static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+	struct prueth *prueth = emac->prueth;
+
+	icssg_fdb_add_del(emac, addr, prueth->default_vlan,
+			  ICSSG_FDB_ENTRY_P0_MEMBERSHIP |
+			  ICSSG_FDB_ENTRY_P1_MEMBERSHIP |
+			  ICSSG_FDB_ENTRY_P2_MEMBERSHIP |
+			  ICSSG_FDB_ENTRY_BLOCK, false);
+
+	return 0;
+}
+
 /**
  * emac_ndo_open - EMAC device open
  * @ndev: network adapter device
@@ -652,7 +682,10 @@ static int emac_ndo_stop(struct net_device *ndev)
 
 	icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac));
 
-	__dev_mc_unsync(ndev, icssg_prueth_del_mcast);
+	if (emac->prueth->is_hsr_offload_mode)
+		__dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast);
+	else
+		__dev_mc_unsync(ndev, icssg_prueth_del_mcast);
 
 	atomic_set(&emac->tdown_cnt, emac->tx_ch_num);
 	/* ensure new tdown_cnt value is visible */
@@ -730,7 +763,12 @@ static void emac_ndo_set_rx_mode_work(struct work_struct *work)
 		return;
 	}
 
-	__dev_mc_sync(ndev, icssg_prueth_add_mcast, icssg_prueth_del_mcast);
+	if (emac->prueth->is_hsr_offload_mode)
+		__dev_mc_sync(ndev, icssg_prueth_hsr_add_mcast,
+			      icssg_prueth_hsr_del_mcast);
+	else
+		__dev_mc_sync(ndev, icssg_prueth_add_mcast,
+			      icssg_prueth_del_mcast);
 }
 
 /**
-- 
cgit v1.3-3-g829e


From c209847b8974d2d5e784e3105d4683835673b18d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 14 Sep 2024 10:18:20 +0200
Subject: net: ethernet: fs_enet: Make the per clock optional

Some platforms that use fs_enet don't have the PER register clock. This
optional dependency on the clock was incorrectly made mandatory when
switching to devm_ accessors.

Reported-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Closes: https://lore.kernel.org/netdev/4e4defa9-ef2f-4ff1-95ca-6627c24db20c@wanadoo.fr/
Fixes: c614acf6e8e1 ("net: ethernet: fs_enet: simplify clock handling with devm accessors")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://patch.msgid.link/20240914081821.209130-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index d300b01859a1..3425c4a6abcb 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -895,7 +895,7 @@ static int fs_enet_probe(struct platform_device *ofdev)
 	 * but require enable to succeed when a clock was specified/found,
 	 * keep a reference to the clock upon successful acquisition
 	 */
-	clk = devm_clk_get_enabled(&ofdev->dev, "per");
+	clk = devm_clk_get_optional_enabled(&ofdev->dev, "per");
 	if (IS_ERR(clk))
 		goto out_free_fpi;
 
-- 
cgit v1.3-3-g829e


From 75834577c0870c9087274f015887b6f4106b3a24 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 14 Sep 2024 12:57:28 +0300
Subject: ice: Fix a couple NULL vs IS_ERR() bugs

The ice_repr_create() function returns error pointers.  It never returns
NULL.  Fix the callers to check for IS_ERR().

Fixes: 977514fb0fa8 ("ice: create port representor for SF")
Fixes: 415db8399d06 ("ice: make representor code generic")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/7f7aeb91-8771-47b8-9275-9d9f64f947dd@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_repr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c
index 00d4a9125dfa..970a99a52bf1 100644
--- a/drivers/net/ethernet/intel/ice/ice_repr.c
+++ b/drivers/net/ethernet/intel/ice/ice_repr.c
@@ -452,8 +452,8 @@ struct ice_repr *ice_repr_create_vf(struct ice_vf *vf)
 		return ERR_PTR(-EINVAL);
 
 	repr = ice_repr_create(vsi);
-	if (!repr)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(repr))
+		return repr;
 
 	repr->type = ICE_REPR_TYPE_VF;
 	repr->vf = vf;
@@ -501,8 +501,8 @@ struct ice_repr *ice_repr_create_sf(struct ice_dynamic_port *sf)
 {
 	struct ice_repr *repr = ice_repr_create(sf->vsi);
 
-	if (!repr)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(repr))
+		return repr;
 
 	repr->type = ICE_REPR_TYPE_SF;
 	repr->sf = sf;
-- 
cgit v1.3-3-g829e


From 472d455e7c6f32e6ae4738de8e6ba212db372661 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 14 Sep 2024 12:57:56 +0300
Subject: ice: Fix a NULL vs IS_ERR() check in probe()

The ice_allocate_sf() function returns error pointers on error.  It
doesn't return NULL.  Update the check to match.

Fixes: 177ef7f1e2a0 ("ice: base subfunction aux driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/6951d217-ac06-4482-a35d-15d757fd90a3@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_sf_eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_sf_eth.c b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
index d00389c405c4..75d7147e1c01 100644
--- a/drivers/net/ethernet/intel/ice/ice_sf_eth.c
+++ b/drivers/net/ethernet/intel/ice/ice_sf_eth.c
@@ -108,9 +108,9 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev,
 	vsi->flags = ICE_VSI_FLAG_INIT;
 
 	priv = ice_allocate_sf(&adev->dev, pf);
-	if (!priv) {
+	if (IS_ERR(priv)) {
 		dev_err(dev, "Subfunction devlink alloc failed");
-		return -ENOMEM;
+		return PTR_ERR(priv);
 	}
 
 	priv->dev = sf_dev;
-- 
cgit v1.3-3-g829e


From 7052622fccb1efb850c6b55de477f65d03525a30 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 14 Sep 2024 12:56:51 +0300
Subject: netfilter: nft_socket: Fix a NULL vs IS_ERR() bug in
 nft_socket_cgroup_subtree_level()

The cgroup_get_from_path() function never returns NULL, it returns error
pointers.  Update the error handling to match.

Fixes: 7f3287db6543 ("netfilter: nft_socket: make cgroupsv2 matching work with namespaces")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Link: https://patch.msgid.link/bbc0c4e0-05cc-4f44-8797-2f4b3920a820@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netfilter/nft_socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 12cdff640492..0a8883a93e83 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -61,8 +61,8 @@ static noinline int nft_socket_cgroup_subtree_level(void)
 	struct cgroup *cgrp = cgroup_get_from_path("/");
 	int level;
 
-	if (!cgrp)
-		return -ENOENT;
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
 
 	level = cgrp->level;
 
-- 
cgit v1.3-3-g829e


From be461814aa4cb32aae061404b9a6a83ef3895018 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 14 Sep 2024 12:58:26 +0300
Subject: net/mlx5: HWS, check the correct variable in hws_send_ring_alloc_sq()

There is a copy and paste bug so this code checks "sq->dep_wqe" where
"sq->wr_priv" was intended.  It could result in a NULL pointer
dereference.

Fixes: 2ca62599aa0b ("net/mlx5: HWS, added send engine and context handling")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/da822315-02b7-4f5b-9c86-0d5176c5069d@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c
index fb97a15c041a..a1adbb48735c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws_send.c
@@ -584,7 +584,7 @@ static int hws_send_ring_alloc_sq(struct mlx5_core_dev *mdev,
 	}
 
 	sq->wr_priv = kzalloc(sizeof(*sq->wr_priv) * buf_sz, GFP_KERNEL);
-	if (!sq->dep_wqe) {
+	if (!sq->wr_priv) {
 		err = -ENOMEM;
 		goto free_dep_wqe;
 	}
-- 
cgit v1.3-3-g829e